Visitor flow adjustment method and device for scenic spot, electronic equipment and storage medium

Abstract

The invention relates to a visitor flow adjusting method for a scenic area. The method comprises the following steps: acquiring visitor data of a positioning device worn on a visitor when the visitor enters the scenic area and data of a camera arranged in the scenic area; tourist data and camera data are imported into a database according to the time sequence; analyzing the tourist data and the camera data, and obtaining a predicted visitor flow rate and a scenic region subarea congestion level; processing the predicted pedestrian flow and the scenic region subarea congestion level to obtain a touring route; and outputting the touring route to a positioning device worn on the tourist so as to adjust the visitor flow rate. The invention further relates to a visitor flow adjusting device for the scenic area, electronic equipment and a storage medium. By using the visitor flow rate adjusting method and device for the scenic area, the electronic equipment and the storage medium provided by the invention, the problem that the experience of tourists is reduced and the potential safety hazard is increased possibly due to the fact that an existing system cannot carry out effective early warning or reasonable shunting under the condition of sudden large flow rate is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of crowd flow management, and in particular to a crowd flow adjustment method, device, electronic equipment and storage medium for a scenic spot. Background Art

[0002] With the rapid development of tourism, the number of tourists received by scenic spots has increased significantly. In order to enhance the tourists' experience and ensure their safety, it is necessary to effectively adjust and divert the flow of people in scenic spots. Traditional scenic spot management methods mainly rely on manual observation, simple diversion or static route planning, which is difficult to respond to changes in the flow of people in real time, and may lead to tourist gathering and congestion, reduce tour efficiency and affect scenic spot operations.

[0003] In recent years, technologies based on positioning devices and video surveillance have been applied to scenic area management, providing support for crowd control by collecting data such as tourist locations and tour speeds. However, existing technologies can usually only monitor a single data indicator or use static analysis models, making it difficult to comprehensively consider tourists' physiological states, real-time distribution, and dynamic route planning needs. This limitation makes it impossible for existing systems to effectively warn or reasonably divert traffic in the event of sudden large traffic, which may lead to a decline in tourist experience and an increase in safety risks.

[0004] Therefore, the prior art has defects and needs to be improved and developed. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and storage medium for adjusting the flow of people in a scenic spot, which is used to solve the problem that the prior art can usually only monitor a single data indicator or adopt a static analysis model, and it is difficult to comprehensively consider the physiological state, real-time distribution and dynamic route planning needs of tourists. This limitation makes it impossible for the existing system to effectively warn or reasonably divert in the case of sudden large flow, which may lead to technical problems such as reduced tourist experience and increased safety hazards.

[0006] According to a first aspect of an embodiment of the present invention, a method for adjusting the flow of people in a scenic spot is provided, comprising:

[0007] Collecting tourist data from the positioning device worn by tourists when entering the scenic spot and camera data arranged in the scenic spot, the tourist data at least includes tourist location, sightseeing speed and physiological state data, and the camera data at least includes tourist distribution and flow information;

[0008] Importing the visitor data and the camera data into a database in time series;

[0009] Analyze the tourist data and the camera data to obtain predicted passenger flow and scenic area zone congestion levels, wherein the scenic area zone congestion levels include level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion;

[0010] Processing the predicted passenger flow and the congestion level of the scenic area division to obtain a tour route;

[0011] The tour route is output to a positioning device worn by tourists to adjust the flow of people.

