Pedestrian flow prediction method, device and equipment

Abstract

The invention discloses a people flow prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the monitoring data of a target region, analyzing the monitoring data, and determining the historical people flow and average residence time of the target region; determining the popularity degree of the target area based on the historical people flow and the average residence time; and performing prediction analysis according to the historical people flow and the popularity degree to obtain the predicted people flow of the target area in the target time period. According to the method, the popularity degree of the target area is evaluated, and the predicted people flow of the target area in the future target time period is predicted in combination with the historical people flow and the popularity degree of the target area, so that accurate expectation of the people flow of the target area is realized, and timely data support is provided for resource allocation of the target area.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and specifically relates to a method, device, equipment and storage medium for predicting human flow. Background Art

[0002] With the development of tourism, scenic spot operations are facing increasingly complex problems. Usually, scenic spots include multiple different functional areas, and the distribution of tourist traffic in different areas and at different times is uneven and changes in real time.

[0003] If the flow of people in a certain period of time or in a certain area is too high, it is easy to cause crowding, trampling and other safety hazards. If a certain period of time or a certain area is relatively deserted, the resources of the scenic spot cannot be fully utilized. Therefore, the scenic spot needs to adjust the resource allocation in advance according to the expected changes in the flow of people.

[0004] However, existing technologies can only determine the flow of people in each area at the current time based on ticket sales or visual observation, which makes it difficult to achieve accurate predictions of the flow of people, resulting in inflexible resource allocation in scenic spots and poor tourist experience. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, equipment and storage medium for predicting passenger flow, which can solve the problem that it is currently difficult to achieve accurate prediction of passenger flow, resulting in inflexible resource allocation in scenic spots and poor tourist experience.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting flow of people, the method comprising:

[0007] Acquire monitoring data of a target area, analyze the monitoring data, and determine the historical flow of people and average stay time of the target area;

[0008] Determining the popularity of the target area based on the historical passenger flow and the average stay time;

[0009] A forecast analysis is performed based on the historical passenger flow and the popularity to obtain a forecast passenger flow of the target area within a target time period.

[0010] Optionally, analyzing the monitoring data to determine the historical flow of people and average stay time in the target area includes:

[0011] Performing human body detection on the monitoring data, counting the number of people detected at each moment, obtaining the flow of people at each moment, and taking the flow of people at each moment in a preset time period as the historical flow of people;

[0012] In the monitoring data, the trajectory of each person detected is tracked to determine the average stay time.

[0013] Optionally, determining the popularity of the target area based on the historical flow of people and the average stay time includes:

[0014] Obtaining the area of ​​the target area, and collecting the behavior data of each person in the target area and the feedback data on the target area;

[0015] The popularity of the target area is determined based on the historical flow of people, the average stay time, the area, the behavior data and the feedback data.

[0016] Optionally, performing a forecast analysis based on the historical flow of people and the popularity to obtain a forecast flow of people in the target area within a target time period includes:

[0017] Inputting the historical passenger flow into a pre-trained time series model for prediction analysis to obtain a reference passenger flow in the target area within a target time period;

[0018] The reference flow of people is adjusted according to the popularity to obtain the predicted flow of people in the target area within the target time period.

[0019] Optionally, there are multiple target areas, and adjusting the reference flow of people according to the popularity to obtain the predicted flow of people in the target area within the target time period includes:

[0020] For each target area, determining a ratio of the corresponding popularity to a reference value, wherein the reference value is the maximum value of the popularity;

[0021] Based on the ratio, the reference human flow is adjusted to obtain the predicted human flow of the target area within the target time period.

[0022] Optionally, after performing the forecast analysis based on the historical flow of people and the popularity to obtain the forecast flow of people in the target area within the target time period, the method further includes:

[0023] Determining a capacity limit value of the target area according to the historical flow of people;

[0024] When the predicted passenger flow exceeds the capacity limit value, a passenger flow warning for the target area is triggered.

[0025] Optionally, determining the capacity limit value of the target area according to the historical flow of people includes:

[0026] According to the historical flow of people, calculate the average and maximum value of the flow of people at each moment in a preset time period;

[0027] The product of the average value and a preset coefficient is used as the capacity limit value of the target area;

[0028] Determine whether the capacity limit value is less than the maximum value; if not, adjust the preset coefficient and return to the step of taking the product of the average value and the preset coefficient as the capacity limit value of the target area.

