Method, device and equipment for identifying abnormal behavior of tourists based on multi-source data

Abstract

The present disclosure provides a method, device and equipment for identifying abnormal behaviors of tourists based on multi-source data, the method comprising: obtaining and integrating real-name registration data, base station access data and face capture data related to target tourists to generate the activity trajectory of the target tourists; determining the baseline behavior score of the target tourists according to the activity trajectory of the target tourists and the pre-constructed baseline behavior model; comparing the baseline behavior characteristics of the target tourists with the abnormal behavior characteristics in the pre-established abnormal behavior feature library to determine the similarity score between the two, the baseline behavior characteristics are extracted according to the activity trajectory of the target tourists; determining the behavior label of the target tourists according to the baseline behavior score and the similarity score. The technical solution of the embodiment of the present application can adapt to the increasing complexity of abnormal behaviors and improve the accuracy of the results of identifying abnormal behaviors of tourists.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing technology, and in particular relates to a method, device and equipment for identifying abnormal behavior of tourists based on multi-source data. Background Art

[0002] In recent years, with the rapid development of the tourism industry, the number of tourists in various tourist attractions has increased day by day. Identifying whether tourists in scenic spots have abnormal behavior is of great significance to the management and development of scenic spots. In the current technical solutions, the behavior patterns of tourists are often determined based on a single data source (such as positioning data, etc.) and whether tourists have abnormal behavior. However, the above method cannot adapt to the increasing complexity of abnormal behavior, resulting in low accuracy of recognition results. Therefore, how to adapt to the increasing complexity of abnormal behavior and improve the accuracy of abnormal behavior recognition results of tourists has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a method, device and equipment for identifying abnormal behavior of tourists based on multi-source data, which can adapt to the increasing complexity of abnormal behavior to a certain extent and improve the accuracy of the results of identifying abnormal behavior of tourists.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] According to one aspect of an embodiment of the present application, a method for identifying abnormal behavior of tourists based on multi-source data is provided, comprising:

[0006] Obtain real-name registration data, base station access data, and facial capture data related to target tourists;

[0007] Integrate the real-name registration data, the base station access data and the face capture data to generate the activity trajectory of the target tourist, the activity trajectory including the time and duration of the target tourist's check-in at the hotel, the base station switching point and the length of stay, the face capture time and the capture location;

[0008] Determining a baseline behavior score of the target tourist based on the activity trajectory of the target tourist and a pre-built baseline behavior model;

[0009] Comparing the baseline behavior characteristics of the target tourist with the abnormal behavior characteristics in a pre-established abnormal behavior characteristic library to determine a similarity score between the two, wherein the baseline behavior characteristics are extracted based on the activity trajectory of the target tourist;

[0010] A behavior label of the target tourist is determined according to the baseline behavior score and the similarity score, and the behavior label is used to indicate whether the target tourist has abnormal behavior.

[0011] According to one aspect of an embodiment of the present application, a device for identifying abnormal behavior of tourists based on multi-source data is provided, comprising:

[0012] An acquisition module is used to acquire real-name registration data, base station access data, and face capture data related to target tourists;

[0013] A trajectory generation module, for integrating the real-name registration data, the base station access data and the face capture data to generate an activity trajectory of the target tourist, wherein the activity trajectory includes the time and duration of check-in at the hotel, the base station switching point and the duration of stay, the face capture time and the capture location of the target tourist;

[0014] A first determination module is used to determine the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and a pre-built baseline behavior model;

[0015] A second determination module is used to compare the baseline behavior characteristics of the target tourist with the abnormal behavior characteristics in a pre-established abnormal behavior characteristic library to determine a similarity score between the two, wherein the baseline behavior characteristics are extracted according to the activity trajectory of the target tourist;

[0016] A processing module is used to determine a behavior tag of the target tourist according to the baseline behavior score and the similarity score, wherein the behavior tag is used to indicate whether the target tourist has abnormal behavior.

[0017] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for identifying abnormal behaviors of tourists based on multi-source data as described in the above embodiment is implemented.

[0018] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for identifying abnormal behavior of visitors based on multi-source data as described in the above embodiments.

[0019] According to one aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for identifying abnormal behaviors of tourists based on multi-source data provided in the above embodiments.

