Detection method and related equipment for scenic spot passenger flow

Abstract

The present application discloses a method for detecting the passenger flow of a scenic spot and related equipment, the method mainly comprising: obtaining real-time visitor flow information of a first scenic spot, wherein the scenic spot includes multiple scenic spots; calculating the visitor transfer probability according to preset scenic spot analysis data and a preset transfer probability formula, wherein the visitor transfer probability is a probability of characterizing the probability of going from a second scenic spot to the first scenic spot; determining the path visitor flow according to the real-time visitor flow information and the visitor transfer probability, wherein the path visitor flow is the number of visitors in the path from the second scenic spot to the first scenic spot; determining the scenic spot passenger flow according to the multiple path visitor flows. Compared with the prior art, the method for detecting the passenger flow of a scenic spot disclosed in the present invention can solve the problem of low accuracy of the detection result caused by inaccurate positioning information or when the user does not provide positioning information during the conventional scenic spot passenger flow detection process.

Description

Technical Field

[0001] The present application relates to the field of display technology, and in particular to a method for detecting the passenger flow of a scenic spot. Background Art

[0002] As people's living standards improve, they like to visit different scenic spots in various places during holidays. Therefore, the number of visitors to various scenic spots is increasing year by year. However, since the carrying capacity of scenic spots is limited, in order to ensure the safety and experience of visitors, each scenic spot will conduct a passenger flow test to ensure timely adjustment of the number of visitors entering the scenic spot.

[0003] Generally, in most scenic spots, the conventional method of detecting the flow of tourists in scenic spots is to track the location of each visitor after authenticating the visitors entering the scenic spot, and count the number of visitors in different scenic spots in the scenic spot to achieve the detection effect of the flow of tourists in the scenic spot. However, in actual applications, the conventional method of detecting the flow of tourists in scenic spots requires visitors to provide positioning information. Once the visitor refuses to provide positioning information, or the visitor's positioning information is abnormal due to network reasons, the accuracy of the current detection method will be affected, making the accuracy of the current conventional method of detecting the flow of tourists in scenic spots low. Summary of the invention

[0004] The present application provides a method and related equipment for detecting the visitor flow in a scenic spot, which can get rid of the reliance on the location information of visitors, thereby solving the problem of low accuracy of the detection results caused by inaccurate location information or the user not providing location information during the conventional scenic spot visitor flow detection process, and can improve the accuracy.

[0005] The present application provides a method for detecting the passenger flow of a scenic spot, including:

[0006] Acquire real-time visitor flow information of a second scenic spot, where the scenic spot includes a plurality of scenic spots;

[0007] Calculate the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula, wherein the visitor transfer probability represents the probability of going from the second scenic spot to the first scenic spot;

[0008] Determine a path visitor flow according to the real-time visitor flow information and the visitor transfer probability, wherein the path visitor flow is the number of visitors in the path from the second scenic spot to the first scenic spot;

[0009] The visitor flow of the scenic spot is determined according to the visitor flow of the multiple paths.

[0010] In an optional embodiment, the calculating the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula includes:

[0011] Determining analysis parameters according to the preset scenic spot analysis data, wherein the analysis parameters are obtained after the preset scenic spot analysis data is calculated by a random utility algorithm;

[0012] Determining the number of paths from the first scenic spot to the second scenic spot;

[0013] The visitor transfer probability is calculated according to the analysis parameters, the number of paths and the preset transfer probability formula.

[0014] In an optional embodiment, the preset transition probability formula includes a softmax formula;

[0015] The calculating the visitor transfer probability according to the analysis parameter, the number of paths and the preset transfer probability formula includes:

[0016] Obtaining analysis parameters of each path from the second scenic spot to the first scenic spot;

[0017] The visitor transfer probability is calculated according to the analysis parameters of each path, the number of paths and the softmax formula.

[0018] In an optional embodiment, determining the analysis parameters according to the preset scenic spot analysis data includes:

[0019] Constructing an initial selection utility formula according to the random utility algorithm, wherein the selection utility formula is constructed according to a preset error, a browsing factor, and a corresponding browsing factor coefficient;

[0020] According to the preset scenic spot analysis data and the initial selection utility formula, the actual value of the browsing factor coefficient corresponding to each browsing factor and the actual value of the preset error are obtained through fitting calculation;

[0021] Determining a selection utility formula corresponding to the initial selection utility formula according to the actual value of the browsing factor and the actual value of the preset error;

[0022] According to the selection utility formula and each of the scenic spots, an analysis parameter corresponding to each of the scenic spots is calculated.

[0023] In an optional embodiment, constructing an initial selection utility formula according to the random utility algorithm includes:

[0024] Acquire preset scenic spot analysis data, wherein the preset scenic spot analysis data is the data recorded in the history when the scenic spot visitors browse the scenic spot;

[0025] Setting corresponding scenic spot browsing factors according to the scenic spot, wherein the scenic spot browsing factors include at least one of a path factor, a scenic spot factor and a visitor factor, the path factor is used to characterize route-related factors when visitors browse, the scenic spot factor is used to characterize factors related to the scenic spot itself, and the visitor factor is used to characterize the situation of the scenic spot when being browsed by visitors;

[0026] The initial selection utility formula is constructed according to the scenic spot browsing factors and a random utility algorithm.

