A method and apparatus for determining a fire assistance strategy for a nursing home

Abstract

The present disclosure relates to the technical field of computer, and particularly provides a method and device for determining a fire assistance strategy of a nursing home. The method comprises: constructing a heterogeneous model of a plurality of heterogeneous individuals in the nursing home, a fire evacuation movement model constructed based on a fire evacuation force, and a fire simulation model; the fire evacuation force at least comprises a driving force, an interaction force, a wall repulsion force, and an assistance willingness and an assistance force; in the process of simulating a fire scene of the nursing home by using the fire simulation model, the fire evacuation movement model and the heterogeneous model are used to simulate a plurality of preset fire assistance strategies to obtain a plurality of simulation results; and a preset fire assistance strategy corresponding to a target simulation result in the plurality of simulation results is determined as a target fire assistance strategy. The present disclosure can simulate the environmental complexity, the heterogeneity of personnel and the assistance behavior under the fire scene of the nursing home, so that the finally determined fire assistance strategy can shorten the evacuation time and reduce the casualties.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method and apparatus for determining a fire assistance strategy for a nursing home. Background Technology

[0002] Because the elderly have weaker mobility and slower reaction time, they already face difficulties during evacuation. In nursing homes, the proportion of elderly residents is particularly high, which further increases the difficulty of effectively organizing evacuations.

[0003] In related technologies, scholars have conducted extensive research on pedestrian evacuation in various environments (such as high-rise buildings, subway stations, tunnels, staircases, etc.), using methods primarily including real-world evacuation experiments, virtual reality experiments, and numerical simulations. However, considering the physiological characteristics of the elderly, organizing large-scale participation of the elderly in real-world evacuation or virtual reality experiments is clearly not feasible. Therefore, in research on evacuation for the elderly, real-world experiments are mainly conducted in two ways: recruiting elderly people to conduct movement characteristic analysis in non-evacuation scenarios, or recruiting able-bodied adult volunteers to simulate the role of the elderly in evacuation experiments. While these methods can provide some basic data, they are difficult to realistically reproduce the heterogeneous behavior and complex social interactions of the elderly population under the pressure of a fire emergency, resulting in low accuracy of fire evacuation methods. Summary of the Invention

[0004] This disclosure is made in view of the above-mentioned problems. This disclosure provides a method and apparatus for determining fire assistance strategies for nursing homes.

[0005] According to one aspect of this disclosure, a method for determining fire assistance strategies for nursing homes is provided, comprising:

[0006] A heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model are constructed. The fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between the heterogeneous individuals and other heterogeneous individuals, the repulsive force between the individual and the walls of the nursing home, and the willingness to assist and the assisting force between the individual being assisted. In simulating a fire scenario in a nursing home using the fire simulation model, the fire evacuation movement model and the heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scenario using various preset fire assistance strategies, resulting in multiple simulation results; each simulation result includes evacuation time and casualty rate. The preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results is determined as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

[0007] According to another aspect of this disclosure, a device for determining a fire assistance strategy for a nursing home is provided, comprising: The construction module is used to construct a heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model; wherein, the fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between the heterogeneous individuals and other heterogeneous individuals, the repulsive force between the heterogeneous individuals and the walls of the nursing home, and the willingness to assist and the assisting force between the heterogeneous individuals being assisted. The simulation module is used to simulate the fire scene of the nursing home using the fire simulation model, and to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scene using the fire evacuation movement model and the heterogeneous model, and to obtain multiple simulation results; wherein each simulation result includes evacuation time and casualty rate. The processing module is used to determine the preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

[0008] In another aspect of exemplary embodiments of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the methods described in exemplary embodiments of this disclosure.

[0009] In another aspect of exemplary embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods described in exemplary embodiments of the present disclosure.

[0010] In another aspect of the exemplary embodiments of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in the exemplary embodiments of this disclosure.

[0011] As will be described in detail below, a method and apparatus for determining fire assistance strategies in a nursing home according to an embodiment of this disclosure involves constructing a heterogeneous model of multiple heterogeneous individuals in the nursing home, a fire evacuation movement model based on fire evacuation forces, and a fire simulation model. The fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between them and other heterogeneous individuals, the repulsive force between them and the walls of the nursing home, and the willingness to assist and the assisting force between them and the heterogeneous individuals being assisted. In simulating a fire scenario in a nursing home using the fire simulation model, the fire evacuation movement model and the heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scenario using various preset fire assistance strategies. Multiple simulation results were obtained, each including evacuation time and casualty rate. The preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results was determined as the target fire assistance strategy. The target fire assistance strategy was used to conduct fire evacuation in a fire scenario in a nursing home. This system can simulate the environmental complexity, heterogeneity of personnel, and assistance behavior in a fire scenario in a nursing home. By conducting fire evacuation simulation through diversified fire assistance strategies, a fire assistance strategy adapted to the fire scenario was finally determined. Using this fire assistance strategy to conduct fire evacuation in a nursing home can shorten evacuation time, reduce casualties, and thus maximize the protection of the lives of the elderly. This has important theoretical value and practical significance.

[0012] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description

[0013] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0014] Figure 1 A flowchart illustrating a method for determining a fire assistance strategy for a nursing home, provided by an exemplary embodiment of this disclosure, is shown. Figure 2 The simulation results of various preset fire assistance strategies provided by the exemplary embodiments of this disclosure are shown in the diagram. Figure 3 A comparison diagram of simulation results for various pre-motion models provided by exemplary embodiments of this disclosure is shown; Figure 4 The exemplary embodiments of this disclosure illustrate recommended assistance strategies for 30 scenarios. Figure 5A schematic diagram of the structure of the device for determining a fire assistance strategy for a nursing home provided in an exemplary embodiment of this disclosure is shown. Figure 6 A schematic diagram of the structure of an electronic device provided in an exemplary embodiment of this disclosure is shown; Figure 7 A schematic diagram of the structure of a computer system provided in an exemplary embodiment of this disclosure is shown. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this disclosure more apparent, exemplary embodiments according to this disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments of this disclosure. It should be understood that this disclosure is not limited to the exemplary embodiments described herein.

[0016] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0017] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0018] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0019] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0020] While real-world evacuation experiments specifically targeting the elderly are not entirely lacking in related technologies, some scholars have conducted evacuation experiments with 25 elderly volunteers in rooms with multiple hidden exits, as well as a full-scale train evacuation experiment (including 8 elderly participants) encompassing four scenarios: platforms, stairs, and exits with a 750mm drop. This innovative experiment yielded an important conclusion: pedestrian heterogeneity has a decisive impact on the evacuation efficiency of non-standard routes. However, such experiments require significant effort to ensure the safety of elderly volunteers, and implementation in environments with high concentrations of elderly people, such as nursing homes, would be even more challenging. Therefore, more scholars are choosing to conduct numerical simulation studies of the elderly evacuation process by improving micro-models such as cellular automata models, social force models, and heterogeneous individual-based models.

[0021] There are two main approaches to improving cellular automata models: one is to construct heterogeneous pedestrian models (such as the elderly and disabled) that consider differences in walking speed and occupied space, to simulate mixed-flow evacuation behavior in environments including one-way and two-way corridors, hospital lobbies, and nursing homes, where vulnerable groups are present; the other is to improve the model by introducing new rules, such as incorporating priority rules for vulnerable groups and avoidance mechanisms, achieving a "slow is fast" effect. These improved models integrate the movement characteristics of heterogeneous elderly people from different perspectives, and can calculate and update the speed and position of each pedestrian based on rules or differential equations. Based on simulation results, evacuation strategies and facility layouts can be optimized. However, existing research still has three key issues that have been overlooked: 1. Complex and Variable Environmental Factors. In single-story nursing homes, the internal space typically includes living areas, activity areas, and nurses' work areas. There is a dynamic correlation between the spatial topology of the fire source location and evacuation exits, and the distribution characteristics of the population, which determines the direction of fire spread, the availability of evacuation routes, and the difficulty of rescue. Therefore, the complex scenario constituted by factors such as the fire source location and the distribution of elderly residents directly affects the selection of evacuation routes and the safety of the elderly. Although existing research confirms that the location of obstacles has a significant impact on evacuation outcomes, studies on the differentiated impact of various complex environmental factors within nursing homes on evacuation outcomes are still significantly lacking.

[0022] 2. Mutual Assistance Behavior Among the Elderly. Based on their physical functions, the elderly can generally be divided into three categories: self-reliant elderly (able to walk freely), semi-self-reliant elderly (requiring walking aids or canes), and disabled elderly (unable to walk and requiring wheelchair assistance). With changing attitudes towards elder care, the number of self-reliant elderly choosing to reside in nursing homes is increasing, and their proportion is gradually surpassing that of semi-self-reliant and disabled elderly. Academic research has primarily focused on differential modeling of motor characteristics to address this phenomenon, but has neglected the crucial issue arising from this: mutual assistance behavior among the elderly. As the proportion of self-reliant elderly increases, some physically fit and willing self-reliant elderly may assist vulnerable groups during evacuation. This is expected to improve evacuation efficiency, but to the best of my knowledge, this issue has not yet received attention in previous research.

[0023] 3. Appropriate Caregiver Assistance Strategies. Clearly, caregiver assistance significantly improves evacuation efficiency, and most elderly individuals require assistance during evacuation. However, different elderly care institutions employ significantly different assistance strategies, such as targeted assistance, random assistance, and priority assistance. Current research on caregiver assistance strategies remains focused on comparing the differences between random and targeted assistance. Some studies even specify that caregivers only assist disabled elderly individuals, neglecting semi-independent or self-reliant elderly, which is clearly biased. Furthermore, the complexity of fire scenarios and the heterogeneity of the elderly population further complicate the development of assistance strategies. Therefore, optimizing caregiver assistance strategies based on specific scenario conditions such as spatial layout, personnel composition, and fire dynamics remains a crucial issue to be addressed.