[0020] In the technical solutions provided in some embodiments of the present application, the real-name registration data, base station access data and face capture data related to the target tourist are obtained and integrated to generate an activity trajectory of the target tourist, which includes the time and duration of the target tourist's check-in at the hotel, the base station switching point and the length of stay, the face capture time and the capture location. Then, based on the activity trajectory of the target tourist and a pre-built baseline behavior model, the baseline behavior score of the target tourist is determined, and then the baseline behavior characteristics of the target tourist are compared with the abnormal behavior characteristics in a pre-established abnormal behavior library to determine the similarity score between the two. The baseline behavior characteristics are extracted according to the activity trajectory of the target tourist. Based on the baseline behavior score and the similarity score of the target tourist, a label of the target tourist is determined to indicate whether the target tourist has abnormal behavior.

[0021] In this way, multi-source data can be effectively integrated to fully grasp the activity trajectories and behavioral characteristics of tourists, so as to adapt to the increasing complexity of abnormal behaviors and improve the accuracy of subsequent abnormal behavior identification results.

[0022] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 A schematic diagram of a process of identifying abnormal behaviors of tourists based on multi-source data according to an embodiment of the present application is shown;

[0025] Figure 2 A block diagram of a device for identifying abnormal behaviors of tourists based on multi-source data according to an embodiment of the present application is shown;

[0026] Figure 3A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0028] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0031] Figure 1 A flow chart of a method for identifying abnormal behaviors of tourists based on multi-source data according to an embodiment of the present application is shown.

[0032] The method can be applied to a terminal device or a server, wherein the terminal device may include but is not limited to one or more of a smart phone, a tablet computer, a portable computer, and a desktop computer; the server may be a physical server or a cloud server.

[0033] The following is an example of applying this method to a terminal device (hereinafter referred to as a "terminal"). Figure 1 As shown, the method for identifying abnormal behavior of tourists based on multi-source data at least includes steps S110 to S150, which are described in detail as follows:

[0034] In step S110, real-name registration data, base station access data, and face capture data related to the target tourist are obtained.

[0035] In this embodiment, the target tourist may be any person who intends to visit the scenic spot, and the terminal may obtain the real-name registration data, base station access data, and face capture data of the target tourist for subsequent analysis.

[0036] Among them, the real-name registration data can be the real-name registration information of the target tourist in hotels and other places, including name, ID number, check-in time, etc. The base station access data can be the interaction information between the target tourist's mobile device and the base station, including the base station identification of the base station connected, access time, stay time, etc. The face capture data can be the face capture information of the target tourist at important points such as hotels, scenic spots or transportation hubs, including the capture location, capture time, etc.

[0037] In step S120, the real-name registration data, the base station access data and the face capture data are integrated to generate the activity trajectory of the target tourist, which includes the time and duration of the target tourist's check-in at the hotel, the base station switching point and the duration of stay, the face capture time and the capture location.

[0038] In this embodiment, after obtaining the real-name registration data, base station access data and face capture data of the target tourist, the terminal can integrate the data from different sources to obtain the complete activity track of the target tourist. The activity track may include but is not limited to the time and duration of the target tourist's check-in at the hotel, the base station switching point and duration of stay of the target tourist, and the time and location of the target tourist's face capture.

[0039] In this way, the activity trajectory obtained by integrating data from different sources can comprehensively and accurately describe the complete behavior of tourists in the scenic area.

[0040] In one example, a suitable database management system (such as MySQL, MongoDB, etc.) can be pre-selected to store and manage various data. In addition, a corresponding data table structure is constructed for each source of data to ensure that fields from different data sources can be effectively integrated. For example:

[0041] The visitor information table may include, but is not limited to: storing real-name registration data, including visitor ID, name, ID number, check-in time, etc.

[0042] The movement track table may include, but is not limited to: storing base station data, including visitor ID, timestamp, location information, signal strength, etc.

[0043] The face recognition table may include, but is not limited to: storing face capture data, including visitor ID, timestamp, image path, capture location, etc.

[0044] In one embodiment, before integrating the real-name registration data, the base station access data, and the face capture data to generate the activity trajectory of the target tourist, the method further includes:

[0045] Matching the real-name registration data with the facial capture data to determine that the two correspond to the same target tourist;

[0046] Standardizing the timestamps of the real-name registration data, the face capture data, and the base station access data so that the time formats of the three are consistent;

[0047] The real-name registration data, the face capture data and the base station access data after the timestamp is standardized are cleaned and normalized and stored.