[0012] Furthermore, the analyzing of the tourist data and the camera data to obtain the predicted flow of people and the congestion level of scenic area zones includes:

[0013] GPS location of the visitor x，y 、The tour speed Speed v The physiological state data HR is subjected to denoising using a sliding window averaging method, wherein the physiological state data HR is the heart rate of the tourist, and the sliding window averaging method formula is:

[0014]

[0015] Among them, t is the total detection time, in seconds;

[0016] k is the detection time interval, the value is 5, and the unit is seconds;

[0017] HR avg is the average heart rate during time t;

[0018] The tour speed is normalized to eliminate the dimension effect, wherein the normalization formula is:

[0019]

[0020] Among them, Speed min is the minimum speed of tourists, in m / s;

[0021] Speed max is the maximum speed of tourists, in m / s;

[0022] Use the LSTM model to predict the flow of people, with the input being the GPS location of the tourists in the past 30 seconds x，y and the tour speed v , the output is the predicted flow of people N pred ;

[0023] According to the predicted flow of people N pred , the scenic area is divided into three levels of scenic area congestion levels, the levels are divided into:

[0024]

[0025] Among them, when Level=0, it means that the congestion level of the scenic area partition is level 0; when Level=1, it means that the congestion level of the scenic area partition is level 1; when Level=2, it means that the congestion level of the scenic area partition is level 2.

[0026] Further, the processing of the predicted passenger flow and the congestion level of the scenic area partition to obtain a tour route includes:

[0027] Additional path costs are assigned to areas where the congestion level of the scenic area is not less than 1:

[0028] g(n)=g(parent)+d(n)+β·Level

[0029] Among them, g(n) represents the total path cost of the current node n, that is, the cumulative cost from the starting node to the current node;

[0030] g(parent) represents the total path cost of the parent node, that is, the cumulative cost from the starting node to the parent node of the current node;

[0031] d(n) represents the path distance between the current node n and the parent node;

[0032] β is the congestion penalty factor, which is 50;

[0033] Level is the congestion level of the scenic area;

[0034] GPS for visitors' current location x，y To the target position P x，y Calculate the total path cost f(n):

[0035] f(n)=g(n)+h(n)

[0036] Among them, h(n) represents the Euclidean distance from the current node to the target node:

[0037]

[0038] Among them, P x Indicates the horizontal coordinate of the target position;

[0039] P y Indicates the vertical coordinate of the target position;

[0040] GPS x Indicates the horizontal coordinate of the target position;

[0041] GPS indicates the vertical coordinate of the target position;

[0042] Traverse the total cost of the path f(n), select the path with the lowest total cost f(n), and the path with the lowest total cost f(n) is the tour route.

[0043] Furthermore, the step of outputting the tour route to a positioning device worn by tourists to adjust the flow of people includes:

[0044] According to the tourist location GPS x，y and the tour speed v Update the predicted flow rate N pred ;

[0045] When the predicted flow of people N pred >400, close the entrance gate of the area in the scenic area and open the predicted flow of people N in the scenic area prea The entrance gates of the area with a congestion level less than 400 will disperse tourists to areas with a congestion level of no more than 1 in the scenic area;

[0046] The tour route is sent to the positioning device worn by the tourists so that the tourists can adjust the route.

[0047] Further, the GPS location of the tourist x，y and the tour speed v Update the predicted flow rate N pred ,include:

[0048] According to the tourist location GPS x，y and the tour speed v Get real-time traffic flow N real , integrating the real-time flow of people N real and the predicted flow of people N pred , get the dynamic flow F combined :

[0049] F combined (t)=0.7·N real (t)+0.3·N pred (t)

[0050] The dynamic flow rate F combined The predicted flow rate N is considered as the updated pred .

[0051] Furthermore, when the predicted flow of people N pred >400, close the entrance gate of the area in the scenic area and open the predicted flow of people N in the scenic area pred The entrance gates of the area with a congestion level of less than 400 will disperse tourists to the areas with a congestion level of no more than 1 in the scenic area, including:

[0052] Import the dynamic flow of people F combined The A* algorithm is used to plan the tour route and avoid the areas where the congestion level of the scenic area partition does not exceed 1.

[0053] Furthermore, the processing of the predicted passenger flow and the congestion level of the scenic area partition to obtain a tour route also includes:

[0054] If the physiological state data HR of the tourist is greater than 120, the destination of the tour route is preferentially planned to be a rest area in the scenic area.

