Methods, devices, equipment, media, and programs for predicting the dynamic location of people in enclosed spaces.

Abstract

This invention discloses a method, device, equipment, medium, and program product for dynamic prediction of crowd location in enclosed spaces. The method includes: dividing a target space into multiple spatial units, determining the facility attraction value of each spatial unit based on the facility distribution information of the target space, dividing the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and determining the target crowd attraction value of each spatial unit, determining the comprehensive attraction value of each spatial unit based on the target crowd attraction value and the facility attraction value, and predicting the dynamic distribution of crowds in the target space based on the comprehensive attraction value. Because this invention analyzes the comprehensive attraction of each spatial unit in the enclosed space from multiple dimensions, it can accurately predict the dynamic distribution of crowds in the enclosed space, achieve reasonable optimization of the space, effectively optimize passenger comfort in the enclosed space, significantly reduce spatial conflicts, and improve safety in the enclosed space.

Description

Technical Field

[0001] This invention relates to the field of crowd prediction technology, and in particular to a method, apparatus, equipment, medium, and program product for dynamic prediction of crowd location in enclosed spaces. Background Technology

[0002] With the increasing prevalence of urban rail transit and the continuous increase in passenger flow during peak hours, the safety and comfort issues arising from changes in crowd density within subway cars have gradually become a focus of attention. In high-density car environments, passengers experience significantly increased crowding, and the resulting safety hazards cannot be ignored. Especially during peak hours, the agglomeration effect intensifies, and the interaction between individual and group behaviors easily leads to spatial conflicts and traffic congestion, significantly reducing the utilization efficiency of car space. Therefore, how to accurately predict the distribution of people within subway cars has become one of the key issues for improving the efficiency of passenger management and optimizing the passenger experience.

[0003] Currently, behavioral modeling and simulation technologies are widely used in the field of public transportation crowd management. For example, research based on pedestrian flow assessment and modeling has revealed the flow characteristics of crowds at different densities, providing a reference for subway passenger flow management. However, such studies mostly focus on passenger flow management in open spaces such as stations and platforms, paying less attention to the special scenarios inside subway cars. Subway cars are relatively small, restricting passenger movement and making it difficult for them to disperse freely, resulting in a highly concentrated and interactive crowd distribution. Furthermore, while research based on pedestrian dynamic models is often used to analyze emergency evacuation and control, it fails to provide detailed predictions of crowd distribution at different densities and time periods because it does not consider the car environment under normal operating conditions. Existing simulation methods mainly rely on physical characteristics (such as space occupancy and movement trajectories) for prediction, failing to fully capture the psychological motivations behind crowd behavior. Different groups (such as families, couples, and solo travelers) have significantly different spatial needs, making it currently impossible to accurately predict the spatial distribution of crowds. This leads to an inability to effectively optimize passenger experience, avoid spatial conflicts, and result in lower safety and comfort in high-density spaces. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, equipment, medium, and program product for dynamic prediction of the location of people in enclosed spaces. This invention aims to solve the technical problem that existing technologies cannot accurately predict the spatial distribution of people, resulting in an inability to effectively optimize passenger experience, avoid spatial conflicts, and reduce the safety and comfort of enclosed spaces.

[0005] To achieve the above objectives, the present invention provides a method for dynamic prediction of the location of people in a confined space, the method comprising the following steps:

[0006] The target space is divided into multiple spatial units, and the facility attractiveness value of each spatial unit is determined based on the facility distribution information of the target space.

[0007] Based on the population distribution characteristics of the passenger group in the target space, the passenger group is divided into multiple subgroups, and the target population attraction value of each spatial unit is determined.

[0008] The overall attractiveness value of each spatial unit is determined based on the target population attractiveness value and the facility attractiveness value;

[0009] Based on the comprehensive attractiveness value, the dynamic distribution of the population in the target space is predicted to obtain the population distribution prediction result. The population distribution prediction result is used to optimize the facility distribution structure and spatial distribution structure of the target space.

[0010] Optionally, the step of dividing the passenger group into multiple subgroups based on the population distribution characteristics of the passenger group in the target space, and determining the target population attraction value for each spatial unit, includes:

[0011] Target detection is performed on the target space to determine the passenger groups within the target space;

[0012] Perform feature analysis on the passenger group to obtain the population distribution characteristics of the passenger group;

[0013] Based on the population distribution characteristics, the passenger group is divided into multiple subgroups, and the intimacy of each subgroup is quantified according to a preset social intimacy quantification table to determine the intimacy value of each subgroup.

[0014] The initial expected distance and initial position of each group member in the subgroup are determined based on the intimacy value;

[0015] Based on the initial expected distance and the initial location, an attraction analysis is performed on each group member to determine the target population attraction value for each spatial unit.

[0016] Optionally, the step of performing attraction analysis on each group member based on the initial expected distance and the initial location to determine the target population attraction value of each spatial unit includes:

[0017] Based on the initial expected distance and the initial location, an attraction analysis is performed on each group member to determine the initial crowd attraction value between each group member:

[0018]

[0019] in, Represents an individual With individuals The initial crowd attraction value between them It represents the peak attractiveness of different subgroups. This represents the maximum attraction value between groups with different levels of intimacy. It is the expected distance. It is the standard deviation of the spatial distribution of attraction, used to control for deviation of attraction from distance. The decay rate, Represents an individual With individuals The distance between them;

[0020] Group aggregation analysis is performed on each subgroup to determine the territory structure type of each subgroup. The territory structure types include chain structure, ring structure and fully connected structure.

[0021] The initial crowd attraction value is adjusted based on the territory structure type to obtain the candidate group attraction value;

[0022] By coupling the attractiveness values ​​of the candidate group, the target population attractiveness value of each spatial unit is obtained:

[0023]

[0024] in, Indicates the attractiveness value to the target audience. This indicates the attractiveness value of the candidate group. Represents an individual The weight of attraction to spatial units.

[0025] Optionally, determining the overall attractiveness value of each spatial unit based on the target population attractiveness value and the facility attractiveness value includes:

[0026] Generate the initial social force weights and initial environmental force weights for the target space;

[0027] Based on the scenario requirement information of the target space, an adjustment factor is obtained, and the initial social force weight and the initial environmental force weight are adjusted based on the adjustment factor to obtain the target social force weight and the target environmental force weight.

