Entertainment equipment real-time safety monitoring system based on Internet of Things

Abstract

The invention relates to the technical field of entertainment equipment safety monitoring, in particular to a real-time entertainment equipment safety monitoring system based on the Internet of Things. The system comprises an equipment information fusion module, a dynamic event triggering module and an equipment optimization control module, the equipment information fusion module is used for inputting node information i belonging to v {1,..., n} of all the entertainment equipment into a stacked automatic encoder neural network to extract data features, establishing a credibility mechanism of feature information based on the data features, obtaining a decision model from state information Si (k) of all the entertainment equipment through a Bayesian decision-based data fusion algorithm, and outputting the decision model; the dynamic event triggering module is used for judging whether the node information of the entertainment equipment subjected to information fusion meets a dynamic event triggering requirement or not; and the equipment optimization control module is used for carrying out group target optimization control on the entertainment equipment meeting the dynamic event triggering requirement. The safety management efficiency of the entertainment equipment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring of amusement equipment, and in particular to a real-time security monitoring system for amusement equipment based on the Internet of Things. Background Art

[0002] With the development of science and technology and the improvement of people's living standards, amusement equipment, as a kind of entertainment facilities, is becoming more and more popular among the general public. However, the potential safety hazards in the operation of amusement equipment cannot be ignored. In order to ensure the safety of tourists and improve the management efficiency of amusement equipment, a real-time safety monitoring system for amusement equipment based on the Internet of Things came into being.

[0003] Traditional amusement equipment safety monitoring methods mainly rely on manual inspections and regular maintenance, which is not only inefficient but also prone to missing safety hazards. In addition, traditional monitoring methods cannot achieve real-time status monitoring and fault warning of amusement equipment. Once a fault or accident occurs, it often causes serious consequences.

[0004] In the prior art, there is a lack of a real-time security monitoring system for amusement equipment based on the Internet of Things to improve the efficiency of real-time security monitoring of amusement equipment and optimize the control of group targets when abnormal data occurs in a certain amusement equipment. Summary of the invention

[0005] The purpose of the present invention is to provide a real-time security monitoring system for amusement equipment based on the Internet of Things: at least to solve the problems of low monitoring efficiency and low security caused by relying on manual inspections and regular maintenance to monitor amusement equipment in existing solutions.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A real-time security monitoring system for amusement equipment based on the Internet of Things, which includes an equipment information fusion module, a dynamic event trigger module, and an equipment optimization control module;

[0008] The device information fusion module is used to input the node information of each amusement device i∈v{1,...,n} into the stacked autoencoder neural network to extract data features, where n is the amusement device number, and establish a trust mechanism for feature information based on data features, where the trust mechanism for feature information is used to assign weights to feature information, and then the status information S of each amusement device is i (k) obtaining a decision model through a data fusion algorithm based on Bayesian decision making, and completing information fusion based on the decision model, where k is the number of hidden layers;

[0009] The dynamic event triggering module is used to determine whether the amusement device node information i∈v{1, ..., n} that has completed information fusion meets the dynamic event triggering requirements;

[0010] The equipment optimization control module is used to optimize the group objectives of amusement equipment after meeting the dynamic event triggering requirements: Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making.

[0011] Furthermore, the information of each amusement device node i∈v{1, ..., n} is input into the stacked autoencoder neural network to extract data features, which specifically includes the following process:

[0012] For each amusement device node information i∈v{1,...,n}, the node information includes the amusement device location information x i and amusement equipment speed status information v i , x i 、v i Input to the stacked autoencoder neural network output network connection weight matrix W h , h∈[1,k] and the output y of the kth hidden layer k , the specific steps are as follows:

[0013] Step S1: train the network parameter W1 corresponding to the first hidden layer using the original training set based on the autoencoder, and obtain the output y1 of the first hidden layer according to the trained parameters;

[0014] Step S2: Use the output y1 of the previous step as the input of the next autoencoder to obtain W1 and y2;

[0015] Step S3: Save W1 and y2;

[0016] Step S4: Repeat steps S2 and S3 until the kth hidden layer is reached and W is obtained. k and k ;

[0017] Step S5: Expand all trained autoencoders and the loss function is applied to the obtained W k and k Perform weight allocation and bind the decoder and encoder weights.

