Simulation method based on complex building crowd evacuation model

Abstract

The present application relates to the technical field of emergency evacuation, in particular to a simulation method based on a complex building crowd evacuation model. The present application divides the personnel in the target building into evacuation groups, combines the planned evacuation route of the personnel in the evacuation groups with the actual stay time of the stay nodes thereon to obtain a theoretical evacuation route; determines an evacuation confusion degree based on the number of evacuation groups accommodated by an example node in a sub-period and the theoretical stay time; determines an evacuation risk degree based on the evacuation confusion degree of each sub-period of the example node in the simulation period and the fluctuation trend thereof; adjusts the theoretical stay time of the example node based on the difference in the evacuation risk degree of the example node and adjacent nodes on the theoretical evacuation route, determines an optimized stay time, and determines an optimized evacuation route of the example group. The present application divides the personnel in the building into groups, adjusts the stay time of the nodes on the evacuation route by considering path intersection and congestion, and improves the evacuation accuracy in the complex environment of super high-rise buildings.

Description

Technical Field

[0001] This invention relates to the field of emergency evacuation technology, specifically to a simulation method based on a complex building crowd evacuation model. Background Technology

[0002] Supertall buildings typically refer to buildings with 40 floors or a height of 100 meters or more. They are a product of industrialization and modernization, and depending on their height and function, they encompass multiple functional areas such as residential, commercial, and office spaces. However, supertall buildings are characterized by their great height, large number of people, and long vertical evacuation distances, which leads to severe challenges in emergencies such as fires, including difficult evacuation, challenging rescue operations, and lengthy processing times, potentially causing significant loss of life and property.

[0003] Existing evacuation models typically treat people as independent individuals for route planning, generally assuming uniform distribution or movement according to simple rules. However, in actual evacuation scenarios, people from different floors continuously converge at nodes such as stairwells during downward evacuation, forming dynamically changing crowd flows. Individual decisions are not entirely independent and are heavily influenced by the surrounding crowd, such as herd mentality, leadership behavior, or collaboration; group behavior can alter individual path choices. Therefore, existing models based on the assumption of independent individuals lack accuracy and reliability when simulating real, complex evacuation scenarios in super high-rise buildings. Summary of the Invention

[0004] To address the technical problem that evacuation models based on the assumption of individual independence fail to consider the dynamic impact of group behavior during evacuation, resulting in insufficient accuracy in simulating crowd evacuation in super high-rise buildings, this invention aims to provide a simulation method based on a complex building crowd evacuation model. The specific technical solution adopted is as follows: This invention proposes a simulation method based on a complex building crowd evacuation model, the method comprising: Obtain the planned evacuation routes for each person in the target building and the actual dwell time of each person at each stop point on the planned evacuation route; Based on the floor differences and the closeness of social relationships among different people, the people in the target building are divided into different evacuation groups; the planned evacuation routes of people in the same evacuation group and the actual stay time of the stops on them are combined to obtain the theoretical evacuation routes and the theoretical stay time of each stop on each evacuation group. Choose any evacuation group as the example group, and choose any node on the theoretical evacuation route of the example group as the example node; based on the number of evacuation groups that the example node can accommodate in each sub-period of the simulation period and the theoretical stay time of the evacuation groups at the example node, determine the evacuation disorder of the example node in each sub-period. Based on the evacuation disorder and its volatility trend of the example node in each sub-period of the simulation period, the evacuation risk of the example node is determined. Based on the difference in evacuation risk between example nodes and adjacent nodes on the theoretical evacuation route of the example group, the theoretical dwell time of the example nodes is adjusted to determine the optimal dwell time of the example nodes, and the optimal evacuation route of the example group is determined.

[0005] Furthermore, the method for obtaining the evacuation group includes: Set the social distance between every two people in the target building, and the smaller the social distance, the closer the social relationship between the two people; The absolute value of the difference between the floors where any two people in the target building were located at the start of evacuation is taken as the floor distance. The product of the social distance and the floor distance is used as the distance indicator between each two people; Based on the distance index, all personnel within the target building are clustered to obtain several clusters; personnel within the same cluster constitute an evacuation group.