[0028]

[0029]

[0030] in, Indicates the target social influence weight. Indicates the target environmental force weights. Indicates the initial social power weight. Indicates the initial environmental force weights. Indicates the adjustment factor;

[0031] Based on the target social influence weight and the target environmental influence weight, the attraction values ​​of the target population and the facility are aggregated to determine the comprehensive attraction value of each spatial unit:

[0032]

[0033] in, This represents the overall attractiveness score. Indicates the attractiveness value to the target audience. Indicates the attractiveness value of the facility;

[0034] The attractiveness value of the facility is calculated using the following formula:

[0035]

[0036] in, For facilities The weight of the attraction of spatial units, As a proportional parameter for the attractiveness of facilities, Used to control the range of attraction decay, For shape parameters, Used to adjust the shape of the curve for attraction decay.

[0037] Optionally, the step of predicting the dynamic distribution of the population in the target space based on the comprehensive attractiveness value includes:

[0038] Determine the occupancy status of each spatial unit, and determine the free units within the spatial units based on the occupancy status;

[0039] Monitor whether there are any idle units around the current unit where each group member is located that have a higher overall attraction value than the current unit;

[0040] Based on the monitoring results and the comprehensive attraction value, the dynamic distribution of the population in the target space is predicted until the members of each group meet the preset steady-state conditions.

[0041] The preset steady-state condition includes at least one of the following:

[0042] The first steady-state condition includes: the positions of group members remain unchanged during the prediction period;

[0043] The second steady-state condition includes: there are no idle units around the current unit where the group member is located that have a higher overall attraction value than the current unit;

[0044] The third steady-state condition includes: the global attractiveness increment of the current unit in which the group members are located is lower than a preset threshold.

[0045] Optionally, the step of predicting the dynamic distribution of the population in the target space based on the comprehensive attractiveness value includes:

[0046] The target space is divided into multiple first-level grids based on the base grid;

[0047] The primary grid is divided into multiple secondary grids according to a preset division scale;

[0048] Calculate the Euclidean distance between each second-level grid and the population center of each subpopulation:

[0049]

[0050] in, Represents Euclidean distance. This represents the position index of the secondary grid in the target space. Representing the second-level grid Axis coordinates Representing the second-level grid Axis coordinates Represents the group center point of Axis coordinates Represents the group center point of Axis coordinates;

[0051] Based on the Euclidean distance, each secondary grid is divided into regional grids to obtain regional grid division results. The regional grid division results include the territory division results of each subgroup and the potential conflict area division results.

[0052] Calculate the conflict risk parameters between each subgroup based on the regional grid division results:

[0053]

[0054] in, Indicates the conflict risk parameter. and Representing groups and group For secondary grids The overall attractiveness value, Representing a group with the group The average distance between them It is a positive number. An indicator function representing the result of the region gridding, when the second-level grid... The indicator function is set to 1 when it is located in the overlapping area of ​​the territories of two subgroups; otherwise, the indicator function is set to 0.

[0055] Based on the conflict risk parameters, the dynamic distribution of the population in the target space is predicted.

[0056] Furthermore, to achieve the above objectives, the present invention also proposes a dynamic prediction device for the location of people in a confined space, the device comprising:

[0057] The facility attractiveness analysis module is used to divide the target space into multiple spatial units and determine the facility attractiveness value of each spatial unit based on the facility distribution information of the target space.

[0058] The crowd attraction analysis module is used to divide the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and to determine the target crowd attraction value of each spatial unit.

[0059] The comprehensive attractiveness analysis module is used to determine the comprehensive attractiveness value of each spatial unit based on the attractiveness value of the target population and the attractiveness value of the facility;

[0060] The crowd dynamic prediction module is used to predict the dynamic distribution of the crowd in the target space based on the comprehensive attraction value, and to obtain the crowd distribution prediction result. The crowd distribution prediction result is used to optimize the facility distribution structure and spatial distribution structure of the target space.

[0061] In addition, to achieve the above objectives, this application also proposes a device for dynamic prediction of the location of people in a confined space. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the method for dynamic prediction of the location of people in a confined space as described above.

[0062] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for dynamic prediction of the location of people in a confined space as described above.

[0063] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the method for dynamic prediction of the location of people in a confined space as described above.

[0064] This invention divides a target space into multiple spatial units, determines the facility attractiveness value of each spatial unit based on the facility distribution information of the target space, divides the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and determines the target crowd attractiveness value of each spatial unit. Based on the target crowd attractiveness value and the facility attractiveness value, a comprehensive attractiveness value is determined for each spatial unit. Based on the comprehensive attractiveness value, the dynamic distribution of the crowd in the target space is predicted. Because this invention analyzes the comprehensive attractiveness of each spatial unit within a confined space from multiple dimensions, it accurately predicts the dynamic distribution of the crowd within the confined space, achieving reasonable optimization of the space. This effectively optimizes passenger comfort in the confined space, significantly reduces spatial conflicts, and improves safety within the confined space. Attached Figure Description

[0065] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 This is a schematic diagram of the structure of a device for dynamically predicting the location of people in a confined space, which is part of the hardware operating environment of the present invention.

[0067] Figure 2 This is a flowchart illustrating the first embodiment of the method for dynamic prediction of the location of people in a confined space according to the present invention.

[0068] Figure 3 This is a flowchart illustrating the second embodiment of the method for dynamic prediction of the location of people in a confined space according to the present invention.

[0069] Figure 4 This is a structural block diagram of the first embodiment of the device for dynamic prediction of the location of people in a confined space according to the present invention.

[0070] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0071] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0072] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a device for dynamically predicting the location of people in a confined space, which is part of the hardware operating environment of an embodiment of the present invention.

[0073] like Figure 1As shown, the enclosed space crowd location dynamic prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0074] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the device for dynamically predicting the location of people in a confined space. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0075] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a dynamic prediction program for the location of people in a confined space.

[0076] exist Figure 1 In the enclosed space crowd location dynamic prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the enclosed space crowd location dynamic prediction device of the present invention can be set in the enclosed space crowd location dynamic prediction device. The enclosed space crowd location dynamic prediction device calls the enclosed space crowd location dynamic prediction program stored in the memory 1005 through the processor 1001 and executes the enclosed space crowd location dynamic prediction method provided in the embodiment of the present invention.

