An Exhibition Intelligent Security Monitoring System and Method Based on the Internet of Things

Abstract

The present invention relates to the field of security monitoring technology, and in particular to an intelligent security monitoring system and method for exhibitions based on the Internet of Things. The system discloses a security monitoring preliminary module, a security monitoring adjustment module, a key security module, a security tracing module, and a tracing security adjustment module. The system combines conventional recognition technology to perform security monitoring on all visitors in an exhibition hall. According to the behavioral characteristics of the visitors, a different security monitoring cycle is customized for each visitor to ensure the reasonable allocation of system monitoring and analysis resources. When abnormal behavior and repeated visitors are found in the exhibition hall, the corresponding visitors are promptly marked as key security visitors, and visitors who may be affected are quickly and accurately discovered. When it is found that the traced visitors have the possibility of performing corresponding behaviors, the traced visitors are synchronously monitored, so that security personnel can take corresponding countermeasures in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring, and more particularly to an exhibition intelligent security monitoring system and method based on the Internet of Things. Background Art

[0002] With the vigorous development of the exhibition industry, exhibition halls, as important places for cultural exchange and product display, their safety precautions are particularly important.

[0003] In recent years, the rapid development of the Internet of Things (IoT) has provided new solutions for exhibition security. Using sensors, RFID tags, video surveillance, and other means, IoT technology enables comprehensive awareness and real-time monitoring of people, objects, and the environment within exhibition halls. However, existing IoT-based security systems are still largely in their early stages of application, plagued by issues such as low intelligence, irrational resource allocation, and inaccurate identification of abnormal behavior.

[0004] Especially at exhibitions, visitors' behavioral characteristics vary. Some may only occasionally stop and watch, while others may exhibit unusual behavior, such as frequently attempting to touch exhibits or crossing isolated areas. Traditional security systems require a large number of security personnel and fail to trigger security alarms when visitors touch exhibits or attempt to cross isolated areas (security alarms typically only occur when exhibits are touched or damaged). Some visitors, after observing others engage in these behaviors without receiving security alarms, may subsequently imitate them.

[0005] Therefore, there is an urgent need for a system and method that can combine Internet of Things technology to perform intelligent security monitoring based on the behavioral characteristics of visitors, so as to achieve comprehensive, accurate and efficient monitoring of visitors in the exhibition hall and ensure the safe and smooth progress of exhibition activities. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an exhibition intelligent security monitoring system and method based on the Internet of Things.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An exhibition intelligent security monitoring system based on the Internet of Things, including a security monitoring preliminary module, a security monitoring adjustment module, a key security module, a security tracing module, and a tracing security adjustment module;

[0009] The security monitoring initialization module deploys video surveillance in the exhibition hall and identifies visitors in the video surveillance in real time. When a visitor in the video surveillance is identified for the first time, the security monitoring period of the visitor is determined;

[0010] The security monitoring adjustment module, when a visitor is not identified for the first time in the video surveillance, obtains the visitor's security monitoring cycle, and if the visitor's security monitoring index has reached one security monitoring cycle since the last time it was obtained, determines whether to adjust the visitor's security monitoring level, and simultaneously determines the visitor's security impact range;

[0011] The key security module marks a visitor as a key security visitor when the visitor's security monitoring level is higher than or equal to the security monitoring threshold level;

[0012] The security tracing module is used to determine security tracing visitors;

[0013] The retrospective security adjustment module determines whether to adjust the security monitoring level of the security retrospective visitor to be consistent with the security monitoring level of the security key visitor.

[0014] Furthermore, the security monitoring period of the visitor is determined based on the following method: obtaining the security monitoring index of the visitor, determining the security monitoring level of the visitor based on the security monitoring index, and performing security monitoring on the visitor based on the security monitoring period corresponding to the security monitoring level.

[0015] Furthermore, the visitor's security monitoring index is obtained based on the following method: extracting the image frame in which the visitor is first identified in the video surveillance, extracting the visitor's behavioral characteristics based on the extracted image frame, obtaining a security monitoring model, using the behavioral characteristics as input data of the security monitoring model, and outputting the visitor's security monitoring index. .

