Design method of urban slow space for optimizing route-finding task under human factors technology

Abstract

The application discloses a human factor technology-oriented urban slow-moving space design method for optimizing a route searching task, and comprises the following steps: 1. simulating modeling of different slow-moving space design schemes, using a path planning algorithm to finely decompose the route searching task of the slow-moving space, and determining human factor space variables and human factor environment variables; 2. designing space measurement experiments and scene virtual experiments corresponding to the route searching task, and based on VR virtual simulation technology and human factor data acquisition technology, carrying out human factor variable data acquisition experiments; 3. using an artificial intelligence deep learning algorithm, coupling and analyzing human factor perception data and space design variable data; 4. based on artificial intelligence data visualization analysis technology, identifying key variables of human factor design, and obtaining the human factor technology-oriented urban slow-moving space planning and design method for optimizing the route searching task. The application solves the shortcoming that traditional route searching technology only recommends the shortest route without considering the path space quality and human comfort.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban slow space design, and particularly relates to a method for optimizing a route-finding task in urban slow space design under the guidance of human factors technology. BACKGROUND

[0002] Under the background of new urbanization, with the continuous improvement of social requirements for space quality, the importance of space design of urban slow space is increasingly prominent.

[0003] The design of urban slow space not only needs to meet the pursuit of modern people for a healthy and environmentally friendly lifestyle, but also should provide a more humanized and pedestrian-friendly street environment.

[0004] The optimization of slow space can greatly improve the quality of life of urban residents and promote social harmony and sustainable development.

[0005] Although the importance of slow space design is increasingly recognized, there is currently a lack of a scientific and quantitative methodology to guide space design in the actual operation process. Existing relevant design guidelines focus on regulating and guiding the use function and physical space size (high-width ratio, street width, discount rate and other indicators), such as: “Indian Street Design Manual” (2011), “Los Angeles Street Design Guidelines” (2011), “New York Street Design Manual” (2009), “Street Design with Balance of Multiple Needs as a Sculpture - Taking “Abu Dhabi Street Design Manual” as an Example” (2014), “Shanghai Street Design Guidelines” (2016), “Nanjing Street Design Guidelines” (2018), “Research on Shanghai Urban Road Classification System” (2004), etc. For the quality of slow space and the consideration of human-oriented perspective, traditional space design methods often rely on the intuition and experience of designers, and there is no comprehensive, objective and quantifiable evaluation system. This method has obvious limitations in evaluating and optimizing slow space, and it is difficult to accurately meet the fine needs of modern urban residents for space quality.

[0006] In recent years, under the guidance of urban human factors engineering, space design can pay more attention to human behavior patterns, psychological feelings and physiological reactions, thereby creating a space that conforms to the principles of human engineering. The introduction of the concept of urban human factors engineering provides a new way to solve this problem. Through quantitative means, a descriptive model is established to accurately support the design decision-making process of urban slow space, making the design more scientific, systematic and human-oriented. Compared with traditional methods, urban human factors engineering can better capture human behavior patterns, psychological feelings and physiological reactions, and provide accurate data support for slow space.

[0007] In this context, the present application aims to construct a method for exploring the perception rules of urban slow space and optimizing the spatial planning and design method of slow space routing task based on modern human factor measurement technology means such as eye tracking, virtual reality (VR), physiological detection, and the theoretical framework of urban human factor engineering.

[0008] Therefore, how to calculate the human factor space variable and the human factor environment variable of public space by computer software, and provide suitable travel paths for different travelers in different environments, so that the paths can meet the travel needs of different objects in different scenarios, rather than just the shortest (fastest) path, has become a technical problem that those skilled in the art need to solve. SUMMARY

[0009] In view of the above defects of the prior art, the present application provides a design method for urban slow space of routing task under the guidance of human factor technology, and the purpose is to build a comprehensive, objective and quantifiable evaluation system through interdisciplinary cooperation, support design decision-making, and improve the design quality of slow space. The ultimate goal is to create a healthier, more comfortable and pleasant urban slow space, promote the sustainable development of the city, and provide residents with a higher quality of life.

