A method, device and medium for predicting urban vitality based on urban three-dimensional spatial form

Abstract

The application discloses a kind of based on urban three-dimensional space form's activity prediction method, equipment and medium, comprising: obtaining the three-dimensional space unit form data and function industry type data of target plot;The three-dimensional grid division is carried out to target plot;According to three-dimensional space unit form data and function industry type data, determine the form index of each three-dimensional space unit;The crowd activity data of each three-dimensional space unit is obtained, and the behavior sharing value is determined according to crowd activity data;With form index as input feature, behavior sharing value as training label, construct training data set;The training data set is trained by machine learning algorithm, and the index weight corresponding to form index is determined;According to index weight and the form index of the region to be measured, generate the form sharing index of the region to be measured.Solve the problem that existing measure method lacks three-dimensional form pertinence, index system is single, can accurately reflect the real sharing potential of three-dimensional space unit.

Description

Technical Field

[0001] This invention relates to the field of urban shared measurement technology, specifically to a method, device, and medium for predicting the vitality of urban three-dimensional spatial morphology. Background Technology

[0002] In the context of modern urban compact and intensive development, three-dimensional spatial units have become the main development model for core urban areas. Their level of shared use directly determines the multi-period vitality and land use efficiency of urban public spaces, and is a key support for achieving sustainable urban development. However, current measurement technologies for the shared use of three-dimensional spatial units in high-intensity urban areas still have significant shortcomings, mainly reflected in the following aspects: Existing measurement methods lack a systematic analysis of the relationship between the morphology of three-dimensional spatial units and their use by people. Traditional technologies often focus on the compactness of planar spaces or the quantification of a single vitality index. For example, patent document CN109977600A provides a standardized method and system for measuring the compactness of urban three-dimensional spatial units. However, its core lies in calculating compactness through the distribution of building volume, without considering the actual usage behavior of people. It fails to fully consider the impact of three-dimensional morphological characteristics such as the number of floors, the functional layout of each floor, and vertical connections on people's activities. This leads to a disconnect between the characteristics of urban three-dimensional morphology and actual usage needs, and fails to accurately reflect the true sharing potential of three-dimensional spatial units. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a method, device, and medium for predicting the vitality of urban three-dimensional spatial morphology. It aims to solve the problems of existing methods lacking three-dimensional morphology specificity and having a single index system, so as to accurately reflect the true sharing potential of three-dimensional spatial units.

[0004] To address the above problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a vitality prediction method based on urban three-dimensional spatial morphology, comprising: In some implementations, the method includes the following steps: Acquire the three-dimensional spatial unit morphology data and functional business type data of the target area; wherein, the three-dimensional spatial unit morphology data includes at least one of the building outlines of the ground floor, above-ground floor and underground floor of the target area, the outline of the outdoor public space and the outline of the above-ground connecting corridor, and the functional business type data is used to identify the use category or activity type of each three-dimensional spatial unit. The target area is divided into a 3D grid to generate multiple 3D spatial units; Based on the morphological data of three-dimensional spatial units and the functional business type data, the morphological index of each three-dimensional spatial unit is determined. The morphological index is used to represent multiple spatial morphological characteristics of three-dimensional spatial units that affect behavioral sharing. Acquire crowd activity data for each three-dimensional spatial unit, determine the behavior sharing value based on the crowd activity data, and use the behavior sharing value to represent the mixed type and intensity of crowd activities within the three-dimensional spatial unit; A training dataset is constructed by using morphological indices as input features and behavioral sharing values ​​as training labels. The training dataset is trained using machine learning algorithms to determine the index weights corresponding to the morphological index. Based on the index weights and the morphological index of the region under test, a morphological sharing index of the region under test is generated.

[0005] In some implementations, the target area is divided into three-dimensional meshes to generate multiple three-dimensional spatial units, including: Based on the preset dimensions, the multiple spatial layers of the target area are divided into planar grids to generate multiple grid units. The spatial layers include a ground layer, at least one above-ground layer, and at least one underground layer. Grid units with consistent planar coordinate ranges on different spatial layers constitute a three-dimensional spatial unit.

[0006] In some implementations, the morphological index includes the public space area index, the space accessibility index, and the functional facilities index; Public space area index It can be calculated using the formula: ; In the formula, For the first The public space area index of each three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For the first The area of ​​the public space on each floor; Space Accessibility Index It can be calculated using the formula: ; In the formula, For the first The spatial accessibility index of each three-dimensional spatial unit For the first The accessibility index of a three-dimensional spatial unit. For the first Vertical transportation weight of each three-dimensional spatial unit For the first Weight of horizontal ground elevation difference of each three-dimensional spatial unit; in, In the formula The total number of floors covered by the three-dimensional space unit. For the first The reachability index of a layer grid cell; in, In the formula, For the first The total number of nodes in a layer of mesh cells. For the first Layer mesh cell removal The remaining nodes of 1 node for The shortest path distance to other nodes. For the first The center point of the layer grid cell; ; In the formula, For vertical transportation weights, For the first The total height difference of each three-dimensional spatial unit For the first The number of layers in a three-dimensional spatial unit; ; In the formula, For the first The horizontal ground elevation difference corresponding to each three-dimensional spatial unit For the first The total height of the podium of each three-dimensional space unit; The facilities index is calculated using the following formula: ; In the formula, For the first Functional facility index of each three-dimensional space unit For the first Functional diversity index of a three-dimensional spatial unit For the first The connectivity index of commercial facilities in a three-dimensional spatial unit For the first Functional visibility index of a three-dimensional spatial unit These are the coefficients of the corresponding indices; in, = ; In the formula, For the first The sum of the number of various functional business types contained in each spatial layer within a three-dimensional spatial unit. No. The total number of layers in a three-dimensional spatial unit; = ; In the formula, For the first The connectivity index of commercial facilities in a three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For this three-dimensional spatial unit in the first The reachability distance from the center point of the layer grid to the nearest commercial service facility; ; In the formula, For the first Functional visibility index of a three-dimensional spatial unit For the first The functional visibility index of the layer The total number of floors covered by the three-dimensional space unit. In the formula, The first point is the view that a pedestrian standing at the entrance of a street or plaza can directly observe from a horizontal, unobstructed viewpoint. The length of the boundaries of the commercial windows, shop entrances / exits, or outdoor commercial areas on each floor. The first of each three-dimensional spatial unit The total length of the public space boundary of the floor.

[0007] In some implementations, crowd activity data for each three-dimensional spatial unit is acquired, and behavioral sharing values ​​are determined based on the crowd activity data, including: Acquire crowd activity data in the public spaces of the ground floor, above-ground floors, and underground floors of the target area. The crowd activity data includes activity type, activity quantity, and activity coordinates. Cluster analysis was performed on the crowd activity data to obtain the cluster type, number of clusters, and cluster coordinates for each layer and time period; The public spaces of the ground floor, above-ground floor, and underground floor are divided into multiple grid units. Based on the cluster type, number of clusters, and cluster coordinates, the behavior occupancy rate of each grid unit in each time period is calculated. The behavior sharing value is determined based on the behavior occupancy rate and the activity type mixing degree.

[0008] In some implementations, the behavior sharing value is determined based on behavior occupancy and activity type mixing, including: Based on behavior share Mixed activity types Calculate the shared behavior value of each three-dimensional spatial unit at each time period using the following formula. : ; In the formula, For the first Each three-dimensional spatial unit in time period Unit behavior occupancy rate For the first Each three-dimensional spatial unit in time period Activity type mix For the first Each three-dimensional spatial unit in time period Behavioral sharing values

[0009] right Summing is performed to obtain the behavioral shared values ​​for each 3D spatial unit: ; In the formula, For the first A preset time period The total number of preset time periods. For the first A three-dimensional spatial unit, For the first Each three-dimensional spatial unit in time period Shared values ​​for behavior.

[0010] In some implementations, a machine learning algorithm is used to train the training dataset to determine the index weights corresponding to the morphological index, including: Multiple morphological indices are divided into a core influence index group and a secondary influence index group; Determine the first correlation sum of the core impact index group and the behavioral sharing values; Determine the second association sum of the auxiliary influence index group and the behavioral sharing values; The weighting ratio between the core influence index group and the auxiliary influence index group is determined based on the ratio of the first correlation sum and the second correlation sum. The index weights corresponding to the morphological index are determined based on the weight allocation ratio.

[0011] In some implementations, if the area to be measured is an undeveloped area, the method further includes: Obtain the morphological sharing index of each three-dimensional spatial unit within the test area, and determine the spatial sharing potential level based on the morphological sharing index; The spatial sharing potential level is used as a predictive result for the vitality of the area to be tested.

[0012] In some implementations, the spatial sharing potential level is determined based on a morphological sharing index, including: Establish a case library containing multiple completed and stable operating reference cases. Each reference case is associated with and stored with its morphological index set, surrounding environment morphological index set, scale and type attributes, and operation stage tags. Based on the case library, determine the similarity between the area to be tested and each reference case; Based on similarity, a predetermined number of reference cases are selected to form a reference case group; Based on historical data of morphological index and behavioral sharing values ​​of each reference case in the reference case group, a model for predicting the vitality of the area to be tested is constructed. Obtain the set of morphological indices for the region to be tested, input them into the model used to predict the vitality of the region to obtain the initial vitality prediction value; The level of space sharing potential is determined based on the initial vitality forecast.

