Method and device for generating recommended tour routes, and computer-readable storage medium

Abstract

The embodiment of the present application provides a method and device for generating a recommended tour route, and a computer-readable storage medium, which can determine the tour path of tourists through surveillance images, and recommend suitable tour routes according to the real-time number of tourists at different tour locations in the scenic area. The method for generating a recommended tour route includes: collecting surveillance images taken by cameras set at different tour locations in the scenic area; identifying the number of tourists appearing in the surveillance images; counting the total number of tourists appearing in the surveillance images of each tour location within the current preset time period; and determining the current recommended tour route according to the total number of tourists at each tour location within the current preset time period.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for generating a recommended tour route, and a computer-readable storage medium. Background Art

[0002] The current method for recommending scenic spot tour routes needs to be based on the big data of a large number of tourists' historical tour routes for statistics and then make recommendations. When tourists visit scenic spots, they usually rely on the support of wireless communication modules such as Bluetooth and Wi-Fi on the tourists' mobile devices, and use wireless communication devices set at different locations in the scenic area to communicate with the wireless communication modules of the tourists' mobile devices to determine the current location of the tourists. Tourists need to turn on these functions of their mobile devices. If the tourists do not turn on the corresponding functions of their mobile devices, the location of the tourists cannot be determined. The inventors found that in the above-mentioned related technologies, since it is impossible to accurately count the number of tourists at different tour locations in the scenic area, it is also impossible to recommend real-time tour routes to tourists based on the real-time tour conditions in the scenic area. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a method and device for generating a recommended tour route, and a computer-readable storage medium, which can determine the tour path of tourists through monitoring images, and recommend suitable tour routes based on the real-time number of tourists at different tour locations in the scenic area.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a recommended tour route, comprising: collecting surveillance images taken by cameras installed at different tour locations in a scenic area; identifying the number of tourists appearing in the surveillance images; counting the total number of tourists appearing in the surveillance images of each tour location within a current preset time period; and determining the current recommended tour route based on the total number of tourists at each tour location within the current preset time period.

[0005] In a possible implementation, the current recommended tour route is determined based on the total number of tourists at each tour location within the current preset time period, including: obtaining the preset tour route; adjusting the tour order of the corresponding tour locations in the preset tour route based on the total number of tourists at each tour location within the current preset time period.

[0006] In a possible implementation, the tour order of corresponding tour locations in a preset tour route is adjusted according to the total number of tourists at each tour location in a current preset time period, including: in the preset tour route, determining the tour locations whose total number of tourists in the current preset time period exceeds a preset threshold, and obtaining a congested tour location; within a preset range near the congested tour location, searching for a tour location whose total number of tourists is less than a preset threshold and which is closest to the congested tour location, to obtain an alternative tour location; and replacing the congested tour location in the preset tour route with the alternative tour location, to obtain the current recommended tour route.

[0007] In a possible implementation, the touring order of the corresponding touring locations in the preset touring route is adjusted according to the total number of tourists at each touring location within the current preset time period, including: in the preset touring route, determining the touring locations whose total number of tourists within the current preset time period exceeds a preset threshold to obtain congested touring locations; and postponing the touring order of the congested touring locations to obtain the current recommended touring route.

[0008] In a possible implementation, obtaining a preset tour route includes: receiving a route recommendation request sent by a target tourist through a client; obtaining a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the target tourist's account, and each tag is used to represent an attribute feature of the target tourist; among multiple candidate tour routes, selecting a tour route with the largest number of matches with tags in the tag combination to obtain a preset tour route, wherein each of the multiple candidate tour routes corresponds to one or more tags.

[0009] In a possible implementation, multiple candidate tour routes are obtained in the following manner: extracting human body recognition features from surveillance images taken at different times and different tour locations; matching the extracted human body recognition features with human body recognition features in a tourist feature library to identify tourists appearing in the surveillance images, wherein the tourist feature library stores human body recognition features of multiple tourists collected in advance; recording the tour location and tour time of each tourist based on the recognition result of each surveillance image to obtain the tour route of each tourist; among the tour routes of multiple tourists, selecting multiple tour routes with the largest number of people having the same tour route to obtain multiple candidate tour routes; obtaining a preset label combination for each tourist; and determining the label corresponding to each candidate tour route based on the preset label combination of the tourist corresponding to each candidate tour route.

[0010] In a possible implementation, after receiving a route recommendation request sent by a target tourist through a client, the method further includes: obtaining a surveillance image of the target tourist's most recent appearance; identifying human behavior characteristics of the target tourist in the surveillance image; judging whether the target tourist has a target behavior based on the human behavior characteristics; and if the judgment result is yes, pushing a message corresponding to the target behavior to the tourist.

[0011] In the second aspect, an embodiment of the present application provides a device for generating a recommended tour route, which includes: a collection unit for collecting surveillance images taken by cameras installed at different tourist locations in a scenic area; an identification unit for identifying the number of tourists appearing in the surveillance images; a counting unit for counting the total number of tourists appearing in the surveillance images of each tourist location within a current preset time period; and a determination unit for determining the current recommended tour route based on the total number of tourists at each tourist location within the current preset time period.

[0012] In a possible implementation, the determination unit includes: a first acquisition module, used to acquire a preset tour route; a first adjustment module, used to adjust the tour order of corresponding tour locations in the preset tour route according to the total number of tourists at each tour location within a current preset time period.

[0013] In a possible implementation, the first adjustment module includes: a first determination module, which is used to determine, in a preset tour route, a tour location whose total number of tourists exceeds a preset threshold in a current preset time period, to obtain a congested tour location; a search module, which is used to search, within a preset range near the congested tour location, for a tour location whose total number of tourists is less than a preset threshold and which is closest to the congested tour location, to obtain an alternative tour location; and a replacement module, which is used to replace the congested tour location in the preset tour route with an alternative tour location, to obtain the current recommended tour route.

