Street activity evaluation and optimization method based on street seat space, storage medium, device and equipment

Abstract

The invention provides a street activity evaluation and optimization method, device and equipment based on a street seat space, and a storage medium, and the method comprises the steps: collecting the multi-modal data of street layout, seat distribution and crowd activity, combining with the image recognition and behavior recognition technology, extracting the quantitative indexes of the seat body, the seat space and the street environment, and carrying out the evaluation of the activity of a street. And a spatial domain weight model is constructed, and a spatial activity intensity value is calculated. Key factors influencing the street vitality are recognized through the correlation analysis model, and seat arrangement optimization suggestions are generated accordingly. According to the method, refined evaluation and visual analysis of the street space vitality are realized, scientificity and pertinence of street space design are improved, the problem that an existing evaluation method lacks analysis of the interaction relation between crowd behaviors and space is effectively solved, and the street space utilization rate and the public space vitality level are improved.

Description

Technical Field

[0001] This invention relates to the technical field of urban space assessment and intelligent optimization, specifically to a method, storage medium, device, and equipment for assessing and optimizing street vitality based on street seating space. Background Technology

[0002] In existing urban spatial assessment technologies, quantitative research on street space vitality remains significantly insufficient. Traditional assessment methods often rely on subjective surveys or small-sample observations, making it difficult to comprehensively reflect space usage and population activity characteristics. While some recent studies have attempted to incorporate unstructured information such as social media images and street view data for auxiliary analysis, a systematic technical approach is still lacking in data integration, feature extraction, and quantitative modeling. Particularly at the level of street furniture, such as seating, the interaction between micro-spatial elements and population behavior has not yet formed an operational assessment index system. In existing technologies, image recognition is mostly used for single-target detection, failing to effectively combine spatial morphology and behavioral data for multi-dimensional modeling, resulting in assessment results lacking depth and interpretability. Furthermore, the identification of factors influencing spatial vitality often remains at the qualitative descriptive level, lacking quantitative analysis methods based on statistical significance. Therefore, a comprehensive technical solution integrating image recognition, spatial modeling, and data analysis is urgently needed to achieve scientific assessment and design optimization guidance for street space vitality. Summary of the Invention

[0003] Based on this, in order to address the technical problems of existing urban street space vitality assessment methods lacking a detailed analysis of the relationship between people's behavior and spatial interaction, making it difficult to effectively guide the optimization design and resource allocation of street seating spaces, resulting in low street space utilization and insufficient public space vitality, a street vitality assessment and optimization method, storage medium, device, and equipment based on street seating space are proposed.

[0004] This invention protects a method for assessing and optimizing street vitality based on street seating space, applied to a computer server, comprising the following steps: collecting multi-source data to obtain multimodal data on street layout, seating distribution, and crowd activity; using image recognition and spatial data processing technologies to preprocess and extract features from the acquired multimodal data to obtain multiple quantitative indicators for assessing spatial vitality; identifying crowd size and behavior types based on image detection algorithms and behavior recognition models, and constructing a spatial domain weight model in conjunction with spatial location information; calculating the spatial vitality intensity value of the target area based on the identification results and the weight model; analyzing the correlation between quantitative indicators and spatial vitality intensity, identifying key factors affecting street spatial vitality, and providing feedback on seating arrangement optimization suggestions based on these key factors.

[0005] Furthermore, the quantitative indicators include evaluation indicators at the level of the seat itself, the level of the seat space, and the level of the street environment. Among them, the quantitative indicators at the level of the seat itself include seat type and seat continuity; the quantitative indicators at the level of the seat environment include the spatial form of the seat and whether lighting facilities are installed; and the quantitative indicators at the level of the street environment include green view rate and spatial openness.

[0006] Furthermore, at the seat body level, seat types are quantified numerically, with different numerical values ​​for different seat types input through the configuration page; image recognition is used to calculate and determine the seat continuity based on the angle and physical distance between adjacent seats; at the seat environment level, the spatial form types of the seats include six types: eaves (located under the eaves of a building), recessed (embedded in the building's gray space, forming a visual barrier on one side), platform (relying on the steps in front of shops), mixed (a composite of multiple spaces, composed of eaves, recesses, or platforms), terraced (without building support behind), and open (no visual obstruction, supporting multi-directional crowd activity), with data for different form types configured through the configuration page; whether seats are equipped with lighting facilities is represented by binary quantization, with the matching values ​​of lighting facilities for seats corresponding to different photos determined through image recognition; at the street environment level, the green view rate is calculated using image recognition technology, with the specific formula as follows:

[0007]

[0008] Where, N photo,j S represents the number of valid images captured at the j-th seat space. l,i Let S represent the area of ​​the green plants in the i-th image. p,i This represents the total area of ​​the i-th image;

[0009] The spatial openness is calculated using image recognition technology to determine the proportion of the sky area, with the specific formula as follows:

[0010]

[0011] Among them, S b,i S represents the area of ​​the sky region in the i-th image. p,i Let represent the total area of ​​the i-th image.

[0012] Furthermore, based on image detection algorithms and behavior recognition models, the number of people and their behavior types are identified, and a spatial domain weight model is constructed by combining spatial location information. Based on the identification results and the weight model, the spatial vitality intensity value of the target area is calculated, including: detecting the number of people (n) in each valid image using image recognition algorithms. i Furthermore, by combining a behavior recognition model to identify crowd behavior types, the influence weight ω of different behavior types on spatial vitality intensity is determined. tThe space surrounding the seats is divided into five spatial domains: seating domain, intimate domain, personal distance, social distance, and public distance. The influence weight ω of each spatial domain on the intensity of spatial vitality is determined based on the frequency of human behavior within each domain. n Calculate the vitality intensity value of the seat space at position j using the following formula:

[0013]

[0014] Among them, S j N represents the area of ​​the seating space. photo,j This represents the number of valid images.

