CN113487055A

CN113487055A - Intelligent ticket pre-selling method and device

Info

Publication number: CN113487055A
Application number: CN202110763034.6A
Authority: CN
Inventors: 黄坤; 冯晓峰; 杨帆; 谭硕; 熊文成; 袁克; 胡侠情; 冯欣怡; 刘亚; 袁静佳
Original assignee: China Construction Bank Corp
Current assignee: China Construction Bank Corp
Priority date: 2021-07-06
Filing date: 2021-07-06
Publication date: 2021-10-08

Abstract

The invention discloses an intelligent ticket pre-selling method and device, which relate to the technical field of big data.A specific implementation mode comprises the steps of obtaining the flow of people allowed in a preset time period of each entrance, determining an entrance list with surplus tickets according to the preset number of tickets corresponding to each current entrance, obtaining the entrance position information of the surplus tickets, and calculating the distance between each entrance and each hotspot area; identifying tourists through object identification equipment corresponding to the hot area, acquiring a tourist browsing data information list of the hot area, calling a loitering judgment component to obtain loitering tourists from the tourist browsing data information list, and determining the effective number of the tourists in the hot area; and calling a utility model to calculate the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the effective number of people in each hot spot area, determining the non-congestion entrance and adjusting the number of the surplus tickets at the entrance. The method and the system can solve the problems of low efficiency and poor real-time performance of the conventional scenic spot passenger flow management and control and ticket pre-sale.

Description

Intelligent ticket pre-selling method and device

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to image recognition, and provides an intelligent ticket pre-selling method and device.

Background

At present, a scenic spot passenger flow management and control and ticketing system focuses on thermal analysis and crowd distribution judgment of tourists by a conventional method, and ticket pre-selling is carried out. For example: aiming at fixed aggregation buildings or scenic spots, a people number change situation curve and a thermal value image of tourist distribution in the scenic spot are drawn through the total number of people entering the scenic spot and the number of people distributed in each scenic spot, so that the full time point can be predicted before the tourists in the scenic spot are full, and the ticketing is finished in advance.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

the existing scenic spot passenger flow management and control and ticket pre-selling are directed at thermal power and distribution analysis in fixed aggregation buildings or scenic spots, so that the problems of single analysis dimension, low scenic spot passenger flow management and control and ticket pre-selling efficiency and poor real-time performance are caused.

Disclosure of Invention

In view of this, embodiments of the present invention provide an intelligent ticket advance selling method and apparatus, which can solve the problems of low efficiency and poor real-time performance in current scenic spot passenger flow management and ticket advance selling.

In order to achieve the above object, according to an aspect of the embodiments of the present invention, an intelligent ticket pre-selling method is provided, including obtaining a flow rate of people allowed in a preset time period of each entrance, determining an entrance list of surplus tickets according to a preset number of tickets corresponding to each current entrance, and further obtaining entrance position information of the surplus tickets, so as to calculate distances to each hot spot area; identifying tourists through object identification equipment corresponding to the hot spot area, acquiring a tourist browsing data information list of the hot spot area, and calling a loitering judgment component to obtain loitering tourists from the tourist browsing data information list so as to determine the effective number of tourists in the hot spot area; and calling a preset utility model, calculating the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the effective number of people in each hot spot area, and further determining a non-congestion entrance from the entrance list with the surplus tickets so as to adjust the number of the surplus tickets at each entrance in the entrance list with the surplus tickets.

Optionally, after obtaining the congestion status of the entry reaching all the hot spot areas by calculation, the method includes:

and according to the congestion condition of the entrances, arranging the entrances in the entrance list with the surplus tickets in an ascending order, and marking the target entrance to forbid ticket selling admission based on the preset limited number of the congested entrances.

Optionally, after adjusting the number of remaining tickets at each entry in the entry list with the remaining tickets, the method includes:

receiving an entrance entering request, and acquiring attribute information of a guest target to be entered in the entrance entering request to determine that a preset entering condition is met;

judging whether the entrance is marked or not, if so, rejecting the entrance entering request; if not, judging whether the current entrance reaches a preset current limit warning threshold value, if so, rejecting the entrance entering request, and if not, responding to the entrance entering request to permit the entrance.

Optionally, invoking a loitering determining component to obtain a loitering tourist from the tourist browsing data information list, including:

calling a loitering judging component, and monitoring object identification equipment of which the times of repeatedly capturing objects in a preset maximum time interval in an object identification equipment list corresponding to a hot spot area are greater than or equal to a preset time threshold;

and when the number of the object recognition devices is larger than or equal to a preset number threshold, extracting the tourist information of the captured object from a tourist browsing data information list as a loitering tourist.