[0024] In summary, current research on simulations of heterogeneous individual evacuation behavior in nursing home fire scenarios is lacking, particularly in the area of ​​mutual assistance among the elderly. Furthermore, traditional fixed assistance strategies are ill-suited to complex and ever-changing fire scenarios, leading to overly idealistic spatial layout optimization schemes and emergency response plans that fail to adequately consider the diverse needs of actual evacuation.

[0025] Therefore, in order to solve the above problems, this disclosure provides a method for determining fire assistance strategies for nursing homes. It can systematically simulate the environmental complexity, heterogeneity of personnel, and assistance behaviors in nursing home fire scenarios. Through fire evacuation simulation using diverse fire assistance strategies, it finally determines a fire assistance strategy that is suitable for the fire scenario. Using this fire assistance strategy for fire evacuation in nursing homes can shorten evacuation time, reduce casualties, and thus maximize the protection of the lives of the elderly. It has important theoretical value and practical significance.

[0026] The method for determining fire assistance strategies for nursing homes provided in this embodiment can be executed by a terminal or by a chip applied to the terminal.

[0027] For example, the terminal may include one or more of the following: mobile phone, tablet computer, wearable device, in-vehicle device, laptop computer, ultra-mobile personal computer (UMPC), netbook, PDA, and wearable device based on augmented reality (AR) and / or virtual reality (VR) technology. The exemplary embodiments disclosed herein do not impose specific limitations on these.

[0028] Figure 1A flowchart illustrating a method for determining a fire assistance strategy for a nursing home, as provided in an exemplary embodiment of this disclosure, is shown. Figure 1 As shown, the method for determining the fire assistance strategy of this nursing home includes: S101, construct a heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model; wherein, the fire evacuation forces include at least the driving force of heterogeneous individuals, the interaction force between heterogeneous individuals and other heterogeneous individuals, the repulsive force between the individual and the walls of the nursing home, and the willingness to assist and the assisting force between the individual being assisted. S102, In the process of simulating a fire scenario in a nursing home using a fire simulation model, a fire evacuation movement model and a heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals in a fire scenario using various preset fire assistance strategies, and multiple simulation results are obtained; among them, each simulation result includes evacuation time and casualty rate. S103, the preset fire assistance strategy corresponding to the target simulation result among multiple simulation results is determined as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

[0029] Specifically, in previous studies, most scholars have used circular, elliptical, or tri-circle models to represent the human body to simulate pedestrian movement. However, in evacuation studies of the elderly, directly applying these conventional human body models to semi-independent and disabled elderly individuals will obviously produce significant errors. Furthermore, there are currently no modeling studies specifically targeting semi-independent elderly individuals using walking aids, despite the continuously increasing number of such individuals in nursing homes. Therefore, to obtain more effective simulation results of nursing home fire evacuation processes, this disclosure's embodiments collected real top-view images of different types of elderly individuals and, combined with relevant parameters of wheelchairs and walking aids, established a more realistic human body model of the elderly.

[0030] According to the type of heterogeneous individuals, the present disclosure divides multiple heterogeneous individuals into caregivers and elderly people. The types of elderly people include, but are not limited to, self-reliant elderly people, semi-self-reliant elderly people, disabled elderly people, assisted self-reliant elderly people, assisted semi-self-reliant elderly people, and assisted disabled elderly people.

[0031] Based on this, the embodiments of this disclosure can effectively abstract the heterogeneous models of various types of heterogeneous individuals into ellipses of different sizes. The embodiments of this disclosure define the type of multiple heterogeneous individuals as: a set. G ={Caregivers (C), Independent Seniors (IE), Semi-Independent Seniors (SE), Disabled Seniors (DE), Assisted Independent Seniors (A-IE), Assisted Semi-Independent Seniors (A-SE), Assisted Disabled Seniors (A-DE)}, [This last part is incomplete and requires further context to translate accurately.] Represents a set G The Middle nTypes , Indicates nursing staff, Indicates self-reliant elderly people, This refers to semi-independent elderly people. Indicating disabled elderly people, This indicates that the elderly person who needs assistance with self-care, This indicates that the elderly who are partially self-reliant and require assistance are eligible for assistance. This refers to elderly people with disabilities who are receiving assistance. Accordingly, each heterogeneous individual... In a Cartesian coordinate system The middle part is modeled as an ellipse with the major semi-axis as the middle part. and short half shaft Characterize the ellipse, major axis With short axis The specific meaning varies depending on the category, as shown in Table 1.

[0032] Table 1 Major Axis With short axis Specific interpretation

[0033] in, Indicates heterogeneous individuals i Shoulder width; Indicates heterogeneous individuals i Her chest was thick; Indicates the length of the walking aid; Indicates the width of the wheelchair; This indicates the length of the wheelchair.

[0034] This disclosure aims to improve upon the classic social force model to more realistically simulate the movement behavior of elderly people and caregivers in a fire evacuation scenario in a nursing home. The classic social force model describes the movement of heterogeneous individuals in a complex environment through the driving force of the heterogeneous individual, the interaction force between the heterogeneous individual and other heterogeneous individuals, and the repulsive force between the heterogeneous individual and the walls of the nursing home. In the original social force model, the driving force of heterogeneous individuals propels them towards the exit, while the interaction force tries to avoid contact between heterogeneous individuals, making it difficult to simulate the assistive behavior of caregivers or self-reliant elderly people. Therefore, to better simulate the assistive behavior of heterogeneous individuals, this disclosure proposes a fire evacuation movement model by introducing the assistive willingness of heterogeneous individuals and the assistive force between heterogeneous individuals and the heterogeneous individuals being assisted.

[0035] The steps for constructing the fire evacuation movement model are as follows: Obtain the fire evacuation forces of heterogeneous individuals, which include at least the driving force of heterogeneous individuals, the interaction force between heterogeneous individuals and other heterogeneous individuals, the repulsive force between heterogeneous individuals and the walls of the nursing home, the willingness of heterogeneous individuals to assist, and the assistance force between heterogeneous individuals and the heterogeneous individuals being assisted; Based on the driving force of heterogeneous individuals, the interaction force between heterogeneous individuals and other heterogeneous individuals, the repulsive force between heterogeneous individuals and the walls of the nursing home, the willingness of heterogeneous individuals to assist, and the assistance force between heterogeneous individuals and the heterogeneous individuals being assisted, construct the fire evacuation movement model.

[0036] The specific process of constructing the fire simulation model is as follows: In fire evacuation scenarios, flame spread and smoke diffusion are the primary threats to personnel safety. Modeling these two physical phenomena is mainly based on computational fluid dynamics methods and has been widely applied in commercial software, such as the Fire Dynamics Simulator (FDS) developed by the National Institute of Standards and Technology (NIST). Numerous studies have confirmed the feasibility and effectiveness of using fire data acquired through FDS for pedestrian evacuation research. Therefore, this disclosure uses fire spread information simulated by FDS to study the evacuation process in a nursing home fire. The specific fire spread and smoke diffusion model is as follows:

[0037]

[0038] in, ρ Indicates position At the moment t The density of the mixed gas; Z This indicates the mass fraction originating from the fuel stream. Indicates a dimensionless parameter; Represents the gas velocity vector; Indicates the fuel diffusion coefficient. T represents temperature; This indicates the mass fraction of smoke and dust. This represents the diffusion coefficient of smoke and dust. This indicates the rate of smoke and dust formation. , The yield factor representing smoke and dust. Indicates volumetric fuel consumption rate; p It indicates air pressure.

[0039] Furthermore, heterogeneous individuals do not initiate evacuation behavior by directly seeing the fire source; their evacuation response is actually triggered by sensing thermal radiation, which is expressed as: ;in, Indicates the rate of ignition source release. This represents the maximum value of the ignition source release rate.

[0040] This embodiment uses FDS 6.3.0 to solve the fire dynamics process, and sets the fire as a t² growth type fire, where the change in the ignition source release rate is proportional to the square of the effective growth time t, that is: ;in, α This represents the fire growth factor, the rate of heat release when it reaches a certain level. Then it remains constant. In FDS, fire data is updated every 0.5 seconds.

[0041] Furthermore, appropriate assistance strategies play a crucial role in the efficiency of safe evacuation in nursing homes, especially for semi-independent and disabled elderly individuals. This disclosure focuses on evacuation assistance strategies employed by caregivers. Based on existing research and field surveys, caregiver assistance strategies can be categorized into four schemes, namely the aforementioned multiple preset fire assistance strategies, which may include: random assistance strategies (referred to as assistance strategy R), priority assistance strategies (referred to as assistance strategy P), and targeted assistance strategies (referred to as assistance strategy V), i.e., S∈{R,P,V}, where S represents the set of preset fire assistance strategies.

[0042] In the event of a fire, a certain response time is required to initiate evacuation. Once caregivers perceive an emergency, they will assist the elderly in evacuating according to pre-defined assistance strategies. All assistance strategies begin with caregivers searching for the elderly and end with the number of remaining caregivers in the nursing home exceeding the number of remaining elderly residents. However, the search and assistance processes differ between different strategies, as detailed below: Assistance strategy R (random assistance strategy): Caregivers directly assist the elderly person who is closest to them within the search range, regardless of the elderly person's type.

[0043] Assistance Strategy P (Priority Assistance Strategy): Caregivers assist elderly individuals within the search area according to a preset priority, determined based on the elderly individual's mobility. Therefore, this priority assistance strategy is further divided into two types: First, strong to weak priority: assisting the elderly individual with the strongest mobility within the search area; second, weak to strong priority: assisting the elderly individual with the weakest mobility within the search area. When multiple elderly individuals of the same type exist within the search area, caregivers will refer to assistance strategy R to assist the closest elderly individual.

