Building emergency evacuation behavior prediction system based on emotion infection

Abstract

The invention relates to the field of public safety, in particular to a building emergency evacuation behavior selection research method based on emotion infection. According to the method, emotional infection intensity data is obtained through a questionnaire, a hybrid selection model (HCM) considering emotional infection is constructed, and a P-SIR model combining an OCEAN model and an SIR infectious disease model is introduced to simulate the emotional infection process. Anylogic simulation software is used for carrying out a simulation experiment on path selection of evacuated people, and the influence of psychological latent variables such as emotional infection on emergency evacuation path selection is explored. According to the method, the problems that in existing research, an emotion infection model is not considered carefully, and psychological factors in a mixed selection model are not considered comprehensively are solved, the accuracy and practicability of an emergency evacuation model are improved, and theoretical support and basis are provided for an emergency management department to formulate an effective library emergency evacuation management strategy and building design specifications.

Description

Technical Field

[0001] The present invention relates to the field of early warning systems, and in particular to a building emergency evacuation behavior prediction system based on emotional contagion. Background Art

[0002] With my country's rapid economic development and accelerated urbanization, safety issues in large public spaces have become increasingly prominent. Emergency evacuation in crowded places, such as university libraries, has become a crucial component of public safety research. During emergencies such as fires, pedestrians' perception of risk often quickly transforms into negative emotions such as anxiety and panic, which spread rapidly among the crowd. This contagious emotion can easily lead to serious accidents such as chaos and stampedes. According to data, since the founding of the People's Republic of China, serious fires in Chinese universities have caused losses totaling nearly 1.18 billion yuan, including casualties and significant property damage. As hubs for cultural knowledge and crucial venues for student learning and advancement, libraries, with their dense populations, complex structures, diverse functions, complex hazards, and fixed exits, are key locations for fire safety management.

[0003] In recent years, scholars both domestically and internationally have conducted extensive research on emergency evacuation from various perspectives, including behavioral and psychological ones. Both research and practice have demonstrated that the generation and spread of panic in groups is a significant contributor to the high number of casualties in emergencies. However, modeling and simulation of emotional contagion in groups during emergencies remain challenging in terms of accuracy and practicality. Existing research has primarily focused on factors such as the generation mechanisms of emergency evacuation environments, group size, and information dissemination and feedback. However, consideration of the impact of psychological factors on people's emergency evacuation behavior remains incomplete. In particular, emotional contagion, a crucial influencing factor, has received insufficient attention in previous research.

[0004] Traditional epidemiologically based models of emotional contagion lack detailed population classification and fail to fully account for individual differences and bidirectional interactions. Furthermore, there is a lack of research examining the mechanism by which emotional contagion intensity, as a psychological latent variable, influences emergency evacuation behavior choices. Therefore, in emergency evacuation research, how to more accurately describe and simulate the emotional contagion process and its impact on people's emergency evacuation behavior choices has become a pressing issue.

[0005] In order to solve the above problems, the present invention proposes a research method for building emergency evacuation behavior selection based on emotional contagion. Summary of the Invention

[0006] The purpose of the present invention is to provide a building emergency evacuation behavior prediction system based on emotional contagion to solve the problems in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a building emergency evacuation behavior prediction system based on emotional contagion, comprising:

[0008] A data collection module is used to collect personal socioeconomic attribute data of people in the building and emotional contagion intensity data based on the Big Five Personality Inventory through questionnaires;

[0009] Model building modules for:

[0010] Construct a structural equation model to analyze the relationship and mechanism between individual socioeconomic attributes and latent variables, as well as between each latent variable, including the intensity of emotional contagion;

[0011] A mixed logit model without considering emotional contagion was constructed as a control model;

[0012] A hybrid choice model considering emotional contagion is constructed. This model incorporates the intensity of emotional contagion as a psychological latent variable into the discrete choice model, and combines the OCEAN model and the SIR epidemic model to construct a P-SIR model to simulate the emotional contagion process.

[0013] The simulation experiment module is used to simulate the emergency evacuation route selection of buildings using AnyLogic simulation software. Parameters such as building layout, evacuation exit location and number are input, and simulations are performed based on a mixed logit model that does not consider latent variables and a mixed choice model that considers emotional contagion. The module outputs evacuation results such as evacuation time, exit selection, and congestion level.

[0014] The result analysis module is used to compare and analyze the simulation results of the mixed logit model without considering latent variables and the mixed selection model considering emotional contagion, evaluate the impact and mechanism of emotional contagion on building emergency evacuation behavior, and the evacuation efficiency of each model in different evacuation periods.

