Resident sharing oriented community public space intelligent optimization design method and system

Abstract

The invention provides a resident sharing oriented community public space intelligent optimization design method and system, and the method comprises the steps: obtaining real track sets and environment data of different groups, filling a data sparsity blind area through employing a conditional generative adversarial network, and generating space-time thermodynamic diagrams of different group behaviors. Then, based on a space-time diagram convolutional network, fusing a grid topology, a thermodynamic diagram and a social association matrix, and analyzing a demand priority map; and coupling cross-modal features by adopting a dual-channel deep learning architecture, and generating physical design parameters conforming to constraints through a bidirectional attention mechanism. According to the method, the confrontation generation network is used for enhancing data, the physical fidelity of the space-time thermodynamic diagram is improved, and different group behaviors and space-time data are fused to overcome the priority deviation of public space design caused by subjective weight distribution. And finally, fusing a spatial topology gradient and a group behavior evolution rule by cross-modal feature fusion, thereby improving demand response precision and dynamic adaptability of public space optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electric digital data processing, in particular to a community public space intelligent optimization design method and system oriented to resident sharing. BACKGROUND

[0002] The mainstream scheme of current public space reconstruction mainly adopts a static environment behavior analysis method. The scheme records the activity mode of residents through artificial questionnaire survey and fixed-point observation, marks the facility distribution combined with the two-dimensional CAD site map, and divides the functional area (such as the rest area and the passing area) by using a simple clustering algorithm. The environmental analysis relies on historical meteorological data and simple thermal comfort indicators, and the reconstruction parameters are artificially set based on the standard. The optimization process adopts a linear programming model to allocate the number of set parameters with the minimum cost as the target, and the output result is a static layout drawing and a material list. Although this method can realize basic function configuration, the data processing and design decision present an open-loop structure, the spatiotemporal resolution of the behavior data obtained artificially is low and the sample size is limited, it is difficult to capture the dynamic interaction rules of different groups, leading to the distortion of the heat map; secondly, the demand analysis relies on the subjective questionnaire weight, and the correlation model between the spatiotemporal behavior characteristics and the physical space is not established, resulting in that the priority atlas ignores the sharing demand of different groups; finally, the parameter generation lacks a cross-modal coupling mechanism, and the spatial topology gradient is not included in the channel accessibility calculation, causing the misalignment of the facility layout and the real behavior flow line, so that the reconstruction effect of the community public space is difficult to meet the demand of most residents. SUMMARY

[0003] In view of the above, the present application provides a community public space intelligent optimization design method and system oriented to resident sharing, which is used to solve at least one of the above technical problems.

[0004] The present application is realized by the following technical scheme. On the one hand, the present application provides a community public space intelligent optimization design method oriented to resident sharing, which comprises a data processing stage, a demand characteristic solving stage, a space-behavior coupling stage and a design parameter decoding stage.

[0005] In the data processing stage, the following steps are performed:

[0006] S11: Obtain a real trajectory set of a plurality of different groups of users in a preset continuous time window, and perform conditional adversarial generation fitting according to the real trajectory set to obtain an enhanced trajectory set; S12: Obtain environment data of a space to be optimized to generate original point cloud data; and generate a grid space and a corresponding spatial topology matrix according to the original point cloud data and the boundary of the space to be optimized, wherein the grid space comprises a plurality of grid units, and each grid unit comprises a center coordinate and a grid size; S13: Obtain environment element data in a preset continuous time window to construct an environment feature tensor; In the demand feature solving phase, the following steps are performed: S21A: calculating a social correlation matrix according to the spatiotemporal distribution characteristics of the social situations of different groups of the enhanced trajectory set in the grid space; S21B: generating a heat value of each grid cell by a kernel density estimation method according to the enhanced trajectory set and the center coordinates of the grid cell, to obtain a spatiotemporal heat map tensor of the enhanced trajectory set; S22: constructing a spatiotemporal graph node and a corresponding spatiotemporal feature vector of each grid cell according to the spatial topology matrix and the spatiotemporal heat map tensor, to obtain a spatiotemporal graph structure and a time causal matrix; S23: performing multi-level graph convolution and mapping on the spatiotemporal graph structure according to the social correlation matrix, the spatial topology matrix and the time causal matrix, to obtain a demand priority graph; In the space-behavior coupling phase, the following steps are performed: S31A: calculating a time sequence feature of each group according to the demand priority graph and the spatiotemporal heat map tensor, to obtain a group behavior feature vector; S31B: performing spatial convolution operation on the environment feature tensor after enhancement according to the demand priority graph, to obtain an environment spatial topology feature; S32: performing cross-modal feature fusion on the group behavior feature vector and the environment spatial topology feature, to obtain a fusion feature; In the design parameter decoding phase, the following steps are performed: S40: performing parameter decoding on the fusion feature through a fully connected network, to obtain an optimized design parameter.

[0007] Further, the step S21A includes: S21A.1: according to the enhanced trajectory set and the grid space, counting the number of occurrences of different groups in different grid cells in different time windows, to obtain a plurality of spatiotemporal distribution frequency vectors of different groups; S21A.2: constructing a social correlation matrix according to the spatiotemporal distribution frequency vectors between different groups.