[0010] To achieve the above purpose, the present application discloses a design method for urban slow space of routing task under the guidance of human factor technology, comprising the following steps:

[0011] Step 1, based on BIM technology and high-precision simulation technology, simulate modeling of different slow space design schemes, and use path planning algorithm to refine and decompose the routing task of slow space, and determine the human factor space variable and the human factor environment variable;

[0012] Step 2, design space measurement experiments and scenario virtual experiments corresponding to the routing task, and based on VR virtual simulation technology and human factor data acquisition technology, carry out data acquisition experiments of human factor variables;

[0013] Step 3, using artificial intelligence deep learning algorithm, coupling analysis and research on human factor perception data and space design variable data;

[0014] Step 4, based on artificial intelligence data visualization analysis technology, identifying key variables of human factor design, and obtaining the design method for urban slow space of routing task under the guidance of human factor technology, for guiding the planning and design of slow space.

[0015] Preferably, step 1 specifically comprises:

[0016] Step 1.1, using BIM technology for high-precision simulation of different slow space design schemes;

[0017] Step 1.2, obtain the simulation modeling of all the design schemes of the slow space;

[0018] Step 1.3, decompose the wayfinding task of the slow space;

[0019] Step 1.4, determine the human factor space variable and the human factor environment variable.

[0020] More preferably, step 1.3 is as follows:

[0021] For the environment of the built slow space, the unmanned aerial vehicle real scene three-dimensional oblique photography technology and the NeDF based on video material, namely Neural Radiance Fields or Gaussian snowball depth learning algorithm, are used to realize high-precision three-dimensional real scene modeling of the slow space;

[0022] For the environment of the un-built slow space, BIM technology and virtual simulation technology are used to realize high-precision three-dimensional real scene modeling of different design schemes of the slow space.

[0023] More preferably, in step 1.4, according to different categories of the slow space, the wayfinding task in specific scenarios is decomposed, and the corresponding human factor space variable and human factor environment variable are selected, which are as follows:

[0024] When the category of the slow space is a walking space, the element of the slow space is an area exclusively for pedestrians, and the corresponding wayfinding task is how pedestrians choose the best walking route;

[0025] Among them, the area exclusively for pedestrians includes pedestrian street, pedestrian square, pedestrian overpass and underground passage;

[0026] How pedestrians choose the best walking route includes distance factor, time factor, landscape factor, and the role of traffic buildings including the pedestrian overpass and the underground passage in guiding the direction and path selection of pedestrians;

[0027] When the category of the slow space is a bicycle space, the element of the slow space is an area for cyclists, and the corresponding wayfinding task includes bicycle path selection, bicycle space layout and cyclist behavior pattern;

[0028] Among them, the area for cyclists includes bicycle lane, bicycle parking area, shared bicycle station;

[0029] When the category of the slow space is a mixed use space, the element of the slow space is an area for pedestrians and cyclists to use together, and the corresponding wayfinding task includes walking and cycling route selection, and the coordination degree of the identification system with the layout of the mixed space and the influence on user wayfinding;

[0030] The area for common use of pedestrians and cyclists includes mixed paths for pedestrians and cyclists, urban greenways and waterfront paths;

[0031] When the category of the slow space is urban center, the elements of the slow space include commercial pedestrian streets, squares, pedestrian streets in parks and cycling paths, and the corresponding wayfinding tasks include route selection in busy urban centers, identification and route design, and the influence of the building and spatial layout of the urban center on wayfinding;

[0032] When the category of the slow space is residential area, the elements of the slow space include pedestrian paths and cycling paths within the community, and the corresponding wayfinding tasks include the selection of main facilities and destinations in the residential area;

[0033] When the category of the slow space is campus, the elements of the slow space include pedestrian and cycling paths in university campuses, and the corresponding wayfinding tasks include route selection of classrooms, libraries, dormitories and dining areas;