[0015] Furthermore, the analysis of the correlation between quantitative indicators and spatial vitality intensity specifically includes: taking each quantitative indicator as the dependent variable and spatial vitality intensity as the independent variable, and inputting the dependent and independent variables into the correlation analysis model; if the model determines that the correlation probability is less than the significance level, it is determined that there is a significant correlation between the quantitative indicators and spatial vitality intensity; otherwise, it is determined that there is no significant correlation between the quantitative indicators and spatial vitality intensity.

[0016] Furthermore, the correlation analysis model includes Pearson correlation coefficient analysis and Spearman rank correlation coefficient analysis. It determines whether the quantitative indicator data conforms to a normal distribution; if so, Pearson correlation coefficient analysis is used to calculate the correlation between the indicator and the intensity of space vitality. When the quantitative indicator data does not conform to a normal distribution or is qualitative data, Spearman rank correlation coefficient analysis is used to calculate the correlation between the indicator and the intensity of space vitality. Based on the correlation analysis results, a correlation probability value is output, and the existence of a significant correlation is determined based on the correlation probability value.

[0017] Furthermore, if it is determined that there is a significant correlation between the quantitative indicator and the spatial vitality intensity, the control result of the quantitative indicator is output, and it is determined whether the current quantitative indicator value is within the control result range; if the current quantitative indicator value is not within the control result range, seat optimization suggestions based on street vitality assessment are fed back to the computer front end.

[0018] This invention protects a street vitality assessment and optimization device based on street seating space, comprising: a data acquisition module for acquiring multimodal data related to street layout, seating distribution, and crowd activity through multi-source data acquisition methods; a data processing module for preprocessing and feature extraction of the acquired multimodal data using image recognition and spatial data processing technologies to obtain multiple quantitative indicators for assessing spatial vitality; a behavior recognition module for identifying crowd size and behavior types based on image detection algorithms and behavior recognition models, and constructing a spatial domain weight model in conjunction with spatial location information; calculating the spatial vitality intensity value of the target area based on the recognition results and the weight model; a correlation analysis module for analyzing the correlation between quantitative indicators and spatial vitality intensity, and identifying key factors affecting street spatial vitality; and an optimization suggestion module for providing optimization suggestions for seating arrangement based on the key factors.

[0019] This invention protects an electronic device including a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. The machine-readable instructions are executed by the processor to perform the steps of the street vitality assessment and optimization method based on street seating space as claimed in any one of claims 1 to 7.

[0020] This invention protects a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the street vitality assessment and optimization method based on street seating space as described in any one of claims 1 to 7.

[0021] This invention protects a method for assessing and optimizing street vitality based on street seating space. Its core lies in systematically evaluating street seating space through a multi-level quantitative indicator system and constructing a spatial vitality intensity model by combining image recognition and behavior analysis technologies. This allows for precise quantification and optimization suggestions for street space vitality. The method introduces quantitative indicators at three levels: seating itself, seating space, and street environment, comprehensively reflecting the multidimensional factors affecting street vitality and enhancing the scientific and systematic nature of the assessment system. Furthermore, by using image detection algorithms and behavior recognition models to identify the number of people and their behavior types, and by establishing a spatial domain weight model based on spatial domain division, the calculation of spatial vitality intensity more closely reflects real-world usage scenarios, improving the accuracy and practicality of the assessment results. Moreover, by inputting the quantitative indicators as dependent variables and spatial vitality intensity as independent variables into a correlation analysis model, the actual impact of each indicator on spatial vitality can be effectively identified, providing data support and decision-making basis for street space optimization, significantly improving the efficiency and targeting of street space design and renovation. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0023] Figure 1 The flowchart of a method for assessing street space vitality and evaluating and optimizing seating provided in this application embodiment;

[0024] Figure 2 : A schematic diagram of the structure of a method for constructing street space vitality assessment indicators provided in this application embodiment;

[0025] Figure 3 This application provides a schematic diagram of a structure for calculating space vitality intensity according to an embodiment.

[0026] Figure 4 The flowchart of a method for calculating seat space vitality intensity based on image recognition and spatial domain division provided in this application embodiment;

[0027] Figure 5 The flowchart of a seating optimization method based on street vitality assessment provided in this application embodiment;

[0028] Figure 6 This application provides a flowchart for calculating seat evaluation and optimization indicators based on street vitality assessment.

[0029] Figure 7 This application provides an embodiment of an image acquisition method based on street vitality assessment.

[0030] Figure 8 This application provides a post-use evaluation system diagram for a seating assessment and optimization method based on street vitality assessment.

[0031] Figure 9 This application provides a schematic diagram of the spatial layering relationship of indicators for a seating assessment and optimization method based on street vitality assessment.

[0032] Figure 10 This application provides a diagram showing the morphological type of the space where seats are located, based on a method for evaluating and optimizing seats according to street vitality assessment.

[0033] Figure 11 This application provides a diagram of a device for seat evaluation and optimization based on street vitality assessment.