[0077] This invention provides a method for dynamically predicting the location of people in a confined space, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the method for dynamic prediction of the location of people in a confined space according to the present invention.

[0078] In this embodiment, the method for dynamically predicting the location of people in a confined space includes the following steps:

[0079] Step S10: Divide the target space into multiple spatial units, and determine the facility attraction value of each spatial unit based on the facility distribution information of the target space.

[0080] It should be noted that this embodiment can be applied to the prediction and layout optimization of crowd distribution in enclosed spaces (such as subway cars, waiting halls, conference rooms, etc.). Based on the attraction value model and the distribution analysis of intimacy, dynamic predictions are made for different groups of people. This method guides space optimization, so that people are more rationally distributed in the space, improving comfort and space utilization.

[0081] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a terminal electronic device capable of performing the above functions. The following description uses a terminal device as an example to illustrate this embodiment and the subsequent embodiments.

[0082] It should be noted that the spatial unit can be a cell grid or a raster grid. In this embodiment, the target space can be divided into multiple body-size cell grids, for example, the target space can be divided into multiple 0.45m×0.45m body-size cell grids.

[0083] In some embodiments, taking a train carriage as an example, the terminal device determines the passenger space occupancy rate in the carriage layout plan based on the passenger vehicle dimensions and projected area. Combining human body dimensions and pedestrian traffic ergonomic design dimensions, it derives the projected area S1 as the area required for comfortable standing by passengers. Based on the area required for comfortable standing by passengers and the passenger space occupancy rate, it determines the baseline social distance for people in the carriage as one body length distance. =45cm, the target space is divided into grids based on the body distance.

[0084] It should be noted that facility distribution information can refer to the location distribution of facilities within the target space, such as vehicle doors, seats, armrests, charging ports, etc. Facility attractiveness value can be the attractiveness of the facilities within the target space to each spatial unit.

[0085] It is understandable that for a particular facility (such as seating), it affects a specific spatial unit. The attractiveness value decreases as the distance between the spatial unit and the facility increases. Therefore, we use an exponential decay function to represent the decrease in attractiveness with distance. The formula for the exponential decay function is as follows:

[0086]

[0087] in, Indicating facilities and space units The distance between them It is an adjustable parameter used to control the rate at which the attractive force diminishes;

[0088] The above exponential decay function means that when the facility is close to the space unit (i.e., When the value approaches 0, the attraction value The attractiveness value approaches 1; however, as distance increases, the attractiveness value gradually approaches zero. This model reflects the trend that the attractiveness of a facility to a spatial unit gradually decreases with increasing distance.

[0089] In some embodiments, within enclosed spaces such as vehicle compartments, multiple facilities (such as seats, armrests, and doors) simultaneously affect a given spatial unit. Therefore, it is necessary to combine the attractive forces of these multiple facilities to obtain the overall attractive force of the spatial unit. The formula for the overall attractive force of multiple facilities is as follows:

[0090]

[0091] in, For facilities The weight of the attraction of spatial units, As a proportional parameter for the attractiveness of facilities, Used to control the range of attraction decay, For shape parameters, Used to adjust the shape of the curve for attraction decay.

[0092] Step S20: Divide the passenger group into multiple subgroups according to the distribution characteristics of the passenger group in the target space, and determine the target crowd attraction value of each spatial unit.

[0093] It should be noted that the target audience's attractiveness value can be the attractiveness value between people in the target space, such as an individual. With individuals The attraction value between them.

[0094] In some embodiments, the terminal device can identify passenger groups in the target space through a target recognition algorithm, collect historical data information of each passenger in the passenger group (e.g., passenger age, gender, occupation, number of trips, etc.), and perform feature analysis on the passenger group based on the distance and spatial distribution information between each passenger, combined with the historical data information, to obtain the population distribution characteristics, classify each passenger based on the population distribution characteristics, divide the passenger group into multiple subgroups based on the classification results, and determine the target population attraction value of each spatial unit.

[0095] Step S30: Determine the comprehensive attractiveness value of each spatial unit based on the target population attractiveness value and the facility attractiveness value.

[0096] It should be noted that the overall attractiveness value can be obtained by combining the attractiveness of people and the attractiveness of facilities to obtain the overall attractiveness value of the current space.

[0097] In some embodiments, the terminal device may combine a multi-factor weighting model to aggregate the attractiveness values ​​of the target population and the facilities to determine the comprehensive attractiveness value of each spatial unit.

[0098] Furthermore, in order to accurately calculate the combined attractive force generated by the interaction between the crowd and the facility, step S30 above may include:

[0099] Step S301: Generate the initial social force weights and initial environmental force weights of the target space;

[0100] Step S302: Obtain adjustment factors based on the scene requirement information of the target space, and adjust the initial social force weight and the initial environmental force weight based on the adjustment factors to obtain the target social force weight and the target environmental force weight;

[0101] Step S303: Aggregate the attraction value of the target population and the attraction value of the facility based on the target social force weight and the target environmental force weight to determine the comprehensive attraction value of each spatial unit.

[0102] It should be noted that this embodiment can apply the social force model to model crowd behavior in enclosed spaces, decomposing "social force" into: social force and environmental force. Social force reflects the interaction force between passengers, i.e., the attraction between group members, denoted as... Environmental forces reflect the interaction between passengers and surrounding facilities, that is, the attraction of facilities to passengers, denoted as ; Considering the combined influence of social and environmental forces, the comprehensive attractiveness model of spatial units is defined as follows:

[0103]

[0104] in, This represents the overall attractiveness score. and These are weighting coefficients, representing the weights of the influence of social forces and environmental forces on the distribution of group members, respectively.

[0105] This represents the target audience's attractiveness value, which is the sum of the attractiveness within the group. It is based on the intimacy and distance between individuals and the group's topology, reflecting the interaction force between group members. This part of the attractiveness will change with time and spatial location.

[0106] This represents the facility's attractiveness value, determined by the facility's location and attractiveness function, indicating the facility's basic appeal to passengers.