[0015] Optionally, the design of the questionnaire comprehensively considers factors such as personal socioeconomic attributes, personality traits, and psychological latent variables of personnel, determines the attributes of alternative options, and then designs a questionnaire suitable for studying the emergency evacuation behavior choices of building groups, and distributes it in a combination of online and offline methods.

[0016] Optionally, the structural equation model in the model building module is used to determine the relationship between various latent variables and analyze the relationship and mechanism of action between psychological latent variables and personal socioeconomic attributes.

[0017] Optionally, the simulation experiment module also includes a comparative analysis function, which is used to compare the simulation results of the mixed Logit model that does not consider latent variables and the mixed selection model that considers emotional contagion from three aspects: evacuation time, path selection, and congestion level, to further explore the degree of influence and mechanism of psychological latent variables such as emotional contagion on the selection of emergency evacuation paths in buildings.

[0018] Optionally, the result analysis module can also output a heat map to intuitively display the evacuation process and crowd congestion level of different models at different evacuation periods.

[0019] Optionally, the system is particularly suitable for predicting emergency evacuation behavior in public places with dense crowds and complex structures, such as university libraries.

[0020] Beneficial effects: 1. The present invention deeply analyzes the generation and contagion mechanism of group emotions under emergencies, combines the Big Five Personality Inventory (NEO) to obtain emotional contagion intensity data, incorporates it into the discrete choice model as a psychological latent variable, and constructs a hybrid choice model (HCM) that considers emotional contagion. This innovative method not only comprehensively considers the observable variables that affect the behavioral choices of evacuees, such as gender, age, etc., but also deeply explores the latent variables that cannot be directly observed, especially the impact of emotional contagion intensity on emergency evacuation behavior decisions. This enables the model to more realistically reflect the behavioral choices of personnel in emergency situations, improving the accuracy and practicality of the model.

[0021] 2. This paper introduces the P-SIR model, a combination of the OCEAN model and the SIR epidemic model, to more accurately simulate the emotional contagion process. This improvement not only overcomes the limitations of traditional emotional contagion models, such as their inadequate classification of populations, their failure to fully account for individual differences, and their two-way interactivity, but also enables the model to more accurately describe and predict the spread and evolution of group emotions during emergencies, providing a more scientific basis for emergency evacuation management.

[0022] 3. By using AnyLogic simulation software to simulate evacuees' route selection, this paper further explored the influence and mechanism of psychological latent variables such as emotional contagion on emergency evacuation route selection in university buildings during fires. This not only helps us better understand the underlying mechanisms of evacuees' choice of routes, but also provides theoretical support and basis for emergency management departments to formulate effective emergency evacuation management strategies and architectural design specifications for libraries. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the technical route of an embodiment of the present invention; DETAILED DESCRIPTION

[0024] The following describes preferred embodiments of the present invention with reference to the accompanying drawings to make its technical content clearer and easier to understand. The present invention can be embodied in many different forms, and the scope of protection of the present invention is not limited to the embodiments mentioned herein.

[0025] This paper proposes a research method for selecting behavior during building emergency evacuation based on emotional contagion. By deeply analyzing the generation and contagion mechanisms of group emotions during emergencies, this method constructs a hybrid selection model that considers emotional contagion. Furthermore, it introduces the P-SIR model, which combines the OCEAN model with the SIR infectious disease model, to simulate the emotional contagion process. Using AnyLogic simulation software, this method simulates evacuees' path choices, further exploring the impact of psychological latent variables such as emotional contagion on emergency evacuation path selection. This approach provides theoretical support and a basis for emergency management departments to formulate effective library emergency evacuation management strategies and building design specifications.

[0026] The present invention aims to solve the problems in existing research that the emotional contagion model is not considered in detail and the psychological factors are not considered comprehensively in the hybrid choice model. By analyzing the generation and contagion mechanism of group emotions in university libraries under emergencies, the emotional contagion intensity data are obtained by combining the Big Five Personality Inventory (NEO) questionnaire, and the data are incorporated into the discrete choice model as a psychological latent variable to construct a hybrid choice model (HCM) considering emotional contagion. At the same time, the P-SIR model, which combines the OCEAN model and the SIR infectious disease model, is introduced to simulate the emotional contagion process in more detail. Finally, the path selection of evacuees is simulated by Anylogic simulation software to further explore the influence of psychological latent variables such as emotional contagion on the choice of emergency evacuation paths.