[0013] In a second aspect, embodiments of the present invention provide an electronic device, the electronic device comprising: At least one processor; and, A memory that is communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform a vitality prediction method based on urban three-dimensional spatial morphology as described in the first aspect.

[0014] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing an executable program, which is executed by a processor to implement the vitality prediction method based on urban three-dimensional spatial morphology as described in the first aspect.

[0015] This invention provides a method, device, and medium for predicting the vitality of urban three-dimensional spatial morphology. It acquires morphological data and functional business type data of three-dimensional spatial units at the ground, above-ground, and underground levels of a target area, divides the target area into multiple three-dimensional spatial units, determines the morphological index of each unit, and combines this with population activity data to determine behavioral sharing values. A training dataset is constructed, and machine learning algorithms are used to determine the corresponding morphological index weights, ultimately generating a morphological sharing index for the area to be measured. This invention effectively solves the problems of existing measurement methods lacking specificity for three-dimensional morphology and having a single index system, and can accurately reflect the true sharing potential of three-dimensional spatial units. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the vitality prediction method based on urban three-dimensional spatial morphology provided in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0018] Figure 3 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] The vitality prediction method based on urban three-dimensional spatial morphology provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Optionally, this embodiment takes the core area of ​​a city's central business district (CBD) as the research object. This area includes a ground-level commercial pedestrian street, a two-story above-ground connecting corridor system, a two-story underground commercial street, and a sunken plaza. It is a high-intensity development area with typical three-dimensional characteristics.

[0023] Please see Figure 1 , Figure 1 This is a flowchart illustrating the vitality prediction method based on urban three-dimensional spatial morphology provided in an embodiment of the present invention. Figure 1 As shown, the vitality prediction method based on urban three-dimensional spatial morphology includes steps S100 to S900.

[0024] Step S100: Obtain the three-dimensional spatial unit morphology data and functional business type data of the target area.

[0025] Optionally, the three-dimensional spatial unit morphology data includes at least one of the following: the building outline of the ground floor, above-ground and underground floors of the target area, the outline of the outdoor public space, and the outline of the above-ground connecting corridor.

[0026] Optionally, functional business type data is used to identify the use category or activity type of each three-dimensional space unit.

[0027] Specifically, the methods for acquiring three-dimensional spatial unit morphology data include: obtaining real-scene videos of the target area through drones or other photography methods, and extracting the building outlines of the ground floor, above-ground and underground floors, the outlines of outdoor public spaces, and the outlines of above-ground connecting corridors in the target area. Alternatively, existing topographic maps or geographic information data can be obtained from urban planning and management departments, and the building outlines of the ground floor, above-ground and underground floors, the outlines of outdoor public spaces, and the outlines of above-ground connecting corridors in the target area can be extracted from them.

[0028] Specifically, the methods for obtaining functional business type data include: obtaining the name, category (rest, children's activities, sports, etc.), and location coordinates of each commercial store from life service platforms such as maps, Dianping, and Meituan, or obtaining it through on-site surveys.

[0029] Step S200: Divide the target area into a three-dimensional mesh to generate multiple three-dimensional spatial units.

[0030] In some embodiments, step S200 includes steps S210 to S220, the specific steps of which are as follows: Step S210: According to the preset size, the multiple spatial layers of the target area are divided into planar grids to generate multiple grid units. The spatial layers include a ground layer, at least one above-ground layer and at least one underground layer.

[0031] Specifically, 25m can be used. 25m or 50m The target area is divided into multiple spatial layers using a 50m or other preset size, generating multiple grid units and assigning a unique code to each grid unit. These multiple spatial layers include ground layer (F1 layer), above-ground layer (such as F2 layer and F3 layer), and underground layer (such as B1 layer and B2 layer).

[0032] Step S220: Grid cells with consistent planar coordinate ranges on different spatial layers constitute a three-dimensional spatial cell.

[0033] Specifically, grid cells with the same row and column numbers on different spatial levels are combined into a three-dimensional spatial unit. The three-dimensional spatial unit contains vertical columnar spaces from the underground level to the above-ground level, and can reflect the spatial morphological characteristics of the vertical region.

[0034] Step S300: Based on the morphological data of the three-dimensional spatial units and the functional business type data, determine the morphological index of each three-dimensional spatial unit. The morphological index is used to represent multiple spatial morphological characteristics of the three-dimensional spatial unit that affect the sharing of behaviors.

[0035] In some implementations, the morphological index includes at least one of the following: public space area index, spatial accessibility index, functional diversity index, commercial facility connectivity index, and functional visibility index. Specifically, the public space area index refers to the area of ​​public space within the three-dimensional spatial unit; the functional diversity index indicates the degree of mixing of functional types within the three-dimensional spatial unit; the commercial facility connectivity index indicates the proximity of the three-dimensional spatial unit to surrounding commercial facilities; the spatial accessibility index indicates the accessibility and accessibility of the three-dimensional spatial unit within the road network; and the functional visibility index indicates the visibility of the public space from the commercial interface within the three-dimensional spatial unit, wherein the commercial interface includes at least one of the following: shop windows, shop entrances / exits, and the boundaries of outdoor commercial areas.

[0036] In some implementations, step S300 includes steps S310A, S310B, S310C, S310D, S310E, and S310F, wherein step S310A is used to determine the public space area index, step S310B is used to determine the functional diversity index, step S310C is used to determine the commercial facility connectivity index, step S310D is used to determine the space accessibility index, step S310E is used to determine the functional visibility index, and step S310F is used to determine the functional facility index based on the functional diversity index, the commercial facility connectivity index, and the functional visibility index.

[0037] Step S310A: Based on the morphological data of the three-dimensional spatial unit, determine the common space area and the total common space area of ​​each spatial layer covered by each three-dimensional spatial unit, and use the sum as the common space area index. .

[0038] In some embodiments, step S310A includes steps S311A to S313A, and the specific steps are as follows: Step S311A: Based on the morphological data of the three-dimensional spatial unit, for each spatial layer, obtain the outer contour of all common spaces in that layer to form a polygonal layer.

[0039] Step S312A: For a single solid space unit, intersect the outer contour of the solid space unit and the common space of each space layer to obtain the common space part of the solid space unit on that layer. The common space part may be one or more sub-polygons.

[0040] Step S313A: Calculate the total area of ​​the intersecting portions, which will be used as the common space area of ​​this unit on this floor. The calculation is performed using the following formula: ; In the formula, For the first The public space area index of each three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For the first The area of ​​the public space on each floor.

[0041] This yields the total public space area of ​​each three-dimensional spatial unit, which is used as the public space area index. .

[0042] Public space area index The larger the value, the more abundant the total amount of public space resources in the three-dimensional space unit, providing a better foundation for carrying diverse activities and improving the quality of the space.

[0043] Step S310B: Based on the functional business type data, determine the total number of functional business types contained in each spatial layer within the three-dimensional space unit; based on the three-dimensional space unit morphology data, determine the number of spatial layers in the three-dimensional space unit; and based on the total number of functional business types and the number of spatial layers, determine the functional diversity index. .

[0044] In some embodiments, step S310B includes steps S311B to S313B, and the specific steps are as follows: Step S311B: Standardize and classify the functional business type data. In this embodiment, functional business types are divided into four categories according to planning requirements: rest, catering, sports, and children's activities.

[0045] Alternatively, public spaces such as restaurants and food courts can be categorized as catering areas, public seating and plaza spaces can be categorized as rest areas, gyms, jogging tracks and various sports fields can be categorized as sports areas, and playgrounds can be categorized as children's activity areas.

[0046] Step S312B: Determine the sum of the number of each functional business type within each three-dimensional space unit.

[0047] Step S313B: For a three-dimensional spatial unit containing multiple spatial layers, calculate the functional diversity index using the following formula. : ; In the formula, For the first The sum of the number of various functional business types contained in each spatial layer within a three-dimensional spatial unit. No. The total number of layers in a three-dimensional spatial unit.

[0048] Functional Diversity Index The larger the value, the more functions the three-dimensional spatial unit has.

[0049] Step S310C: Based on the morphological data of the three-dimensional space unit, determine the horizontal distance and number of spatial layers from the grid unit on each spatial layer within the three-dimensional space unit to the nearest commercial service facility, and determine the connectivity index of the commercial facility based on the horizontal distance and the number of spatial layers.

[0050] In some embodiments, step S310C includes steps S311C to S314C, and the specific steps are as follows: Step S311C: Based on the three-dimensional spatial unit morphology data and functional business type data, extract each commercial service facility point and its coordinates. Commercial service facility points may include subway station entrances and exits, large shopping mall entrances, and concentrated catering areas, etc.

