Museum event handling platform based on multiple agents

Abstract

The invention discloses a museum event handling platform based on multiple agents, relates to the technical field of artificial intelligence, and solves the problems that the risk event handling process of a museum is tedious, risk events cannot be well solved and the risk events occur repeatedly. The museum event handling platform comprises an environment monitoring agent, an event early warning agent, a resource scheduling agent, an emergency handling agent and a collaborative rehearsal agent. Through effective cooperation of multiple agents, the tedious and complex museum risk event processing flow is simplified, so that the museum risk event processing time is shortened, and the museum risk event processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a museum event handling platform based on multi-agents. Background Art

[0002] As a strategic technology leading a new round of scientific and technological revolution and industrial transformation, artificial intelligence has increasingly realized innovative applications across fields, tasks, and modes. With the deepening integration of digital technology and museums, using artificial intelligence to improve the digital supply efficiency of museums and achieve high-quality development has important strategic value and practical significance.

[0003] The digital supply of museums is a new model and form that deeply uses the Internet and digital technology to reshape the core functions of museums such as collection, research, display, and education, innovate the museum's online and offline integrated product and service system, and enhance the museum's protection, management, and service capabilities. The current museum digital supply system can be summarized into three levels.

[0004] First, digital technology is used to digitize the cultural relics in the collection. That is, digital information collection, storage, analysis and processing of cultural relics are carried out, and the form, structure, decoration and other information of buildings, landscapes and environments are fully and accurately reproduced, thus providing the necessary conditions for the restoration, reproduction, sharing and reuse of cultural relics.

[0005] Second, integrate, develop and transform museum database resources. Use virtual reality, 3D vision, holographic imaging and other technical means to build a virtual roaming system, and provide visitors with remote access, online visits, voice guides, positioning navigation and other "at your fingertips" and "out-of-the-box" services through the Internet and various smart terminals, providing multiple scenarios for museum digital exhibitions, research and educational activities.

[0006] Third, the construction and system integration of the museum digital management platform. Using technologies such as big data, artificial intelligence, the Internet of Things, blockchain, digital twins, AR / VR / MR, image recognition, and knowledge graphs, we will build a digital operation and management platform from protection and restoration to exhibition, display, education, and communication, giving the museum an "intelligent brain" and realizing the transformation of museum management from "experience-driven" to "data-driven".

[0007] AI agents are based on large language models and have the ability to autonomously understand, perceive, plan, remember, and use tools. They are systems that can automatically execute and complete complex tasks. The success of AI agents has provided strong support for the construction of group intelligence. Multiple AI agents can collaborate and complement each other to complete higher-level complex tasks that go beyond a single agent.

[0008] Patent No. CN2022104095185 discloses a museum cultural relic management system based on big data analysis and a method for use thereof, the system comprising a management platform, the management platform comprising a core control module, a data display module, and a platform operation module; the above invention also proposes a method for use of a museum cultural relic management system based on big data analysis, comprising the following steps: S1, setting a vehicle gate at the vehicle entrance and exit, S2, setting a face recognition camera in the museum display area, storage area and other cultural relic storage areas, S3, setting a monitoring center in the museum, and the monitoring center is equipped with a behavior analysis camera. The present invention is provided with an intelligent recognition module, so that the personnel, wheels, and cultural relics entering and leaving the museum can be effectively identified, recorded, and monitored in real time, thereby ensuring the safety inside and outside the museum, and in addition, an intelligent early warning system is provided, which can analyze and warn the events occurring in the museum, so as to achieve the purpose of timely early warning, thereby ensuring the safety of cultural relics.

[0009] Patent No. CN2019102129931 discloses a museum tour guide robot based on Raspberry Pi and its use method. The museum tour guide robot based on Raspberry Pi includes a main control robot base, a visual sensor, a speaker, a Raspberry Pi, an LCD and a humanoid shell; the use method of the museum tour guide robot based on Raspberry Pi includes: starting the system; initialization; controlling the robot to walk and establish a map of the museum's indoor environment; loading the established two-dimensional map in the 3D visualization tool RVIZ, and setting multiple destinations in the LCD; combining global path planning and local path planning for navigation to complete the navigation guidance task; after arriving at the destination, the Raspberry Pi plays the relevant audio through the speaker to complete the explanation task to the visitor. The present invention realizes the autonomous navigation of the robot, strengthens the human-computer interaction function, improves the ability to respond to emergencies, and realizes the guidance function during the navigation process.