[0055] According to a second aspect of an embodiment of the present invention, there is provided a crowd flow adjustment device for a scenic spot, comprising:

[0056] A collection module is used to collect tourist data from the positioning device worn by tourists when entering the scenic area and camera data arranged in the scenic area, wherein the tourist data at least includes tourist location, sightseeing speed and physiological state data, and the camera data at least includes tourist distribution and flow information;

[0057] An import module, used for importing the visitor data and the camera data into a database in time series;

[0058] An analysis module is used to analyze the tourist data and the camera data to obtain predicted passenger flow and congestion levels of scenic area zones, wherein the congestion levels of scenic area zones include level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion;

[0059] A processing module, used for processing the predicted passenger flow and the congestion level of the scenic area partition to obtain a sightseeing route;

[0060] The output module is used to output the tour route to a positioning device worn by tourists to adjust the flow of people.

[0061] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method for adjusting the flow of people in a scenic spot.

[0062] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for adjusting the flow of people in a scenic spot is implemented.

[0063] Beneficial effects:

[0064] It can be seen from the above scheme that the present invention provides a method, device, electronic device and storage medium for adjusting the flow of people in scenic spots, aiming to solve the problems existing in the prior art, such as insufficient data collection dimensions, poor accuracy of prediction models, single diversion methods, insufficient personalization considerations and poor processing timeliness, and proposes a method and related device for adjusting the flow of people in scenic spots based on multi-source data fusion and dynamic programming algorithms. By collecting multi-dimensional data provided by devices worn by tourists and cameras in scenic spots, combined with machine learning prediction models, path optimization algorithms and real-time dynamic update mechanisms, accurate prediction and intelligent diversion of the flow of people in scenic spots can be achieved, effectively reducing congestion, improving tourist experience, and improving the overall tour efficiency and management efficiency of scenic spots.

[0065] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, may be considered to be part of the inventive subject matter of the present disclosure, provided such concepts are not mutually inconsistent.

[0066] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are not drawn to scale according to actual reference objects. In the accompanying drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For the sake of clarity, not every component is labeled in each figure. Now, embodiments of various aspects of the present invention will be described by way of example and with reference to the accompanying drawings, in which:

[0068] Figure 1 This is a flow chart of a method for adjusting the flow of people in a scenic spot according to an embodiment of the present application.

[0069] Figure 2 A flowchart of analyzing tourist data and camera data to obtain predicted passenger flow and congestion levels of scenic area zones in an embodiment of the present application.

[0070] Figure 3 This is a flowchart of processing predicted passenger flow and congestion levels of scenic area zones to obtain a tour route in an embodiment of the present application.

[0071] Figure 4 This is a flow chart of outputting a tour route to a positioning device worn by tourists to adjust the flow of people in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be the common meaning understood by people with general skills in the field to which the present invention belongs.

[0073] The words "first", "second" and similar terms used in the patent specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular form "a" or "an" shall not be construed as "a" or "an";

[0074] The words “a”, “an”, “the” and the like do not denote a limitation of quantity, but rather denote the presence of at least one.

[0075] The words "include" or "comprises" and the like mean that the elements or objects appearing before "includes" or "comprises" include the features, wholes, steps, operations, elements and / or components listed after "includes" or "comprises", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0076] In the existing technology, usually only a single data indicator can be monitored or a static analysis model is used, which makes it difficult to comprehensively consider the physiological state, real-time distribution and dynamic route planning needs of tourists. This limitation makes it impossible for the existing system to effectively warn or reasonably divert traffic in the case of sudden large traffic, which may lead to a decline in tourist experience and an increase in safety hazards.

[0077] In view of this, an embodiment of the present invention provides a method for adjusting the flow of people in a scenic spot, referring to Figure 1 ,include:

[0078] Step S102: collecting tourist data from the positioning device worn by tourists when entering the scenic spot and camera data arranged in the scenic spot, the tourist data at least includes tourist location, sightseeing speed and physiological state data, and the camera data at least includes tourist distribution and flow information;

[0079] Step S104: Importing visitor data and camera data into the database in time series;

[0080] Step S106: Analyze the tourist data and camera data to obtain the predicted passenger flow and the congestion level of the scenic area, where the congestion level of the scenic area includes level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion;

[0081] Step S108: Process the predicted passenger flow and the congestion level of the scenic area to obtain a tour route;

[0082] Step S110: outputting the tour route to the positioning device worn by the tourists to adjust the flow of people.