[0014] In a possible implementation, the first adjustment module includes: a second determination module, which is used to determine, in a preset tour route, the tour locations where the total number of tourists exceeds a preset threshold within a current preset time period, to obtain congested tour locations; and a second adjustment module, which is used to postpone the tour order of the congested tour locations to obtain the current recommended tour route.

[0015] In a possible implementation, a first acquisition module includes: a receiving module for receiving a route recommendation request sent by a target tourist through a client; a second acquisition module for acquiring a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the target tourist's account, and each tag is used to represent an attribute feature of the target tourist; a selection module for selecting, from a plurality of candidate tour routes, a tour route with the largest number of matches with tags in the tag combination to obtain a preset tour route, wherein each of the plurality of candidate tour routes corresponds to one or more tags.

[0016] In a possible implementation, the device also includes: a first acquisition unit, used to acquire multiple candidate tour routes, the first acquisition unit includes: an extraction module, used to extract human body recognition features from surveillance images taken at different times and different tour locations; a matching module, used to match the extracted human body recognition features with the human body recognition features in a tourist feature library to identify tourists appearing in the surveillance images, wherein the tourist feature library stores the human body recognition features of multiple tourists collected in advance; a recording module, used to record the tour location and tour time of each tourist according to the recognition result of each surveillance image, so as to obtain the tour route of each tourist; a selection module, used to select multiple tour routes with the largest number of people with the same tour route from the tour routes of multiple tourists, to obtain multiple candidate tour routes; a third acquisition module, used to acquire a preset label combination for each tourist; a third determination module, used to determine the label corresponding to each candidate tour route according to the preset label combination of the tourist corresponding to each candidate tour route.

[0017] In a possible implementation, the device also includes: a second acquisition unit, used to obtain the surveillance image of the target tourist's most recent appearance after receiving a route recommendation request sent by the target tourist through a client; an identification unit, used to identify the human behavior characteristics of the target tourist in the surveillance image; a judgment unit, used to judge whether the target tourist has a target behavior based on the human behavior characteristics; and a push unit, used to push a message corresponding to the target behavior to the tourist if the judgment result is yes.

[0018] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method provided in the first aspect or any optional implementation of the first aspect.

[0019] One of the above technical solutions has the following beneficial effects: by collecting surveillance images taken by cameras installed at different tourist locations in a scenic area; identifying tourists appearing in the surveillance images according to image recognition features in a tourist feature library, wherein the tourist feature library stores image recognition features of multiple tourists, and the image recognition features of each tourist include face recognition features and body recognition features extracted from ticket checking images of the corresponding tourists taken by cameras installed at ticket checking locations of the scenic area, and the image recognition features of each tourist are bound to the tourist identity identifier collected by the ticket checking equipment installed at the ticket checking location; according to the shooting location and shooting time of the surveillance images of the identified tourists, The tour path of each tourist is recorded in the database; multiple tourists in the tourist feature database are divided into multiple categories according to attribute characteristics, wherein the attribute characteristics of each tourist include human body recognition characteristics, and / or group characteristics obtained according to the tourist identity identification; for each category of tourists, a recommended tour route corresponding to the category of tourists is generated according to the tour paths of tourists belonging to the category, so that the statistics of tourists' tour paths are more accurate, without relying on tourists' mobile devices or corresponding card swiping devices configured in the scenic area, saving the operating costs of the scenic area, and recommending recommended tour routes that are more in line with tourists' personalities to tourists based on more accurate tour path statistics results, thereby improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a flow chart of an optional embodiment of a method for generating a recommended tour route provided in an embodiment of the present application;

[0022] Figure 2 This is an interactive diagram of a method for generating a recommended tour route provided in an embodiment of the present application. Figure 1 ;

[0023] Figure 3 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0024] Figure 4 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0025] Figure 5 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0026] Figure 6 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0027] Figure 7 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0028] Figure 8 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0029] Fig. 9 It is a flowchart diagram of another optional embodiment of the method for generating a recommended tour route provided in the embodiment of the present application;

[0030] Fig.10 It is a schematic diagram of a scene of obtaining a ticket checking image in the method for generating a recommended tour route provided in an embodiment of the present application;

[0031] Fig.11 This is an interactive diagram of a method for generating a recommended tour route provided in an embodiment of the present application. Figure 2 ;

[0032] Fig.12 This is an interactive diagram of a method for generating a recommended tour route provided in an embodiment of the present application. Figure 3 ;

[0033] Fig.13 It is a schematic diagram of the communication architecture of the method for generating a recommended tour route provided in an embodiment of the present application;

[0034] Fig.14 It is a module schematic diagram of the monitoring terminal provided in the embodiment of the present application;

[0035] Fig.15 This is an interactive diagram of a method for generating a recommended tour route provided in an embodiment of the present application. Figure 4 ;

[0036] Fig.16 It is a schematic diagram of a historical tour route generated by the method for generating a recommended tour route provided in an embodiment of the present application;

[0037] Fig.17 It is a schematic diagram of the functional modules of the device for generating the recommended tour route provided in the embodiment of the present application. DETAILED DESCRIPTION

[0038] The terms used in the embodiments of the present application are only used to explain specific embodiments, and are not intended to limit the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should be understood that the term "and / or" used in this article is only a kind of association relationship describing the associated object, indicating that there can be three kinds of relationships, for example, A and / or B, which can be represented by: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are a kind of "or" relationship. It should be understood that although the terms first, second, third, etc. may be used to describe a certain term in the embodiments of the present application, it should not be limited to these terms. The first, second, and third are only used to distinguish these terms from each other. Depending on the context, the word "if" used in the embodiments of the present application can be interpreted as "at the time of..." or "when..." or "in response to...".

[0039] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below in conjunction with the accompanying drawings. It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0040] The embodiment of the present application provides a method for generating a recommended tour route. The method provided by the embodiment of the present application can be executed by a server, and the recommended tour route can be provided to a client connected to the server, such as Figure 1 As shown, the method for generating a recommended tour route provided in the embodiment of the present application may include the following steps:

[0041] Step 101, collecting monitoring images taken by cameras installed at different sightseeing locations in the scenic area.