[0051] Step S312C: For a single three-dimensional space unit, calculate the horizontal distance from the center point of the grid unit of each space layer of the three-dimensional space unit to the nearest commercial service facility. Specifically: the ground layer adopts a ground pedestrian road network, the above-ground layer adopts an above-ground corridor network, and the underground layer adopts an underground passage network.

[0052] Step S313C: For three-dimensional space units, calculate the connectivity index of commercial facilities using the formula. : ; In the formula, For the first The connectivity index of commercial facilities in a three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For this three-dimensional spatial unit in the first The reachability distance from the center point of the layer grid to the nearest commercial service facility.

[0053] Commercial facility connectivity index The larger the value, the closer the connection between the three-dimensional space unit and the surrounding commercial service facilities, the easier it is for people to reach, and the higher the sharing potential.

[0054] Step S310D: Based on the morphological data of the three-dimensional spatial units, determine the node distribution of the three-dimensional spatial units in the road network and the path distance between the nodes. Based on the node distribution and path distance, determine the spatial accessibility index. .

[0055] In some embodiments, step S310D includes steps S311D to S317D, and the specific steps are as follows: Step S311D: Construct a three-dimensional road network model of the three-dimensional spatial units based on the morphological data of the three-dimensional spatial units.

[0056] Specifically, the road network model includes: determining multiple nodes for each spatial layer of the three-dimensional spatial unit, where nodes can include road intersections, road endpoints, stair or elevator locations, and the center point of the grid unit at that layer. Road endpoints can be connections to other three-dimensional spatial units.

[0057] Step S312D: For each spatial layer, take the center point of the grid cell in that layer as... ,Sure The shortest path distance to other nodes is denoted as . , The remaining nodes of this layer of mesh cells Each node.

[0058] Step S313D: Calculate the reachability index of the mesh cells in this layer according to the formula. , ; In the formula, For the first The total number of nodes in a layer of mesh cells. For the first Layer mesh cell removal The remaining nodes of 1 node for The shortest path distance to other nodes. For the first The center point of the layer grid cell.

[0059] Step S314D: Calculate the accessibility index of the three-dimensional spatial unit according to the formula. , In the formula, For the first The reachability index of layered grid cells, The total number of floors covered by the three-dimensional space unit.

[0060] Accessibility Index The smaller the value, the more central the three-dimensional spatial unit is in the road network, and the better its spatial accessibility.

[0061] Step S315D: Obtain the total height difference and number of layers of the three-dimensional space unit, determine the vertical traffic weight, and form the accessibility weight.

[0062] Specifically, vertical transportation weight ; In the formula, For vertical transportation weights, For the first The total height difference of each three-dimensional spatial unit For the first The number of layers in a three-dimensional spatial unit.

[0063] Specifically, It is obtained by accumulating the height differences between adjacent layers.

[0064] Step S316D: Obtain the first The horizontal ground elevation difference corresponding to each three-dimensional spatial unit Total height of the podium Determine the weight of the horizontal ground elevation difference.

[0065] In this embodiment, the horizontal ground of the three-dimensional space unit is the ground floor. It should be noted that when the three-dimensional space unit is stacked with multiple floors in the vertical direction, the height difference at various points on the horizontal ground is only measured at multiple points for the ground floor of the unit.

[0066] Specifically, the total height of the podium is the vertical dimension of the podium or main building attached to the ground floor from the outdoor ground to the highest point of the roof, which can be obtained through three-dimensional spatial unit morphology data.

[0067] Specifically, horizontal ground elevation difference It is the difference between the highest and lowest points of the above-ground layer.

[0068] Specifically, the weight of horizontal ground elevation difference .

[0069] Step S317D: Based on the accessibility index The spatial accessibility index is determined by the weights of vertical transportation and horizontal ground elevation differences. .

[0070] Specifically, .

[0071] Accessibility Index By verifying that the shorter the path distance from the center of the grid to a node on the same level, the more central the point is in the road network, and the less obstruction there is to other areas. and Used to characterize physical obstacles. Vertical transportation weights... The average floor height is obtained by dividing the total elevation difference by the number of floors; vertical transportation weight. The larger the value, the greater the distance and time required for each vertical movement, which is less conducive to barrier-free access. Horizontal ground elevation difference weighting. The difference in elevation between the highest and lowest points of the ground floor, divided by the total height of the podium, quantifies the impact of uphill / downhill and step-like descents due to horizontal ground level differences. Road network accessibility and physical barriers are variables measuring the objective difficulty of spatial passage, thus jointly determining the spatial accessibility index. Space accessibility index The bigger the better.

[0072] Step S310E: Based on the morphological data of the three-dimensional spatial units, determine the interface proportion of spatial entities or facilities with commercial service attributes on the boundary of the public space, and determine the functional visibility index based on the interface proportion.

[0073] In some embodiments, step S310E includes steps S311E to S314E, and the specific steps are as follows: Step S311E: Obtain the length of the commercial window, shop entrance / exit, or commercial outdoor area boundary that can be directly observed by a pedestrian standing at the street entrance or plaza entrance under the condition of horizontal view and unobstructed line of sight, wherein the commercial interface is a spatial entity or facility with commercial service attributes.

[0074] Step S312E: Determine the total length of the common space boundary of each three-dimensional space unit based on the morphological data of the three-dimensional space unit.

[0075] Step S313E: Calculate the functional visibility index of the mesh cells in a single spatial layer of the 3D spatial unit. The calculation is performed using the following formula: ; In the formula, The first point is the view that a pedestrian standing at the entrance of a street or plaza can directly observe from a horizontal, unobstructed viewpoint. The length of the boundaries of the commercial windows, shop entrances / exits, or outdoor commercial areas on each floor. The first of each three-dimensional spatial unit The total length of the public space boundary of the floor.

[0076] Step S314E: Calculate the functional visibility index of the three-dimensional spatial unit according to the formula. , In the formula, For the first The functional visibility index of the layer The total number of floors covered by the three-dimensional space unit.

[0077] Functional visibility index The larger the value, the easier it is for commercial activities within the three-dimensional space unit to be seen by pedestrians in the public space, which is more conducive to attracting people to engage in corresponding activities (such as stopping to watch, entering shops, dining outdoors, etc.), thereby enhancing the space's shared nature.

[0078] Step S310F: Determine the functional facility index based on the functional diversity index, commercial facility connectivity index, and functional visibility index.

[0079] Specifically, step S310F includes step S311F.

[0080] Step S311F: Calculate using the following formula: ; In the formula, For the first Functional facility index of each three-dimensional space unit For the first Functional diversity index of a three-dimensional spatial unit For the first The connectivity index of commercial facilities in a three-dimensional spatial unit For the first Functional visibility index of a three-dimensional spatial unit These are the coefficients of the corresponding indices. =1.

[0081] Step S400: Obtain crowd activity data for each three-dimensional spatial unit, and determine the behavior sharing value based on the crowd activity data. The behavior sharing value is used to represent the mixed type and intensity of crowd activities within the three-dimensional spatial unit.

[0082] In some embodiments, step S400 includes steps S410 to S450, the specific steps of which are as follows: Step S410: Obtain crowd activity data for the public spaces on the ground floor, above-ground floor, and underground floor of the target area. The crowd activity data includes activity type, number of activities, and activity coordinates.

[0083] Optionally, video equipment can be used to continuously film in high-intensity development areas, with the camera range covering the main public spaces on the ground floor, above-ground floors, and underground floors to obtain data on crowd activity in the public spaces on the ground floor, above-ground floors, and underground floors of the target area.

[0084] It is important to note that during video capture, all cameras only film public spaces and do not focus on or track individuals. In the video analysis phase, deep learning-based pedestrian detection algorithms are used, such as YOLOv5, to identify pedestrian regions in the images. However, this algorithm only extracts the bounding boxes and center point coordinates of pedestrians, without extracting facial features or any biometric information that could identify an individual. For situations involving multiple people walking together, only the number of people in the group is counted; the identities of individuals within the group are not identified.

[0085] In some embodiments, steps S411 to S413 are further included after step S410, and the specific steps are as follows: Step S411: Extract the feature information of each individual based on the crowd activity data.

[0086] Optionally, the video data includes a time series, and the feature information includes the consecutive location points of each individual in the time series and the corresponding timestamps.

[0087] Optionally, a deep learning-based multi-object tracking algorithm (DeepSORT) is used to analyze the video, extracting the continuous position coordinate sequence of each individual over time, thereby constructing a spatiotemporal trajectory representing the individual's motion characteristics. For each individual, its position coordinates at each timestamp are recorded ( ) and the corresponding timestamp This forms a complete sequence of trajectory features.

[0088] Step S412: Construct the behavioral feature vector for each individual based on the feature information.

[0089] Optionally, construct a behavioral feature vector F that includes spatiotemporal attributes. ,in, Continuous position points of each individual in the time series coordinate, Continuous position points of each individual in the time series coordinate, For the corresponding timestamp, For each individual's instantaneous velocity, The acceleration for each individual, The displacement change for each individual. The neighborhood density for each individual.