[0008] Further, the construction formula of the social correlation matrix is as follows:

[0009]

[0010] wherein, is a group index, represents the appearance frequency of group in grid at time ​representing groups in the grid time the frequency of occurrence, is a normalization factor, is an indicator function, is the total number of time windows, is the grid space.

[0011] Further, the step S23 comprises: S231: performing multi-layer convolution processing on the spatio-temporal graph structure by a spatio-temporal convolution kernel constructed by the social association matrix, the spatial topology matrix and the time causal matrix to obtain group features; S232: performing global tie-breaking pooling on the group features to obtain a group representation vector; S233: performing full connection mapping and normalization processing on the group representation vector to obtain a priority graph.

[0012] Further, the step S31A comprises: S31A.1: performing group weighting processing on the heat map tensor according to the demand priority graph to obtain a weighted heat map of different groups in different grid cells at different time windows; S31A.2: performing spatial flattening on the weighted heat map of each group to obtain a one-dimensional time series of each group; S31A.3: sequentially extracting time series features from the one-dimensional time series of each group and performing time series maximum pooling to obtain a group behavior feature vector including a behavior feature vector of each group.

[0013] Further, the step S31B comprises: S31B.1: extracting a gradient field of a geometric model corresponding to the grid space; S31B.2: correcting and enhancing the environmental feature tensor and the gradient field according to the demand priority graph to obtain an enhanced environmental feature tensor of each group; S31B.3: sequentially performing convolution processing and global spatio-temporal average pooling on the enhanced environmental feature tensor of each group to obtain an environmental spatial topology feature including a spatial topology feature of each group.

[0014] Further, the resident-sharing-oriented community public space intelligent optimization design method further comprises: an iterative optimization phase, in which the following steps are performed: S51: calculating the group matching degree of the high-frequency activity area of each group according to the optimization design parameters, the spatio-temporal heat map tensor and the demand priority graph, and obtaining the global matching degree of the space to be optimized by weighted summation; S52: iteratively optimizing the optimization design parameters according to the global matching degree until the evaluation function converges, and outputting the final design parameters.

[0015] Further, the calculation formula of the global matching degree is as follows:

[0016]

[0017] Wherein, the is a high-frequency activity area set of the group , that is, a grid set whose heat value exceeds a preset threshold; is a demand weight of the group , is the total number of group categories, is the total number of time windows, is a vitality intensity function, is an environmental comfort function.

[0018] On the other hand, the present application also provides a resident sharing oriented community public space intelligent optimization design system, which comprises a data processing module, a demand feature solving module, a space-behavior coupling module and a design parameter decoding module. The data processing module comprises a user trajectory processing unit: used for obtaining a real trajectory set of multiple different group users in a preset continuous time window, and performing conditional adversarial generation fitting according to the real trajectory set to obtain an enhanced trajectory set; a space data processing unit: used for obtaining environmental data of a space to be optimized to generate original point cloud data; and generating a grid space and a corresponding space topology matrix according to the original point cloud data and the boundary of the space to be optimized, the grid space comprising a plurality of grid units, each grid unit comprising a center coordinate and a grid size; an environmental data processing unit: used for obtaining environmental element data in a preset continuous time window, and constructing an environmental feature tensor; The demand feature solving module comprises a social association matrix solving unit: used for calculating a social association matrix according to the spatiotemporal distribution characteristics of the social situation of different groups in the enhanced trajectory set in the grid space; a spatiotemporal heat map generation unit: used for generating a heat value of each grid unit by a kernel density estimation method according to the enhanced trajectory set and the center coordinates of the grid units, to obtain a spatiotemporal heat map tensor of the enhanced trajectory set; a spatiotemporal graph construction unit: used for constructing a spatiotemporal graph node and a corresponding spatiotemporal feature vector of each grid unit according to the space topology matrix and the spatiotemporal heat map tensor, to obtain a spatiotemporal graph structure and a time causal matrix; A demand priority graph generation unit is configured to perform multi-level graph convolution and mapping on the spatio-temporal graph structure according to the social association matrix, the spatial topology matrix and the time causality matrix, to obtain a demand priority graph; The space-behavior coupling module comprises a time sequence feature extraction unit configured to calculate time sequence features of each group according to the demand priority graph and the spatio-temporal heat map tensor, to obtain a group behavior feature vector; A space feature extraction unit is configured to perform spatial convolution operation on the environment feature tensor after enhancement according to the demand priority graph, to obtain environment spatial topology features; A modal fusion feature extraction unit is configured to perform cross-modal feature fusion on the group behavior feature vector and the environment spatial topology features, to obtain a fusion feature; A design parameter decoding module is configured to perform parameter decoding on the fusion feature through a fully connected network, to obtain optimized design parameters.

[0019] Further, the method further comprises an iterative optimization module comprising: A global matching degree calculation unit is configured to calculate a group matching degree of a high-frequency activity area of each group according to the optimized design parameters, the spatio-temporal heat map tensor and the demand priority graph, and to obtain a global matching degree of a space to be optimized through weighted summation; A matching degree iterative optimization unit is configured to perform iterative optimization on the optimized design parameters according to the global matching degree, until an evaluation function converges, and to output final design parameters.