[0018] Furthermore, the trust mechanism of feature information based on data features specifically includes the following processes:

[0019] For each amusement device node information i∈v{1,...,n}, the characteristic information f under the trust weight distribution i (k) is calculated as follows:

[0020]

[0021] Among them, εi (k) represents all neighboring nodes centered on node i, β ab (k) represents the weight of the type b information contained in node i with respect to the type a information, γ(S i (k)-S i (k-1)) represents the state information S of each amusement device corresponding to the kth hidden layer i (k) The state information S of each amusement device corresponding to the k-1th hidden layer i (k-1) information difference, f ib (k) represents the eigenvalue corresponding to the characteristic information of type b, f ia (k) represents the feature value corresponding to the feature information of type a information.

[0022] Furthermore, the status information S of each amusement device is i (k) Obtaining a decision model through a Bayesian decision-making data fusion algorithm, and completing information fusion based on the decision model, specifically including the following process:

[0023] Preset Bayesian decision model: P(S i (k)|f i (k), τ), where τ is the expected deviation under the loss function;

[0024] Get the conditional probability P(S i (k)|f i (k)) and P(f i (k)), where P(S i (k)|f i (k)) represents the status information S of each amusement device i (k) In the feature information f i (k) probability of occurrence under condition, P(f i (k)) represents the feature information f i (k) probability of occurrence;

[0025] The decision model is obtained through the data fusion algorithm of Bayesian decision-making, and information fusion is completed based on the decision model. The decision model is as follows:

[0026] P(f i (k)|S i (k)) = P(S i (k)|f i (k),τ)*P(f i (k)) / P(S i (k))

[0027] Among them, P(S i (k)) represents the status information S of each amusement device i(k) Probability of occurrence.

[0028] Furthermore, the dynamic event triggering module is used to determine whether the information of the amusement device node that has completed information fusion meets the dynamic event triggering requirements, which specifically includes the following process:

[0029] Obtain neighbor node information μ based on amusement device node information i∈v{1,...,n} i (t), the neighbor node information is the sum of the distances from all neighbor nodes centered on node i to the target node;

[0030] Determine neighbor node information μ i (t) Whether it exceeds a preset total threshold, if so, the dynamic event triggering requirement is met, if not, the dynamic event triggering requirement is not met.

[0031] Furthermore, Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making. Specifically, the following processes are included:

[0032] Step 1: Calculate the Euclidean distance between the next node and the target node and the adjacent nodes;

[0033] Step 2: Determine groups based on Euclidean distance;

[0034] Step 3: Calculate the average value of the cumulative deviations of other nodes in the group except the current node from the target node;

[0035] Step 4: Based on the average value of the accumulated deviation, determine whether the task set of the central node is updated. If so, update the task set of the central node.

[0036] Step 5: Optimize control based on the updated central node task set.

[0037] Furthermore, the Pareto optimal method is adopted in the optimization control method.

[0038] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0039] On the one hand, the present invention extracts data features by inputting each amusement device node information i∈v{1,...,n} into a stacked autoencoder neural network, where n is the amusement device number, and establishes a trust mechanism for feature information based on data features, where the trust mechanism for feature information is used to assign weights to feature information, and then the state information S of each amusement device is converted into a trust mechanism for feature information. i (k) The decision model is obtained through the data fusion algorithm of Bayesian decision-making, and information fusion is completed based on the decision model. There is no need to rely on manual inspection of amusement equipment on a regular basis, which can improve the management efficiency of amusement equipment and improve the safety of amusement equipment operation.

[0040] On the other hand, the present invention improves the control efficiency of the entire amusement system when abnormal data appears in the amusement equipment by optimizing the group target control of the amusement equipment after satisfying the dynamic event triggering requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 This is a system block diagram of a real-time security monitoring system for amusement equipment based on the Internet of Things according to an embodiment of the present invention;

[0043] Figure 2 This is a workflow diagram of a real-time security monitoring system for amusement equipment based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0046] This embodiment provides a real-time security monitoring system for amusement equipment based on the Internet of Things. Figure 1 is a system block diagram of a real-time security monitoring system for amusement equipment based on the Internet of Things according to an embodiment of the present invention. Figure 1 As shown, the system includes an equipment information fusion module, a dynamic event triggering module and an equipment optimization control module;

[0047] The device information fusion module is used to input the node information of each amusement device i∈v{1,...,n} into the stacked autoencoder neural network to extract data features, where n is the amusement device number, and establish a trust mechanism for feature information based on data features, where the trust mechanism for feature information is used to assign weights to feature information, and then the status information S of each amusement device is i (k) A decision model is obtained through a data fusion algorithm based on Bayesian decision making, and information fusion is completed based on the decision model, where k is the number of hidden layers.