[0083] The embodiment of the present invention provides a method for adjusting the flow of people in a scenic spot, which covers the collection of tourist and camera data, data analysis, crowd flow prediction, congestion level classification, and a complete process of dynamically planning tour routes based on prediction and classification results. It has the following advantages: Comprehensive data collection capabilities: Through the combination of tourist positioning devices and cameras in the scenic area, multi-dimensional data including location, speed, physiological state and distribution information is obtained, providing a reliable basis for subsequent analysis. Accurate congestion prediction: Using the method of predicting crowd flow and congestion level classification, potential congested areas can be effectively identified. Dynamic adjustment mechanism: Based on real-time analysis results and tour route push functions, tourists are guided to be diverted to reasonable areas, which helps to balance the distribution of people in the scenic area.

[0084] The data and distribution information of tourists are obtained through positioning devices and cameras. The collected data include the location of tourists, such as GPS coordinates, speed, physiological status, such as heart rate and crowd distribution characteristics. The above data are stored in the database in time series to ensure the traceability and consistency of the data. The analysis algorithm is used to predict the flow of people and divide the regional congestion level into three levels. The tour route is dynamically generated based on the prediction results and pushed to tourists through the positioning device to adjust the tourist route and achieve the effect of optimizing the distribution of people flow.

[0085] In some embodiments, the visitor data and camera data are analyzed to obtain the predicted flow of people and the congestion level of the scenic area. Figure 2 ,include:

[0086] Step S1061: GPS the tourist's location x，y , browsing speed v And the physiological state data HR is denoised using the sliding window averaging method, where the physiological state data HR is the heart rate of the tourists, and the sliding window averaging method formula is:

[0087]

[0088] Among them, t is the total detection time, in seconds;

[0089] k is the detection time interval, the value is 5, and the unit is seconds;

[0090] HR avg is the average heart rate during time t.

[0091] This step can filter out instantaneous fluctuation noise and retain the true heart rate trend, which can be used to provide tourists with physically suitable tour routes in the future.

[0092] Step S1062: normalize the tour speed to eliminate the dimension effect, wherein the normalization formula is:

[0093]

[0094] Among them, Speed min is the minimum speed of tourists, in m / s;

[0095] Speed max is the maximum speed of tourists, in m / s.

[0096] After normalization, the data is converted to the interval [0, 1] to facilitate subsequent calculations.

[0097] Step S1063: Use the LSTM model to predict the flow of people, with the input being the GPS location of tourists in the past 30 seconds x，y and tour speed v , the output is the predicted flow of people N pred ;

[0098] Step S1064: According to the predicted flow of people N pred , the scenic area is divided into three levels of scenic area congestion levels, the levels are divided into:

[0099]

[0100] Among them, when Level = 0, it means that the congestion level of the scenic area is level 0; when Level = 1, it means that the congestion level of the scenic area is level 1; when Level = 2, it means that the congestion level of the scenic area is level 2.

[0101] The location and speed of tourists in the past 30 seconds are used as input to predict the flow of people in the future time period. During the model training process, the input time series length is set to 30 seconds, and the output is the predicted value for the next 5 seconds. The time input in step S1063 is 30 seconds. In some other embodiments, the viewing areas, channels, etc. in the scenic area can be identified based on the camera data, and different seconds can be set according to the area where the tourists are located. For example, 30 seconds can be set to a longer time in the viewing area. In the channel, because it is convenient for tourists to pass, it can be set to a shorter time based on 30 seconds, thereby optimizing the data input into the LSTM model and improving the accuracy of predicting the flow of people. The output predicted flow of people N pred If it is for real-time dynamic statistics, you can choose the number of people in the area within the rated time. If it is for a separate crowding analysis, you can also choose the number of people in the rated area. If it is for long-term statistics, you can also choose the total number of people.