[0044] Assistance Strategy V (Targeted Assistance Strategy): This is a one-to-one precise assistance strategy. Caregivers provide targeted assistance to elderly individuals within the search range based on a pre-defined list of heterogeneous individuals. Each caregiver is assigned a specific assistance recipient (heterogeneous individual) and assistance order, and must search for the designated elderly individuals in sequence and assist them in completing the evacuation. If the evacuation is not yet complete after completing the pre-defined assistance list, the caregiver will randomly assist the nearest elderly individual to continue the evacuation according to Assistance Strategy R.

[0045] Therefore, there are four types of preset fire assistance strategies in this embodiment.

[0046] Based on this, the embodiments of this disclosure can also utilize a fire simulation model to simulate a fire scenario in a nursing home. Within this fire scenario, a fire evacuation movement model and a heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals according to various preset fire assistance strategies, yielding multiple simulation results corresponding to each preset fire assistance strategy. Each simulation result includes evacuation time and casualty rate. Here, the practicality and effectiveness of each preset fire assistance strategy are quantitatively described using evacuation time from the perspective of evacuation efficiency and casualty rate from the perspective of heterogeneous individual safety. This allows for the determination of a target fire assistance strategy from among the multiple preset fire assistance strategies, and the use of the target fire assistance strategy for fire evacuation in the nursing home fire scenario.

[0047] Given the differences in dimensionality and magnitude between evacuation time and casualty rate, these indicators need to be normalized before integration. Since shorter evacuation times represent better performance, a min-max normalization method is used to calculate the evacuation time score, using the following formula:

[0048] in, This represents the normalized evacuation time score; Representing a fire scene o The longest evacuation time for multiple pre-set fire evacuation strategies; Representing a fire scene o Short evacuation time for multiple pre-set fire evacuation strategies Representing a fire scene o Pre-set fire evacuation strategy evacuation time = R, P or T .

[0049] On the other hand, the normalization of the casualty rate cannot rely solely on specific casualty figures, as this would weaken the severe impact of individual deaths. Therefore, embodiments of this disclosure introduce a casualty rate score. The formula for calculating the casualty rate score is as follows:

[0050] in, Indicates the casualty rate score; Representing a fire scene o Pre-set fire evacuation strategy The average number of deaths; Representing a fire scene o Pre-set fire evacuation strategy The average number of seriously injured persons; Representing a fire scene o Pre-set fire evacuation strategy The average number of people with minor injuries, with a weighting coefficient that is a custom setting in this embodiment of the disclosure.

[0051] The casualty scores were then standardized using a min-max normalization method.

[0052] in, A score representing the normalized casualty rate; Representing a fire scene o The highest casualty score for multiple pre-set fire evacuation strategies in China; Representing a fire scene o The lowest casualty score for multiple pre-set fire evacuation strategies; Representing a fire scene o The Middle i Casualty scores for pre-defined fire evacuation strategies.

[0053] Finally, the normalized evacuation time score and the normalized casualty rate score are integrated by weighted summation to calculate the comprehensive score of each preset fire evacuation strategy under different fire scenarios:

[0054] in, Representing a fire scene o Pre-set fire evacuation strategy The overall score; Weighting coefficients representing evacuation time; This represents the weighting coefficients for the casualty rate. Weights are set based on relevant research findings. This reflects the equal importance of evacuation time and casualty rate in evacuation assessment. The preset fire evacuation strategy (i.e., the target fire assistance strategy) with the highest overall score (i.e., the target simulation result) in each fire scenario will be selected as the most suitable assistance strategy for that fire scenario.

[0055] Based on this, the present disclosure provides a method for determining fire assistance strategies in nursing homes, which can use a multi-strategy comparison (MSC) framework to simulate the overall evacuation process of heterogeneous elderly individuals and caregivers in a fire within a nursing home. This framework consists of four models: a fire simulation model, a heterogeneous model (also known as a human model), multiple preset fire assistance strategies (also known as assistance strategy models), and a fire evacuation movement model (also known as a movement model). The fire simulation model provides real-time fire dynamic data, the heterogeneous model constructs physical models of heterogeneous individuals with different physiological characteristics, and the assistance strategy model generates differentiated caregiver assistance strategies and inputs them into the movement model. Furthermore, to accurately simulate the micro-interaction characteristics of the evacuation process in continuous space (such as the assistance behavior of caregivers and mutual assistance behavior among the elderly), this framework makes key improvements to the original social force model in the movement model: by adding an assistance force mechanism, it incorporates the assistance behaviors of self-reliant elderly individuals and caregivers, respectively. This realistically simulates the movement and assistance behaviors of heterogeneous groups during evacuation, and the effectiveness and realism of the model have been verified through numerous simulation experiments. Simultaneously, it obtains assistance strategy formulation rules applicable to the complex and ever-changing fire scenarios in nursing homes.

[0056] According to the technical solution of the exemplary embodiments of this disclosure, a heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation movement model based on fire evacuation forces, and a fire simulation model are constructed. The fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between them and other heterogeneous individuals, the repulsive force between them and the walls of the nursing home, and the willingness to assist and the assisting force between them and the heterogeneous individuals being assisted. In simulating a fire scenario in a nursing home using the fire simulation model, the fire evacuation movement model and the heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scenario using various preset fire assistance strategies, resulting in multiple simulation results. In this study, each simulation result includes evacuation time and casualty rate. The preset fire assistance strategies corresponding to the target simulation results from multiple simulations are identified as the target fire assistance strategy. This target fire assistance strategy is then used to conduct fire evacuation in a nursing home fire scenario. The study systematically simulates the environmental complexity, heterogeneity of personnel, and assistance behaviors in a nursing home fire scenario. Through diverse fire assistance strategies, fire evacuation simulations are conducted, ultimately determining a fire assistance strategy suitable for the fire scenario. Using this strategy for fire evacuation in a nursing home can shorten evacuation time, reduce casualties, and thus maximize the safety of the elderly population. This has significant theoretical and practical value.

[0057] The classic social force model (SFM) can be expressed as:

[0058]

[0059]

[0060]

[0061] in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals i The initial velocity; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing towards the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of a nursing home w They do not come into contact with each other.

[0062] To better simulate the assisting behavior of heterogeneous individuals, this disclosure proposes a fire evacuation movement model by introducing the assisting willingness of heterogeneous individuals and the assisting force between heterogeneous individuals and the heterogeneous individuals being assisted.

[0063] In some embodiments, the fire evacuation movement model can be an assistive social force model (A-SFM); the assistive social force model is expressed as:

[0064]

[0065]

[0066]

[0067]

[0068]

[0069] in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides;W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals i The initial velocity; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing towards the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individualsi and heterogeneous individuals j Or the walls of a nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1.

[0070] Assisting force is similar to driving force, but its direction is directed towards the heterogeneous individual being assisted. The selection of the heterogeneous individual being assisted is related to the heterogeneity of the individuals performing the assisting behavior and the assisting strategies employed. As mentioned before, caregivers ( The search and assistance for elderly people will be based on four preset fire assistance strategies, while self-reliant elderly people ( Mutual aid behavior among individuals is limited to assisting the nearest elderly person within their capabilities. Therefore, the selection of heterogeneous individuals to be assisted is defined as follows:

[0071] in, Indicates nursing staff; This refers to elderly people who are self-reliant. This refers to semi-independent elderly people; Indicates a disabled elderly person; This refers to elderly people who require assistance to care for themselves. This refers to semi-independent elderly people who require assistance; This refers to disabled elderly people receiving assistance; This indicates a random assistance strategy; Indicates priority assistance strategy; This indicates a targeted assistance strategy; Let S represent the set of preset fire assistance strategies, where S∈{R,P,T}; The weights represent preset priorities, used to ensure that caregivers assist heterogeneous individuals with higher priorities according to the preset priorities; This represents a small random perturbation term, used to avoid completely deterministic choices; This indicates a pre-defined list of heterogeneous individuals to assist. , This indicates the sequence number of the heterogeneous individual currently being assisted. This represents the total number of heterogeneous individuals who receive assistance.

[0072] Willingness to assist is a crucial improvement in adjusting driving forces and interaction forces, ensuring the feasibility of assistive behavior. Interaction forces are originally intended to prevent disorderly collisions between heterogeneous individuals, but when heterogeneous individuals develop a willingness to assist, they will actively approach the heterogeneous individual being assisted, at which point the strength and range of the interaction forces will change. Therefore, through... and Ensure that heterogeneous individuals can successfully carry out assistance behaviors when they have the willingness to help.

[0073] For example, the adjusted strength of social force is expressed as:

[0074] The adjusted scope of social influence is expressed as follows:

[0075] On the other hand, regarding the probability of assistance Caregivers have a fixed probability of assisting (1), while the probability of assisting self-reliant elderly people is affected by factors such as their own attributes, the density of the surrounding population, and the fire situation.

[0076] For example, the assist probability is represented as:

[0077]

[0078] in, Indicates nursing staff; This refers to elderly people who are self-reliant. , and Indicates the adjustment factor; Indicates heterogeneous individuals i Heterogeneous properties; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates the search range The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed.

[0079] A-SFM realizes cooperative behavior among heterogeneous individuals. However, in a fire environment, factors such as fire source, heat radiation, and smoke can significantly affect pedestrian visibility, walking speed, probability of assistance, and evacuation route selection. Therefore, to more accurately simulate individual behavior during fire evacuation, the fire evacuation forces in this embodiment can also incorporate the fire source repulsion force, smoke avoidance force, and random disturbance force caused by panic of heterogeneous individuals, extending A-SFM into a fire assistance social force model (FA-SFM).