[0029] In a second aspect, an embodiment of the present application provides a pedestrian flow prediction device, the device comprising:

[0030] An acquisition module is used to acquire monitoring data of a target area, analyze the monitoring data, and determine the historical flow of people and average stay time of the target area;

[0031] A determination module, configured to determine the popularity of the target area based on the historical flow of people and the average stay time;

[0032] The prediction module is used to perform prediction analysis based on the historical passenger flow and the popularity to obtain the predicted passenger flow of the target area within the target time period.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0034] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0035] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0036] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0037] In the present application, first, the monitoring data of the target area is obtained, and the monitoring data is analyzed to determine the historical flow of people and the average residence time of the target area; based on the historical flow of people and the average residence time, the popularity of the target area is determined; and a predictive analysis is performed based on the historical flow of people and the popularity to obtain the predicted flow of people in the target area during the target time period.

[0038] From the above, it can be seen that by analyzing the monitoring data of the target area, the historical flow of people and the average stay time of the target area can be determined, and then the popularity of the target area can be evaluated based on the historical flow of people and the average stay time. In combination with the historical flow of people and the popularity of the target area, the predicted flow of people in the target area in the future target time period is predicted, thereby achieving accurate prediction of the flow of people in the target area and providing timely data support for resource allocation in the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a method for predicting human flow according to an exemplary embodiment;

[0040] Figure 2 is a system architecture diagram of a method for predicting human flow according to an exemplary embodiment;

[0041] Figure 3 is a block diagram of a pedestrian flow prediction device according to an exemplary embodiment;

[0042] Figure 4 is a block diagram of an electronic device according to an exemplary embodiment;

[0043] Figure 5 The figure is a schematic diagram showing the hardware structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0045] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0046] The following is a detailed description of the crowd flow prediction method provided by the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0047] Figure 1 The present invention is a flowchart of a method for predicting human flow according to an exemplary embodiment, which is applied to a client. The method for predicting human flow includes the following steps.

[0048] In step S11, the monitoring data of the target area is acquired, and the monitoring data is analyzed to determine the historical flow of people and the average stay time of the target area.

[0049] At present, scenic spot operators can only determine the flow of people in each area at the current time based on ticket sales or visual observation, which makes it difficult to accurately predict the flow of people, resulting in inflexible resource allocation in scenic spots and poor tourist experience. Based on this, this application proposes a method for predicting flow of people to solve the above problems.

[0050] In this step, the target area must be identified first. The target area can be a public place such as a shopping mall, park, station, airport, or a certain area within a scenic area. For example, the scenic area map can be combined to divide multiple target areas according to different functional areas of the scenic area.

[0051] By installing surveillance cameras or other sensor devices, the surveillance data of the target area can be collected in real time to capture the flow of people in the target area. The surveillance data usually includes video images, timestamps and other information.

[0052] In order to better predict the flow of people, it is necessary to ensure the integrity, accuracy and real-time nature of the monitoring data. Integrity means that the monitoring data must cover all key locations in the target area in order to fully understand the flow of people. Accuracy requires that the monitoring data can truly reflect the actual situation and avoid errors and deviations. Real-time ensures that the monitoring data can be updated in a timely manner so that decisions and adjustments can be made in a timely manner.

[0053] After obtaining the monitoring data, it can be analyzed to determine the historical flow of people and the average stay time using technologies such as human detection and tracking, trajectory analysis, data statistics and visualization.

[0054] Among them, historical passenger flow can help us understand the changing trends and patterns of passenger flow in the target area over the past period of time, providing a basis for future predictions and planning. The average length of stay can reflect the attractiveness of the target area and tourist satisfaction by tracking and analyzing the trajectory of each person, which is of great significance for optimizing service quality and improving tourist experience.