[0020] The resident sharing oriented community public space intelligent optimization design method of the present application collects resident behavior trajectories and environment data through an integrated sensor network, solves the sparsity problem of behavior data in old communities by using a conditional generative adversarial network, and generates a high-precision spatio-temporal heat map. Based on a spatio-temporal graph convolution network, grid topology, heat maps and a social association matrix related to social behaviors of different groups are fused to analyze a normalized demand priority graph. A dual-channel deep learning architecture is used to couple cross-modal features, and a physical design parameter conforming to constraints is generated through a bidirectional attention mechanism. Finally, a vitality intensity and comfort quantification model is established to calculate an entropy weighted global matching degree, to drive gradient optimization iteration, and to output executable instructions and environment configurations. After deployment, real-time data closed loop verification is performed through the Internet of Things, and when the measured deviation exceeds a threshold value, the optimization process is automatically restarted, to realize continuous adaptive optimization of space reconstruction.

[0021] Therefore, compared with the prior art, the present application has the following advantages: 1. The conditional generative adversarial network is used to fill in data sparse areas, which significantly improves the physical fidelity and sample coverage of the spatio-temporal heat map.

[0022] 2. Introduce spatiotemporal graph convolutional networks to fuse gridded topology and social association matrices, so as to realize interpretable quantification of the interaction needs of different resident groups in the community, and overcome the priority bias in public space design caused by subjective weight allocation.

[0023] 3. By coupling cross-modal features with a bidirectional attention mechanism, the features are integrated with the spatial topological gradient and the evolution law of group behavior, ensuring that the generated optimized design parameters can meet the spatial distribution requirements and practical scenario requirements of most groups.

[0024] 4. The closed-loop verification mechanism is based on dynamic optimization and iteration of monitoring feedback to ensure that the transformation plan significantly improves the actual effect in the optimization application of public space, and automatically restarts the optimization process when the deviation exceeds the threshold, so as to continuously strengthen the vitality and sustainability of public space.

[0025] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0026] Figure 1 This is a structural block diagram of the resident-shared-oriented intelligent optimization design system for community public spaces according to the present invention; Figure 2 For execution Figure 1 The flowchart illustrates a resident-shared, oriented intelligent optimization design method for community public spaces in the system shown. Figure 3 for Figure 1 The diagram shown is a structural block diagram of the resident-shared community public space intelligent optimization design system after adding an iterative optimization module. Figure 4 To execute Figure 3 The execution flowchart of the iterative optimization module of the system shown is illustrated. Detailed Implementation

[0027] To address the shortcomings of existing public space optimization methods that rely on static questionnaires and manual analysis, this invention proposes a resident-shared-oriented intelligent optimization design method and system for community public spaces. This method and system can provide scientific and quantitative intelligent decision support for public space renovation, guided by the shared needs of user groups.

[0028] This invention uses the community redevelopment process as an example for illustration; please refer to [link / reference]. Figure 1The present invention relates to a resident-shared, community-oriented intelligent optimization design system for public spaces, which is connected to an integrated sensor network. Based on user trajectory data, spatial data of the space to be optimized, and environmental data collected by the integrated sensor network, the system performs analysis and decision-making. Specifically, the intelligent optimization design system includes: a data processing module, a demand feature solving module, a space-behavior coupling module, and a design parameter decoding module. The data processing module first preprocesses the acquired data and uses a conditional generative adversarial network to address the sparsity problem of behavioral data in older communities. The demand feature solving module generates a high-precision spatiotemporal heatmap from the data output of the data processing module. Then, based on a spatiotemporal graph convolutional network, it fuses the grid topology, heatmap, and social association matrix to parse a normalized demand priority map. The space-behavior coupling module employs a dual-channel deep learning architecture to couple cross-modal features. Finally, the design parameter decoding module decodes the fused features and outputs constrained physical design parameters for the design optimization of public spaces.

[0029] Please see Figure 2 The working process of each component of the community public space intelligent optimization design system based on resident sharing includes: In the data processing phase, each unit of the data processing module performs the following steps: The user trajectory processing unit 11 is used to perform step S11: obtain a set of real trajectories of various groups of users within a preset continuous time window, and perform conditional adversarial generation fitting based on the set of real trajectories to obtain an enhanced trajectory set.

[0030] The system tracks the daily movement trajectories of different residents within the community in real time using GPS positioning. The trajectory set is defined as follows: ,in This indicates the total number of individual residents surveyed, and a single trajectory. Includes time series data, where It's a timestamp. Indicates the index of the number of trajectory points. The number of trajectory points for each individual. Represents an individual At any moment The spatial coordinates are obtained using local coordinate system values. However, since the number of residents participating in the survey differs significantly from the number of people at different times, behavioral data augmentation is used to compensate for the sparsity of the original trajectories. Specifically, a Conditional Generative Adversarial Network (cGAN) is employed for high-density mapping. The cGAN consists of a generator... and discriminator Composition, generator input noise vector (in (representing standard Gaussian distribution) and conditional data (i.e., the original set of trajectories), output the generated trajectory. The generator employs a U-Net architecture, where the encoder extracts trajectory features and the decoder generates a new sequence of trajectory points. The discriminator, based on a convolutional network structure, distinguishes between real and generated input trajectories. The loss function is designed to ensure that the distribution of generated trajectories approximates the real distribution while maintaining spatial consistency; the adversarial loss function is defined as:

[0031] in, Represents the expectation operator. It is the actual data distribution. This is the noise distribution.

