People flow sudden increase area identification method and device and nonvolatile storage medium

Abstract

The invention discloses a method and a device for identifying a human flow sudden increase area and a nonvolatile storage medium. The method comprises the following steps: determining resident user number information and load information of a plurality of cells in a target area, and determining a target cell from the plurality of cells according to the resident user number information and the load information; according to the timing advance information of the target cell, determining a plurality of timing advance areas and target resident users in the target cell corresponding to the plurality of timing advance areas, the target resident users being resident users whose resident duration in the target cell exceeds a preset duration; and clustering the position information of the target resident users corresponding to the plurality of timing advance regions, and determining a people flow sudden increase region according to a clustering result. According to the method and the device, the technical problem that all possible people stream sudden increase areas cannot be accurately identified due to the fact that people stream conditions are determined only depending on video data in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of electronic digital data processing, and more specifically, to a method, apparatus, and non-volatile storage medium for identifying areas of sudden increase in pedestrian traffic. Background Technology

[0002] In related technologies, determining areas of sudden surges in pedestrian traffic typically relies solely on single data sources such as video footage. However, in areas with inadequate camera deployment and insufficient server resources, this method cannot accurately identify all possible areas of sudden surges in pedestrian traffic.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and non-volatile storage medium for identifying areas of sudden surge in pedestrian flow, in order to at least solve the technical problem that related technologies cannot accurately identify all possible areas of sudden surge in pedestrian flow due to relying solely on video data to determine pedestrian flow.

[0005] According to one aspect of the embodiments of this application, a method for identifying areas with sudden surges in pedestrian traffic is provided, comprising: determining the number of resident users and load information of multiple cells in a target area, and determining a target cell from the multiple cells based on the number of resident users and load information; determining multiple time advance areas based on the time advance information of the target cells, and target resident users in the target cells corresponding to the multiple time advance areas, wherein the target resident users are resident users whose resident time in the target cell exceeds a preset time; clustering the location information of the target resident users corresponding to the multiple time advance areas, and determining the areas with sudden surges in pedestrian traffic based on the clustering results.

[0006] Optionally, clustering the location information of target users corresponding to each advance-time zone includes: determining the target advance-time zone based on the number of target users corresponding to the advance-time zone, wherein the number of target users corresponding to the target advance-time zone is greater than a first preset threshold; clustering the location information of target users corresponding to each target advance-time zone to obtain multiple clusters, wherein each cluster includes the location information of multiple target users; determining the area of ​​sudden increase in pedestrian flow based on the clustering results includes: determining the polygonal region corresponding to the cluster based on the location information of multiple target users contained in the cluster, wherein the polygonal region covers the location information of all target users contained in the cluster; determining the number of cell identifiers covered by the polygonal region, and determining the polygonal region as a sudden increase in pedestrian flow if the number of cell identifiers exceeds a second preset threshold.

[0007] Optionally, determining the number of users residing in multiple cells within the target area includes: determining a first timestamp and a second timestamp corresponding to the user based on the user's communication behavior information within a preset time period, wherein the first timestamp indicates the moment when the user's terminal device first accesses the cell within the preset time period, and the second timestamp indicates the moment when the user's terminal device last leaves the cell, and if the user's terminal device does not leave the cell within the preset time period, the second timestamp indicates the end time of the preset time period; determining the difference between the second timestamp and the first timestamp to obtain the user's residence time; and determining users whose residence time exceeds the preset time period as valid residing users, wherein the number of residing users includes the number of valid residing users.

[0008] Optionally, determining the target cell from multiple cells based on the number of resident users and load information includes: determining the load information of the cell within a preset time period, wherein the load information includes the load rate of the cell within the preset time period and the increase in load rate relative to a baseline preset time period, the baseline preset time period being the time period preceding the preset time period; determining the cell as a candidate target cell within the preset time period if the number of effective users in the cell within the preset time period is greater than a first preset user number threshold or a second preset user number threshold, and the load rate is greater than a preset load rate threshold, and the increase in load rate is greater than a preset increase threshold, wherein the first preset user number threshold is determined based on the historical number of effective users in the cell; and determining the cell that has been rated as a candidate target cell within a consecutive preset number of preset time periods as the target cell.

[0009] Optionally, determining multiple advance timing areas based on the advance timing information of the target cell includes: determining the effective coverage area of ​​the target cell based on the advance timing information of the target cell, wherein the ratio of the number of resident users covered by the effective coverage area of ​​the target cell to the total number of resident users covered by the target cell is greater than a preset threshold; determining multiple advance timing areas within the effective coverage area, wherein the advance timing duration corresponding to each user in the same advance timing area is within the same preset value range.

[0010] Optionally, determining the target users in the target cells corresponding to the multiple time advance areas based on the time advance information of the target cell includes: determining the time advance duration distribution of the target users based on the time advance information; determining the probability that the target users are assigned to each time advance area based on the time advance duration distribution; and determining the time advance area corresponding to the target users based on the probability.

[0011] Optionally, before clustering the location information of the target users corresponding to each advance timing area, the method further includes: determining the location information of the center point of the advance timing area; and determining the location information of the target users based on the location information of the center point.