[0027] Questionnaire design and survey

[0028] To obtain data on emotional contagion intensity, this study designed an emergency evacuation behavior decision-making questionnaire based on the Big Five Personality Inventory (NEO). The questionnaire comprehensively considered factors such as individuals' socioeconomic attributes, personality traits, and psychological latent variables, determined the attributes of alternative options, and then designed a questionnaire suitable for studying emergency evacuation behavior choices among library groups.

[0029] The questionnaire was distributed through a combination of online and offline methods. Before the large-scale formal survey, a pre-survey was conducted to collect samples to test the validity of the questionnaire. Based on the results of the pre-survey, the questionnaire was modified and improved to form the formal questionnaire.

[0030] Constructing a hybrid selection model based on emotional contagion

[0031] This paper constructs a hybrid choice model (HCM) that considers emotional contagion to analyze the emergency evacuation behavior decisions of university libraries during emergencies. The model fully considers the influence of unobservable psychological latent variables such as personality traits and emotional contagion on the emergency evacuation behavior choices of university libraries.

[0032] Specifically, this paper utilizes the survey data to incorporate emotional contagion intensity as a psychological latent variable into a discrete choice model. Furthermore, a P-SIR model is constructed by combining the OCEAN model with the SIR epidemic model to simulate the emotional contagion process. The parameters in the P-SIR model are adjusted and optimized based on the survey data to ensure the model's accuracy and practicality.

[0033] When constructing a mixed choice model, this paper employed methods such as structural equation modeling to analyze the relationships and mechanisms between individual socioeconomic attributes and latent variables, as well as between each latent variable. By comparing the explanatory power and fitting accuracy of discrete choice models without latent variables and mixed choice models with latent variables, this paper provides an in-depth analysis of the impact and mechanisms of emotional contagion during library emergency evacuations.

[0034] Anylogic simulation experiment

[0035] To verify the effectiveness and practicality of the hybrid selection model, the present invention used AnyLogic simulation software to conduct a simulation experiment on the path selection of evacuees. In the simulation experiment, the present invention set different evacuation scenarios and parameter combinations to simulate the emergency evacuation process under different circumstances.

[0036] Specifically, the present invention constructs a mixed logit model (ML) that does not consider emotional contagion and a hybrid choice model (HCM) that does, for comparative analysis. The P-SIR model is introduced into the HCM to simulate the emotional contagion process. Through simulation experiments, the present invention obtains evacuation process data for different models at different evacuation times, including indicators such as evacuation time, exit selection, and congestion level.

[0037] Through comparative analysis of simulation results, the present study found that the HCM model exhibited higher evacuation efficiency and a more orderly evacuation process in the middle and late stages of the evacuation. This demonstrates the superiority and accuracy of the hybrid choice model considering emotional contagion in describing and predicting crowd evacuation behavior choices during emergencies.

[0038] Technology Roadmap

[0039] Figure 1The technical roadmap for this invention is presented. As can be seen from the figure, the research process includes questionnaire design and survey, construction of a mixed choice model based on emotional contagion, AnyLogic simulation experiments, and analysis and application of the results. Each stage includes specific research content and methods to ensure the systematic and scientific nature of the research.

[0040] The research method for selecting building emergency evacuation behaviors based on emotional contagion provided by the present invention has a significant beneficial effect in solving the emergency evacuation problem in large public places.

[0041] Improved the accuracy and practicality of emergency evacuation models

[0042] This paper, based on an in-depth analysis of the generation and contagion mechanisms of group emotions during emergencies, constructs a hybrid choice model (HCM) that accounts for emotional contagion. This model not only considers observable variables that influence evacuees' behavioral choices, such as gender and age, but also explores latent variables that are not directly observable, particularly the impact of emotional contagion intensity on emergency evacuation decisions. This enables the model to more realistically reflect individuals' behavioral choices in emergency situations, improving its accuracy and practicality.

[0043] Provides theoretical support for emergency management and architectural design

[0044] This study simulated evacuees' path selection using AnyLogic simulation software, further exploring the impact of psychological latent variables such as emotional contagion on emergency evacuation path selection. This not only helps us gain a deeper understanding of the underlying mechanisms of evacuees' preferences but also provides theoretical support and a basis for emergency management departments to formulate effective library emergency evacuation management strategies and architectural design specifications. By optimizing evacuation paths and exit locations, it is possible to reduce congestion and risk during evacuations, thereby improving evacuation efficiency and safety.

[0045] Promoted the development of emergency evacuation research

[0046] The proposal and implementation of this invention have advanced emergency evacuation research. By incorporating psychological factors such as emotional contagion, this invention enriches the research content and methods of emergency evacuation models. Furthermore, by applying advanced technologies such as AnyLogic simulation software, this invention improves the efficiency and accuracy of emergency evacuation research. This provides new ideas and methods for future emergency evacuation research.