[0032] The reconstruction loss function is defined as:

[0033] in It is the L1 norm, which constrains the generation position. and measured position The deviation.

[0034] Total loss weighted combination is ,in, and Using typical weight values, priority is given to ensuring reconstruction accuracy to avoid spatial distortion. This yields the enhanced trajectory set. .

[0035] The spatial data processing unit 12 is used to perform step S12: acquire environmental data of the space to be optimized to generate raw point cloud data; and generate a grid space and a corresponding spatial topology matrix based on the raw point cloud data and the boundary of the space to be optimized. The grid space includes multiple grid cells, and each grid cell includes center coordinates and grid size.

[0036] Point cloud geometry is obtained by scanning raw point cloud data using LiDAR. .

[0037]

[0038] in, For point index, The total number of point clouds describes the three-dimensional geometric features of the space.

[0039] The acquired point cloud data is then preprocessed, including denoising and registration operations, to generate an accurate 3D spatial surface model. The model is then projected onto a two-dimensional ground plane and discretized into a mesh structure to accommodate behavioral analysis. Specifically, the space is divided into... There are 1 grid cells, each denoted as _____. ,in and These represent the row and column indices of the grid. The formula for calculating the center coordinates of a grid cell is as follows:

[0040] in, and This represents the total length and width of the space, with a typical mesh resolution of 0.5m × 0.5m to balance accuracy and computational efficiency. Topology connectivity is constructed by defining a spatial topology matrix. Implementation. Matrix elements satisfy the condition: when the mesh element... and Spatially adjacent (i.e.) and When there are 8 adjacent relationships, Otherwise, it is 0. This matrix is ​​subsequently used for spatial correlation modeling in spatiotemporal graph convolutional networks.

[0041] The environmental data processing unit 13 is used to perform step S13: acquire environmental element data of a preset continuous time window and construct an environmental feature tensor; Microclimate parameters are obtained by collecting time-series data using temperature and humidity sensors and anemometers. These represent temperature, humidity, and wind speed, respectively; environmental factors such as light intensity, noise, and vegetation cover data are acquired through dedicated sensors. The environmental feature tensor constructed from this foundational data is used to ensure the coupling of behavior with spatial input.

[0042] In the requirement feature solving phase, the execution flow of each component of the requirement feature solving module includes: The social association matrix solving unit 21A is used to perform step S21A: calculate the social association matrix based on the spatiotemporal distribution characteristics of the social situations of different groups in the enhanced trajectory set in the grid space.

[0043] Step S21A includes: S21A.1: Based on the enhanced trajectory set and the grid space, count the number of times different groups appear in different time windows of different grids to obtain the spatiotemporal distribution frequency vectors of multiple groups.

[0044] S21A.2: Construct a social association matrix based on the spatiotemporal distribution frequency vectors between different groups.

[0045] To quantify social connections between groups, define A group of residents. In this application, ( , , ), and construct the social connection matrix using the following formula :

[0046]

[0047] in, For group indexing, Representing a group In the grid time Frequency of occurrence Representing a group In the grid time Frequency of occurrence As the normalization factor, For indicator functions, The total number of time windows. This represents a grid space. This matrix reveals the co-occurrence patterns of the population, which will be subsequently mapped to a node-level graph structure.

[0048] The spatiotemporal heatmap generation unit 21B is used to perform step S21B: generate the thermal value of each grid cell based on the center coordinates of the enhanced trajectory set and the grid cell using the kernel density estimation method, and obtain the spatiotemporal heatmap tensor of the enhanced trajectory set.

[0049] High-density behavioral heatmap generation based on enhanced trajectories The spatiotemporal thermodynamic values ​​are calculated to quantify the density of resident behavior. Specifically, the kernel density estimation method is used for the calculation of grid cells. within a specific time window The internal thermal value is defined as:

[0050] in, It is the heat value. For grid cells, For the target time point, and These are individual resident indexes and trajectory point indexes, It is individual weight. Represents Euclidean distance. These are the coordinates of the grid center. Kernel function. Using Gaussian kernel ,in It is the normalized distance; bandwidth parameter To control the attenuation of spatial influence, a typical value is 1.5 times the grid side length, ensuring a smooth distribution of thermal values ​​in local areas. The time dimension is discretized into a full day. The final output is a spatiotemporal heatmap tensor for each time period. The complete encoding behavior is distributed spatiotemporally.

[0051] The spatiotemporal graph construction unit 22 is used to perform step S22: construct the spatiotemporal graph nodes of each grid unit and the corresponding spatiotemporal feature vectors based on the spatial topology matrix and the spatiotemporal heatmap tensor, so as to obtain the spatiotemporal graph structure and the time causality matrix.

[0052] High-density behavioral heatmap generated in the preceding sequence With spatial topological matrix By combining these elements, a spatiotemporal graph structure is constructed as the computational foundation. Spatiotemporal graph nodes are defined as follows: Each node Corresponding grid cell At time step ( The entity's feature vector integrates multidimensional information about its behavior and environment:

[0053] in, Statistical time window Entering the grid The number of residents, Calculate the average length of stay for individuals within the same time period. The calculation is performed by counting the frequency of instances where the minimum Euclidean distance between individuals is less than the interaction threshold. This is the thermal value output by the previous module. This is a microclimate vector.