[0012] According to another aspect of the embodiments of this application, a device for identifying areas of sudden increase in pedestrian flow is also provided, comprising: a first processing module, configured to determine the number of resident users and load information of each plurality of cells in a target area, and to determine a target cell from the plurality of cells based on the number of resident users and load information; a second processing module, configured to determine a plurality of advance timing areas based on the advance timing information of the target cell, and target resident users in the target cells corresponding to each plurality of advance timing areas, wherein the target resident users are resident users whose residence time in the target cell exceeds a preset duration; and a third processing module, configured to cluster the location information of the target resident users corresponding to each plurality of advance timing areas, and to determine the areas of sudden increase in pedestrian flow based on the clustering results.

[0013] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, wherein the program controls the device where the non-volatile storage medium is located to execute a method for identifying areas of sudden increase in pedestrian flow when it is running.

[0014] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes a method for identifying areas of sudden increase in pedestrian flow when it runs.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements a method for identifying areas of sudden increase in pedestrian flow.

[0016] In this embodiment, the method involves determining the number of users and load information of multiple cells in the target area, and then identifying the target cell from among the multiple cells based on the number of users and load information. Multiple advance timing areas are determined based on the advance timing information of the target cell, and the target users in the target cells corresponding to each of the multiple advance timing areas are identified. The target users are those whose dwell time in the target cell exceeds a preset duration. The location information of the target users corresponding to the multiple advance timing areas is clustered, and the surge areas are determined based on the clustering results. By considering the user and load information of each cell in the target area to determine the target cell, and further clustering the users in the target cell to determine possible surge areas, this method achieves the goal of identifying surge areas without requiring video data. This improves the accuracy of identifying surge areas and solves the technical problem in related technologies where relying solely on video data to determine pedestrian flow results in the inability to accurately identify all possible surge areas. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a schematic diagram of the structure of a computer terminal (mobile device) according to an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a method for identifying areas of sudden increase in pedestrian flow according to an embodiment of this application;

[0020] Figure 3 This is a flowchart illustrating a process for identifying areas experiencing a sudden surge in pedestrian traffic, according to an embodiment of this application.

[0021] Figure 4 This is a schematic diagram of a device for identifying areas of sudden increase in pedestrian flow, provided according to an embodiment of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application are explained below:

[0025] Deep Packet Inspection (DPI) is a network packet inspection technology that allows network devices to examine the content of passing data packets, including the header and payload. DPI technology can identify specific applications, services, and protocols, enabling functions such as flow control, security monitoring, and bandwidth management. It is crucial in network security, traffic analysis, and network management.

[0026] Timing Advance (TA) is a parameter in mobile communication technology, especially in wireless communication systems such as GSM and UMTS. TA is used to adjust the timing of signal transmission by mobile terminals (such as mobile phones) to ensure synchronization with the base station. Because the distance between the mobile terminal and the base station varies, the signal propagation time will also differ, thus requiring TA adjustment to compensate for this delay.

[0027] E-UTRAN Cell Identity (ECI): A unique identifier defined by 3GPP (3rd Generation Partnership Project) to identify each cell in an LTE (Long Term Evolution) network. ECI is a 24-bit number used to uniquely identify a cell within the network for network management, scheduling, and identification.

[0028] NR Cell Identity (NCI): Composed of gNB ID and Cell ID, used to identify 5G cells. In this application embodiment, LTE / NR cell identity will be referred to as ECI.

[0029] Physical Resource Block (PRB): This is the basic unit used for allocating radio resources in LTE and NR networks. A PRB consists of a series of consecutive subcarriers used to carry user data. PRB utilization refers to the proportion of PRBs used for transmitting user data within a given time period, out of the total available PRBs. It is an important indicator for measuring cell load and network performance.

[0030] PRB: Radio Resource Physical Resource Block. PRB utilization is usually used to represent the load status of a cell.

[0031] GIS Map: A GIS map is a map created using Geographic Information System (GIS) technology. GIS is a computer system used to capture, store, analyze, and display geospatial data. GIS maps can provide rich geographic information, such as topography, roads, and buildings, and support geographic data analysis and decision support. GIS maps have wide applications in urban planning, environmental monitoring, resource management, and other fields.

[0032] With the rapid development of mobile communication technology and the widespread adoption of smart terminals, the network load changes and potential security issues caused by large crowds are becoming increasingly prominent. Current crowd monitoring methods often rely on a single data source, such as judging crowd flow solely through video data, which suffers from inadequate camera deployment and requires significant investment in processing servers. Furthermore, for fast-moving scenarios like high-speed rail and urban rail transit, existing base station connections cannot effectively filter out instantaneous connections, leading to data redundancy and analytical bias. In addition, clustering algorithms in related technologies struggle to accurately identify small-scale crowd gathering areas when processing geospatial data, and their low computational efficiency fails to meet real-time early warning requirements. Therefore, there is an urgent need for a technical solution that can integrate multi-source data, accurately identify, and quickly provide early warnings of sudden surges in crowd flow.

[0033] To address the aforementioned issues, this application provides relevant solutions, which are detailed below.