[0042] A scenic area is an area in a physical space, and the scenic area includes different tourist locations. Each tourist location is a location in the scenic area, and each tourist location corresponds to a node in a tourist route. The tourist route includes multiple tourist location nodes arranged in a certain order. At least one camera is set at each tourist location to shoot monitoring images in real time. The shooting cycle interval can be set, for example, it can be set to shoot once every 1 minute, or once every 5 minutes. The specific shooting cycle setting can be determined according to the specific situation.

[0043] Step 102, identifying the number of tourists appearing in the surveillance image.

[0044] Identifying the number of tourists appearing in the surveillance image is equivalent to performing face recognition (and / or body recognition) in the surveillance image. After identifying all the people appearing in the surveillance image, the number of people is determined to obtain the number of tourists. Face recognition or body recognition can use some image recognition algorithms provided in existing related technologies. For example, a pre-trained face recognition neural network model can be used to identify all faces in the image, determine the number of faces, and obtain the number of tourists.

[0045] Step 103, counting the total number of tourists appearing in the monitoring image of each tourist location within the current preset time period.

[0046] The total number of tourists at each tourist location within a preset time before the current moment (within the current preset time period) is counted. For each tourist location, all surveillance images of the camera set for this tourist location within this period of time (within the current preset time period) can be determined, and the number of tourists identified in these images can be added together to obtain the total number of tourists that appeared at each tourist location within this period of time.

[0047] Step 104, determining the current recommended tour route according to the total number of tourists at each tour location within the current preset time period.

[0048] The total number of tourists counted in step 103 can indicate the passenger flow of a tourist location in the current preset time period. A high total number of tourists indicates that the tourist location is in the peak period during this period, and the passenger flow is large. A low total number of tourists indicates that the location is not in the peak period during this period, and the passenger flow is small. According to the total number of tourists at each tourist location in the current preset time period, the real-time passenger flow of each tourist location can be determined, and then according to the passenger flow, whether to put a tourist location in the recommended tourist route and the tour order of each tourist location in the recommended tourist route are determined to obtain the current recommended tourist route.

[0049] Optionally, determining the current recommended tour route may be in response to a recommendation request sent by the client, where the recommendation request is used to request the server to send the recommended tour route. After the server determines the recommended tour route, the recommended tour route may be sent to the client for display on the client. For example, the interactive interface when the recommended tour route is displayed on the client may be as follows: Figure 2 As shown, the tour route may include: entrance - tour location A - tour location B - tour location C - tour location D - exit. Optionally, the content sent by the server to the client may include node (tour location) identifiers of the recommended tour route arranged in order (tour order). After receiving the content sent by the server, the client connects the positions of each node identifier on the map according to the tour order to display the recommended tour route.

[0050] Optional, such as Figure 3 As shown, step 104 determines the current recommended tour route according to the total number of tourists at each tour location within the current preset time period, which may include the following steps:

[0051] Step 1041, obtaining a preset tour route;

[0052] Step 1042, adjusting the tour order of the corresponding tour locations in the preset tour route according to the total number of tourists at each tour location in the current preset time period.

[0053] That is, the recommended tour route is to adjust a default tour route (preset tour route) according to the real-time passenger flow in the current scenic area to obtain the current recommended tour route. The adjustment method is to adjust the tour order according to the current passenger flow of each tour location in the preset tour route.

[0054] The adjustment rules used to adjust the tour order can be preset rules, such as Figure 4 As shown, in a possible implementation, step 1042 adjusts the tour order of the corresponding tour locations in the preset tour route according to the total number of tourists at each tour location in the current preset time period, which may include the following steps:

[0055] Step 1421, in the preset tour route, determine the tour locations where the total number of tourists exceeds the preset threshold in the current preset time period, and obtain the congested tour locations;

[0056] Step 1422, within a preset range near the congested tourist location, searching for a tourist location with a total number of tourists less than a preset threshold and closest to the congested tourist location to obtain an alternative tourist location;

[0057] Step 1423, replacing the congested tour location in the preset tour route with the alternative tour location to obtain the current recommended tour route.

[0058] That is, a tourist location that is not in the preset tourist route (alternative tourist location) is used to replace the congested tourist location in the preset tourist route. The selected alternative tourist location is a tourist location with a total number of tourists less than a preset threshold and the closest distance to the congested tourist location.

[0059] For example, the preset tour route is tour location A-tour location B-tour location C-tour location D-tour location E. The total number of tourists visiting tour location B during the current preset period exceeds 1,000. Within 200 meters around tour location B, the tour locations with a total number of tourists less than 1,000 during the current preset period are searched, and tour location F, tour location G, and tour location H are obtained. Among them, tour location F is closest to tour location B, so tour location F replaces tour location B, and the current recommended tour route is obtained: tour location A-tour location F-tour location C-tour location D-tour location E. After the server obtains the current recommended tour route, it can push it to the client that requests the recommended tour route, so as to achieve the effect of guiding tourists to locations with less passenger flow.

[0060] In another possible implementation, Figure 5 As shown, step 1042 adjusts the tour order of the corresponding tour locations in the preset tour route according to the total number of tourists at each tour location in the current preset time period, which may include the following steps:

[0061] Step 1424, in the preset tour route, determine the tour locations where the total number of tourists in the current preset time period exceeds the preset threshold, and obtain the congested tour locations;

[0062] Step 1425, postpone the tour order of the congested tour location to obtain the current recommended tour route.

[0063] The tour order of congested tour locations can be pushed back by a preset value. For example, the preset tour route is tour location A-tour location B-tour location C-tour location D-tour location E, and the total number of tourists visiting tour location B during the current preset time period exceeds 1,000. Tour location B is pushed back by 2 positions, and the current recommended tour route is tour location A-tour location C-tour location D-tour location B-tour location E.