Optionally, determining the number of valid people in the hotspot area comprises:

and acquiring loitering factors corresponding to the hot spot area, and calculating the effective number of the hot spot area through a preset effective model based on loitering tourists and non-loitering tourists in a tourist browsing data information list.

Optionally, calculating a congestion status of the entry reaching all hot spot areas, including:

and acquiring distance weighting factors corresponding to the distances from the entrance to each hot spot area, so as to calculate the congestion status from the entrance to each hot spot area based on the effective number of people in each hot spot area, and further obtain the congestion status from the entrance to all the hot spot areas.

Optionally, before guest identification is performed through the object identification device corresponding to the hotspot area, the method includes:

deploying a plurality of object recognition devices to N discrete points, and acquiring position information of each object recognition device;

and clustering or averaging the position information of the object identification equipment to obtain a hot spot region, and further generating a mapping relation between the hot spot region and the object identification equipment.

Optionally, the method further comprises:

and identifying the tourists through the object identification equipment corresponding to the hot spot area to obtain the behavior data and emotion data of the tourists, and further pulling the target discrimination model from the discrimination model pool to obtain a corresponding discrimination result and send an alarm.

In addition, the invention also provides an intelligent ticket pre-selling device which comprises a parameter configuration module, a parameter configuration module and a parameter configuration module, wherein the parameter configuration module is used for acquiring the flow of people allowed in the preset time period of each entrance, so as to determine an entrance list of surplus tickets according to the preset number of tickets corresponding to each current entrance, and further acquire the entrance position information of the surplus tickets, so as to calculate the distance between each entrance and each hot spot area;

the face capturing and identifying module is used for identifying tourists through object identifying equipment corresponding to the hot area, acquiring a tourists browsing data information list of the hot area, and calling the loitering judging component to obtain loitering tourists from the tourists browsing data information list so as to determine the effective number of the tourists in the hot area;

the multi-feature fusion entrance ticket pre-selling module is used for calling a preset utility model, calculating the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the effective number of people in each hot spot area, and further determining the uncongested entrance from the entrance list with the surplus tickets so as to adjust the number of the surplus tickets at each entrance in the entrance list with the surplus tickets.

Optionally, after the calculation of the congestion status of the entrance to all hot spot areas by the multi-feature fused entrance ticket pre-selling module, the method includes:

Optionally, the method further comprises:

the ticket selling acquisition module is used for receiving an entrance entering request, acquiring the attribute information of a tourist target to be entered in the entrance entering request and determining that a preset entering condition is met; judging whether the entrance is marked or not, if so, rejecting the entrance entering request; if not, judging whether the current entrance reaches a preset current limit warning threshold value, if so, rejecting the entrance entering request, and if not, responding to the entrance entering request to permit the entrance.

Optionally, the face capturing and recognizing module calls a loitering judging component to obtain the loitering tourist from the tourist browsing data information list, and the loitering tourist comprises:

Optionally, the face capturing and recognizing module determines the effective number of people in the hot spot area, including:

Optionally, the pre-selling module of the multi-feature fused entrance ticket calculates the congestion status of the entrance to all hot spot areas, including:

Optionally, the method further comprises:

the geographic marking module is used for deploying the object identification devices to N discrete points and acquiring the position information of each object identification device; and clustering or averaging the position information of the object identification equipment to obtain a hot spot region, and further generating a mapping relation between the hot spot region and the object identification equipment.

Optionally, the method further comprises:

and the tourist statistical analysis module is used for identifying the tourists through the object identification equipment corresponding to the hot spot area so as to obtain the behavior data and the emotion data of the tourists, and further pulling the target discrimination model from the discrimination model pool so as to obtain a corresponding discrimination result and send an alarm.

One embodiment of the above invention has the following advantages or benefits: the invention can provide health judgment characteristics to judge admission based on the real-time health condition of the tourist health code, intelligently distribute the crowd based on face recognition, introduce multi-dimensional indexes such as hot spot zone wandering characteristics, hot spot zone distance weighting characteristics and the like, and describe the real-time congestion condition of the scenic spot in a more real-time, dynamic, comprehensive, fine and hierarchical manner; establishing an entrance congestion condition utility function by using the multidimensional indexes and the influence factors to model and describe the entrance congestion condition, and acquiring a real-time entrance congestion state as a ticket selling basis; moreover, the invention can dynamically know the real-time congestion state and wandering crowd distribution of the scenic spot, and dynamically adjust the surplus tickets at the entrance of the ticketing period, so that the congestion of the crowd is relieved, the health and safety risks of tourists are eliminated to the maximum extent, the congestion state of the hot spot area of the scenic spot is relieved, and meanwhile, the economic benefit of the scenic spot and the problem of the explosion of the tourists are guaranteed through intelligent ticketing.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic view of the main flow of an intelligent ticket reselling method according to a first embodiment of the present invention;