[0107] In practical applications, social power in different scenarios and environmental forces The influence weights are different. This is addressed by introducing initial weights. and This allows for flexible adjustment of the influence of social and environmental forces. Adjustment factors are introduced based on different scenario requirements. To adjust the weights.

[0108]

[0109]

[0110] in, Indicates the target social influence weight. Indicates the target environmental force weights. Indicates the initial social power weight. Indicates the initial environmental force weights. The adjustment factor determines the relative weights of social and environmental power, through... Positive and negative changes, regulation and The magnitude of this factor allows the influence of social and environmental forces to be adapted to different scenarios. For example, the adjustment factor. =0.2 indicates that increasing reduces the influence of environmental forces, while decreasing increases the influence of social forces; and = -0.2 indicates that the influence of social forces is increased, while the influence of environmental forces is decreased;

[0111] Based on the above settings, the final formula for overall attractiveness is:

[0112]

[0113] In some embodiments, the facility attractiveness value is calculated with reference to the following formula:

[0114]

[0115] in, For facilities The weight of the attraction of spatial units, As a proportional parameter for the attractiveness of facilities, Used to control the range of attraction decay, For shape parameters, Used to adjust the shape of the curve for attraction decay.

[0116] Step S40: Based on the comprehensive attraction value, predict the dynamic distribution of the population in the target space to obtain the population distribution prediction result.

[0117] It should be noted that the crowd distribution prediction results are used to optimize the facility distribution structure and spatial distribution structure of the target space. For example, the terminal device can adjust and optimize the facilities such as seats and handrails in the carriage space based on the crowd distribution prediction results to improve the rationality of the carriage space layout, thereby improving the spatial comfort of passengers and reducing the risk of spatial conflicts.

[0118] In some embodiments, the terminal device can guide group members in the target space based on the crowd distribution prediction results to guide them to adjust their current position. For example, it can guide group members to the nearby empty cell grid with high overall attractiveness through voice broadcast, thereby improving the comfort of group members in the target space.

[0119] It is understood that this embodiment divides the target space into multiple spatial units, calculates the comprehensive attractiveness value of each spatial unit by combining facility attractiveness and crowd attractiveness, and determines the attractiveness of each spatial unit to members of each group in the target space. This enables dynamic prediction of crowd distribution, spatial optimization, facility optimization, and dynamic location adjustment, thereby improving the spatial comfort of members of each group and reducing the risk of spatial conflict.

[0120] Furthermore, in order to effectively improve the spatial comfort of group members within the target space and to reasonably adjust the positions of each group member, in some embodiments, step S40 above may include:

[0121] Step S41: Determine the occupancy status of each space unit, and determine the free units in the space unit based on the occupancy status;

[0122] Step S42: Monitor whether there are any idle units around the current unit where each group member is located that have a higher overall attraction value than the current unit;

[0123] Step S43: Based on the monitoring results and the comprehensive attraction value, predict the dynamic distribution of the population in the target space until the members of each group meet the preset steady-state conditions.

[0124] In some embodiments, the terminal device can monitor in real time whether there are unoccupied, more attractive cell grids within eight grid distances in any direction around the cell grid where each member is located, predict whether the member will move based on the real-time monitoring results, and dynamically adjust the position of each group member.

[0125] It should be noted that the aforementioned preset steady-state condition can be a pre-set judgment condition used to determine whether a member has reached a steady state, and the preset steady-state condition includes at least one of the following:

[0126] The first steady-state condition includes: the position of the group members remains unchanged within the prediction time, that is, the position of each member remains unchanged in multiple consecutive cycles, then the system can be considered to have reached steady state;

[0127] The second steady-state condition includes: there are no idle cells around the current cell where a group member is located that have a higher overall attraction value than the current cell. This is achieved by calculating the attraction value difference between the grid where each member is located and the attraction values ​​of the eight surrounding grids. If the difference is negative or zero, it indicates that the individual has no target location with higher attraction, and steady-state can be considered achieved.

[0128] The third steady-state condition includes: the global attraction increment of the current unit where a group member is located is lower than a preset threshold. That is, after each iteration, the total attraction value of all member positions is calculated, and the difference between the two iterations is compared. If the difference is less than the set threshold (e.g., 0.1), the system is considered to be close to steady state.

[0129] Furthermore, in order to reduce the risk of conflict within the target space, in some embodiments, step S40 above may include:

[0130] Step S401: Divide the target space into multiple first-level grids based on the base grid.

[0131] It should be noted that in this embodiment, the entire carriage can be regarded as a two-dimensional plane. A basic grid is used to divide the carriage into grids, and each first-level grid cell is used as the basic calculation unit. This level of division is used to identify the main distribution area of ​​the group, that is, the territory of each group.

[0132] Step S402: Divide the primary grid into multiple secondary grids according to a preset division scale.

[0133] It should be noted that this embodiment introduces a finer-grained grid on top of the primary grid, for example, further subdividing the grid cells to a scale of 0.15*0.15m. This secondary grid is used to analyze more subtle behavioral patterns in important or high-risk areas, particularly the microscopic distribution and conflict situations of passengers in crowded spaces.

[0134] Step S403: Calculate the Euclidean distance between each secondary grid and the population center of each sub-population.

[0135] It should be noted that, assuming there are within the space There are several groups, and the center position of each group is... It means that, among them The position of each cell in the grid is denoted as... , indicating that the cell is located at the th grid. row and number Column. Calculate each grid cell using the Euclidean distance formula. To the center point of all groups The distance is calculated using the following formula:

[0136]

[0137] in, Represents Euclidean distance. This represents the position index of the secondary grid in the target space. Representing the second-level grid Axis coordinates Representing the second-level grid Axis coordinates Represents the group center point of Axis coordinates Represents the group center point of Axis coordinates.

[0138] Step S404: Divide each secondary grid into regional grids based on the Euclidean distance to obtain the regional grid division results.

[0139] It should be noted that the regional grid division results include the territorial area division results of each subgroup and the potential conflict area division results.

[0140] The above territory division results can be used to find the distance from the grid cell. The nearest group center The grid cell is then assigned to the nearest group to reflect that group's territory.

[0141] The above-mentioned conflict zone delineation can be used to mark grid cells that are close to the center points of multiple groups as potential conflict zones. These zones may experience conflict due to interactions between groups.