[0034] Figure 12 This application provides an electronic device diagram for seat evaluation and optimization based on street vitality assessment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0036] Research has revealed that current assessments of street space vitality primarily focus on macro-level factors such as overall street layout, traffic flow, and building form, neglecting the significant impact of street furniture, especially seating, on spatial vitality. While seating plays an irreplaceable role in improving street space utilization and promoting social interaction as a crucial medium for human-space interaction, a systematic and quantifiable assessment method is currently lacking to analyze the correlation between seating layout and spatial vitality. Furthermore, traditional assessment methods often rely on subjective surveys or small-sample observations, making it difficult to accurately identify and dynamically assess the vitality of large-scale street spaces, and hindering the development of scalable optimization pathways, thus limiting the scientific rigor and feasibility of urban street renewal.

[0037] Based on this, please refer to Figure 1 This application provides a method for assessing and optimizing street vitality based on street seating space, applied to a computer server. The method includes the following steps: collecting multi-source data to obtain multimodal data on street layout, seating distribution, and crowd activity; using image recognition and spatial data processing technologies to preprocess and extract features from the acquired multimodal data to obtain multiple quantitative indicators for assessing spatial vitality; identifying crowd size and behavior types based on image detection algorithms and behavior recognition models, and constructing a spatial domain weight model based on spatial location information; calculating the spatial vitality intensity value of the target area based on the identification results and the weight model; analyzing the correlation between the quantitative indicators and the spatial vitality intensity, identifying key factors affecting street spatial vitality, and providing feedback on seating arrangement optimization suggestions based on these key factors.

[0038] This application provides a method for assessing and optimizing street vitality based on street seating space. By collecting multi-source data and combining image recognition and behavioral analysis technologies, it achieves an objective and quantitative assessment of street space vitality. This method can accurately identify the relationship between seating layout and pedestrian activity, uncover key factors affecting street space vitality, and thus provide scientific optimization suggestions for seating arrangement. Compared to traditional assessment methods, this method has a wider data coverage and higher analytical accuracy, not only improving the efficiency and accuracy of street space vitality assessment but also providing a replicable and scalable technical path for urban street renewal, contributing to improving the pleasantness and usability of urban public spaces.

[0039] S101 collects multi-source data to obtain multimodal data on street layout, seating distribution, and crowd activity;

[0040] In this invention, the collection of multi-source data is a fundamental step in the street space vitality assessment and optimization method. It aims to obtain comprehensive information on street layout, seating distribution, and pedestrian activity, providing data support for subsequent spatial vitality analysis and optimization recommendations. This step integrates various online and offline data sources to construct a multimodal dataset encompassing image data, spatial data, and behavioral data, ensuring data diversity and accuracy.

[0041] In the specific implementation process, the physical layout information of the street space is first obtained through on-site surveys, including basic spatial data such as street direction, width, building facade features, physical location, material, and form of seating. The survey team uses portable measuring equipment (such as laser rangefinders and total stations) and 3D scanning equipment to accurately map the street space and obtain a 3D spatial model of the seating and its surrounding environment, providing basic data for subsequent spatial modeling.

[0042] Secondly, visual information about street spaces is acquired through image acquisition technology. Image data sources include street view images, social media images, and surveillance videos. Street view images are collected along street paths using street view acquisition vehicles or handheld devices to create continuous panoramic images; social media images are crawled from platforms such as Xiaohongshu, Douyin, and Bilibili to ensure that images cover different time periods, weather conditions, and crowd activity states regarding seating space usage; surveillance videos are used to obtain real-time crowd activity data, supporting dynamic behavior recognition and statistics (such as...). Figure 7 (As shown).

[0043] In addition, crowd activity data is collected through image recognition and video analysis technologies. Object detection algorithms (such as YOLO and Faster R-CNN) are used to identify and count pedestrians in images, and behavior recognition models (such as OpenPose and 3D convolutional networks) are combined to classify crowd behavior types, including necessary behaviors, spontaneous behaviors, and social behaviors, and record their spatial distribution and activity frequency.

[0044] Finally, all collected data were registered and fused according to a unified spatial coordinate system to form a multimodal dataset containing information on street layout, seating distribution, and pedestrian activity, providing an input foundation for subsequent image recognition and spatial data processing. This dataset includes not only static spatial information but also dynamic behavioral information, comprehensively reflecting the usage status and vitality characteristics of street spaces.

[0045] S102 employs image recognition and spatial data processing technologies to preprocess and extract features from the acquired multimodal data, obtaining multiple quantitative indicators for assessing spatial vitality. These quantitative indicators are then stored in a database. For details on the processing and storage procedures, please refer to [link to documentation]. Figure 2 ;

[0046] S1021 Determine the quantitative indicators that need to be quantified.

[0047] After completing multi-source data acquisition, this step, based on image recognition and spatial data processing technologies, systematically preprocesses and extracts features from the acquired multimodal data on street layout, seating distribution, and crowd activity, ultimately generating multiple quantitative indicators for assessing street space vitality. This step integrates multiple technical processes, including image processing, spatial modeling, and data fusion, ensuring that the extracted indicators are quantifiable, comparable, and analyzable, providing a data foundation for subsequent spatial vitality intensity calculations and correlation analyses.

[0048] The quantitative indicators include evaluation indicators at the level of the seat itself, the level of the seat environment, and the level of the street environment.

[0049] In this invention, the extracted quantitative indicators cover three dimensions: the seat itself, the seat space, and the street environment, respectively reflecting the impact of the seat's own attributes, the characteristics of the local space in which the seat is located, and the characteristics of the overall street environment on the vitality of the space. By constructing a multi-level indicator system, the constituent elements of street space vitality can be comprehensively characterized from the micro to the macro level.