[0010] However, the above patents cannot provide corresponding processing strategies for museums in dealing with risk events. For example, there is often no system in the process of handling risk events in the same museum, which leads to cumbersome risk event handling process, failure to properly resolve risk events and repeated occurrence of risk events. Summary of the invention

[0011] The purpose of the present invention is to provide a museum event handling platform based on multi-agents, which can simplify the cumbersome and complex museum risk event handling process through effective collaboration of multiple agents, thereby effectively shortening the handling time of museum risk events and greatly improving the handling efficiency of museum risk events.

[0012] The present invention utilizes the following technical solutions: A museum event handling platform based on multi-agents, including environmental monitoring agent, event warning agent, resource scheduling agent, emergency response agent and collaborative rehearsal agent; The environment monitoring agent is used to build a digital virtual museum based on the museum's architecture and exhibition information. On the other hand, it collects the museum's internal and surrounding comprehensive data in real time to obtain the museum's comprehensive monitoring data, and combines the preset abnormality judgment rules to obtain the abnormal data set. Then, a dynamic virtual museum is obtained based on the digital virtual museum and the abnormal data set. Among them, the internal comprehensive data includes display environment data and visitor quantity behavior data; display environment data includes temperature, humidity, air quality, light intensity, oxygen concentration and noise decibel value; visitor quantity behavior data includes crowd density and visitor behavior; surrounding comprehensive data includes weather data, public activity data and natural disaster data; The event warning agent is used to simulate the risk anomalies of the abnormal data set based on the museum monitoring data and the abnormal data set, and obtain risk warning reports and security control information; Resource scheduling agent, used to schedule the physical museum's security resources according to the risk warning report, and to allocate security resources according to the security control information, and obtain the resource allocation table; The emergency response agent is used to use the spatiotemporal data analysis algorithm or the game consensus algorithm to simulate and process risk events of the dynamic virtual museum based on the proposed resource allocation table and the abnormal data set to obtain a multimodal emergency plan; The collaborative rehearsal agent is used to coordinate the museum risk events through the above four agents according to the multimodal emergency plan and obtain the event emergency rehearsal report.

[0013] Preferably, the environment monitoring agent uses a three-dimensional modeling algorithm to construct a digital virtual museum based on the museum's architecture and display information; On the other hand, the environmental monitoring agent first uses wireless sensor networks, intelligent monitoring cameras, data analysis tools and remote sensing meteorological satellites to collect the museum's internal comprehensive data and surrounding comprehensive data, and records the data collection time; then the environmental monitoring agent uses the data segmentation algorithm to divide the internal comprehensive data and surrounding comprehensive data into several original data blocks according to the data collection time; the environmental monitoring agent then uses the data cleaning algorithm to deduplicate the information data in each original data block, verify the data consistency and standardize the data to obtain several standard data blocks; then, the environmental monitoring agent uses the data classification algorithm to cluster the information data in each standard data block according to the data type to obtain several set data blocks; then, the environmental monitoring agent uses the data association algorithm to associate and normalize the set data blocks of the internal environment and the surrounding environment according to the data collection time to obtain the museum's comprehensive monitoring data; finally, combined with the preset anomaly judgment rules and using the data anomaly detection algorithm, the abnormal information data in the set data block is aggregated into an abnormal data set, that is, an abnormal data set is obtained; at that time, the environmental monitoring agent uses the data fusion algorithm to integrate the abnormal data set into the digital virtual museum to obtain a dynamic virtual museum.

[0014] Preferably, the event warning agent first extracts the tourist quantity behavior data from the museum monitoring data, and uses the human body reconstruction algorithm in combination with the cultural relics display information to reshape all tourists within the range of X1 to X2 centimeters near each cultural relics exhibition stand according to the tourist behavior characteristics to generate virtual characters, and generate virtual visitors; then the event warning agent uses the action redirection algorithm in combination with the tourist behavior to generate a set of tourist action vectors for the virtual visitors; then the event warning agent simulates various risk events of the digital virtual museum based on the virtual visitors and the tourist action vector set, and at the same time predicts the probability of occurrence of risk events in combination with the exhibition hall distribution information and the display environment data in the museum monitoring data, and then generates a risk warning report; finally, the event warning agent simulates and upgrades the alarm level of the risk event according to the risk warning report, and generates corresponding security control information for the museum as the alarm level changes.