[0034] When the category of the slow space is waterfront path, the elements of the slow space include pedestrian and cycling paths built along rivers, lakes or coastlines, and the corresponding wayfinding tasks include the influence of route design of the waterfront path on wayfinding;

[0035] When the category of the slow space is commuting space, the elements of the slow space include pedestrian and cycling paths designed for daily commuting, connecting residential areas and work sites, schools, and the corresponding wayfinding tasks include route efficiency, commuting difficulty of residential areas and work sites, schools;

[0036] When the category of the slow space is leisure space, the elements of the slow space are spaces for leisure, sports and entertainment, connecting residential areas and work sites, schools, and the corresponding wayfinding tasks include wayfinding identification and natural landscape and design elements of the leisure space;

[0037] The space for leisure, sports and entertainment includes park paths and waterfront paths;

[0038] When the category of the slow space is tourism space, the elements of the slow space include pedestrian and cycling paths connecting tourist attractions, providing sightseeing and experience services, and the corresponding wayfinding tasks include identification of main attractions, cultural sites and natural landscapes.

[0039] Preferably, step 2 specifically includes:

[0040] Step 2.1, design space measurement experiments and scenario virtual experiments corresponding to the wayfinding tasks;

[0041] Step 2.2, adopt VR virtual simulation technology and human factor data acquisition technology;

[0042] Step 2.3, carry out data acquisition experiment of human factor variable.

[0043] More preferably, in step 2.2, through the VR equipment and human factor data acquisition experiment equipment worn by the subjects, the data is collected by behavior experiment in the three-dimensional reconstructed virtual scene or real street scene;

[0044] In step 2.3, the data obtained by the VR equipment and human factor data acquisition experiment equipment is used to collect and record the human factor variable data of the subjects' visual attention point data, facial micro-expression data, electroencephalogram data, skin electricity data, walking path selection data, and residence time data.

[0045] Preferably, step 3 is specifically as follows:

[0046] Step 3.1, adopt artificial intelligence deep learning algorithm;

[0047] Step 3.2, take human factor perception data and space design variable data as input;

[0048] Step 3.3, carry out coupling analysis research, and establish variable database of route-finding task and human factor perception data in different slow-moving spaces.

[0049] More preferably, through the VR equipment and human factor data acquisition experiment equipment worn by the subjects, the eye movement tracking data, facial recognition data and VR experience data of the subjects are collected, and then a parameter coupling analysis model is constructed based on decision tree and self-organizing mapping neural network to simulate the parameter relationship between multiple variables, and to establish the variable database of route-finding task and human factor perception data in different slow-moving spaces.

[0050] Preferably, step 4 is specifically as follows:

[0051] Step 4.1, artificial intelligence data visualization analysis;

[0052] Step 4.2, identify key variables of human factor design;

[0053] Step 4.3, obtain urban slow-moving space planning and design method for optimizing route-finding task under the guidance of human factor technology.

[0054] More preferably, based on the variable database of different said slow space routing tasks and human perception data, the key variables of human design are identified through machine learning, deep learning algorithms including decision tree, random forest, convolutional neural network, the influence of space design features on pedestrians is obtained, and then the human parameter design index is summarized and quantified for different design scenarios.

[0055] Finally, through the quantified human parameter design index, based on data analysis, the optimization design scheme under the guidance of human technology is obtained.

[0056] The present application proposes an optimization design scheme under the guidance of human technology through a full-process quantitative research method based on data analysis, and improves the usability, safety and comfort of urban slow space.

[0057] The beneficial effects of the present application are:

[0058] The present application will expand the research scope to the public space where the road is based on the traditional routing software, and consider the human variable at the public space level, collect, experiment and analyze the data of human variable in the public space, identify the key variables under different space types, and take these variables into the influencing factors of travel path selection under different scenarios, and find the path with the best quality and relatively short path.

[0059] The path search result provided by the present application fully considers the travel demand of different spaces and different crowds, provides the most comfortable and reasonable path, and avoids the shortcomings of traditional routing technology that only recommends the shortest path without considering the space quality and human comfort of the path.

