Service area people flow density AI analysis and early warning method and system

Abstract

The invention provides a service area people flow density AI analysis and early warning method and system. The method comprises the following steps: preprocessing obtained service area monitoring personnel data and base station connection data to respectively obtain effective monitoring personnel data and effective connection data, and training an obtained personnel quantity evaluation model according to an effective connection data set to obtain effective personnel data of a base station after processing, according to the effective monitoring personnel data, the effective personnel data of the base station and a preset service area, processing to obtain people flow density data, and performing threshold comparison on the people flow density data to obtain an early warning level; therefore, the technology of improving the management level of the service area and guaranteeing the operation safety of the service area is realized by obtaining the effective monitoring personnel data and the effective connection data, calculating the effective personnel data and the people flow density data of the base station and dynamically evaluating the early warning level in combination with threshold comparison.

Description

Technical Field

[0001] This application relates to the field of service area management technology, and more specifically, to a method and system for AI analysis and early warning of pedestrian density in service areas. Background Technology

[0002] With the continuous improvement of my country's highway transportation network and the rapid growth of motor vehicle ownership, highway service areas, as key nodes in the transportation chain, are facing increasing pressure on their service capacity. Especially during peak travel periods such as the Spring Festival and National Day holidays, as well as during daily commuting peak hours, service areas often experience high concentrations of people, which not only leads to longer waiting times and a decline in service experience but also poses potential safety hazards, posing a severe challenge to the refined operation and management of service areas.

[0003] Existing methods for managing pedestrian density in service areas generally suffer from technical bottlenecks, making it difficult to meet actual operational needs. Firstly, data collection is limited to a single dimension. Most solutions rely solely on smart cameras for personnel counting, which is susceptible to factors such as lighting changes, pedestrian obstruction, and equipment malfunctions, resulting in low accuracy of pedestrian data and failing to provide a reliable basis for density calculation. While some solutions incorporate base station data, they fail to effectively filter fixed devices and short-lived devices connected to the base stations, leading to poor data validity. Secondly, density calculation models are static. Traditional methods often use a simple calculation of "total number of people in the area / area of ​​the area," failing to consider the different carrying capacity characteristics of different functional areas within the service area, nor the impact of pedestrian dwell time on real-time congestion, resulting in a disconnect between density assessment and actual needs.

[0004] Third, the early warning mechanism lacks foresight and flexibility. Existing early warning systems are mostly based on fixed density thresholds, which can only respond to existing congestion and cannot predict future trends in pedestrian flow, causing managers to miss opportunities for crowd control. At the same time, they do not consider the impact of differences in pedestrian flow structure on the early warning level, making the early warning strategy rigid and unable to cope with the safety management needs in complex scenarios.

[0005] Furthermore, existing systems have shortcomings in data fusion and collaborative application, failing to effectively integrate the advantages of monitoring personnel data and base station data. This results in low efficiency in service area pedestrian flow management, making it difficult to balance user experience and operational safety. Therefore, there is an urgent need for an AI-based analysis and early warning method for service area pedestrian flow density that can achieve accurate fusion of multi-source data, intelligent dynamic density calculation, forward-looking early warning, and personalized control, in order to improve the intelligence and precision of service area operation and management. Summary of the Invention

[0006] The purpose of this application is to provide a service area crowd density AI analysis and early warning method and system. It can improve the management level of service areas and ensure the safe operation of service areas by effectively monitoring personnel data and effective connection data, calculating effective personnel data and crowd density data of base stations, and combining threshold comparison to dynamically evaluate the early warning level.

[0007] This application also provides a method for AI analysis and early warning of pedestrian density in service areas, including the following steps:

[0008] Acquire service area monitoring personnel data and base station connection data;

[0009] Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data, respectively.

[0010] Historical base station connection data is acquired and a personnel quantity assessment model is trained. Based on the effective connection data, the personnel quantity assessment model is used to obtain the effective personnel data of the base station.

[0011] Comprehensive effective personnel data is obtained by processing effective monitoring personnel data and effective personnel data from base stations, and population density data is obtained by combining the data with the preset service area area.

[0012] The warning level is obtained by comparing the pedestrian density data with the preset warning assessment threshold.

[0013] Optionally, in the service area pedestrian density AI analysis and early warning method described in this application, the acquisition of service area monitoring personnel data and base station connection data specifically includes:

[0014] Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel;

[0015] Obtain base station connection data, including the total number of connected devices, fixed device data, and the dwell time data for each connected device.

[0016] Optionally, in the service area pedestrian density AI analysis and early warning method described in this application, the preprocessing of service area monitoring personnel data and base station connection data to obtain effective monitoring personnel data and effective connection data respectively includes:

[0017] The effective monitoring personnel data is obtained by subtracting the total number of monitoring personnel from the data on fixed personnel.

[0018] Subtract the fixed device data from the total number of connected devices to obtain the mobile device data;

[0019] The dwell time data corresponding to the mobile device is compared with the preset dwell state evaluation threshold to obtain valid connection data;

[0020] The preset dwell state evaluation thresholds include a first threshold and a second threshold, and the first threshold is greater than the second threshold;

[0021] If the dwell time data is greater than the second threshold and less than the first threshold, then the base station connection data corresponding to the device is valid connection data.