[0102] The heart rate data is denoised and the tour speed is normalized by the sliding window averaging method. The flow of people is predicted based on the LSTM model, and the congestion level is divided according to the predicted value. Therefore, it has the following advantages: Improve data accuracy: Denoising eliminates the instantaneous interference that may occur in data collection, and normalization eliminates the dimensional effect, providing a consistent input data format for subsequent analysis. Prediction model used: The use of the LSTM model improves the timeliness and reliability of the flow of people prediction. Classification of congestion: The congestion level is divided by predicting the flow of people, which provides a clear basis for planning tour routes.

[0103] In some embodiments, the predicted passenger flow and the congestion level of the scenic area are processed to obtain the tour route, and the reference Figure 3 ,include:

[0104] Step S1081: assigning an additional path cost to the area where the congestion level of the scenic area is not less than 1:

[0105] g(n)=g(parent)+d(n)+β·Level

[0106] Among them, g(n) represents the total path cost of the current node n, that is, the cumulative cost from the starting node to the current node;

[0107] g(parent) represents the total path cost of the parent node, that is, the cumulative cost from the starting node to the parent node of the current node;

[0108] d(n) represents the path distance between the current node n and the parent node;

[0109] β is the congestion penalty factor, which is 50;

[0110] Level is the congestion level of the scenic area.

[0111] Assumption: The path cost from the starting point to the parent node of the current node is: g(parent) = 100m;

[0112] The distance between the current node and the parent node: d(n) = 30m;

[0113] The current scenic area congestion level is Level = 2;

[0114] The total path cost is calculated as: g(n) = 100 + 30 + 50·2 = 230 m. At this time, the severely congested area adds an additional path cost of 100 m, and the total path cost reaches 230 m, which makes the path tend to choose other paths less than 230 m as the optimal choice.

[0115] Step S1082: GPS the current location of the tourist x，y To the target position P x，y Calculate the total path cost f(n):

[0116] f(n)=g(n)+h(n)

[0117] Among them, h(n) represents the Euclidean distance from the current node to the target node:

[0118]

[0119] Among them, P x Indicates the horizontal coordinate of the target position;

[0120] P y Indicates the vertical coordinate of the target position;

[0121] GPS x Indicates the horizontal coordinate of the target position;

[0122] GPS indicates the vertical coordinate of the target position;

[0123] Step S1083: traverse the total path cost f(n), select the path with the lowest total path cost f(n), and the path with the lowest total path cost f(n) is the tour route.

[0124] In some other embodiments, after traversing the total path cost f(n), the opening and closing status of the channels in the scenic area can be identified in real time through camera data. After superimposing the opening and closing status of the channels in the scenic area obtained by the camera and the total path cost f(n), the path available for passage is obtained, and then the total path cost f(n) with the lowest value is selected to improve the efficiency of adjusting the flow of people.

[0125] By adding path costs, the congested areas are penalized so that a tour route containing the optimal path can be dynamically planned. Therefore, it has the following advantages: Reduce the impact of congestion: By assigning additional path costs to areas with high congestion levels, the planned tour routes can avoid congested areas as much as possible. Efficient path planning: Based on the comprehensive evaluation of path costs based on Euclidean distance and congestion level, the route with the lowest total cost is selected to achieve optimized tourist guidance. High flexibility: The dynamic planning method can adjust the path according to the actual situation and adapt to the changing scenic environment.

[0126] In some embodiments, the tour route is output to the positioning device worn by the tourists to adjust the flow of people, referring to Figure 4 ,include:

[0127] Step S1101: According to the tourist's GPS location x，y and tour speed v Update predicted traffic flow N pred ;

[0128] Step S1102: When the predicted flow of people N pred When the number of people is greater than 400, the entrance gate of the scenic area is closed and the predicted flow of people N in the scenic area is opened. pred The entrance gates of the area with a congestion level less than 400 will disperse tourists to areas with a congestion level of no more than 1 in the scenic area;

[0129] Step S1103: Send the tour route to the positioning device worn by the tourist so that the tourist can adjust the route.