[0142] Step S405: Calculate the conflict risk parameters between each subgroup based on the regional grid division results;

[0143] Step S406: Based on the conflict risk parameters, predict the dynamic distribution of the population in the target space.

[0144] It should be noted that, in order to assess the conflict risk of each grid cell, a generalization based on the law of universal gravitation is used, analogizing the attraction between people to gravity, thus equating the conflict risk between groups of people to the forces acting in a gravitational field. Therefore, a conflict risk function is defined. Used to evaluate each spatial unit The risk of conflict.

[0145] The conflict risk formula is defined as follows:

[0146]

[0147] in, Indicates the conflict risk parameter. Indicates the position index of the grid cell, located at the . line, number List, and Representing groups and group For secondary grids The overall attractiveness value, Representing a group with the group The average distance between them An indicator function representing the result of the region gridding, when the second-level grid... The indicator function is set to 1 when the territory of the two subgroups overlaps; otherwise, the indicator function is set to 0. It is a small positive number used to prevent the denominator from being zero.

[0148] In the conflict risk formula, conflict risk Includes each group and The attraction product of a specific grid cell This product term reflects the combined attractiveness of the two groups to the cell: if the two groups have a combined attraction to the mesh cell... If the attraction of a group to a unit is high, the product value will be large, indicating that the area has high conflict potential. If the attraction of a group to a unit is weak or nonexistent, the conflict risk of that unit is low.

[0149] In the calculation of conflict risk, a term similar to the inverse square distance term in the gravity formula is introduced. This reflects the following relationship: when the average distance between two groups... When the distance between the two groups is small, this term increases, indicating a higher risk of conflict when they are close together. When the distance between the two groups is large, this term approaches zero, indicating a lower risk of conflict when they are far apart. Introducing a small positive number... This can prevent the denominator from being zero, ensuring the stability of the formula.

[0150] Indicator Function Used to identify whether a spatial cell belongs to an overlapping area of ​​two groups' territories. Through Thiessen polygon partitioning, the territories of two groups can overlap to form potential conflict areas, according to the following rules: when a grid cell... Falling into the group and group When the grid cell belongs to an overlapping territory, the indicator function takes a value of 1. If the grid cell belongs to only one group's territory or is not within any overlapping territory, the indicator function takes a value of 0.

[0151] It should be noted that this embodiment monitors the conflict risk of spatial units in real time and dynamically adjusts the crowd layout in high-risk areas to ensure passenger safety and comfort. This dynamically adjusted crowd distribution optimization strategy can effectively avoid crowd conflicts and reduce unnecessary congestion.

[0152] This embodiment divides the target space into multiple spatial units and determines the facility attractiveness value of each spatial unit based on the facility distribution information of the target space. It also divides the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space and determines the target crowd attractiveness value of each spatial unit. Finally, it determines the comprehensive attractiveness value of each spatial unit based on the target crowd attractiveness value and the facility attractiveness value, and predicts the dynamic distribution of the crowd in the target space based on the comprehensive attractiveness value. Because this embodiment analyzes the comprehensive attractiveness of each spatial unit within the enclosed space from multiple dimensions, it accurately predicts the dynamic distribution of the crowd within the enclosed space, achieving reasonable optimization of the space. This effectively optimizes passenger comfort in the enclosed space, significantly reduces spatial conflicts, and improves safety within the enclosed space.

[0153] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the method for dynamic prediction of the location of people in a confined space according to the present invention.

[0154] Based on the first embodiment described above, in this embodiment, step S20 further includes:

[0155] Step S201: Perform target detection on the target space to determine the passenger group in the target space.

[0156] In some embodiments, the terminal device may use object detection algorithms (such as YOLO v7 deep learning object detection algorithm) to identify and classify historical data of passenger groups in the carriage, and use the spatial clustering algorithm DBSCAN to analyze the spatial relationship between individuals within the same group, thereby completing the preliminary division of the passenger group.

[0157] Step S202: Perform feature analysis on the passenger group to obtain the population distribution characteristics of the passenger group.

[0158] In practical implementation, the terminal device can identify passenger groups in the target space through target recognition algorithms, collect historical data information of each passenger in the passenger group (such as passenger age, gender, occupation, number of trips, etc.), and perform feature analysis on the passenger group based on the distance and spatial distribution information between each passenger, combined with historical data information, to obtain the population distribution characteristics, classify each passenger based on the population distribution characteristics, divide the passenger group into multiple subgroups based on the classification results, and determine the target population attraction value of each spatial unit.

[0159] Step S203: Based on the population distribution characteristics, the passenger group is divided into multiple subgroups, and the intimacy of each subgroup is quantified according to a preset social intimacy quantification table to determine the intimacy value of each subgroup.

[0160] It should be noted that the preset social intimacy quantification scale can be the MSIS scale, which is a psychological scale used to measure social intimacy. In this embodiment, intimacy values ​​can be randomly assigned based on the preset social intimacy quantification scale using a normal distribution.

[0161] It is understood that this embodiment can quantify intimacy using the MSIS scale. For example, through factor analysis, three factors were extracted: "family relationships," "friendship relationships," and "romantic relationships," for example:

[0162] (1) Based on data analysis, the mean intimacy of family groups was obtained as CGf~N (0.60, 0.272).

[0163] (2) The mean intimacy of the romantic group CGl~N (0.69, 0.212);

[0164] (3) The mean intimacy of the friend group CGm~N (0.52, 0.242).

[0165] It should be noted that this embodiment randomly assigns affinity values ​​between groups, based on a normal distribution, and considers the relationship characteristics of different groups when predicting population distribution, ensuring the accuracy and rationality of the prediction results. This process ensures that the system can adapt to real-time dynamic needs and adjust its layout in a timely manner.

[0166] Step S204: Determine the initial expected distance and initial position of each group member in the subgroup based on the intimacy value.

[0167] In some embodiments, the terminal device can randomly place a "leader" within each subgroup, and sequentially place the "leaders" of each subgroup into the spatial unit with the highest unoccupied basic attraction. Based on intimacy and combined with three different aggregation modes, the initial expected distance and initial position of other group members are determined. The aggregation modes include chain topology, ring topology, and fully connected topology. Chain topology indicates that group members move along a linear path, and their influence on each other is limited to adjacent members. Ring topology indicates that the connections between members form a closed loop, and the movement of the group tends to revolve around the centroid. Fully connected topology indicates that all members have direct influence on each other, exhibiting a high degree of synergy.