[0022] Optionally, in the service area pedestrian density AI analysis and early warning method described in this application, the step of acquiring historical base station connection data and training a personnel quantity assessment model, and processing the effective connection data through the personnel quantity assessment model to obtain effective personnel data for the base station, specifically includes:

[0023] Historical base station connection data is obtained and a personnel quantity assessment model is trained. The model includes the per capita device number coefficient and device active carrying rate obtained during training.

[0024] The effective connection data is input into the personnel quantity assessment model to obtain the effective personnel data of the base station.

[0025] Optionally, in the service area pedestrian density AI analysis and early warning method described in this application, the step of obtaining comprehensive effective personnel data by processing effective monitoring personnel data and base station effective personnel data, and combining it with the preset service area area to obtain pedestrian density data, specifically includes:

[0026] Comprehensive effective personnel data is obtained by weighted calculation based on effective monitoring personnel data and effective personnel data from base stations.

[0027] The population density data is obtained by dividing the total effective personnel data by the preset service area area.

[0028] Optionally, in the service area pedestrian density AI analysis and early warning method described in this application, the step of comparing pedestrian density data with a preset early warning assessment threshold to obtain an early warning level specifically includes:

[0029] The third and fourth thresholds are extracted based on the preset early warning assessment thresholds, and the third threshold is greater than the fourth threshold;

[0030] The warning level is obtained by comparing the crowd density data with the third and fourth thresholds, including normal level, first-level warning or second-level warning;

[0031] If the pedestrian density data is less than or equal to the fourth threshold, the warning level is normal and the service area is operating normally.

[0032] If the crowd density data is greater than the fourth threshold but less than the third threshold, the warning level is Level 1, the broadcast zone notification is activated, and staff are dispatched to guide the crowd on site.

[0033] If the pedestrian density data is greater than or equal to the third threshold, the warning level is level two. The warning level of the service area will be pushed to highway vehicles within a preset distance through the navigation app, and users' stopping intentions will be collected.

[0034] Optionally, it also includes:

[0035] Obtain age data of people staying in service areas, including the elderly, young and middle-aged adults, or children;

[0036] The total number of people in each age group was counted, and the proportion of young and middle-aged people was calculated.

[0037] The data on the proportion of young and middle-aged people is compared with the preset warning correction threshold to obtain the warning correction data;

[0038] If the percentage of young people is less than or equal to the preset warning correction threshold, the warning correction status data will be the start correction data, and the warning level will be automatically raised by one level.

[0039] If the proportion of young people exceeds the preset warning correction threshold, the warning correction status will be maintained.

[0040] Secondly, this application provides a service area pedestrian density AI analysis and early warning system, which includes: a memory and a processor. The memory includes a service area pedestrian density AI analysis and early warning method program. When the processor executes the service area pedestrian density AI analysis and early warning method program, it performs the following steps:

[0041] Acquire service area monitoring personnel data and base station connection data;

[0042] Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data, respectively.

[0043] Historical base station connection data is acquired and a personnel quantity assessment model is trained. Based on the effective connection data, the personnel quantity assessment model is used to obtain the effective personnel data of the base station.

[0044] Comprehensive effective personnel data is obtained by processing effective monitoring personnel data and effective personnel data from base stations, and population density data is obtained by combining the data with the preset service area area.

[0045] The warning level is obtained by comparing the pedestrian density data with the preset warning assessment threshold.

[0046] Optionally, in the service area pedestrian density AI analysis and early warning system described in this application, the acquisition of service area monitoring personnel data and base station connection data specifically includes:

[0047] Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel;

[0048] Obtain base station connection data, including the total number of connected devices, fixed device data, and the dwell time data for each connected device.

[0049] As described above, this application provides a service area pedestrian density AI analysis and early warning method and system. This method obtains effective monitoring personnel data and effective connection data by preprocessing the acquired service area monitoring personnel data and base station connection data. It then obtains effective base station personnel data by processing the personnel quantity evaluation model trained on the effective connection data set. Finally, it obtains pedestrian density data by processing the effective monitoring personnel data, base station effective personnel data, and a preset service area area. The method then compares the pedestrian density data against a threshold to obtain an early warning level. Thus, by obtaining effective monitoring personnel data and effective connection data, calculating base station effective personnel data and pedestrian density data, and combining threshold comparisons, the method dynamically evaluates the early warning level, thereby improving service area management and ensuring service area operational safety.