[0064] Optional, such as Figure 6 As shown, the above step 1041 of obtaining the preset tour route may include the following steps:

[0065] Step 1411, receiving a route recommendation request sent by a target tourist through a client;

[0066] Step 1412, obtaining a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the target tourist's account, and each tag is used to represent an attribute feature of the target tourist;

[0067] Step 1413 , among the multiple candidate tour routes, select a tour route that has the largest number of matching tags in the tag combination to obtain a preset tour route, wherein each of the multiple candidate tour routes corresponds to one or more tags.

[0068] For example, a tourist logs in to a client through an account, clicks a button icon of "route recommendation" in the interface of the client, and then the client sends a route recommendation request to the server. After receiving the route recommendation request, the server obtains all tags corresponding to the tourist account, and each tag can represent an attribute feature. For example, the attribute feature of the gender attribute is "female", the attribute feature of the age attribute is "born in the 1970s", the attribute feature of the occupation attribute is "lawyer", and the attribute features of the personality attribute include "humorous", "cheerful", etc. The tag of each tourist can be automatically generated according to the personal information filled in by the tourist, or can be selected by the tourist himself. There are three existing candidate tour routes. The tags corresponding to the first candidate tour route include "male", "female", "student", "born in the 2000s", and "humorous". The tags corresponding to the second candidate tour route include "female", "student", "lawyer", "cheerful", "master", "star chasing", "born in the 1970s", and "born in the 1980s". The tags corresponding to the third candidate tour route include "male", "doctor", "calm", "born in the 1960s", and "Beijing". The candidate tour route with the largest number of tags matching the tourist is the second one, and the second candidate tour route is selected as the preset tour route.

[0069] The candidate tour routes may be the most popular tour routes calculated based on historical tourist tour records. Then, for each candidate tour route, the tags with the largest number of tourist tags are calculated as the tags of the candidate tour route. An optional implementation is that before executing step 1413, Figure 7 The following steps are shown to obtain multiple candidate tour routes:

[0070] Step 1051, extracting human recognition features from surveillance images taken at different times and different sightseeing locations;

[0071] Step 1052, matching the extracted human body recognition features with human body recognition features in a tourist feature library to identify tourists appearing in the surveillance image, wherein the tourist feature library stores human body recognition features of a plurality of tourists collected in advance;

[0072] Step 1053, recording the sightseeing location and sightseeing time of each tourist according to the recognition result of each monitoring image, so as to obtain the sightseeing route of each tourist;

[0073] Step 1054, selecting multiple tourist routes with the largest number of visitors from among the multiple tourist routes, to obtain multiple candidate tourist routes;

[0074] Step 1055, obtaining a preset tag combination of each visitor;

[0075] Step 1056, determining the label corresponding to each candidate tour route according to the preset label combination of the tourists corresponding to each candidate tour route.

[0076] Through the above steps, multiple candidate tour routes and labels corresponding to each tour route can be obtained.

[0077] Optional, such as Figure 8 As shown, after executing step 1411 to receive the route recommendation request sent by the target tourist through the client, the method further includes the following steps:

[0078] Step 1061, obtaining the surveillance image of the target tourist's most recent appearance;

[0079] Step 1062, identifying the human behavior characteristics of the target tourist in the monitoring image;

[0080] Step 1063, judging whether the target tourist has the target behavior according to the human behavior characteristics;

[0081] Step 1064: If the judgment result is yes, a message corresponding to the target behavior is pushed to the visitor.

[0082] For example, a behavior recognition algorithm is configured in the server. The behavior recognition algorithm is a technology for identifying and analyzing the behavior of pedestrians by analyzing video data. This technology has been widely used in the fields of video classification, human-computer interaction, security monitoring, etc. The embodiment of the present application will not repeat the specific implementation of the behavior recognition algorithm. Optionally, a human behavior recognition algorithm based on deep learning can be used to identify human behavior characteristics, such as behavior recognition based on unsupervised learning, behavior recognition based on convolutional neural networks, methods based on recurrent neural networks and some extended models, etc. The server can analyze the individual behavior of tourists and use the behavior recognition algorithm to assist in identifying tourists appearing in the monitoring image. Furthermore, the human behavior recognition algorithm is used to determine whether the tourist has a certain specific behavior, such as the willingness to purchase goods. For example, if the behavior recognition algorithm identifies that the tourist has been watching the product for more than a preset time, it means that the tourist may have the intention to purchase. The server can push some product introduction information, promotional activity information, etc. to the client of the tourist.

[0083] In order to further illustrate the method for generating the recommended tour route provided in the embodiment of the present application, the following will be combined with Figures 9 to 16The implementation method of the method for generating a recommended tour route provided in an embodiment of the present application in a specific application scenario is described in detail.

[0084] like Fig. 9 As shown, the method for generating a recommended tour route provided in the embodiment of the present application includes the following steps:

[0085] Step 201: The visitor scans the QR code at the ticket checking device.

[0086] The ticket checking device can be set at the entrance of the scenic spot. An optional implementation of the ticket checking device is as follows: Fig.10 The ticket gate 301 shown can be set at the ticket checking position of the scenic area. A ticket checking terminal 304 is arranged inside the ticket gate 301. The ticket gate 301 is also equipped with a camera 303 and a QR code scanning port 302 that can communicate with the ticket checking terminal 304.

[0087] Before entering the scenic spot, tourists can open the pre-installed ticketing software on their mobile phones (such as Fig.11 Visitors can purchase tickets in real time or in advance to obtain the QR code corresponding to the ticket to enter the scenic spot (as shown in Fig.12 Visitors can point the QR code displayed on their mobile phone to Fig.10 The QR code scanning port 302 shown in the figure can capture the image of the QR code displayed on the tourist's mobile phone through the camera of the QR code scanning port 302, and the ticket checking terminal 304 can receive the scanned QR code image.

[0088] 202. In response to the tourist's ticket checking operation of scanning the QR code, the ticket checking terminal 304 may control the camera 303 to capture the image of the tourist.