[0050] The quantitative indicators at the seat body level include seat type and seat continuity;

[0051] The indicators at the seat body level are used to describe the seat's physical properties and layout characteristics. In one implementation, seat type is represented by numerical quantification, specifically including types such as backrest (denoted as "4"), with small table (denoted as "3"), no backrest (denoted as "2"), folding type (denoted as "1"), and flower stand type (denoted as "0"). This value is entered through the configuration page for different seat type values, and is used for classification and weight setting in subsequent correlation analysis.

[0052] Seating continuity measures the continuity and clustering characteristics of seating arrangements on streets, reflecting the spatial coherence and ease of use of seating. This indicator uses image recognition technology to identify the angle and physical distance between adjacent seats, and calculates the result using a cosine function model. The formula is as follows:

[0053]

[0054] Where, θ i Let d represent the angle formed between the i-th seat and the two seats in front and behind it. i This represents the distance between the i-th seat and the previous seat.

[0055] The quantitative indicators of the seating environment include the spatial form of the seating and whether lighting facilities are provided.

[0056] The indicators at the seating space level are used to describe the local spatial characteristics of the seating. Among them, the spatial form of the seating is divided into six types: overhanging (located in the space under the building's eaves), recessed (embedded in the building's gray space, forming a visual barrier on one side), platform (relying on the steps in front of the shop), mixed (a complex of multiple spaces, composed of overhanging, recessed, or platform spaces), setback (no building support behind), and open (no visual obstruction, supporting multi-directional crowd activity), denoted as "1" to "6" respectively. This data can be configured through a configuration page for different form types, and is used for subsequent correlation analysis between spatial form and activity intensity.

[0057] Whether lighting facilities are installed is represented using binary quantization, with "1" indicating the presence of lighting facilities and "0" indicating the absence of lighting facilities. This information is verified by using image recognition technology to identify the presence of lighting devices around the seats, combined with on-site survey data to ensure data accuracy.

[0058] The quantitative indicators for the street environment include green view rate and spatial openness;

[0059] Street-level environmental indicators are used to describe the overall environmental quality of the streets where the seating is located. Among them, the green view rate measures the proportion of green vegetation in the field of vision, reflecting the impact of greening on spatial vitality. This indicator uses image recognition technology to identify the area of ​​green vegetation in an image and calculates it based on the total area of ​​the image. The specific formula is as follows:

[0060]

[0061] Where, N photo,j S represents the number of valid images captured at the j-th seat space. l,i Let S represent the area of ​​the green plants in the i-th image. p,i Let represent the total area of ​​the i-th image.

[0062] Spatial openness quantifies the perceived openness of a space from a given seat by analyzing the proportion of sky area in the field of vision. It directly reflects visual experience and is an important indicator for assessing the spatial environment. The calculation is performed by identifying the proportion of sky area using image recognition technology; the specific formula is as follows:

[0063]

[0064] Among them, S b,i S represents the area of ​​the sky region in the i-th image. p,i Let represent the total area of ​​the i-th image.

[0065] In image recognition and spatial data processing, the acquired image data is first preprocessed, including denoising, color correction, and viewpoint correction, to improve image quality and ensure the accuracy of the recognition results. Subsequently, deep learning models (such as YOLO, Mask R-CNN, and UNet) are used to identify and label key objects in the image, such as seats, crowds, green plants, and sky areas, extracting the basic data used to calculate various quantitative indicators.

[0066] In terms of spatial data modeling, a topological model of the seats and their surrounding space is constructed by combining 3D point cloud data and image recognition results to calculate indicators such as seat continuity and spatial morphology. Simultaneously, the image recognition results are integrated with field survey data to ensure data integrity and consistency.

[0067] All extracted quantitative indicators are stored and standardized according to a unified data format to form a structured evaluation indicator database, providing input data for subsequent spatial vitality intensity calculation and correlation analysis. This database includes not only static spatial attribute indicators but also dynamic behavior recognition results, comprehensively reflecting the vitality characteristics of street spaces.

[0068] S103 uses image detection algorithms and behavior recognition models to identify the number of people and their behavior types, and constructs a spatial domain weight model by combining spatial location information. Based on the identification results and the weight model, it calculates the spatial vitality intensity value of the target area. For details on the calculation of the vitality intensity value, please refer to [link to relevant documentation]. Figure 3 ;

[0069] Based on the completion of multimodal data collection and quantitative indicator extraction, this step uses image detection and behavior recognition technologies to identify the number and behavior types of people in street seating areas. It then constructs a spatial domain weight model based on spatial location information. Finally, based on the identification results and the weight model, it calculates the spatial vitality intensity value of the target area. This step is the core calculation link in street spatial vitality assessment, enabling a dynamic quantitative expression of the space's usage status.