[0048] In this embodiment, before integrating data from different sources, the ID card number in the real-name registration data can be used to match the recognition result in the face recognition data to ensure that the identity of the same tourist is consistent. In one example, a matching algorithm (such as Levenshtein distance) can be used to perform fuzzy matching on the name of the target tourist to avoid possible spelling errors.

[0049] Next, the timestamps in different data sources are standardized to ensure that the time format is consistent (such as ISO 8601 format) to facilitate subsequent time series analysis. Then, the movement trajectory is associated with the face capture data through the time window to ensure that activities in the same time period are integrated into the activity trajectory of the same tourist.

[0050] Then, the processed data can be cleaned, normalized and stored. Specifically, duplicate records in the data (such as multiple snapshots of the same tourist or multiple base station data in the same time period) can be identified and deleted, and missing data in key fields (such as identity document number, timestamp) can be filled or deleted. Ensure that the data formats of different data sources are consistent, such as unifying geographic coordinates to the WGS84 standard, and normalizing numerical features (such as residence time, signal strength, etc.). The terminal can store the integrated data in the aforementioned database management system for subsequent processing.

[0051] Please continue to refer to Figure 1 In step S130, the baseline behavior score of the target tourist is determined according to the activity trajectory of the target tourist and the pre-built baseline behavior model.

[0052] In this embodiment, the baseline behavior model can be pre-constructed by a person skilled in the art, and a baseline model of normal tourist behavior can be established by statistics of large-scale tourist behavior data, which covers typical movement patterns, dwell time distribution, signal switching frequency, etc. It should be noted that the core purpose of the baseline behavior model is to establish a reference standard for "normal tourist behavior", that is, to evaluate whether a tourist exhibits behavior similar to that of most "normal tourists".

[0053] The terminal may determine the baseline behavior score of the target tourist according to the activity trajectory of the target tourist determined in step S120 and the baseline behavior model.

[0054] In one embodiment, determining the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and the pre-built baseline behavior model includes:

[0055] According to the activity trajectory of the target tourists, determine the average moving distance, average stay time and signal switching frequency of the target tourists;

[0056] A baseline behavior score of the target visitor is determined according to the average moving distance, the average stay time, and the signal switching frequency.

[0057] In this embodiment, the terminal can analyze the target tourist's activity trajectory to determine various activity characteristics of the target tourist, including but not limited to the target tourist's average moving distance (i.e., the aforementioned moving mode), average stay time (i.e., the aforementioned stay time distribution) and signal switching frequency.

[0058] Then, the baseline behavior score of the target tourists is determined based on the determined average movement distance, average stay time and signal switching frequency.

[0059] In one example, the baseline behavior score of a target visitor may be determined according to the following formula:

[0060]

[0061] in, B k Baseline behavior score for target visitors, N is the number of target visitors’ movements, d i For target tourists i The distance moved; M The number of places visited by target tourists, t j For target tourists j Duration of stay at a location; C For target visitors in time periodT Number of signal switching within ; w 1 , w 2 , w 3 is the weight value. It should be noted that w 1 , w 2 , w 3 It can be determined by combining data-driven and principal component analysis to ensure the accuracy and interpretability of the model.

[0062] In this way, the above baseline behavior model can calculate the comprehensive score of the target tourist's behavior through multiple dimensions to measure the difference between the target tourist and the "normal tourist" behavior.

[0063] In one example, when calculating the baseline action score of a target tourist, the terminal can record the base station switching of the target tourist in a specific time period through the base station data provided by the operator, thereby calculating the target tourist's movement trajectory, movement distance, and signal switching frequency. Alternatively, the terminal can also combine the face capture data (such as the capture location and capture time, etc.) to calculate the target tourist's movement at a specific location.

[0064] In addition, the terminal can also obtain the target tourists' length of stay through the hotel's check-in and check-out records. Facial capture data at specific locations (such as scenic spots, shopping malls, etc.) can also be used to identify the target tourists' stay and calculate their length of stay.

[0065] Please continue to refer to Figure 1 In step S140, the baseline behavior characteristics of the target tourist are compared with the abnormal behavior characteristics in the pre-established abnormal behavior characteristic library to determine the similarity score between the two, wherein the baseline behavior characteristics are extracted according to the activity trajectory of the target tourist.