[0050] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating a service area pedestrian density AI analysis and early warning method provided in this application embodiment;

[0053] Figure 2 A flowchart illustrating the acquisition of service area monitoring personnel data and base station connection data for a service area pedestrian density AI analysis and early warning method provided in this application embodiment;

[0054] Figure 3 This is a flowchart illustrating the process of obtaining effective monitoring personnel data and effective connection data for a service area pedestrian density AI analysis and early warning method provided in this application embodiment. Detailed Implementation

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0056] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0057] Please refer to Figure 1 , Figure 1 This is a flowchart of a service area pedestrian density AI analysis and early warning method in some embodiments of this application. This service area pedestrian density AI analysis and early warning method is used in terminal devices, such as computers and mobile phones. A service area pedestrian density AI analysis and early warning method includes the following steps:

[0058] S11. Obtain service area monitoring personnel data and base station connection data;

[0059] S12. Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data respectively;

[0060] S13. Obtain historical base station connection data and train a personnel quantity assessment model. Based on the effective connection data, process the personnel quantity assessment model to obtain effective personnel data for the base station.

[0061] S14. Based on the effective monitoring personnel data and the effective personnel data of the base station, obtain comprehensive effective personnel data, and combine it with the preset service area area to obtain population density data;

[0062] S15. Compare the pedestrian density data with the preset early warning assessment threshold to obtain the early warning level.

[0063] It should be noted that the service area monitoring personnel data is obtained through detection by various sensors. Due to the complexity of the on-site environment, the sensor detection results have a certain degree of inaccuracy. In order to better achieve personnel monitoring, base station connection data is also obtained. Base station connection data reflects the connection status of devices to base stations within a short period of time. Since there is interference data in the devices connected to base stations, it is necessary to preprocess the service area monitoring personnel data and base station connection data to obtain effective monitoring personnel data and effective connection data. After training a personnel quantity assessment model based on historical base station connection data, the effective connection data can be combined to obtain the effective personnel data of the base station. Both service area monitoring personnel data and base station connection data can reflect the number of people in the service area to a certain extent, but both have certain limitations. Therefore, a weighted calculation method can be used to obtain a more accurate comprehensive effective personnel number that reflects the true number of people. Then, the population density data is obtained by combining the preset service area area. The reception capacity of the service area is fixed. Based on the reception capacity, an early warning assessment threshold can be obtained. Then, the early warning level is obtained by comparing the thresholds.

[0064] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the acquisition of effective operating parameters for an AI-based analysis and early warning method for pedestrian density in service areas, as provided in an embodiment of this application. According to an embodiment of the present invention, acquiring service area monitoring personnel data and base station connection data specifically includes:

[0065] S21. Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel;

[0066] S22. Obtain base station connection data, including the total number of connected devices, fixed device data, and dwell time data for each connected device.

[0067] It should be noted that the total number of monitoring personnel refers to the total number of personnel obtained through monitoring equipment; fixed personnel data refers to the number of service area staff working within the monitoring range that will be monitored and counted by the monitoring equipment; base station connection data refers to the data corresponding to the devices that are still connected to the base station as of now, including the total number of connected devices, which refers to the total number of devices connected to the base station; fixed device data refers to the number of smart devices used by staff in the service area, smart devices used by merchants, and service area operating equipment connected to the base station; and dwell time data refers to the dwell time of the device since it connected to the base station up to the time of data acquisition.

[0068] Please refer to Figure 3 , Figure 3This is a flowchart illustrating the process of obtaining effective monitoring personnel data and effective connection data in a service area pedestrian density AI analysis and early warning method provided in this application embodiment. According to this embodiment, the preprocessing of service area monitoring personnel data and base station connection data to obtain effective monitoring personnel data and effective connection data specifically includes:

[0069] S31. Obtain valid monitoring personnel data by subtracting the total number of monitoring personnel from the fixed personnel data;

[0070] S32. Subtract the fixed device data from the total number of connected devices to obtain the mobile device data;

[0071] S33. Compare the dwell time data corresponding to the mobile device with the preset dwell state evaluation threshold to obtain valid connection data;

[0072] S34. The preset dwell state evaluation threshold includes a first threshold and a second threshold, and the first threshold is greater than the second threshold;

[0073] S35. If the dwell time data is greater than the second threshold and less than the first threshold, then the base station connection data corresponding to the device is valid connection data.

[0074] It should be noted that the effective monitoring personnel data is obtained by subtracting the fixed personnel data from the total number of monitoring personnel. The effective monitoring personnel data refers to the number of mobile personnel monitored within the service area. Connecting to a base station does not necessarily mean entering the service area; it may just be passing through. Therefore, it is necessary to train based on a combination of factors such as base station coverage and highway speed limits to obtain the time required for a driver to pass through a service area without stopping, and use this as the second threshold. If the device stays for too long, it indicates that the person is not moving around in the service area and may be resting in the parking lot, which will interfere with the movement. The first threshold is also obtained based on the actual situation of the service area. Only those within the range of the first and second thresholds are considered effective mobile personnel, and the number of effectively connected devices can be obtained.

[0075] According to an embodiment of the present invention, the step of acquiring historical base station connection data and training a personnel quantity assessment model, and processing the effective connection data through the personnel quantity assessment model to obtain effective personnel data for the base station, specifically includes:

[0076] Historical base station connection data is obtained and a personnel quantity assessment model is trained. The model includes the per capita device number coefficient and device active carrying rate obtained during training.