[0060] The concept, specific structure and technical effects of the present application will be further described below with reference to the accompanying drawings, so as to fully understand the purpose, features and effects of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 A flowchart showing an embodiment of the present application is shown.

[0062] Figure 2 A slow space scene classification and routing task decomposition table of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0063] EMBODIMENT

[0064] As shown in Figure 1 The urban slow space design method for optimizing routing task under the guidance of human technology includes the following steps:

[0065] Step 1, based on BIM technology and high-precision simulation technology, simulate modeling of different slow space design schemes, and use path planning algorithm to refine and decompose the slow space routing task, determine the human factor space variable and human factor environment variable;

[0066] Step 2, design and routing task corresponding space measurement experiment and scene virtual experiment, based on VR virtual simulation technology and human factor data acquisition technology, carry out human factor variable data acquisition experiment;

[0067] Step 3, using artificial intelligence deep learning algorithm, coupling analysis of human factor perception data and space design variable data;

[0068] Step 4, based on artificial intelligence data visualization analysis technology, identify the key variables of human factor design, and obtain the urban slow space planning and design method of optimizing routing task under the guidance of human factor technology, which is used to guide the planning and design of slow space.

[0069] The present application uses modern scientific and technological means, such as eye tracking, virtual reality (VR), physiological detection, etc., combined with the theoretical framework of urban human factor engineering, explores the perception law of urban slow space, and develops a quantifiable space design method for slow space routing task under the guidance of human factor, to improve the travel experience of users.

[0070] In some embodiments, step 1 specifically includes:

[0071] Step 1.1, using BIM technology for high-precision simulation of different slow space design schemes;

[0072] Step 1.2, obtain the simulation modeling of all slow space design schemes;

[0073] Step 1.3, decompose the slow space routing task;

[0074] Step 1.4, determine the human factor space variable and human factor environment variable.

[0075] In some embodiments, step 1.3 is specifically as follows:

[0076] In practical application, the slow space routing task is decomposed, which is the simulation modeling of various urban slow space design schemes and the decomposition of slow space routing task.

[0077] For the environment of the built slow space, the unmanned aerial vehicle real scene three-dimensional oblique photography technology and NeDF based on video material, namely Neural Radiance Fields or Gaussian snowball deep learning algorithm, are used to realize high-precision three-dimensional real scene modeling of slow space;

[0078] For the environment of the slow space that has not been built, BIM technology and virtual simulation technology are used to carry out high-precision three-dimensional real scene modeling on different slow space design schemes.

[0079] As shown in Figure 2 in some embodiments, in step 1.4, according to the category of different slow space, the route finding task in a specific scene is decomposed, and the corresponding human factor space variable and human factor environment variable are selected, as follows:

[0080] When the category of slow space is walking space, the element of slow space is an area specially used for pedestrians, and the corresponding route finding task is how pedestrians choose the best walking route;

[0081] Among them, the area specially used for pedestrians includes pedestrian street, pedestrian square, pedestrian overpass and underground passage;

[0082] How pedestrians choose the best walking route includes distance factor, time factor, landscape factor, and the role of traffic buildings including pedestrian overpass and underground passage in guiding pedestrian direction and path selection;

[0083] When the category of slow space is bicycle space, the element of slow space is an area used for cyclists, and the corresponding route finding task includes bicycle path selection, bicycle space layout and cyclist behavior pattern;

[0084] Among them, the area used for cyclists includes bicycle lane, bicycle parking area, shared bicycle station;

[0085] When the category of slow space is mixed use space, the element of slow space is an area used for pedestrians and cyclists, and the corresponding route finding task includes walking and cycling route selection, and the coordination degree of identification system with mixed space layout and the influence on user route finding;

[0086] The area used for pedestrians and cyclists includes pedestrian and bicycle mixed lane, urban greenway and waterfront trail;

[0087] When the category of slow space is urban center, the element of slow space includes commercial pedestrian street, square, pedestrian street and bicycle lane in the park, and the corresponding route finding task includes busy urban center route selection, identification and route design, and the influence of urban center building and space layout on route finding;