[0055] In one implementation, monitoring data is analyzed to determine the historical flow of people and average dwell time in the target area, including:

[0056] Perform human detection on the monitoring data, count the number of people detected at each moment, obtain the flow of people at each moment, and take the flow of people at each moment in the preset time period as the historical flow of people;

[0057] In the monitoring data, the trajectory of each person detected is tracked to determine the average residence time.

[0058] That is to say, it is first necessary to perform human body detection on the monitoring data. Human body detection involves image processing technology and machine learning algorithms. For example, deep learning models such as YOLO (You Only Look Once) and SSD (Single Shot MultiBox Detector) can be used to perform real-time human body detection on each video frame of the monitoring data, so as to accurately identify the human body in each frame and output its position and size information.

[0059] After detecting a human body, the number of detected human bodies in each frame can be counted to count the number of people detected at each moment. Furthermore, the detection results of adjacent frames can be smoothed using methods such as sliding windows or time averaging to reduce counting fluctuations caused by detection errors or human movement, and obtain more accurate human flow data.

[0060] Finally, the flow of people at each moment in the preset time period is summarized and recorded to obtain historical flow data for subsequent flow prediction and analysis. The preset time period can be a time period within a certain time range from the current time, such as the last 24 hours, or a certain set time period, such as the past 7 natural days, etc., without specific limitation.

[0061] After obtaining the human body detection data, the trajectory of each detected person can also be tracked. Trajectory tracking usually involves target tracking algorithms in video sequences, such as Kalman filtering, particle filtering or deep learning trackers. These target tracking algorithms can track the movement trajectory of each person in the continuous video frames of the monitoring data based on the results of human body detection.

[0062] By tracking the trajectory, we can get the time each person spends in the target area, and then we can count and calculate the time everyone spends in the target area to get the average time. Specifically, we can add up the time each person spends in the target area and divide it by the total number of people to get the average time.

[0063] In step S12, the popularity of the target area is determined based on the historical flow of people and the average stay time.

[0064] It can be understood that historical traffic refers to the change in traffic in the target area over a period of time, which can reflect the attractiveness and activity of the target area; average stay time refers to the average length of time that tourists stay in the target area over a period of time, which can reflect the attractiveness, comfort and tourist satisfaction of the target area. Generally, the higher the historical traffic and the longer the average stay time, the more attractive the services or experiences provided by the target area are, and tourists are more willing to stay and move around here.

[0065] For example, determining popularity based on historical traffic and average stay time can be achieved as follows:

[0066] According to the type, scale, historical data and other factors of the target area, a reasonable threshold of passenger flow and residence time is set as the standard for judging the popularity of the target area. Then, the calculated historical passenger flow is compared with the set passenger flow threshold, and the average residence time is compared with the set residence time threshold. If the historical passenger flow is higher than the passenger flow threshold and the average residence time is higher than the residence time threshold, it means that the target area is highly popular; if the historical passenger flow is lower than the passenger flow threshold or the average residence time is lower than the residence time threshold, it means that the target area is less popular and corresponding measures need to be taken to improve its attractiveness.

[0067] Alternatively, you can determine the popularity of the target area by analyzing the changing trends of historical passenger flow and average length of stay. If the historical passenger flow and average length of stay are on an upward trend, it means that the attractiveness of the target area is increasing; if the historical passenger flow and average length of stay are on a downward trend, it means that the popularity of the target area is low, and timely measures need to be taken to improve it.

[0068] In one implementation, the popularity of a target area is determined based on historical passenger flow and average stay time, including:

[0069] Obtain the area of ​​the target area, and collect the behavior data of each person in the target area and the feedback data on the target area;

[0070] Determine the popularity of the target area based on historical traffic, average dwell time, area, behavioral data and feedback data.

[0071] That is to say, we first need to obtain the area of ​​the target area. It is understandable that the size of the target area will directly affect the target area's capacity and the distribution of passenger flow. A larger target area can accommodate more people and generate more types of behaviors, which will affect passenger flow and popularity.

[0072] At the same time, it is also necessary to collect the behavioral data of each person in the target area, which may include but is not limited to shopping, dining, entertainment, rest, etc. By analyzing these behavioral data, we can understand the popularity of different activities in the target area, as well as people's stay time and consumption habits in these activities.