[0015] Preferably, the resource scheduling agent first classifies and counts the security resources to obtain a security resource list; then adaptively allocates various types of resources in the security resource list according to the security control information to obtain a proposed resource allocation table; then uses the expert prior model to modify the proposed resource allocation table according to the characteristics of each control node in the security control information to obtain a node resource allocation list; at the same time, uses the path planning algorithm to arrange and plan the resource allocation sequence of each control node according to the node resource allocation list to obtain a resource allocation path; finally, uses the redundant fusion algorithm to fuse and judge the node resource allocation list and the resource allocation path to generate a proposed resource allocation table.

[0016] Preferably, the emergency response intelligent agent includes a data extraction unit, an event simulation unit and a strategy handling unit; the data extraction unit extracts data from the museum monitoring data table according to the alarm level and event type by using an information extraction algorithm combined with a risk warning report to obtain key feature data of the event; the event simulation unit generates risk events to be processed with different alarm levels in a dynamic virtual museum according to the key feature data of the event by using a generative adversarial network model; the strategy handling unit uses an expert prior model combined with the handling methods and handling basis of historical risk events, and uses a game consensus algorithm to combine the risk events to be processed with the resource allocation table and the abnormal behavior information table to generate a corresponding event handling report.

[0017] Preferably, the policy handling unit first uses the expert prior model combined with the feature extraction layer to extract the core elements of the historical risk event data, and generates an event core list in combination with the event sequence code; the core elements include event type, time and place, target object, alarm level, event cause, scale assessment, handling measures and responsibility determination; then the expert prior model uses the context word vector function combined with the first learning and training branch to convert each core element in the event core list into a corresponding word vector, and at the same time uses the polymorphic fitting function to construct a number of functional utility functions and a number of event handling strategy functions according to the event type and the functional department; then the policy handling unit uses the game consensus algorithm combined with the second learning and training branch to determine the strategy plan of each functional department according to the resource allocation table and the abnormal behavior information table; then the update output layer is used to optimize the strategy plan of each functional department according to the processing time of various historical risk events, combined with the functional utility function and the event handling strategy function, to obtain the optimal strategy plan of each functional department; finally, the optimal strategy plan is converted into consensus according to the strategy consensus point to obtain the final strategy plan.

[0018] Preferably, the feature extraction layer includes 3 5X5 convolutional layers with a step size of 2, 2 3X3 convolutional layers with a step size of 1, and 2 batch normalization layers; the first learning and training branch includes 2 InceptionV3 blocks of different depths, 3 residual blocks, 2 inverted residual blocks, 3 batch normalization layers, and a MISH activation function; the second learning and training branch includes 2 CBR blocks, 2 residual blocks, 2 InceptionV4 blocks, 3 Transformer encoding blocks, 1 batch standard layer, and a Silu activation function; the CBR block includes 3 5X5 convolutional layers with a step size of 1, 4 batch standard layers, and a Relu activation function; the update output layer includes 3 fully connected layers, 2 random dropout layers, and a cross entropy loss function.

[0019] Preferably, the emergency response intelligent body also includes a plan generation unit and an emergency assistance unit; the plan generation unit uses a multimodal large model to convert the final strategy plan into a multimodal emergency plan; the multimodal emergency plan includes a text plan, an image plan and a video plan; the emergency assistance unit performs real-time correction and supervision of the emergency process of risk events based on the real-time situation of the risk event in combination with the multimodal emergency plan.

[0020] Preferably, the collaborative rehearsal agent includes a communication interaction unit and an information sharing unit; the communication interaction unit is responsible for communication operations between multiple agents using a communication protocol; the information sharing unit uses an information tracking algorithm to identify and record information between multiple agents, and share the information.

[0021] Preferably, the collaborative rehearsal agent also includes a collaborative rehearsal unit and an integrated management unit; the collaborative rehearsal unit uses a rehearsal decision algorithm to design and implement cooperation strategies between agents based on the multimodal emergency plan, and ensures smooth collaborative work between agents; the integrated management unit uses a state monitoring algorithm to manage the operating state and collaborative relationship of the agents, and ensures effective collaboration between the agents to generate event emergency rehearsal reports.