[0070] S1031 describes the identification of crowd size and behavior type based on image detection algorithms and behavior recognition models, and the construction of a spatial domain weight model by combining spatial location information; based on the identification results and the weight model, the calculation of the spatial vitality intensity value of the target area includes:

[0071] The number of people (n) in each valid image is detected using an image recognition algorithm. i Furthermore, by combining a behavior recognition model to identify crowd behavior types, the influence weight ω of different behavior types on spatial vitality intensity is determined. t The space surrounding the seats is divided into five spatial domains: seating domain, intimate domain, personal distance, social distance, and public distance. The influence weight ω of each spatial domain on the intensity of spatial vitality is determined based on the frequency of human behavior within each domain. n Based on the number of people n identified i Behavior type weight ω t and spatial domain weight ω n Combined with the area S of the seat space j And the number of valid images N photo,j The vitality intensity value of the seat space at location j is calculated using the following formula. For the detailed calculation process of the vitality intensity value, please refer to [link to relevant documentation]. Figure 4 :

[0072]

[0073] S10311 uses an image recognition algorithm to detect the number of people (n) in each valid image. i Furthermore, by combining a behavior recognition model to identify crowd behavior types, the influence weight ω of different behavior types on spatial vitality intensity is determined. t ;

[0074] In this invention, crowd size recognition employs target detection algorithms such as YOLO or Faster R-CNN to detect and count pedestrians in the acquired valid images, obtaining the number of people n in each image. i Meanwhile, by combining behavior recognition models such as OpenPose and 3D convolutional networks, the types of crowd behavior are classified into three categories: necessary behaviors (such as resting and waiting for a bus), spontaneous behaviors (such as taking photos and reading), and social behaviors (such as talking and interacting).

[0075] Based on statistical analysis and expert evaluation, the weights ω of the three types of behaviors on the intensity of spatial vitality are... t The weights are as follows: necessary behavior 0.10, spontaneous behavior 0.45, and social behavior 0.45. This weighting reflects the differences in the contribution of different types of behavior to spatial vitality. Social behavior, due to its interactivity and openness, has the most significant effect on enhancing spatial vitality.

[0076] S10312 divides the space around seats into five spatial domains: seating domain, intimate domain, personal distance, social distance, and public distance. Based on the frequency of human behavior within each domain, the influence weight ω of each spatial domain on the intensity of spatial vitality is determined. n ;

[0077] In terms of spatial division, based on Edwards' social distance theory, the space surrounding the seats is divided into five levels:

[0078] - Seating area (within 0.2m): People have direct contact with the seats, their behavior is highly concentrated, and the weight is 0.21;

[0079] - Intimacy Zone (0.2–0.5m): There is close interaction between the crowd and the seat user, with a weight of 0.27;

[0080] -Personal distance (0.5–1.2m): Individual's independent activity area, with a weight of 0.18;

[0081] - Social distancing (1.2–3.7m): Areas for multi-person interaction, with a weight of 0.24;

[0082] - Public distance (beyond 3.7m): Area for observation or passage at a distance, with a weight of 0.10.

[0083] Using image recognition and spatial positioning technologies, the distribution of people in each image across the five spatial domains is identified. Combined with their behavioral types, the comprehensive influence weight ω of each spatial domain on the spatial vitality intensity is calculated. n .

[0084] S10313 Based on the number of people n identified i Behavior type weight ωt and spatial domain weight ω n Combined with the area S of the seat space j And the number of valid images N photo,j The vitality intensity value of the seat space at position j is calculated according to the following formula:

[0085]

[0086] In this invention, the formula for calculating the spatial vitality intensity value V comprehensively considers multiple factors such as population size, behavior type, spatial distribution, and spatial area, ensuring the scientific validity and comparability of the assessment results. Wherein, N... photo,j This represents the number of valid images collected at the j-th seat location, used to reflect the completeness of data coverage; n i ω represents the number of people detected in the i-th image; t Represents the weight of behavior type; ω n S represents the spatial domain weight; j This represents the area of ​​the seating space at position j.

[0087] This formula allows for standardized calculation of the vitality intensity of different seating spaces, generating comparable vitality intensity values ​​that provide a quantitative basis for subsequent correlation analysis and optimization suggestions.

[0088] In its implementation, S1032 first preprocesses the acquired image data, including image denoising, color correction, and viewpoint unification, to improve recognition accuracy. Then, it uses a target detection model to identify the number of people in the image and combines this with a behavior recognition model to determine their behavior type. Simultaneously, based on spatial positioning information, it maps the crowd distribution to five spatial domains and performs a weighted calculation combining behavior weights and spatial weights.

[0089] S1033 Finally, the system summarizes the recognition results of all images, calculates the vitality intensity value of each seating space according to the above formula, and generates structured data output to the database for subsequent analysis. This calculation process supports batch processing and automated execution, ensuring evaluation efficiency and data consistency.

[0090] S104 analyzes the correlation between the quantitative indicators and the spatial vitality intensity, identifies key factors affecting street space vitality, and provides feedback on seating arrangement optimization suggestions based on these key factors. These optimization suggestions are then fed back to the computer front-end. For details of the feedback process, please refer to [link to relevant documentation]. Figure 5 .

[0091] After calculating the spatial vitality intensity value, this step conducts a correlation analysis based on the relationship between the aforementioned extracted quantitative indicators and the spatial vitality intensity, identifies key factors that have a significant impact on street space vitality, and generates optimization suggestions for seating arrangement based on the analysis results, providing a scientific basis and operable improvement path for street space design.

[0092] The analysis of the correlation between the quantitative indicators and the intensity of space vitality specifically includes:

[0093] S1041 Using the quantitative indicators as dependent variables and the spatial vitality intensity as independent variables, the dependent and independent variables are input into a correlation analysis model; if the model determines that the correlation probability is less than the significance level, it is determined that there is a significant correlation between the quantitative indicators and the spatial vitality intensity; otherwise, it is determined that there is no significant correlation between the quantitative indicators and the spatial vitality intensity.