[0130] A mechanism is proposed to adjust the gate opening status of scenic spots based on real-time predicted passenger flow, and the adjusted tour route is sent to the tourist positioning device. Therefore, it has the following advantages: Dynamic diversion mechanism: The gate status of scenic spots is adjusted in real time according to the passenger flow, which can effectively disperse the flow of tourists and avoid local congestion. Rapid response capability: It realizes timely guidance of high-congestion areas and improves the overall traffic efficiency of scenic spots. Intuitive guidance: The adjusted tour route is directly pushed to the tourist positioning device, which is convenient for tourists to receive information.

[0131] In some embodiments, based on the visitor's GPS location x，y and tour speed v Update predicted traffic flow N pred ,include:

[0132] Step S10631: According to the tourist location GPS x，y and tour speed v Get real-time traffic flow N real , integrating real-time traffic flow N real and predicted flow rate N pred , get the dynamic flow Fcombined :

[0133] F combined (t)=0.7·N real (t)+0.3·N pred (t)

[0134] Step S10632: Dynamic human flow F combined Considered as the updated predicted flow rate N pred .

[0135] By integrating real-time and predicted traffic, the distribution of traffic in scenic spots is updated dynamically, and the updated results are used to guide subsequent route planning. Therefore, it has the following advantages: Data fusion enhancement: Combining real-time and predicted data makes the distribution of traffic more accurate. Improve planning accuracy: Dynamically adjust the prediction results to reflect real-time changes and improve the rationality of the tour route. Real-time feedback mechanism: The updated prediction data provides more reliable input for subsequent route planning.

[0136] In some embodiments, when the predicted flow rate N pred When the number of people is greater than 400, the entrance gate of the scenic area is closed and the predicted flow of people N in the scenic area is opened. pred The entrance gates of the area with a congestion level of less than 400 will disperse tourists to the areas with a congestion level of no more than 1 in the scenic area, including:

[0137] Import dynamic traffic flow F combined The A* algorithm is used to plan the tour route and avoid areas where the congestion level of the scenic area does not exceed 1.

[0138] It is proposed to use the A* algorithm to plan tour routes based on dynamic passenger flow data to avoid congested areas. Therefore, it has the following advantages: Accurate congestion avoidance function: The A* algorithm comprehensively considers dynamic passenger flow and congestion level, and the planned path can effectively bypass high congestion areas. Optimized path search: The heuristic search mechanism of the algorithm improves planning efficiency. Wide range of applications: It can quickly find the optimized path under different congestion conditions.

[0139] In some embodiments, processing the predicted passenger flow and the congestion level of the scenic area partition to obtain the tour route also includes:

[0140] If the tourist's physiological status data HR>120, the priority destination of the tour route will be the rest area within the scenic area.

[0141] The function of planning rest areas based on tourists' physiological status has been added to further enhance the tourists' experience. Therefore, it has the following advantages: Enhanced comfort: For tourists with higher heart rates, rest areas are recommended first to pay attention to tourists' health needs. Differentiated services: Provide personalized tour guidance according to different tourist status to improve service level. Safety guarantee: When tourists are in abnormal status, they are guided to safe areas first to reduce safety hazards.

[0142] Another embodiment of the present invention further provides a crowd flow adjustment device for a scenic spot, comprising:

[0143] A collection module is used to collect tourist data from the positioning device worn by tourists when entering the scenic area and camera data arranged in the scenic area. The tourist data at least includes the tourist location, sightseeing speed and physiological state data, and the camera data at least includes the tourist distribution and flow information;

[0144] Import module, used to import visitor data and camera data into the database in time series;

[0145] An analysis module is used to analyze tourist data and camera data to obtain predicted passenger flow and scenic area zone congestion levels, where the scenic area zone congestion levels include level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion;

[0146] A processing module is used to process the predicted passenger flow and the congestion level of the scenic area to obtain the tour route;

[0147] The output module is used to output the tour route to the positioning device worn by the tourists to adjust the flow of people.