[0016] Furthermore, the visitor's security monitoring level is determined based on the following method: obtaining the visitor's security monitoring index , set the range of each security monitoring index to correspond to a security monitoring level, the range of security monitoring index includes ,The security monitoring levels include security monitoring level 1, security monitoring level 2, …, security monitoring level S-1, security monitoring level S, each security monitoring level 1 corresponds to a security monitoring cycle, and the cycle length of the security monitoring cycle corresponding to the security monitoring level 1 is less than the cycle length of the security monitoring cycle corresponding to the security monitoring level 2, and so on.

[0017] Furthermore, determine whether to adjust the visitor's security monitoring level: obtain the visitor's security monitoring index, simultaneously determine the visitor's visiting dynamic index, set the visiting dynamic upper index and the visiting dynamic lower index; when the visitor's visiting dynamic index is greater than the visiting dynamic upper index, the corresponding visitor's security monitoring level will be increased by one level; when the visitor's visiting dynamic index is less than the visiting dynamic lower index, the corresponding visitor's security monitoring level will be decreased by one level; when the visitor's visiting dynamic index is between the visiting dynamic upper index and the visiting dynamic lower index, the corresponding visitor's security monitoring level will be maintained.

[0018] Furthermore, the visitor's visit dynamic index is determined based on the following method: obtain all security monitoring indices previously obtained by a visitor, sort all security monitoring indices in the order of acquisition, calculate the absolute difference between two adjacent security monitoring indices after sorting, calculate the monitoring dynamic index, set the monitoring dynamic threshold index, and when the monitoring dynamic index is greater than the monitoring dynamic threshold index, increase the number of behavior repetitions by one, and mark the number of behavior repetitions as , calculate the average value of all security monitoring indexes and get the average security monitoring index , Get the visitor's visit dynamic index .

[0019] Furthermore, the security impact range of key security visitors is determined based on the following method: each security monitoring level is set to correspond to a security impact radius. The higher the security monitoring level, the larger the corresponding security impact radius. A circle is drawn with the current position of the key security visitor as the center and the security impact radius as the radius to determine the security impact range of the key security visitor.

[0020] Furthermore, the security tracing visitor is determined based on the following method: determining the security impact range of the key security visitor, marking the remaining visitors within the security impact range as security-related visitors, determining the involved synchronization value of the security-related visitors, setting the involved synchronization threshold, and when the involved synchronization value of the security-related visitor is greater than the involved synchronization threshold, marking the corresponding security-related visitor as a security tracing visitor;

[0021] The synchronization value of the security-related visitor is determined based on the following method: select a security-related visitor, obtain all the security impact ranges of the key security visitors that have been determined before, and when the security impact range is determined and the security-related visitor is within the security impact range, increase the number of synchronizations by one, calculate the ratio of the number of synchronizations to the total number of security impact ranges, and calculate the synchronization value of the security-related visitor.

[0022] Further, determining whether to adjust the security monitoring level of the security tracing visitor to be consistent with the security monitoring level of the security key visitor: obtaining the security impact visit index of each security tracing visitor, setting the security impact visit threshold index, and when the security impact visit index of the security tracing visitor is greater than the security impact visit threshold index, adjusting the security monitoring level of the security tracing visitor to be consistent with the security monitoring level of the security key visitor;

[0023] The security impact visit index of the security traceability visitor is obtained based on the following method: select a security traceability visitor, obtain the impact superposition index and visit dynamic index of the security traceability visitor, and mark , X1 is the impact superposition index of security retrospective visitors, X2 is the visit dynamic index of security retrospective visitors, obtain the impact superposition index and visit dynamic index of security key visitors, and mark them as ,Y1 is the impact superposition index of security key visitors, Y2 is the visit dynamic index, and the cosine similarity algorithm is used to calculate the security impact visit index of security traceability visitors;

[0024] The impact superposition index is obtained based on the following method: obtain all the security impact ranges previously determined by the visitor, sort all the security impact ranges in the determined order, compare the two adjacent security impact ranges after sorting, and when the two security impact ranges have an intersection, mark the intersection area as , d=1, 2, ..., D-1, D, d is the sequence number of the intersection area, D is the total number of intersection areas, set the intersection area coefficient to Lz, z=1, 2, ..., Z, L1<L2<...<LZ-1<LZ, through Get the visitor's influence superposition index .