[0022] The present invention simplifies the cumbersome and complex museum risk event handling process through effective collaboration of multiple intelligent agents, thereby shortening the handling time of museum risk events and improving the handling efficiency of museum risk events. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is the flow chart of the museum incident handling platform.

[0024] Figure 2 Schematic diagram of the principle of emergency response intelligent agent. DETAILED DESCRIPTION

[0025] 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.

[0026] like Figure 1 to Figure 2 As shown, the museum event handling platform based on multiple agents described in the present invention includes an environment monitoring agent, an event warning agent, a resource scheduling agent, an emergency handling agent and a collaborative rehearsal agent; wherein, The environment monitoring agent is used to build a digital virtual museum based on the museum's architecture and exhibition information. On the other hand, it collects the museum's internal and surrounding comprehensive data in real time to obtain the museum's comprehensive monitoring data, and combines the preset abnormality judgment rules to obtain the abnormal data set. Then, a dynamic virtual museum is obtained based on the digital virtual museum and the abnormal data set. Among them, the internal comprehensive data includes display environment data and visitor quantity behavior data; display environment data includes temperature, humidity, air quality, light intensity, oxygen concentration and noise decibel value; visitor quantity behavior data includes crowd density and visitor behavior; surrounding comprehensive data includes weather data, public activity data and natural disaster data; The event warning agent is used to simulate the risk anomalies of the abnormal data set based on the museum monitoring data and the abnormal data set, and obtain risk warning reports and security control information; Resource scheduling agent, used to schedule the physical museum's security resources according to the risk warning report, and to allocate security resources according to the security control information, and obtain the resource allocation table; The emergency response agent is used to use the spatiotemporal data analysis algorithm or the game consensus algorithm to simulate and process risk events of the dynamic virtual museum based on the proposed resource allocation table and the abnormal data set to obtain a multimodal emergency plan; The collaborative rehearsal agent is used to coordinate the museum risk events through the above four agents according to the multimodal emergency plan and obtain the event emergency rehearsal report.

[0027] In this embodiment, the interior of the museum includes the main building of the museum and its ancillary facilities (such as underground warehouses, office areas, equipment rooms, etc.), as well as all indoor spaces such as exhibition halls, corridors, stairs, elevators, toilets, and rest areas; the periphery of the museum includes areas outside the main building of the museum, including surrounding green spaces, squares, parking lots, roads, etc.; it also includes other buildings adjacent to the museum (such as commercial areas, residential areas, schools) and public facilities (such as subway stations and bus stations); In this embodiment, the display environment data has an impact on the preservation of exhibits: Temperature and humidity are the most common environmental factors for exhibits. They have a significant impact on certain exhibits, such as cultural relics, paintings, paper, etc., and even display cabinets and showcases. Excessive temperature and humidity will lead to bacterial growth, decomposition and oxidation reactions, causing exhibits to rot, damage and deteriorate. Poor air quality will cause dust and dirt to adhere to the surface of exhibits, which will damage the appearance and quality of the exhibits and accelerate the aging and decay of the exhibits. At the same time, harmful gases in the air will also cause damage to the exhibits; Too much or too little light intensity will not only affect the appearance and quality of the exhibits, but may also cause the colors of the exhibits to fade and become damaged; Too much or too little oxygen concentration will affect the quality and appearance of the exhibits. In the display of certain cultural relics, paintings and other cultural and artistic works, there cannot be too much or too little oxygen, otherwise it will accelerate the aging and decay of the exhibits; Noise can directly generate mechanical vibrations and sound waves that can harm exhibits. Physical damage to some ceramics, glass, and paper products is related to noise, and angular fiber materials are also prone to breakage when stimulated; Visitor quantity behavior data can easily cause damage to exhibits or cause stampedes and congestion: If the crowd density is too high and visitors do not walk in the right way, it is easy to cause friction and collision between people and objects. Especially in the busier places of the exhibition area, such as entrances and exits, intersections, etc., special attention should be paid to the protection of exhibits; When there is too much traffic, carbon dioxide, ammonia, volatile organic compounds, etc. will be produced, which can easily reduce the air quality in the exhibition area. Exhibition air management is an important task, otherwise the exhibits may oxidize, mold, and discolor; When tourists hit some electromechanical exhibits in the museum hard due to extreme haste or crowds, it is easy to cause damage to the exhibits; Due to the dense crowds of tourists, unexpected changes may occur to the lighting time, light intensity, air conditioning positioning, and humidity stability of the exhibits while creating the atmosphere for the event. These changes may cause a certain degree of damage to the exhibits and need to be dealt with in a timely manner; Some visitors may touch or fiddle with the exhibits, which may cause minor damage to them.