[0077] The effective connection data is input into the personnel quantity assessment model to obtain the effective personnel data of the base station.

[0078] It should be noted that a population quantity assessment model can be trained using historical base station connection data. This model can then be used to obtain the effective number of people connected to the base station. The per capita device count coefficient refers to the average number of smart devices a person owns; for example, a person may have multiple mobile phones, tablets, or connected vehicles. This coefficient can be obtained through training on historical base station connection data and its value ranges from greater than 1. The device active carrying rate is used to correct for situations where "people do not carry devices / devices are offline" (e.g., elderly people or young children do not carry devices, or mobile phones are turned off / have no signal), reflecting "the proportion of the actual population carrying active devices," and its value ranges from less than 1. The calculation formula for the population quantity assessment model is:

[0079] ;

[0080] in, For base station valid personnel data, To effectively connect data, This is the coefficient for the number of devices per capita. The active carrying rate of the equipment.

[0081] According to an embodiment of the present invention, the step of obtaining comprehensive effective personnel data by processing effective monitoring personnel data and effective personnel data from base stations, and obtaining population density data by combining the data with the preset service area area, specifically includes:

[0082] Comprehensive effective personnel data is obtained by weighted calculation based on effective monitoring personnel data and effective personnel data from base stations.

[0083] The population density data is obtained by dividing the total effective personnel data by the preset service area area.

[0084] It should be noted that both effective monitoring personnel data and base station effective personnel data can reflect the flow of people in the service area to a certain extent, but they also have certain limitations. In order to better estimate the flow of people in the service area, a weighted calculation method is used to calculate the comprehensive effective personnel data, that is, the number of effective personnel after comprehensive consideration. When performing the weighted calculation, the weight coefficients corresponding to the effective monitoring personnel data and the base station effective personnel data can be obtained by training based on the historical data of the service area and can change with time and holidays.

[0085] According to an embodiment of the present invention, the step of comparing the pedestrian density data with a preset early warning assessment threshold to obtain the early warning level specifically includes:

[0086] The third and fourth thresholds are extracted based on the preset early warning assessment thresholds, and the third threshold is greater than the fourth threshold;

[0087] The warning level is obtained by comparing the crowd density data with the third and fourth thresholds, including normal level, first-level warning or second-level warning;

[0088] If the pedestrian density data is less than or equal to the fourth threshold, the warning level is normal and the service area is operating normally.

[0089] If the crowd density data is greater than the fourth threshold but less than the third threshold, the warning level is Level 1, the broadcast zone notification is activated, and staff are dispatched to guide the crowd on site.

[0090] If the pedestrian density data is greater than or equal to the third threshold, the warning level is level two. The warning level of the service area will be pushed to highway vehicles within a preset distance through the navigation app, and users' stopping intentions will be collected.

[0091] It should be noted that the third and fourth thresholds can be set according to the carrying capacity of the service area and operational needs. If it is a level 2 warning, it means that there are many people moving around in the service area, which is very crowded and may cause safety accidents. Therefore, the navigation app sends the warning level to vehicles traveling on the highway within a preset distance of the service area and collects the users' stopping intentions in order to respond to subsequent situations at any time.

[0092] According to an embodiment of the present invention, it further includes:

[0093] Obtain age data of people staying in service areas, including the elderly, young and middle-aged adults, or children;

[0094] The total number of people in each age group was counted, and the proportion of young and middle-aged people was calculated.

[0095] The data on the proportion of young and middle-aged people is compared with the preset warning correction threshold to obtain the warning correction data;

[0096] If the percentage of young people is less than or equal to the preset warning correction threshold, the warning correction status data will be the start correction data, and the warning level will be automatically raised by one level.

[0097] If the proportion of young people exceeds the preset warning correction threshold, the warning correction status will be maintained.

[0098] It should be noted that the age group data of people staying in the service area can be obtained through computer vision and artificial intelligence algorithms. Specifically, cameras acquire facial images of people staying in the area, and preset artificial intelligence algorithms capture key biometric features of the face, such as facial contour proportions and the degree of relaxation of the corners of the eyes and mouth. The system compares the extracted features with a large number of facial samples labeled with age in the database, calculates the closest estimated age through a machine learning model, and then compares the estimated age with preset age group thresholds to obtain age group data. For people staying in the area whose faces cannot be identified, the total number is counted and then distributed according to a preset ratio, which is obtained through the analysis of historical data. The safety of people in the service area is of paramount importance. The elderly and children are vulnerable groups and require special attention. The proportion of young and middle-aged people is obtained by dividing the number of young and middle-aged people by the total number of migrant workers. The warning correction data refers to whether the warning level is corrected. In this embodiment, when the warning level is normal, if the warning correction data is set to initiate correction, the warning level will be automatically raised by one level to Level 1 warning.