[0090] Step S413: Based on the behavioral feature vector of each individual, determine whether the behavior type of each individual belongs to the stationary behavior or the passage behavior.

[0091] according to and The system identifies behavior types, confirms whether each individual's behavior type belongs to a common behavior category, and combines this with... Distinguish between single-person passage and multi-person passage.

[0092] Aside from passage-type behaviors, the rest are defaulted to stay-type behaviors, which are further divided into stay-type behaviors with complete trajectories and stay-type behaviors with interrupted trajectories.

[0093] For stationary behaviors with complete trajectories, according to and To identify behavior types.

[0094] For example, if the moving speed is less than a preset first threshold, or the displacement distance is less than a preset second threshold, then the individual is determined to be in a stationary state during that time period, and the stationary state point is marked as the clustering input for stationary state behavior.

[0095] For example, the first threshold can be set to 0.3 m / s to 0.5 m / s, and the second threshold can be set to 0.5 m to 1 m. When <First threshold or When the speed falls below the second threshold, the individual is considered to be in a stationary state during that time period. The first threshold is set based on the lower limit of normal human walking speed, typically between 0.3 m / s and 0.5 m / s. When the speed is below this range, the individual can be considered to be in a state of stagnation or slight movement.

[0096] For stationary behaviors with interrupted trajectories, such as those caused by an individual entering an indoor area or obstructing a region in video surveillance, if the point of interruption is within the effective service radius of a preset activity label, the continuous location points are marked as clustering inputs for stationary behaviors. The corresponding behavior type is then identified based on the activity label, thereby enabling the identification of stationary behaviors within video blind spots.

[0097] For example, if the moving speed is greater than a preset first threshold, or the displacement distance is greater than a preset second threshold, then the individual is determined to be passing through during that time period.

[0098] when ≥ First threshold and When the value is greater than or equal to the second threshold, the individual is determined to have engaged in passage behavior during that time period. Passage behavior includes single-person passage and multi-person passage. When it is determined to be multi-person passage, the number of people is additionally identified and recorded.

[0099] Specifically, if an individual is in a passage state within an adjacent timestamp and there are no other individuals in its neighborhood (radius 3 meters, time window ± 2 seconds), it is marked as a single person passage point, and its coordinates and time are recorded separately. If there are other individuals in the neighborhood, mark it as a multi-person passage point and record the number of people in the group.

[0100] Step S413 can distinguish between passage behavior and dwelling behavior. For individuals whose trajectory is interrupted, their dwelling behavior type can be determined. For individuals whose trajectory is not interrupted and whose behavior is dwelling, their behavior type can be identified through subsequent steps S42134.

[0101] Step S420: Perform cluster analysis on the crowd activity data to obtain the cluster type, number of clusters, and cluster coordinates for each layer and time period.

[0102] In some implementations, step S420 includes steps S421 to S423, wherein step S421 is used to determine the cluster type, step S422 is used to determine the number of clusters, and step S423 is used to determine the cluster coordinates.

[0103] In some embodiments, step S421 includes steps S4211 to S4213, and the specific steps are as follows: Step S4211: Divide the various behaviors into passing behaviors and staying behaviors.

[0104] Specifically, through the above step S413, various behaviors can be divided into passage behaviors and stay behaviors.

[0105] Step S4212: Perform cluster analysis on the traffic behavior to obtain traffic clusters for each layer and time period.

[0106] Specifically, a density-based spatial clustering algorithm (DBSCAN) is used to cluster traffic behavior points in each layer and time period. The clustering parameters of the DBSCAN algorithm are set as follows: the neighborhood radius ranges from 8 to 12 meters, which can be set according to the minimum aggregation scale of crowd activities in urban public spaces. In this embodiment, 10 meters is used. The minimum number of neighborhood samples ranges from 1 to 8, which can be set according to the data sampling frequency. The minimum number of neighborhood samples also ranges from 1 to 8, and in this embodiment, 5 is used. This means that only when there are 5 or more traffic behavior points within a radius of 10 meters can a traffic cluster be formed. Single-person traffic points (only 1 person in the neighborhood) and groups of 2 to 4 people (less than 5 people in the neighborhood) do not meet the core point condition and are therefore classified as noise points and removed from the clustering results.

[0107] Specifically, step S4212 includes steps S42121 to S42125, and the specific steps are as follows: Step S42121: For each passage point, calculate the number of sample points contained in its neighborhood.

[0108] Step S42122: If the number of sample points in the neighborhood of a point is greater than or equal to the number of samples in the minimum neighborhood, then mark the point as a core point; Step S42123: Using each core point as a seed, group all points within its neighborhood into the same cluster; Step S42124: Merge interconnected core points and their associated points into the same common cluster; Step S42125: Noise points that cannot be assigned to any cluster are removed.

[0109] Step S4213: Perform cluster analysis on the dwell behavior to obtain dwell behavior clusters for each layer and time period, and determine the type of each dwell behavior cluster. The types of dwell behavior clusters include at least one of rest cluster, dining cluster, sports cluster, and children's activity cluster.

[0110] In some implementations, step S4213 includes steps S42131 to S42134.

[0111] Step S42131: Perform cluster analysis on dwell behavior to obtain dwell behavior clusters for each layer and time period.

[0112] Specifically, the DBSCAN algorithm is used for cluster analysis of dwelling behavior, with parameter settings consistent with those for passage behavior. The difference lies in the clustering input: the complete trajectory point set and the trajectory interruption point set are used for dwelling behavior. The complete trajectory point set includes multiple dwelling behavior points identified in step S413 that maintain a continuous trajectory within the video surveillance range. The trajectory interruption point set includes multiple trajectory interruption points identified in step S413, where the coordinates of their last occurrence are located within the effective service radius of a preset active tag. By unifying these two types of point sets as clustering input, collaborative clustering of dwelling behavior in both blind and non-blind spots of video surveillance is achieved, ensuring the completeness and accuracy of dwelling behavior analysis.

[0113] For example, the kernel density analysis of the lingering behavior at the ground level from 16:00 to 17:00 on weekends showed that multiple high-density clusters formed in the plaza area, located in the rest seating area, the dining area, and other shopping areas.

[0114] Step S42132: Obtain activity labels for the public spaces of the ground floor, above-ground floor, and underground floor of the target area. Each activity label corresponds to a location coordinate.

[0115] Specifically, activity tags can be obtained from planning drawings, site surveys, or map data, including the coordinates, names, and types of restaurants, fitness facilities, indoor playgrounds, children's playgrounds, rest areas, etc. Each activity tag corresponds to a specific location coordinate.

[0116] Step S42133: Match the coordinates of the dwell behavior cluster with the location coordinates corresponding to the activity label.

[0117] For the cluster of dwell behaviors corresponding to complete trajectory points, optionally, a spatial proximity matching algorithm can be used to calculate the distance between the center coordinates of each dwell behavior cluster and the location coordinates of each activity label. If the distance is less than a preset threshold, the cluster is considered to match the activity label. Optionally, the preset threshold can be in the range of 3 to 5 meters.

[0118] For the cluster of dwell behavior corresponding to the trajectory interruption point, optionally, the trajectory interruption point is located within the effective service radius of the preset activity label, and the trajectory interruption point is regarded as the cluster corresponding to the activity label.

[0119] Step S42134: Determine the type of cluster for dwell behavior.

[0120] Optionally, the type of dwell behavior cluster can be determined based on the matching results. For example, if a dwell behavior cluster matches the rest area label, it is determined to be a rest cluster. If a dwell behavior cluster matches the restaurant label, it is determined to be a restaurant cluster. If a dwell behavior cluster matches the fitness facility label, it is determined to be an exercise cluster. If a dwell behavior cluster matches labels such as indoor amusement park or children's playground, it is determined to be a children's activity cluster.

[0121] The above scheme can quickly identify the type of cluster of dwelling behavior and save computing power, but some complete trajectory points and activity labels cannot be matched, so algorithm recognition is required to analyze individual actions.

[0122] Optionally, the behavior of staying can be divided into corresponding individual actions, including rest, such as sitting, lying down, leaning, etc.; eating, such as eating, etc.; exercise, such as running, fitness, square dancing, etc.; and children's activities, such as playing in areas such as children's playgrounds, etc.

[0123] In some implementations, to further improve the accuracy of dwelling behavior recognition, a human pose recognition-based method can be used to determine the type of specific dwelling behavior clusters. Optionally, the YOLOv8 algorithm can be used to detect human bodies and output keypoint coordinates, performing human target detection and pose estimation on video stream data, and extracting the skeletal keypoint coordinates of each individual. The model using the YOLOv8 algorithm can detect multiple keypoints, such as nose, eyes, ears, shoulders, elbows, wrists, palms, hips, knees, and ankles, with each keypoint corresponding to pixel coordinates and its confidence level in the image coordinates. To protect personal privacy, the algorithm only extracts the geometric position information of the keypoints and does not perform facial feature recognition or identity matching. All keypoint data is used only for behavior analysis, and the original image is discarded immediately after keypoint extraction. Based on the angular relationships, distances, and time-series features between keypoints, behavior types such as resting (sitting, lying down, leaning), eating (eating actions), and exercise (square dancing, high knees in place, fitness) can be identified. The identification results can be cross-validated with the activity label matching results: for successfully matched clusters, posture recognition can be used as an auxiliary verification; for clusters without matching labels, posture recognition can be used as the primary identification method. By fusing the two methods, comprehensive and accurate identification of dwelling behavior is achieved.