FIG. 2 is a schematic diagram of a hot spot region object identification device deployment distribution according to an embodiment of the present invention;

fig. 3 is a schematic view of the main flow of an intelligent ticket reselling method according to a second embodiment of the present invention;

FIG. 4 is a schematic diagram of the main modules of an intelligent ticket reselling apparatus according to a first embodiment of the present invention;

FIG. 5 is a schematic diagram of the main modules of an intelligent ticket reselling apparatus according to a second embodiment of the present invention;

FIG. 6 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 7 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic view of a main flow of an intelligent ticket advance selling method according to a first embodiment of the present invention, as shown in fig. 1, the intelligent ticket advance selling method includes:

step S101, obtaining the flow rate of people allowed in the preset time period of each entrance, determining an entrance list with surplus tickets according to the preset number of entrance corresponding to each entrance at present, and further obtaining entrance position information of the surplus tickets, so as to calculate the distance between each entrance and each hotspot area.

In some embodiments, the current scenic spot is defined at the d (r) th entrance, and the time period t _ duration (p) allows the following people to flow:

psnflow (D (r), t _ duration (p)), and satisfies:

wherein, config _ weight (d (r)) represents weight value of total ticket sales preset in d (r) entrance, such as scenic spot with two entrances, the main entrance is 0.8, the secondary entrance is 0.2, and

it should be noted that, the d (r) entry, the time period t _ duration (p), the predetermined number of tickets as ticket _ order (d (r), t), and whether there are remaining tickets has _ tickets (user _ id), the database satisfies the following conditions:

as some examples, the hotspot zone may be located as follows: deploying a plurality of object recognition devices to the N discrete points, and acquiring the position information of each object recognition device. And clustering or averaging the position information of the object identification equipment to obtain the position information of the hot spot region, and further generating a mapping relation between the hot spot region and the object identification equipment.

In an embodiment, each object recognition device (for example, one or more ways of a camera, an infrared sensor, a pressure sensor, a wifi access number of a network layer, etc. are used as object recognition devices) has an identifier, and for an object recognition device i, the identifier is defined as camera (i), assuming that N object recognition devices are deployed at 1-N discrete points, the geographic Location of the object recognition device is labeled and collected, which is defined as Location (camera (i)), and:

Location(camera(i))＝Location(Lon(camera(i)),Lat(camera(i))

here, Lon (camera (i)) represents longitude information of the object recognition device camera (i), and Lat (camera (i)) represents latitude information of the object recognition device camera (i).

By clustering or averaging the N object recognition devices, 1 to M hot spot areas (Zone of Interest) are obtained, as shown in fig. 2, zon for short, which are generally areas of large people flow density or people gathering concentration, such as buildings, scenic spots, or site buildings. And labeling the zoi, so that each object identification device belongs to one zoi, and assuming that the object identification device i belongs to a hot spot area j, the formula is as follows:

camera (i) e zoi (j), j being the index for zoi

Thus, a list of all object recognition devices for hotspot zone j can be obtained:

camera_list(zoi(j))

in addition, there are D (r) entries in the scenic region, which are defined as Location (D (r)), and

Location(D(r))＝Location(Lon(D(r)),Lat(D(r))

where Lon (d (r)) represents longitude information of the r-th door of the scenic spot, and Lat (d (r)) represents latitude information of the r-th door of the scenic spot.

Therefore, the distance from the entrance of d (r) to zoi (j) can be calculated by Location (d (r)) and zoi (j) position information.

And S102, identifying tourists through object identification equipment corresponding to the hot area, acquiring a tourist browsing data information list of the hot area, and calling a loitering judgment component to obtain loitering tourists from the tourist browsing data information list so as to determine the effective number of the tourists in the hot area.

In some embodiments, invoking the loitering determining component to obtain loitering tourists from the tourists browsing data information list includes:

and calling a loitering judging component, and monitoring object recognition equipment of which the times of repeatedly capturing the object in the preset maximum time interval in an object recognition equipment list corresponding to the hot spot area is greater than or equal to a preset time threshold. And when the number of the object recognition devices is larger than or equal to a preset number threshold, extracting the tourist information of the captured object from a tourist browsing data information list as a loitering tourist.

For example, in the qth time period [ T (q), T (q +1) ] of the hotspot area zoi (j), the identity of the guest is faceid (i) (e.g., the face data of the guest captured by the object recognition device is used as a unique identifier), captured by the object recognition device LIST CAMERA _ LIST (zoi (j)), and filtered:

maximum time interval < ═ wander _ interval (1) repeatedly captured by any object recognition device of camera _ list (zoi (j))

Repeat capturing times of any object recognition device by camera _ list (zoi (j)) are more than or equal to a time threshold Repeat (2)

Repeatedly captured by any object recognition device of camera _ list (zoi (j)), the number of different object recognition devices is more than or equal to S (3)

And the three formulas are met, and the faces (i) of the tourists in zoi (j) are defined as wandering tourists.