[0006] Furthermore, obtaining the theoretical evacuation route for each evacuation group and the theoretical dwell time at each stop point along it includes: For each evacuation group, the set of stops consists of the stops along the planned evacuation routes of all personnel within the evacuation group. Obtain the arrival time of each person in the evacuation group to each stop point on their planned evacuation route; The average arrival time of all personnel in the evacuation group to each stop point in the stop set is calculated to obtain the group arrival time of each stop point in the stop set. The theoretical evacuation routes for the evacuation groups are generated by sequentially connecting the nodes within the evacuation group according to the order of their arrival times. Select any one of the stops on the theoretical evacuation route and record it as the analysis node. Take the maximum value of the actual stay time of all personnel in the evacuation group at the analysis node as the theoretical stay time of the analysis node on the theoretical evacuation route.

[0007] Further, determining the evacuation disorder level of the example node in the corresponding sub-time period includes: Obtain the number of evacuation groups accommodated by the example node at each time point during the simulation period; Calculate the average number of evacuation groups accommodated by the example node at all times within each sub-period, and use the ratio of the average to the area of ​​the corresponding dwelling location of the example node as the group aggregation density of the example node in each sub-period. Choose any sub-time period as the example time period, and select high-density clustering nodes from the dwelling nodes on the theoretical evacuation route of the example group based on the group's aggregation density. The average of the theoretical dwell time of the evacuation groups accommodated at each high-density gathering point during all times within the example period is used to obtain the overall dwell time of each high-density gathering point during the example period. The degree of evacuation disorder is obtained based on the group aggregation density and the overall dwell time of each high-density aggregation point during the example time period; The evacuation risk of all remaining nodes on the theoretical evacuation route of the example group, except for the high-density gathering point during the example period, is set to zero during the example period.

[0008] Furthermore, determining the evacuation hazard level of the example node includes: Arrange the evacuation disorder of the example node in all sub-periods within the simulation period in chronological order to obtain the disorder sequence; Obtain the first-order difference sequence of the disorder sequence, and use the number of sign changes of two adjacent elements in the first-order difference sequence as the volatility trend of the example node; The overall disorder is obtained by averaging the evacuation disorder of the example node across all sub-periods during the simulation period. Based on the fluctuation trend and the overall disorder, the evacuation risk level of the example node is obtained.

[0009] Furthermore, determining the optimized dwell time of the example node includes: The difference between the evacuation hazard level of the example node and the next adjacent node on the theoretical evacuation route of the example group is normalized to obtain the emergency response level of the example node. Based on the negative correlation mapping of the evacuation hazard degree of the example node, the product of the mapping result and the emergency response degree is normalized to obtain the planning rationality of the example node. The theoretical dwell time of the example node is weighted using the planning rationality to obtain the optimized dwell time of the example node.

[0010] Furthermore, determining the optimal evacuation route for the example group includes: By using the optimized dwell time of each stop node on the theoretical evacuation route of the example group, the theoretical dwell time of the corresponding stop node is updated, and the updated theoretical evacuation route is used as the optimized evacuation route of the example group.

[0011] Furthermore, the high-density clustered nodes selected for the example time period include: The average of the group aggregation densities of all the stops along the theoretical evacuation route of the example team during the example time period is used as the baseline aggregation density for the example time period. The high-density clustered nodes have a higher group cluster density during the example time period than the baseline cluster density during the example time period.

[0012] Furthermore, the example node contains at least one person within the evacuation group at each moment during the simulation period, who is present at the example node at the corresponding moment.

[0013] Furthermore, the method for clustering all personnel within the target building is the K-means clustering algorithm.

[0014] The present invention has the following beneficial effects: Firstly, the evacuation groups were divided based on the floor differences and the closeness of social relationships among different personnel, and individual routes were merged. This fully simulated the dynamic behavior of groups during real evacuations, making the simulation more realistic and significantly improving the accuracy of evacuation in complex environments of super high-rise buildings.

[0015] Secondly, based on the number of groups and their stay time in the sub-period of the example node, the degree of evacuation disorder is determined. Combined with the fluctuation trend of the degree of evacuation disorder in the sub-period, the degree of danger of the example node during the evacuation process is assessed. This allows the evacuation danger to be captured in real time by changes in path intersections and congestion caused by group behavior, thus improving the accuracy of risk prediction.