[0066] In this embodiment, the abnormal behavior feature library can be a data set for identifying and analyzing abnormal behaviors, which includes a variety of key features and patterns related to abnormal behaviors. Those skilled in the art can convert common abnormal behaviors into a set of feature sets for subsequent identification.

[0067] After determining the target tourist's activity trajectory, the terminal can extract the target tourist's baseline behavior characteristics according to the activity trajectory. It should be understood that the baseline behavior characteristics can be actual behavior characteristics extracted from the target tourist within a certain period of time, such as residence time, movement trajectory, signal switching frequency, etc. In one example, the baseline behavior characteristics can be represented in the form of a vector, which is used to represent the performance of the target tourist's behavior in various feature dimensions, such as [ b 1 , b 2 , b 3 ,…, b n ],in, b i ( i =1,2,…, n ) represents the characteristic value of a specific behavioral characteristic.

[0068] After extracting the baseline behavior characteristics of the target tourist, the terminal can compare it with the abnormal behavior characteristics in the abnormal behavior characteristic library to obtain the similarity scores corresponding to the two. It should be understood that the higher the similarity score, the closer the behavior of the target tourist is to the known abnormal behavior pattern.

[0069] In one embodiment, the similarity score of the target visitor may be calculated according to the following formula:

[0070]

[0071] in, For the target tourists i The characteristic value of the behavior characteristic, S k ( i ) is the feature value of the corresponding behavior feature in the abnormal behavior feature library, m represents the number of behavioral features to be compared, and |·| represents the absolute value.

[0072] Please continue to refer to Figure 1 In step S150, the behavior label of the target tourist is determined according to the baseline behavior score and the similarity score, and the behavior label is used to indicate whether the target tourist has abnormal behavior.

[0073] In this embodiment, the terminal can combine the baseline behavior score and similarity score of the target tourist to classify the target tourist to determine the behavior label of the target tourist, and the behavior label can be used to indicate whether the target tourist has abnormal behavior. In one example, the behavior label can include "normal tourist" and "abnormal tourist". If the behavior label of the target tourist is "normal tourist", it means that the behavior of the target tourist is similar to that of most tourists and there is no abnormal behavior. If the behavior label of the target tourist is "abnormal tourist", it means that the behavior of the target tourist is abnormal and needs to be paid special attention.

[0074] In some embodiments of the present application, determining the behavior tag of the target visitor according to the baseline behavior score and the similarity score includes:

[0075] The baseline behavior score and the similarity score are used as inputs of a pre-trained classification model, so that the classification model outputs a behavior label corresponding to the target tourist according to the baseline behavior score and the similarity score.

[0076] In this embodiment, those skilled in the art may pre-build and train a classification model. After obtaining the baseline behavior score and similarity score of the target tourist, the terminal may input the two into the trained classification model so that the classification model outputs the corresponding behavior label.

[0077] In one example, a classification model based on a logistic regression algorithm can be used for identification to obtain the behavior label of the target tourist. The input of the classification model can be a baseline behavior score and a similarity score, and other relevant features (such as historical data or geographic location, etc.) can also be input into the classification model for identification.

[0078] The formula used by the classification model can be shown as follows:

[0079] in, is the conditional probability, which means that given the known features X Under the condition of Y =1 (the tourist's behavior is abnormal), X is the input feature set, including baseline behavior score, similarity score, etc. B k is the baseline behavior score, S sim is the similarity score, 、 、 … is the model parameter.

[0080] So, based on Figure 1 In the embodiment shown, the target tourist's activity track is generated by acquiring the real-name registration data, base station access data and face capture data related to the target tourist and integrating the three. The activity track includes the time and duration of the target tourist's check-in at the hotel, the base station switching point and the length of stay, the face capture time and the capture location. Then, according to the target tourist's activity track and the pre-built baseline behavior model, the target tourist's baseline behavior score is determined, and then the target tourist's baseline behavior characteristics are compared with the abnormal behavior characteristics in the pre-established abnormal behavior library to determine the similarity score between the two. The baseline behavior characteristics are extracted according to the target tourist's activity track. According to the target tourist's baseline behavior score and the similarity score, the target tourist's label used to indicate whether the target tourist has abnormal behavior is determined. It can effectively integrate multi-source data, fully grasp the activity track and behavior characteristics of tourists, so as to adapt to the increasing complexity of abnormal behavior and improve the accuracy of subsequent abnormal behavior identification results.