[0073] In addition, it is necessary to collect feedback data from the target area, which can come from multiple channels such as tourist satisfaction surveys, social media comments, online reviews, etc. By collecting and analyzing these feedback data, we can understand tourists' overall impressions and specific suggestions on the target area, so as to more accurately assess its popularity.

[0074] After obtaining the area, behavior data, and feedback data of the target area, the popularity can be evaluated by combining the historical flow of people and the average length of stay. Specifically, an evaluation model can be constructed, with the area, behavior data, feedback data, historical flow of people, and average length of stay as input features, and the popularity of the target area as the output of the evaluation model. The evaluation model can be implemented using a machine learning algorithm (such as a support vector machine, random forest, etc.) or a deep learning model (such as a neural network), without specific limitation.

[0075] For example, if the target area is a service area within a scenic spot, then first, the total consumption of tourists in the target area can be obtained through the mobile payment records of the scenic spot as behavioral data; the tourists' satisfaction scores for the target area can be collected through the feedback system of the scenic spot as feedback data; and the actual area of ​​each target area can be extracted through the scenic spot information provided by GIS (Geographic Information System) technology.

[0076] Then, the popularity of each target area can be calculated according to the following formula:

[0077]

[0078] Among them, P i represents the popularity of the i-th target area, w i represents the weight of the i-th target area, f i represents the historical flow of people in the i-th target area, a i represents the area of ​​the i-th target area, T i represents the average length of stay of tourists in the i-th target area, c i represents the total consumption of the i-th target area, s i represents the satisfaction score of the i-th service area, α i , β i , η i , σ i They represent the weight coefficients of historical passenger flow, average stay time, total consumption and satisfaction score in evaluating the popularity of the i-th target area, E i represents the activity factor of the i-th target area set by the activity schedule of the scenic spot, λ i Represents the weight coefficient of the activity factor when evaluating the popularity of the i-th target area.

[0079] In step S13, a forecast analysis is performed based on historical passenger flow and popularity to obtain the predicted passenger flow of the target area within the target time period.

[0080] After determining the popularity of the target area, a prediction analysis can be performed based on the historical passenger flow and popularity according to the pre-selected prediction analysis model to obtain the predicted passenger flow in the target time period. Specifically, the historical passenger flow and popularity data can be input in the format required by the prediction analysis model, and then the trained prediction analysis model is used to predict the input data and output the predicted passenger flow value.

[0081] Among them, the prediction and analysis model can adopt a time series model or a regression model, or it can adopt an integrated learning method that combines multiple prediction and analysis models, which is not limited in this application.

[0082] For example, the time series model can predict the flow of people in the future time period based on the time series data of historical flow of people. Commonly used time series models include ARIMA (Autoregressive Integrated Moving Average) model, exponential smoothing model, machine learning model, etc.

[0083] The regression model can predict future traffic flow by taking historical traffic flow and popularity as independent variables and predicted traffic flow as dependent variables, and establishing a mathematical relationship between the independent and dependent variables. Commonly used regression models include linear regression, polynomial regression, ridge regression, lasso regression, etc.

[0084] The ensemble learning method is a method that combines multiple forecasting analysis models to improve the forecast accuracy. In the flow forecasting, the time series model and the regression model can be integrated to make full use of their respective advantages.

[0085] In one implementation, a forecast analysis is performed based on historical passenger flow and popularity to obtain the predicted passenger flow of the target area within the target time period, including:

[0086] Input the historical passenger flow into the pre-trained time series model for forecasting analysis to obtain the reference passenger flow of the target area within the target time period;

[0087] According to the popularity, the reference flow of people is adjusted to obtain the predicted flow of people in the target area during the target time period.

[0088] That is to say, after obtaining the historical traffic and popularity data, the historical traffic needs to be input into the pre-trained time series model for prediction analysis. During the prediction analysis process, the model will output the reference traffic based on the input historical traffic and the corresponding timestamp. Furthermore, the reference traffic can be adjusted according to the popularity to obtain a more accurate prediction result.

[0089] The reference flow can be adjusted by setting an adjustment coefficient, which can be determined according to the popularity of the target area. When the popularity of the target area is high, the adjustment coefficient can be appropriately increased to increase the predicted flow; when the popularity of the target area is low, the adjustment coefficient can be appropriately reduced to reduce the predicted flow.