[0080] The social force model for fire assistance is represented as follows:

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090]

[0091]

[0092]

[0093]

[0094]

[0095] in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individualsi With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The repulsive force of the fire source; Indicates heterogeneous individuals i Its ability to avoid smoke; Indicates heterogeneous individuals i Random disturbances caused by panic; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals during fire evacuation. i At any moment t Effective speed; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals iand heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing towards the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of a nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; This indicates the intensity of the repulsive force from the fire source; Indicates the range of action of the repulsive force from the fire source; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i A normalized vector pointing to the source of the fire; This indicates the mass fraction originating from the fuel stream. Indicates a dimensionless parameter; Represents the small perturbation term; Indicates the flue gas avoidance coefficient; Indicates time t Smoke concentration at the location; This indicates the mass fraction of smoke and dust. This represents the panic intensity coefficient, which is related to the degree of environmental danger at the current location of a heterogeneous individual. , Indicates the basic random strength. This represents the enhancement coefficient of the fire source. Indicates the smoke enhancement factor; Indicates time t Fire hazard parameters at the location; This represents Gaussian white noise. , where I represents the identity matrix; Indicates heterogeneous individuals i The initial velocity; This represents the visibility attenuation term; Represents the visibility coefficient; This represents the thermal radiation attenuation term; Indicates the thermal emissivity; Indicates time t The intensity of thermal radiation at the location; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1. This represents the inhibition coefficient of the fire scene environment on the probability of assistance; This refers to caregivers among multiple heterogeneous individuals; This refers to a self-reliant elderly person among multiple heterogeneous individuals; , and Indicates the adjustment factor; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates time t Heterogeneous individuals i Search scope The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed; Indicates heterogeneous individuals i The acceleration; Indicates heterogeneous individuals i At any moment t Location; Indicates heterogeneous individuals i The initial position.

[0096] To realistically simulate the heterogeneous behavior of different individuals during a fire evacuation in a nursing home, this embodiment establishes a simulation environment based on the MSC framework, and calibrates the parameters by combining field survey results with existing research. Subsequently, a virtual experimental environment is constructed to verify the feasibility of the proposed framework and the effectiveness of mutual assistance behaviors.

[0097] 1. Construction of a simulation environment based on the MSC framework: As previously stated, this disclosure improves the social force model by reconstructing the behavioral models of heterogeneous individuals and groups and incorporating helping forces and willingness to help into the original model. Considering the operability of modifying the underlying logic, this disclosure compares various simulation software based on the social force model and ultimately selects Anylogic Professional 8.8.5, running on the JAVA 2.0 platform, as the base software to establish the simulation environment based on the MSC framework. All simulation experiments will be run on a computer platform equipped with an Intel Core i5-10210U 1.60GHz processor and 4GB of memory.

[0098] 1.1 Human body model reconstruction: Based on the above classification of elderly individuals, seven heterogeneous individuals were constructed: caregivers (C), self-reliant elderly (IE), semi-disabled elderly (SE), disabled elderly (DE), assisted self-reliant elderly (A-IE), assisted semi-disabled elderly (A-SE), and assisted disabled elderly (A-DE). The original circular human body model was reconstructed into an elliptical shape using the Anylogic heterogeneous individual module. Although this embodiment distinguishes individual gender based on physiological characteristics such as weight, shoulder width, and chest thickness, it ignores the influence of gender on individual behavior during fire evacuation. This embodiment sets different sized human body models for males and females, while maintaining consistent parameters such as movement speed and assisting probability for individuals of the same type but different genders. Furthermore, heterogeneous individuals of the same type are randomly generated into male and female genders with a 1:1 probability.

[0099] 1.2. Fulfillment of Assisted Behavior: As the basis for implementing assisted behavior, the embodiments of this disclosure first need to define the search range. According to relevant research, under normal circumstances, an individual's visual field angle is 170°, and the visual depth is approximately 10 meters. However, as visual depth increases, the visual field angle decreases accordingly. Therefore, when an individual's attention is focused on a long-distance, wide-area search, their visual field angle needs to be narrowed to 120° to achieve a visual depth of 10 meters. This range can be defined as the search range of the caregiver (C). Unlike caregivers who need to search a wide area for elderly individuals, self-reliant elderly individuals (IEs) who have the willingness to assist tend to assist individuals in their vicinity and will not provide assistance to individuals at a distance. Based on relevant research results, the embodiments of this disclosure reduce the search range of IEs to 3 meters while increasing their visual field angle to 170°.

[0100] Subsequently, this embodiment of the disclosure requires assigning different states (STs) to heterogeneous individuals through a state diagram module to achieve assisted behavior. Four states are set for caregivers (C) and self-reliant elderly individuals (IE): , Indicates heterogeneous individuals i At any momentt state, Other heterogeneous individuals only retain the movement state, i.e. , At the same time, by default, IE, SE, and DE are included in the "Waiting for Assistance" set. When they merge into a group, they are removed from the set, and new heterogeneous individuals receiving assistance, A-IE, A-SE, or A-DE, are generated simultaneously. Furthermore, the state transition model between caregivers and self-reliant elderly is as follows:

[0101] in, Indicates heterogeneous individuals i At any moment t state, ; Indicates heterogeneous individuals i heterogeneous individuals being assisted The distance between their centroids; Indicates the preset merging distance.

[0102] It should be noted that, due to the large search range of caregivers, recalculating the distance at each time step could lead to unreasonable oscillations. Therefore, this embodiment of the disclosure stipulates that caregivers will not change the assistance target midway; that is, after selecting an assistance target, unless the target is assisted first by a nearby self-reliant elderly person, the caregiver will not return to the search state. Furthermore, when waiting for an assistance set... When the field is empty, the nursing staff will initiate the autonomous evacuation procedure, and their movement direction will be directly towards the exit.

[0103] 1.3 Injury and Casualty Rules Setting: In addition to simulating the movement behavior and decision-making processes of different individuals during fire evacuation, this disclosure also considers the varying degrees of risk posed by the spread of fire, such as the risk of burns due to excessive heat and the risk of poisoning from excessive inhalation of harmful gases. Therefore, this disclosure employs a dual injury mechanism of burns and poisoning to formulate injury and death rules during fire evacuation.

[0104] The human body has a limited tolerance to high temperatures and toxic gases, a process that gradually accumulates and changes with environmental conditions and duration of exposure. Therefore, this disclosure employs an effective dose fraction model to construct this process, considering heterogeneous individuals. i The total cumulative damage effect of burns and toxic gases can be expressed as:

[0105]

[0106]

[0107]

[0108]

[0109] in, Indicates heterogeneous individuals i At any moment t The total cumulative damage effect of burns and toxic gases; Indicates heterogeneous individuals i At any moment t The cumulative damage effect of burns; Indicates heterogeneous individuals i At any moment t The cumulative harmful effects of toxic gases; The escape time of an individual under thermal radiation conditions is represented by heat flux. Q Decide; This represents the individual's escape time from disability under thermal convection conditions, determined by ambient temperature. T Decide; This indicates the maximum time that humans can tolerate under extreme thermal radiation conditions. ; Indicates toxic gas m At the deadline t The average concentration within; Indicates toxic gas m The lethal concentration-time product; This indicates the total number of types of toxic gases.

[0110] Furthermore, based on relevant research, the injury and death rules for heterogeneous individuals during fire evacuation can be defined by the following formula:

[0111] The embodiments disclosed herein set the initial values ​​for each heterogeneous individual. The value is 0, when When accumulated to 1, heterogeneous individuals i They will lose their mobility and be transformed into static obstacles in the simulation environment. Furthermore, when a caregiver's health condition reaches a level of severe injury, the caregiver will immediately initiate a self-evacuation procedure, regardless of whether there are still elderly people remaining in the evacuation area.

[0112] 1.4 Simulation Logic Construction: Finally, this embodiment establishes simulation logic for all heterogeneous individuals based on the MSC framework, as detailed in the MSC framework above, which will not be repeated here.

[0113] 2. Simulation model parameter calibration: As mentioned earlier, existing research on semi-disabled elderly people mostly focuses on individuals using canes, with little attention paid to those using walking aids. This results in current calibrations of expected speed and evacuation speed for semi-disabled elderly people only applicable to those using canes. Therefore, we conducted field visits to three elderly care facilities and, ensuring the safety of the elderly, recruited 12 elderly people using walking aids to conduct a walking speed measurement experiment.

[0114] To avoid disrupting the daily lives of the elderly, all experiments were conducted in the space where the elderly were currently located. Each volunteer underwent three measurements. The results showed that gender and age had little impact on the walking speed of elderly people using walking aids, and their speed generally followed a normal distribution of N[0.6,1]. Notably, the speed distribution obtained in this experiment was highly similar to the speed distribution of elderly people using canes in previous studies (U[0.5,0.6] and N[0.57,1]). To ensure the safety of the elderly, this experiment did not simulate evacuation conditions for speed measurement, but instead set the evacuation speed of semi-disabled elderly people in this embodiment based on existing research results. Although this method may lead to some errors, the speed distribution of the assisted group was still set using the same method.

[0115] Based on the results of field experiments and relevant research reference data, the embodiments of this disclosure respectively obtained and calibrated the physiological parameters of heterogeneous individuals and the parameters of the simulation model.

[0116] 3. Simulation result verification and validation: 3.1 Feasibility verification of the simulation model: To verify the feasibility of the simulation model based on the MSC framework, this embodiment constructs a 20m×20m rectangular virtual room as the verification environment. Each side of the virtual room has an exit with a width of 2 meters, and 15 elderly people of each of the three disability categories (IE, SE, and DE) are randomly generated within the room, totaling 45 elderly people. According to relevant regulations, elderly care institutions should allocate nursing staff according to the disability level of the elderly. To ensure that the minimum ratio of nursing staff to IE, SE, and DE individuals is not less than 1:15, 1:6, and 1:3 respectively, this embodiment sets up 9 nursing staff within the space, whose initial positions are also randomly generated.