The repeated capturing times are more than Repeat, namely the tourists switch and walk in a certain area in a short time, the maximum time interval of repeated capturing is wandering and staying within a short time which is continuously limited by the tourists, and the number of different cameras is more than S, so that the tourists are continuously shot in a plurality of scenes which are densely deployed in the object recognition equipment and are close in geographic position.

In a further embodiment, the specific implementation process of determining the effective number of people in the hot spot area includes: and acquiring loitering factors corresponding to the hot spot area, and calculating the effective number of the hot spot area through a preset effective model based on loitering tourists and non-loitering tourists in a tourist browsing data information list.

For example: in the hotspot area zoi (j) q time period T _ duration (P) ([ T (q)), T (q +1) ], the face deduplication processing may obtain the number of non-loitering persons P (zoi (j)), T _ duration (P)), loitering persons W (zoi (j), T _ duration (P)), the current hotspot area zoi (j), the q time period [ T (q)), T (q +1) ], the effective number of persons psn _ effective, and satisfy:

psn_effective(zoi(j)，t_duration(p))

＝(P(zoi(j)，t_duration(p))-W(zoi(j)，t_duration(p)))+k1

*W(zoi(j)，t_duration(p))

k1 is a wandering factor corresponding to the hot spot area, because wandering visitors in a certain hot spot area with feedback can increase the congestion degree of the whole area, which causes tourist gathering, and can be adjusted by adjusting the wandering factor.

It is worth to be noted that when the tourist passes through 1-N discrete camera monitoring points, the face is identified and captured; obtaining the labeled geographic information of the object identification device through the association of the information of the object identification device, and further adding data information under an area zoi _ id, such as:

[zoi_id,faceid(i),Lon,Lat,timestamp,camera_id]

wherein, zoi _ id represents the identification id of the hot spot area (such as a scenic spot, a building, etc.) where the current camera is located; faceid (i) a face information base identification id for identifying the current user; lon represents longitude information; lat represents dimension information; timestamp represents a captured timestamp; camera _ id represents the current camera id.

By acquiring data of a certain time period T (for example, one day), and arranging timetags of the same zoi _ id in an ascending order, a list of tourist visit data information of an area zoi _ id can be acquired.

As another embodiment, the guest is identified by the object identification device corresponding to the hot spot area to obtain guest behavior data and emotion data, and then the target discrimination model (for example, the behavior discrimination model CNN, the emotion discrimination model SVM, or the like) is pulled from the discrimination model pool to obtain a corresponding discrimination result and send an alarm. Therefore, the invention can realize analysis and statistical mining of scene dangerous behaviors, scene region easy-fall region discrimination and the like based on other richer behaviors and emotions except the human face.

Step S103, calling a preset utility model, calculating the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the number of the effective people in each hot spot area, and further determining a non-congestion entrance from the entrance list with the surplus tickets so as to adjust the number of the surplus tickets at each entrance in the entrance list with the surplus tickets.

In some embodiments, after the congestion status of the entries reaching all the hot spot areas is calculated, the entries in the entry list of the remaining tickets may be sorted in an ascending order according to the congestion status of the entries, and then the target entries are marked to prohibit ticket admission based on a preset number of congestion entry limits. For example: an entry list that is sorted in an ascending order according to the congestion status of the entries is defined as entry _ asc (t _ duration (p)), a forbidden number of congested entries is defined as forbidden, for example, forbidden admission is not allowed for two most congested and next congested entries in the ascending order, and so on. The forbidden _ num most congested entries may be excluded from the entry _ asc (t _ duration (p)) list, and the list of non-congested entries may be obtained as: entry _ asc _ unwounded (t _ duration (p)).

In a further embodiment, after the number of remaining tickets at each entry in the entry list with the remaining tickets is adjusted, an entry request may be received, and attribute information of a guest object to be entered in the entry request is acquired to determine that a preset entry condition is satisfied. Then, judging whether the entrance is marked or not, if so, rejecting the entrance entering request; if not, judging whether the current entrance reaches a preset current limit warning threshold value, if so, rejecting the entrance entering request, and if not, responding to the entrance entering request to permit the entrance. For example: the following formula is defined:

vistor_permits(user_id)＝health_state*has_tickets(user_id)＞0 (4)

ticket_order(D(r)，t)≤psnflow(t_duration(p))*enter_th (5)

D(r)∈enterlist_asc_uncrowded (6)

wherein, formula (4) shows that the current tourist meets the health and spare ticket conditions. Equation (5) indicates that the current inlet has not reached the current limit warning threshold during the sub-period. Equation (6) represents that the current entry belongs to the list of non-congested entries.