[0081] In some embodiments of the present application, after determining the behavior label of the target tourist according to the baseline behavior score and the similarity score, the method further includes:

[0082] If the target tourist's behavior label is abnormal behavior, the target tourist's face capture data and base station access data at different times and locations are integrated to generate and display a spatiotemporal heat map of the target tourist; and / or the target tourist's activity trajectory is visualized.

[0083] In this embodiment, after determining that the behavior label of a target tourist is abnormal behavior, the terminal can integrate the face capture data and base station access data of the target tourist at different times and locations to generate a spatiotemporal heat map of the target tourist. The terminal can display the spatiotemporal heat map to enable management personnel to clearly identify the activity location of the target tourist with abnormal behavior.

[0084] Alternatively, the terminal can visualize the activity trajectory of the target tourist so that the management personnel can know the specific activity trajectory of the target tourist and the current location of the target tourist for timely processing.

[0085] In addition, when it is determined that the behavior tag of the target tourist is abnormal, the terminal can generate corresponding warning information to notify the relevant departments for further monitoring or processing.

[0086] The following describes an apparatus embodiment of the present application, which can be used to execute the method for identifying abnormal behavior of tourists based on multi-source data in the above-mentioned embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the embodiment of the method for identifying abnormal behavior of tourists based on multi-source data in the above-mentioned embodiment of the present application.

[0087] Figure 2 A block diagram of a device for identifying abnormal behaviors of visitors based on multi-source data according to an embodiment of the present application is shown.

[0088] Reference Figure 2 As shown, according to an embodiment of the present application, a device for identifying abnormal behavior of tourists based on multi-source data includes:

[0089] An acquisition module is used to acquire real-name registration data, base station access data, and face capture data related to target tourists;

[0090] A trajectory generation module, for integrating the real-name registration data, the base station access data and the face capture data to generate an activity trajectory of the target tourist, wherein the activity trajectory includes the time and duration of check-in at the hotel, the base station switching point and the duration of stay, the face capture time and the capture location of the target tourist;

[0091] A first determination module is used to determine the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and a pre-built baseline behavior model;

[0092] A second determination module is used to compare the baseline behavior characteristics of the target tourist with the abnormal behavior characteristics in a pre-established abnormal behavior characteristic library to determine a similarity score between the two, wherein the baseline behavior characteristics are extracted according to the activity trajectory of the target tourist;

[0093] A processing module is used to determine a behavior tag of the target tourist according to the baseline behavior score and the similarity score, wherein the behavior tag is used to indicate whether the target tourist has abnormal behavior.

[0094] In some embodiments of the present application, determining the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and the pre-built baseline behavior model includes:

[0095] According to the activity trajectory of the target tourists, determine the average moving distance, average stay time and signal switching frequency of the target tourists;

[0096] A baseline behavior score of the target visitor is determined according to the average moving distance, the average stay time, and the signal switching frequency.

[0097] In some embodiments of the present application, after determining the behavior label of the target tourist according to the baseline behavior score and the similarity score, the processing module is further used to:

[0098] If the target tourist's behavior label is abnormal behavior, the target tourist's face capture data and base station access data at different times and locations are integrated to generate and display a spatiotemporal heat map of the target tourist; and / or the target tourist's activity trajectory is visualized.

[0099] In some embodiments of the present application, before integrating the real-name registration data, the base station access data, and the face capture data to generate the activity trajectory of the target tourist, the trajectory generation module is further used to:

[0100] Matching the real-name registration data with the facial capture data to determine that the two correspond to the same target tourist;

[0101] Standardizing the timestamps of the real-name registration data, the face capture data, and the base station access data so that the time formats of the three are consistent;

[0102] The real-name registration data, the face capture data and the base station access data after the timestamp is standardized are cleaned and normalized and stored.

[0103] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0104] It should be noted that Figure 3 The computer system of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0105] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0106] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0107] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.