[0099] According to an embodiment of the present invention, it further includes:

[0100] Obtain the service area zoning data, including catering areas, restroom areas, shopping areas, and parking areas;

[0101] Obtain the regional density data corresponding to each region, and compare the regional density data with the corresponding preset regional early warning assessment threshold to obtain the regional early warning status;

[0102] The regional warning status will be pushed to highway vehicles within a preset distance via the navigation app;

[0103] Users select their desired parking location and intended usage area based on the push notification information.

[0104] It should be noted that different areas within a service area have different functions, and the demand probability for each function varies. Therefore, if the overall pedestrian density of the service area is used for calculation, there may be a situation where the overall level is at the first level of warning, but individual areas are at the normal level. Therefore, in order to assess the warning level of an area, the highway vehicles within the preset distance refer to vehicles that are about to arrive at the service area and are within the preset distance.

[0105] It is worth mentioning that it also includes:

[0106] Obtain the current time data and the pause intention mapping table. The pause intention mapping table includes date type data, pause time period data, and the corresponding pause intention coefficient.

[0107] Obtain vehicle attribute data within a preset distance. The vehicle attribute data includes vehicle type, number of vehicle types, and average number of passengers per vehicle corresponding to each vehicle type.

[0108] The stationing intention coefficient is obtained by querying the stationing intention mapping table based on the current time data;

[0109] The number of people intending to park is calculated based on the number of vehicle types, the average number of passengers per vehicle, and the parking intention coefficient.

[0110] The estimated crowd density data is calculated based on the number of people intending to stay and the current crowd density data.

[0111] The estimated warning level is obtained by comparing the estimated pedestrian density data with the preset warning assessment threshold.

[0112] It should be noted that date type data includes holiday date data or ordinary date data, because traffic flow on holidays is significantly higher than on ordinary dates. Stop time phase type refers to rest periods or ordinary periods, with rest periods referring to meal times. The stop intention coefficient is the ratio of the number of vehicles entering the service area to the total number of vehicles passing through, obtained from historical data for each date type and stop time phase. Vehicle type refers to trucks, special vehicles, buses, or ordinary passenger cars. The number of vehicle types refers to the number of each type. The average number of passengers per vehicle refers to the average number of passengers per vehicle type, obtained from historical data. The number of people intending to stop refers to the number of people who may enter the service area to stop. Obtaining the estimated warning level is helpful for taking countermeasures in advance.

[0113] This invention also discloses a service area pedestrian density AI analysis and early warning system, including a memory and a processor. The memory stores a service area pedestrian density AI analysis and early warning method program. When the processor executes the service area pedestrian density AI analysis and early warning method program, it performs the following steps:

[0114] Acquire service area monitoring personnel data and base station connection data;

[0115] Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data, respectively.

[0116] Historical base station connection data is acquired and a personnel quantity assessment model is trained. Based on the effective connection data, the personnel quantity assessment model is used to obtain the effective personnel data of the base station.

[0117] Comprehensive effective personnel data is obtained by processing effective monitoring personnel data and effective personnel data from base stations, and population density data is obtained by combining the data with the preset service area area.

[0118] The warning level is obtained by comparing the pedestrian density data with the preset warning assessment threshold.

[0119] It should be noted that the service area monitoring personnel data is obtained through detection by various sensors. Due to the complexity of the on-site environment, the sensor detection results have a certain degree of inaccuracy. In order to better achieve personnel monitoring, base station connection data is also obtained. Base station connection data reflects the connection status of devices to base stations within a short period of time. Since there is interference data in the devices connected to base stations, it is necessary to preprocess the service area monitoring personnel data and base station connection data to obtain effective monitoring personnel data and effective connection data. After training a personnel quantity assessment model based on historical base station connection data, the effective connection data can be combined to obtain the effective personnel data of the base station. Both service area monitoring personnel data and base station connection data can reflect the number of people in the service area to a certain extent, but both have certain limitations. Therefore, a weighted calculation method can be used to obtain a more accurate comprehensive effective personnel number that reflects the true number of people. Then, the population density data is obtained by combining the preset service area area. The reception capacity of the service area is fixed. Based on the reception capacity, an early warning assessment threshold can be obtained. Then, the early warning level is obtained by comparing the thresholds.

[0120] According to an embodiment of the present invention, the acquisition of service area monitoring personnel data and base station connection data specifically includes:

[0121] Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel;

[0122] Obtain base station connection data, including the total number of connected devices, fixed device data, and the dwell time data for each connected device.

[0123] It should be noted that the total number of monitoring personnel refers to the total number of personnel obtained through monitoring equipment; fixed personnel data refers to the number of service area staff working within the monitoring range that will be monitored and counted by the monitoring equipment; base station connection data refers to the data corresponding to the devices that are still connected to the base station as of now, including the total number of connected devices, which refers to the total number of devices connected to the base station; fixed device data refers to the number of smart devices used by staff in the service area, smart devices used by merchants, and service area operating equipment connected to the base station; and dwell time data refers to the dwell time of the device since it connected to the base station up to the time of data acquisition.

[0124] According to an embodiment of the present invention, the preprocessing of service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data respectively includes:

[0125] The effective monitoring personnel data is obtained by subtracting the total number of monitoring personnel from the data on fixed personnel.