In a preferred embodiment, if the entry satisfies the condition! Formula (4), wherein! And if the logical operation is represented, the condition that the admission of the tourists is not met is represented, and ticket purchasing and admission to the park are not allowed.

If the current visitor meets the formula (4) and the formula (5) at the entrance d (r), that is, on the premise that the preliminary judgment condition for the visitor admission is met, the enter _ th represents the warning threshold value of the current entrance requiring current flow limitation, for example, the value is 0.9, the visitor can directly enter the scenic spot from the entrance (without judging whether the current entrance is in the non-congested entrance list).

If the guest currently satisfies the formula (4) & &!at entry D (r)! Formula (5) & & formula (6), where & & represents "conditional and", then on the premise that the preliminary judgment condition of visitor admission is satisfied, that is, the current time reaches the warning threshold value requiring current limiting, and the current entrance does not belong to the most congested forbidden _ num entrances, tickets can be purchased from the entrance directly to the scenic spot.

If the guest currently satisfies the formula (4) & &!at entry D (r)! Equation (5) & &! Formula (6), on the premise that the preliminary judgment condition of the admission of the guest is satisfied (i.e. formula (4) is satisfied), when the current threshold value of the warning required for limiting the flow is reached and the current entry also belongs to the most congested forbidden _ num entries, the ticket admission from the entry cannot be obtained, but the ticket admission from other entries can be considered, at this time, the ticket software system will prompt for warmth, suggest the admission of other entries, and provide the detailed remaining ticket information and the admission guide of the admission of other entries. Therefore, the invention realizes early warning and management and control, and is convenient for guiding the tourists to avoid the current congested entrance and enter the scenic spot from the uncongested passage entrance.

It should be noted that the entry _ asc _ unwounded (t _ duration (p)) is strongly associated with the current sub-time period t _ duration (p), so that as the dynamic control of the ticket system is performed for some time in the future, there is a possibility that the congested entrance will become a smooth and uncongested entrance again, and thus the remaining tickets at the entrance of the ticketing period are dynamically adjusted by the method and the system, so that the congestion of the crowd is relieved.

As another embodiment, the congestion status of the entrance to all the hot spot areas is calculated, and a specific implementation process includes obtaining distance weighting factors corresponding to distances from the entrance to each hot spot area, so as to calculate the congestion status of the entrance to each hot spot area based on the number of effective people in each hot spot area, and further obtain the congestion status of the entrance to all the hot spot areas.

For example: defining the congestion utility function of the entry D (r) to reach the hot spot zone zoi (j) as yield _ efficiency (D (r), zoi (j), t _ duration (p)), and satisfying:

wherein, distance weighting factor distance _ weight (d (r), zoi (j)) is the negative correlation between the distance of the entry and the hot spot zone zoi (j), and the farther the hot spot zone is from the entry, the less influence on the congestion status of the current entry.

For d (r), summing and accumulating the corresponding entrance congestion status utility functions of j hot spot areas of all the hot spot areas zoi (1) -zoi (j), and finally obtaining the whole entrance congestion status utility function crowd _ effectiveness (d (r), t _ duration (p)), and meeting the requirement

The physical meaning of the ingress congestion utility function "crowd _ effeacvice (d (r)", t _ duration (p) ") is: the method can be used for measuring whether the current entrance d (r) is a crowded entrance, when the number of valid people is larger, the scenic spot is closer to the current entrance, which indicates that the current entrance d (r) is present, or a larger passenger flow volume exists at a future moment, early warning and management and control are needed, and certainly, the follow-up of the utility function can be used for making crowd distribution statistical information or one of other indicators for measuring the crowded degree of the scenic spot.

It should be noted that, for the r-th entry d (r) of the scenic spot, the distances to the j hot spot areas may be represented as distances (d (r), zoi (j)), and the maximum value is selected from the r × j distance values: max _ distance _ d2zoi, therefore

Defining the hotspot zone distance weighting characteristics distance _ weight (D (r), zoi (j)) of the entry D (r), and satisfying

It can be seen that when distance (d (r), zoi (j)) is small, e.g., near point 0, distance _ weight is large, approaching 1+ k _ dist; distance _ weight reaches a minimum value of 1+ k _ dist/e when distance (D (r), zoi (j)) is large, e.g., close to max _ distance _ d2 zoi. The invention introduces max _ distance _ d2zoi, normalizes the distance (D (r), zoi (j)) values, and adopts the normalized distance to process the distance weighting factor, so that the distance _ weight (D (r), zoi (j)) weight is dynamically expanded and contracted in a limited controllable range, thereby further achieving the effect of congestion condition regulation and control.