[0047] Example 1: Questionnaire design and survey

[0048] In this example, a questionnaire on emergency evacuation behavior decision-making was designed in conjunction with the Big Five Personality Inventory (NEO). The questionnaire included basic personal information, personality trait assessment, and emergency evacuation behavior choices. A questionnaire survey was conducted among university library faculty and students using a combination of online and offline methods, resulting in 326 valid questionnaires. The questionnaire data was statistically analyzed to obtain data on the evacuees' socioeconomic attributes, personality traits, and emotional contagion intensity.

[0049] Example 2: Constructing a hybrid selection model based on emotional contagion

[0050] In this example, a hybrid choice model (HCM) based on emotional contagion was constructed using the questionnaire data obtained in Example 1. First, the relationships and mechanisms between individual socioeconomic attributes and latent variables, as well as between each latent variable, were analyzed using methods such as structural equation modeling. Then, a P-SIR model was constructed by combining the OCEAN model and the SIR infectious disease model to simulate the emotional contagion process. Finally, an HCM model was constructed by incorporating latent variables such as emotional contagion intensity into a discrete choice model. The explanatory power and fitting accuracy of the discrete choice model without latent variables were compared with the HCM model.

[0051] Example 3: AnyLogic simulation experiment

[0052] In this example, AnyLogic simulation software was used to simulate evacuee route selection. First, a mixed logit model (ML) without considering emotional contagion and a hybrid choice model (HCM) with emotional contagion were constructed for comparative analysis. Different evacuation scenarios and parameter combinations were then set to simulate emergency evacuation processes under different circumstances. Finally, simulation data for different models at different evacuation times was obtained, including metrics such as evacuation time, exit selection, and congestion levels. The simulation results were then compared, analyzed, and discussed.

[0053] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from all points of view, the embodiments should be regarded as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim to which they relate.

[0054] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A building emergency evacuation behavior prediction system based on emotional contagion, characterized by: include: A data collection module is used to collect personal socioeconomic attribute data of people in the building and emotional contagion intensity data based on the Big Five Personality Inventory through questionnaires; Model building modules for: Construct a structural equation model to analyze the relationship and mechanism between individual socioeconomic attributes and latent variables, as well as between each latent variable, including the intensity of emotional contagion; A mixed logit model without considering emotional contagion was constructed as a control model; A hybrid choice model considering emotional contagion is constructed. This model incorporates the intensity of emotional contagion as a psychological latent variable into the discrete choice model, and combines the OCEAN model and the SIR epidemic model to construct a P-SIR model to simulate the emotional contagion process. The simulation experiment module is used to simulate the emergency evacuation route selection of buildings using AnyLogic simulation software. Parameters such as building layout, evacuation exit location and number are input, and simulations are performed based on a mixed logit model that does not consider latent variables and a mixed choice model that considers emotional contagion. The module outputs evacuation results such as evacuation time, exit selection, and congestion level. The result analysis module is used to compare and analyze the simulation results of the mixed logit model without considering latent variables and the mixed selection model considering emotional contagion, evaluate the impact and mechanism of emotional contagion on building emergency evacuation behavior, and the evacuation efficiency of each model in different evacuation periods.

2. The system according to claim 1, wherein: The design of the questionnaire comprehensively considers factors such as personal socioeconomic attributes, personality traits, and psychological latent variables of personnel, determines the attributes of alternative options, and then designs a questionnaire suitable for studying the emergency evacuation behavior choices of building groups, and distributes it in a combination of online and offline methods.

3. The system according to claim 1, wherein: The structural equation model in the model building module is used to determine the relationship between various latent variables and analyze the relationship and mechanism of action between psychological latent variables and personal socioeconomic attributes.

4. The system according to claim 1, wherein: The simulation experiment module also includes a comparative analysis function, which is used to compare the simulation results of a mixed logit model that does not consider latent variables and a mixed choice model that considers emotional contagion in terms of evacuation time, route selection, and congestion level, and further explore the influence and mechanism of psychological latent variables such as emotional contagion on the selection of emergency evacuation routes in buildings.

5. The system according to claim 1, wherein: The result analysis module can also output a heat map to visually display the evacuation process and crowd congestion level of different models at different evacuation periods.

6. The system according to claim 1, wherein: The system is particularly suitable for predicting emergency evacuation behavior in public places with dense crowds and complex structures, such as university libraries.

Images