[0034] According to an embodiment of this application, a method embodiment for identifying areas of sudden increase in pedestrian flow is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1A hardware block diagram of a computer terminal (or mobile device) for implementing a method to identify areas of sudden increase in pedestrian traffic is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the pedestrian surge area identification method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned pedestrian surge area identification method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the aforementioned operating environment, this application provides a method for identifying areas of sudden surge in pedestrian traffic, such as... Figure 2 As shown, the method includes the following steps:

[0041] Step S202: Determine the number of users and load information of multiple cells in the target area, and determine the target cell from the multiple cells based on the number of users and load information;

[0042] In the technical solution provided in step S202, the step of determining the number of users residing in multiple cells in the target area includes: determining a first timestamp and a second timestamp corresponding to the user based on the user's communication behavior information within a preset time period, wherein the first timestamp is used to indicate the moment when the user's terminal device first accesses the cell within the preset time period, and the second timestamp is used to indicate the moment when the user's terminal device last leaves the cell, and if the user's terminal device does not leave the cell within the preset time period, the second timestamp is used to indicate the end time of the preset time period; determining the difference between the second timestamp and the first timestamp to obtain the user's residence time; determining users whose residence time exceeds the preset time period as valid residing users, wherein the number of residing users includes the number of valid residing users.

[0043] In some embodiments of this application, the step of determining a target cell from multiple cells based on the number of resident users and load information includes: determining the load information of the cell in a preset time period, wherein the load information includes the load rate of the cell in the preset time period and the load rate increase relative to a baseline preset time period, the baseline preset time period being the time period prior to the preset time period; determining the cell as a candidate target cell in the preset time period if the number of effective users of the cell in the preset time period is greater than a first preset user number threshold or a second preset user number threshold, and the load rate is greater than a preset load rate threshold, and the load rate increase is greater than a preset increase threshold, wherein the first preset user number threshold is determined based on the historical number of effective users of the cell; and determining the cell that has been rated as a candidate target cell in a consecutive preset number of preset time periods as the target cell.

[0044] In some embodiments of this application, heterogeneous data from multiple sources, such as user DPI (Deep Packet Inspection) data, cell TA (Time Lead) time-series data, and cell PRB utilization data, from multiple cells in the target area can be integrated first. Data cleaning algorithms are then used to remove outliers (such as abnormally high TA values) and duplicates. Furthermore, standardization processes are applied to unify data of different formats and sampling frequencies into an analyzable format, providing a high-quality data source for subsequent processing.

[0045] In some embodiments of this application, cell handover occurs when users move within a small area at the cell edge or when the signal is unstable, but the actual user gathering area does not change significantly. Therefore, the user's dwell time can be calculated using the initial access time and the final departure time. The specific formula for calculating the user's dwell time is as follows:

[0046] T_{staytime}=Min(T_{end},T_{last})-T_{first}

[0047] Where T_{staytime} is the user's stay time, T_{first} is the user's first access timestamp within a preset time period (e.g., 15 minutes), T_{last} is the user's last departure timestamp within the period, and T_{end} is the period end timestamp (this is the endpoint if the user has not left the cell). By setting a baseline value for user stay time, users whose stay time reaches or exceeds the baseline value are marked as valid clustered users. If the overall user stay time in a cell is lower than the baseline value, the cell is determined to be a transient scenario cell (e.g., a cell along a high-speed rail line, rail transit line, or highway), and its related data is removed to reduce interference from invalid data.

[0048] In some embodiments of this application, after determining the effective number of resident users in each cell, a joint criterion can be established from two dimensions: the number of resident users and the PRB load. The target cell can then be determined based on this joint criterion and multi-dimensional threshold conditions. Optionally, the multi-dimensional threshold conditions include a user number mutation criterion and a PRB load criterion. The user number mutation criterion is Max(average of the previous 15 days × 2, second preset user number threshold); the PRB load must satisfy (current PRB ≥ preset load rate threshold) ∪ (PRB increase ≥ preset increase threshold). Only cells that simultaneously meet these two conditions are initially identified as potentially experiencing a sudden increase in population. This multi-dimensional comprehensive judgment can significantly improve the identification accuracy.

[0049] The aforementioned average for the same period over the previous 15 days refers to the average number of active users at the corresponding time point within the 15 days preceding the current moment. For example, if the current time falls within the period of 10:00 AM to 10:30 AM, then the average for the same period over the previous 15 days is the average number of active users at the corresponding time point each day within those 15 days. It should be noted that the 15 days and the multiplier of 2 are for illustrative purposes only and do not represent a limitation of this application. The average for the same period over the previous 15 days multiplied by 2 is the aforementioned first preset user number threshold. The specific values ​​of the aforementioned preset load rate threshold and preset increase threshold can be set independently; for example, the preset load rate threshold can be set to 70%, and the preset increase threshold can be set to 30%.

[0050] In some embodiments of this application, the aforementioned PRB load refers to the average load rate of the cell during a preset time period, or the minimum load rate or the maximum load rate. The PRB increase can be an increase in the average load rate, or the minimum load rate or the maximum load rate. Furthermore, when the PRB load is the average load rate, the PRB increase is the increase in the average load rate. When the PRB load is the minimum load rate, the PRB increase is the increase in the minimum load rate. When the PRB load is the maximum load rate, the PRB increase is the increase in the maximum load rate.