[0124] Specifically, based on the key features of the hand and mouth, a function of the hand-mouth distance changing over time is calculated. ,like If the distance is less than a preset threshold and the duration exceeds a preset time, it is counted as one hand-mouth proximity event. The number N of proximity events within the preset time window is counted. If the number N is greater than or equal to the preset threshold, the behavior cluster is determined to be a dining cluster. For example, the preset threshold ranges from 0.1 to 0.15 meters, and the preset time ranges from 1 to 2 seconds. When a hand-mouth proximity event is detected, even if the individual is simultaneously in a resting posture, it is still preferentially determined to be a dining behavior. This is because eating is a definitive indicator of dining behavior, while a resting posture only indicates a resting state and does not exclude the possibility of eating.

[0125] Specifically, resting behavior is identified by the angular relationships formed by key points on the human body to determine different posture types. Based on biomechanical principles, the angles between different limb segments exhibit a specific range distribution in different postures such as sitting, lying down, and leaning. Based on the characteristics of the hip, knee, and ankle key points, the angles between the hip-knee vector and the knee-ankle vector are calculated to obtain the angle between the thigh and lower leg. Based on the key features of the shoulder, hip, and knee, the angles between the shoulder-hip vector and the hip-knee vector are calculated to obtain the angle between the upper torso and the thigh. Based on the key features of the shoulder and hip, the angle between the shoulder-hip vector and the horizontal plane is calculated to obtain the angle between the upper torso and the horizontal plane. .

[0126] If the conditions for catering behavior are not met, then according to and First, determine whether it is a seated or reclining type of rest, for example... , The duration must be greater than or equal to a preset time, which can optionally be 20 to 30 seconds. If the rest is not in a seated or reclining position, then according to... To determine whether it is leaning against something for rest, if If so, it is determined to be resting in a lying position.

[0127] The core characteristic of motor behavior is the periodic swinging of limbs. Whether it's running in place or stationary movement (routine movements of the arms or legs), it will exhibit a clear periodic signal in the time series. Specifically, the type of movement is determined based on the key features of the wrist and ankle. A Fast Fourier Transform (FFT) is performed on the positional changes of the wrist and ankle to extract the dominant frequency and amplitude. If the dominant frequency exceeds a preset threshold, it is determined that periodic movement has occurred, thus classifying it as a type of movement.

[0128] It is important to note that periodic limb swinging can occur during commuting activities (running, brisk walking) or stationary exercises (aerobics, weightlifting), and can be distinguished in the following ways: Based on step S120, the displacement distance or movement speed of each individual has been determined. If the displacement distance within a preset time period is less than a preset threshold, or the movement speed is less than a preset threshold, then it is determined to be a moving cluster within the stationary behavior cluster; otherwise, it is a passing cluster. For example, if the preset time is one minute, and the displacement distance within one minute is greater than 1 meter, or the speed is greater than 0.5 meters / s, then it is a passing cluster; otherwise, it is a moving cluster within the stationary behavior cluster.

[0129] Step S422 is used to determine the number of clusters. Specifically, step S422 includes steps S4221 to S4222, and the specific steps are as follows: Step S4221: Count the total number of independent clusters formed in each layer and time period. This indicator is used to characterize the spatial dispersion and distribution breadth of crowd activities in public spaces.

[0130] Step S4222: Count the number of people in each independent cluster at each level and time period.

[0131] For clusters with complete trajectories: count the number of individuals contained in the cluster to obtain the real-time number of residents in the cluster.

[0132] For clusters with interrupted trajectories: Since they are in blind spots, calculations are performed based on the law of conservation of traffic flow at entrances and exits in the video capture area. Specifically, the calculation is as follows: Number of people in this cluster at the current time = Number of people in this cluster at the previous time + Total number of individuals entering the area. The total number of individuals who left the area.

[0133] Step S423 is used to determine the coordinates of the clusters. Specifically, step S423 includes step S4231.

[0134] Step S4231: For clusters with complete trajectories, the centroid calculation method can be used. Specifically, by calculating the average value of these coordinates in the horizontal direction (X-axis) and the vertical direction (Y-axis), the center coordinates of the cluster can be obtained. These center coordinates represent the geometric center of the population activity area and can effectively characterize the spatial distribution of the cluster in the three-dimensional area.

[0135] For clusters with interrupted trajectories, since these clusters are located in blind spots of video surveillance, their centroids cannot be calculated from the trajectory points. Therefore, the coordinates of this cluster are used as the position coordinates of its corresponding active label.

[0136] Step S430: Divide the public spaces of the ground floor, above-ground floor and underground floor into multiple grid units respectively. Calculate the behavior occupancy rate of each grid unit in each time period based on the cluster type, number of clusters and cluster coordinates.

[0137] In some embodiments, step S430 includes steps S431 to S433, the specific steps of which are as follows: Step S431: Divide the common space of the ground floor, above-ground floor and underground floor into multiple grid units according to the preset size, and spatially encode each grid unit.

[0138] In some implementations, the public spaces of the ground floor, above-ground floor, and underground floor are divided into grids according to preset dimensions. Optionally, the preset dimensions can be 50 meters × 50 meters for macro-structural control and functional zoning; alternatively, the preset dimensions can be 10 meters × 10 meters or 5 meters × 5 meters for more detailed design.

[0139] Each grid cell is assigned a unique spatial code, and the coding rule can be in the form of layer code - grid row number - grid column number - scale identifier.

[0140] Optionally, when dividing the common space of the ground floor, above-ground floor, and underground floor into grid units, the grid units of each floor can correspond, that is, have the same two-dimensional planar coordinates, namely the X coordinate and Y coordinate. Multiple grid units with the same two-dimensional planar coordinates form a three-dimensional space unit.

[0141] Step S432: Determine the corresponding grid cell based on the cluster coordinates.

[0142] The center coordinates of each cluster are imported into the GIS server, and each cluster is matched to its corresponding grid cell based on the coordinates. For clusters located on grid boundaries, their corresponding grid cells are determined by the center point of the cluster.

[0143] Step S433: Determine the behavior occupancy rate of each three-dimensional spatial unit in each time period based on the number of clusters.

[0144] For the The behavior occupancy rate of a three-dimensional spatial unit in time period j. Calculate using the following formula: ; In the formula, For the first The three-dimensional space unit in the first Cluster occupancy rate over a given time period For the first The number of clusters of a three-dimensional spatial unit in the j-th time period. For the first The number of clusters of a three-dimensional spatial unit throughout the entire time period. satisfy It has been normalized.

[0145] Specifically, For the first The grid in the first The number of clusters for a given time period, with the minimum number of neighboring samples ranging from 1 to 8, can be set to 1. This means that there is one behavior point within a 10-meter radius, forming a passage cluster. In this case, the number of clusters includes all passage points and all stopping points. Passage points include single-person passage points, multi-person passage points, and all points within the passage cluster. Stopping points include various types of stopping points such as rest areas, restaurants, sports areas, and children's activity areas.

[0146] Step S440: Determine the activity type mixing degree of each three-dimensional spatial unit based on the cluster type, number of clusters, and cluster coordinates.

[0147] In some implementations, step S440 includes step S441, the specific steps of which are as follows: Step S441: Determine the activity type mixing degree of each three-dimensional spatial unit in each time period according to the cluster type.

[0148] For the The three-dimensional space unit in the first The mixing degree of time period and activity type is calculated using the following formula:

[0149] In the formula, For the first The activity type mixing degree of a three-dimensional spatial unit in time period j This represents the total number of activity types. For the first The three-dimensional spatial unit in the j-th time period The percentage of clusters of activity types.

[0150] Specifically, the total number of activity types The value is 5, which includes passage, rest, dining, exercise, and children's activities in this embodiment. Calculation using the formula: , For the first The three-dimensional spatial unit in the j-th time period is... Number of clusters for activity types.

[0151] In the above technical solution, the activity type mixing degree reflects the diversity of activities within a specific time period of the three-dimensional spatial unit. The higher the activity type mixing degree, the richer the types of activities carried by the grid within the same time period, and the better the sharing.

[0152] Step S450: Determine the behavior sharing value based on behavior occupancy and activity type mixing.

[0153] In some embodiments, step S450 includes steps S451 to S452, the specific steps of which are as follows: Step S451: Based on behavior occupancy Mixed activity types Calculate the shared behavior value of each three-dimensional spatial unit at each time period using the following formula. : ; In the formula, For the first Each three-dimensional spatial unit in time period Unit behavior occupancy rate For the first Each three-dimensional spatial unit in time period Activity type mix For the first Each three-dimensional spatial unit in time period Shared values ​​for behavior.