[0117] Furthermore, the embodiments disclosed herein are intended only to verify the feasibility of the proposed framework and do not require overly complex settings. Therefore, the fire source is set at the center of the room, and all other parameters are configured according to the physiological parameters of the calibrated heterogeneous individuals and the simulation model parameters. When no fire occurs, all heterogeneous individuals move freely within the space; when a fire occurs, the heterogeneous individuals evacuate according to the operational logic of the MSC framework. To verify that all assistance strategies can be realistically simulated, the nursing agent is set to execute each strategy sequentially for 10 simulation experiments, resulting in 40 sets of simulation videos. The assistance list for assistance strategy V is randomly generated and remains fixed after generation; that is, in the 10 simulations of executing assistance strategy V, the assistance order of each nursing agent remains fixed.

[0118] Figure 2 The following diagram illustrates a comparison of simulation results for various preset fire assistance strategies provided by exemplary embodiments of this disclosure, such as... Figure 2 As shown, under the random assistance strategy R, caregivers provide assistance based on proximity, quickly helping elderly people near the exit. However, the assistance strategy P (P(StW)) based on self-care ability from highest to lowest is clearly unsuitable for this scenario. Prioritizing assistance to IE not only reduces the likelihood of mutual assistance among elderly people but also increases the overall evacuation time and probability of injury or death due to assistance to DE last. In contrast, the assistance strategy P (P(WtS)) based on self-care ability from lowest to highest achieves better results, demonstrating shorter evacuation time and fewer injuries or deaths. For the fixed-list assistance strategy V, although the results show relatively outstanding performance from an injury or death perspective, caregivers need to spend more time and sacrifice their own health to search for designated assistance recipients, thus its assistance efficiency is significantly lower than other strategies. Furthermore, this strategy also leads to a more dispersed evacuation time distribution; if the elderly person's random location happens to match the assistance order, evacuation can be completed in a shorter time; otherwise, it will take longer.

[0119] This section does not analyze the advantages and disadvantages of different assistance strategies. These results are only used to verify that all assistance strategies employed by nursing staff can be realistically simulated, thus demonstrating the good feasibility of the simulation model based on the MSC framework.

[0120] 3.2 Verification of the effectiveness of mutual assistance behavior: Furthermore, this embodiment of the disclosure also verifies the effectiveness of incorporating mutual assistance behavior among the elderly. In the same scenario, this embodiment removes the heterogeneous model of caregivers while keeping other parameter settings unchanged, simulating a fire evacuation process when only the mutual assistance behavior of the elderly is retained. As a control experiment, this embodiment uses the original social force model for equivalent simulation. To avoid the influence of randomly generated individual locations on the accuracy of the simulation results, 50 simulation experiments are performed on each model, and the evacuation efficiency and casualty situation of the elderly are extracted as follows: Figure 3 As shown, Figure 3 A comparison diagram of simulation results for various pre-motion models provided by exemplary embodiments of this disclosure is shown.

[0121] Simulation videos reveal that although only a small number of self-reliant elderly individuals (IE) participated in mutual assistance, these limited instances significantly improved overall evacuation efficiency and reduced the casualty rate, particularly when the recipients were disabled elderly individuals (DE). This finding demonstrates that introducing mutual assistance among the elderly during fire evacuation has a substantial impact on evacuation outcomes, further supporting the rationale for the framework proposed in this disclosure.

[0122] 4. Simulation experiment on the application of flexible assistance strategy: This disclosure selects a typical single-story nursing home as the research object, establishes a simulation environment, and verifies the necessity and effectiveness of implementing flexible assistance strategies from both qualitative and quantitative perspectives.

[0123] 4.1 Simulation Environment Setup: The nursing home has a building area of ​​approximately 5,000 square meters, including a residential area (38 single rooms and 12 double rooms), a nursing work area (nursing stations, storage rooms, power distribution rooms, boiler rooms, etc.), an activity area, and corridors. It also has seven evenly distributed evacuation exits, each with a net width of 1.5 meters. Based on this, a simulation environment of the nursing home was established in this embodiment. Based on survey data, the facility houses 62 elderly people (including 36 self-reliant elderly, 16 semi-disabled elderly, and 10 disabled elderly) and 16 caregivers. All semi-disabled and disabled elderly reside in single rooms, and their locations are relatively dispersed. Through communication with the nursing home, this embodiment obtained a list of elderly people each caregiver is responsible for; therefore, in subsequent simulation experiments, the fixed list strategy will be set based on the actual assistance list obtained.

[0124] This disclosure aims to explore the effectiveness of various assistance strategies under different fire source locations and elderly population distribution conditions. Given the inherent uncertainties in fire source location and elderly population distribution, and the inevitable differences in evacuation outcomes under different scenarios, exhaustive simulation of all permutations and combinations is not feasible. Therefore, this disclosure selects six typical fire source locations and five elderly population distribution patterns for subsequent research. The fire source locations are respectively set in: residential area rooms (RR), residential area corridors (RC), evacuation exits (EE), activity area center (AC), one side of the activity area (AS), and nursing work area center (NW); the elderly population distribution is roughly divided into: all located in the residential area (10R), all located in the activity area (10A), and the ratio of elderly people in the residential area to those in the activity area is 5:5 (5R5A), 3:7 (3R7A), and 7:3 (7R3A).

[0125] Because the seven evenly distributed exits in the nursing home layout eliminate distance-based differences, the locations of the four types of fire sources (RR, RC, EE, and NW) are randomly selected. Furthermore, the distribution of elderly residents is only constrained by the number of elderly people in each area, ignoring individual physiological differences; that is, ensuring that each area contains all three types of elderly residents, but their proportions are randomly allocated. In addition, this embodiment does not consider the impact of different room layouts on evacuation efficiency. Although this issue has significant research value, it differs from the research objectives of this embodiment; therefore, only existing nursing home layouts are used for simulation experiments.

[0126] In summary, this embodiment of the invention selected six types of fire source locations and five types of elderly population distributions to test the effectiveness of different assistance strategies, designing a total of 120 simulation scenarios. To reduce the influence of uncontrollable random variables, 100 simulation experiments were conducted for each scenario, resulting in a total of 12,000 datasets.

[0127] 4.2 Qualitative results of simulation experiments: The model not only effectively simulates the differentiated individual behavior during fire evacuation, but also visualizes the group evacuation results under diverse conditions by introducing pedestrian heat density maps. Therefore, from a qualitative perspective, the embodiments disclosed in this publication believe that the proposed model is practical and effective, and its research results are of significant value in improving the fire evacuation efficiency of elderly care institutions.

[0128] 4.3 Quantitative results of simulation experiments: 4.3.1 Evacuation Time: Evacuation time is defined as the duration from the start of evacuation to the last surviving elderly person leaving the nursing home, and it is an important indicator for evaluating the effectiveness of assistance strategies. In this embodiment, all fire sources are located in visible space; therefore, it is assumed that the fire occurs synchronously with the evacuation start time, and that this information is immediately communicated to all individuals in the environment. In other words, this embodiment does not consider the reaction time after a fire is discovered. The evacuation time results of 100 simulations using four different assistance strategies are presented under a fixed elderly population distribution. Overall, under the same elderly population distribution, the difference in evacuation time caused by different fire source locations is relatively small. However, in each specific scenario, the evacuation time distribution is significantly affected by the assistance strategy employed. For example, in the 10R-AC scenario, compared to the commonly used random assistance strategy R in real-world scenarios, the assistance strategy P, which ranks individuals by disability level from low to high, reduces evacuation time by approximately 18.9%, significantly improving evacuation efficiency. Although the assistance strategy P, ranked by disability level from low to high, performs best overall, the other four strategies are still applicable in specific scenarios, such as the random assistance strategy R in the 10A-AS scenario and the fixed-list assistance strategy V in the 5R5C-RC scenario.

[0129] On the other hand, by fixing the fire source location and analyzing the simulation results of four assistance strategies under different elderly population distribution scenarios, more systematic patterns can be discovered. The results show that in each fire source location scenario, as the distribution of elderly people shifts from a dispersed pattern (10R) to a clustered pattern (10A), evacuation time gradually increases. The underlying mechanism is that when the degree of elderly population clustering increases (from 10R to 10A), assistance is easier to implement, but the individuals receiving assistance occupy more space, leading to more frequent congestion than in other scenarios.

[0130] Overall, from the perspective of evacuation time, simulation results show that both the distribution pattern of the elderly and the assistance strategy significantly affect evacuation effectiveness. Specifically, assistance strategy P, ranked from low to high disability level, remained stable across all scenarios. In contrast to existing research, assistance strategy V, using a fixed assistance list, did not demonstrate significantly superior evacuation performance. Although assistance strategy V generally resulted in the shortest evacuation time, its effectiveness fluctuated considerably: evacuation time was minimized when caregivers could quickly locate the designated recipients; however, excessive time spent searching for the specified elderly significantly worsened evacuation efficiency. Therefore, the fixed list strategy may not be suitable as a routine evacuation strategy in real-world scenarios.

[0131] 4.3.2 Casualty Rate: Clearly, assessing assistance strategies solely based on evacuation time has inherent limitations, as it fails to consider critical safety factors such as elderly casualties. Therefore, this disclosure's embodiments statistically analyzed the average proportion of individuals in different health states across 100 simulations in 120 scenarios to evaluate the evacuation effectiveness of various assistance strategies under different conditions. Casualty statistics only consider the health status of the elderly and do not include caregivers. Although caregivers also have a health status model, they will immediately move to the most appropriate exit when their health status reaches severe injury. According to all simulation results, except for the scenario where the fire source is located in the care work area, where 8 caregivers directly reach a state of death, the health status of caregivers in other scenarios is generally severe injury but not death. Furthermore, due to the lack of caregiver assistance in the later stages of the fire, elderly deaths occurred in almost all scenarios. This result is consistent with the characteristics of real fire evacuation events and should not be attributed to strategy design flaws.