[0090] By adjusting the reference flow, we can get the predicted flow of people in the target area during the target time period. The predicted flow of people not only takes into account the impact of the historical flow of people in the target area in the past period of time, but also takes into account the changes in the popularity of the target area, so it is more accurate and reliable.

[0091] In one implementation, there are multiple target areas, and the reference flow of people is adjusted according to the popularity to obtain the predicted flow of people in the target area within the target time period, including:

[0092] For each target area, determine the ratio of the corresponding popularity to the reference value, where the reference value is the maximum popularity;

[0093] Based on the ratio, the reference flow rate is adjusted to obtain the predicted flow rate of the target area within the target time period.

[0094] Among them, multiple target areas means not only focusing on a single location or area, but considering the crowd flow prediction of multiple locations or areas at the same time.

[0095] Specifically, it is first necessary to determine a reference value, which is usually the maximum value of the popularity of all target areas. The reference value can be used as a benchmark to compare the popularity of each target area.

[0096] Then, for each target area, its popularity is compared with the reference value to obtain a ratio. This ratio reflects the attractiveness of the target area relative to the most popular target area. Based on the calculated ratio, the reference flow can be adjusted to obtain the predicted flow of each target area during the target time period.

[0097] Specifically, if the ratio of a target area is higher, it means that it is more popular, so the predicted flow of people in the target area can be appropriately increased; conversely, if the ratio of a target area is lower, the predicted flow of people in the target area can be appropriately reduced.

[0098] For example, the reference flow of the i-th target area in the future t-th time period can be expressed as Pf i,t ; Adjust the reference flow rate according to the popularity of the target area, which can be achieved according to the following formula:

[0099]

[0100] Among them, Af i,t represents the adjusted predicted flow rate, MP i represents the maximum value of popularity of all target areas, and ε is a regulatory constant;

[0101] In this embodiment, the predicted flow of people can be combined with the area a of the i-th target area. i , to calculate the predicted tourist density in the future t-th time period, expressed as:

[0102]

[0103] Among them, D i,t It represents the predicted tourist density of the i-th target area in the future t-th time period.

[0104] In one implementation, after performing a forecast analysis based on historical passenger flow and popularity to obtain the predicted passenger flow of the target area within the target time period, the method further includes:

[0105] Determine the capacity limit of the target area based on historical passenger flow;

[0106] When the predicted flow of people exceeds the capacity limit, a flow warning for the target area is triggered.

[0107] That is to say, firstly, it is necessary to collect historical traffic data of the target area and analyze these historical data to understand the traffic change trend and peak value of the target area in different time periods (such as weekdays, weekends, and holidays).

[0108] Then, based on the analysis results of historical passenger flow, a capacity limit value can be set. This value is usually determined based on the maximum carrying capacity of the target area to ensure that when the passenger flow does not reach or exceed this value, the facilities and services in the area can operate normally while ensuring the safety and comfort of tourists. Among them, the capacity limit value may be a fixed value or a dynamic value that changes according to time period or special events.

[0109] After obtaining the predicted flow of people in the target area during the target time period, it is necessary to compare it with the capacity limit value. If the predicted flow of people is lower than the capacity limit value, it indicates that the flow of people in the target area in the future time period is safe and no additional measures are required. If the predicted flow of people exceeds the capacity limit value, a flow warning is triggered.

[0110] After the warning is triggered, a series of response measures need to be taken to reduce the impact of excessive flow of people. These measures may include increasing security personnel, adjusting business hours, guiding the flow of people to disperse, etc., without specific restrictions.

[0111] In one implementation, the capacity limit value of the target area is determined based on the historical flow of people, including:

[0112] According to the historical flow of people, calculate the average and maximum value of the flow of people at each moment in the preset time period;

[0113] The product of the average value and the preset coefficient is used as the capacity limit value of the target area;

[0114] It is determined whether the capacity limit value is less than the maximum value. If not, the preset coefficient is adjusted and the process returns to the step of taking the product of the average value and the preset coefficient as the capacity limit value of the target area.