[0051] In some embodiments of this application, a sliding window verification method can also be used. When the cell to be judged meets the multi-dimensional threshold judgment condition for N or more consecutive periods, the early warning process is triggered, and the cell is identified as the target cell. This mechanism effectively avoids false alarms caused by instantaneous network fluctuations, occasional data anomalies, etc., ensuring the accuracy and reliability of the early warning results. The preset number can be set by the user, for example, 2. N is the number of periods in which the cell to be judged continuously meets the above multi-dimensional threshold judgment condition. That is, the cell to be judged meets the above multi-dimensional threshold judgment condition in each of the N consecutive periods.

[0052] Step S204: Based on the timing advance information of the target cell, determine multiple timing advance areas and target users in the target cell corresponding to the multiple timing advance areas. The target users are users whose dwell time in the target cell exceeds a preset time.

[0053] In the technical solution provided in step S204, the step of determining multiple timing advance areas based on the timing advance information of the target cell includes: determining the effective coverage area of ​​the target cell based on the timing advance information of the target cell, wherein the ratio of the number of users covered by the effective coverage area of ​​the target cell to the total number of users covered by the target cell is greater than a preset threshold; determining multiple timing advance areas within the effective coverage area, wherein the timing advance duration corresponding to each user in the same timing advance area is within the same preset value range.

[0054] In some embodiments of this application, the step of determining the target users in the target cells corresponding to multiple timing advance areas based on the timing advance information of the target cell includes: determining the timing advance duration distribution of the target users based on the timing advance information; determining the probability that the target users are assigned to each timing advance area based on the timing advance duration distribution; and determining the timing advance area corresponding to the target users based on the probability.

[0055] Step S206: Cluster the location information of target users corresponding to multiple timed advance areas, and determine the areas of sudden increase in people flow based on the clustering results.

[0056] The aforementioned areas experiencing a surge in pedestrian traffic refer to regions where pedestrian density suddenly increases compared to historical times. For example, if the pedestrian traffic in a certain area increases significantly compared to the previous day, then that area can be considered an area experiencing a surge in pedestrian traffic.

[0057] In the technical solution provided in step S206, before clustering the location information of the target resident users corresponding to each timing advance area, the method further includes: determining the center point location information of the timing advance area; and based on the center point location information and the timing advance area corresponding to the target resident user.

[0058] In the technical solution provided in step S206, before clustering the location information of the target users corresponding to each timing advance area, the method further includes: determining the location information of the center point of the timing advance area; and determining the location information of the target users based on the location information of the center point.

[0059] In some embodiments of this application, the step of clustering the location information of target users corresponding to each advance timing area includes: determining a target advance timing area based on the number of target users corresponding to the advance timing area, wherein the number of target users corresponding to the target advance timing area is greater than a first preset number threshold; clustering the location information of target users corresponding to each target advance timing area to obtain multiple clusters, wherein each cluster includes the location information of multiple target users; determining a surge area based on the clustering results includes: determining a polygonal region corresponding to the cluster based on the location information of multiple target users contained in the cluster, wherein the polygonal region covers the location information of all target users contained in the cluster; determining the number of cell identifiers covered by the polygonal region, and determining the polygonal region as a surge area if the number of cell identifiers exceeds a second preset number threshold.

[0060] In some embodiments of this application, the cell types include outdoor cells and indoor distributed antenna system (DAS) cells. For outdoor cells, based on the cumulative distribution of TA (Transportation Aspect Ratio) proportions, a cell is considered to have effective coverage when it contains 90% of the users. Different TA unit distances correspond to different subcarrier intervals within the cell, as detailed below:

[0061]

[0062] The table above shows the TAL values ​​for different subcarriers.

[0063] When the cumulative distribution of TA reaches or exceeds 90%, the cell coverage distance D can be calculated using the following formula.

[0064]

[0065] Where P(TA) represents the percentage of users for each TA value, d represents the coverage distance, and TAL is determined according to the subcarrier spacing configuration.

[0066] For indoor distributed antenna systems (DAS) cells, due to factors such as the complexity of the devices and the influence of repeaters, the TA value cannot accurately reflect the actual coverage area. Therefore, a fixed radius (such as 50 meters or other preset values) is used for modeling.

[0067] In some embodiments of this application, after determining the effective coverage area of ​​a cell, an effective TA area (i.e., the target timing advance area) can be determined within the effective coverage area. Optionally, based on the relationship that "the longer a user stays in a certain place, the greater the proportion of user TA sampling points and intervals," the effective clustered users of the outdoor cell can be discretized into various TA areas according to a proportional relationship. When the number of effective clustered users in an area is greater than or equal to a preset number (such as 100 people or other custom values), the interval is identified as an effective user cluster area, and the cluster area number uses the cell ECI_TA value. The phrase "the longer a user stays in a certain place, the greater the proportion of user TA sampling points and intervals" refers to determining the probability of a user being in each TA area based on the distribution of the user's TA within a preset time period. For example, if a user's TA is within the first TA value range for 3 / 5 of the preset time period, and their TA is within the second TA value range for the remaining time, then the probability of the user belonging to the TA area corresponding to the first TA value range is 0.6, and the probability of belonging to the TA area corresponding to the second TA value range is 0.4.