[0168] It should be noted that, in order to derive the expected distance between groups... With intimacy C The relationship function aims to establish a mathematical model that allows for the expression of intimacy as... C Changes in expected distance between groups It can exhibit the following characteristics:

[0169] (1) Non-linear relationship: As intimacy increases, the expected distance decreases rapidly.

[0170] (2) Boundary conditions: When the intimacy is close to 0 or 1, the rate of change of the expected distance slows down, reflecting the characteristics of high intimacy groups and low intimacy groups.

[0171] To achieve the above characteristics, the logistic function, i.e., the exponential decay function, is used. This function has the following form:

[0172]

[0173] in, The rate of change of the control function; It is the midpoint of intimacy, when The rate of change of the logistic function is greatest when . The characteristic of the logistic function is: when hour, when hour, By adjusting the parameters and It can make The changes are faster in the middle range, while the changes tend to be gentler at both ends, which meets the requirements for nonlinear relationships.

[0174] Expected distance As intimacy increases The changes, from Smooth transition to Therefore, by transforming the logistic function, such that when hour ,when hour, Therefore, the following relationship is constructed:

[0175]

[0176] Will Substituting into the above equation, we get:

[0177]

[0178] The final form of the formula is:

[0179]

[0180] The above formula describes intimacy. and group distance The relationship between them, and Let the logistic function represent the expected distance at the lowest and highest intimacy levels, respectively. Used to control the changing relationship between intimacy and desired distance;

[0181] when When the value is small, the logistic function value is close to 0, making .

[0182] when When the value is large, the logistic function value is close to 1, making .

[0183] parameter : Controls the rate of change of distance. Larger The value will make the expected distance The change is steeper and smaller in the middle region. The value will make the change more gradual.

[0184] parameter : Control the central location of change, that is, when At this point, the rate of change of the logistic function reaches its maximum.

[0185] Step S205: Based on the initial expected distance and the initial location, perform an attraction analysis on each group member to determine the target population attraction value of each spatial unit.

[0186] It's important to note that intimacy reflects the strength of social relationships between individuals, ranging from [0,1]. Higher intimacy indicates greater attraction. In this analogy, intimacy can be likened to the "mass" of an object. Therefore, higher intimacy leads to greater attraction, allowing us to construct an initial formula for crowd attraction:

[0187]

[0188] in, Indicating the attractiveness of primitive populations, Represents an individual With individuals The distance between them represents the initial idea that gravity decreases inversely with the square of the distance.

[0189] Furthermore, to improve the accuracy of the target audience attraction value calculation, step S205 above may include:

[0190] Step S2051: Based on the initial expected distance and the initial location, perform attraction analysis on each group member to determine the initial crowd attraction value between each group member;

[0191] Step S2052: Perform population aggregation analysis on each subgroup to determine the territory structure type of each subgroup;

[0192] Step S2053: Adjust the initial crowd attraction value based on the territory structure type to obtain the candidate group attraction value;

[0193] Step S2054: Couple the attractiveness values ​​of the candidate group to obtain the target population attractiveness value of each spatial unit.

[0194] It should be noted that in actual population distribution, the observed change in attractiveness with distance is not a simple inverse square relationship, but rather exhibits a non-linear trend. In particular, different types of groups reach a peak attractiveness at a specific distance, after which it gradually decreases with increasing distance. Therefore, a Gaussian decay function is used instead of the inverse square decay to better reflect the actual distribution of populations.

[0195] The initial formula for crowd attraction described above can be converted into a Gaussian decay function as follows:

[0196]

[0197] in, Represents an individual With individuals The initial crowd attraction value between them It represents the peak attractiveness of different subgroups. This represents the maximum attraction value between groups with different levels of intimacy. It is the expected distance. It is the standard deviation of the spatial distribution of attraction, used to control for deviation of attraction from distance. The decay rate, Represents an individual With individuals The formula for the Gaussian decay function above expresses the characteristic that the attraction reaches its peak at the desired distance and gradually decreases as the distance deviates from the ideal value, which is consistent with the distribution characteristics of different groups.

[0198] The aforementioned peak of attraction The peak attraction value represents the maximum attraction value between groups with different levels of intimacy. The non-linear dependence of distance indicates that the distance decay is controlled by a Gaussian function, so that the attraction reaches its peak at the desired distance and gradually decays when it deviates from the desired distance. The relationship between intimacy and desired distance indicates that the desired distance changes with intimacy and is controlled by a logistic function, which satisfies the need for high-intimacy groups to maintain a closer distance.

[0199] It should be noted that the territory structure types include chain structure, ring structure, and fully connected structure. The territory structure type can be the territory aggregation method of the subgroup. The chain structure mentioned above indicates that the group members move along a linear path and the influence between them is limited to adjacent members. The ring structure mentioned above indicates that the connection between members forms a closed loop, and the movement of the group tends to be around the center of mass. The fully connected structure mentioned above indicates that all members have direct influence on each other, showing a high degree of cooperation.

[0200] In the chain structure, there are Passenger_0 (leader), Passenger_1, and Passenger_2;

[0201] Among them, Passenger_0 is not affected by other passengers and is the starting point of the entire chain; Passenger_1 is directly affected by Passenger_0 and closely follows the behavior of Passenger_0; Passenger_2 is affected by Passenger_1, and Passenger_1 is affected by Passenger_0, so Passenger_2 is indirectly affected by Passenger_0.

[0202] This form can be extended to:

[0203]

[0204] Indicates passenger Influence The first passenger was a leader, forming a chain of influence.

[0205] In the ring structure, Passenger_0 affects Passenger_1; Passenger_1 affects Passenger_2; and Passenger_2 affects Passenger_0.

[0206] Because it is a circular structure, each passenger is both an influencer and a affected party, and the relationship is expressed by the following formula:

[0207]

[0208] In a fully linked structure, Passenger_0 affects Passenger_1 and Passenger_2; Passenger_1 affects Passenger_0 and Passenger_2; and Passenger_2 affects Passenger_0 and Passenger_1.