[0115] That is to say, firstly, the average and maximum values ​​of the flow of people at each moment (such as every hour and every minute) in a preset time period need to be calculated to understand the changing trend and peak value of the flow of people in the target area in different time periods. The preset time period is the time period corresponding to the historical flow of people.

[0116] Then, the average value is multiplied by the preset coefficient to obtain the capacity limit value of the target area, which can reflect the maximum flow of people that the target area can accommodate under normal circumstances. Among them, the preset coefficient is an adjustment factor set according to the specific conditions of the target area (such as facility scale, service capacity, etc.), which is usually determined through various means such as expert evaluation and historical data analysis.

[0117] Then, it is necessary to compare the initially obtained capacity limit value with the maximum value of the historical flow of people in the preset time period. If the capacity limit value is not less than the maximum value, it means that the preset coefficient may be too large, resulting in the capacity limit value being too loose and unable to effectively guarantee the normal operation of facilities in the area and the safety of personnel.

[0118] If the capacity limit value is not less than the maximum value, the preset coefficient needs to be adjusted. Specifically, the preset coefficient value can be appropriately reduced, and then the capacity limit value can be recalculated until the capacity limit value is less than the maximum value. This process may require multiple iterations and optimizations to ensure that the final capacity limit value is neither too strict nor too loose, and can achieve the best effect in actual applications.

[0119] In another embodiment, the predicted tourist density of the target area may also be subject to capacity restrictions. The specific method is the same as the method of limiting the capacity of the predicted passenger flow, which will not be described in detail here.

[0120] For example, if the average flow of people in a preset time period is Af i , the maximum value is Mf i The average tourist density is AD i , the maximum value is MD i , then the passenger flow capacity limit value Lf i and the tourist density capacity limit LD i It can be expressed as:

[0121]

[0122] Among them, k1 and k2 are the preset coefficients corresponding to the flow of people and the density of tourists respectively; according to the set flow capacity limit value Lf i and the tourist density capacity limit LD i , respectively compare the predicted passenger flow and predicted tourist density of the i-th target area in the t-th time period to determine whether the passenger flow and tourist density exceed the standard. If Af i,t >Lf i Then the traffic volume exceeds the limit warning is triggered, indicating that "the target area may have exceeded the capacity"; if D i,t >LD iThis will trigger an alert for excessive tourist density, indicating that "the target area may be exceeding capacity."

[0123] like Figure 2 As shown in FIG. 1 , a system architecture diagram of a method for predicting human flow in a specific embodiment of the present application includes a region division and density monitoring module, a video analysis module, a popularity analysis module, a capacity prediction module, and an intelligent early warning module, wherein:

[0124] The area division and density monitoring module includes an area division unit and a density monitoring unit;

[0125] The regional division unit uses GIS technology and combines the scenic area map to divide the scenic area into multiple target areas according to different functional areas, and sets high-definition cameras and sensors in each target area to collect scenic area data in real time;

[0126] The density monitoring unit uses the YOLO model for human detection, automatically identifies and locates tourists in the monitoring data, counts the detected tourists to obtain the historical flow of each target area, and calculates the tourist density in real time based on the area of ​​the target area.

[0127] The video analysis module includes a video data analysis unit and an information extraction unit;

[0128] The video data analysis unit uses high-definition cameras deployed in the target area to capture monitoring data in real time, identify tourist behaviors in the monitoring data, perform human body detection through the YOLO model, track the movement trajectory of each tourist, and obtain the average stay time of tourists in the target area;

[0129] The information extraction unit obtains the total consumption of tourists in the target area through the mobile payment records of the scenic spot as behavioral data; collects tourists' satisfaction scores on the target area through the feedback system of the scenic spot as feedback data; and extracts the actual area of ​​each target area through the scenic spot information provided by GIS technology.

[0130] The popularity analysis module obtains relevant data from the area division and density monitoring module and the video analysis module to calculate the popularity of each target area, understand the operating status and market potential of each target area, and provide important reference for future planning and development. By adjusting the weight coefficient and activity factor, it can flexibly respond to the characteristics and market demands of different target areas.