[0132] Simulation data on casualty rates for various strategies under different fire source locations with the same elderly population distribution clearly shows that the difference in casualty rates between strategies is far greater than the difference in evacuation time. Furthermore, among all elderly population distribution scenarios, the fire source scenario in the center of the activity area resulted in the most severe casualties. This is because when the fire source is located in the central area of ​​the nursing home, toxic gases penetrate the entire building more quickly as the flames spread outwards, causing greater harm. When the simulation results are reorganized according to the elderly population distribution pattern, the same conclusion as regarding evacuation time is reached: the more concentrated the elderly population is, the higher the casualty rate. Moreover, among all fire source location scenarios, the highest casualty rate is achieved when all elderly people are located in the activity area.

[0133] In summary, evaluating the four assistance strategies from the perspective of casualty rates can reveal the proportion of individuals in different health states under various scenarios. However, such results can only provide a preliminary optimal strategy for each scenario. For example, in the 10R-RR scenario, the proportion of deaths under the random assistance strategy R is higher than that under the assistance strategy P, which is ranked from low to high disability level, while the latter leads to a significant increase in the proportion of seriously injured individuals. This complexity means that it is difficult to definitively determine the optimal strategy for a specific scenario simply by comparing casualty data.

[0134] 4.3.3 Comparison of Assistance Strategies: As mentioned earlier, the location of the fire source and the distribution of elderly residents both influence the choice of assistance strategies. However, evaluating assistance strategies solely from the single dimension of efficiency (evacuation time) or safety (casualty rate) is insufficient to comprehensively measure their effectiveness and cannot provide a systematic basis for developing reasonable evacuation assistance strategies for nursing homes. Therefore, it is necessary to comprehensively evaluate the combined performance of the four proposed strategies in different scenarios, considering both evacuation efficiency and individual safety. Specific calculations are detailed in the previous section on calculating the comprehensive score and will not be repeated here.

[0135] According to the calculation results of this embodiment, the scores of the two different strategies are very close in some scenarios, a phenomenon also reflected in the simulation results mentioned above. For example, in the 5R5A-RC scenario, from the perspective of evacuation time, the assistance strategy P, ranked from low to high disability level, achieved an average evacuation time of 54.7 seconds, significantly better than the random assistance strategy R's 57.8 seconds. However, the random assistance strategy R compensated for this by reducing the number of seriously and slightly injured individuals, thus gaining an advantage in terms of casualty rate. Ultimately, the difference in the overall score between the two strategies in this scenario was only 0.023.

[0136] To highlight whether the selected strategy is significantly superior to other strategies, embodiments of this disclosure introduce the concept of an isolation index. This index measures the significance of the strategy advantage by calculating the proportion of the relative distance between the highest and second-highest scores to the total score range. The formula for defining the isolation index is:

[0137] in, Indicates the isolation index; This represents the lowest overall score across all strategies in a given scenario; This represents the second-lowest overall score across all strategies in a given scenario. This represents the highest overall score among all strategies in a given scenario. The larger the isolation index, the more isolated the overall score of the optimal assisting strategy is, meaning that the advantage of this strategy compared to other strategies is more obvious.

[0138] Figure 4 The figure illustrates recommended assistance strategies for 30 scenarios provided by exemplary embodiments of this disclosure. Figure 4 As shown, it is clear that the assistance strategy P (referred to as P(StW)) based on the level of self-care ability from high to low, and the fixed-list assistance strategy V, are not recommended under any circumstances. Based on the distribution of elderly people and the location of fire sources, the applicable patterns of assistance strategies can be summarized as follows: When the elderly population is relatively dispersed (10R, 7R3A, and 5R5A), considering both evacuation efficiency and safety, the random assistance strategy R performs optimally. However, when the elderly population is more concentrated (3R7A and 10A), the assistance strategy P, which prioritizes assistance based on disability level from low to high, is more suitable. This is because in dispersed scenarios, the elderly (especially vulnerable semi-disabled and fully disabled elderly) are widely distributed, making locating and assisting them time- and energy-intensive. If caregivers prioritize assisting vulnerable groups, they need to frequently travel long distances to find specific vulnerable individuals, resulting in significant ineffective movement and wasted time. Furthermore, when spatially dispersed, the lower population density around self-reliant elderly increases the frequency of mutual assistance. In this context, prioritizing assistance to vulnerable individuals may trigger competition, significantly impacting evacuation efficiency.

[0139] On the other hand, in scenarios involving large gatherings, the assistance strategy P (referred to as P(WtS)) based on disability level from low to high has proven more effective. This is because most elderly people are concentrated in activity areas and are densely distributed, resulting in shorter distances to assistance targets and a lower probability of mutual assistance. Consequently, the dwell time of vulnerable elderly people (semi-disabled and fully disabled elderly) increases significantly. As the concentration of vulnerable groups intensifies, their slow movement becomes a significant bottleneck in evacuation routes. The assistance strategy P based on disability level from low to high can effectively alleviate such bottlenecks, prevent crowd congestion, and improve overall evacuation efficiency. Furthermore, in concentrated environments, caregivers can quickly locate vulnerable elderly people within a limited area, so the priority assistance strategy does not incur excessive additional time costs. Instead, it can significantly reduce the dwell time of high-risk groups, reduce the risk of entrapment or fire injury, and thus improve evacuation safety.

[0140] In summary, when vulnerable elderly individuals are concentrated and easily become evacuation bottlenecks, the assistance strategy P, which prioritizes assistance based on disability level from low to high, can alleviate local congestion and ensure rapid and safe passage. Conversely, when elderly individuals are widely distributed across various evacuation routes in a residential area and vulnerable individuals are scattered, the increased search time for caregivers reduces overall evacuation efficiency, and the assistance strategy P, prioritizing assistance based on disability level from low to high, cannot maintain its advantage. Therefore, in such cases, this embodiment recommends using a random assistance strategy R. The selection criteria for assistance strategies based on the distribution characteristics of the elderly are as follows: Guideline 1: If the fire occurs during active periods (when elderly people are concentrated), the recommended assistance strategy P, based on disability level from low to high, is suggested; if it occurs during rest periods (when elderly people are dispersed), the recommended strategy R is randomized assistance. If the current complex environment makes it difficult to accurately assess the distribution of elderly people, the randomized assistance strategy R should be prioritized to reduce decision-making and route planning costs.

[0141] When the fire source is located in the center of the activity area, although the isolation of the assistance strategy P, which prioritizes assistance based on disability level from low to high, is relatively low, a clear and consistent pattern indicates that this strategy is optimal under these conditions. In contrast, no similar significant pattern was observed at other fire source locations. This phenomenon mainly stems from the central location of the activity area within the overall layout of the nursing home: a fire originating here would spread rapidly in all directions. The advantages of the assistance strategy P, prioritizing assistance based on disability level from low to high, in improving mobility and alleviating congestion bottlenecks when elderly residents are concentrated in the activity area have already been discussed. However, when the elderly residents are more dispersed, a fire in the central area can quickly block multiple available evacuation routes, preventing both the elderly and caregivers from traversing the central area. Therefore, evacuation must be carried out through peripheral passages, making slow-moving, vulnerable individuals a bottleneck affecting the overall evacuation flow. Therefore, under these conditions, the assistance strategy P, prioritizing assistance based on disability level from low to high, is particularly important. By prioritizing assistance to elderly residents with slower mobility to reduce their time spent in evacuation routes, the bottleneck can be effectively cleared, thereby significantly improving evacuation efficiency and safety.

[0142] In contrast, in evacuation environments with other fire source locations, the initial impact area of ​​a fire remains localized. Although local damage is significant, from a global evacuation perspective, the effectiveness of assistance strategies is more influenced by the distribution characteristics of the elderly than by the location of the fire source. In summary, the guidelines for developing assistance strategies based on fire source location are as follows: Guideline 2: If the fire source is located in the central activity area, the assistance strategy P, which is based on the degree of disability from low to high, should be adopted unconditionally; if the fire source originates from other locations, the selection of assistance strategies should be determined based on the distribution characteristics of the elderly.

[0143] Extensive simulation experiments have demonstrated that the simulation model based on the MSC framework can effectively simulate diverse assistance strategies in complex nursing home fire evacuation scenarios. On one hand, the FA-SFM proposed in this disclosure not only accurately simulates the assistance behavior of caregivers but also constructs a mutual assistance behavior model among the elderly, significantly improving the realism of the simulation model. On the other hand, by integrating quantitative analysis of evacuation time and casualty rates, this disclosure demonstrates that differentiated assistance strategies produce different evacuation effects in complex fire scenarios with varying fire source locations and elderly population distributions. Furthermore, customized assistance strategies are proposed for 30 different nursing home fire scenarios, and two general rules applicable to single-story nursing homes are summarized.

[0144] As a pioneering study on heterogeneous assistance behaviors in complex nursing home fire evacuation environments, this disclosure categorizes elderly individuals into three groups based on their physiological characteristics and mobility: independent elderly (IE), semi-disabled elderly (SE), and disabled elderly (DE). To the best of our knowledge, this is the first study to simulate real-world mutual assistance behaviors during elderly evacuation. For complex fire scenarios involving different fire source locations and elderly distribution patterns, this disclosure develops four assistance strategies and proposes the MSC framework to simulate these diverse assistance behaviors in complex environments. Model parameters are calibrated through experiments involving real elderly individuals, and the effectiveness and fidelity of the model are verified through virtual scenario simulation experiments. Furthermore, large-scale simulations are conducted in a real single-story nursing home environment, combining six types of fire source locations with five types of elderly distribution patterns to construct combined scenarios. These simulation experiments not only verify the effectiveness and rationality of the proposed framework but also establish general evacuation strategies applicable to single-story nursing homes.