Fig. 3 is a schematic main flow chart of an intelligent ticket advance selling method according to a second embodiment of the present invention, and as shown in fig. 3, the implementation process of the intelligent ticket advance selling method may further include:

step S301, the entrance ticket pre-selling core service is started.

Step S302, determining whether the start is the first start, if so, performing step S303 and then performing step S304, otherwise, directly performing step S304.

In step S303, all parameters (e.g., the respective modules in fig. 4 or the respective modules in fig. 5) are started and initialized. Specifically, the parameter configuration may be performed through a preset interface (for example, the parameter configuration may be implemented by a parameter configuration module), for example: configuring a mapping relation between the zoi and the object recognition device, for example, associating 100 object recognition devices with 10 zoi information, there are point locations of the 100 object recognition devices, where 1-10 th cameras (1) -10 belong to the zoi (1), 10-20 th cameras (10) -20 belong to the zoi (2), and so on. A threshold of the number of repeated acquisitions, such as Repeat, is configured to be 10. And configuring a maximum time interval threshold for repeated capture, such as wander _ interval ═ 30 min. The configuration repeatedly captures different object recognition device number thresholds, such as S-3. The number of inlets d (R) is configured, for example, R ═ 4. And (4) configuring the guest capacity, such as vistor _ capacity being 2000. And configuring a sub-period, for example, P ═ 10, the sub-periods are [8:00-9:00], … [17:00-18:00], and the uniform distribution weight config _ weight is 1/R. Loitering factors are configured, such as k1 ═ 1.5, and k _ dist ═ 3. And configuring the number of the hot spot areas, such as j being 10.

In step S304, the d (r) th entry, the time period t _ duration (p), and the allowable human traffic psnflow (d (r), t _ duration (p)) are obtained.

Assuming that there are d (R) entrances in a scenic spot, the value range of R is 1,2, … R, the capacity of conventional tourists that the scenic spot can accommodate is vistor _ capacity, the ticketing time period T, for example, [ T _ start, T _ start + T ] is a ticketing time period, the ticketing time T is divided to obtain [ T (1) -T (2) ], [ T (P), T (P +1) ] … [ T (P), T (P +1) ] for totaling P sub-time periods; the p-th time period is denoted by T _ duration (p), which is obviously T _ duration (p) [ T (p), T (p +1) ]; typically we denote an individual ticketing period by an integer of one hour, e.g. [8:00-9:00], … [17:00-18:00 ].

Preferably, the current weather is represented by a weather variable, and the value can be: sunny, rainy, snowy, or the like. Weather has positive and negative influence on ticket selling, and factor _ weather (weather) is defined to represent influence factors, for example, influence factors on clear days are defined to be 1, influence factors on rainy days are defined to be 0.7, influence factors on the ticket selling amount of scenic spots caused by rainy days are represented, and more tickets can be sold in advance on clear days. In addition, health _ state is used for indicating the health status of the current visitor, for example, the health status of the visitor on the current day can be obtained by acquiring the epidemic situation health code in real time in combination with factors such as cold, epidemic situation and the like, 1 is used for indicating health, and 0 is used for indicating unhealthy status. The tourist ID (such as ID card id and mobile phone number id) can be carried to call a third party public queryable health code Internet application program web interface to feed back health data in real time.

In step S305, a plurality of visitors who have entered the scenic spot are frequently moved, captured and captured by an object recognition device (e.g., a camera) for capturing a snapshot.

Step S306, traversing the captured visitor list faceid (i) information record for the current zoi _ id and the current time subset T _ duration (q), and obtaining the loitering visitor and the non-loitering visitor according to the following filtering conditions:

In step S307, after all the zoi _ id traverses, the current time subset T _ duration (q) is calculated for the current zoi _ id, and the effective number psn _ effective (zoi (j), T _ duration (p)) of the hot spot area is calculated.

Step S308, calculating the distances (D (r), zoi (j)) for D (r) to reach j hot spot areas.

In step S309, by calculating the hot spot area distance weighting feature distance _ weight (d (r), zoi (j)) of the entry d (r), the congestion status utility function yield _ effectiveness (d (r), zoi (j), t _ duration (p)) when the entry d (r) reaches the hot spot area zoi (j) is calculated.

Step S310, calculating a congestion condition utility function of the entrances D (r) (D (r) and t _ duration (p)) reaching all the hot spots of the scenic region, and acquiring a non-congestion entrance list entry _ asc _ uncrowded.