[0094] The correlation analysis model includes Pearson correlation coefficient analysis and Spearman rank correlation coefficient analysis. In this invention, two statistical methods are used for correlation analysis: Pearson correlation coefficient analysis and Spearman rank correlation coefficient analysis. The Pearson method is suitable for continuous variables that conform to a normal distribution, such as green view rate, spatial openness, and seat continuity; the Spearman method is suitable for non-normally distributed data or qualitative variables, such as seat type, whether lighting facilities are installed, and spatial form type.

[0095] Determine whether the quantitative indicator data conforms to a normal distribution. If it does, use the Pearson correlation coefficient analysis method to calculate the correlation between the indicator and the space vitality intensity. If the quantitative indicator data does not conform to a normal distribution or is qualitative data, use the Spearman rank correlation coefficient analysis method to calculate the correlation between the indicator and the space vitality intensity.

[0096] In the specific implementation process, the normality test of the data distribution of each quantitative indicator is first performed, using the Shapiro-Wilk test or the Kolmogorov-Smirnov test to determine whether it conforms to a normal distribution. If it conforms to a normal distribution, the Pearson correlation coefficient analysis method is used to calculate its correlation with the intensity of spatial vitality; if it does not conform to a normal distribution or is qualitative data, the Spearman rank correlation coefficient analysis method is used for calculation.

[0097] The system outputs correlation probability values ​​based on the correlation analysis results, and determines whether a significant correlation exists based on these probabilities. After the correlation analysis is completed, the system outputs the correlation coefficient r and the significance probability p value. A significance level α is set (usually 0.05 or 0.01). If p < α, a significant correlation is determined between the quantitative indicator and the intensity of spatial vitality; otherwise, no significant correlation is determined. For example, if the p value for seat continuity is 0.003, which is less than 0.01, it is considered to have a significant positive correlation with the intensity of spatial vitality.

[0098] If the model determines that the correlation probability is less than the significance level, it is determined that there is a significant correlation between the quantitative indicator and the spatial vitality intensity; otherwise, it is determined that there is no significant correlation between the quantitative indicator and the spatial vitality intensity.

[0099] In this invention, the system automatically determines the significance of the correlation between each quantitative indicator and the intensity of space vitality. For indicators with significant correlation, the system further outputs their control result range to guide the generation of subsequent optimization suggestions.

[0100] S1042 If it is determined that the quantitative indicator is significantly correlated with the space vitality intensity, the control result of the quantitative indicator is output, and it is determined whether the current value of the quantitative indicator is within the control result range.

[0101] For indicators with significant correlation, the system outputs the ideal control range for that indicator based on the correlation analysis results and statistical characteristics of the data. For example, the ideal control range for seat continuity is 0.63–0.90, the ideal range for green view rate is 0.28–0.35, and the ideal range for spatial openness is 0.09–0.18. The system compares the current quantitative indicator value of the seat space with this control range to determine whether it is within the ideal range.

[0102] S1043 If the current quantitative indicator value is not within the control result range, feed back seat optimization suggestions based on street vitality assessment to the computer front end;

[0103] If the current quantitative indicator value is not within the control range, the system will trigger the optimization suggestion generation mechanism and provide specific optimization suggestions to the user interface. For example:

[0104] - If the seat continuity is below 0.63, it is recommended to adjust the seat layout to increase continuity;

[0105] - If the green view rate is below 0.28, it is recommended to increase green plants or optimize the orientation of the seats;

[0106] - If the space openness is higher than 0.18, it is recommended to adjust the seat position or add screen elements;

[0107] - If the seat has no backrest or lighting, it is recommended to add a backrest or lighting.

[0108] In practice, the system outputs all correlation analysis results and optimization suggestions to the front-end interface in structured data format, supporting visualization and interactive operation. Users can view the evaluation results, correlation analysis conclusions, and optimization suggestions for each seating space through the graphical interface, facilitating decision-making and implementation by street designers or urban planners.

[0109] After optimization suggestions are generated, the system supports exporting the results as a report document or pushing them to the urban planning management platform, achieving a closed-loop feedback between the evaluation results and the optimization path. Simultaneously, the system supports re-evaluating the spatial vitality after the implementation of optimization suggestions, forming a continuous optimization mechanism to enhance the overall vitality and livability of street spaces. Figure 6 The logical process of the entire solution is presented, through... Figure 6 It allows for an intuitive understanding of the entire process of data processing and information display in the solution.

[0110] Please see Figure 10 , Figure 10 This is a schematic diagram of a street vitality assessment and optimization device based on street seating space, provided as an embodiment of this application. Figure 10 As shown, the street vitality assessment and optimization device 200 based on street seating space includes:

[0111] The data acquisition module 210 is used to acquire multimodal data related to street layout, seat distribution and crowd activity through multi-source data acquisition methods;

[0112] The data processing module 220 is used to preprocess and extract features from the acquired multimodal data using image recognition and spatial data processing technologies to obtain multiple quantitative indicators for evaluating spatial vitality. These quantitative indicators include evaluation indicators at the seat body level, seat space level, and street environment level. The quantitative indicators at the seat body level include seat type and seat continuity. The quantitative indicators at the seat space level include the spatial form of the seat and whether lighting facilities are installed. The quantitative indicators at the street environment level include green view rate and spatial openness. Figure 8 , 9 The evaluation system provides the dimensions and factors to be considered for the quantitative indicators, extending from the seat itself to the surrounding space to form the entire evaluation system. Figure 10 Examples for different scenarios are provided, which can help to quickly process data and also help technical personnel understand the considerations for various scenarios in this solution.