[0027] In an optional embodiment, the path factor includes: a distance factor and an adjacent factor; the distance factor is used to characterize the distance between the first scenic spot and the second scenic spot; the adjacent factor is used to characterize whether the first scenic spot is adjacent to the second scenic spot;

[0028] The scenic spot factors include: scenic spot type factor, scenic spot feature factor, scenic spot area factor, and scenic spot location factor; the scenic spot type factor is used to characterize the type of the scenic spot, the scenic spot feature factor is used to characterize whether the scenic spot has browsing features, the scenic spot area factor is used to characterize the level of the scenic spot area size, and the scenic spot location factor is used to characterize whether the scenic spot is located at the exit of the scenic spot;

[0029] The visitor factors include: a visit duration factor, a visit crowding factor, a visit queue factor and a re-browsing factor; the visitor duration factor is used to characterize the duration of the visit to the attraction, the visit crowding factor is used to characterize the degree of crowding of the attraction, the visit queue factor is used to characterize the queuing duration of the attraction, and the re-browsing factor is used to characterize whether the attraction is visited again.

[0030] In an optional embodiment, determining the path visitor flow according to the real-time visitor flow information and the visitor transfer probability includes:

[0031] Acquire visitor traffic according to the real-time visitor traffic information;

[0032] The path visitor flow is obtained by performing a product operation on the visitor flow and the visitor transfer probability.

[0033] In a second aspect, an embodiment of the present invention further provides a device for detecting the flow of tourists in a scenic spot, comprising:

[0034] An acquisition unit, used to acquire real-time visitor flow information of a second scenic spot, wherein the scenic spot includes a plurality of scenic spots;

[0035] A calculation unit, used to calculate the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula, wherein the visitor transfer probability represents the probability of going from the second scenic spot to the first scenic spot;

[0036] A first determining unit, configured to determine a path visitor flow rate according to the real-time visitor flow rate information and the visitor transfer probability, wherein the path visitor flow rate is the number of visitors in a path from the second scenic spot to the first scenic spot;

[0037] The second determining unit is used to determine the scenic spot visitor flow according to the visitor flow of the multiple paths.

[0038] In a third aspect, the present invention provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for detecting the passenger flow of a scenic spot as described in any one of the first aspects above.

[0039] In a fourth aspect, the present invention provides a device comprising at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; and the processor is used to call program instructions in the memory to execute a method for detecting the passenger flow of a scenic spot as described in any one of the first aspects above.

[0040] An embodiment of the present invention provides a method for detecting the visitor flow of a scenic spot. First, real-time visitor flow information of a second scenic spot is obtained, and then the visitor transfer probability is calculated according to preset scenic spot analysis data and a preset transfer probability formula. Then, the path visitor flow is determined according to the real-time visitor flow information and the visitor transfer probability. Finally, the scenic spot visitor flow is determined according to multiple path visitor flows, thereby realizing the detection of the scenic spot visitor flow. In the above scheme, since the scenic area includes multiple attractions, and the visitor transfer probability is a probability of characterizing the probability of going from the second attraction to the first attraction, the path visitor flow is the number of visitors in the path from the second attraction to the first attraction. This ensures that in the present invention, in the process of determining the path visitor flow based on the real-time visitor flow information and the visitor transfer probability, there is no need to collect and count the positions of each visitor, but the flow situation in the path from the second attraction to the first attraction can be calculated based only on the real-time visitor flow information of the second attraction. Therefore, in the process of determining the scenic spot passenger flow based on multiple path visitor flows, there is no need to obtain the visitor positioning information, and the passenger flow of each path can be directly calculated based on the calculation method, so there is no need to rely on the positioning information, which avoids the problem of inaccurate scenic spot passenger flow detection results due to inaccurate positioning information or the visitor not providing positioning information, and can improve the accuracy of the detection results. In addition, since the only data that needs to be collected in real time in the above scheme is the real-time visitor flow of the second scenic spot, that is to say, only monitoring equipment for collecting real-time visitor flow needs to be set up at the second scenic spot in the scenic area. Compared with the prior art, there is no need to verify the identity of the visitor and track each visitor, which can significantly reduce the amount of data required to be collected during the detection process, and reduce the occupation and consumption of system resources during the implementation of the method described in the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a method for detecting the passenger flow of a scenic spot provided in an embodiment of the present application;

[0042] Figure 2 A block diagram of a device for detecting the flow of tourists in a scenic spot provided in an embodiment of the present application;

[0043] Figure 3 A block diagram of the composition of a device for detecting the passenger flow in a scenic spot provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0045] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment 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 equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0046] As people's living standards improve, people are increasingly fond of visiting and playing in different scenic spots around the country during holidays. Therefore, the number of visitors to each scenic spot is also increasing year by year. However, since the carrying capacity of the scenic spot is limited, in order to ensure the safety and sightseeing experience of visitors, each scenic spot will conduct a detection of the scenic spot passenger flow to ensure that the number of visitors entering the scenic spot is adjusted in time. Usually, in most scenic spots, the conventional method for detecting the passenger flow of scenic spots is generally to track the location of each visitor after authenticating the visitors entering the scenic spot, and to count the number of visitors in different scenic spots in the scenic spot to achieve the detection effect of the passenger flow of the scenic spot. However, in actual applications, the conventional method for detecting the passenger flow of scenic spots requires visitors to provide positioning information. Once the visitor refuses to provide positioning information, or the visitor has abnormal positioning information due to network and other reasons, the accuracy of the current detection method will be affected, making the accuracy of the current conventional method for detecting the passenger flow of scenic spots low.