[0088] When the category of slow space is residential area, the element of slow space includes pedestrian path and bicycle path inside the community, and the corresponding route finding task includes residential area main facility and destination selection;

[0089] When the category of the slow space is campus, the elements of the slow space include walking and cycling paths in the university campus, and the corresponding wayfinding tasks include route selection of classrooms, libraries, dormitories and dining areas;

[0090] When the category of the slow space is waterfront path, the elements of the slow space include walking and cycling paths built along rivers, lakes or coastlines, and the corresponding wayfinding tasks include the influence of the route design of the waterfront path on wayfinding;

[0091] When the category of the slow space is commuting space, the elements of the slow space include walking and cycling paths designed for daily commuting, connecting residential areas and workplaces, schools, and the corresponding wayfinding tasks include route efficiency and commuting difficulty of residential areas and workplaces, schools;

[0092] When the category of the slow space is leisure space, the elements of the slow space are spaces for leisure, sports and entertainment, connecting residential areas and workplaces, schools, and the corresponding wayfinding tasks include wayfinding signs and natural landscapes and design elements of the leisure space;

[0093] The spaces for leisure, sports and entertainment include park paths and waterfront paths;

[0094] When the category of the slow space is tourism space, the elements of the slow space include walking and cycling paths connecting tourist attractions, providing sightseeing and experience services, and the corresponding wayfinding tasks include identification of major attractions, cultural sites and natural landscapes.

[0095] In some embodiments, step 2 specifically comprises:

[0096] Step 2.1, design space measurement experiments and scenario virtual experiments corresponding to wayfinding tasks;

[0097] Step 2.2, adopt VR virtual simulation technology and human factor data acquisition technology;

[0098] Step 2.3, carry out data acquisition experiments of human factor variables.

[0099] In some embodiments, in step 2.2, the subject wears VR equipment and human factor data acquisition experiment equipment, and carries out behavior experiments to collect data in a three-dimensionally reconstructed virtual scene or a real street scene;

[0100] In practical applications, the present application simulates the slow space of the actual city by establishing a virtual environment, so that researchers can observe and record the behavior response of participants in a specific scene without physical limitations.

[0101] In step 2.3, the data obtained by the VR device and the human factor data acquisition experimental equipment are used to obtain the route-finding task of the slow space, and the human factor variable data acquisition experiment is carried out from the human perspective to collect and record the human factor variable data of the visual attention point data, facial micro-expression data, electroencephalogram data, skin electricity data, walking path selection data and residence time data of the subjects.

[0102] In some embodiments, step 3 is specifically as follows:

[0103] Step 3.1, using an artificial intelligence deep learning algorithm;

[0104] Step 3.2, taking the human factor perception data and the space design variable data as inputs;

[0105] Step 3.3, coupling analysis research is carried out to establish a variable database of the route-finding task and the human factor perception data in different slow spaces.

[0106] In some embodiments, the eye movement tracking data, facial recognition data and VR experience data of the subjects are collected by the subjects wearing the VR device and the human factor data acquisition experimental equipment, and then a parameter coupling analysis model is constructed based on a decision tree and a self-organizing mapping neural network to simulate the parameter relationship between multiple variables and establish a variable database of the route-finding task and the human factor perception data in different slow spaces.

[0107] The virtual reality technology of the present application provides an immersive slow space route-finding task experience environment, allowing the subjects to freely move and explore in a completely controlled virtual environment, and collecting eye movement tracking, facial recognition and VR experience data of the subjects by the subjects wearing the VR device and the human factor data acquisition experimental equipment, and constructing a parameter coupling analysis model based on a decision tree (REP-Tree) and a self-organizing mapping (Self-organizing, SOM) neural network to simulate the parameter relationship between multiple variables and establish a variable database of the route-finding task and the human factor perception data in different slow spaces.

[0108] In some embodiments, step 4 is specifically as follows:

[0109] Step 4.1, artificial intelligence data visualization analysis;

[0110] Step 4.2, identifying key variables of human factor design;

[0111] Step 4.3, obtaining a city slow space planning and design method for optimizing the route-finding task under the guidance of human factor technology.