[0028] Security resources include fire extinguishers, fire hydrants, smoke alarms, access control equipment, inspection equipment and explosion-proof equipment; In the present invention, the environment monitoring agent uses a three-dimensional modeling algorithm to construct a digital virtual museum based on the museum's architecture and display information; On the other hand, the environmental monitoring agent first uses wireless sensor networks, intelligent monitoring cameras, data analysis tools and remote sensing meteorological satellites to collect the museum's internal comprehensive data and surrounding comprehensive data, and records the data collection time; then the environmental monitoring agent uses the data segmentation algorithm to divide the internal comprehensive data and surrounding comprehensive data into several original data blocks according to the data collection time; the environmental monitoring agent then uses the data cleaning algorithm to perform data deduplication, data consistency verification and data standardization on the information data in each original data block to obtain several standard data blocks; then, the environmental monitoring agent uses the data classification algorithm to cluster the information data in each standard data block according to the data type to obtain several set data blocks; then, the environmental monitoring agent uses the data association algorithm to associate and normalize the set data blocks of the internal environment and the surrounding environment according to the data collection time to obtain the museum's comprehensive monitoring data; finally, combined with the preset anomaly judgment rules and using the data anomaly detection algorithm, the abnormal information data in the set data block is aggregated into an abnormal data set, that is, an abnormal data set is obtained; then, the environmental monitoring agent uses the data fusion algorithm to integrate the abnormal data set into the digital virtual museum to obtain a dynamic virtual museum; In this embodiment, the wireless sensor network includes a temperature sensor, a humidity sensor, a light sensor, a gas sensor, a noise sensor, an infrared pyroelectric sensor, a fiber grating sensor, a geomagnetic sensor and a tilt sensor; The temperature sensor, humidity sensor, light sensor, gas sensor and noise sensor collect temperature, humidity, air quality, light intensity, oxygen concentration and noise decibel value respectively; Infrared pyroelectric sensors sense the movement of dynamic heat sources by detecting changes in infrared radiation released by objects (human bodies, animals, etc.); fiber grating sensors are used to sense low-frequency vibrations caused by earthquakes or construction, triggering cultural relic reinforcement mechanisms; geomagnetic sensors are used to monitor the position and movement of metal cultural relics (bronze and iron objects) and trigger anti-theft alarms; tilt sensors are used to monitor geological activities; Weather is an important factor affecting public travel. Sunny weather usually increases tourists' willingness to travel, thereby increasing the number of visitors to museums, promoting cultural dissemination and economic benefits. Extreme weather (such as high temperatures, heavy rains, lightning, etc.) may cause damage to museum collections and buildings. For example, high temperatures may cause the aging of cultural relics materials, and heavy rains may cause leakage or flooding, posing a threat to building structures; By analyzing data on public activities (such as holiday schedules, school holidays, large-scale events, etc.), museums can predict peak periods of visiting and thus optimize resource allocation, such as adding tour guides and extending opening hours. By analyzing data on public activities (such as holiday schedules, school holidays, large-scale events, etc.), museums can predict peak periods of visiting and thus optimize resource allocation, such as adding tour guides and extending opening hours. High-frequency public activities may accelerate the aging or damage of cultural relics, especially in the absence of effective protection measures.

[0029] By analyzing natural disaster data (such as floods, earthquakes, mudslides, etc.), museums can formulate targeted emergency plans in advance to reduce disaster losses. For example, install flood control facilities and carry out earthquake reinforcement; Natural disasters are one of the biggest threats facing museums. For example, floods can destroy ancient buildings and submerge cultural relics; earthquakes can cause building collapse or damage cultural relics. Natural disasters can cause museums to close, affecting exhibitions and educational activities, while increasing the cost of restoration and reconstruction.

[0030] Spatiotemporal data analysis algorithms, data segmentation algorithms, data cleaning algorithms, data classification algorithms, data association algorithms, data fusion algorithms and three-dimensional modeling algorithms are all commonly used technical means by personnel in this field and will not be elaborated here.