[0048] Specifically, the process of inputting the node information of each amusement device i∈v{1, ..., n} into the stacked autoencoder neural network to extract data features specifically includes the following steps:

[0049] For each amusement device node information i∈v{1,...,n}, the node information includes the amusement device location information x i and amusement equipment speed status information v i , x i 、v i Input to the stacked autoencoder neural network output network connection weight matrix W h , h∈[1,k] and the output y of the kth hidden layer k , the specific steps are as follows:

[0050] Step S1: train the network parameter W1 corresponding to the first hidden layer using the original training set based on the autoencoder, and obtain the output y1 of the first hidden layer according to the trained parameters;

[0051] Step S2: Use the output y1 of the previous step as the input of the next autoencoder to obtain W1 and y2;

[0052] Step S3: Save W1 and y2;

[0053] Step S4: Repeat steps S2 and S3 until the kth hidden layer is reached and W is obtained. k and k ;

[0054] Step S5: Expand all trained autoencoders and the loss function is applied to the obtained w k and k Perform weight allocation and bind the decoder and encoder weights.

[0055] Furthermore, the trust mechanism of feature information based on data features specifically includes the following processes:

[0056] For each amusement device node information i∈v{1,...,n}, the characteristic information f under the trust weight distribution i(k) is calculated as follows:

[0057]

[0058] Among them, ε i (k) represents all neighboring nodes centered on node i, β ab (k) represents the weight of the type b information contained in node i with respect to the type a information, γ(S i (k)-S i (k-1)) represents the state information S of each amusement device corresponding to the kth hidden layer i (k) The state information S of each amusement device corresponding to the k-1th hidden layer i (k-1) information difference, f ib (k) represents the eigenvalue corresponding to the characteristic information of type b, f ia (k) represents the feature value corresponding to the feature information of type a information.

[0059] Furthermore, the status information S of each amusement device is i (k) Obtaining a decision model through a Bayesian decision-making data fusion algorithm, and completing information fusion based on the decision model, specifically including the following process:

[0060] Preset Bayesian decision model: P(S i (k)|f i (k), τ), where τ is the expected deviation under the loss function;

[0061] Get the conditional probability P(S i (k)|f i (k)) and P(f i (k)), where P(S i (k)|f i (k)) represents the status information S of each amusement device i (k) In the feature information f i (k) probability of occurrence under condition, P(f i (k)) represents the feature information f i (k) probability of occurrence;

[0062] The decision model is obtained through the data fusion algorithm of Bayesian decision-making, and information fusion is completed based on the decision model. The decision model is as follows:

[0063] P(f i (k)|S i (k)) = P(S i (k)|f i (k),τ)*P(f i (k)) / P(S i(k))

[0064] Among them, P(S i (k)) represents the status information S of each amusement device i (k) Probability of occurrence.

[0065] The dynamic event triggering module is used to determine whether the amusement device node information i∈v{1, ..., n} that has completed information fusion meets the dynamic event triggering requirements.

[0066] It is worth noting that the dynamic event triggering module is used to determine whether the information of the amusement device node that has completed information fusion meets the dynamic event triggering requirements, and specifically includes the following process:

[0067] Obtain neighbor node information μ based on amusement device node information i∈v{1,...,n} i (t), the neighbor node information is the sum of the distances from all neighbor nodes centered on node i to the target node;

[0068] Determine neighbor node information μ i (t) Whether it exceeds a preset total threshold, if so, the dynamic event triggering requirement is met, if not, the dynamic event triggering requirement is not met.

[0069] The equipment optimization control module is used to optimize the group objectives of amusement equipment after meeting the dynamic event triggering requirements: Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making.

[0070] Figure 2 : is a workflow diagram of a real-time security monitoring system for amusement equipment based on the Internet of Things according to an embodiment of the present invention, such as Figure 2 As shown in the figure, Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups, and the global coordination under distributed small-scale decision-making is realized, which specifically includes the following processes:

[0071] Step 1: Calculate the Euclidean distance between the next node and the target node and the adjacent nodes;

[0072] Step 2: Determine groups based on Euclidean distance;

[0073] Step 3: Calculate the average value of the cumulative deviations of other nodes in the group except the current node from the target node;

[0074] Step 4: Based on the average value of the accumulated deviation, determine whether the task set for updating the central node is met. If so, update the central node task set. When the average value of the accumulated deviation is greater than a preset threshold, the task set for updating the central node is met. Otherwise, the task set for updating the central node is not met.

[0075] Step 5: Optimize control based on the updated central node task set.

[0076] In some embodiments, Mesh dynamic networking divides the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making, which is a complex and delicate process. This process involves multiple key steps to ensure that the intelligent cluster can achieve overall collaborative work while maintaining local autonomy. The following are the specific steps of this process:

[0077] Agent cluster initialization:

[0078] Initialize all intelligent agents, including communication modules, perception modules, decision-making modules, etc.