[0047] In view of this, the embodiment of the present invention provides a method for detecting the flow of tourists in a scenic spot, which can get rid of the reliance on the location information of visitors, thereby solving the problem of low accuracy of the detection results caused by inaccurate location information or when the user does not provide location information in the conventional detection process of the flow of tourists in the scenic spot, and can improve the accuracy. Specifically, the method for detecting the flow of tourists in a scenic spot according to the embodiment of the present invention can be as follows Figure 1 shown, including:

[0048] 101. Obtain real-time visitor flow information of the second scenic spot.

[0049] Wherein, the scenic area includes multiple scenic spots. In this embodiment, the real-time visitor flow information can be obtained by an image acquisition device or an information statistics device preset in the second scenic spot, wherein the image acquisition device can be a camera, and the information statistics device can be a routing device providing WIFI. Of the two, the former can be used to obtain the visitor browsing situation of the second scenic spot based on the image, and based on this, it can be determined as real-time visitor flow information; the latter can be used to determine the real-time visitor flow information based on the WIFI connection situation. Here, the method for obtaining the real-time visitor flow information includes but is not limited to the above-mentioned method, and it can also be selected based on the needs of the user during the specific execution process.

[0050] 102. Calculate the visitor transfer probability based on the preset scenic spot analysis data and the preset transfer probability formula.

[0051] Among them, the visitor transfer probability is a probability of characterizing the travel from the second scenic spot to the first scenic spot. In this embodiment, the preset transfer probability formula can be understood as a formula specifically used to analyze and calculate the transfer of visitors from one scenic spot to another, that is, a formula for calculating the visitor transfer probability. At the same time, the preset scenic spot analysis data can be understood as the data required for calculating the visitor transfer probability determined from the historical data when the visitor browses the scenic spot. For example, the preset scenic spot analysis data can be based on related data corresponding to different browsing factors and browsing situations, such as the queuing situation of the first scenic spot, the route from the first scenic spot to the second scenic spot, the browsing time of the first scenic spot, and other data. It should be noted that the specific data types, quantities, contents, and forms contained in the preset scenic spot analysis data can be determined as required for calculating the visitor transfer probability, and are not limited here.

[0052] 103. Determine the path visitor flow according to the real-time visitor flow information and the visitor transfer probability.

[0053] The path visitor flow is the number of visitors on the path from the second scenic spot to the first scenic spot.

[0054] Once the real-time visitor flow and visitor transfer probability are determined, it is equivalent to knowing the current visitor flow of the second scenic spot and the transfer situation from the second scenic spot to the first scenic spot. At this time, based on these two data, the current situation of visitors on the road from the second scenic spot to the first scenic spot can be determined, that is, the path visitor flow.

[0055] 104. Determine the visitor flow of the scenic spot according to the visitor flow of the multiple paths.

[0056] After determining the visitor situation on the path from the second scenic spot to the first scenic spot, that is, the path visitor flow, the path visitor flow between each scenic spot can be determined by analogy, and statistics can be performed to determine the overall visitor browsing situation of the scenic spot, that is, the scenic spot visitor flow. Of course, when the first scenic spot is a scenic spot near the exit and the second scenic spot is a scenic spot near the entrance, the path visitor flow can be directly used as the scenic spot visitor flow. Specifically, which of the above execution methods is selected is not limited here, and can depend on the selection of the first scenic spot and the second scenic spot in the scenic spot.

[0057] An embodiment of the present invention provides a method for detecting the visitor flow of a scenic spot. First, real-time visitor flow information of a second scenic spot is obtained, and then the visitor transfer probability is calculated according to preset scenic spot analysis data and a preset transfer probability formula. Then, the path visitor flow is determined according to the real-time visitor flow information and the visitor transfer probability. Finally, the scenic spot visitor flow is determined according to multiple path visitor flows, thereby realizing the detection of the scenic spot visitor flow. In the above scheme, since the scenic area includes multiple attractions, and the visitor transfer probability is a probability of characterizing the probability of going from the second attraction to the first attraction, the path visitor flow is the number of visitors in the path from the second attraction to the first attraction. This ensures that in the present invention, in the process of determining the path visitor flow based on the real-time visitor flow information and the visitor transfer probability, there is no need to collect and count the positions of each visitor, and the flow situation in the path from the second attraction to the first attraction can be calculated based only on the real-time visitor flow information of the second attraction. Therefore, in the process of determining the scenic spot passenger flow based on multiple path visitor flows, there is no need to obtain the visitor positioning information, and the passenger flow of each path can be directly calculated based on the calculation method, so there is no need to rely on the positioning information, which avoids the problem of inaccurate scenic spot passenger flow detection results due to inaccurate positioning information or the visitor not providing positioning information, and can improve the accuracy of the detection results. In addition, since the only data that needs to be collected in real time in the above scheme is the real-time visitor flow of the second scenic spot, that is to say, only monitoring equipment for collecting real-time visitor flow needs to be set up at the second scenic spot in the scenic area. Compared with the prior art, there is no need to verify the identity of the visitor and track each visitor, which can significantly reduce the amount of data required to be collected during the detection process, and reduce the occupation and consumption of system resources during the implementation of the method described in the present invention.