[0016] Thirdly, the difference in evacuation hazard between the example node and its adjacent nodes reflects the rationality of the theoretical evacuation route planning at the example node. This difference is used to dynamically adjust the theoretical dwell time of evacuation groups at nodes along the theoretical evacuation route, reducing the time groups spend in high-risk areas. By considering the dynamic impact of group behavior, the efficiency and safety of evacuation in super high-rise buildings are ensured, and the overall evacuation time is reduced. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the steps of a simulation method based on a complex building crowd evacuation model, provided in one embodiment of the present invention; Figure 2A schematic diagram of a computer device for simulating crowd evacuation in complex buildings, provided in one embodiment of the present invention. Detailed Implementation

[0019] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a simulation method based on a complex building crowd evacuation model proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0021] The following description, in conjunction with the accompanying drawings, details a specific scheme for a simulation method based on a complex building crowd evacuation model provided by the present invention.

[0022] Example 1: This invention proposes a simulation method based on a complex building crowd evacuation model. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a simulation method based on a complex building crowd evacuation model, provided by an embodiment of the present invention. The method includes: Step S1: Obtain the planned evacuation routes for each person in the target building and the actual dwell time of each person at each stop point on the planned evacuation route.

[0023] Dynamic simulations were performed using evacuation simulation software such as Pathfinder. Input parameters included: the target evacuation scenario (fire or earthquake); attributes of participants in the evacuation test (gender, age, and behavioral patterns, including calmness and panic); and a building model, i.e., a floor plan of the target building, including stairwells, corridors, refuge floors, and other rest areas. Participants could stay at these rest areas. Each participant evacuated downwards from their current floor. The simulation software calculated the building layout and rest area locations, and after the simulation, output the planned evacuation routes for each participant. Nodes on the planned evacuation routes represented the locations where participants stayed during the evacuation, and each node corresponded to an actual stay time, representing the time from arrival to departure from the rest area corresponding to that node.

[0024] Step S2: Based on the floor differences and the closeness of social relationships among different personnel, the personnel in the target building are divided into different evacuation groups; the planned evacuation routes of personnel in the same evacuation group are combined with the actual stay time of the nodes on them to obtain the theoretical evacuation routes and the theoretical stay time of each node on each evacuation group.

[0025] Existing evacuation models treat people as independent individuals, assuming they move along planned evacuation routes. However, complex buildings can be divided into different functional areas, including shopping malls, offices, and residences. Social relationships between people within these areas influence their route choices, leading to aggregation during evacuation. Therefore, this paper divides people within the target building into different evacuation groups based on floor differences and the closeness of their social relationships. Then, the planned evacuation routes for people within the same group are replanned to determine the theoretical evacuation routes for the group. This approach avoids the shortcomings of traditional models that treat people as independent individuals and ignore group dynamics, taking into account individual differences and ensuring coordination within the group.

[0026] Step S3: Select any evacuation group as the example group, and select any node on the theoretical evacuation route of the example group as the example node; based on the number of evacuation groups accommodated by the example node in each sub-period of the simulation period and the theoretical stay time of the evacuation groups at the example node, determine the evacuation disorder of the example node in each sub-period.

[0027] Different evacuation groups may choose to stay at the same location, leading to multiple groups converging at the same evacuation location within the same time period. This causes overlapping evacuation trajectories, increasing the chaos of the evacuation process. The theoretical dwell time of the evacuation groups accommodated at the example node in a sub-time period reflects the severity of congestion at the example node; severe congestion exacerbates the chaos of the evacuation process. Therefore, by analyzing the number of evacuation groups accommodated in a sub-time period and their theoretical dwell time, we can dynamically assess the spatial congestion and time delay at the example node, obtaining the degree of evacuation chaos. This helps prevent congestion and chaos and improves the controllability of the evacuation process.

[0028] In one implementation of this invention, the time period from the start to the end of the evacuation simulation software is denoted as the simulation period. The simulation period is evenly divided into several sub-periods of equal duration, and the number of sub-periods needs to be greater than 10. The implementer can set this according to the specific circumstances.

[0029] In this embodiment of the invention, at least one person is present in the evacuation group accommodated by the example node at each time point during the simulation period.

[0030] Step S4: Determine the evacuation risk level of the example node based on the evacuation disorder and its volatility trend in each sub-period of the simulation period.