[0025] Furthermore, an exhibition intelligent security monitoring method based on the Internet of Things includes the following steps:

[0026] Step 1: Deploy video surveillance in the exhibition hall to identify visitors in real time. When a visitor is identified for the first time, determine the visitor's security monitoring cycle. If the visitor is not identified for the first time, obtain the visitor's security monitoring cycle. If the visitor's security monitoring index has reached one security monitoring cycle since the last time it was obtained, determine whether to adjust the visitor's security monitoring level and simultaneously determine the visitor's security impact range.

[0027] Step 2: When the visitor's security monitoring level is higher than or equal to the security monitoring threshold level, the visitor is marked as a key security visitor;

[0028] Step 3: Determine security traceability visitors;

[0029] Step 4: Determine whether to adjust the security monitoring level of the security traceability visitor to be consistent with the security monitoring level of the security key visitor.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The system of the present invention uses a security monitoring preliminary module, a security monitoring adjustment module, a key security module, a security tracing module, and a tracing security adjustment module, combined with conventional identification technology, to conduct security monitoring on all visitors in the exhibition hall. Based on the visitor's behavioral characteristics, a different security monitoring cycle is customized for each visitor to ensure the rational allocation of system monitoring and analysis resources. When abnormal behavior or repeated visitors are found in the exhibition hall, the corresponding visitors are promptly marked as key security visitors. Visitors who may be affected are quickly and accurately identified and retrospectively analyzed to determine whether there is a possibility that the visitors will engage in behavior corresponding to the key security visitors.

[0032] 2. The method of the present invention can retroactively analyze whether a visitor has the possibility of engaging in behaviors corresponding to those of security-focused visitors. When it is found that the traced visitor has the possibility of engaging in corresponding behaviors, the traced visitor is synchronously monitored, so that security personnel can take corresponding countermeasures in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a module block diagram of an exhibition intelligent security monitoring system based on the Internet of Things;

[0034] Figure 2 A flow chart for adjusting the security monitoring level for visitors;

[0035] Figure 3 This is a flowchart of an exhibition intelligent security monitoring method based on the Internet of Things. DETAILED DESCRIPTION

[0036] Example 1: Reference Figures 1 to 2 , an exhibition intelligent security monitoring system based on the Internet of Things, including a security monitoring preliminary module, a security monitoring adjustment module, a key security module, a security tracing module, and a tracing security adjustment module.

[0037] Preliminary security monitoring module: Deploy video surveillance in the exhibition hall (the deployed video surveillance is all-round monitoring, so all visitors can appear in the video surveillance in real time), and identify visitors in the video surveillance in real time (the recognition technology is conventional face recognition technology and body recognition technology). When a visitor in the video surveillance is identified for the first time, obtain the visitor's security monitoring index, determine the visitor's security monitoring level based on the security monitoring index, and conduct security monitoring of the visitor based on the security monitoring period corresponding to the security monitoring level.

[0038] The visitor's security monitoring index is obtained based on the following method: extracting the image frame in which the visitor is first identified in the video surveillance, extracting the visitor's behavioral characteristics based on the extracted image frame, obtaining a security monitoring model, using the behavioral characteristics as input data of the security monitoring model, and the security monitoring model outputs the visitor's security monitoring index. .

[0039] The visitor's security monitoring level is determined based on the following method: Get the visitor's security monitoring index , set the range of each security monitoring index to correspond to a security monitoring level, the range of security monitoring index includes , , , security monitoring levels include security monitoring level 1, security monitoring level 2, ..., security monitoring level S-1, security monitoring level S, when the security monitoring index , corresponding to security monitoring level 1, each security monitoring level 1 corresponds to a security monitoring cycle, the cycle length of the security monitoring cycle corresponding to security monitoring level 1 is less than the cycle length of the security monitoring cycle corresponding to security monitoring level 2, and so on.