[0089] After the visitor performs the ticket checking operation by scanning the QR code, the ticket checking terminal 304 receives the QR code image captured by the QR code scanning port 302. In response to the ticket checking terminal 304 receiving the QR code image, the ticket checking terminal 304 can control the camera 303 to capture a visitor's entry image, which is referred to as the ticket checking image in the embodiment of the present application.

[0090] 203. Based on the ticket checking image, the image recognition features of the tourists can be extracted.

[0091] Image recognition features may include facial recognition features and body recognition features of tourists. Facial recognition features can be extracted using some existing facial recognition technologies, and facial recognition features in ticket inspection images can be extracted based on technologies such as deep learning or neural network models. Body recognition features are attribute features of the human body that can be used to classify tourists, such as one or more attribute features such as age, gender, height, and clothing color, which can be processed using some existing image extraction technologies. The embodiment of the present application does not specifically limit the method for extracting image recognition features.

[0092] It should be noted that this step can be executed by the ticket checking terminal 304. Optionally, when the computing pressure of the ticket checking terminal 304 is too large (for example, whether the computing pressure of the ticket checking terminal 304 is too large can be judged based on the processing time for extracting the image recognition features), the ticket checking terminal 304 can send the ticket checking image to the server 300, and the server 300 will extract the image recognition features in the ticket checking image. The specific configuration method can be determined according to the situation, and the embodiment of the present application is not limited to this.

[0093] 204. After receiving the QR code image for ticket inspection, the ticket checking terminal 304 obtains the visitor identity in the QR code information.

[0094] The QR code information carried in the QR code image may include a tourist identity identifier, which may include one or more of the following information: name, ID number, ticket purchase account number, mobile phone number, and the tourist identity identifier is used to mark the tourist.

[0095] 205. Obtain group characteristics of tourists based on their identity identifiers.

[0096] After obtaining the tourist identity, the ticket checking terminal 304 can send the tourist identity to the server 300 through the wireless communication module configured by itself. Fig.13 As shown, the server 300 can query the associated server 307 for the group characteristics of the tourists corresponding to the tourist identification, such as age, gender, work industry, hobbies, etc., according to the tourist identification. An optional implementation is that if the group characteristics and the human body recognition characteristics include the same type, the human body recognition characteristics, such as age and gender, can be used as the standard. This is because the ticket purchaser may not be the tourist himself, and the real characteristics extracted from the image of the tourist entering the scenic spot can be used as the standard.

[0097] It should be noted that step 202 and step 204 are executed after step 201 is executed, but there is no sequence relationship between step 202 and step 204.

[0098] 206. The attribute characteristics of tourists include image recognition characteristics and group characteristics of tourists. After obtaining the image recognition characteristics and group characteristics of tourists, the attribute characteristics of tourists are stored in the tourist database of the scenic spot.

[0099] The scenic spot visitor database (visitor feature database) can be stored by the server 300, or can be stored by other database servers that can communicate with the server 300. The scenic spot visitor database can include the attribute features of the visitors entering the scenic spot, wherein the image recognition features of the visitors and the identity identifiers of the visitors are bound. Among them, the scenic spot visitor database also includes a visitor database of the day, and the data in the visitor database of the day is cleared on a daily basis. For example, the data in the visitor database of the day is cleared at 0:00 every day, so that the information stored in the visitor database of the day is the attribute features of the visitors who visited the scenic spot on that day. Setting up the visitor database of the day improves the efficiency of the server 300 in extracting the image recognition features of the visitor of the day, and facilitates the server 300 to provide more real-time services for the visitors of the day.

[0100] 207. Collect surveillance images from multiple locations within the scenic area.

[0101] In addition to the ticket inspection terminal 304 provided at the entrance of the scenic spot, which has a camera, monitoring terminals including cameras are also provided at different locations within the scenic spot, such as Fig.13 As shown, it includes monitoring terminal 305, monitoring terminal 306, ... and so on. An optional implementation of the structure of monitoring terminal 305 is as follows Fig.14 As shown, it may include a camera 3051 , a micro-processing unit 3053 and a wireless communication module 3052 , wherein the wireless communication module 3052 is used to communicate with the server 300 .

[0102] The microprocessing unit 3053 can execute some preset instructions. For example, it can respond to the image acquisition instruction sent by the server 300, control the camera 3051 to capture the surveillance image, and use the wireless communication module 3052 to send the surveillance image to the server 300. For another example, the microprocessing unit 3053 can perform preset processing on the surveillance image collected by the camera 3051 to extract image recognition features in the surveillance image.

[0103] The monitoring terminals 305 and 306 can collect monitoring images of corresponding positions at a preset period. Optionally, the server 300 can control the collection period of the monitoring terminals 305 and 306. When the monitoring terminals 305 and 306 are installed on a controllable pan-tilt head, the server 300 can also control the movement and rotation of the pan-tilt head installed on the monitoring terminals 305 and 306 to achieve the purpose of controlling the shooting angle of the monitoring terminals 305 and 306.

[0104] 208. Extract image recognition features from surveillance images.

[0105] The microprocessing unit 3053 of the monitoring terminal 305 can perform preset processing on the monitoring image collected by the camera 3051. For example, the microprocessing unit 3053 can include a computer-readable storage medium, in which program instructions of an algorithm capable of executing an algorithm for extracting image recognition features (including face recognition features and body recognition features) from the monitoring image are stored. The algorithm can be the same as the algorithm for extracting image recognition features from the ticket inspection image by the ticket inspection terminal 304. When the instructions are executed, the microprocessing unit 3053 can extract the image recognition features from the monitoring image captured by the camera 3051.

[0106] Optionally, when the current processing capacity of the microprocessor unit 3053 of the monitoring terminal 305 is insufficient (for example, the time required to process a monitoring image exceeds a preset time, or the time required to respond to information sent by the server 300 exceeds a preset time), the monitoring terminal 305 may send the monitoring image directly to the server 300, and the server 300 will extract image recognition features from the monitoring image, thereby maximizing the utilization of the server 300 and the monitoring terminal equipment installed in the scenic area.