[0068] In some embodiments of this application, the latitude and longitude information of the center point of each TA area in the cell can be calculated in the following way: the distance d calculated by the known antenna latitude and longitude, antenna azimuth angle, and time advance is finally calculated to obtain the center point position.

[0069] Alternatively, the latitude and longitude information of the center point of each TA area in the outdoor community can be determined using the following methods:

[0070] Based on the antenna's latitude, longitude, azimuth, and TA coverage area, the TA value is divided into multiple value intervals, such as (TA0, TA2), (TA2, TA4), (TA4, TA6)..., each interval corresponding to a TA region. The distance d from the center point of each region to the antenna corresponds to the values ​​of TA1, TA3, TA5, TA7..., respectively. The latitude and longitude of the center point are calculated using the following formula:

[0071] long2=long1+d×sin(a) / R×cos(lat1)×2π / 360

[0072] lat2=lat1+d×cos(a) / (R×2π / 360)

[0073] Where long2 is the longitude of the center point, lat2 is the latitude of the center point, the average radius of the Earth is R = 6371.393 × 1000 meters, long1 is the longitude of the antenna, lat1 is the latitude of the antenna, a is the azimuth of the antenna (which needs to be converted to radians), and d is the distance from the center point to the antenna, the maximum distance of which is less than the effective coverage distance of the cell D.

[0074] All effective users residing in the indoor distributed antenna system (DAS) are concentrated within a preset radius (e.g., 50 meters), with the center latitude and longitude being the latitude and longitude of the equipment installation location.

[0075] In some embodiments of this application, the location of valid resident users can be estimated in the following manner, thereby clustering the user location information:

[0076] Calculating the center point of the TA interval: First, the center point's latitude and longitude are calculated using the base station's antenna latitude and longitude, the coverage distance corresponding to the TA value, and the antenna's azimuth. The center point can also serve as an approximate estimate of the user's location.

[0077] User location estimation: The specific location of users within the same TA interval can be further estimated in various ways, such as:

[0078] Random distribution model: Assuming users are uniformly distributed within the circular coverage area of ​​the TA interval, a point within this area can be randomly selected as the estimated location of the user. This eliminates the need for further estimation of the user's specific location within the interval.

[0079] Heatmap model: Generates a user heatmap based on historical data, analyzes which locations within the TA range have a higher frequency of user appearance, and uses this to estimate the user's possible location.

[0080] In some embodiments of this application, the TA value of an urban base station cell is typically 2, and the radius of its coverage area is typically around 240 meters. TA(0-1) and TA(1-2) can be divided into two center point regions, and the latitude and longitude of the center points of the two center point regions can be calculated using the aforementioned center point calculation formula. When estimating the number of users within each center point region, the following calculation method can be used: the number of users equals the ratio of the sampled value of each TA interval to the total number of sampled points in the cell multiplied by the number of users residing in the cell.

[0081] Combining with other data sources: The location of users within the same TA range can be further refined by combining other data sources (such as the user's rough GPS location at a specific time, movement trajectory, etc.).

[0082] In some embodiments of this application, after obtaining the estimated user location information, the DBSCAN algorithm can be used to cluster the location information of each target resident user in the target timing advance area, including the following process:

[0083] 1) Core Object Definition: The minimum number of sampling points required for a core object is set to MinPoints≥3. That is, if a point has at least 3 sample points in its neighborhood, then that point is considered a core object. Here, both sampling points and data points refer to the target resident users.

[0084] 2) Neighborhood radius setting: Define the neighborhood radius R = 400 meters to determine the neighborhood range of the sample point. The neighborhood radius R can also be customized to other values. It should be noted that the neighborhood radius can be set according to actual needs.

[0085] 3) Algorithm Implementation: First, iterate through all data points in the target timing advance area. For each point, calculate the number of sample points in its ε (i.e., neighborhood radius R) neighborhood. If the number is greater than or equal to MinPoints, mark the point as a core object and add all points in its neighborhood to the current cluster. Then, for each non-core object point in the cluster, check if a core object exists in its neighborhood. If so, add the point to the cluster and continue checking other points in its neighborhood. Repeat this process until no more points can be added to the cluster, thus completing the generation of one cluster. Repeat the above steps until all core objects have been processed, finally outputting the geographic boundary polygon of the aggregated area.

[0086] As an optional implementation, the aggregated regional geographic boundary polygon includes multiple polygons determined by clusters obtained from clustering. When determining polygons based on clusters, the polygons can be determined based on the location information of each data point in the cluster (i.e., the location information of the target resident users). This application does not limit the method for determining the polygons, as long as the finally determined polygons cover the locations of all target resident users in the cluster. The boundary location information of each polygon can then be determined in the GIS map, ultimately obtaining the aggregated regional geographic boundary polygon.

[0087] As an optional implementation, after the polygon is determined, it can be further filtered. The boundary location information of the polygon will only be determined in the GIS map if the number of included cell ECIs is greater than a preset threshold. The preset threshold can be set by the user, for example, to 3.

[0088] In some embodiments of this application, to avoid misidentifying long-term densely populated areas as areas experiencing sudden increases in population, a 7-day sliding window can be established to monitor the cells within the aggregation area. If more than 50% of the cells within the aggregation area meet the multi-dimensional threshold judgment criteria for 3 out of 7 consecutive days, the aggregation area is determined to be a long-term densely populated area and excluded from the warning results, thus avoiding misjudgment of sudden increases in population. It should be noted that the specific number of days mentioned above are for illustrative purposes only and do not represent a limitation of this application.