[0040] The security monitoring model is constructed in the following way: a deep learning model is constructed, the behavioral characteristics of multiple visitors are collected, the deep learning model is trained based on the behavioral characteristics of the visitors, and a security monitoring index is assigned to the behavioral characteristics of each visitor. The index range of the security monitoring index is (1.0~15.0). The larger the security monitoring index, the more abnormal the corresponding visitor's behavior is. The training data is divided into training set, validation set and test set in a ratio of 70%:15%:15%. The model is trained using the training set, and the value of the loss function is minimized by continuously adjusting the parameters of the model. During the training process, the validation set is used to monitor the performance of the model to avoid overfitting, and the trained model is evaluated using the test set. Finally, the security monitoring model is constructed.

[0041] Security monitoring adjustment module: When a visitor is not identified for the first time in video surveillance, the security monitoring cycle of the visitor is obtained. If one security monitoring cycle has passed since the last security monitoring index of the visitor was obtained, the security monitoring index of the visitor is obtained, and the visitor's visit dynamic index is simultaneously determined. The visitor's security monitoring level is adjusted according to the visit dynamic index, and the security impact range of the visitor is simultaneously determined;

[0042] The security impact range of key security visitors is determined based on the following method: a security impact radius is set corresponding to each security monitoring level. The higher the security monitoring level, the larger the corresponding security impact radius (for example, the security impact radius of security monitoring level 1 is larger than the security impact radius of security monitoring level 2). The security impact range of key security visitors is determined by drawing a circle with the current position of the key security visitor as the center and the security impact radius as the radius.

[0043] Adjust the visitor's security monitoring level according to the visit dynamic index: set the visit dynamic upper index and the visit dynamic lower index (the visit dynamic upper index is greater than the visit dynamic lower index, and both the visit dynamic upper index and the visit dynamic lower index are preset indexes). When the visitor's visit dynamic index is greater than the visit dynamic upper index, the corresponding visitor's security monitoring level will be increased by one level (for example, if the visitor's original security monitoring level is 2, it will be adjusted to security monitoring level 1). When the visitor's visit dynamic index is less than the visit dynamic lower index, the corresponding visitor's security monitoring level will be decreased by one level (for example, if the visitor's original security monitoring level is 2, it will be adjusted to security monitoring level 3). When the visitor's visit dynamic index is between the visit dynamic upper index and the visit dynamic lower index, the corresponding visitor's security monitoring level will be maintained.

[0044] The visitor's visit dynamic index is determined based on the following method: obtain all security monitoring indices previously obtained by a visitor, sort all security monitoring indices in the order of acquisition, calculate the absolute difference between two adjacent security monitoring indices after sorting, calculate the monitoring dynamic index, set the monitoring dynamic threshold index (the monitoring dynamic threshold index is a preset index used for comparison with the monitoring dynamic index), when the monitoring dynamic index is greater than the monitoring dynamic threshold index, increase the number of behavior repetitions by one (when the monitoring dynamic index is less than or equal to the monitoring dynamic threshold index, no processing is performed), and mark the number of behavior repetitions as , calculate the average value of all security monitoring indexes and get the average security monitoring index ,pass Get the visitor's visit dynamic index Among them, a1 is the first coefficient, and the value of a1 is 0.56.

[0045] Key security module: Set the security monitoring demarcation level (the security monitoring demarcation level is a preset level used for comparison with the security monitoring level). When a visitor's security monitoring level is higher than or equal to the security monitoring demarcation level, the visitor will be marked as a key security visitor (for example, if the security monitoring demarcation level is security monitoring level 4, then if the visitor is security monitoring level 1, security monitoring level 2, security monitoring level 3 or security monitoring level 4, the corresponding visitor needs to be marked as a target visitor).