[0209] Each passenger directly affects all other passengers, forming a fully connected network:

[0210]

[0211] From the above, it can be seen that the attractiveness of a spatial unit within a group is often obtained by coupling the attractiveness of multiple people. Therefore, the following mathematical model for calculating the attractiveness value of a target group is proposed:

[0212]

[0213] in, Indicates the attractiveness value to the target audience. This indicates the attractiveness value of the candidate group. Represents an individual The weight of attraction to spatial units.

[0214] This embodiment identifies passenger groups within the target space through target detection, performs feature analysis on these passenger groups to obtain their distribution characteristics, divides them into multiple subgroups based on these characteristics, and quantifies the intimacy of each subgroup according to a preset social intimacy quantification table to determine their intimacy value. Based on these intimacy values, it determines the initial expected distance and initial position of each member within the subgroup, and performs attraction analysis on these initial expected distances and initial positions to determine the target crowd attraction value for each spatial unit. This embodiment, by quantifying the intimacy of the crowd and combining intimacy, distance, and position to calculate the target crowd attraction value for each spatial unit, accurately determines the attractiveness of each spatial unit to the crowd within the target space, thus improving prediction accuracy.

[0215] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing a dynamic prediction program for the location of people in a confined space. When the dynamic prediction program for the location of people in a confined space is executed by a processor, it implements the steps of the dynamic prediction method for the location of people in a confined space as described above.

[0216] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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 thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0217] The aforementioned computer-readable storage medium may be included in a device for dynamic prediction of the location of people in a confined space; or it may exist independently and not be assembled into a device for dynamic prediction of the location of people in a confined space.

[0218] Furthermore, this invention also proposes a computer program product, including a dynamic prediction program for the location of people in a confined space, which, when executed by a processor, implements the steps of the dynamic prediction method for the location of people in a confined space as described above.

[0219] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned method for dynamic prediction of the location of people in a confined space, and will not be described again here.

[0220] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the device for dynamic prediction of the location of people in a confined space according to the present invention.

[0221] like Figure 4 As shown, the enclosed space crowd location dynamic prediction device proposed in this embodiment of the invention includes:

[0222] The facility attractiveness analysis module 10 is used to divide the target space into multiple spatial units and determine the facility attractiveness value of each spatial unit based on the facility distribution information of the target space.

[0223] The crowd attraction analysis module 20 is used to divide the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and to determine the target crowd attraction value of each spatial unit.

[0224] The comprehensive attractiveness analysis module 30 is used to determine the comprehensive attractiveness value of each spatial unit based on the attractiveness value of the target population and the attractiveness value of the facility;

[0225] The crowd dynamic prediction module 40 is used to predict the dynamic distribution of the crowd in the target space based on the comprehensive attraction value, and obtain the crowd distribution prediction result. The crowd distribution prediction result is used to optimize the facility distribution structure and spatial distribution structure of the target space.

[0226] This embodiment divides the target space into multiple spatial units and determines the facility attractiveness value of each spatial unit based on the facility distribution information of the target space. It also divides the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space and determines the target crowd attractiveness value of each spatial unit. Finally, it determines the comprehensive attractiveness value of each spatial unit based on the target crowd attractiveness value and the facility attractiveness value, and predicts the dynamic distribution of the crowd in the target space based on the comprehensive attractiveness value. Because this embodiment analyzes the comprehensive attractiveness of each spatial unit within the enclosed space from multiple dimensions, it accurately predicts the dynamic distribution of the crowd within the enclosed space, achieving reasonable optimization of the space. This effectively optimizes passenger comfort in the enclosed space, significantly reduces spatial conflicts, and improves safety within the enclosed space.

[0227] The enclosed space crowd location dynamic prediction device provided in this application, employing the enclosed space crowd location dynamic prediction method in the above embodiments, can solve the technical problem of dynamic crowd location prediction in enclosed spaces. Compared with the prior art, the beneficial effects of the enclosed space crowd location dynamic prediction device provided in this application are the same as those of the enclosed space crowd location dynamic prediction method provided in the above embodiments, and other technical features in the enclosed space crowd location dynamic prediction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0228] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0229] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0230] In addition, for technical details not described in detail in this embodiment, please refer to the method for dynamic prediction of the location of people in a confined space provided in any embodiment of the present invention, which will not be repeated here.

[0231] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0232] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0233] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0234] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for dynamically predicting the location of people in a confined space, characterized in that, The method for dynamically predicting the location of people in a confined space includes: The target space is divided into multiple spatial units, and the facility attractiveness value of each spatial unit is determined based on the facility distribution information of the target space. Based on the population distribution characteristics of the passenger group in the target space, the passenger group is divided into multiple subgroups, and the target population attraction value of each spatial unit is determined. The overall attractiveness value of each spatial unit is determined based on the target population attractiveness value and the facility attractiveness value; Based on the comprehensive attractiveness value, the dynamic distribution of the population in the target space is predicted to obtain the population distribution prediction result. The population distribution prediction result is used to optimize the facility distribution structure and spatial distribution structure of the target space. The step of dividing the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and determining the target crowd attraction value of each spatial unit, includes: Target detection is performed on the target space to determine the passenger groups within the target space; Perform feature analysis on the passenger group to obtain the population distribution characteristics of the passenger group; Based on the population distribution characteristics, the passenger group is divided into multiple subgroups, and the intimacy of each subgroup is quantified according to a preset social intimacy quantification table to determine the intimacy value of each subgroup. The initial expected distance and initial position of each group member in the subgroup are determined based on the intimacy value; Based on the initial expected distance and the initial location, an attraction analysis is performed on each group member to determine the target population attraction value of each spatial unit.