[0031] Evacuation disorder reflects the likelihood of irregular movement of groups causing path intersections during the evacuation process at the example node. Path intersections exacerbate congestion at the example node, thus increasing the time required for the evacuation of groups accommodated by the example node. When the number of groups accommodated by a station exceeds the area's capacity, the evacuation disorder of the example node will fluctuate rapidly or decrease with the entry or exit of groups. Therefore, the fluctuation trend of the evacuation disorder of the example node in each sub-time period can indicate whether the number of groups accommodated by the example node exceeds the area's capacity. Staying at the example node is more dangerous when the area's capacity is exceeded. Therefore, by combining the above two factors to analyze the degree of danger of the example node during the evacuation process, the evacuation danger level is obtained.

[0032] Step S5: Based on the difference in evacuation risk between the example node and its adjacent nodes on the theoretical evacuation route of the example group, adjust the theoretical dwell time of the example node, determine the optimal dwell time of the example node, and determine the optimal evacuation route of the example group.

[0033] In the event of an emergency, the evacuation groups accommodated by the example node can evacuate to the next adjacent node with a lower risk level during the evacuation process, thus enabling the example node to cope with emergencies. The evacuation risk level of the example node directly reflects the rationality of the theoretical evacuation route planning at the example node. By adjusting the theoretical dwell time of the example node using both factors, and considering the actual evacuation capacity of the groups, the evacuation time of the example node is adjusted to obtain the optimized dwell time. The theoretical dwell time of the nodes on the theoretical evacuation route is then updated, enabling the replanning of evacuation routes for the example groups to obtain the optimized evacuation route, thereby ensuring the safe evacuation of personnel in the shortest possible time in complex building environments.

[0034] This scheme takes into account the dynamic impact of group behavior and achieves real-time optimization of evacuation routes by dynamically adjusting the theoretical dwell time of dwelling nodes. This ensures that evacuation groups can evacuate quickly and safely in complex environments, making the evacuation model more flexible and adaptable, and improving the simulation accuracy of crowd evacuation in super high-rise buildings.

[0035] Preferably, in some possible implementations of the embodiments of the present invention, the group division method includes: setting a social distance between every two people in the target building, wherein the smaller the social distance, the closer the social relationship between the two people; taking the absolute value of the difference between the floors where every two people in the target building are located at the start of evacuation as the floor distance; taking the product of the social distance and the floor distance as the distance index between every two people; clustering all people in the target building based on the distance index to obtain several clusters; and forming a group from people in the same cluster.

[0036] If the social relationships among the people in the target building can be categorized as: family members, company employees, and shop employees. In residential areas, people are typically distributed in family units, and the evacuation speed is influenced by the mutual care among family members; in office areas, people are distributed in company units, mostly young and middle-aged adults; in shop areas, people are distributed in shop units, with a relatively mixed distribution, and the closeness of social relationships decreases sequentially from family members to company employees to shop employees. In this embodiment, the social distance between two family members within the same family is set to 0.1, the social distance between two company employees within the same company is set to 0.5, the social distance between two shop employees within the same shop is set to 0.8, and in other cases, the social distance between two people is set to 1.

[0037] It should be noted that the smaller the social distance and floor distance, the closer the two people are on the floor and the closer their social relationship is when the evacuation begins. In this case, the greater the possibility that the two people will gather during the evacuation process.

[0038] In one implementation of this invention, the K-means clustering algorithm is used to cluster people, and the K value is determined by the elbow method.

[0039] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the theoretical evacuation route and the theoretical dwell time of its dwell nodes includes: for each evacuation group, a dwell set is formed by the dwell nodes included on the planned evacuation route of all personnel in the evacuation group; the arrival time of each person in the evacuation group to each dwell node on its planned evacuation route is obtained; the average arrival time of all personnel in the evacuation group to each dwell node in the dwell set is calculated to obtain the group arrival time of each dwell node in the dwell set; the dwell nodes in the dwell set are connected sequentially according to the order of group arrival time to generate the theoretical evacuation route of the evacuation group; a dwell node is randomly selected from the theoretical evacuation route and recorded as an example node, and the maximum value of the actual dwell time of all personnel in the evacuation group at the example node is taken as the theoretical dwell time of the example node on the theoretical evacuation route.

[0040] It should be noted that the dwell set determines the key locations that all members of the evacuation group may pass through along the theoretical evacuation route; the group's arrival time provides a time reference standard for coordinated group action, representing the time characteristic of the entire evacuation group reaching the dwell point. The evacuation of the group is constrained by the person with the longest dwell time, and the theoretical dwell time ensures sufficient accommodation for all personnel. The theoretical evacuation route considers both individual differences and group coordination, achieving a good balance between safety and feasibility.