[0131] The capacity prediction module includes a passenger flow prediction unit and a tourist density prediction unit;

[0132] The passenger flow prediction unit obtains the historical passenger flow of each target area every day in the past month (including the passenger flow in each time period of each day), builds and trains a time series analysis model, and outputs the predicted passenger flow in a certain time period in the future through the time series analysis model;

[0133] The tourist density prediction unit calculates the predicted tourist density in the future time period by predicting the flow of people and combining it with the area of ​​the target area.

[0134] The intelligent early warning module includes a capacity limitation unit and an over-limit early warning unit;

[0135] The capacity limit unit collects the historical passenger flow and historical tourist density of each target area every day in the past month, calculates the average and maximum values ​​of the historical passenger flow and historical tourist density of each target area, and takes the product of the historical passenger flow and historical tourist density in the past period of time and the preset coefficient as the capacity limit value, and the capacity limit value cannot exceed the maximum value;

[0136] The over-capacity warning unit compares the predicted passenger flow and predicted tourist density in the tth time period predicted by the capacity prediction module according to the set capacity limit value to determine whether there is an over-capacity situation. If the predicted passenger flow exceeds the standard, the passenger flow over-capacity warning is triggered, indicating that "the target area may have an over-capacity situation"; if the predicted tourist density exceeds the standard, the tourist density over-capacity warning is triggered, indicating that "the target area may have an over-capacity situation";

[0137] Furthermore, the passenger flow prediction system can give corresponding prompts based on the exceeding situation, and automatically retrieve surveillance videos of the exceeding areas to display the predicted passenger flow and tourist density in the exceeding areas. Relevant managers can formulate relevant adjustment strategies in advance based on the early warning prompts.

[0138] From the above, it can be seen that the technical solution provided by the embodiment of the present application determines the historical flow of people and the average residence time of the target area by analyzing the monitoring data of the target area, and then evaluates the popularity of the target area based on the historical flow of people and the average residence time, and combines the historical flow of people and the popularity of the target area to predict the predicted flow of people in the target area in the future target time period, thereby achieving accurate prediction of the flow of people in the target area and providing timely data support for resource allocation in the target area.

[0139] The method for predicting the flow of people provided in the embodiment of the present application can be executed by a device for predicting the flow of people. In the embodiment of the present application, a method for predicting the flow of people performed by a device for predicting the flow of people is taken as an example to illustrate the device for predicting the flow of people provided in the embodiment of the present application.

[0140] Figure 3 The figure is a block diagram of a pedestrian flow prediction device according to an exemplary embodiment, comprising:

[0141] An acquisition module 201 is used to acquire monitoring data of a target area, analyze the monitoring data, and determine the historical flow of people and the average stay time of the target area;

[0142] A determination module 202, configured to determine the popularity of the target area based on the historical flow of people and the average stay time;

[0143] The prediction module 203 is used to perform prediction analysis based on the historical passenger flow and the popularity to obtain the predicted passenger flow of the target area within the target time period.

[0144] From the above, it can be seen that the technical solution provided by the embodiment of the present application determines the historical flow of people and the average residence time of the target area by analyzing the monitoring data of the target area, and then evaluates the popularity of the target area based on the historical flow of people and the average residence time, and combines the historical flow of people and the popularity of the target area to predict the predicted flow of people in the target area in the future target time period, thereby achieving accurate prediction of the flow of people in the target area and providing timely data support for resource allocation in the target area.

[0145] The method for predicting the flow of people provided in the embodiment of the present application can be executed by a terminal access terminal. The method for performing terminal access by a terminal access terminal is taken as an example to illustrate the device for the method for predicting the flow of people provided in the embodiment of the present application.

[0146] The flow prediction device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than the terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., and the embodiment of the present application is not specifically limited.

[0147] The crowd flow prediction device provided in the embodiment of the present application can achieve Figure 1 to Figure 2 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0148] Alternatively, if Figure 4 As shown, an embodiment of the present application also provides an electronic device 500, including a processor 501 and a memory 502, wherein the memory 502 stores a program or instruction that can be executed on the processor 501, and when the program or instruction is executed by the processor 501, each step of the above-mentioned pedestrian flow prediction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0149] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0150] Figure 5 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0151] The electronic device 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010 and other components.