[0107] 209. Compare the image recognition features of the ticket inspection image and the image recognition features of the surveillance image to identify the tourists appearing in the surveillance image.

[0108] This step can be performed by the server 300. The server 300 obtains the image recognition features of the tourists in the tourist database of the day and compares them with the image recognition features in the surveillance image. The specific comparison algorithm can use the target re-identification algorithm of the existing technology, the trained image recognition neural network algorithm, etc. The embodiment of the present application does not limit this and will not be repeated here.

[0109] Optionally, facial recognition features may be used to preferentially identify tourists appearing in surveillance images. Since some tourists appearing in surveillance images may not face the camera directly, resulting in no surveillance images from which facial recognition features can be extracted, human body recognition feature recognition technology may be used to identify tourists appearing in surveillance images.

[0110] 210. In the scenic spot tourist database, record the tour route of each tourist.

[0111] The tourist's tour path includes the tourist's tour location and tour time. The tour location can be determined according to the shooting location of the surveillance image that identifies the tourist, and the tour time can be determined according to the shooting time of the surveillance image that identifies the tourist. The shooting location of the surveillance image is the location of the monitoring terminal that shoots the surveillance image, and the shooting time is the time when the monitoring terminal shoots the surveillance image. The tourist's tour location can be determined according to the shooting location. Specifically, the tour location can refer to the area covered by the monitoring terminal. For example, the tour location can be a pre-manually configured area that has a mapping relationship with the number of the monitoring terminal. According to the shooting time, the tourist's tour time can be determined. For example, if tourist f appears in the surveillance images shot at the first tour location at 10:35 and 10:45, and tourist f is not identified in the surveillance images of other locations from 10:35 to 10:45, then the tour time of tourist f at the first tour location is recorded as 10:35 to 10:45. After the tourist's sightseeing location and sightseeing time are determined according to the shooting location and shooting time, the tourist's sightseeing location and sightseeing time are recorded in the scenic spot tourist database, and the tourist's sightseeing path is recorded in the form of sightseeing location and sightseeing time.

[0112] 211. Categorize the tourists in the scenic area tourist database according to their attribute characteristics and generate recommended tour routes for each type of tourists.

[0113] The server 300 can read the data of all tourists in the scenic spot tourist database at a fixed period (for example, every week) and cluster them according to attribute characteristics. An optional implementation method is to use each attribute characteristic as a dimension based on a part of the attribute characteristics (such as gender, age, work, place of residence, clothing characteristics), and cluster the tourists in the scenic spot tourist database based on the dimensions of multiple attribute characteristics to divide the tourists into multiple categories.

[0114] For each category of tourists, a recommended tour route corresponding to the category of tourists is generated according to the tour paths of the tourists belonging to the category. An optional implementation is to determine the tour order of each tourist at each tour location according to the tour location and tour time of each tourist, and to sort the tour preferences of the category of tourists according to the number of visitors and tour order of each tour location. For example, the average number of visitors and the average tour order of each tour location can be counted, and the top n tour locations with the highest average number of visitors are selected, and then the n tour locations are sorted in order of the average tour order to obtain an ordered tour location sequence, and then the recommended tour route of the category of tourists is generated according to the tour location sequence. In addition, the tour time of a tourist at a tour location can be determined according to the tour time of the tourist at the tour location, and then the average tour time of a category of tourists at a tour location can be counted, and then the recommended tour time of the corresponding tour location can be provided to the category of tourists according to the average tour time of the category of tourists at a tour location.

[0115] The generated recommended tour routes can be stored in a database, optionally in the scenic spot tourist database, or a database for storing recommended tour routes for tourists with different attribute characteristics can be configured separately. The database storing the recommended tour routes can be accessed and read by the server 300, and the server 300 can recommend recommended tour routes that meet the attribute characteristics of the tourist to the tourist according to the tourist's request. An optional implementation includes the following steps:

[0116] Step 1: Receive a route recommendation request from a target tourist.

[0117] For example, the interface of the ticketing software is Fig.15 As shown, multiple function icons are displayed, and the target tourist can click on the icon of "recommended tour route" among the multiple icons. After receiving the click from the user (target tourist), the mobile phone receives the route recommendation request of the target tourist.

[0118] Step 2: Obtain the attribute characteristics of the target tourists and determine the corresponding category according to the attribute characteristics of the target tourists.

[0119] The mobile phone can send a route recommendation request to the server 300. After receiving the route recommendation request, the server 300 uses the target tourist's account sent by the mobile phone to log in to the ticketing software as an index to find the target tourist's attribute characteristics, such as gender, age, occupation, height, etc., in the scenic spot tourist database, and then clusters the target tourist's attribute characteristics. The clustering method is the same as the clustering method described in the above step 211. The specific clustering method used is not limited in this embodiment of the application. After clustering, the server 300 can determine the category to which the target tourist belongs.

[0120] Step 3: Find the recommended tour routes for the corresponding category of tourists.

[0121] The server 300 can read a database storing recommended tour routes, search for recommended tour routes corresponding to the category to which the target tourist belongs, and send the recommended tour routes to the target tourist's mobile phone. An optional implementation of the interactive schematic diagram of the recommended tour routes displayed on the mobile phone side is as follows: Figure 2 As shown, from the entrance to the exit, you will pass through attractions A, B, C, and D.

[0122] Optionally, before the server 300 sends the recommended tour route to the mobile phone side, the server 300 can also adjust the recommended tour route according to the real-time tour situation of the day. For example, the server 300 can read the tourist tour data of the day from the tourist database of the day, and determine the tour locations (i.e., congested tour locations) where the number of tourists exceeds a preset threshold in the current period of time (such as within 20 minutes). If there are congested tour locations in the recommended tour route, the server 300 can remove the congested tour locations in the recommended tour route and replace them with other tour locations. It can be set to replace other nearby tour locations, or, replace them with tour locations with the largest number of visitors of this category other than the tour locations that appear in the recommended tour route, and so on. The embodiments of the present application are not limited to this.