[0058] In an optional embodiment, in step 102 of the above embodiment, calculating the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula includes:

[0059] First, the analysis parameters are determined according to the preset scenic spot analysis data, wherein the analysis parameters are obtained after the preset scenic spot analysis data is calculated by the random utility algorithm. In this embodiment, the random utility algorithm (random utility theory, also known as random utility theory), the implementation model of the algorithm is actually a discrete choice model. Its general principle is to assume that the selector has J alternatives, each corresponding to a certain utility U, which is composed of the sum of fixed and random parts. The fixed utility V can be explained by a certain observable factor x, and the random utility comes from the change of the influence quantity. This change is unpredictable or random in time and space, and it will cause the change of the measured repeated observation value. In this embodiment, since the possibility of a visitor transferring from one scenic spot to another node is affected by multiple different factors, that is, the specific data of each factor combined with the corresponding coefficient can determine the overall random utility value, that is, the overall possibility. Therefore, in this step, the preset analysis data is combined with the random utility algorithm to determine the analysis parameters when the visitor transfers.

[0060] Then, determining the number of paths from the first scenic spot to the second scenic spot;

[0061] Finally, the visitor transfer probability is calculated according to the analysis parameters, the number of paths and the preset transfer probability formula. In the process of determining the transfer probability, since there may be multiple different paths from the second scenic spot to the first scenic spot, it is necessary to determine how many paths there are in total, and calculate the probability of visitor transfer based on the selection parameters of each path through the preset transfer probability formula, so that the transfer of visitors from the second scenic spot to the first scenic spot can be analyzed, thereby laying the foundation for the subsequent calculation of passenger flow.

[0062] In an optional embodiment, the preset transition probability formula includes a softmax formula;

[0063] Among them, the softmax function, also known as the normalized exponential function, aims to present the results of multi-classification in the form of probability. The first step of softmax is to transform the prediction results of the model into an exponential function, which ensures the non-negativity of the probability. In order to ensure that the sum of the probabilities of each prediction result is equal to 1, only the transformed results need to be normalized here. The specific method is to divide the transformed result by the sum of all transformed results, which can be understood as the percentage of the transformed results in the total. In this way, an approximate probability is obtained.

[0064] Based on this, the aforementioned embodiment calculates the visitor transfer probability according to the analysis parameters, the number of paths and the preset transfer probability formula, which may include:

[0065] First, obtaining analysis parameters of each path from the second scenic spot to the first scenic spot;

[0066] Then, the visitor transfer probability is calculated according to the analysis parameters of each path, the number of paths and the softmax formula.

[0067] The specific execution process of the above steps can be as follows:

[0068]

[0069] in, represents the transition probability from scenic spot i to scenic spot j, represents the analysis parameter from scenic spot i to scenic spot j, K represents the number of routes from scenic spot i to other scenic spots, Represents the analysis parameters from attraction i to the next attraction k.

[0070] Based on the above formula, it can be seen that when determining the transfer probability from scenic spot i to scenic spot j, it is necessary to determine all the analysis parameters in the K paths, and calculate them based on the analysis parameters from scenic spot i (the second scenic spot) to scenic spot j (the first scenic spot) to find the corresponding probability value as the transfer probability.

[0071] In the above method, the visitor transfer probability is calculated by using the softmax formula. Since the softmax formula can ensure that the calculation results are all positive values, this avoids the situation where negative values ​​affect the calculation results, thereby ensuring the accuracy of the final calculated visitor transfer probability.

[0072] In an optional embodiment, determining the analysis parameters according to the preset scenic spot analysis data in the aforementioned step includes:

[0073] First, constructing an initial selection utility formula according to the random utility algorithm, wherein the selection utility formula is constructed according to a preset error, a browsing factor, and a corresponding browsing factor coefficient;

[0074] Then, according to the preset scenic spot analysis data and the initial selection utility formula, the actual value of the browsing factor coefficient corresponding to each browsing factor and the actual value of the preset error are obtained through fitting calculation;

[0075] Afterwards, determining a selection utility formula corresponding to the initial selection utility formula according to the actual value of the browsing factor and the actual value of the preset error;

[0076] Finally, according to the selection utility formula and each of the scenic spots, the analysis parameters corresponding to each of the scenic spots are calculated.

[0077] In the method described in this embodiment, by constructing an initial selection utility formula based on preset errors, browsing factors and corresponding browsing factor coefficients, it can be ensured that the constructed initial selection utility formula can take into account different browsing factors and errors, thereby ensuring the accuracy of the selection utility formula determined after the subsequent fitting calculation of the preset scenic spot analysis data, thereby ensuring the accuracy of the analysis parameters of each scenic spot finally calculated, thereby improving the accuracy of the passenger flow detection results as a whole.

[0078] In an optional embodiment, the initial selection utility formula is constructed according to the random utility algorithm in the above steps, including:

[0079] First, obtain preset scenic spot analysis data, wherein the preset scenic spot analysis data is the data recorded in the history when the scenic spot visitors browse the scenic spot;

[0080] Then, corresponding scenic spot browsing factors are set according to the scenic spot, wherein the scenic spot browsing factors include at least one of a path factor, a scenic spot factor and a visitor factor, the path factor is used to characterize route-related factors when visitors browse, the scenic spot factor is used to characterize factors related to the scenic spot itself, and the visitor factor is used to characterize the situation of the scenic spot when it is browsed by visitors;

[0081] Finally, the initial selection utility formula is constructed according to the scenic spot browsing factors and the random utility algorithm.