[0148] Another embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements a method for adjusting the flow of people in a scenic spot when executed by the processor.

[0149] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the data processing device of the gateway, and uses various interfaces and lines to connect various parts of the data processing device of the entire gateway.

[0150] Another embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, a method for adjusting the flow of people in a scenic spot is implemented.

[0151] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory is preferably but not limited to a high-speed random access memory, for example, it may also be a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may also optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0152] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing related hardware through a computer program, which can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0153] In summary, a method, device, electronic device and storage medium for adjusting the flow of people in a scenic area provided by the present invention are used to obtain data such as the real-time location, tour speed and physiological state of tourists through positioning devices worn on tourists, such as smart bracelets, smart watches, etc., and at the same time, combined with cameras arranged inside the scenic area, capture the distribution and flow information of tourists to form a panoramic data collection network. The heart rate data is denoised by the sliding window averaging method to ensure that the analysis results are accurate and reliable, and the tourist tour speed is normalized to eliminate the differences between different data dimensions. The location and speed of tourists are predicted based on the LSTM model to obtain the future flow of people; the congestion conditions in different areas of the scenic area are graded by dividing the congestion levels by zoning. Combined with the congestion level information, additional path costs are imposed on high congestion areas, and the tourist tour routes are dynamically planned by the A* algorithm to ensure that tourists are diverted to low congestion areas. When the regional flow of people exceeds the set threshold, the flow of tourists is guided by closing or opening the regional entrance gate; and the future distribution is dynamically updated by combining the real-time flow of people with the predicted flow of people. It can achieve accurate prediction and intelligent diversion of scenic spot flow, effectively reduce congestion, enhance tourist experience, and improve the overall tour efficiency and management effectiveness of the scenic spot.

[0154] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. A method for adjusting the flow of people in a scenic area, characterized in that: include: Collecting tourist data from the positioning device worn by tourists when entering the scenic spot and camera data arranged in the scenic spot, the tourist data at least includes tourist location, sightseeing speed and physiological state data, and the camera data at least includes tourist distribution and flow information; Importing the visitor data and the camera data into a database in time series; Analyze the tourist data and the camera data to obtain predicted passenger flow and scenic area zone congestion levels, wherein the scenic area zone congestion levels include level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion; Processing the predicted passenger flow and the congestion level of the scenic area division to obtain a tour route; The tour route is output to a positioning device worn by tourists to adjust the flow of people.

2. A method for adjusting the flow of people in a scenic spot according to claim 1, characterized in that: The analyzing the tourist data and the camera data to obtain predicted passenger flow and congestion level of scenic area zones includes: GPS location of the visitor x，y 、The tour speed Speed v The physiological state data HR is subjected to denoising using a sliding window averaging method, wherein the physiological state data HR is the heart rate of the tourist, and the sliding window averaging method formula is: Among them, t is the total detection time, in seconds; k is the detection time interval, the value is 5, and the unit is seconds; HR avg is the average heart rate during time t; The tour speed is normalized to eliminate the dimension effect, wherein the normalization formula is: Among them, Speed min is the minimum speed of tourists, in m / s; Speed max is the maximum speed of tourists, in m / s; Use the LSTM model to predict the flow of people, with the input being the GPS location of the tourists in the past 30 seconds x,y and the tour speed v , the output is the predicted flow of people N pred ; According to the predicted flow rate N pred , the scenic area is divided into three levels of scenic area congestion levels, the levels are divided into: Among them, when Level=0, it means that the congestion level of the scenic area partition is level 0; when Level=1, it means that the congestion level of the scenic area partition is level 1; when Level=2, it means that the congestion level of the scenic area partition is level 2.