[0054] The edge structure of the spatiotemporal graph contains dual associations. Spatial adjacency edges inherit the mesh topology matrix. At each time step Inside, if the grid cell and satisfy and (8 adjacency relationships) then establish an undirected edge and assign a basic weight. .

[0055] For time-related characteristics, the weights of the temporal causal edges are calculated. This is done in adjacent time steps. and Between, for the same grid cell The formula for calculating the weight of a directed edge with temporal causality is as follows:

[0056] in As the attenuation factor, t This represents the time window number. The temporal causal edge weight characterizes the continuous evolution of behavioral patterns. When two nodes are in the same grid cell and in adjacent time steps, the temporal causal edge weight is... Otherwise By traversing the temporal relationships of all nodes in the spatiotemporal graph, the weights of all temporal causal edges are obtained, and a temporal causal matrix is ​​generated. .

[0057] The demand priority graph generation unit 23 is used to perform step S23: perform multi-level graph convolution and mapping on the spatiotemporal graph structure according to the social association matrix, spatial topology matrix and temporal causality matrix to obtain the demand priority graph.

[0058] Step S23 includes: S231: The spatiotemporal graph structure is processed by a multi-layer convolutional process using a spatiotemporal convolutional kernel constructed from the social association matrix, spatial topology matrix and temporal causality matrix to obtain group features.

[0059] Spatiotemporal graph convolution operations extract desired features by hierarchically aggregating neighborhood information. The layer feature update formula is:

[0060] in, For the first Layer node feature matrix, convolution kernel set These correspond to three types of adjacency matrices, including spatial adjacency matrices. ( (For degree matrix, achieve symmetric normalization) Time causality matrix Preserving directionality, social connection matrix By Give to all who belong to the group and Node pairs, parameter matrix Trainable The ReLU activation function is used. After multiple convolutional layers, the group features are obtained. .

[0061] S232: Perform global flat pooling on the group features to obtain the group representation vector; group characteristics The vectors are aggregated into a group-level representation vector using global average pooling:

[0062]

[0063] S233: Perform fully connected mapping and normalization on the group representation vector to obtain the priority map.

[0064] Mapping to requirement priority scores via a fully connected layer:

[0065] in, 、 、 These are trainable parameters. The obtained priority scores are then normalized using Softmax to satisfy the following condition:

[0066]

[0067] Finally, a demand priority map was obtained. This heatmap quantitatively characterizes the weight allocation of each group in the optimization of public space. Its output strictly adheres to spatiotemporal topological constraints and social relevance, providing interpretable decision input for the space-behavior coupled optimization module. In this step, the heatmap... Provides behavioral density and spatial grid topology. Define spatial adjacency and temporal causal edge weights. To ensure the continuity of behavioral evolution, the social matrix Softmax normalization forces the elimination of population cardinal bias by normalizing frequency. Avoid optimizing for divergent goals.

[0068] In the spatial-behavior coupling phase, the execution flow of each component of the spatial-behavior coupling module includes: The temporal feature extraction unit 31A is used to perform step S31A: calculate the temporal features of each group based on the demand priority map and the spatiotemporal heat map tensor to obtain the group behavior feature vector.

[0069] Step S31A includes: S31A.1: Performing group weighting processing on the heat map tensor according to the demand priority map to obtain weighted heat maps of different groups in different time windows of different grid cells; Based on demand priority map The spatiotemporal heatmap is subjected to group weighting. The weighted heatmap value of each point in the weighted heatmap of any group is calculated using the following formula:

[0070]

[0071] Among them, the For the group spatiotemporal coverage Here, t represents the spatial grid coordinates, and t represents the time window number. For the group Priority map.

[0072] S31A.2: Spatially flatten the weighted heatmap of each group to obtain a one-dimensional time series for each group.

[0073] Flatten the 3D weighted heatmap using the following formula:

[0074] in This represents the overall spatial behavior density, where T is the total number of time windows.

[0075] S31A.3: Sequentially extract time series features from the one-dimensional time series of each group and perform time series max pooling to obtain a group behavior feature vector that includes the behavior feature vector of each group.

[0076] Temporal features are extracted using an LSTM encoder, and the cell state update mechanism is as follows:

[0077]

[0078] in, For input gate, For the Gate of Oblivion For output gate, This involves element-wise multiplication. The final group behavior feature vector is obtained through temporal max pooling. .

[0079] The spatial feature extraction unit 31B is used to perform step S31B: after enhancing the environmental feature tensor according to the demand priority map, perform spatial convolution operation to obtain environmental spatial topological features.

[0080] Specifically, step S31B includes: S31B.1: Extract the gradient field of the geometric model corresponding to the grid space.

[0081] S31B.2: The environmental feature tensor and gradient field are modified and enhanced according to the demand priority map to obtain the enhanced environmental feature tensor for each group.

[0082] The demand weights are combined with the spatial geometric gradient. The environmental feature tensor is enhanced as follows:

[0083] in ， Geometric model corresponding to the grid space The gradient field.

[0084] S31B.3: Sequentially perform convolution processing and global spatiotemporal average pooling on the enhanced environmental feature tensor of each group to obtain environmental spatial topology features including the spatial topology features of each group.

[0085] Feature extraction using a three-layer 3D-CNN encoder:

[0086]

[0087] in, Represents a three-dimensional convolution operation. The kernel is used for convolution. Global spatiotemporal average pooling is then applied to obtain the environmental spatial topological features.