2. The method for dynamic prediction of the location of people in a confined space as described in claim 1, characterized in that, The attractiveness analysis of each group member based on the initial expected distance and the initial location, to determine the target population attractiveness value of each spatial unit, includes: Based on the initial expected distance and the initial location, an attraction analysis is performed on each group member to determine the initial crowd attraction value between each group member: in, Represents an individual With individuals The initial crowd attraction value between them It represents the peak attractiveness of different subgroups. This represents the maximum attraction value between groups with different levels of intimacy. It is the expected distance. It is the standard deviation of the spatial distribution of attraction, used to control for deviation of attraction from distance. The decay rate, Represents an individual With individuals The distance between them; Group aggregation analysis is performed on each subgroup to determine the territory structure type of each subgroup. The territory structure types include chain structure, ring structure and fully connected structure. The initial population attraction value is adjusted based on the territory structure type to obtain the candidate population attraction value. The territory structure type is the way the subgroups gather in the territory. The territory structure type includes chain structure, ring structure and fully connected structure. The chain structure indicates that the group members move along a linear path. The ring structure indicates that the connection between members forms a closed loop. The fully connected structure indicates that all members have a direct influence on each other. By coupling the attractiveness values ​​of the candidate group, the target population attractiveness value of each spatial unit is obtained: in, Indicates the attractiveness value to the target audience. This indicates the attractiveness value of the candidate group. Represents an individual The weight of attraction to spatial units.

3. The method for dynamic prediction of the location of people in a confined space as described in claim 2, characterized in that, The determination of the overall attractiveness value of each spatial unit based on the target population attractiveness value and the facility attractiveness value includes: Generate the initial social force weights and initial environmental force weights for the target space; Based on the scenario requirement information of the target space, an adjustment factor is obtained, and the initial social force weight and the initial environmental force weight are adjusted based on the adjustment factor to obtain the target social force weight and the target environmental force weight. in, Indicates the target social influence weight. Indicates the target environmental force weights. Indicates the initial social power weight. Indicates the initial environmental force weights. Indicates the adjustment factor; Based on the target social influence weight and the target environmental influence weight, the attraction values ​​of the target population and the facility are aggregated to determine the comprehensive attraction value of each spatial unit: in, This represents the overall attractiveness score. Indicates the attractiveness value to the target audience. Indicates the attractiveness value of the facility; The attractiveness value of the facility is calculated using the following formula: in, For facilities The weight of the attraction of spatial units, As a proportional parameter for the attractiveness of facilities, Used to control the range of attraction decay, For shape parameters, Used to adjust the shape of the curve for attraction decay.

4. The method for dynamically predicting the location of people in a confined space as described in any one of claims 1 or 2, characterized in that, The prediction of dynamic population distribution in the target space based on the comprehensive attractiveness value includes: Determine the occupancy status of each spatial unit, and determine the free units within the spatial units based on the occupancy status; Monitor whether there are any idle units around the current unit where each group member is located that have a higher overall attraction value than the current unit; Based on the monitoring results and the comprehensive attraction value, the dynamic distribution of the population in the target space is predicted until the members of each group meet the preset steady-state conditions. The preset steady-state condition includes at least one of the following: The first steady-state condition includes: the positions of group members remain unchanged during the prediction period; The second steady-state condition includes: there are no idle units around the current unit where the group member is located that have a higher overall attraction value than the current unit; The third steady-state condition includes: the global attractiveness increment of the current unit in which the group members are located is lower than a preset threshold.

5. The method for dynamically predicting the location of people in a confined space as described in any one of claims 1 or 2, characterized in that, The prediction of dynamic population distribution in the target space based on the comprehensive attractiveness value includes: The target space is divided into multiple first-level grids based on the base grid; The primary grid is divided into multiple secondary grids according to a preset division scale; Calculate the Euclidean distance between each second-level grid and the population center of each subpopulation: in, Represents Euclidean distance. This represents the position index of the secondary grid in the target space. Representing the second-level grid Axis coordinates Representing the second-level grid Axis coordinates Represents the group center point of Axis coordinates Represents the group center point of Axis coordinates; Based on the Euclidean distance, each secondary grid is divided into regional grids to obtain regional grid division results. The regional grid division results include the territory division results of each subgroup and the potential conflict area division results. Calculate the conflict risk parameters between each subgroup based on the regional grid division results: in, Indicates the conflict risk parameter. and Representing groups and group For secondary grids The overall attractiveness value, Representing a group with the group The average distance between them It is a positive number. An indicator function representing the result of the region gridding, when the second-level grid... The indicator function is set to 1 when it is located in the overlapping area of ​​the territories of two subgroups; otherwise, the indicator function is set to 0. Based on the conflict risk parameters, the dynamic distribution of the population in the target space is predicted.

6. A device for dynamically predicting the location of people in a confined space, characterized in that, The enclosed space crowd location dynamic prediction device includes: The facility attractiveness analysis module is used to divide the target space into multiple spatial units and determine the facility attractiveness value of each spatial unit based on the facility distribution information of the target space. The crowd attraction analysis module is used to divide the passenger group into multiple subgroups based on the crowd distribution characteristics of the passenger group in the target space, and to determine the target crowd attraction value of each spatial unit. The comprehensive attractiveness analysis module is used to determine the comprehensive attractiveness value of each spatial unit based on the attractiveness value of the target population and the attractiveness value of the facility; The crowd dynamic prediction module is used to predict the dynamic distribution of the crowd in the target space based on the comprehensive attraction value, and to obtain the crowd distribution prediction result. The crowd distribution prediction result is used to optimize the facility distribution structure and spatial distribution structure of the target space. The crowd attraction analysis module is further configured to perform target detection in the target space to identify passenger groups within the target space; perform feature analysis on the passenger groups to obtain their distribution characteristics; divide the passenger groups into multiple subgroups based on the distribution characteristics, and quantify the intimacy of each subgroup according to a preset social intimacy quantification table to determine the intimacy value of each subgroup; determine the initial expected distance and initial position of each group member within the subgroup based on the intimacy value; and perform attraction analysis on each group member based on the initial expected distance and initial position to determine the target crowd attraction value for each spatial unit.

7. A device for dynamically predicting the location of people in a confined space, characterized in that, The enclosed space crowd location dynamic prediction device includes: a memory, a processor, and an enclosed space crowd location dynamic prediction program stored in the memory and executable on the processor, wherein the enclosed space crowd location dynamic prediction program is configured to implement the enclosed space crowd location dynamic prediction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a dynamic prediction program for the location of people in a confined space, which, when executed by a processor, implements the dynamic prediction method for the location of people in a confined space as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes a dynamic prediction program for the location of people in a confined space, which, when executed by a processor, implements the steps of the dynamic prediction method for the location of people in a confined space as described in any one of claims 1 to 5.

Images