[0089] In some embodiments of this application, it can also interface with a high-precision electronic map database. Within the identified areas of high pedestrian traffic, spatial retrieval and matching algorithms can be used to find landmark buildings or typical scene names, generate and output warning information containing specific location information, such as "A sudden increase in pedestrian traffic has occurred near [landmark building / scene name], involving the community [Community ECI List], please pay attention in time".

[0090] In some embodiments of this application, a method such as... is also provided. Figure 3 The process for identifying areas with sudden surges in pedestrian traffic, as shown, includes the following steps:

[0091] Step S302, Data Acquisition and Preprocessing;

[0092] User DPI data, cell TA time-series data, and PRB utilization data are collected periodically at 15-minute intervals using base station equipment and core network data acquisition systems in the communication network. Then, a data cleaning script is used to remove outlier data. Finally, a data standardization library is used to convert data of different formats into a unified format before storing it in the database.

[0093] Step S304, Dwell time calculation and scene filtering;

[0094] The system reads user access and departure time data for each cell within a 15-minute period from the database and calculates the dwell time for each user based on the dwell time calculation formula. A reasonable baseline dwell time value is set, such as 6 minutes, and user dwell time data from cells with values ​​below the baseline value are removed.

[0095] Step S306, Multidimensional threshold determination;

[0096] The system retrieves data on the number of active users and PRB utilization rate from the database for the same period 15 days prior, and compares this data with the current period's data. When a cell simultaneously meets the user count and PRB load threshold conditions, it is marked as a cell suspected of experiencing a sudden surge in population.

[0097] Step S308, Continuous verification;

[0098] For areas marked as suspected of experiencing a sudden surge in pedestrian traffic, a sliding window is used for inspection. The window size is set to two 15-minute cycles. If the multidimensional threshold judgment conditions are met for two consecutive cycles, the area is determined to be a real area with a sudden surge in pedestrian traffic.

[0099] Step S310: Calculate the effective coverage distance of the cell;

[0100] For outdoor cells, the TA value distribution data is read, and the coverage distance is calculated according to the cumulative distribution rules of TA proportion. When it reaches 90%, the coverage distance is calculated in combination with the subcarrier spacing correspondence. For indoor distributed antenna systems (DAS) cells, a fixed radius of 50 meters is directly used for modeling, and the calculation results are stored in the database.

[0101] Step S312, User distribution calculation;

[0102] Retrieve valid aggregated user data and antenna parameter data from the database, discretize users into TA areas proportionally, determine the number of users in each area, calculate the center latitude and longitude of areas that meet the conditions, and then store the results in the database.

[0103] Step S314: Cluster the users in the effective user cluster area;

[0104] Read the latitude and longitude data of the center of the valid user gathering area from the database, and use the DBSCAN algorithm module in the scikit-learn library of Python, set MinPoints=3 and ε=500 meters, to perform clustering operation and obtain the polygon of the human gathering area.

[0105] Step S316, long-term hotspot filtering;

[0106] A 7-day sliding window is established to count the number of communities within the aggregation area that meet the sudden increase criteria each day. If the proportion of communities meeting the criteria exceeds 50% for 3 out of 7 consecutive days, the aggregation area is removed from the warning results.

[0107] Step S318, early warning output;

[0108] Input the polygonal boundary information of the remaining areas where people gather into the GIS intelligent labeling system. The system then calls the high-precision map database, uses spatial retrieval algorithms to match the names of landmark buildings or scenes, generates early warning information, and pushes it to network maintenance personnel.

[0109] It should be noted that the specific figures mentioned in the above process are for illustrative purposes only and do not represent any limitation on the solution provided in this application.

[0110] By employing methods such as determining the number of users and load information of multiple cells in a target area, and identifying the target cell from these cells based on this information; determining multiple advance timing areas based on the advance timing information of the target cell, and identifying the target users in the target cells corresponding to each advance timing area (where target users are those whose dwell time in the target cell exceeds a preset duration); and clustering the location information of the target users corresponding to the multiple advance timing areas, the method achieves the goal of identifying areas of sudden surge in pedestrian flow without the need for video data. This improves the accuracy of identifying areas of sudden surge in pedestrian flow and solves the technical problem of failing to accurately identify all possible areas of sudden surge in pedestrian flow caused by relying solely on video data to determine pedestrian flow in related technologies.

[0111] This application provides a device for identifying areas with sudden increases in pedestrian traffic. Figure 4 This is a schematic diagram of the device. From Figure 4 As can be seen from the diagram, the device includes: a first processing module 40, used to determine the number of users and load information of each of the multiple cells in the target area, and to determine the target cell from the multiple cells based on the number of users and load information; a second processing module 42, used to determine multiple time advance areas based on the time advance information of the target cell, and the target users in the target cells corresponding to each of the multiple time advance areas, wherein the target users are users whose dwell time in the target cell exceeds a preset time; and a third processing module 44, used to cluster the location information of the target users corresponding to each of the multiple time advance areas, and to determine the areas of sudden increase in population based on the clustering results.