Step S311, receiving a ticket purchase request from the guest at the entrance d (r), and determining that the guest has the preliminary qualification for admission. Specifically, whether the user _ id has the preliminary admission qualification can be judged according to the vistor _ limits (user _ id) so as to meet the requirement of preliminary admission qualification

vistor_permits(user_id)＝health_state*has_tickets(user_id)

It can be seen that when the health _ state does not satisfy the epidemic prevention requirement or for other reasons, the health _ state does not have the preliminary qualification of admission.

Step S312, determining that the entry exists in the non-congested entry list, and obtaining a remainder ticket corresponding to the entry to determine that the guest is allowed to enter.

Fig. 4 is a schematic diagram of the main modules of the intelligent ticket advance selling device according to the first embodiment of the present invention, and as shown in fig. 4, the intelligent ticket advance selling device comprises a parameter configuration module 401, a face capture and recognition module 402 and a multi-feature fused ticket advance selling module 403. The parameter configuration module 401 obtains the flow rate of people allowed in the preset time period of each entrance, determines an entrance list with surplus tickets according to the preset number of entrance tickets corresponding to each current entrance, and further obtains entrance position information of the surplus tickets to calculate the distance between each entrance and each hotspot area. The face snapshot and recognition module 402 performs tourist recognition through object recognition equipment corresponding to the hot area, acquires a tourist browsing data information list of the hot area, and then calls a loitering judgment component to obtain loitering tourists from the tourist browsing data information list so as to determine the effective number of tourists in the hot area. The multi-feature fused entrance ticket pre-selling module 403 calls a preset utility model, calculates the congestion status of the entrance to all the hot spot areas based on the distance between the entrance with the remaining tickets and each hot spot area and the effective number of people in each hot spot area, and further determines the non-congestion entrance from the entrance list with the remaining tickets so as to adjust the number of the remaining tickets at each entrance in the entrance list with the remaining tickets.

In some embodiments, after the calculation of the congestion status of the entrance to all hot spot areas by the multi-feature fused entrance ticket pre-sale module 403, the method includes:

In some embodiments, the face capture and recognition module 402 invokes the loiter determination component to retrieve loiter guests from the guest browsing data information list, including:

In some embodiments, the face capture and recognition module 402 determines the number of active people in the hotspot region, including:

In some embodiments, the multi-feature fused ticket pre-sale module 403 calculates the congestion status of the entrance to all hot spot areas, including:

As another embodiment, as shown in fig. 5, the intelligent ticket pre-selling device may further include a ticket pre-selling core service module 404, a visitor face data storage module 405, a geographic marking module 406, a visitor statistical analysis module 407, and a ticket collecting module 408.

The ticket pre-sale core service module 404 is used for starting and initializing other modules.

The guest face data storage module 405 registers and stores attribute information such as a unique id (e.g., identification number, mobile phone number, etc.), name, face image, etc. of the guest. For example, the face capturing and recognizing module 402 may compare and calculate the features of the face image data captured by the object recognition device with the face data pre-stored in the guest face data storage module 405 (for example, by using open source software such as FaceNet, various face recognition algorithms implemented in github, etc.), and generate the face recognition information after matching.

The geo-tagging module 406 may deploy a plurality of object recognition devices to N discrete points, and obtain location information of each object recognition device; and clustering or averaging the position information of the object identification equipment to obtain a hot spot region, and further generating a mapping relation between the hot spot region and the object identification equipment. As can be seen, the geographic labeling module 406 may record longitude and latitude information of the object recognition device in advance for the deployed object recognition device, so as to facilitate subsequent retrieval and calculation of trajectory data.

The tourist statistical analysis module 407 can identify the tourists through the object identification device corresponding to the hot spot area to obtain the behavior data and emotion data of the tourists, and further pull the target discrimination model from the discrimination model pool to obtain a corresponding discrimination result and send an alarm.

The ticket selling acquisition module 408 may receive an entrance entering request, and acquire the target attribute information of the guest to enter in the entrance entering request to determine that a preset entering condition is met; judging whether the entrance is marked or not, if so, rejecting the entrance entering request; if not, judging whether the current entrance reaches a preset current limit warning threshold value, if so, rejecting the entrance entering request, and if not, responding to the entrance entering request to permit the entrance.

It should be noted that the intelligent ticket advance selling method and the intelligent ticket advance selling device of the present invention have corresponding relation in the specific implementation content, so the repeated content is not described again.

Fig. 6 shows an exemplary system architecture 600 of an intelligent ticket advance sales method or an intelligent ticket advance sales device to which embodiments of the present invention can be applied.