[0088] The modal fusion feature extraction unit 32 is used to perform step S32: cross-modal feature fusion of the group behavior feature vector and the environmental spatial topology features to obtain fused features.

[0089] Cross-modal feature fusion employs a bidirectional cross-channel attention mechanism. The behavior-to-space attention module uses behavioral features as queries and spatial features as keys.

[0090] Space → Behavioral Attention operates in reverse:

[0091] in, ， ， This is the projection matrix. The final fused feature is... ( (Indicates splicing).

[0092] The design parameter decoding module 40 is used to perform step S40: decode the fused features through a fully connected network to obtain optimized design parameters.

[0093] Parametric design decoding is implemented through a fully connected network:

[0094] in, This includes physical design parameters such as rest facility density, main passage width, shading coverage, and vegetation bandwidth. To meet engineering constraints, a differentiable projection operator is embedded in the output layer, including boundary constraints. and normalization constraints ( (For mutually exclusive parameter groups).

[0095] The closed-loop optimization mechanism is implemented using a differentiable surrogate evaluator. This applies to the weighted aggregation scheme. Calculate the overall score:

[0096] Among them, the spatial vitality function Predicting future usage density using an LSTM-based behavioral simulator, thermal comfort function The PMV index is calculated by integrating microclimate models. Iterative optimization is performed using gradient ascent.

[0097] The final output is standardized design instructions, geometric parameters are converted into BIM entities in IFC format, and material parameters are generated into XML configuration files (defining vegetation reflectivity and the thermal conductivity of shading materials). Requirements Map The weighting mechanism ensures fairness within the group, heatmap The time step and grid size are consistent with the spatiotemporal graph convolution module. Spatial gradient. The mesh topology, derived from the point cloud geometry processing module, ensures geometric continuity.

[0098] Please see Figure 3 In a preferred embodiment, the resident-shared community public space intelligent optimization design system further includes an iterative optimization module, which iteratively optimizes the optimization design parameters output by the design parameter decoding module. The execution flow of each component of the iterative optimization module is as follows: Figure 4 As shown, the details are as follows: The global matching degree calculation unit 51 executes step S51; it is used to calculate the group matching degree of the high-frequency activity area of ​​each group according to the optimization design parameters, spatiotemporal heat map tensor, and demand priority map, and obtain the global matching degree of the space to be optimized by weighted summation.

[0099] This step involves generating parameterized design vectors using preorder space-behavior coupling optimization. Using the demand priority graph as the core input. Spatiotemporal behavior heatmap and environmental feature tensors This involves establishing a mapping relationship between design parameters and spatial performance. Its core lies in quantifying the matching degree of design schemes to the needs of different groups and generating executable engineering instructions.

[0100] First, perform matching metric optimization and design parameters. Spatial performance is evaluated using two key metrics: vitality intensity and environmental comfort. Vitality intensity... Comprehensive behavioral density facility density （ The number of rest facilities per unit area, and accessibility of pathways (path width) With spatial topological gradient The product of (the product of the two elements) is standardized to a value in the interval [0,1] by the Sigmoid function. Environmental comfort Integrated thermodynamic indicators PMV and shading coverage With solar radiation The interaction effect and vegetation bandwidth noise The attenuation effect.

[0101] Group-level matching degree Focus Group High-frequency activity area (defined as the heat value continuously exceeding a threshold) (grid set), by demand weight The weighted performance of vitality and comfort is used to calculate the overall matching degree, as follows:

[0102]

[0103] Among them, the For the group The set of high-frequency activity areas, that is, the set of grids whose thermal values ​​exceed a preset threshold; For the group Demand weight, The total number of group types The total number of time windows. Let the vitality intensity function be... The environmental comfort function is used. The global matching degree adopts an entropy-weighted form, and the sensitivity to the needs of small groups is enhanced through logarithmic transformation, avoiding design bias towards the mainstream group.

[0104] The matching degree iterative optimization unit 52 executes step S52: iteratively optimizing the optimization design parameters based on the global matching degree until the evaluation function converges and outputs the final design parameters.

[0105] Finally, based on the gradient ascent strategy and matching degree feedback, the parameters are continuously adjusted, and the update formula is as follows:

[0106] in, For learning rate, To suppress overfitting, an L2 regularization term is used. The optimization process must enforce physical boundary constraints and geometric conflict constraints. Physical boundary constraints are ensured through projection operators that physical parameters remain within the feasible region (e.g., the lower limit of channel width). Meet the standards, maximum facility density (To prevent overcrowding). Geometric conflict constraints are based on Voronoi diagrams and repulsion field algorithms to iteratively adjust facility locations, ensuring minimum spacing.

[0107] Corrected parameters Convert geometric instructions to IFC format and environment instructions to XML format. The geometric instructions will include the site elevation gradient. Mapped to the `IfcSite` entity in Building Information Modeling (BIM), aisle width The topology properties of the `IfcPath` object are written, and the coordinates of the rest facilities are generated using the Poisson disk sampling algorithm and output as an `IfcBuildingElementProxy` instance. The environment directive defines the reflectivity of the shading structure. And based on vegetation bandwidth Plant communities are configured in a hierarchical manner.