[0154] Step S452: For the first Each three-dimensional spatial unit in time period Behavioral sharing values Summing to obtain the first... Shared behavioral values ​​for each three-dimensional spatial unit: ; In the formula, No. Shared behavioral values ​​for each three-dimensional spatial unit For the first A preset time period The total number of preset time periods. For the first A three-dimensional spatial unit, For the first Each three-dimensional spatial unit in time period Shared values ​​for behavior.

[0155] Step S500: Use the morphological index as the input feature and the behavior sharing value as the training label to construct the training dataset.

[0156] Specifically, for the first Each three-dimensional spatial unit, its common spatial area index Functional diversity index Commercial facility connectivity index Accessibility index of space Functional visibility index These five morphological indices form a feature vector. The behavior-sharing values ​​obtained in step S450 are used as labels to form a training sample. The samples of all X three-dimensional spatial units are combined to form the training dataset D. In some implementations, prior to step S500, the method further includes: obtaining the morphological index and behavioral sharing value of each three-dimensional spatial unit; calculating the mean and standard deviation of various morphological indices within all three-dimensional spatial units; determining the Pearson correlation coefficient between each index and the behavioral sharing value based on the index value, behavioral sharing value, and index mean of each three-dimensional spatial unit; and screening key indices based on the Pearson correlation coefficient, eliminating indices with insignificant correlation. >0.05), specifically, it is calculated according to the following formula: ; In the formula, For the first Pearson correlation coefficient between morphological index and behavioral sharing value. For the first The first three-dimensional spatial unit Item morphology index, For all three-dimensional space units The mean of the morphological index, For the first Shared behavioral values ​​for each three-dimensional spatial unit This represents the average of the shared values ​​of behavior across all three-dimensional spatial units. This represents the total number of three-dimensional spatial units.

[0157] Including public space area index Functional diversity index Commercial facility connectivity index Accessibility index of space Functional visibility index .

[0158] Step S600: Train the training dataset using a machine learning algorithm to determine the index weights corresponding to the morphological index.

[0159] In some embodiments, step S600 includes steps S610 to S650, the specific steps of which are as follows: Step S610: Divide the multiple morphological indices into a core influence index group and a secondary influence index group; Based on the calculation of the Pearson correlation coefficient between the various indices and behavioral sharing values ​​in step S500 above, the functional diversity index is... Connectivity Index of Commercial Facilities Divided into core impact index groups, the public space area index Accessibility index of space and functional visibility index It is divided into the auxiliary influence index group.

[0160] Step S620: Determine the first correlation sum of the core influence index group and the behavioral sharing values.

[0161] Calculate the first correlation sum using the following formula: ; In the formula, The first correlation sum of the core influence index group and behavioral sharing values, For the first The absolute value of the Pearson correlation coefficient between the index and the behavioral sharing value, the first This index belongs to the core influence index group.

[0162] Step S630: Determine the second association sum of the auxiliary influence index group and the behavioral sharing value.

[0163] Calculate the second correlation sum using the following formula: ; In the formula, The second correlation sum is the core influence index group and the behavioral sharing value. For the first The absolute value of the Pearson correlation coefficient between the index and the behavioral sharing value, the first This index belongs to the auxiliary influence index group.

[0164] Step S640: Based on the ratio of the first correlation sum to the second correlation sum Determine the weighting ratio between the core influence index group and the auxiliary influence index group.

[0165] calculate ; In the formula, Assigning weights proportionally, This is the first correlation sum. This is the second related sum.

[0166] This reflects the overall importance of the core index group relative to the auxiliary index group.

[0167] Step S650: Determine the index weight corresponding to the morphological index according to the weight allocation ratio.

[0168] In some implementations, step S650 includes steps S651 to S656, the specific steps of which are as follows: Step S651: Multiple indices of the morphological index constitute the morphological sharing index of the three-dimensional spatial unit. Assuming the morphological sharing index of the three-dimensional spatial unit... In the formula, , , , as well as The weighting coefficients for each index of the morphology index are used to normalize the multiple indices of the morphology index.

[0169] Step S652: Train the training dataset using a machine learning algorithm to obtain... , , , as well as The initial value.

[0170] Specifically, decision tree algorithms or random forest algorithms can be used for training. The following conditions must be met: 1.

[0171] Step S653: Allocate according to weight ratio Solve for the coefficients of the core index group and auxiliary index group coefficients .

[0172] / and 1. From this, we can solve for... and The specific value, , .

[0173] Step S654: According to and The value of, for , , , as well as The initial value is corrected. , , , , This is to obtain the final weight of the morphology index.

[0174] Step S655: Normalize the multiple final weights so that their sum is 1.

[0175] Step S700: Generate the morphological sharing index of the region to be tested based on the index weight and the morphological index of the region to be tested.

[0176] Based on the final index weights obtained in step S655, determine The function substitutes the morphological index of the region to be tested into... The function obtains the morphological sharing index of the region to be tested.

[0177] In some embodiments, steps S810 to S840 are also included, whereby steps S810 to S840 are used to implement step S800: predicting the viability of the area to be tested. The specific steps are as follows: Step S810: Obtain the morphological sharing index of each three-dimensional spatial unit in the area to be tested, and determine the spatial sharing potential level based on the morphological sharing index.

[0178] Specifically, the morphological sharing index can be divided into several levels.

[0179] Optionally, if the area to be tested is an undeveloped area, step S810 includes steps S811A to S817A, and the specific steps are as follows: Step S811A: Establish a case library containing multiple completed and stable operating reference cases. Each reference case is associated with and stored with its morphological index set, surrounding environment morphological index set, scale and type attributes, and operation stage tags.

[0180] Alternatively, for a newly built vacant lot that has never had any pedestrian traffic data, the formula in step S651 can be directly applied to calculate the pedestrian traffic data. It is only a potential value of form, which is not accurate enough. Therefore, we can find existing areas with similar objective conditions to the newly built vacant land to train the corresponding model in order to predict the vitality value of the newly built vacant land.

[0181] Data from multiple completed and stably operating three-dimensional spatial unit areas was collected in advance and stored in a database. The data records for each reference case include: The set of morphological indices includes morphological indices such as the public space area index and functional diversity index obtained in step S300.

[0182] Optionally, the surrounding environment morphology index set includes, but is not limited to, traffic connection matching degree and surrounding attractor density, wherein the traffic connection matching degree is used to represent the overlap index between the direction of pedestrian flow and the main entrance of the shopping mall, and the surrounding attractor density is used to represent the weighted density of surrounding schools, office buildings and residential areas.

[0183] Optionally, the scale and type attributes may include: the area of ​​surrounding commercial buildings and the type label of commercial buildings, such as community type, regional type, destination type, etc. Community type includes fresh food supermarkets, fast food, parent-child education and training, community services, etc. Regional type includes department stores, large cinemas, mid-to-high-end restaurants, leisure and entertainment, etc. Destination type includes outlets, large theme parks, high-end luxury duty-free shops, distinctive cultural and tourism blocks, etc.

[0184] Optionally, the operational stage label includes the number of years since opening, whether it is in the incubation period, and whether it is in the stable operation period, where the incubation period usually refers to 1-2 years after opening.

[0185] Step S812: Based on the case library, determine the similarity between the area to be tested and each reference case.

[0186] Optionally, for the area to be tested, its surrounding environmental morphology index set and scale and type attributes are obtained, and its similarity with all reference cases in the case library is calculated. The similarity calculation is based on the weighted Euclidean distance of the following multidimensional feature vectors, where the multidimensional feature vectors include scale similarity, which can be obtained through the commercial building area of ​​the scale and type attributes; type similarity, which can be obtained through the type label of the scale and type attributes; and environmental feature similarity, which can be obtained by comparing the similarity of the surrounding environmental morphology index set.

[0187] Step S813: Sort by similarity and select a preset number of reference cases to form a reference case group.

[0188] Specifically, three to five existing shopping malls with the highest similarity were selected as a reference case group. This multi-case mechanism effectively eliminated the fluctuation bias in activity caused by accidental factors in a single neighboring shopping mall.

[0189] Step S814: Based on historical data of morphological index and behavioral sharing values ​​of each reference case in the reference case group, construct a model for predicting the vitality of the area to be tested.

[0190] Optionally, a regression model can be selected.

[0191] Step S815: Obtain the set of morphological indices for the region to be tested, input them into the model, and obtain the initial vitality prediction value.

[0192] Step S816: Determine the space sharing potential level based on the initial vitality prediction value.

[0193] If the area to be tested is not yet built or operational, the space sharing potential level can be determined directly based on the space sharing potential level.

[0194] Step S820: If the area to be tested is an already running area, then the behavior occupancy rate and activity type mixing degree of the area to be tested need to be obtained.

[0195] The behavior occupancy rate and activity type mixing degree of the test area can be obtained according to steps S433 and S441.

[0196] Step S830: Determine the vitality duration based on behavior occupancy and activity type mix.