As shown in fig. 6, the system architecture 600 may include

terminal devices

601, 602, 603, a network 604, and a server 605. The network 604 serves to provide a medium for communication links between the

terminal devices

601, 602, 603 and the server 605. Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

The guest may use the

terminal devices

601, 602, 603 to interact with the server 605 over the network 604 to receive or send messages, etc. The

terminal devices

601, 602, 603 may have installed thereon various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The

terminal devices

601, 602, 603 may be various electronic devices with smart ticket pre-sale screens and supporting web browsing, including but not limited to smart phones, tablets, laptop portable computers, desktop computers, and the like.

The server 605 may be a server that provides various services, such as a background management server (for example only) that supports shopping websites browsed by guests using the

terminal devices

601, 602, 603. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.

It should be noted that the intelligent ticket pre-selling method provided by the embodiment of the present invention is generally executed by the server 605, and accordingly, the computing device is generally disposed in the server 605.

It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data necessary for the operation of the computer system 700 are also stored. The CPU701, the ROM702, and the RAM703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a liquid crystal smart ticket reseller (LCD), and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 701.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a parameter configuration module, a face snapshot and recognition module and a multi-feature fused ticket pre-sale module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself.

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs, and when the one or more programs are executed by the device, the device comprises a function of acquiring the flow of people allowed in a preset time period of each entrance, so as to determine an entrance list with surplus tickets according to the preset number of entrance tickets corresponding to each current entrance, and further acquire entrance position information of the surplus tickets, so as to calculate the distance between each entrance and each hotspot area; identifying tourists through object identification equipment corresponding to the hot spot area, acquiring a tourist browsing data information list of the hot spot area, and calling a loitering judgment component to obtain loitering tourists from the tourist browsing data information list so as to determine the effective number of tourists in the hot spot area; and calling a preset utility model, calculating the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the effective number of people in each hot spot area, and further determining a non-congestion entrance from the entrance list with the surplus tickets so as to adjust the number of the surplus tickets at each entrance in the entrance list with the surplus tickets.

According to the technical scheme of the embodiment of the invention, the problems of low efficiency and poor real-time performance of the conventional scenic spot passenger flow management and control and ticket pre-sale can be solved.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent ticket pre-sale method, comprising:

acquiring the flow of people allowed in a preset time period of each entrance, determining an entrance list of the surplus tickets according to the preset number of entrance tickets corresponding to each current entrance, and further acquiring entrance position information of the surplus tickets to calculate the distance between each entrance and each hotspot area;

identifying tourists through object identification equipment corresponding to the hot spot area, acquiring a tourist browsing data information list of the hot spot area, and calling a loitering judgment component to obtain loitering tourists from the tourist browsing data information list so as to determine the effective number of tourists in the hot spot area;

and calling a preset utility model, calculating the congestion condition of the entrance to all the hot spot areas based on the distance between the entrance with the surplus tickets and each hot spot area and the effective number of people in each hot spot area, and further determining a non-congestion entrance from the entrance list with the surplus tickets so as to adjust the number of the surplus tickets at each entrance in the entrance list with the surplus tickets.

2. The method of claim 1, wherein calculating the congestion status of the entry to all hot spot areas comprises:

3. The method of claim 2, wherein adjusting the number of remaining tickets for each entry in the list of entries having remaining tickets comprises:

4. The method of claim 1, wherein invoking the loitering determination component to loiter the tourist from the tourist navigation data information list comprises:

5. The method of claim 4, wherein determining the number of active people in the hotspot region comprises:

6. The method of claim 1, wherein calculating the congestion status of the entry to all hot spot areas comprises:

7. The method of claim 1, wherein before the guest identification by the object identification device corresponding to the hotspot area, the method comprises:

8. The method of any of claims 1-7, further comprising:

9. An intelligent ticket advance selling device, comprising:

the parameter configuration module is used for acquiring the flow of people allowed in the preset time period of each entrance, determining an entrance list with surplus tickets according to the preset number of entrance tickets corresponding to each current entrance, and further acquiring entrance position information of the surplus tickets to calculate the distance between each entrance and each hotspot area;

10. The apparatus of claim 9, wherein the multi-feature fused ticket pre-sale module, after calculating the congestion status of the entrance to all hot spot areas, comprises:

11. The apparatus of claim 10, further comprising:

12. The apparatus of claim 9, wherein the face capture and recognition module invokes the loiter determination component to retrieve the loiter visitor from the visitor view data information list, comprising:

13. The apparatus of claim 12, wherein the face capture and recognition module determines the number of active people in the hotspot region, comprising:

14. The apparatus of claim 9, wherein the multi-feature fused ticket pre-sale module calculates congestion status of the entrance to all hot spot areas, comprising:

15. The apparatus of claim 9, further comprising:

16. The apparatus of any of claims 9-15, further comprising:

17. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

18. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-8.