[0046] Security tracing module: determine the security impact range of key security visitors, mark the remaining visitors within the security impact range as security-related visitors, determine the involved synchronization value of the security-related visitors, set the involved synchronization threshold (the involved synchronization threshold is a preset threshold used to compare with the involved synchronization value), when the involved synchronization value of the security-related visitor is greater than the involved synchronization threshold, mark the corresponding security-related visitor as a security tracing visitor (when the involved synchronization value of the security-related visitor is less than or equal to the involved synchronization threshold, no processing is performed).

[0047] The synchronization value of the security-related visitor is determined based on the following method: select a security-related visitor, obtain all the security impact ranges of the key security visitors that have been determined before, and when the security impact range is determined and the security-related visitor is within the security impact range, increase the number of synchronizations by one, calculate the ratio of the number of synchronizations to the total number of security impact ranges, and calculate the synchronization value of the security-related visitor.

[0048] Retrospective security adjustment module: obtain the security impact visit index of each security retrospective visitor, set the security impact visit threshold index (the security impact visit threshold index is a preset index used to compare with the security impact visit index). When the security impact visit index of the security retrospective visitor is greater than the security impact visit threshold index, the security monitoring level of the security retrospective visitor is adjusted to be consistent with the security monitoring level of the security key visitor (when the security impact visit index of the security retrospective visitor is less than or equal to the security impact visit threshold index, no processing is performed).

[0049] The security impact visit index of the security traceability visitor is obtained based on the following method: select a security traceability visitor, obtain the impact superposition index and visit dynamic index of the security traceability visitor, and mark , X1 is the impact superposition index of security retrospective visitors, X2 is the visit dynamic index of security retrospective visitors, obtain the impact superposition index and visit dynamic index of key security visitors, and mark them as , Y1 is the impact superposition index of security key visitors, Y2 is the visit dynamic index, and the cosine similarity algorithm is used to calculate the security impact visit index of security traceability visitors.

[0050] Security Retrospective Visitors' Security Impact Visiting Index .

[0051] The impact superposition index is obtained based on the following method: obtain all the security impact ranges previously determined by the visitor, sort all the security impact ranges in the determined order, compare the two adjacent security impact ranges after sorting, and when there is an intersection between two security impact ranges, mark the intersection area as Area (dz), d = 1, 2, ..., D-1, D, d is the sequence number of the intersection area, D is the total number of intersection areas, set the intersection area coefficient to Lz, z = 1, 2, ..., Z, L1 < L2 < ... < LZ-1 < LZ, each intersection area coefficient corresponds to the intersection area within a range, and the range of the intersection area includes When the intersection area When the intersection area coefficient is L1, Get the visitor's influence superposition index .

[0052] Through the security monitoring preliminary module, security monitoring adjustment module, key security module, security tracing module and tracing security adjustment module, combined with conventional identification technology, security monitoring is carried out on all visitors in the exhibition hall. According to the behavioral characteristics of the visitors, different security monitoring cycles are customized for each visitor to ensure the reasonable allocation of system monitoring and analysis resources. When abnormal behavior and repeated visitors are found in the exhibition hall, the corresponding visitors are promptly marked as key security visitors, and the visitors who may be affected are quickly and accurately identified, and retrospective analysis is carried out on the corresponding visitors to retrospectively analyze whether there is a possibility that the visitors will behave in accordance with the corresponding security key visitors.

[0053] Example 2: Reference Figure 3 , an exhibition intelligent security monitoring method based on the Internet of Things, comprising the following steps:

[0054] Step 1: Deploy video surveillance in the exhibition hall to identify visitors in real time. When a visitor is identified for the first time, determine the visitor's security monitoring cycle. If the visitor is not identified for the first time, obtain the visitor's security monitoring cycle. If the visitor's security monitoring index has reached one security monitoring cycle since the last time it was obtained, determine whether to adjust the visitor's security monitoring level and simultaneously determine the visitor's security impact range.