[0145] In summary, the research presented in this disclosure provides a novel approach for research on the assistance and evacuation of vulnerable groups in complex environments. The proposed framework overcomes the limitations of traditional methods, such as scenario homogenization and fixed assistance strategies, while significantly improving the realism of the simulation model by introducing individual behavioral heterogeneity.

[0146] Compared with the prior art, the embodiments disclosed herein have the following beneficial effects: This disclosure proposes a multi-strategy comparison framework. By constructing a fire simulation model and a heterogeneous model to provide fire environment data and heterogeneous individual physical characteristics respectively, an assistance strategy model is established, which includes behavioral logic and judgment rules for different assistance strategies. This model is then used as input to a motion model. By introducing two key improvements—assistance force and assistance willingness—a force-aware social force model is constructed in the motion model, which can realistically simulate the movement and assistance behavior of heterogeneous groups during evacuation. This disclosure verifies the effectiveness and realism of the model through extensive simulation experiments, and also obtains assistance strategy formulation rules applicable to the complex and ever-changing fire scenarios in nursing homes.

[0147] The details are as follows: (1) In response to the complex fire environment of nursing homes formed by the diverse combination of fire source location and elderly distribution, an MSC framework was constructed based on the mainstream assistance strategies in real-world scenarios, which includes multiple strategies such as nearby assistance, priority assistance and fixed-point assistance. The aim is to compare and evaluate the effectiveness of various assistance strategies in different scenarios.

[0148] (2) A fire-assisted social force model is proposed. By introducing fire repulsion and smoke effects (synchronously adjusting visibility and mobility), integrating assistance forces, and adding assistance willingness, the original model's ability to simulate the evacuation behavior of heterogeneous elderly groups and caregiver assistance behavior in fire environments is significantly improved. The effectiveness and authenticity of the proposed model are verified through a large number of simulation experiments in virtual scenarios.

[0149] (3) A large number of simulation experiments were conducted in both virtual and real environments. With evacuation time and casualty rate as the core evaluation indicators, the results of the virtual environment simulation verified the authenticity and effectiveness of the model, while the simulation of the real scene summarized two general rules for formulating assistance strategies applicable to fire evacuation in single-story nursing homes.

[0150] Guideline 1: If the fire occurs during active periods (when elderly people are concentrated), strategy P, based on disability level from low to high, is recommended; if it occurs during rest periods (when elderly people are dispersed), a stochastic strategy R is suggested. If the current complex environment makes it difficult to accurately assess the distribution of elderly people, the stochastic strategy R should be prioritized to reduce decision-making and route planning costs.

[0151] Guideline 2: If the fire source is located in the central activity area, strategy P, which is based on the degree of disability from low to high, should be adopted unconditionally; if the fire source originates from other locations, the choice of assistance strategy should be determined based on the distribution characteristics of the elderly.

[0152] Overall, the embodiments disclosed herein represent both a novel attempt and foundational work. Taking a complex scenario defined by the location of the fire source and the distribution of elderly residents as an example, the evacuation effects of differentiated assistance strategies were simulated while incorporating mutual assistance behaviors among the elderly. The research results demonstrate the success of these innovative efforts, not only enhancing the realism of the simulation model but also providing a theoretical basis for selecting assistance strategies that consider heterogeneity during evacuation in nursing homes. Future embodiments of this disclosure will conduct more real-world experiments to calibrate model parameters and improve accuracy, while also considering more complex environmental factors to develop universal fire evacuation assistance strategies applicable to diverse and complex nursing home scenarios.

[0153] The foregoing mainly describes the solutions provided by the embodiments of this disclosure. It is understood that, in order to achieve the above functions, the electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0154] This disclosure embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0155] In the case of dividing each functional module according to its corresponding functions, an exemplary embodiment of this disclosure provides a device for determining a fire assistance strategy for a nursing home. The device for determining a fire assistance strategy for a nursing home can be a terminal or a chip applied to a terminal. Figure 5 A schematic diagram of the structure of the device for determining a fire assistance strategy for a nursing home, provided in an exemplary embodiment of this disclosure, is shown. Figure 5 As shown, the device 500 includes: The construction module 501 is used to construct a heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model; wherein, the fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between the heterogeneous individuals and other heterogeneous individuals, the repulsive force between the heterogeneous individuals and the walls of the nursing home, and the willingness to assist and the assisting force between the heterogeneous individuals being assisted. The simulation module 502 is used to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scene of the nursing home using the fire simulation model and the heterogeneous model, and to simulate multiple preset fire assistance strategies to obtain multiple simulation results; wherein each simulation result includes evacuation time and casualty rate. The processing module 503 is used to determine the preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

[0156] In some embodiments, the fire evacuation movement model is an assisting social force model; the assisting social force model is expressed as follows:

[0157]

[0158]

[0159]

[0160]

[0161]

[0162] in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals i The initial velocity; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individualsi willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing to the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of the nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1.

[0163] In some embodiments, the types of the plurality of heterogeneous individuals include caregivers and elderly people, and the types of elderly people include, but are not limited to, self-reliant elderly people, semi-self-reliant elderly people, disabled elderly people, assisted self-reliant elderly people, assisted semi-self-reliant elderly people and assisted disabled elderly people. The various preset fire assistance strategies include a random assistance strategy, a priority assistance strategy, and a targeted assistance strategy; wherein, the random assistance strategy is that the caregiver directly assists the elderly person who is closest to the search area; the priority assistance strategy is that the caregiver assists the elderly person within the search area according to a preset priority; and the targeted assistance strategy is that the caregiver provides targeted assistance to the elderly person within the search area according to a preset list of heterogeneous individuals to assist.

[0164] In some embodiments, the selection of the assisted heterogeneous individual is defined as:

[0165] in, This refers to the nursing staff; This refers to the self-reliant elderly person; This refers to the semi-independent elderly person; This refers to the disabled elderly person mentioned above; This refers to the elderly person who is receiving assistance with self-care. This refers to the assisted semi-independent elderly person; This refers to the elderly people with disabilities who are receiving assistance. This refers to the random assistance strategy; This indicates the priority assistance strategy; This refers to the targeted assistance strategy; Let S represent the set of preset fire assistance strategies, where S∈{R,P,T}; The weight representing the preset priority is used to ensure that the caregiver assists high-priority heterogeneous individuals according to the preset priority; This represents a small random perturbation term, used to avoid completely deterministic choices; This represents the preset list of heterogeneous individuals for assistance. , This indicates the sequence number of the heterogeneous individual currently being assisted. This represents the total number of heterogeneous individuals who receive assistance.

[0166] In some embodiments, the intensity of the adjusted social force is expressed as:

[0167] The scope of the adjusted social influence is expressed as follows:

[0168] The cooperation probability is expressed as:

[0169]

[0170] in, This refers to the nursing staff; This refers to the self-reliant elderly person; , and Indicates the adjustment factor; Indicates heterogeneous individuals i Heterogeneous properties; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates the search range The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed.

[0171] In some embodiments, the fire evacuation force also includes the fire repulsion force of the heterogeneous individual, the smoke avoidance force, and the random disturbance force caused by panic. The fire evacuation movement model is a fire-assisted social force model, which is expressed as follows:

[0172]

[0173]

[0174]

[0175]

[0176]

[0177]

[0178]

[0179]

[0180]

[0181]

[0182]

[0183]

[0184]

[0185]

[0186] in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The repulsive force of the fire source; Indicates heterogeneous individuals i Its ability to avoid smoke; Indicates heterogeneous individuals i Random disturbances caused by panic; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals during fire evacuation. i At any moment t Effective speed; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing to the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of the nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; This indicates the intensity of the repulsive force from the fire source; Indicates the range of action of the repulsive force from the fire source; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i A normalized vector pointing to the source of the fire; This indicates the mass fraction originating from the fuel stream. Indicates a dimensionless parameter; Represents the small perturbation term; Indicates the flue gas avoidance coefficient; Indicates time t Smoke concentration at the location; This indicates the mass fraction of smoke and dust. This represents the panic intensity coefficient, which is related to the degree of environmental danger at the current location of a heterogeneous individual. , Indicates the basic random strength. This represents the enhancement coefficient of the fire source. Indicates the smoke enhancement factor; Indicates time t Fire hazard parameters at the location; This represents Gaussian white noise. , where I represents the identity matrix; Indicates heterogeneous individuals i The initial velocity; This represents the visibility attenuation term; Represents the visibility coefficient; This represents the thermal radiation attenuation term; Indicates the thermal emissivity; Indicates time t The intensity of thermal radiation at the location; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1. This represents the inhibition coefficient of the fire scene environment on the probability of assistance; This refers to the caregivers among the multiple heterogeneous individuals; This refers to self-reliant elderly individuals among the aforementioned heterogeneous individuals; , and Indicates the adjustment factor; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates time t Heterogeneous individuals i Search scope The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed; Indicates heterogeneous individuals i The acceleration; Indicates heterogeneous individuals i At any moment t Location; Indicates heterogeneous individuals i The initial position.

[0187] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the methods disclosed in this disclosure.

[0188] Figure 6 A schematic diagram of the structure of an electronic device provided in an exemplary embodiment of this disclosure is shown. For example... Figure 6 As shown, the electronic device 600 includes at least one processor 601 and a memory 602 coupled to the processor 601. The processor 601 can perform the corresponding steps in the methods disclosed in the embodiments of this disclosure.

[0189] The processor 601 described above can also be referred to as a Central Processing Unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method disclosed in this embodiment can be implemented by the integrated logic circuitry in the processor 601 or by software instructions. The processor 601 can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this embodiment can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 602, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 601 reads information from the memory 602 and, in conjunction with its hardware, completes the steps of the method described above.