[0082] Based on the description in the foregoing embodiments, it can be known that since the core of the random utility algorithm is to determine the relationship between the results and factors by considering each factor, it is necessary to set the browsing factors in this step. Since the browsing factors include at least one of the path factors, scenic spot factors and visitor factors, this ensures that the influence of different factors such as visitors, routes and attractions are taken into account in the process of setting the browsing factors. It can not only ensure the accuracy of the initial selection utility formula set at the end, but also can be adjusted based on the needs of the user, and the required factors can be selected as browsing factors, which is conducive to timely adjustment when the actual attractions or routes of the scenic area change, and has good flexibility and adaptability.

[0083] In an optional embodiment, the path factor includes: a distance factor and an adjacent factor; the distance factor is used to characterize the distance between the first scenic spot and the second scenic spot; the adjacent factor is used to characterize whether the first scenic spot is adjacent to the second scenic spot;

[0084] The scenic spot factors include: scenic spot type factor, scenic spot feature factor, scenic spot area factor, and scenic spot location factor; the scenic spot type factor is used to characterize the type of the scenic spot, the scenic spot feature factor is used to characterize whether the scenic spot has browsing features, the scenic spot area factor is used to characterize the level of the scenic spot area size, and the scenic spot location factor is used to characterize whether the scenic spot is located at the exit of the scenic spot;

[0085] The visitor factors include: a visit duration factor, a visit crowding factor, a visit queue factor and a re-browsing factor; the visitor duration factor is used to characterize the duration of the visit to the attraction, the visit crowding factor is used to characterize the degree of crowding of the attraction, the visit queue factor is used to characterize the queuing duration of the attraction, and the re-browsing factor is used to characterize whether the attraction is visited again.

[0086] Based on the method of the above embodiment, in the specific implementation process of constructing the initial selection utility formula and determining the selection utility formula, it can be performed in the following manner:

[0087] The process of a visitor's tour can be understood as a continuous selection process from one attraction to another and then to the next attraction, so a mathematical model of tour behavior can be established. As a decision-making subject (person or group), he will choose the option that he thinks is the most useful to him from a set of options that can be selected and are independent of each other. Therefore, it is necessary to calculate the analysis parameters of tourists from the previous attraction to the next attraction. In this process, it is first necessary to build a corresponding formula based on the random utility algorithm. The formula can be based on the preset scenic spot analysis data, or the scenic spot itself determines the factors that can affect the visitor's browsing behavior, and at the same time set the corresponding coefficient for each factor. Based on this, the initial selection utility formula can be defined as:

[0088]

[0089] in: ,… The coefficients corresponding to each browsing factor; Represents the analysis parameter from scenic spot i to scenic spot j. The natural logarithm of the probability of selecting the analysis probability of the preset scenic spot is adopted here.

[0090] In the above formula, is the distance factor, which is used to represent the distance from scenic spot i to scenic spot j;

[0091] is an adjacent factor, used to indicate whether scenic spot i is adjacent to scenic spot j. Specifically, it can be set to 1 if it is adjacent and 0 if it is not adjacent.

[0092] is the scenic spot visit duration factor, which is used to represent the visiting time of scenic spot j;

[0093] is the attraction queuing factor, which is used to represent the queuing time of attraction j;

[0094] It is the re-browsing factor, which is used to indicate whether the visit is repeated, with 1 for yes and 0 for no;

[0095] is the scenic spot area factor, which is used to represent the area of ​​scenic spot j. Specifically, it can be divided into three categories according to size, represented by 1, 2, and 3 respectively;

[0096] is the crowdedness factor of the scenic spot, which is used to indicate the crowdedness of the scenic spot j. Specifically, it can be divided into three categories, represented by 1, 2, and 3 respectively;

[0097] is a characteristic factor of scenic spot, which is used to indicate whether scenic spot j is characteristic. Specifically, it can be set to 1 if it is a characteristic scenic spot, and 0 otherwise;

[0098] is the attraction type factor, which is used to indicate the type of attraction j. It can be classified according to the actual situation, for example, it can be represented by 1, 2, and 3 respectively;

[0099] is the scenic spot location factor, which is used to indicate whether the scenic spot j is the exit of the scenic spot. Specifically, it can be set to 1 if it is an exit and 0 if it is not.

[0100] is a random error.

[0101] After the corresponding initial selection utility formula is constructed based on the above 10 factors, the fitting operation can be performed based on the preset scenic spot analysis data. The process is to substitute the previously acquired historical data into the formula according to the factors in the above formula and determine the coefficient of each browsing factor, so as to obtain ,… The actual value of , thus obtaining the corresponding choice utility formula.

[0102] In an optional embodiment, in step 103 of the above embodiment, determining the path visitor flow according to the real-time visitor flow information and the visitor transfer probability includes:

[0103] First, obtaining visitor traffic according to the real-time visitor traffic information;

[0104] Then, the visitor flow rate of the path is obtained by performing a product operation on the visitor flow rate and the visitor transfer probability.

[0105] Specifically, the specific execution process in this step can be as follows:

[0106]

[0107] in, represents the path visitor flow on the path from attraction i (the second attraction) to attraction j (the first attraction) at time t, represents the visitor flow of scenic spot i at time t (the visitor flow in the real-time visitor flow information of the second scenic spot), represents the transfer probability from attraction i to attraction j (the transfer probability of visitors from the second attraction to the first attraction).