[0113] The behavior recognition module 230 is used to identify the number of people and their behavior types based on image detection algorithms and behavior recognition models, and to construct a spatial domain weight model by combining spatial location information. Based on the recognition results and the weight model, it calculates the spatial vitality intensity value of the target area, including detecting the number of people (n) in each valid image using image recognition algorithms. i Furthermore, by combining a behavior recognition model to identify crowd behavior types, the influence weight ω of different behavior types on spatial vitality intensity is determined. t The space surrounding the seats is divided into five spatial domains: seating domain, intimate domain, personal distance, social distance, and public distance. The influence weight ω of each spatial domain on the intensity of spatial vitality is determined based on the frequency of human behavior within each domain. n ;

[0114] Calculate the vitality intensity value of the seat space at position j using the following formula:

[0115]

[0116] Among them, S j N represents the area of ​​the seating space. photo,j This represents the number of valid images.

[0117] The correlation analysis module 240 is used to analyze the correlation between the quantitative indicators and the spatial vitality intensity, and to identify key factors affecting street spatial vitality. Specifically, it includes: using each quantitative indicator as the dependent variable and the spatial vitality intensity as the independent variable, inputting the dependent and independent variables into a correlation analysis model; if the model determines that the correlation probability is less than the significance level, it determines that there is a significant correlation between the quantitative indicators and the spatial vitality intensity; otherwise, it determines that there is no significant correlation between the quantitative indicators and the spatial vitality intensity. The correlation analysis model includes Pearson correlation coefficient analysis and Spearman rank correlation coefficient analysis; it determines whether the quantitative indicator data conforms to a normal distribution; if so, it uses Pearson correlation coefficient analysis to calculate the correlation between the indicator and the spatial vitality intensity; if the quantitative indicator data does not conform to a normal distribution or is qualitative data, it uses Spearman rank correlation coefficient analysis to calculate the correlation between the indicator and the spatial vitality intensity; it outputs a correlation probability value based on the correlation analysis results, and determines whether a significant correlation exists based on the correlation probability value.

[0118] The optimization suggestion module 250 is used to provide optimization suggestions for seat arrangement based on key factors; if it is determined that the quantitative index is significantly correlated with the spatial vitality intensity, the control result of the quantitative index is output, and it is determined whether the current quantitative index value is within the control result range; if the current quantitative index value is not within the control result range, the seat optimization suggestions based on street vitality assessment are fed back to the computer front end.

[0119] Furthermore, when the data processing module 220 is used to obtain quantitative indicators at the seat body level, it is specifically used for: quantifying the seat type at the seat body level by numerical values, inputting the numerical values ​​corresponding to different seat types through the configuration page; recognizing the angle and physical distance between adjacent seats through image recognition, and calculating and determining the seat continuity.

[0120] The seating space is categorized into six spatial types: overhanging (located under the building's eaves), recessed (embedded in the building's gray space, forming a visual barrier on one side), platform (relying on the steps in front of the shop), mixed (a combination of multiple spaces, consisting of overhanging, recessed, or platform spaces), terraced (without building support behind), and open (without obstructed views, supporting multi-directional crowd movement). Data for different spatial types can be configured via a configuration page. Whether the seats are equipped with lighting facilities is represented by binary quantization, and the lighting facility values ​​for different photos are determined using image recognition.

[0121] The green view rate at the street environment level is calculated using image recognition technology, with the specific formula as follows:

[0122]

[0123] Where, N photo,j S represents the number of valid images captured at the j-th seat space. l,i Let S represent the area of ​​the green plants in the i-th image. p,i This represents the total area of ​​the i-th image;

[0124] The spatial openness is calculated using image recognition technology to determine the proportion of the sky area, with the specific formula as follows:

[0125]

[0126] Among them, S b,i S represents the area of ​​the sky region in the i-th image. p,i Let represent the total area of ​​the i-th image.

[0127] The street vitality assessment and optimization device based on street seating space provided in this application acquires multimodal data related to street layout, seating distribution, and crowd activities through multi-source data acquisition methods. It preprocesses and extracts features from the acquired multimodal data using image recognition and spatial data processing technologies to obtain multiple quantitative indicators for assessing spatial vitality. Based on image detection algorithms and behavior recognition models, it identifies the number of people and their behavior types, and constructs a spatial domain weight model by combining spatial location information. Based on the identification results and the weight model, it calculates the spatial vitality intensity value of the target area. It analyzes the correlation between the quantitative indicators and the spatial vitality intensity, identifies key factors affecting street spatial vitality, and provides feedback on seating arrangement optimization suggestions based on these key factors. This enables scientific assessment and intelligent optimization of street seating space vitality, improving the utilization efficiency of urban public spaces and resident satisfaction.

[0128] Please see Figure 12 , Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 12 As shown, the electronic device 300 includes a processor 310, a memory 320, and a bus 330.

[0129] The memory 320 stores machine-readable instructions that can be executed by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate via the bus 330. When the machine-readable instructions are executed by the processor 310, the steps of the street vitality assessment and optimization method based on street seating space as described in the above method embodiment can be executed. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0130] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the street vitality assessment and optimization method based on street seating space as described in the above method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0131] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0135] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, 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 this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for assessing and optimizing street vitality based on street seating space, applied to a computer server, characterized in that, Includes the following steps: Collect multi-source data to obtain multimodal data on street layout, seating distribution, and crowd activity; Image recognition and spatial data processing technologies are used to preprocess and extract features from the acquired multimodal data to obtain multiple quantitative indicators for assessing spatial vitality. Based on image detection algorithms and behavior recognition models, the number of people and their behavior types are identified, and a spatial domain weight model is constructed by combining spatial location information; based on the identification results and the weight model, the spatial vitality intensity value of the target area is calculated. The correlation between the quantitative indicators and the intensity of spatial vitality is analyzed to identify key factors affecting the vitality of street spaces, and suggestions for optimizing seating arrangements based on these key factors are provided.