[0108] After deployment, real-world data is collected via IoT sensors. Calculate the prediction bias of the matching degree .like If this is not the case, closed-loop optimization will be initiated. The optimization process first integrates the measured heatmap. Secondly, spatiotemporal graph convolutional networks are used to correct the group weights. and with Restart the coupling optimization process with initial values. The iterative process is determined by the evaluation function. Driven by the Adam optimizer, the solution is solved until convergence.

[0109] In summary, the resident-shared-oriented intelligent optimization design method for community public spaces of this invention collects resident behavior trajectories and environmental data through an integrated sensor network. It utilizes conditional generative adversarial networks to address the sparsity of behavioral data in older communities, generating a high-precision spatiotemporal heatmap. Based on a spatiotemporal graph convolutional network, it fuses grid topology, heatmaps, and social association matrices related to the social behaviors of different groups to parse a normalized demand priority map. A dual-channel deep learning architecture couples cross-modal features, generating constrained physical design parameters through a bidirectional attention mechanism. Finally, a quantification model for vitality intensity and comfort is established to calculate the entropy-weighted global matching degree, driving gradient optimization iteration and outputting executable instructions and environmental configurations. After deployment, real-time data from the Internet of Things provides closed-loop verification. When the measured deviation exceeds a threshold, the optimization process is automatically restarted, achieving continuous adaptive optimization of space transformation.

[0110] Therefore, the present invention has the following advantages compared to the prior art: 1. Conditional generative adversarial networks are used to fill the data sparsity blind spots, significantly improving the physical fidelity and sample coverage of spatiotemporal heatmaps.

[0111] 2. Introduce spatiotemporal graph convolutional networks to fuse gridded topology and social association matrices, so as to realize interpretable quantification of the interaction needs of different resident groups, thereby overcoming the priority bias in public space design caused by subjective weight allocation.

[0112] 3. By coupling cross-modal features with a bidirectional attention mechanism, the features are integrated with the spatial topological gradient and the evolution law of group behavior, ensuring that the generated optimized design parameters can meet the spatial distribution requirements and practical scenario requirements of most groups.

[0113] 4. The closed-loop verification mechanism is based on dynamic optimization and iteration of monitoring feedback to ensure that the transformation plan significantly improves the actual effect in the optimization application of public space, and automatically restarts the optimization process when the deviation exceeds the threshold, so as to continuously strengthen the vitality and sustainability of public space.

[0114] The embodiments described above are merely examples of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and the present invention also intends to include these modifications and variations.

Claims

1. A resident sharing oriented community public space intelligent optimization design method, characterized in that, Comprise: a data processing stage, a demand feature solving stage, a space-behavior coupling stage, and a design parameter decoding stage; In the data processing stage, the following steps are performed: S11: Obtain a plurality of different groups of user real trajectory sets in a preset continuous time window, and perform conditional adversarial generation fitting according to the real trajectory sets to obtain an enhanced trajectory set; S12: Obtain environment data of a space to be optimized to generate original point cloud data; and generate a grid space and a corresponding space topology matrix according to the original point cloud data and the boundary of the space to be optimized, the grid space comprising a plurality of grid units, each grid unit comprising a center coordinate and a grid size; S13: Obtain environment element data in a preset continuous time window to construct an environment feature tensor; In the demand feature solving stage, the following steps are performed: S21A: Calculate a social association matrix according to the spatiotemporal distribution characteristics of the social situations of different groups in the grid space in the enhanced trajectory set; S21B: Generate a heat value of each grid unit by kernel density estimation method according to the enhanced trajectory set and the center coordinates of the grid units to obtain a spatiotemporal heat map tensor of the enhanced trajectory set; S22: Construct a spatiotemporal graph node and a corresponding spatiotemporal feature vector of each grid unit according to the space topology matrix and the spatiotemporal heat map tensor to obtain a spatiotemporal graph structure and a time causal matrix; S23: Perform multi-level graph convolution and mapping on the spatiotemporal graph structure according to the social association matrix, the space topology matrix, and the time causal matrix to obtain a demand priority graph; In the space-behavior coupling stage, the following steps are performed: S31A: Calculate a time sequence feature of each group according to the demand priority graph and the spatiotemporal heat map tensor to obtain a group behavior feature vector; S31B: Perform spatial convolution operation on the environment feature tensor after enhancement according to the demand priority graph to obtain an environment space topology feature; S32: Perform cross-modal feature fusion on the group behavior feature vector and the environment space topology feature to obtain a fusion feature; In the design parameter decoding stage, the following steps are performed: S40: Perform parameter decoding on the fusion feature through a fully connected network to obtain an optimized design parameter.

2. The resident-share-oriented community public space intelligent optimization design method according to claim 1, characterized in that, The step S21A comprises: S21A.1: According to the enhanced trajectory set and the grid space, count the number of appearances of different groups in different grid units in different time windows to obtain a plurality of spatiotemporal distribution frequency vectors of different groups; S21A.2: Construct a social association matrix according to the spatiotemporal distribution frequency vectors between each two groups. 3.The resident-share-oriented community public space intelligent optimization design method according to claim 2, characterized in that, The construction formula of the social association matrix is as follows: wherein, is a group index, denotes a group in a grid time frequency of occurrence, denotes a group in a grid time frequency of occurrence, is a normalization factor, is an indicator function, is the total number of time windows, is a grid space.