[0197] Vitality duration is calculated using the following formula: ; In the formula, For the first The vitality and sustainability of each three-dimensional spatial unit The total number of preset time periods. For the first The three-dimensional space unit in the first Time-based behavior occupancy For the first The three-dimensional space unit in the first Mixed activity types during different time periods.

[0198] In this embodiment, It can be 24 hours, which is one day, or it can be one month or even one year.

[0199] It should be noted that steps S820 to S840 are only applicable to the test area that is already running, and cannot be applied to areas that are not running.

[0200] Step S840: Determine the vitality prediction results of the area to be tested based on the spatial sharing potential level and vitality persistence.

[0201] For undeveloped areas, the vitality prediction results of the area to be tested can be determined directly based on the spatial sharing potential level obtained in step S810.

[0202] For the established areas, the spatial sharing potential level and vitality sustainability can be obtained according to steps S810 to S840 to determine the vitality prediction results of the areas to be tested.

[0203] Specifically, the spatial sharing potential level and vitality sustainability are normalized and then summed after being assigned corresponding weights to obtain the vitality prediction results of the area to be tested.

[0204] Space sharing potential level measures the inherent, long-term vitality potential of a space, unaffected by short-term operational fluctuations. Vitality sustainability, on the other hand, reflects current operational performance and the stability of visitor numbers. Combining these two metrics reflects the current reality while avoiding interference from short-term fluctuations, making the final vitality forecast more relevant for long-term planning.

[0205] Step S900: Application and optimization steps based on prediction results: Build an application platform, integrate data collection, index calculation, and vitality prediction functions, and realize the visualization display and scheme optimization guidance of the shared three-dimensional spatial units.

[0206] Specifically, the application platform setup includes the following modules: Data acquisition module: Connects to IoT devices such as cameras and sensors deployed in the target area to automatically collect real-time crowd activity data; connects to the GIS database of the planning department to obtain the latest spatial form data and functional business data.

[0207] Calculation module: Built-in algorithms for steps S300 to S700, including functions such as morphological index calculation, behavior sharing numerical calculation, machine learning model training and weight determination, and morphological sharing index generation.

[0208] Vitality Prediction Module: Based on the algorithm in step S800, this module predicts the vitality of the area to be tested. It supports multiple prediction modes: short-term prediction based on real-time data and long-term prediction based on planning schemes.

[0209] The visualization module can display the distribution of morphological index scores, behavioral sharing values, morphological sharing index, and vitality prediction results for each three-dimensional spatial unit. It can also display the behavioral occupancy rate change curves for each time period.

[0210] The solution optimization guidance module automatically generates space optimization suggestions based on the analysis results. For example, for vertical space units with a low functional diversity index, it is recommended to introduce new functional business formats; for vertical space units with a low commercial facility connectivity index, it is recommended to add vertical connection facilities or improve pedestrian paths; for vertical space units with a low functional visibility index, it is recommended to optimize the commercial interface design and add shop windows, outdoor display areas, etc.; for areas with a low overall form sharing index, it is recommended to carry out comprehensive renovation and transformation, etc.

[0211] In some implementations, commercial layout planning data for the area to be tested is obtained to determine the suitability of the proposed solution. The functional layout of the planned business formats is then input into the application platform, the form sharing index and vitality prediction results are recalculated, and compared with the original solution to assess the impact of the planned solution on space sharing.

[0212] In some embodiments, according to the measurement method provided by the present invention, the method further includes step S1000, which is used to comprehensively evaluate the schemes, including: obtaining the highest value of the morphological sharing index among multiple schemes; calculating the ratio of the index of each scheme to the highest value; normalizing the construction cost to obtain the target cost value, so that the lower the cost, the higher the score; setting the weight values ​​of the morphological sharing index, the vitality prediction result, the target cost value, and the implementation feasibility score; generating a comprehensive evaluation score based on the weight values ​​and various data; and selecting the optimal scheme based on the comprehensive evaluation score.

[0213] In summary, the vitality prediction method based on urban three-dimensional spatial morphology provided by the embodiments of the present invention has the following advantages: 1. This invention acquires morphological data and functional business type data of three-dimensional spatial units at the ground, above-ground, and underground levels of a target area, divides the target area into multiple three-dimensional spatial units, determines the morphological index of each three-dimensional spatial unit, and determines the behavioral sharing value by combining it with population activity data, constructs a training dataset, uses machine learning algorithms to determine the corresponding morphological index weights, and finally generates the morphological sharing index of the area to be tested. This forms a complete technical solution from data collection, index calculation, association learning to index generation, effectively solving the problems of existing measurement methods lacking three-dimensional morphological specificity and having a single index system, and can accurately reflect the true sharing potential of three-dimensional spatial units.

[0214] 2. This invention obtains crowd activity data for each three-dimensional spatial unit to determine the behavior sharing value. This value can accurately represent the mixed type and intensity of crowd activities within the three-dimensional spatial unit. A training dataset is constructed by using morphological indices as input features and behavior sharing values ​​as training labels. The machine learning algorithm automatically learns the correlation between each morphological index and the true sharing, objectively determines the index weights, and improves the accuracy of the morphological sharing index.

[0215] 3. This invention further improves the accuracy of the morphological sharing index by dividing the morphological index into a core influence index group and an auxiliary influence index group, and determining the weight allocation ratio between the groups based on the sum of the correlation between the two groups of indices and the behavioral sharing values.

[0216] 4. This invention integrates data collection, index calculation, and vitality prediction functions by building an application platform, enabling the visualization and optimization guidance of shared three-dimensional spatial units. It can automatically generate spatial optimization suggestions, support planning scheme evaluation and multi-scheme comprehensive evaluation, and provide quantitative basis for planning decisions.

[0217] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 2As shown, the electronic device 400 includes: one or more processors 410 and a memory 420. Figure 2 Take a processor 410 as an example.

[0218] In some implementations, the processor 410 and the memory 420 may be connected via a bus or other means. Figure 2 Taking the example of a connection between China and Israel via a bus.

[0219] In some implementations, the processor 410 is used to acquire morphological data and functional business type data of three-dimensional spatial units in a target area; wherein, the morphological data of three-dimensional spatial units includes at least one of the building outlines of the ground floor, above-ground and underground floors, the outlines of outdoor public spaces, and the outlines of above-ground connecting corridors in the target area; the functional business type data is used to identify the use category or activity type of each three-dimensional spatial unit; the target area is divided into three-dimensional grids to generate multiple three-dimensional spatial units; based on the morphological data and functional business type data of the three-dimensional spatial units, a morphological index is determined for each three-dimensional spatial unit, the morphological index being used to represent multiple spatial morphological features of the three-dimensional spatial unit that affect behavioral sharing; crowd activity data of each three-dimensional spatial unit is acquired, and behavioral sharing values ​​are determined based on the crowd activity data, the behavioral sharing values ​​being used to represent the mixed type and intensity of crowd activities within the three-dimensional spatial unit; a training dataset is constructed by using the morphological index as input features and the behavioral sharing values ​​as training labels; the training dataset is trained using a machine learning algorithm to determine the index weights corresponding to the morphological indexes; and a morphological sharing index for the area to be tested is generated based on the index weights and the morphological index of the area to be tested.

[0220] In some embodiments, memory 420 serves as a non-volatile computer-readable storage medium, used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules of the vitality prediction method based on urban three-dimensional spatial morphology in this embodiment of the invention. Processor 410 executes various functional applications and data processing of electronic device 400 by running the non-volatile software programs, instructions, and modules stored in memory 420, thereby implementing the vitality prediction method based on urban three-dimensional spatial morphology described in the above-described method embodiment.

[0221] In some embodiments, memory 420 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of electronic device 400, etc. Furthermore, memory 420 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 420 may optionally include memory remotely located relative to processor 410, and this remote memory may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0222] In some implementations, one or more modules are stored in memory 420 and, when executed by one or more processors 410, perform the vitality prediction method based on urban three-dimensional spatial morphology in any of the above method embodiments, for example, performing the above-described... Figure 1 The method steps S100 to S900.

[0223] In some implementations, the electronic device can be a chip, such as a data processing unit (DPU) chip used in a data center, or the electronic device can be a network interface card including a chip and multiple interfaces (such as PCI / PCIE interface, UART interface, USB interface, etc.), or the electronic device can be a traditional server, or a server including a network interface card or chip. The server includes a host and a data processor. The data processor is used to schedule packets to the host or the data processor itself for processing, and the host is used to process the packets scheduled by the data processor.

[0224] Please refer to Figure 3 , Figure 3 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of the present invention. The computer-readable storage medium 500 stores program code 510, which can be called by a processor to execute the vitality prediction method based on urban three-dimensional spatial morphology described in the above method embodiments.

[0225] The computer-readable storage medium 500 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a nontransitory computer-readable storage medium. The computer-readable storage medium 500 has storage space for program code that performs any of the method steps of the above-described method for predicting vitality based on urban three-dimensional spatial morphology. This program code can be read from or written to one or more computer program products. The program code may, for example, be compressed in an appropriate form.