[0126] Subtract the fixed device data from the total number of connected devices to obtain the mobile device data;

[0127] The dwell time data corresponding to the mobile device is compared with the preset dwell state evaluation threshold to obtain valid connection data;

[0128] The preset dwell state evaluation thresholds include a first threshold and a second threshold, and the first threshold is greater than the second threshold;

[0129] If the dwell time data is greater than the second threshold and less than the first threshold, then the base station connection data corresponding to the device is valid connection data.

[0130] It should be noted that the effective monitoring personnel data is obtained by subtracting the fixed personnel data from the total number of monitoring personnel. The effective monitoring personnel data refers to the number of mobile personnel monitored within the service area. Connecting to a base station does not necessarily mean entering the service area; it may just be passing through. Therefore, it is necessary to train based on a combination of factors such as base station coverage and highway speed limits to obtain the time required for a driver to pass through a service area without stopping, and use this as the second threshold. If the device stays for too long, it indicates that the person is not moving around in the service area and may be resting in the parking lot, which will interfere with the movement. The first threshold is also obtained based on the actual situation of the service area. Only those within the range of the first and second thresholds are considered effective mobile personnel, and the number of effectively connected devices can be obtained.

[0131] According to an embodiment of the present invention, the step of acquiring historical base station connection data and training a personnel quantity assessment model, and processing the effective connection data through the personnel quantity assessment model to obtain effective personnel data for the base station, specifically includes:

[0132] Historical base station connection data is obtained and a personnel quantity assessment model is trained. The model includes the per capita device number coefficient and device active carrying rate obtained during training.

[0133] The effective connection data is input into the personnel quantity assessment model to obtain the effective personnel data of the base station.

[0134] It should be noted that a population quantity assessment model can be trained using historical base station connection data. This model can then be used to obtain the effective number of people connected to the base station. The per capita device count coefficient refers to the average number of smart devices a person owns; for example, a person may have multiple mobile phones, tablets, or connected vehicles. This coefficient can be obtained through training on historical base station connection data and its value ranges from greater than 1. The device active carrying rate is used to correct for situations where "people do not carry devices / devices are offline" (e.g., elderly people or young children do not carry devices, or mobile phones are turned off / have no signal), reflecting "the proportion of the actual population carrying active devices," and its value ranges from less than 1. The calculation formula for the population quantity assessment model is:

[0135] ;

[0136] in, For base station valid personnel data, To effectively connect data, This is the coefficient for the number of devices per capita. The active carrying rate of the equipment.

[0137] According to an embodiment of the present invention, the step of obtaining comprehensive effective personnel data by processing effective monitoring personnel data and effective personnel data from base stations, and obtaining population density data by combining the data with the preset service area area, specifically includes:

[0138] Comprehensive effective personnel data is obtained by weighted calculation based on effective monitoring personnel data and effective personnel data from base stations.

[0139] The population density data is obtained by dividing the total effective personnel data by the preset service area area.

[0140] It should be noted that both effective monitoring personnel data and base station effective personnel data can reflect the flow of people in the service area to a certain extent, but they also have certain limitations. In order to better estimate the flow of people in the service area, a weighted calculation method is used to calculate the comprehensive effective personnel data, that is, the number of effective personnel after comprehensive consideration. When performing the weighted calculation, the weight coefficients corresponding to the effective monitoring personnel data and the base station effective personnel data can be obtained by training based on the historical data of the service area and can change with time and holidays.

[0141] According to an embodiment of the present invention, the step of comparing the pedestrian density data with a preset early warning assessment threshold to obtain the early warning level specifically includes:

[0142] The third and fourth thresholds are extracted based on the preset early warning assessment thresholds, and the third threshold is greater than the fourth threshold;

[0143] The warning level is obtained by comparing the crowd density data with the third and fourth thresholds, including normal level, first-level warning or second-level warning;

[0144] If the pedestrian density data is less than or equal to the fourth threshold, the warning level is normal and the service area is operating normally.

[0145] If the crowd density data is greater than the fourth threshold but less than the third threshold, the warning level is Level 1, the broadcast zone notification is activated, and staff are dispatched to guide the crowd on site.

[0146] If the pedestrian density data is greater than or equal to the third threshold, the warning level is level two. The warning level of the service area will be pushed to highway vehicles within a preset distance through the navigation app, and users' stopping intentions will be collected.

[0147] It should be noted that the third and fourth thresholds can be set according to the carrying capacity of the service area and operational needs. If it is a level 2 warning, it means that there are many people moving around in the service area, which is very crowded and may cause safety accidents. Therefore, the navigation app sends the warning level to vehicles traveling on the highway within a preset distance of the service area and collects the users' stopping intentions in order to respond to subsequent situations at any time.

[0148] According to an embodiment of the present invention, it further includes:

[0149] Obtain age data of people staying in service areas, including the elderly, young and middle-aged adults, or children;

[0150] The total number of people in each age group was counted, and the proportion of young and middle-aged people was calculated.