[0108] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0109] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0111] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0112] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0113] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0114] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0115] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for identifying abnormal behavior of tourists based on multi-source data, characterized in that: include: Acquire real-name registration data, base station access data, and face capture data related to a target tourist, wherein the target tourist is any person who intends to visit the scenic spot; Integrate the real-name registration data, the base station access data and the face capture data to generate the activity trajectory of the target tourist, the activity trajectory including the time and duration of the target tourist's check-in at the hotel, the base station switching point and the length of stay, the face capture time and the capture location; Determining the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and the pre-built baseline behavior model, including: determining the average moving distance, average stay time and signal switching frequency of the target tourist according to the activity trajectory of the target tourist; and determining the baseline behavior score of the target tourist according to the average moving distance, the average stay time and the signal switching frequency, wherein the baseline behavior is the actual behavior of the target tourist in a certain period of time; Comparing the baseline behavior characteristics of the target tourist with the abnormal behavior characteristics in a pre-established abnormal behavior characteristic library to determine a similarity score between the two, wherein the baseline behavior characteristics are extracted according to the activity trajectory of the target tourist; Determine the behavior label of the target tourist according to the baseline behavior score and the similarity score, wherein the behavior label is used to indicate whether the target tourist has abnormal behavior. The baseline behavior score of the target tourist is determined according to the following formula: in, B k Baseline behavior score for target visitors, N is the number of target visitors’ movements, d i For target tourists i The distance moved; M The number of places visited by target tourists, t j For target tourists j Duration of stay at a location; C For target visitors in time period T Number of signal switching within ; w 1 , w 2 , w 3 is the weight value.

2. The method according to claim 1, characterized in that After determining the behavior label of the target tourist according to the baseline behavior score and the similarity score, the method further includes: If the target tourist's behavior label is abnormal behavior, the target tourist's face capture data and base station access data at different times and locations are integrated to generate and display a spatiotemporal heat map of the target tourist; and / or the target tourist's activity trajectory is visualized.

3. The method according to claim 1, characterized in that Before integrating the real-name registration data, the base station access data, and the face capture data to generate the activity trajectory of the target tourist, the method further includes: Matching the real-name registration data with the facial capture data to determine that the two correspond to the same target tourist; Standardizing the timestamps of the real-name registration data, the face capture data, and the base station access data so that the time formats of the three are consistent; The real-name registration data, the face capture data and the base station access data after the timestamp is standardized are cleaned and normalized and stored.

4. The method according to any one of claims 1 to 3, characterized in that Determining the behavior label of the target visitor according to the baseline behavior score and the similarity score includes: The baseline behavior score and the similarity score are used as inputs of a pre-trained classification model, so that the classification model outputs a behavior label corresponding to the target tourist according to the baseline behavior score and the similarity score.

5. A device for identifying abnormal behavior of tourists based on multi-source data, characterized in that: include: An acquisition module is used to acquire real-name registration data, base station access data, and face capture data related to a target tourist, wherein the target tourist is any person who intends to visit the scenic spot; A trajectory generation module, for integrating the real-name registration data, the base station access data and the face capture data to generate an activity trajectory of the target tourist, wherein the activity trajectory includes the time and duration of check-in at the hotel, the base station switching point and the duration of stay, the face capture time and the capture location of the target tourist; The first determination module is used to determine the baseline behavior score of the target tourist according to the activity trajectory of the target tourist and the pre-built baseline behavior model, including: determining the average moving distance, average stay time and signal switching frequency of the target tourist according to the activity trajectory of the target tourist; and determining the baseline behavior score of the target tourist according to the average moving distance, the average stay time and the signal switching frequency, wherein the baseline behavior is the actual behavior of the target tourist in a certain period of time; A second determination module is used to compare the baseline behavior characteristics of the target tourist with the abnormal behavior characteristics in a pre-established abnormal behavior characteristic library to determine a similarity score between the two, wherein the baseline behavior characteristics are extracted according to the activity trajectory of the target tourist; A processing module is used to determine the behavior label of the target tourist according to the baseline behavior score and the similarity score, wherein the behavior label is used to indicate whether the target tourist has abnormal behavior. The baseline behavior score of the target tourist is determined according to the following formula: in, B k Baseline behavior score for target visitors, N is the number of target visitors’ movements, d i For target tourists i The distance moved; M The number of places visited by target tourists, t j For target tourists j Duration of stay at a location; C For target visitors in time period T Number of signal switching within ; w 1 , w 2 , w 3 is the weight value.

6. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying abnormal behaviors of tourists based on multi-source data as described in any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the method for identifying abnormal behavior of tourists based on multi-source data as described in any one of claims 1 to 4.

Images