[0041] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the evacuation disorder degree includes: taking the number of evacuation groups accommodated by the example node at each moment in the simulated time period; calculating the average number of evacuation groups accommodated by the example node at all moments in each sub-time period, and using the ratio of the average to the area of ​​the corresponding dwelling position of the example node as the group aggregation density of the example node in each sub-time period; arbitrarily selecting a sub-time period as the example time period, and selecting high-density aggregation nodes of the example time period from the dwelling nodes on the theoretical evacuation route of the example group based on the group aggregation density; averaging the theoretical dwelling time of the evacuation groups accommodated by each high-density aggregation point at all moments in the example time period to obtain the overall dwelling time of each high-density aggregation point in the example time period; obtaining the evacuation disorder degree based on the group aggregation density and overall dwelling time of each high-density aggregation point in the example time period; and setting the evacuation hazard degree of the remaining dwelling nodes on the theoretical evacuation route of the example group, excluding the high-density aggregation points of the example time period, to zero during the example time period.

[0042] In this embodiment of the invention, the average group aggregation density of all stopping nodes on the theoretical evacuation route of the example team during the example time period is used as the baseline aggregation density for the example time period; the group aggregation density of high-density aggregation nodes during the example time period is greater than the baseline aggregation density. It should be noted that the baseline aggregation density reflects the overall level of congestion on the theoretical evacuation route in the sub-time period; high-density aggregation nodes are congestion hotspots on the theoretical evacuation route and require targeted diversion measures.

[0043] The higher the group cluster density, the more evacuation groups a sample node can accommodate within a sample time period. This leads to more severe intersections of evacuation trajectories within the sample node during that time period, and a smaller area corresponding to the stop location of the sample node, resulting in a more chaotic evacuation process. Conversely, a longer overall dwell time indicates a longer dwell time for evacuation groups accommodated by high-density clusters within the sample time period. A longer dwell time signifies more severe congestion, further contributing to a more chaotic evacuation process. Therefore, both group cluster density and overall dwell time are positively correlated with evacuation disorder. In this embodiment of the invention, the product of the group cluster density and the overall dwell time of a high-density cluster during the sample time period is normalized to obtain the evacuation disorder of the high-density cluster during the sample time period.

[0044] In this embodiment of the invention, the product of the group aggregation density and the overall residence time of the high-density aggregation points in all sub-time periods is used for normalization processing using min-max normalization. Alternatively, normalization methods such as function transformation and Sigmoid function can be selected, and no limitation is made here.

[0045] It should be noted that the theoretical evacuation route of the example group is obtained using the same method as the high-density cluster nodes in the example time period and the other sub-time periods; the evacuation disorder of high-density cluster points is also obtained using the same method as the example time period and the other sub-time periods.

[0046] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the evacuation hazard degree includes: arranging the evacuation disorder degree of the example node in all sub-periods within the simulation period in chronological order to obtain a disorder degree sequence; obtaining a first-order difference sequence of the disorder degree sequence, and using the number of sign changes of two adjacent elements in the first-order difference sequence as the fluctuation trend degree of the example node; averaging the evacuation disorder degree of the example node in all sub-periods within the simulation period to obtain the overall disorder degree; and obtaining the evacuation hazard degree of the example node based on the fluctuation trend degree and the overall disorder degree.

[0047] It should be noted that the greater the overall disorder, the higher the probability of path intersections due to irregular movement of groups during the evacuation of the example node. This leads to increased congestion at the corresponding stopping point of the example node, further complicating the evacuation paths of different groups and resulting in longer evacuation times for the groups accommodated by the example node, thus increasing the danger of the evacuation process. Conversely, a greater fluctuation trend indicates a rapid increase and decrease in evacuation disorder between adjacent sub-periods of the high-density cluster point within the simulation period. This suggests that the number of groups accommodated at the stopping point of the high-density cluster point far exceeds the area's capacity, indicating that the theoretical evacuation route planning is unreasonable and that staying at that node during evacuation is more dangerous. Therefore, both fluctuation trend and overall disorder are positively correlated with evacuation danger. In this embodiment of the invention, the product of the fluctuation trend of the high-density cluster point and the overall disorder is used as the evacuation danger.