[0151] The data on the proportion of young and middle-aged people is compared with the preset warning correction threshold to obtain the warning correction data;

[0152] If the percentage of young people is less than or equal to the preset warning correction threshold, the warning correction status data will be the start correction data, and the warning level will be automatically raised by one level.

[0153] If the proportion of young people exceeds the preset warning correction threshold, the warning correction status will be maintained.

[0154] It should be noted that the age group data of people staying in the service area can be obtained through computer vision and artificial intelligence algorithms. Specifically, cameras acquire facial images of people staying in the area, and preset artificial intelligence algorithms capture key biometric features of the face, such as facial contour proportions and the degree of relaxation of the corners of the eyes and mouth. The system compares the extracted features with a large number of facial samples labeled with age in the database, calculates the closest estimated age through a machine learning model, and then compares the estimated age with preset age group thresholds to obtain age group data. For people staying in the area whose faces cannot be identified, the total number is counted and then distributed according to a preset ratio, which is obtained through the analysis of historical data. The safety of people in the service area is of paramount importance. The elderly and children are vulnerable groups and require special attention. The proportion of young and middle-aged people is obtained by dividing the number of young and middle-aged people by the total number of migrant workers. The warning correction data refers to whether the warning level is corrected. In this embodiment, when the warning level is normal, if the warning correction data is set to initiate correction, the warning level will be automatically raised by one level to Level 1 warning.

[0155] According to an embodiment of the present invention, it further includes:

[0156] Obtain the service area zoning data, including catering areas, restroom areas, shopping areas, and parking areas;

[0157] Obtain the regional density data corresponding to each region, and compare the regional density data with the corresponding preset regional early warning assessment threshold to obtain the regional early warning status;

[0158] The regional warning status will be pushed to highway vehicles within a preset distance via the navigation app;

[0159] Users select their desired parking location and intended usage area based on the push notification information.

[0160] It should be noted that different areas within a service area have different functions, and the demand probability for each function varies. Therefore, if the overall pedestrian density of the service area is used for calculation, there may be a situation where the overall level is at the first level of warning, but individual areas are at the normal level. Therefore, in order to assess the warning level of an area, the highway vehicles within the preset distance refer to vehicles that are about to arrive at the service area and are within the preset distance.

[0161] It is worth mentioning that it also includes:

[0162] Obtain the current time data and the pause intention mapping table. The pause intention mapping table includes date type data, pause time period data, and the corresponding pause intention coefficient.

[0163] Obtain vehicle attribute data within a preset distance. The vehicle attribute data includes vehicle type, number of vehicle types, and average number of passengers per vehicle corresponding to each vehicle type.

[0164] The stationing intention coefficient is obtained by querying the stationing intention mapping table based on the current time data;

[0165] The number of people intending to park is calculated based on the number of vehicle types, the average number of passengers per vehicle, and the parking intention coefficient.

[0166] The estimated crowd density data is calculated based on the number of people intending to stay and the current crowd density data.

[0167] The estimated warning level is obtained by comparing the estimated pedestrian density data with the preset warning assessment threshold.

[0168] It should be noted that date type data includes holiday date data or ordinary date data, because traffic flow on holidays is significantly higher than on ordinary dates. Stop time phase type refers to rest periods or ordinary periods, with rest periods referring to meal times. The stop intention coefficient is the ratio of the number of vehicles entering the service area to the total number of vehicles passing through, obtained from historical data for each date type and stop time phase. Vehicle type refers to trucks, special vehicles, buses, or ordinary passenger cars. The number of vehicle types refers to the number of each type. The average number of passengers per vehicle refers to the average number of passengers per vehicle type, obtained from historical data. The number of people intending to stop refers to the number of people who may enter the service area to stop. Obtaining the estimated warning level is helpful for taking countermeasures in advance.

[0169] This invention discloses an AI-based analysis and early warning method and system for pedestrian density in service areas. It obtains effective monitoring personnel data and effective connection data by preprocessing acquired service area monitoring personnel data and base station connection data. Then, it obtains effective personnel data for base stations by processing a personnel quantity assessment model trained on the effective connection data set. Finally, it obtains pedestrian density data by processing the effective monitoring personnel data, base station effective personnel data, and a preset service area area. The system then compares the pedestrian density data against a threshold to determine the early warning level. By obtaining effective monitoring personnel data and effective connection data, calculating base station effective personnel data and pedestrian density data, and combining threshold comparisons, the system dynamically assesses the early warning level, thereby improving service area management and ensuring service area operational safety.

[0170] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0171] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0172] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0173] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0174] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This 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 methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for AI analysis and early warning of pedestrian density in service areas, characterized in that, include: Acquire service area monitoring personnel data and base station connection data; Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data, respectively. Historical base station connection data is acquired and a personnel quantity assessment model is trained. Based on the effective connection data, the personnel quantity assessment model is used to obtain the effective personnel data of the base station. Comprehensive effective personnel data is obtained by processing effective monitoring personnel data and effective personnel data from base stations, and population density data is obtained by combining the data with the preset service area area. The warning level is obtained by comparing the pedestrian density data with the preset warning assessment threshold.