[0152] Those skilled in the art will appreciate that the electronic device 1000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1010 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 5 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0153] From the above, it can be seen that the technical solution provided by the embodiment of the present application determines the historical flow of people and the average residence time of the target area by analyzing the monitoring data of the target area, and then evaluates the popularity of the target area based on the historical flow of people and the average residence time, and combines the historical flow of people and the popularity of the target area to predict the predicted flow of people in the target area in the future target time period, thereby achieving accurate prediction of the flow of people in the target area and providing timely data support for resource allocation in the target area.

[0154] It should be understood that in the embodiment of the present application, the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0155] The memory 1009 can be used to store software programs and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0156] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.

[0157] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned pedestrian flow prediction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0158] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0159] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned pedestrian flow prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0160] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0161] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned pedestrian flow prediction method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0162] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0163] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0164] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for predicting human flow, characterized in that: The method comprises: Acquire monitoring data of a target area, analyze the monitoring data, and determine the historical flow of people and average stay time of the target area; Determining the popularity of the target area based on the historical passenger flow and the average stay time; A forecast analysis is performed based on the historical passenger flow and the popularity to obtain a forecast passenger flow of the target area within a target time period.

2. The method for predicting the flow of people according to claim 1, characterized in that: The analyzing the monitoring data to determine the historical flow of people and the average stay time of the target area includes: Performing human body detection on the monitoring data, counting the number of people detected at each moment, obtaining the flow of people at each moment, and taking the flow of people at each moment in a preset time period as the historical flow of people; In the monitoring data, the trajectory of each person detected is tracked to determine the average stay time.

3. The method for predicting the flow of people according to claim 1, characterized in that: The determining the popularity of the target area based on the historical flow of people and the average stay time includes: Obtaining the area of ​​the target area, and collecting the behavior data of each person in the target area and the feedback data on the target area; The popularity of the target area is determined based on the historical flow of people, the average stay time, the area, the behavior data and the feedback data.

4. The method for predicting the flow of people according to claim 1, characterized in that: The predictive analysis based on the historical flow of people and the popularity to obtain the predicted flow of people in the target area within the target time period includes: Inputting the historical passenger flow into a pre-trained time series model for prediction analysis to obtain a reference passenger flow in the target area within a target time period; The reference flow of people is adjusted according to the popularity to obtain the predicted flow of people in the target area within the target time period.

5. The method for predicting the flow of people according to claim 4, characterized in that: There are multiple target areas, and adjusting the reference flow of people according to the popularity to obtain the predicted flow of people for the target area within the target time period includes: For each target area, determining a ratio of the corresponding popularity to a reference value, wherein the reference value is the maximum value of the popularity; Based on the ratio, the reference human flow is adjusted to obtain the predicted human flow of the target area within the target time period.

6. The method for predicting the flow of people according to claim 1, characterized in that: After performing forecast analysis based on the historical flow of people and the popularity to obtain the forecast flow of people in the target area within the target time period, the method further includes: Determining a capacity limit value of the target area according to the historical flow of people; When the predicted passenger flow exceeds the capacity limit value, a passenger flow warning for the target area is triggered.

7. The method for predicting the flow of people according to claim 6, characterized in that: Determining the capacity limit value of the target area according to the historical flow of people includes: According to the historical flow of people, calculate the average and maximum value of the flow of people at each moment in a preset time period; The product of the average value and a preset coefficient is used as the capacity limit value of the target area; Determine whether the capacity limit value is less than the maximum value; if not, adjust the preset coefficient and return to the step of taking the product of the average value and the preset coefficient as the capacity limit value of the target area.

8. A pedestrian flow prediction device, characterized in that: The device comprises: An acquisition module is used to acquire monitoring data of a target area, analyze the monitoring data, and determine the historical flow of people and average stay time of the target area; A determination module, configured to determine the popularity of the target area based on the historical flow of people and the average stay time; The prediction module is used to perform prediction analysis based on the historical passenger flow and the popularity to obtain the predicted passenger flow of the target area within the target time period.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the pedestrian flow prediction method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the pedestrian flow prediction method as described in any one of claims 1-7 are implemented.

Images