[0112] In some embodiments of this application, the step of the first processing module 40 in determining the number of users residing in multiple cells in the target area includes: determining a first timestamp and a second timestamp corresponding to the user based on the user's communication behavior information within a preset time period, wherein the first timestamp is used to indicate the moment when the user's terminal device first accesses the cell within the preset time period, the second timestamp is used to indicate the moment when the user's terminal device last leaves the cell, and if the user's terminal device does not leave the cell within the preset time period, the second timestamp is used to indicate the end time of the preset time period; determining the difference between the second timestamp and the first timestamp to obtain the user's residence time; determining users whose residence time exceeds the preset time period as valid residing users, wherein the number of residing users includes the number of valid residing users.

[0113] In some embodiments of this application, the step of the first processing module 40 determining a target cell from multiple cells based on the number of resident users and load information includes: determining the load information of the cell in a preset time period, wherein the load information includes the load rate of the cell in the preset time period and the load rate increase relative to a baseline preset time period, the baseline preset time period being the time period prior to the preset time period; determining the cell as a candidate target cell in the preset time period if the number of effective users of the cell in the preset time period is greater than a first preset user number threshold or a second preset user number threshold, and the load rate is greater than a preset load rate threshold, and the load rate increase is greater than a preset increase threshold, wherein the first preset user number threshold is determined based on the historical number of effective users of the cell; and determining the cell that has been rated as a candidate target cell in a consecutive preset number of preset time periods as the target cell.

[0114] In some embodiments of this application, the step of the second processing module 42 determining multiple timing advance areas based on the timing advance information of the target cell includes: determining the effective coverage area of ​​the target cell based on the timing advance information of the target cell, wherein the ratio of the number of resident users covered by the effective coverage area of ​​the target cell to the total number of resident users covered by the target cell is greater than a preset threshold; determining multiple timing advance areas within the effective coverage area, wherein the timing advance duration corresponding to each user in the same timing advance area is within the same preset value range.

[0115] In some embodiments of this application, the step of the second processing module 42 in determining the target users in the target cells corresponding to multiple timing advance areas based on the timing advance information of the target cell includes: determining the timing advance duration distribution of the target users based on the timing advance information; determining the probability that the target users are assigned to each timing advance area based on the timing advance duration distribution; and determining the timing advance area corresponding to the target users based on the probability.

[0116] In some embodiments of this application, before clustering the location information of the target users corresponding to each advance timing area, the third processing module 44 is used to: determine the location information of the center point of the advance timing area; and determine the location information of the target users based on the center point location information.

[0117] In some embodiments of this application, the step of the third processing module 44 clustering the location information of target users corresponding to each advance timing area includes: determining the target advance timing area based on the number of target users corresponding to the advance timing area, wherein the number of target users corresponding to the target advance timing area is greater than a first preset number threshold; clustering the location information of target users corresponding to each target advance timing area to obtain multiple clusters, wherein each cluster includes the location information of multiple target users; the step of the third processing module 44 determining the area of ​​sudden increase in pedestrian flow based on the clustering results includes: determining the polygonal area corresponding to the cluster based on the location information of multiple target users contained in the cluster, wherein the polygonal area covers the location information of all target users contained in the cluster; determining the number of cell identifiers covered by the polygonal area, and determining the polygonal area as a sudden increase in pedestrian flow if the number of cell identifiers exceeds a second preset number threshold.

[0118] It should be noted that each module in the above-mentioned pedestrian surge area identification device can be a program module (for example, a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0119] According to an embodiment of this application, a non-volatile storage medium is also provided, which stores a program. When the program runs, it controls the device containing the non-volatile storage medium to execute the following method for identifying areas experiencing sudden increases in pedestrian traffic: determining the number of users and load information of multiple cells in a target area, and determining a target cell from the multiple cells based on the number of users and load information; determining multiple time-advance regions based on the time advance information of the target cell, and target users in the target cells corresponding to the multiple time-advance regions, wherein the target users are users whose dwell time in the target cell exceeds a preset time; clustering the location information of the target users corresponding to the multiple time-advance regions, and determining the areas experiencing sudden increases in pedestrian traffic based on the clustering results.

[0120] According to an embodiment of this application, an electronic device is also provided, including a memory and a processor. The processor is used to run a program stored in the memory, wherein the program executes the following method for identifying areas with sudden surges in pedestrian flow: determining the number of users and load information of multiple cells in a target area, and determining a target cell from the multiple cells based on the number of users and load information; determining multiple advance timing areas and target users in the target cells corresponding to the multiple advance timing areas based on the advance timing information of the target cells, wherein the target users are users whose dwell time in the target cell exceeds a preset time; clustering the location information of the target users corresponding to the multiple advance timing areas, and determining the areas with sudden surges in pedestrian flow based on the clustering results.

[0121] According to an embodiment of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the following method for identifying areas of sudden surge in pedestrian traffic: determining the number of resident users and load information of multiple cells in a target area, and determining a target cell from the multiple cells based on the number of resident users and load information; determining multiple advance timing areas based on the advance timing information of the target cell, and target resident users in the target cells corresponding to the multiple advance timing areas, wherein the target resident users are resident users whose residence time in the target cell exceeds a preset time; clustering the location information of the target resident users corresponding to the multiple advance timing areas, and determining the areas of sudden surge in pedestrian traffic based on the clustering results.