2. The service area pedestrian density AI analysis and early warning method according to claim 1, characterized in that, The acquisition of service area monitoring personnel data and base station connection data specifically includes: Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel; Obtain base station connection data, including the total number of connected devices, fixed device data, and the dwell time data for each connected device.

3. The service area pedestrian density AI analysis and early warning method according to claim 2, characterized in that, The preprocessing of service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data specifically includes: The effective monitoring personnel data is obtained by subtracting the total number of monitoring personnel from the data on fixed personnel. Subtract the fixed device data from the total number of connected devices to obtain the mobile device data; The dwell time data corresponding to the mobile device is compared with the preset dwell state evaluation threshold to obtain valid connection data; The preset dwell state evaluation thresholds include a first threshold and a second threshold, and the first threshold is greater than the second threshold; If the dwell time data is greater than the second threshold and less than the first threshold, then the base station connection data corresponding to the device is valid connection data.

4. The service area pedestrian density AI analysis and early warning method according to claim 3, characterized in that, The process of acquiring historical base station connection data and training a personnel quantity assessment model, and then processing the effective connection data using the personnel quantity assessment model to obtain effective personnel data for the base station, specifically includes: Historical base station connection data is obtained and a personnel quantity assessment model is trained. The model includes the per capita device number coefficient and device active carrying rate obtained during training. The effective connection data is input into the personnel quantity assessment model to obtain the effective personnel data of the base station.

5. The service area pedestrian density AI analysis and early warning method according to claim 4, characterized in that, The process of obtaining comprehensive effective personnel data based on effective monitoring personnel data and effective personnel data from base stations, and then combining this with processing based on the preset service area area to obtain population density data, specifically includes: Comprehensive effective personnel data is obtained by weighted calculation based on effective monitoring personnel data and effective personnel data from base stations. The population density data is obtained by dividing the total effective personnel data by the preset service area area.

6. The service area pedestrian density AI analysis and early warning method according to claim 5, characterized in that, The step of comparing pedestrian density data with a preset early warning assessment threshold to obtain the early warning level specifically includes: The third and fourth thresholds are extracted based on the preset early warning assessment thresholds, and the third threshold is greater than the fourth threshold; The warning level is obtained by comparing the crowd density data with the third and fourth thresholds, including normal level, first-level warning or second-level warning; If the pedestrian density data is less than or equal to the fourth threshold, the warning level is normal and the service area is operating normally. If the crowd density data is greater than the fourth threshold but less than the third threshold, the warning level is Level 1, the broadcast zone notification is activated, and staff are dispatched to guide the crowd on site. If the pedestrian density data is greater than or equal to the third threshold, the warning level is level two. The warning level of the service area will be pushed to highway vehicles within a preset distance through the navigation app, and users' stopping intentions will be collected.

7. The service area pedestrian density AI analysis and early warning method according to claim 6, characterized in that, Also includes: Obtain age data of people staying in service areas, including the elderly, young and middle-aged adults, or children; The total number of people in each age group was counted, and the proportion of young and middle-aged people was calculated. The data on the proportion of young and middle-aged people is compared with the preset warning correction threshold to obtain the warning correction data; If the percentage of young people is less than or equal to the preset warning correction threshold, the warning correction status data will be the start correction data, and the warning level will be automatically raised by one level. If the proportion of young people exceeds the preset warning correction threshold, the warning correction status will be maintained.

8. The service area pedestrian density AI analysis and early warning method according to claim 7, characterized in that, Also includes: Obtain the service area zoning data, including catering areas, restroom areas, shopping areas, and parking areas; Obtain the regional density data corresponding to each region, and compare the regional density data with the corresponding preset regional early warning assessment threshold to obtain the regional early warning status; The regional warning status will be pushed to highway vehicles within a preset distance via the navigation app; Users select their desired parking location and intended usage area based on the push notification information.

9. A service area pedestrian density AI analysis and early warning system, characterized in that, The system includes a memory and a processor. The memory contains a program for AI analysis and early warning of pedestrian density in service areas. When the processor executes the program, the program performs the following steps: Acquire service area monitoring personnel data and base station connection data; Preprocess the service area monitoring personnel data and base station connection data to obtain valid monitoring personnel data and valid connection data, respectively. Historical base station connection data is acquired and a personnel quantity assessment model is trained. Based on the effective connection data, the personnel quantity assessment model is used to obtain the effective personnel data of the base station. Comprehensive effective personnel data is obtained by processing effective monitoring personnel data and effective personnel data from base stations, and population density data is obtained by combining the data with the preset service area area. The warning level is obtained by comparing the pedestrian density data with the preset warning assessment threshold.

10. The service area pedestrian density AI analysis and early warning system according to claim 9, characterized in that, The acquisition of service area monitoring personnel data and base station connection data specifically includes: Obtain service area monitoring personnel data, including the total number of monitoring personnel and data on permanent personnel; Obtain base station connection data, including the total number of connected devices, fixed device data, and the dwell time data for each connected device.

Images