[0108] In this embodiment, based on the above method, the effect of determining the path visitor flow rate by the visitor flow rate and the visitor transfer probability can be achieved. Since the above process is based on statistical calculations, that is to say, there is no need to determine the specific location of each visitor on each road, the process of determining the visitor flow rate based on the positioning information is avoided. On the basis of simplifying the detection process, it can also avoid the problem of inaccurate results of the path visitor flow rate caused by the inability to obtain positioning information or inaccurate positioning information, thereby improving the accuracy of the detection results.

[0109] It should be noted that, in the above embodiment, the specific data content obtained by the preset scenic spot analysis data can be selected based on actual needs. Of course, the following data can also be obtained from historical data according to the following process as the preset scenic spot analysis data, including: the visiting route data of tourist samples, the passenger flow data of each scenic spot at a certain time, and the geographical location data of the scenic spot;

[0110] Among them, the visit route data of tourist samples: select different time periods to record the process of each tourist starting from the entrance and visiting each attraction (attraction or store) one by one, including the order of visiting attractions, visiting time, waiting time, whether to visit repeatedly, etc., until choosing the exit to end the trip;

[0111] Passenger flow data of each scenic spot at a certain time: The passenger flow data of some scenic spots (scenic spots with cameras installed) is obtained through camera video monitoring;

[0112] Geographical location data of scenic spots: distance between adjacent scenic spots, area of ​​scenic spots, degree of crowding, whether the scenic spots are distinctive, type of scenic spots, whether there are exits, etc.

[0113] Furthermore, as a response to the above Figure 1 In addition to the implementation of the methods shown in various embodiments, the present invention also provides a detection device for the flow of tourists in a scenic spot, which is used to detect the above-mentioned Figure 1This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. Figure 2 As shown, the device includes: an acquisition unit 21, a calculation unit 22, a first determination unit 23 and a second determination unit 24, wherein

[0114] The acquisition unit 21 may be used to acquire real-time visitor flow information of a second scenic spot, wherein the scenic spot includes a plurality of scenic spots;

[0115] The calculation unit 22 can be used to calculate the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula, wherein the visitor transfer probability represents the probability of going from the second scenic spot to the first scenic spot;

[0116] The first determining unit 23 may be configured to determine a path visitor flow rate according to the real-time visitor flow rate information and the visitor transfer probability, wherein the path visitor flow rate is the number of visitors in a path from the second scenic spot to the first scenic spot;

[0117] The second determining unit 24 may be configured to determine the scenic spot visitor flow according to the visitor flow along the plurality of paths.

[0118] Based on the above description, an embodiment of the present invention provides a method and device for detecting the passenger flow of a scenic spot. First, the real-time visitor flow information of the second scenic spot is obtained, and then the visitor transfer probability is calculated according to the preset scenic spot analysis data and the preset transfer probability formula. Then, the path visitor flow is determined according to the real-time visitor flow information and the visitor transfer probability. Finally, the scenic spot passenger flow is determined according to multiple path visitor flows, thereby realizing the detection of the scenic spot passenger flow. In the above scheme, since the scenic area includes multiple attractions, and the visitor transfer probability is a probability of characterizing the probability of going from the second attraction to the first attraction, the path visitor flow is the number of visitors in the path from the second attraction to the first attraction. This ensures that in the present invention, in the process of determining the path visitor flow based on the real-time visitor flow information and the visitor transfer probability, there is no need to collect and count the positions of each visitor, but the flow situation in the path from the second attraction to the first attraction can be calculated based only on the real-time visitor flow information of the second attraction. Therefore, in the process of determining the scenic spot passenger flow based on multiple path visitor flows, there is no need to obtain the visitor positioning information, and the passenger flow of each path can be directly calculated based on the calculation method, so there is no need to rely on the positioning information, which avoids the problem of inaccurate scenic spot passenger flow detection results due to inaccurate positioning information or the visitor not providing positioning information, and can improve the accuracy of the detection results. In addition, since the only data that needs to be collected in real time in the above scheme is the real-time visitor flow of the second scenic spot, that is to say, only monitoring equipment for collecting real-time visitor flow needs to be set up at the second scenic spot in the scenic area. Compared with the prior art, there is no need to verify the identity of the visitor and track each visitor, which can significantly reduce the amount of data required to be collected during the detection process, and reduce the occupation and consumption of system resources during the implementation of the method described in the present invention.

[0119] Furthermore, in the aforementioned embodiment, the processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and a method for detecting the flow of tourists in a scenic spot can be implemented by adjusting the kernel parameters, which can get rid of the dependence on the location information of visitors, thereby solving the problem of low accuracy of the detection result caused by inaccurate location information or when the user does not provide location information in the process of detecting the flow of tourists in conventional scenic spots, and can improve the accuracy.

[0120] An embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the method for detecting the passenger flow of a scenic spot is implemented.

[0121] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for detecting the tourist flow of a scenic spot is executed when the program is running.

[0122] The embodiment of the present invention provides a device 30, such as Figure 3 As shown, the device includes at least one processor 301, and at least one memory 302 and a bus 303 connected to the processor; wherein the processor 301 and the memory 302 communicate with each other via the bus 303; the processor 301 is used to call the program instructions in the memory to execute the above-mentioned method for detecting the passenger flow of the scenic spot.