[0123] Optional, such as Fig.15 As shown, in addition to the function of recommending tour routes, the mobile phone ticketing software can also provide the function of historical tour routes, so that the target tourist can view the routes visited on the day in real time, or view the tour routes of previous visits to the scenic spot. The historical tour routes can be generated by the server 300 according to the tour locations and tour times stored in the tourist database of the scenic spot by the target tourist. An optional schematic diagram is shown in FIG. Fig.16 As shown, the target tourist is identified in the monitoring images of the corresponding area captured by the monitoring terminals 305, 306, and 307 respectively set at different locations in the scenic area, and the order of the monitoring terminals that captured the monitoring images of the target tourist is monitoring terminal 305, monitoring terminal 306, and monitoring terminal 307. According to the order and location of the target tourist, each tourist location is connected in series in time sequence to generate a fitting image as shown in FIG. Fig.16 Optionally, the tour path may be a path taken by tourists in one day, or may be a path taken by tourists for multiple visits on different dates, and may be configured according to the needs of target tourists.

[0124] Optionally, the server 300 can also count popular tourist locations within a period of time. For example, every quarter, the server 300 reads the tourist data of tourists in the scenic spot tourist database, including the tourist location and the tourist time, and evaluates the most popular tourist location of the quarter according to the preset popular evaluation criteria. For example, the tourist location with the most tourists during peak hours, the tourist location with the most tourists on average, the tourist location with the longest average tourist visit time, etc. can be counted. The above is only for illustrative purposes and is not intended to be a limitation on the embodiments of the present application.

[0125] In some possible implementations, the ticketing software of the mobile phone may also include functions such as scenic spot explanation and scenic spot activity information release, provide users with voice or text explanations of scenic spots, release the locations of scenic spots where performances are about to take place, etc. Optionally, the server 300 can determine the current sightseeing location of the tourists based on the monitoring images, select tourists near the location of the scenic spot where the activities are about to take place, and push scenic spot activity information to attract tourists near the activity location.

[0126] The method for recommending tour routes provided in the embodiment of the present application does not rely on modules such as Bluetooth and Wi-Fi of mobile devices, and does not require tourists to turn on the Bluetooth and Wi-Fi functions on their mobile phones; nor does it require devices for swiping physical tickets with RFID to be set up at different locations to count tourists' movement routes, thereby saving the operating costs of the scenic area. The embodiment of the present application stores the image recognition features of tourists contained in the ticket inspection image as comparison features, compares and identifies tourists in the monitoring image, and can identify tourists using existing monitoring terminal equipment in the scenic area. There is no need to increase the operating costs of hardware equipment in the scenic area, and only requires improvements in the algorithm and the addition of limited server equipment to implement the method of the embodiment of the present application.

[0127] The embodiments of the present application further provide device embodiments for implementing the various steps and methods in the above method embodiments.

[0128] Please refer to Fig.17 , which is a functional block diagram of a device for generating a recommended tour route provided in an embodiment of the present application. Fig.17 As shown, the device includes: a collection unit 10, an identification unit 20, a statistics unit 30 and a determination unit 40. The collection unit is used to collect monitoring images taken by cameras set at different tourist locations in the scenic area; the identification unit is used to identify the number of tourists appearing in the monitoring images; the statistics unit is used to count the total number of tourists appearing in the monitoring images of each tourist location within the current preset time period; the determination unit is used to determine the current recommended tourist route according to the total number of tourists at each tourist location within the current preset time period.

[0129] In a possible implementation, the determination unit includes: a first acquisition module, used to acquire a preset tour route; a first adjustment module, used to adjust the tour order of corresponding tour locations in the preset tour route according to the total number of tourists at each tour location within a current preset time period.

[0130] In a possible implementation, the first adjustment module includes: a first determination module, which is used to determine, in a preset tour route, a tour location whose total number of tourists exceeds a preset threshold in a current preset time period, to obtain a congested tour location; a search module, which is used to search, within a preset range near the congested tour location, for a tour location whose total number of tourists is less than a preset threshold and which is closest to the congested tour location, to obtain an alternative tour location; and a replacement module, which is used to replace the congested tour location in the preset tour route with an alternative tour location, to obtain the current recommended tour route.

[0131] In a possible implementation, the first adjustment module includes: a second determination module, which is used to determine, in a preset tour route, the tour locations where the total number of tourists exceeds a preset threshold within a current preset time period, to obtain congested tour locations; and a second adjustment module, which is used to postpone the tour order of the congested tour locations to obtain the current recommended tour route.

[0132] In a possible implementation, a first acquisition module includes: a receiving module for receiving a route recommendation request sent by a target tourist through a client; a second acquisition module for acquiring a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the target tourist's account, and each tag is used to represent an attribute feature of the target tourist; a selection module for selecting, from a plurality of candidate tour routes, a tour route with the largest number of matches with tags in the tag combination to obtain a preset tour route, wherein each of the plurality of candidate tour routes corresponds to one or more tags.

[0133] In a possible implementation, the device also includes: a first acquisition unit, used to acquire multiple candidate tour routes, the first acquisition unit includes: an extraction module, used to extract human body recognition features from surveillance images taken at different times and different tour locations; a matching module, used to match the extracted human body recognition features with the human body recognition features in a tourist feature library to identify tourists appearing in the surveillance images, wherein the tourist feature library stores the human body recognition features of multiple tourists collected in advance; a recording module, used to record the tour location and tour time of each tourist according to the recognition result of each surveillance image, so as to obtain the tour route of each tourist; a selection module, used to select multiple tour routes with the largest number of people with the same tour route from the tour routes of multiple tourists, to obtain multiple candidate tour routes; a third acquisition module, used to acquire a preset label combination for each tourist; a third determination module, used to determine the label corresponding to each candidate tour route according to the preset label combination of the tourist corresponding to each candidate tour route.