[0048] It should be noted that the evacuation hazard level of the last stop node, i.e., the exit, on the theoretical evacuation route of the example group is set to zero.

[0049] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the optimized evacuation time includes: normalizing the difference between the evacuation hazard level of the example node and the next adjacent node on the theoretical evacuation route of the example group to obtain the emergency response level of the example node; normalizing the product of the mapping result and the emergency response level based on the negative correlation mapping of the evacuation hazard level of the example node to obtain the planning rationality of the example node; and weighting the theoretical dwell time of the example node using the planning rationality to obtain the optimized dwell time of the example node.

[0050] It should be noted that the higher the evacuation hazard level of the example node, the greater the influence of group behavior patterns on the evacuation process and the higher the hazard level. Therefore, the theoretical evacuation route planning at the example node is less reasonable. Conversely, a higher emergency response level indicates a greater likelihood that the evacuation group accommodated by the example node can adjust to the next adjacent node with a lower hazard level during the evacuation process, thus adequately responding to emergencies. Therefore, the theoretical evacuation route planning at the example node is more reasonable. Thus, evacuation hazard level is negatively correlated with planning rationality, while emergency response level is positively correlated with planning rationality. A higher planning rationality level indicates a more reasonable theoretical dwell time planning for the example node, and the corrected optimized dwell time should be closer to the theoretical dwell time. Conversely, a less reasonable theoretical dwell time planning for the example node can reduce the hazard level by decreasing the dwell time, and the corrected optimized dwell time should be less than the theoretical dwell time.

[0051] In this embodiment of the invention, max-min normalization is used for normalization. Alternatively, function transformation, sigmoid function, or other normalization methods may be selected, and no limitation is made here.

[0052] It should be noted that the optimized dwell time of the example group at the example node is obtained in the same way as that of the other dwelling nodes.

[0053] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the optimized evacuation route includes: updating the theoretical dwell time of the corresponding dwell node using the optimized dwell time of each dwell node on the theoretical evacuation route of the example group, and using the updated theoretical evacuation route as the optimized evacuation route of the example group. It should be noted that the method for obtaining the optimized evacuation route is the same for all evacuation groups and the example group.

[0054] This invention is now complete.

[0055] Example 2: This invention also presents a schematic diagram of a computer device for simulating crowd evacuation in complex buildings. Please refer to [link / reference]. Figure 2 The computer device includes a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602. When the processor 602 executes the computer program 603, the computer device can execute any of the simulation methods based on complex building crowd evacuation models described above.

[0056] Furthermore, this application also protects an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a simulation method based on a complex building crowd evacuation model provided in this application.

[0057] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0058] When each module is divided according to its function, the device may also include a communication module, a signal analysis module, a complexity analysis module, and a positioning module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0059] It should be understood that the device provided in this embodiment is used to execute the above-described simulation method based on a complex building crowd evacuation model, and therefore can achieve the same effect as the above-described implementation method.

[0060] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0061] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0062] Example 3: This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement the simulation method based on a complex building crowd evacuation model provided in the above embodiment.

[0063] In this embodiment, the device or computer-readable storage medium is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding method provided above, and will not be repeated here.

[0064] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0065] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A simulation method based on a complex building crowd evacuation model, characterized in that, The method includes: Obtain the planned evacuation routes for each person in a target building with multiple floors, as well as the actual dwell time of each person at each stop point on the planned evacuation route. Based on the floor differences and the closeness of social relationships among different individuals, the people in the target building are divided into different evacuation groups. This includes: setting a social distance between every two people in the target building, where the smaller the social distance, the closer the social relationship between the two individuals; using the absolute value of the difference in the floors where every two people in the target building are located at the start of evacuation as the floor distance; using the product of the social distance and the floor distance as the distance index between every two people; clustering all people in the target building based on the distance index to obtain several clusters; and forming an evacuation group from individuals within the same cluster. The planned evacuation routes of people within the same evacuation group are combined with the actual stay times at the stops along these routes to obtain the theoretical evacuation routes and the theoretical stay times at each stop along these routes for each evacuation group; wherein, the theoretical stay time is the maximum value among the actual stay times of all people within the evacuation group at the corresponding stop nodes. Select an evacuation group as an example group, and select a node from the theoretical evacuation route of the example group as an example node; based on the number of evacuation groups accommodated by the example node in each sub-period of the simulation period and the theoretical stay time of the evacuation groups at the example node, determine the evacuation disorder of the example node in each sub-period; wherein, the evacuation group accommodated refers to an evacuation group in which at least one person is at the example node at the corresponding time. Based on the evacuation disorder and its volatility trend of the example node in each sub-period of the simulation period, the evacuation risk of the example node is determined. Based on the difference in evacuation hazard between example nodes and adjacent nodes on the theoretical evacuation route of the example group, the theoretical dwell time of the example nodes is adjusted to determine the optimal dwell time of the example nodes, and the optimal evacuation route of the example group is determined, including: using the optimal dwell time of each dwell node on the theoretical evacuation route of the example group, updating the theoretical dwell time of the corresponding dwell node, and using the updated theoretical evacuation route as the optimal evacuation route of the example group.