4. The resident-share-oriented community public space intelligent optimization design method according to claim 3, characterized in that, The step S23 comprises: S231: Perform multi-level convolution processing on the spatiotemporal graph structure through a spatiotemporal convolution kernel constructed by the social association matrix, the space topology matrix, and the time causal matrix to obtain a group feature; S232: Perform global tie-breaking pooling on the group feature to obtain a group representation vector; S233: Perform fully connected mapping and normalization processing on the group representation vector to obtain a priority graph.

5. The resident-share-oriented community public space intelligent optimization design method according to claim 4, characterized in that, The step S31A comprises: S31A.1: group-weighting the heat map tensor according to the demand priority atlas, to obtain a weighted heat map of different groups in different grid cells in different time windows; S31A.2: spatially flattening the weighted heat map of each group to obtain a one-dimensional time series of each group; S31A.3: sequentially extracting time sequence features from the one-dimensional time series of each group and performing time sequence max-pooling to obtain a group behavior feature vector including a behavior feature vector of each group.

6. The resident-share-oriented community public space intelligent optimization design method according to claim 5, characterized in that, The step S31B includes: S31B.1: extracting a gradient field of a geometric model corresponding to the grid space; S31B.2: correcting and enhancing the environmental feature tensor and the gradient field according to the demand priority atlas to obtain an enhanced environmental feature tensor of each group; S31B.3: sequentially performing convolution processing and global spatio-temporal average pooling on the enhanced environmental feature tensor of each group to obtain an environmental spatial topology feature including a spatial topology feature of each group.

7. The resident-share-oriented community public space intelligent optimization design method according to any one of claims 1-6, characterized in that, Further comprising: an iterative optimization phase, in which the following steps are performed: S51: calculating a group matching degree of a high-frequency activity area of each group according to the optimization design parameter, the spatio-temporal heat map tensor, and the demand priority atlas, and obtaining a global matching degree of the space to be optimized by weighted summation; S52: iteratively optimizing the optimization design parameter according to the global matching degree until the evaluation function converges, and outputting the final design parameter.

8. The resident-share-oriented community public space intelligent optimization design method according to claim 7, characterized in that, The calculation formula of the global matching degree is as follows: Among them, the For the group The set of high-frequency activity areas, that is, the set of grids whose thermal values ​​exceed a preset threshold; For the group Demand weight, The total number of group types The total number of time windows. Let the vitality intensity function be... This is a function for environmental comfort.

9. A resident sharing oriented community public space intelligent optimization design system, characterized in that, It includes: a data processing module, a demand feature solving module, a space-behavior coupling module, and a design parameter decoding module; The data processing module includes: a user trajectory processing unit: configured to obtain a real trajectory set of a plurality of different groups of users in a preset continuous time window, and to perform conditional adversarial generation fitting according to the real trajectory set to obtain an enhanced trajectory set; a spatial data processing unit: configured to obtain environmental data of a space to be optimized to generate original point cloud data; and to generate a grid space and a corresponding spatial topology matrix according to the original point cloud data and the boundary of the space to be optimized, the grid space including a plurality of grid cells, each grid cell including a center coordinate and a grid size; an environmental data processing unit: configured to obtain environmental element data in a preset continuous time window to construct an environmental feature tensor; The demand feature solving module includes: a social association matrix solving unit: configured to calculate a social association matrix according to the spatio-temporal distribution characteristics of the social situation of different groups in the grid space based on the enhanced trajectory set; a spatio-temporal heat map generation unit: configured to generate a heat value of each grid cell by a kernel density estimation method based on the enhanced trajectory set and the center coordinates of the grid cells to obtain a spatio-temporal heat map tensor of the enhanced trajectory set; a spatio-temporal graph construction unit: configured to construct a spatio-temporal graph node and a corresponding spatio-temporal feature vector of each grid cell based on the spatial topology matrix and the spatio-temporal heat map tensor to obtain a spatio-temporal graph structure, a time causal matrix, and a time causal matrix; The demand priority graph generation unit is configured to perform multi-level graph convolution and mapping on the space-time graph structure according to the social association matrix, the space topology matrix and the time causality matrix, to obtain a demand priority graph; The space-behavior coupling module includes: a time sequence feature extraction unit configured to calculate time sequence features of each group according to the demand priority graph and the space-time heat map tensor, to obtain a group behavior feature vector; The space feature extraction unit is configured to perform spatial convolution operation on the environment feature tensor after enhancement according to the demand priority graph, to obtain environment space topology features; The modality fusion feature extraction unit is configured to perform cross-modality feature fusion on the group behavior feature vector and the environment space topology features, to obtain a fusion feature; The design parameter decoding module is configured to perform parameter decoding on the fusion feature through a fully connected network, to obtain an optimized design parameter. 10.The resident-share-oriented community public space intelligent optimization design system according to claim 9, characterized in that, Further comprising: The iterative optimization module includes: A global matching degree calculation unit configured to calculate a group matching degree of a high-frequency activity area of each group according to the optimized design parameter, the space-time heat map tensor and the demand priority graph, and to obtain a global matching degree of the space to be optimized through weighted summation; The matching degree iterative optimization unit is configured to perform iterative optimization on the optimized design parameter according to the global matching degree, until an evaluation function converges, and to output a final design parameter.

Images