[0112] In some embodiments, based on the variable database of the wayfinding tasks and human perception data in different slow space, the key variables of human design are identified by machine learning, deep learning algorithms including decision tree, random forest, convolutional neural network, the influence of space design features on pedestrians is obtained, and then the design indicators of quantified human parameters are summarized for different design scenarios.

[0113] Finally, through the quantified human parameter design indicators, the optimization design scheme under the guidance of human technology is obtained based on data analysis.

[0114] The present application proposes an optimization design scheme under the guidance of human technology through a full-process quantitative research method based on data analysis, and improves the usability, safety and comfort of urban slow space.

[0115] The above describes the preferred embodiments of the present application in detail. It should be understood that those skilled in the art can make many modifications and changes without creative labor according to the concept of the present application. Therefore, any technical solution obtained by logical analysis, reasoning or limited experiment based on the existing technology according to the concept of the present application should be within the protection scope determined by the claims.

Claims

1. A method for designing urban slow-moving space for optimizing a route-finding task under the guidance of human factors technology, characterized in that, The method comprises the following steps: Step 1: Based on BIM technology and high-precision simulation technology, simulation modeling is performed on different design schemes of slow-moving space, and path planning algorithm is used to refine and decompose the slow-moving space routing task, and human factor space variables and human factor environment variables are determined; Step 2: Design and conduct space measurement experiments and scenario virtual experiments corresponding to the routing task, and based on VR virtual simulation technology and human factor data acquisition technology, carry out data acquisition experiments of human factor variables; Step 3: Using artificial intelligence deep learning algorithm, the coupling effect of human factor perception data and space design variable data is analyzed and researched; Step 4: Based on artificial intelligence data visualization analysis technology, the key variables of human factor design are identified, the influence law of space design characteristics on pedestrians is obtained, and then different design scenarios are summarized and quantified human factor parameter design indexes; finally, through the quantified human factor parameter design index, the data analysis is carried out to obtain the urban slow-moving space planning and design method for optimizing the routing task under the guidance of human factor technology, which is used to guide the planning and design of slow-moving space.

2. The method of claim 1, wherein, Step 1 specifically comprises: Step 1.1: High-precision simulation of different design schemes of slow-moving space is adopted by using BIM technology; Step 1.2: Simulation modeling of all design schemes of slow-moving space is obtained; Step 1.3: The routing task of slow-moving space is decomposed; Step 1.4: The human factor space variables and the human factor environment variables are determined.

3. The method of claim 2, wherein, Step 1.3 specifically comprises: For the environment of the slow-moving space that has been built, the unmanned aerial vehicle real scene three-dimensional oblique photography technology and the NeDF (Neural Radiance Fields) based on video material or Gaussian snowball deep learning algorithm are used to realize high-precision three-dimensional real scene modeling of the slow-moving space; For the environment of the slow-moving space that has not been built, BIM technology and virtual simulation technology are used to realize high-precision three-dimensional real scene modeling of different design schemes of slow-moving space.