3. A method for adjusting the flow of people in a scenic spot according to claim 1, characterized in that: The processing of the predicted passenger flow and the congestion level of the scenic area partition to obtain a tour route includes: Additional path costs are assigned to areas where the congestion level of the scenic area is not less than 1: g(n)=g(parent)+d(n)+β·Level Among them, g(n) represents the total path cost of the current node n, that is, the cumulative cost from the starting node to the current node: g(parent) represents the total path cost of the parent node, that is, the cumulative cost from the starting node to the parent node of the current node: d(n) represents the path distance between the current node n and the parent node; β is the congestion penalty factor, which is 50; Level is the congestion level of the scenic area: GPS for visitors' current location x,y To the target position P x，y Calculate the total path cost f(n): f(n)=g(n)+h(n) Among them, h(n) represents the Euclidean distance from the current node to the target node: Among them, P x Indicates the horizontal coordinate of the target position; P y Indicates the vertical coordinate of the target position; GPS x Indicates the horizontal coordinate of the target position; GPS indicates the vertical coordinate of the target position; Traverse the total cost of the path f(n), select the path with the lowest total cost f(n), and the path with the lowest total cost f(n) is the tour route.

4. A method for adjusting the flow of people in a scenic spot according to claim 2, characterized in that: Outputting the tour route to a positioning device worn by tourists to adjust the flow of people includes: According to the tourist location GPS x,y and the tour speed v Update the predicted flow rate N pred : When the predicted flow of people N pred >400, close the entrance gate of the area in the scenic area and open the predicted flow of people N in the scenic area pred The entrance gates of the area with a congestion level less than 400 will disperse tourists to areas with a congestion level of no more than 1 in the scenic area; The tour route is sent to the positioning device worn by the tourists so that the tourists can adjust the route.

5. A method for adjusting the flow of people in a scenic spot according to claim 4, characterized in that: According to the tourist location GPS x,y and the tour speed v Update the predicted flow rate N pred ,include: According to the tourist location GPS x,y and the tour speed v Get real-time traffic flow N real , integrating the real-time flow of people N real and the predicted flow of people N pred , get the dynamic flow F combined : F combined (t)=0.7·N real (t)+0.3·N pred (t) The dynamic flow rate F combined The predicted flow rate N is considered as the updated pred .

6. A method for adjusting the flow of people in a scenic spot according to claim 5, characterized in that: When the predicted flow of people N pred >400, close the entrance gate of the area in the scenic area and open the predicted flow of people N in the scenic area pred The entrance gates of the area with a congestion level of less than 400 will disperse tourists to the areas with a congestion level of no more than 1 in the scenic area, including: Import the dynamic flow of people F combined The A* algorithm is used to plan the tour route and avoid the areas where the congestion level of the scenic area partition does not exceed 1.

7. A method for adjusting the flow of people in a scenic spot according to claim 2, characterized in that: The processing of the predicted passenger flow and the congestion level of the scenic area partition to obtain a tour route also includes: If the physiological status data HR of the tourist is greater than 120, the destination of the tour route is preferentially planned to be a rest area in the scenic area.

8. A crowd flow adjustment device for a scenic spot, characterized in that: include: A collection module is used to collect tourist data from the positioning device worn by tourists when entering the scenic area and camera data arranged in the scenic area, wherein the tourist data at least includes tourist location, sightseeing speed and physiological state data, and the camera data at least includes tourist distribution and flow information; An import module, used for importing the visitor data and the camera data into a database in time series; An analysis module is used to analyze the tourist data and the camera data to obtain predicted passenger flow and congestion levels of scenic area zones, wherein the congestion levels of scenic area zones include level 0, level 1 and level 2, where level 0 indicates no congestion, level 1 indicates mild congestion, and level 2 indicates severe congestion; A processing module, used for processing the predicted passenger flow and the congestion level of the scenic area partition to obtain a sightseeing route; The output module is used to output the tour route to a positioning device worn by tourists to adjust the flow of people.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the method for adjusting the flow of people in a scenic spot as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for adjusting the flow of people in a scenic spot as described in any one of claims 1 to 7 is implemented.

Images