[0190] Furthermore, the various operations / processes according to this disclosure, when implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, for example, Figure 7 The computer system 700 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including functions such as those described above. Figure 7 A schematic diagram of the structure of a computer system provided in an exemplary embodiment of this disclosure is shown.

[0191] Computer system 700 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0192] like Figure 7As shown, the computer system 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 may also store various programs and data required for the operation of the computer system 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0193] Multiple components in the computer system 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device capable of inputting information into the computer system 700. The input unit 706 can receive input numerical or character information and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 707 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. The storage unit 708 may include, but is not limited to, a hard disk and an optical disk. The communication unit 709 allows the computer system 700 to exchange information / data with other devices via a network such as the Internet, and may include, but is not limited to, a modem, network card, infrared communication device, wireless communication transceiver, and / or chipset, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0194] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the methods disclosed in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 702 and / or communication unit 709. In some embodiments, the computing unit 701 can be configured to perform the methods disclosed in this disclosure by any other suitable means (e.g., by means of firmware).

[0195] This disclosure also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the methods disclosed in this disclosure.

[0196] The computer-readable storage medium in this disclosure can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The aforementioned computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the aforementioned computer-readable storage medium may include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0197] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0198] This disclosure also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, it implements the methods disclosed in the embodiments of this disclosure.

[0199] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer.

[0200] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0201] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0202] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0203] The above description is merely an illustration of some embodiments of this disclosure and the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0204] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for determining a fire assistance strategy for a nursing home, characterized in that, include: A heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model are constructed. The fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between the heterogeneous individuals and other heterogeneous individuals, the repulsive force between the individual and the walls of the nursing home, and the willingness to assist and the assisting force between the individual being assisted. In simulating a fire scenario in a nursing home using the fire simulation model, the fire evacuation movement model and the heterogeneous model are used to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scenario using various preset fire assistance strategies, resulting in multiple simulation results; each simulation result includes evacuation time and casualty rate. The preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results is determined as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

2. The method as described in claim 1, characterized in that, The fire evacuation model is a social assistance model; the social assistance model is expressed as follows: in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals i The initial velocity; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing to the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of the nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1.

3. The method as described in claim 2, characterized in that, The types of the multiple heterogeneous individuals include caregivers and elderly people, and the types of elderly people include, but are not limited to, self-reliant elderly people, semi-self-reliant elderly people, disabled elderly people, assisted self-reliant elderly people, assisted semi-self-reliant elderly people and assisted disabled elderly people. The various preset fire assistance strategies include a random assistance strategy, a priority assistance strategy, and a targeted assistance strategy; wherein, the random assistance strategy is that the caregiver directly assists the elderly person who is closest to the search area; the priority assistance strategy is that the caregiver assists the elderly person within the search area according to a preset priority; and the targeted assistance strategy is that the caregiver provides targeted assistance to the elderly person within the search area according to a preset list of heterogeneous individuals to assist.

4. The method as described in claim 3, characterized in that, The selection of the assisted heterogeneous individuals is defined as follows: in, This refers to the nursing staff; This refers to the self-reliant elderly person; This refers to the semi-independent elderly person; This refers to the disabled elderly person mentioned above; This refers to the elderly person who is receiving assistance with self-care. This refers to the assisted semi-independent elderly person; This refers to the elderly people with disabilities who are receiving assistance. This refers to the random assistance strategy; This indicates the priority assistance strategy; This refers to the targeted assistance strategy; Let S represent the set of preset fire assistance strategies, where S∈{R,P,T}; The weight representing the preset priority is used to ensure that the caregiver assists high-priority heterogeneous individuals according to the preset priority; This represents a small random perturbation term, used to avoid completely deterministic choices; This represents the preset list of heterogeneous individuals for assistance. , This indicates the sequence number of the heterogeneous individual currently being assisted. This represents the total number of heterogeneous individuals who receive assistance.

5. The method as described in claim 3, characterized in that, The adjusted strength of social force is expressed as follows: The scope of the adjusted social influence is expressed as follows: The cooperation probability is expressed as: in, This refers to the nursing staff; This refers to the self-reliant elderly person; , and Indicates the adjustment factor; Indicates heterogeneous individuals i Heterogeneous properties; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates the search range The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed.

6. The method as described in claim 1, characterized in that, The fire evacuation force also includes the fire repulsion force, smoke avoidance force, and random disturbance force caused by panic of the heterogeneous individuals. The fire evacuation model is a fire-assisted social force model, which is expressed as follows: in, Indicates heterogeneous individuals i The quality; Indicates heterogeneous individuals i The actual speed; Indicates heterogeneous individuals i The driving force; Indicates heterogeneous individuals i Other heterogeneous individuals j Interaction forces between them; Indicates heterogeneous individuals i With the walls of the nursing home w The repulsive force between them; Indicates heterogeneous individuals i The assistance of; Indicates heterogeneous individuals i The repulsive force of the fire source; Indicates heterogeneous individuals i Its ability to avoid smoke; Indicates heterogeneous individuals i Random disturbances caused by panic; Indicates heterogeneous individuals i The willingness to assist; J Including heterogeneous individuals i The total number of other heterogeneous individuals besides; W This indicates the total number of walls in the nursing home; Indicates heterogeneous individuals during fire evacuation. i At any moment t Effective speed; Indicates heterogeneous individuals i At any moment t A unit vector pointing towards the desired target; Indicates heterogeneous individuals i At any moment t The expected speed; Indicates a specific characteristic time; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted strength of social influence; Indicates based on heterogeneous individuals i willingness to assist and heterogeneous individuals j willingness to assist The adjusted scope of social influence; Indicates heterogeneous individuals i and heterogeneous individuals j The sum of the radii; Indicates heterogeneous individuals i heterogeneous individuals j The distance between their centroids; Indicates heterogeneous individuals i Pointing to heterogeneous individuals j The normalized vector; Indicates the body's compressibility factor; Indicates the coefficient of sliding friction; Indicates heterogeneous individuals j The actual speed; Indicates heterogeneous individuals i and heterogeneous individuals j The direction of the tangent; Indicates heterogeneous individuals i The wall pointing to the nursing home w The normalized vector; Indicates heterogeneous individuals i radius, Indicates heterogeneous individuals i With the walls of the nursing home w The distance between their centroids; Indicates the intensity of social influence; Indicates the scope of social influence; Indicates heterogeneous individuals i and the walls of the nursing home w The direction of the tangent; Indicates heterogeneous individuals i and heterogeneous individuals j Or the walls of the nursing home w No contact between them; Indicates the speed adjustment coefficient; Indicates heterogeneous individuals j The initial velocity; Indicates heterogeneous individuals i At any moment t The current direction of motion, unit vector; Indicates the heterogeneous individual being assisted At any moment t The current direction of motion, unit vector; Indicates the intensity of the repulsive force from the fire source; Indicates the range of action of the repulsive force from the fire source; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i A normalized vector pointing to the source of the fire; This indicates the mass fraction originating from the fuel stream. Indicates a dimensionless parameter; Represents the small perturbation term; Indicates the flue gas avoidance coefficient; Indicates time t Smoke concentration at the location; This indicates the mass fraction of smoke and dust. This represents the panic intensity coefficient, which is related to the degree of environmental danger at the current location of a heterogeneous individual. , Indicates the basic random strength. This represents the enhancement coefficient of the fire source. Indicates the smoke enhancement factor; Indicates time t Fire hazard parameters for the location; This represents Gaussian white noise. , where I represents the identity matrix; Indicates heterogeneous individuals i The initial velocity; This represents the visibility attenuation term; Represents the visibility coefficient; This represents the thermal radiation attenuation term; Indicates the thermal emissivity; Indicates time t The intensity of thermal radiation at the location; Indicates heterogeneous individuals i The probability of assistance; This represents a pseudo-random number generation function, with a return value between 0 and 1. This represents the inhibition coefficient of the fire scene environment on the probability of assistance; This refers to the caregivers among the multiple heterogeneous individuals; This refers to self-reliant elderly individuals among the aforementioned heterogeneous individuals; , and Indicates the adjustment factor; Indicates heterogeneous individuals i The fire risk sensitivity coefficient; Indicates the search scope; Indicates time t Heterogeneous individuals i Search scope Density of heterogeneous individuals within the organism; Indicates time t Heterogeneous individuals i Search scope The number of heterogeneous individuals; Indicates heterogeneous individuals i Distance from the source of fire; Indicates heterogeneous individuals i The actual maximum speed; Indicates heterogeneous individuals i The acceleration; Indicates heterogeneous individuals i At any moment t Location; Indicates heterogeneous individuals i The initial position.

7. A device for determining a fire assistance strategy for a nursing home, characterized in that, include: The construction module is used to construct a heterogeneous model of multiple heterogeneous individuals in a nursing home, a fire evacuation motion model based on fire evacuation forces, and a fire simulation model; wherein, the fire evacuation forces include at least the driving force of the heterogeneous individuals, the interaction force between the heterogeneous individuals and other heterogeneous individuals, the repulsive force between the heterogeneous individuals and the walls of the nursing home, and the willingness to assist and the assisting force between the heterogeneous individuals being assisted. The simulation module is used to simulate the fire scene of the nursing home using the fire simulation model, and to simulate the evacuation behavior of multiple heterogeneous individuals in the fire scene using the fire evacuation movement model and the heterogeneous model, and to obtain multiple simulation results; wherein each simulation result includes evacuation time and casualty rate. The processing module is used to determine the preset fire assistance strategy corresponding to the target simulation result among the multiple simulation results as the target fire assistance strategy, so as to use the target fire assistance strategy to carry out fire evacuation in the fire scenario of the nursing home.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 6.

Images