[0226] In summary, this invention provides a method, device, and medium for predicting the vitality of urban three-dimensional spatial morphology. The method includes acquiring morphological data and functional type data of three-dimensional spatial units in a target area. The morphological data of the three-dimensional spatial units includes at least one of the building outlines of the ground floor, above-ground floors, and underground floors of the target area, the outlines of outdoor public spaces, and the outlines of above-ground connecting corridors. The functional type data is used to identify the purpose or activity type of each three-dimensional spatial unit. The target area is divided into three-dimensional grids to generate multiple three-dimensional spatial units. Based on the morphological data and functional type data of the three-dimensional spatial units, the vitality prediction method determines... This invention defines a morphological index for each three-dimensional spatial unit, representing multiple spatial morphological features that influence behavioral sharing within that unit. It acquires crowd activity data for each unit and determines behavioral sharing values ​​based on this data, representing the mixed types and intensity of crowd activities within the unit. A training dataset is constructed using the morphological index as input features and the behavioral sharing values ​​as training labels. Machine learning algorithms are then used to train the training dataset and determine the index weights corresponding to the morphological indices. Finally, based on these weights and the morphological index of the region under test, a morphological sharing index for the region under test is generated. This invention effectively addresses the shortcomings of existing measurement methods, such as lack of specificity for three-dimensional morphology and a single index system, and accurately reflects the true sharing potential of three-dimensional spatial units.

[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vitality prediction method based on urban three-dimensional spatial morphology, characterized in that, The method includes the following steps: Acquire the three-dimensional spatial unit morphology data and functional business type data of the target area; wherein, the three-dimensional spatial unit morphology data includes at least one of the building outlines of the ground floor, above-ground floor and underground floor of the target area, the outline of the outdoor public space and the outline of the above-ground connecting corridor, and the functional business type data is used to identify the use category or activity type of each three-dimensional spatial unit; The target area is divided into three-dimensional grids to generate multiple three-dimensional spatial units; Based on the morphological data of the three-dimensional spatial units and the functional business type data, a morphological index is determined for each three-dimensional spatial unit. The morphological index is used to represent multiple spatial morphological features of the three-dimensional spatial unit that affect behavioral sharing. Acquire crowd activity data for each of the three-dimensional spatial units, and determine a behavior sharing value based on the crowd activity data. The behavior sharing value is used to represent the mixed type and intensity of crowd activities within the three-dimensional spatial unit. The morphological index is used as the input feature, and the behavior sharing value is used as the training label to construct a training dataset. The training dataset is trained using a machine learning algorithm to determine the index weights corresponding to the morphological index. Based on the index weights and the morphological index of the region to be tested, a morphological sharing index of the region to be tested is generated. The step of dividing the target area into a three-dimensional mesh to generate multiple three-dimensional spatial units includes: According to the preset size, the multiple spatial layers of the target area are divided into planar grids to generate multiple grid units. The spatial layers include a ground layer, at least one above-ground layer, and at least one underground layer. The three-dimensional spatial unit is composed of grid cells with consistent planar coordinate ranges on different spatial layers. The step of acquiring crowd activity data for each of the three-dimensional spatial units and determining a behavior sharing value based on the crowd activity data includes: Acquire crowd activity data in the public spaces of the ground floor, above-ground floors, and underground floors of the target area. The crowd activity data includes activity type, activity quantity, and activity coordinates. Cluster analysis was performed on the crowd activity data to obtain the cluster type, number of clusters, and cluster coordinates for each layer and time period; The public spaces of the ground floor, above-ground floor, and underground floor are divided into multiple grid units. Based on the cluster type, the number of clusters, and the cluster coordinates, the behavior occupancy rate of each grid unit in each time period is calculated. The behavior sharing value is determined based on the behavior occupancy rate and the activity type mixing degree.

2. The vitality prediction method based on urban three-dimensional spatial morphology according to claim 1, characterized in that, The morphological index includes the public space area index. Accessibility index of space and functional facilities index ; The public space area index It can be calculated using the formula: ; In the formula, For the first The public space area index of each three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For the first The area of ​​the public space on each floor; The space can reach accessibility index It can be calculated using the formula: ; In the formula, For the first The spatial accessibility index of each three-dimensional spatial unit. For the first The accessibility index of a three-dimensional spatial unit. For the first Vertical transportation weight of each three-dimensional spatial unit For the first Weight of horizontal ground elevation difference of each three-dimensional spatial unit; Among them, the In the formula The total number of floors covered by the three-dimensional space unit. For the first The reachability index of a layer grid cell; in, In the formula, For the first The total number of nodes in a layer of mesh cells. For the first Layer mesh cell removal The remaining nodes of 1 node for The shortest path distance to other nodes. For the first The center point of the layer grid cell; ; In the formula, For vertical transportation weights, For the first The total height difference of each three-dimensional spatial unit For the first The number of layers in a three-dimensional spatial unit; ; In the formula, For the first The horizontal ground elevation difference corresponding to each three-dimensional spatial unit For the first The total height of the podium of each three-dimensional space unit; The functional facilities index is calculated using the following formula: ; In the formula, For the first Functional facility index of each three-dimensional space unit For the first Functional diversity index of a three-dimensional spatial unit For the first The connectivity index of commercial facilities in a three-dimensional spatial unit For the first Functional visibility index of a three-dimensional spatial unit These are the coefficients of the corresponding indices; in, = ; In the formula, For the first The sum of the number of various functional business types contained in each spatial layer within a three-dimensional spatial unit. No. The total number of layers in a three-dimensional spatial unit; = ; In the formula, For the first The connectivity index of commercial facilities in a three-dimensional spatial unit The total number of floors covered by the three-dimensional space unit. For this three-dimensional spatial unit in the first The reachability distance from the center point of the layer grid to the nearest commercial service facility; ; In the formula, For the first Functional visibility index of a three-dimensional spatial unit For the first The functional visibility index of the layer The total number of floors covered by the three-dimensional space unit. In the formula, The first point is the view that a pedestrian standing at the entrance of a street or plaza can directly observe from a horizontal, unobstructed viewpoint. The length of the boundaries of the commercial windows, shop entrances / exits, or outdoor commercial areas on each floor. The first of each three-dimensional spatial unit The total length of the public space boundary of the floor.

3. The vitality prediction method based on urban three-dimensional spatial morphology according to claim 1, characterized in that, The step of determining the behavior sharing value based on the behavior occupancy rate and activity type mixing degree includes: Based on behavior share Mixed activity types The behavioral sharing value of each of the three-dimensional spatial units in each time period is calculated according to the following formula. : ; In the formula, For the first Each three-dimensional spatial unit in time period Unit behavior occupancy rate For the first Each three-dimensional spatial unit in time period Activity type mix For the first Each three-dimensional spatial unit in time period Shared behavioral values; right Summing is performed to obtain the behavioral shared value for each of the three-dimensional spatial units: ; In the formula, For the first A preset time period The total number of preset time periods. For the first A three-dimensional spatial unit, For the first Each three-dimensional spatial unit in time period Shared values ​​for behavior.

4. The vitality prediction method based on urban three-dimensional spatial morphology according to claim 2, characterized in that, The training dataset is trained using a machine learning algorithm to determine the index weights corresponding to the morphological index, including: Multiple morphological indices are divided into a core influence index group and a secondary influence index group; Determine the first correlation sum between the core influence index group and the behavioral sharing value; Determine the second correlation sum between the auxiliary influence index group and the behavioral sharing value; The weight allocation ratio between the core influence index group and the auxiliary influence index group is determined based on the ratio of the first correlation sum to the second correlation sum. The index weight corresponding to the morphological index is determined based on the weight allocation ratio.

5. The vitality prediction method based on urban three-dimensional spatial morphology according to claim 1, characterized in that, If the area to be tested is an undeveloped area, the method also includes: Obtain the morphological sharing index of each three-dimensional spatial unit within the test area, and determine the spatial sharing potential level based on the morphological sharing index; The spatial sharing potential level is used as the vitality prediction result of the area to be tested.

6. The vitality prediction method based on urban three-dimensional spatial morphology according to claim 5, characterized in that, The determination of spatial sharing potential level based on the morphological sharing index includes: Establish a case library containing multiple completed and stable operating reference cases. Each reference case is associated with and stored with its morphological index set, surrounding environment morphological index set, scale and type attributes, and operation stage tags. Based on the case library, determine the similarity between the region to be tested and each reference case; Based on the similarity ranking, a preset number of reference cases are selected to form a reference case group; Based on historical data of the morphological index and behavioral sharing values ​​of each reference case in the reference case group, a model for predicting the vitality of the area to be tested is constructed. Obtain the set of morphological indices for the region to be tested, input them into the model used to predict the vitality of the region to be tested, and obtain the initial vitality prediction value. The space-sharing potential level is determined based on the initial vitality prediction value.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the vitality prediction method based on urban three-dimensional spatial morphology as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an executable program, which is executed by a processor to implement the vitality prediction method based on urban three-dimensional spatial morphology as described in any one of claims 1 to 6.

Images