[0134] In a possible implementation, the device also includes: a second acquisition unit, used to obtain the surveillance image of the target tourist's most recent appearance after receiving a route recommendation request sent by the target tourist through a client; an identification unit, used to identify the human behavior characteristics of the target tourist in the surveillance image; a judgment unit, used to judge whether the target tourist has a target behavior based on the human behavior characteristics; and a push unit, used to push a message corresponding to the target behavior to the tourist if the judgment result is yes.

[0135] Since each unit in this embodiment can execute the method for generating a recommended tour route provided in the embodiment of the present application, for the parts not described in detail in the embodiment of the present device, reference can be made to the relevant description of the above method embodiment.

[0136] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method for generating a recommended tour route provided in the embodiment of the present application. For parts not described in detail in this embodiment, reference can be made to the relevant description of the above method embodiment.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0141] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0142] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for generating a recommended tour route, characterized in that: The method comprises: Collect surveillance images taken by cameras installed at different tourist locations in the scenic area; Identifying the number of tourists appearing in the surveillance image; Counting the total number of tourists appearing in the surveillance image at each tourist location within a current preset time period; Determine a current recommended tour route according to the total number of tourists at each tour location within the current preset time period; Wherein, determining the current recommended tour route according to the total number of tourists at each tour location within the current preset time period includes: Receive route recommendation requests sent by target tourists through the client; Acquire a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the account of the target tourist, and each tag is used to represent an attribute feature of the target tourist; Selecting a tour route with the largest number of matching tags in the tag combination from among multiple candidate tour routes to obtain a preset tour route, wherein each of the multiple candidate tour routes corresponds to one or more tags; According to the total number of tourists at each tourist location within the current preset time period, adjusting the tour order of the corresponding tourist locations in the preset tour route; Wherein, adjusting the tour order of the corresponding tour locations in the preset tour route according to the total number of tourists at each tour location in the current preset time period includes: In the preset tour route, determine the tour locations where the total number of tourists exceeds a preset threshold in the current preset time period, and obtain the congested tour locations; Searching for a tourist location closest to the congested tourist location and having a total number of tourists less than the preset threshold within a preset range near the congested tourist location to obtain an alternative tourist location; Replacing the congested tour location in the preset tour route with the alternative tour location to obtain the current recommended tour route; Alternatively, adjusting the tour order of corresponding tour locations in the preset tour route according to the total number of tourists at each tour location in the current preset time period includes: In the preset tour route, determine the tour locations where the total number of tourists exceeds a preset threshold in the current preset time period, and obtain the congested tour locations; Postponing the tour order of the congested tour location to obtain the current recommended tour route; After receiving a route recommendation request sent by the target tourist through the client, the method further includes: Obtaining the surveillance image of the target tourist's most recent appearance; Identifying the human behavior characteristics of the target tourist in the surveillance image; Determining whether the target tourist has a target behavior according to the human behavior characteristics; If the judgment result is yes, a message corresponding to the target behavior is pushed to the visitor.

2. The method according to claim 1, characterized in that The multiple candidate tour routes are obtained in the following manner: Extract human recognition features from surveillance images taken at different times and different tourist locations; Matching the extracted human body recognition features with human body recognition features in a tourist feature library to identify tourists appearing in the surveillance image, wherein the tourist feature library stores human body recognition features of a plurality of tourists collected in advance; According to the recognition result of each monitoring image, the visiting location and visiting time of each tourist are recorded to obtain the visiting route of each tourist; Among the tour routes of multiple tourists, multiple tour routes with the largest number of visitors that have the same tour routes are selected to obtain the multiple candidate tour routes; Obtaining a preset tag combination of each of the visitors; The label corresponding to each candidate tour route is determined according to the preset label combination of the tourists corresponding to each candidate tour route.

3. A device for generating a recommended tour route, characterized in that: The device comprises: A collection unit, used to collect monitoring images taken by cameras installed at different tourist locations in the scenic area; an identification unit, used to identify the number of tourists appearing in the surveillance image; A statistical unit, used to count the total number of tourists appearing in the monitoring image at each tourist location within a current preset time period; A determination unit, configured to determine a current recommended tour route according to the total number of tourists at each tour location within the current preset time period; Wherein, the determining unit includes: A first acquisition module is used to receive a route recommendation request sent by a target tourist through a client; obtain a tag combination of the target tourist, wherein the tag combination includes all tags pre-configured in the account of the target tourist, and each tag is used to represent an attribute feature of the target tourist; among multiple candidate tour routes, select a tour route with the largest number of matches with tags in the tag combination to obtain a preset tour route, wherein each of the multiple candidate tour routes corresponds to one or more tags; A first adjustment module, configured to adjust the tour order of corresponding tour locations in the preset tour route according to the total number of tourists at each tour location within the current preset time period; The first adjustment module includes: a first determination module, used to determine, in the preset tour route, the tour locations where the total number of tourists exceeds a preset threshold in the current preset time period, to obtain a congested tour location; a search module, used to search within a preset range near the congested tour location for the tour location where the total number of tourists is less than the preset threshold and the distance to the congested tour location is closest, to obtain an alternative tour location; a replacement module, used to replace the congested tour location in the preset tour route with the alternative tour location, to obtain the current recommended tour route; Alternatively, the first adjustment module includes: a second determination module, configured to determine, in the preset tour route, a tour location where the total number of tourists exceeds a preset threshold in the current preset time period, to obtain a congested tour location; and a second adjustment module, configured to postpone the tour order of the congested tour location to obtain the current recommended tour route; The device also includes: a second acquisition unit, which is used to obtain the monitoring image of the target tourist's most recent appearance after receiving a route recommendation request sent by the target tourist through the client; an identification unit, which is used to identify the human behavior characteristics of the target tourist in the monitoring image; a judgment unit, which is used to judge whether the target tourist has a target behavior based on the human behavior characteristics; and a push unit, which is used to push a message corresponding to the target behavior to the tourist if the judgment result is yes.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 2.

Images