[0123] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining real-time visitor flow information of a second scenic spot, wherein the scenic spot includes multiple scenic spots; calculating a visitor transfer probability based on preset scenic spot analysis data and a preset transfer probability formula, wherein the visitor transfer probability is a probability of traveling from the second scenic spot to the first scenic spot; determining a path visitor flow based on the real-time visitor flow information and the visitor transfer probability, wherein the path visitor flow is the number of visitors in the path from the second scenic spot to the first scenic spot; and determining the scenic spot passenger flow based on multiple path visitor flows.

[0125] Furthermore, the calculation of visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula includes:

[0126] Determining analysis parameters according to the preset scenic spot analysis data, wherein the analysis parameters are obtained after the preset scenic spot analysis data is calculated by a random utility algorithm;

[0127] Determining the number of paths from the first scenic spot to the second scenic spot;

[0128] The visitor transfer probability is calculated according to the analysis parameters, the number of paths and the preset transfer probability formula.

[0129] Furthermore, the preset transition probability formula includes a softmax formula;

[0130] The calculating the visitor transfer probability according to the analysis parameter, the number of paths and the preset transfer probability formula includes:

[0131] Obtaining analysis parameters of each path from the second scenic spot to the first scenic spot;

[0132] The visitor transfer probability is calculated according to the analysis parameters of each path, the number of paths and the softmax formula.

[0133] Further, determining the analysis parameters according to the preset scenic spot analysis data includes:

[0134] Constructing an initial selection utility formula according to the random utility algorithm, wherein the selection utility formula is constructed according to a preset error, a browsing factor, and a corresponding browsing factor coefficient;

[0135] According to the preset scenic spot analysis data and the initial selection utility formula, the actual value of the browsing factor coefficient corresponding to each browsing factor and the actual value of the preset error are obtained through fitting calculation;

[0136] Determining a selection utility formula corresponding to the initial selection utility formula according to the actual value of the browsing factor and the actual value of the preset error;

[0137] According to the selection utility formula and each of the scenic spots, an analysis parameter corresponding to each of the scenic spots is calculated.

[0138] Furthermore, constructing an initial selection utility formula according to the random utility algorithm includes:

[0139] Acquire preset scenic spot analysis data, wherein the preset scenic spot analysis data is the data recorded in the history when the scenic spot visitors browse the scenic spot;

[0140] Setting corresponding scenic spot browsing factors according to the scenic spot, wherein the scenic spot browsing factors include at least one of a path factor, a scenic spot factor and a visitor factor, the path factor is used to characterize route-related factors when visitors browse, the scenic spot factor is used to characterize factors related to the scenic spot itself, and the visitor factor is used to characterize the situation of the scenic spot when being browsed by visitors;

[0141] The initial selection utility formula is constructed according to the scenic spot browsing factors and a random utility algorithm.

[0142] Furthermore, the path factor includes: a distance factor and an adjacent factor; the distance factor is used to characterize the distance between the first scenic spot and the second scenic spot; the adjacent factor is used to characterize whether the first scenic spot is adjacent to the second scenic spot;

[0143] The scenic spot factors include: scenic spot type factor, scenic spot feature factor, scenic spot area factor, and scenic spot location factor; the scenic spot type factor is used to characterize the type of the scenic spot, the scenic spot feature factor is used to characterize whether the scenic spot has browsing features, the scenic spot area factor is used to characterize the level of the scenic spot area size, and the scenic spot location factor is used to characterize whether the scenic spot is located at the exit of the scenic spot;

[0144] The visitor factors include: a visit duration factor, a visit crowding factor, a visit queue factor and a re-browsing factor; the visitor duration factor is used to characterize the duration of the visit to the attraction, the visit crowding factor is used to characterize the degree of crowding of the attraction, the visit queue factor is used to characterize the queuing duration of the attraction, and the re-browsing factor is used to characterize whether the attraction is visited again.

[0145] Furthermore, determining the path visitor flow according to the real-time visitor flow information and the visitor transfer probability includes:

[0146] Acquire visitor traffic according to the real-time visitor traffic information;

[0147] The path visitor flow is obtained by performing a product operation on the visitor flow and the visitor transfer probability.

[0148] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] In a typical configuration, the device includes one or more processors (CPU), memory and bus. The device may also include input / output interface, network interface and the like.

[0150] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

[0151] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0152] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A method for detecting the passenger flow of a scenic spot, characterized in that: include: Acquire real-time visitor flow information of a second scenic spot, where the scenic spot includes a plurality of scenic spots; Calculate the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula, wherein the visitor transfer probability represents the probability of going from the second scenic spot to the first scenic spot; Determine a path visitor flow according to the real-time visitor flow information and the visitor transfer probability, wherein the path visitor flow is the number of visitors in the path from the second scenic spot to the first scenic spot; Determine the visitor flow of the scenic spot according to the visitor flow of the plurality of paths; The calculation of visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula includes: Determining analysis parameters according to the preset scenic spot analysis data, wherein the analysis parameters are obtained after the preset scenic spot analysis data is calculated by a random utility algorithm; Determining the number of paths from the first scenic spot to the second scenic spot; Calculate the visitor transfer probability according to the analysis parameters, the number of paths and the preset transfer probability formula; The preset transfer probability formula includes a softmax formula; The calculating the visitor transfer probability according to the analysis parameter, the number of paths and the preset transfer probability formula includes: Obtaining analysis parameters of each path from the second scenic spot to the first scenic spot; Calculating the visitor transfer probability according to the analysis parameters of each path, the number of paths and the softmax formula; Determining the analysis parameters according to the preset scenic spot analysis data includes: Constructing an initial selection utility formula according to the random utility algorithm, wherein the selection utility formula is constructed according to a preset error, a browsing factor, and a corresponding browsing factor coefficient; According to the preset scenic spot analysis data and the initial selection utility formula, the actual value of the browsing factor coefficient corresponding to each browsing factor and the actual value of the preset error are obtained through fitting calculation; Determining a selection utility formula corresponding to the initial selection utility formula according to the actual value of the browsing factor and the actual value of the preset error; According to the selection utility formula and each of the scenic spots, an analysis parameter corresponding to each of the scenic spots is calculated.