2. The simulation method based on a complex building crowd evacuation model according to claim 1, characterized in that, The process of obtaining the theoretical evacuation route for each evacuation group and the theoretical dwell time at each stop point on it includes: For each evacuation group, the set of stops consists of the stops along the planned evacuation routes of all personnel within the evacuation group. Obtain the arrival time of each person in the evacuation group to each stop point on their planned evacuation route; The average arrival time of all personnel in the evacuation group to each stop point in the stop set is calculated to obtain the group arrival time of each stop point in the stop set. The theoretical evacuation routes for the evacuation groups are generated by sequentially connecting the nodes within the evacuation group according to the order of their arrival times. Select any one of the stops on the theoretical evacuation route and record it as the analysis node. Take the maximum value of the actual stay time of all personnel in the evacuation group at the analysis node as the theoretical stay time of the analysis node on the theoretical evacuation route.

3. The simulation method based on a complex building crowd evacuation model according to claim 1, characterized in that, The determination of the evacuation disorder level of the example node in the corresponding sub-time period includes: Obtain the number of evacuation groups accommodated by the example node at each time point during the simulation period; Calculate the average number of evacuation groups accommodated by the example node at all times within each sub-period, and use the ratio of the average to the area of ​​the corresponding dwelling location of the example node as the group aggregation density of the example node in each sub-period. Choose any sub-time period as the example time period, and select high-density clustering nodes of the example time period from the dwelling nodes on the theoretical evacuation route of the example group based on the group's clustering density. The average of the theoretical dwell time of the evacuation groups accommodated at each high-density cluster node at all times during the example period is used to obtain the overall dwell time of each high-density cluster node during the example period. The degree of evacuation disorder is obtained based on the group aggregation density and the overall dwell time of each high-density aggregation node during the example time period; The evacuation risk of all remaining nodes on the theoretical evacuation route of the example group, except for the high-density cluster nodes during the example period, is set to zero during the example period.

4. The simulation method based on a complex building crowd evacuation model according to claim 1, characterized in that, Determining the evacuation hazard level of the example node includes: Arrange the evacuation disorder of the example node in all sub-periods within the simulation period in chronological order to obtain the disorder sequence; Obtain the first-order difference sequence of the disorder sequence, and use the number of sign changes of two adjacent elements in the first-order difference sequence as the volatility trend of the example node; The overall disorder is obtained by averaging the evacuation disorder of the example node across all sub-periods during the simulation period. Based on the fluctuation trend and the overall disorder, the evacuation risk level of the example node is obtained.

5. The simulation method based on a complex building crowd evacuation model according to claim 1, characterized in that, The determination of the optimized dwell time for the example node includes: The difference between the evacuation hazard level of the example node and the next adjacent node on the theoretical evacuation route of the example group is normalized to obtain the emergency response level of the example node. A negative correlation mapping is performed on the evacuation hazard degree of the example node, and the product of the mapping result and the emergency response degree is normalized to obtain the planning rationality of the example node. The theoretical dwell time of the example node is weighted using the planning rationality to obtain the optimized dwell time of the example node.

6. The simulation method based on a complex building crowd evacuation model according to claim 3, characterized in that, The high-density clustered nodes selected for the example time period include: The average of the group aggregation density of all the stopping nodes on the theoretical evacuation route of the example group during the example time period is used as the baseline aggregation density for the example time period. The high-density clustered nodes have a higher group cluster density during the example time period than the baseline cluster density during the example time period.

7. The simulation method based on a complex building crowd evacuation model according to claim 1, characterized in that, The method used to cluster all people in the target building is the K-means clustering algorithm.

Images