[0079] Determine the basic properties and capabilities of the agent, such as movement speed, perception range, communication distance, etc.

[0080] Mesh dynamic networking construction:

[0081] The Mesh network is dynamically constructed based on the location, communication capabilities and network environment of the intelligent agent.

[0082] Mesh networks should have good robustness and adaptability and be able to cope with dynamic changes in intelligent agent clusters.

[0083] Small-scale segmentation strategy development:

[0084] Design a suitable partitioning algorithm, taking into account factors such as the number, distribution, and task requirements of agents.

[0085] The algorithm should be able to quickly and efficiently divide the agent cluster into multiple small sub-clusters.

[0086] Distributed decision-making mechanism design:

[0087] A distributed decision-making mechanism is designed for each sub-cluster to enable them to make autonomous decisions locally.

[0088] The decision-making mechanism should take into account the information interaction and coordination within the sub-cluster to ensure the optimality of local decisions.

[0089] Global coordination strategy implementation:

[0090] Design a global coordination strategy to integrate the local decisions of each sub-cluster and achieve overall collaborative work.

[0091] The coordination strategy should be able to handle conflicts and competitions between subclusters to ensure the achievement of global goals.

[0092] Communication and information sharing mechanisms:

[0093] Establish an effective communication mechanism to ensure that agents can exchange information in real time.

[0094] Design information sharing strategies to enable intelligent agents to fully utilize information resources in the cluster and improve decision-making efficiency.

[0095] Dynamic adjustment and optimization:

[0096] Dynamically adjust the topology of the Mesh network and the strategy of small-scale partitioning according to task execution and environmental changes.

[0097] By learning and optimizing algorithms, the collaborative ability and global performance of the intelligent agent cluster are continuously improved.

[0098] Furthermore, the Pareto optimal method is used for optimizing control:

[0099] The application of Pareto optimal strategy in amusement equipment is mainly reflected in resource allocation and operation management. Pareto optimality, as an ideal state for solving multi-objective optimization problems, emphasizes making at least one person's situation better without anyone's situation getting worse. In the actual operation of amusement equipment, this strategy can help achieve more efficient and fairer resource utilization and allocation.

[0100] First, from the perspective of resource allocation, the resources that may need to be allocated to amusement equipment include electricity, maintenance personnel, equipment usage time, etc. The Pareto optimal strategy can help decision makers determine how to optimally allocate these resources to meet the needs of different amusement equipment while ensuring that no equipment is affected by insufficient resources. For example, resources can be dynamically allocated based on factors such as the frequency of use of each device, maintenance requirements, and visitor satisfaction to maximize resource utilization efficiency.

[0101] Secondly, in terms of operation management, the Pareto optimal strategy can also play an important role. The operation management of amusement equipment involves multiple aspects such as equipment scheduling, maintenance, and updating. By applying the Pareto optimal strategy, it is possible to minimize operating costs and improve operating efficiency while meeting the needs of tourists. For example, the optimal equipment scheduling and maintenance plan can be formulated based on information such as the operating status of the equipment, fault prediction, and the real-time needs of tourists to reduce equipment downtime and improve tourist satisfaction.

[0102] In addition, the Pareto optimal strategy can also be combined with modern technologies such as the Internet of Things and big data to further improve the management efficiency and safety of recreational equipment. By real-time monitoring of the operating status of equipment and the use of tourists, resource allocation and operation strategies can be adjusted in real time to achieve Pareto optimality.

[0103] In summary, the present invention extracts data features by inputting the node information of each amusement device i∈v{1,...,n} into a stacked autoencoder neural network, where n is the number of the amusement device, and establishes a trust mechanism for feature information based on data features, where the trust mechanism for feature information is used to assign weights to feature information, and then the state information S of each amusement device is converted into a trust mechanism for feature information. i (k) The decision model is obtained through the data fusion algorithm of Bayesian decision-making, and information fusion is completed based on the decision model. There is no need to rely on manual inspection of amusement equipment on a regular basis, which can improve the management efficiency of amusement equipment and improve the safety of amusement equipment operation.

[0104] By optimizing the group target control of the amusement equipment after meeting the dynamic event triggering requirements, the control efficiency of the entire amusement system is improved when abnormal data appears in the amusement equipment.

[0105] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by 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 programs 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 site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access 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 hard disk.