4. The method of claim 3, wherein, In step 1.4, according to different categories of slow-moving space, the routing task in specific scenarios is decomposed, and corresponding human factor space variables and human factor environment variables are selected, which specifically comprises: When the category of slow-moving space is walking space, the element of slow-moving space is an area specially used by pedestrians, and the corresponding routing task is how pedestrians choose the best walking route; The area specially used by pedestrians includes pedestrian street, pedestrian square, pedestrian overpass and underground passage; How pedestrians choose the best walking route includes distance factor, time factor, landscape factor, and the role of traffic buildings including pedestrian overpass and underground passage in guiding pedestrian direction and path selection; When the category of slow-moving space is bicycle space, the element of slow-moving space is an area used by cyclists, and the corresponding routing task includes bicycle path selection, bicycle space layout and cyclist behavior mode; The area used by cyclists includes bicycle lane, bicycle parking area and shared bicycle station; When the category of the slow space is mixed use space, the element of the slow space is an area for both pedestrians and cyclists, and the corresponding wayfinding task includes pedestrian and cycling route selection, and the coordination degree of the identification system with the layout of the mixed space and the influence on user wayfinding; The area for both pedestrians and cyclists includes pedestrian and cycling mixed paths, urban greenways, and waterfront paths; When the category of the slow space is urban center, the element of the slow space includes commercial pedestrian streets, squares, and pedestrian streets and cycling paths in parks, and the corresponding wayfinding task includes busy urban center route selection, and the influence of identification and route design on wayfinding in the urban center; When the category of the slow space is residential area, the element of the slow space includes pedestrian paths and cycling paths within the community, and the corresponding wayfinding task includes main facility and destination selection in the residential area; When the category of the slow space is campus, the element of the slow space includes pedestrian and cycling paths in university campuses, and the corresponding wayfinding task includes classroom, library, dormitory, and dining area route selection; When the category of the slow space is waterfront path, the element of the slow space includes pedestrian and cycling paths built along rivers, lakes, or coastlines, and the corresponding wayfinding task includes the influence of waterfront path route design on wayfinding; When the category of the slow space is commuting space, the element of the slow space includes pedestrian and cycling paths designed for daily commuting, connecting residential areas with work sites and schools, and the corresponding wayfinding task includes residential area and work site or school route efficiency and commuting difficulty; When the category of the slow space is leisure space, the element of the slow space is space for leisure, sports, and entertainment, connecting residential areas with work sites and schools, and the corresponding wayfinding task includes wayfinding identification and natural landscape and design elements of the leisure space; The space for leisure, sports, and entertainment includes park paths and waterfront paths; When the category of the slow space is tourism space, the element of the slow space includes pedestrian and cycling paths connecting tourist attractions, providing sightseeing and experience services, and the corresponding wayfinding task includes main attraction, cultural site, and natural landscape identification.

5. The method of claim 1, wherein, Step 2 specifically includes: Step 2.1, designing space measurement experiments and scenario virtual experiments corresponding to the wayfinding task; Step 2.2, using VR virtual simulation technology and human factor data collection technology; Step 2.3, conducting data collection experiments of human factor variables.

6. The method of claim 5, wherein the method is characterized by, In step 2.2, the subject wears VR equipment and human factor data collection experiment equipment, and conducts behavior experiments to collect data in a three-dimensionally reconstructed virtual scene or a real street scene; In step 2.3, the data obtained by the VR device and the human factor data acquisition experiment device are used to acquire the route-finding task of the slow space, and the human factor variable data acquisition experiment is carried out from the human perspective to acquire and record the human factor variable data of the visual attention point data, facial micro-expression data, electroencephalogram data, skin electricity data, walking path selection data and residence time data of the subjects.

7. The method of claim 6, wherein the method is characterized by, Step 3 is specifically as follows: Step 3.1, using artificial intelligence deep learning algorithm; Step 3.2, taking the human factor perception data and space design variable data as input; Step 3.3, coupling analysis and research are carried out to establish a variable database of the route-finding task and human factor perception data in different slow spaces.

8. The method of claim 7, wherein the method is characterized by, Through the subjects wearing VR devices and human factor data acquisition experiment devices to collect eye tracking data, facial recognition data and VR experience data of the subjects, and based on the decision tree and self-organizing mapping neural network, a parameter coupling analysis model is constructed to simulate the parameter relationship between multiple variables, and a variable database of the route-finding task and human factor perception data in different slow spaces is established.

9. The method of claim 8, wherein, Step 4 is specifically as follows: Step 4.1, artificial intelligence data visualization analysis; Step 4.2, identifying key variables of human factor design; Step 4.3, obtaining the urban slow space planning and design method for optimizing the route-finding task under the guidance of human factor technology.

10. The method of claim 9, wherein the method is characterized by, Based on the variable database of the route-finding task and human factor perception data in different slow spaces, machine learning and deep learning algorithms including decision tree, random forest and convolutional neural network are used to identify key variables of human factor design.

Images