[0055] Step 2: When the visitor's security monitoring level is higher than or equal to the security monitoring threshold level, the visitor is marked as a key security visitor;

[0056] Step 3: Determine security traceability visitors;

[0057] Step 4: Determine whether to adjust the security monitoring level of the security traceability visitor to be consistent with the security monitoring level of the security key visitor.

[0058] The above method can trace back and analyze whether there is a possibility that a visitor will engage in behavior corresponding to a security-focused visitor. When it is found that the traced visitor has the possibility of engaging in corresponding behavior, the traced visitor is synchronously monitored, so that security personnel can take corresponding response measures in advance.

[0059] The above formulas are all dimensionless and numerically calculated, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0060] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0061] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0062] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0063] Those skilled in the art will 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.

[0064] In the several embodiments provided in this 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 merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0065] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0066] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An exhibition intelligent security monitoring system based on the Internet of Things, characterized by: Including security monitoring preliminary module, security monitoring adjustment module, key security module, security tracing module, and tracing security adjustment module; The security monitoring initialization module deploys video surveillance in the exhibition hall and identifies visitors in the video surveillance in real time. When a visitor in the video surveillance is identified for the first time, the security monitoring period of the visitor is determined; The security monitoring adjustment module, when a visitor is not identified for the first time in the video surveillance, obtains the visitor's security monitoring cycle, and if the visitor's security monitoring index has reached one security monitoring cycle since the last time it was obtained, determines whether to adjust the visitor's security monitoring level, and simultaneously determines the visitor's security impact range; The key security module marks a visitor as a key security visitor when the visitor's security monitoring level is higher than or equal to the security monitoring threshold level; The security tracing module is used to determine security tracing visitors; The retrospective security adjustment module determines whether to adjust the security monitoring level of the security retrospective visitor to be consistent with the security monitoring level of the security key visitor.

2. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 1 is characterized in that: The security monitoring period of a visitor is determined based on the following method: obtaining the security monitoring index of the visitor, determining the security monitoring level of the visitor based on the security monitoring index, and performing security monitoring on the visitor based on the security monitoring period corresponding to the security monitoring level.

3. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 2 is characterized in that: The visitor's security monitoring index is obtained based on the following method: extracting the image frame in which the visitor is first identified in the video surveillance, extracting the visitor's behavioral characteristics based on the extracted image frame, obtaining a security monitoring model, using the behavioral characteristics as input data of the security monitoring model, and the security monitoring model outputs the visitor's security monitoring index value (dcs).

4. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 2 is characterized in that: The security monitoring level of the visitor is determined based on the following method: obtaining the visitor's security monitoring index value (dcs), setting the range of each security monitoring index to correspond to a security monitoring level, the range of the security monitoring index includes (0, value (dc1)], (value (dc1), value (dc2)], ..., (value (dcS-1), (value (dcS)], the security monitoring levels include security monitoring level 1, security monitoring level 2, ..., security monitoring level S-1, security monitoring level S, each security monitoring level corresponds to a security monitoring cycle, the cycle length of the security monitoring cycle corresponding to security monitoring level 1 is less than the cycle length of the security monitoring cycle corresponding to security monitoring level 2, and so on.

5. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 1 is characterized in that: Determine whether to adjust the visitor's security monitoring level: obtain the visitor's security monitoring index, simultaneously determine the visitor's visit dynamic index, set the visit dynamic upper index and the visit dynamic lower index. When the visitor's visit dynamic index is greater than the visit dynamic upper index, the corresponding visitor's security monitoring level will be increased by one level. When the visitor's visit dynamic index is less than the visit dynamic lower index, the corresponding visitor's security monitoring level will be decreased by one level. When the visitor's visit dynamic index is between the visit dynamic upper index and the visit dynamic lower index, the corresponding visitor's security monitoring level will be maintained.

6. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 5 is characterized in that: The visitor's visit dynamic index is determined based on the following method: obtain all the security monitoring indexes previously obtained by a visitor, sort all the security monitoring indexes in the order of acquisition, calculate the absolute difference between the two adjacent security monitoring indexes after sorting, calculate the monitoring dynamic index, set the monitoring dynamic threshold index, when the monitoring dynamic index is greater than the monitoring dynamic threshold index, increase the number of repeated behaviors by one, mark the number of repeated behaviors as nuti (repeatedly), calculate the sum and average of all security monitoring indexes, and calculate the average security monitoring index Avj (monitor), and obtain the visitor's visit dynamic index dyn (visit) by dyn (visit) = nuti (repeatedly) * [Avj (monitor) + a1].

7. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 1 is characterized in that: The security impact range of key security visitors is determined based on the following method: each security monitoring level is set to correspond to a security impact radius. The higher the security monitoring level, the larger the corresponding security impact radius. The security impact range of key security visitors is determined by drawing a circle with the current position of the key security visitor as the center and the security impact radius as the radius.

8. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 1 is characterized in that: The security traceability visitor is determined based on the following method: determining the security impact range of the key security visitor, marking the remaining visitors within the security impact range as security-related visitors, determining the involved synchronization value of the security-related visitors, setting the involved synchronization threshold, and when the involved synchronization value of the security-related visitor is greater than the involved synchronization threshold, marking the corresponding security-related visitor as a security traceability visitor; The synchronization value of the security-related visitor is determined based on the following method: select a security-related visitor, obtain all the security impact ranges of the key security visitors that have been determined before, and when the security impact range is determined and the security-related visitor is within the security impact range, increase the number of synchronizations by one, calculate the ratio of the number of synchronizations to the total number of security impact ranges, and calculate the synchronization value of the security-related visitor.

9. The exhibition intelligent security monitoring system based on the Internet of Things according to claim 1 is characterized in that: Determine whether to adjust the security monitoring level of the security tracing visitor to be consistent with the security monitoring level of the security key visitor: obtain the security impact visit index of each security tracing visitor, set the security impact visit threshold index, and when the security impact visit index of the security tracing visitor is greater than the security impact visit threshold index, adjust the security monitoring level of the security tracing visitor to be consistent with the security monitoring level of the security key visitor; The security impact visit index of a security tracing visitor is obtained based on the following method: select a security tracing visitor, obtain the impact superposition index and visit dynamic index of the security tracing visitor, and mark them as [X1, X2], where X1 is the impact superposition index of the security tracing visitor, and X2 is the visit dynamic index of the security tracing visitor; obtain the impact superposition index and visit dynamic index of a key security visitor, and mark them as [Y1, Y2], where Y1 is the impact superposition index of the key security visitor, and Y2 is the visit dynamic index of the key security visitor; and use the cosine similarity algorithm to calculate the security impact visit index of the security tracing visitor; The impact superposition index is obtained based on the following method: obtain all security impact ranges previously determined by the visitor, sort all security impact ranges in the determined order, compare the two adjacent security impact ranges after sorting, and when two security impact ranges have an intersection, mark the intersection area as Area(dz), d = 1, 2, ..., D-1, D, d is the sequence number of the intersection area, D is the total number of intersection areas, set the intersection area coefficient as Lz, z = 1, 2, ..., Z, L1 < L2 < ... < LZ-1 < LZ, through Get the visitor's influence superposition index index (fr).

10. An exhibition intelligent security monitoring method based on the Internet of Things, applied to an exhibition intelligent security monitoring system based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Deploy video surveillance in the exhibition hall to identify visitors in real time. When a visitor is identified for the first time, determine the visitor's security monitoring cycle. If the visitor is not identified for the first time, obtain the visitor's security monitoring cycle. If the visitor's security monitoring index has reached one security monitoring cycle since the last time it was obtained, determine whether to adjust the visitor's security monitoring level and simultaneously determine the visitor's security impact range. Step 2: When the visitor's security monitoring level is higher than or equal to the security monitoring threshold level, the visitor is marked as a key security visitor; Step 3: Determine security traceability visitors; Step 4: Determine whether to adjust the security monitoring level of the security traceability visitor to be consistent with the security monitoring level of the security key visitor.

Images