[0106] Those of ordinary skill 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 to be beyond the scope of this application.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0108] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, 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.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] 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 can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A real-time security monitoring system for amusement equipment based on the Internet of Things, characterized by: The system includes an equipment information fusion module, a dynamic event triggering module and an equipment optimization control module; The device information fusion module is used to input the node information of each amusement device i∈v{1,...,n} into the stacked autoencoder neural network to extract data features, where n is the amusement device number, and establish a trust mechanism for feature information based on data features, where the trust mechanism for feature information is used to assign weights to feature information, and then the status information S of each amusement device is i (k) obtaining a decision model through a data fusion algorithm based on Bayesian decision making, and completing information fusion based on the decision model, where k is the number of hidden layers; The dynamic event triggering module is used to determine whether the amusement device node information i∈v{1,...,n} that has completed information fusion meets the dynamic event triggering requirements; The equipment optimization control module is used to optimize the group objectives of amusement equipment after meeting the dynamic event triggering requirements: Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making.

2. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 1 is characterized in that: Input the node information of each amusement device i∈v{1,...,n} into the stacked autoencoder neural network to extract data features. The process includes: For each amusement device node information i∈v{1,...,n}, the node information includes the amusement device location information x i and amusement equipment speed status information v i , x i 、v i Input to the stacked autoencoder neural network output network connection weight matrix W h , h∈[1,k] and the output y of the kth hidden layer k , the specific steps are as follows: Step S1: train the network parameter W1 corresponding to the first hidden layer using the original training set based on the autoencoder, and obtain the output y1 of the first hidden layer according to the trained parameters; Step S2: Use the output y1 of the previous step as the input of the next autoencoder to obtain W1 and y2; Step S3: Save W1 and y2; Step S4: Repeat steps S2 and S3 until the kth hidden layer is reached and W is obtained. k and k ; Step S5: Expand all trained autoencoders and the loss function is applied to the obtained W k and k Perform weight allocation and bind the decoder and encoder weights.

3. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 2 is characterized in that: The trust mechanism for feature information based on data features specifically includes the following processes: For each amusement device node information i∈v{1,...,n}, the characteristic information f under the trust weight distribution i (k0 is calculated as follows: Among them, ε i (k) represents all neighboring nodes centered on node i, β ab (k) represents the weight of the type b information contained in node i with respect to the type a information, γ(S i (k)-S i (k-1)) represents the state information S of each amusement device corresponding to the kth hidden layer i (k) The state information S of each amusement device corresponding to the k-1th hidden layer i (k-1) information difference, f ib (k) represents the eigenvalue corresponding to the characteristic information of type b, f ia (k) represents the feature value corresponding to the feature information of type a information.

4. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 3 is characterized in that: The status information S of each amusement device i (k) Obtaining a decision model through a Bayesian decision-making data fusion algorithm, and completing information fusion based on the decision model, specifically including the following process: Preset Bayesian decision model: P(S i (k0|f i (k), τ), where τ is the expected deviation under the loss function; Get the conditional probability P(S i (k)|f i (k)) and P(f i (k)), where P(S i (k)|f i (k)) represents the status information S of each amusement device i (k) In the feature information f i (k) probability of occurrence under condition, P(f i (k)) represents the feature information f i (k) probability of occurrence; The decision model is obtained through the data fusion algorithm of Bayesian decision-making, and information fusion is completed based on the decision model. The decision model is as follows: P(f i (k)|S i (k))=P(S i (k)|f i (k),τ)*P(f i (k)) / P(S i (k)) Among them, P(S i (k)) represents the status information S of each amusement device i (k) Probability of occurrence.

5. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 1 is characterized in that: The dynamic event trigger module is used to determine whether the information of the amusement device node that has completed information fusion meets the dynamic event trigger requirements, which specifically includes the following processes: Get neighbor node information μ based on amusement device node information i∈v{1,...,n} i (t), the neighbor node information is the sum of the distances from all neighbor nodes centered on node i to the target node; Determine neighbor node information μ i (t) Whether it exceeds a preset total threshold, if so, the dynamic event triggering requirement is met, if not, the dynamic event triggering requirement is not met.

6. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 1 is characterized in that: Mesh dynamic networking is used to divide the multi-agent cluster into small-scale groups to achieve global coordination under distributed small-scale decision-making. The specific process also includes the following: Step 1: Calculate the Euclidean distance between the next node and the target node and the adjacent nodes; Step 2: Grouping based on Euclidean distance; Step 3: Calculate the average value of the cumulative deviations of other nodes in the group except the current node from the target node; Step 4: Based on the average value of the accumulated deviation, determine whether the task set of the central node is updated. If so, update the task set of the central node. Step 5: Optimize control based on the updated central node task set.

7. The real-time security monitoring system for amusement equipment based on the Internet of Things according to claim 6 is characterized in that: The Pareto optimal method is adopted for optimizing control.

Images