2. The method for detecting the passenger flow of a scenic spot according to claim 1, characterized in that: The constructing of the initial selection utility formula according to the random utility algorithm comprises: Acquire preset scenic spot analysis data, wherein the preset scenic spot analysis data is the data recorded in the history when the scenic spot visitors browse the scenic spot; Setting corresponding scenic spot browsing factors according to the scenic spot, wherein the scenic spot browsing factors include at least one of a path factor, a scenic spot factor and a visitor factor, the path factor is used to characterize route-related factors when visitors browse, the scenic spot factor is used to characterize factors related to the scenic spot itself, and the visitor factor is used to characterize the situation of the scenic spot when being browsed by visitors; The initial selection utility formula is constructed according to the scenic spot browsing factors and a random utility algorithm.

3. The method for detecting the passenger flow of a scenic spot according to claim 2, characterized in that: The path factors include: a distance factor and an adjacent factor; the distance factor is used to characterize the distance between the first scenic spot and the second scenic spot; the adjacent factor is used to characterize whether the first scenic spot is adjacent to the second scenic spot; The scenic spot factors include: scenic spot type factor, scenic spot feature factor, scenic spot area factor, and scenic spot location factor; the scenic spot type factor is used to characterize the type of the scenic spot, the scenic spot feature factor is used to characterize whether the scenic spot has browsing features, the scenic spot area factor is used to characterize the level of the scenic spot area size, and the scenic spot location factor is used to characterize whether the scenic spot is located at the exit of the scenic spot; The visitor factors include: a visit duration factor, a visit crowding factor, a visit queue factor and a re-browsing factor; the visitor duration factor is used to characterize the duration of the visit to the attraction, the visit crowding factor is used to characterize the degree of crowding of the attraction, the visit queue factor is used to characterize the queuing duration of the attraction, and the re-browsing factor is used to characterize whether the attraction is visited again.

4. The method for detecting the passenger flow of a scenic spot according to any one of claims 1 to 3, characterized in that: Determining the path visitor flow according to the real-time visitor flow information and the visitor transfer probability includes: Acquire visitor traffic according to the real-time visitor traffic information; The path visitor flow is obtained by performing a product operation on the visitor flow and the visitor transfer probability.

5. A device for detecting the flow of tourists in a scenic spot, characterized in that: include: An acquisition unit, used to acquire real-time visitor flow information of a second scenic spot, wherein the scenic spot includes a plurality of scenic spots; A calculation unit, used to calculate the visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula, wherein the visitor transfer probability represents the probability of going from the second scenic spot to the first scenic spot; A first determining unit, configured to determine a path visitor flow rate according to the real-time visitor flow rate information and the visitor transfer probability, wherein the path visitor flow rate is the number of visitors in a path from the second scenic spot to the first scenic spot; A second determining unit, configured to determine the scenic spot visitor flow rate according to the visitor flow rates of the plurality of paths; The calculation of visitor transfer probability according to the preset scenic spot analysis data and the preset transfer probability formula includes: Determining analysis parameters according to the preset scenic spot analysis data, wherein the analysis parameters are obtained after the preset scenic spot analysis data is calculated by a random utility algorithm; Determining the number of paths from the first scenic spot to the second scenic spot; Calculate the visitor transfer probability according to the analysis parameters, the number of paths and the preset transfer probability formula; The preset transfer probability formula includes a softmax formula; The calculating the visitor transfer probability according to the analysis parameter, the number of paths and the preset transfer probability formula includes: Obtaining analysis parameters of each path from the second scenic spot to the first scenic spot; Calculating the visitor transfer probability according to the analysis parameters of each path, the number of paths and the softmax formula; Determining the analysis parameters according to the preset scenic spot analysis data includes: Constructing an initial selection utility formula according to the random utility algorithm, wherein the selection utility formula is constructed according to a preset error, a browsing factor, and a corresponding browsing factor coefficient; According to the preset scenic spot analysis data and the initial selection utility formula, the actual value of the browsing factor coefficient corresponding to each browsing factor and the actual value of the preset error are obtained through fitting calculation; Determining a selection utility formula corresponding to the initial selection utility formula according to the actual value of the browsing factor and the actual value of the preset error; According to the selection utility formula and each of the scenic spots, an analysis parameter corresponding to each of the scenic spots is calculated.

6. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for detecting the passenger flow of a scenic spot as described in any one of claims 1 to 4.

7. A device, characterized in that: The device includes at least one processor, and at least one memory and bus connected to the processor; wherein the processor and memory communicate with each other through the bus; the processor is used to call the program instructions in the memory to execute the method for detecting the passenger flow of a scenic spot as described in any one of claims 1 to 4.

Images