[0031] In the present invention, the event warning agent first extracts the tourist quantity behavior data from the museum monitoring data, and uses the human body reconstruction algorithm in combination with the cultural relics display information to reshape all tourists within the range of X1 to X2 centimeters near each cultural relics exhibition stand according to the tourist behavior characteristics to generate virtual characters, and then the event warning agent uses the action redirection algorithm in combination with the tourist behavior to generate a set of tourist action vectors for the virtual visitors; then the event warning agent simulates various risk events of the digital virtual museum based on the virtual visitors and the tourist action vector set, and at the same time predicts the probability of occurrence of risk events in combination with the exhibition hall distribution information and the display environment data in the museum monitoring data, and then generates a risk warning report; finally, the event warning agent simulates and upgrades the alarm level of the risk event according to the risk warning report, and generates corresponding security deployment information for the museum as the alarm level changes.

[0032] In this embodiment, risk events include vandalism and graffiti, fire and explosion, entry of prohibited items into the museum, group trampling, natural disasters, and security failures.

[0033] Derivative simulation refers to the process of assuming the occurrence of a certain risk event and deducing its possible development process, impact range and final consequences during the risk assessment process. This method helps decision makers understand potential risks more comprehensively and formulate effective response measures. "Simulation upgrade" refers to the process of gradually enhancing or optimizing a system or process in a hypothetical or virtual scenario. In this process, the performance, function or capability of the system or process will be gradually improved as the simulated conditions change to evaluate its performance and response capabilities in different situations.

[0034] In the present invention, the resource scheduling intelligent body first classifies and counts the security resources to obtain a security resource list; then, according to the security control information, various types of resources in the security resource list are adaptively allocated to obtain a resource proposed allocation table; then, the expert prior model is used to modify the resource proposed allocation table according to the characteristics of each control node in the security control information to obtain a node resource allocation list; at the same time, a path planning algorithm is used to arrange and plan the resource allocation sequence of each control node according to the node resource allocation list to obtain a resource allocation path; finally, a redundant fusion algorithm is used to fuse and judge the node resource allocation list and the resource allocation path to generate a resource proposed allocation table.

[0035] In this embodiment, the expert prior model, the redundant fusion algorithm and the path planning algorithm are all commonly used technical means by those skilled in the art and will not be described in detail here.

[0036] In the present invention, the emergency response intelligent body includes a data extraction unit, an event simulation unit, a strategy handling unit, a plan generation unit and an emergency assistance unit; the data extraction unit uses an information extraction algorithm in combination with a risk warning report to extract data from the museum monitoring data according to the alarm level and event type, and obtains key feature data of the event; the event simulation unit uses a generative adversarial network model to generate risk events to be processed with different alarm levels in a dynamic virtual museum according to the key feature data of the event; the strategy handling unit uses an expert prior model in combination with the processing method and handling basis of historical risk events, and uses a game consensus algorithm to combine the risk events to be processed with the resource allocation table and the abnormal data set to generate a corresponding event processing report; the plan generation unit uses a multimodal large model to convert the final strategy plan into a multimodal emergency plan; the multimodal emergency plan includes a text plan, an image plan and a video plan; the emergency assistance unit performs real-time correction and supervision on the emergency process of the risk event in combination with the multimodal emergency plan according to the real-time status of the risk event; In this embodiment, the characteristics of the control nodes include the first-level risk area (core exhibition area), the second-level risk area (ordinary exhibition hall area) and the third-level risk area (auxiliary facilities area); the generative adversarial network model, the game consensus algorithm and the multimodal large model are all commonly used technical means by personnel in this field, and will not be described in detail here; A text plan is an emergency plan that is mainly expressed in text and is used to describe in detail the response measures, division of responsibilities, resource allocation and other key information when an emergency occurs; Graphic plans are emergency plans presented in the form of pictures, charts, etc., which convey information in a visual way, making it easy to understand and implement quickly; The video plan is an emergency plan in the form of dynamic video, which displays emergency procedures and measures through simulated scenarios and demonstration operations.