2. The method for assessing and optimizing street vitality based on street seating space according to claim 1, characterized in that, The quantitative indicators include evaluation indicators at the level of the seat body, the level of the seat space, and the level of the street environment. The quantitative indicators at the seat body level include seat type and seat continuity; the quantitative indicators at the seat space level include the spatial form of the seat and whether lighting facilities are installed; and the quantitative indicators at the street environment level include green view rate and spatial openness.

3. The method for assessing and optimizing street vitality based on street seating space according to claim 2, characterized in that, The seat type at the seat body level is quantified by numerical values, and different numerical values ​​corresponding to different seat types are input through the configuration page; the angle and physical distance between adjacent seats are recognized by image recognition, and the continuity of the seats is calculated and determined. The spatial form of the seats in the aforementioned seating environment includes six types: overhanging, recessed, platform, mixed, stepped, and open. Data for different form types can be configured through a configuration page. Whether the seats are equipped with lighting facilities is represented by binary quantization, and the lighting facility values ​​for different photos are determined by image recognition. The green view rate at the street environment level is calculated using image recognition technology, with the specific formula as follows: Where, N photo,j S represents the number of valid images captured at the j-th seat space. l,i Let S represent the area of ​​the green plants in the i-th image. p,i This represents the total area of ​​the i-th image; The spatial openness is calculated using image recognition technology to determine the proportion of the sky area, with the specific formula as follows: Among them, S b,i S represents the area of ​​the sky region in the i-th image. p,i Let represent the total area of ​​the i-th image.

4. The method for assessing and optimizing street vitality based on street seating space according to claim 1, characterized in that, The method, based on image detection algorithms and behavior recognition models, identifies the number of people and their behavior types, and constructs a spatial domain weight model by combining spatial location information. Based on the identification results and the weight model, the spatial vitality intensity value of the target area is calculated, including: The number of people (n) in each valid image is detected using an image recognition algorithm. i Furthermore, by combining behavioral recognition models to identify crowd behavior types, the influence weights ω of different behavior types on spatial vitality intensity are determined. t ; The space surrounding seating is divided into five spatial domains: seating domain, intimate domain, personal distance, social distance, and public distance. Based on the frequency of human behavior within each domain, the influence weight ω of each spatial domain on the intensity of spatial vitality is determined. n ; Calculate the vitality intensity value of the seat space at position j using the following formula: Among them, S j N represents the area of ​​the seating space. photo,j This represents the number of valid images.

5. The method for assessing and optimizing street vitality based on street seating space according to claim 1, characterized in that, The analysis of the correlation between the quantitative indicators and the intensity of space vitality specifically includes: Using the aforementioned quantitative indicators as dependent variables and the spatial vitality intensity as independent variables, the dependent and independent variables are input into a correlation analysis model. If the model determines that the correlation probability is less than the significance level, it is determined that there is a significant correlation between the quantitative indicator and the spatial vitality intensity; otherwise, it is determined that there is no significant correlation between the quantitative indicator and the spatial vitality intensity.

6. The method for assessing and optimizing street vitality based on street seating space according to claim 5, characterized in that, The correlation analysis models include Pearson correlation coefficient analysis method and Spearman rank correlation coefficient analysis method; Determine whether the quantitative indicator data conforms to a normal distribution. If it does, use the Pearson correlation coefficient analysis method to calculate the correlation between the indicator and the space vitality intensity. If the quantitative indicator data does not conform to a normal distribution or is qualitative data, use the Spearman rank correlation coefficient analysis method to calculate the correlation between the indicator and the space vitality intensity. The correlation probability value is output based on the correlation analysis results, and the existence of a significant correlation is determined based on the correlation probability value.

7. The method for assessing and optimizing street vitality based on street seating space according to claim 5, characterized in that, If it is determined that the quantitative indicator is significantly correlated with the spatial vitality intensity, the control result of the quantitative indicator is output, and it is determined whether the current value of the quantitative indicator is within the control result range. If the current quantitative indicator value is not within the control range, feedback on seat optimization suggestions based on street vitality assessment is sent to the computer front end.

8. A street vitality assessment and optimization device based on street seating space, characterized in that, include: The data acquisition module is used to acquire multimodal data related to street layout, seating distribution, and crowd activity through multi-source data acquisition methods; The data processing module is used to preprocess and extract features from the acquired multimodal data using image recognition and spatial data processing technologies to obtain multiple quantitative indicators for assessing spatial vitality. The behavior recognition module is used to identify the number of people and their behavior types based on image detection algorithms and behavior recognition models, and to construct a spatial domain weight model by combining spatial location information; based on the recognition results and the weight model, the spatial vitality intensity value of the target area is calculated. The correlation analysis module is used to analyze the correlation between the quantitative indicators and the intensity of spatial vitality, and to identify key factors affecting the vitality of street space. The optimization suggestion module provides optimization suggestions for seating arrangement based on key factors.

9. An electronic device, characterized in that, The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions that the processor can execute. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the street vitality assessment and optimization method based on street seating space as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the street vitality assessment and optimization method based on street seating space as described in any one of claims 1 to 7.

Images