[0122] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0124] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0126] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0127] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for identifying a human flow surge area, characterized in that, The method comprises: determining the number of users and load information of a plurality of cells in a target area, and determining a target cell from the plurality of cells according to the number of users and load information; determining a plurality of timing advance areas according to the timing advance information of the target cell, and target users in the target cell corresponding to the plurality of timing advance areas, wherein the target users are users who have stayed in the target cell for more than a preset time length; clustering the location information of the target users corresponding to the plurality of timing advance areas, and determining the crowd surge area according to the clustering result.

2. The crowd surge area identification method of claim 1, wherein: clustering the location information of the target users corresponding to each of the timing advance areas comprises: determining a target timing advance area according to the number of target users corresponding to the timing advance area, wherein the number of target users corresponding to the target timing advance area is greater than a first preset number threshold; and clustering the location information of the target users corresponding to each target timing advance area to obtain a plurality of clustering clusters, wherein each clustering cluster includes the location information of a plurality of target users; determining the crowd surge area according to the clustering result comprises: determining a polygonal area corresponding to the clustering cluster according to the location information of the plurality of target users included in the clustering cluster, wherein the polygonal area covers all the location information of the target users included in the clustering cluster; determining the number of cell identifiers covered by the polygonal area, and determining the polygonal area as the crowd surge area if the number of cell identifiers exceeds a second preset number threshold.

3. The method of claim 1, wherein, determining the number of users of a plurality of cells in a target area comprises: determining a first timestamp and a second timestamp corresponding to a user according to the communication behavior information of the user within a preset time period, wherein the first timestamp is used to indicate the time when the terminal device of the user accesses the cell for the first time within the preset time period, the second timestamp is used to indicate the time when the terminal device of the user last leaves the cell, and in the case that the terminal device of the user does not leave the cell within the preset time period, the second timestamp is used to indicate the termination time of the preset time period; determining the difference between the second timestamp and the first timestamp to obtain the residence time of the user; determining the user whose residence time exceeds the preset time length as an effective user, wherein the number of effective users is included in the number of users.

4. The method of claim 3, wherein, determining a target cell from the plurality of cells according to the number of users and load information comprises: determining the load information of the cell in the preset time period, wherein the load information includes the load rate of the cell in the preset time period, and the load rate increase relative to the reference preset time period, the reference preset time period being a time period before the preset time period; In a case where the effective user quantity of the cell in the preset time period is greater than a first preset user quantity threshold or a second preset user quantity threshold, the load rate is greater than a preset load rate threshold, and the load rate increment is greater than a preset increment threshold, the cell in the preset time period is determined as a candidate target cell, wherein the first preset user quantity threshold is determined according to a historical effective user quantity of the cell; The cell that is evaluated as a candidate target cell in a continuous preset number of preset time periods is determined as the target cell.

5. The method of claim 1, wherein, Determining a plurality of timing advance areas according to timing advance information of the target cell comprises: Determining an effective coverage range of the target cell according to the timing advance information of the target cell, wherein a ratio of a quantity of resident users covered by the effective coverage range of the target cell to a total quantity of resident users covered by the target cell is greater than a preset threshold; Determining a plurality of the timing advance areas in the effective coverage range, wherein a timing advance duration corresponding to each user in a same timing advance area is in a same preset value interval.

6. The method of claim 1, wherein, Determining target resident users in the target cell corresponding to the plurality of timing advance areas according to the timing advance information of the target cell comprises: Determining a timing advance duration distribution corresponding to the target resident users according to the timing advance information; Determining a probability of the target resident users being attributed to each of the timing advance areas according to the timing advance duration distribution; Determining the timing advance area corresponding to the target resident users according to the probability.

7. The method of claim 1, wherein, Before clustering position information of the target resident users corresponding to each of the timing advance areas, the method further comprises: Determining center point position information of the timing advance area; Determining the position information of the target resident users according to the center point position information.

8. A device for identifying a human flow surge area, characterized by, Comprise: A first processing module configured to determine resident user quantity information and load information of each of a plurality of cells in a target area, and determine a target cell from the plurality of cells according to the resident user quantity information and the load information; A second processing module configured to determine a plurality of timing advance areas according to timing advance information of the target cell, and target resident users in the target cell corresponding to each of the plurality of timing advance areas, wherein the target resident users are resident users with a resident duration in the target cell that exceeds a preset duration; A third processing module configured to cluster position information of the target resident users corresponding to each of the plurality of timing advance areas, and determine the human flow surge area according to a clustering result.

9. A non-volatile storage medium, comprising: The nonvolatile storage medium has a program stored therein, wherein the program controls a device in which the nonvolatile storage medium is located to perform the human flow surge area identification method in any one of claims 1 to 7 when the program is running.

10. An electronic device, comprising: Comprise: A memory and a processor, the processor is used to run a program stored in the memory, wherein the program performs the human flow surge area identification method in any one of claims 1 to 7 when the program is running. Comprise:

11. A computer program product, characterised in that, The computer program comprises a computer program which, when executed by a processor, implements the human flow surge area identification method according to any one of claims 1 to 7.

Images