[0037] In the present invention, the policy handling unit first uses the expert prior model combined with the feature extraction layer to extract the core elements of the historical risk event data, and generates an event core list in combination with the event sequence code; the core elements include event type, time and place, target object, alarm level, event cause, scale assessment, handling measures and responsibility determination; then the expert prior model uses the context word vector function combined with the first learning and training branch to convert each core element in the event core list into a corresponding word vector, and at the same time uses the polymorphic fitting function to construct a number of functional utility functions and a number of event handling strategy functions according to the event type combined with the functional department; then the policy handling unit uses the game consensus algorithm combined with the second learning and training branch to determine the strategy plan of each functional department according to the resource allocation table and the abnormal data set; then the update output layer is used to optimize the strategy plan of each functional department according to the processing time of various historical risk events, combined with the functional utility function and the event handling strategy function, to obtain the optimal strategy plan of each functional department; finally, the optimal strategy plan is converted into a consensus according to the strategy consensus point to obtain the final strategy plan.

[0038] The feature extraction layer includes 3 5X5 convolutional layers with a step size of 2, 2 3X3 convolutional layers with a step size of 1, and 2 batch normalization layers; the first learning and training branch includes 2 InceptionV3 blocks of different depths, 3 residual blocks, 2 inverted residual blocks, 3 batch normalization layers, and MISH activation functions; the second learning and training branch includes 2 CBR blocks, 2 residual blocks, 2 InceptionV4 blocks, 3 Transformer encoding blocks, 1 batch standard layer, and Silu activation function; the CBR block includes 3 5X5 convolutional layers with a step size of 1, 4 batch standard layers, and Relu activation functions; the update output layer includes 3 fully connected layers, 2 random dropout layers, and a cross entropy loss function; In this embodiment, the working principle of the combination of the expert prior model and the feature extraction layer is: Preprocess the historical risk event data, such as cleaning data, removing noise and standardizing, to ensure data quality; use the feature extraction layer to process the historical risk event data; extract the feature vector that can represent the core elements of the event through the combination of convolution layer and batch normalization layer; combine the prior knowledge in the expert prior model with the feature vector extracted by the feature extraction layer: select the most representative features based on the prior knowledge; weight the different features in the feature vector according to the prior knowledge to highlight the important features and suppress the secondary features; input the feature vector output by the expert prior model and the feature extraction layer into a joint model to generate a core event list by comprehensively considering the prior knowledge and the extracted features; based on the fused feature vector and prior knowledge, generate a core event list containing event type, time and place, target object, alarm level, event cause, scale assessment, disposal measures and responsibility determination; deduplicate, sort and format the generated core event list to ensure the accuracy and readability of the core event list.

[0039] In this embodiment, the working principle of the expert prior model using the context word vector function combined with the first learning training branch is: Use the context word vector function to convert each core element in the event core list into a corresponding word vector. These word vectors will serve as the input of the first learning and training branch; the first learning and training branch receives the word vector as input, and performs feature extraction and fusion through network layers such as InceptionV3 blocks, residual blocks, and inverted residual blocks; these network layers can capture high-level features in word vectors and fuse them into more representative feature representations; using polymorphic fitting functions, according to the event type and functional departments, several functional utility functions and event handling strategy functions are constructed. These functions can perform intelligent analysis and decision-making on events based on the extracted and fused feature representations; based on the constructed functional utility functions and event handling strategy functions, intelligent analysis and decision-making on events are performed, and corresponding handling strategies or suggestions are output.

[0040] In this embodiment, the working principle of the game consensus algorithm combined with the second learning and training branch is: The historical data, current status and resource table to be deployed of each functional department are collected. After preprocessing, these data are used as the input of the second learning and training branch; the data are feature extracted and represented through CBR blocks, residual blocks, InceptionV4 blocks and Transformer encoding blocks; these model blocks can extract rich feature information from the data and convert it into a form suitable for subsequent processing; based on the extracted feature information, the game consensus algorithm uses a game theory model to generate preliminary strategy plans for each functional department; then, the strategy plan is optimized through optimization algorithms (such as gradient descent) to improve its performance and stability; a consensus algorithm is used to ensure that each functional department can reach a consensus on the final strategy plan.

[0041] In this embodiment, the working principle of updating the output layer is: The feature representation extracted from the second learning training branch is input to the first fully connected layer of the update output layer. The fully connected layer performs a linear transformation on the input features and introduces nonlinearity through activation functions (such as ReLU). Subsequent fully connected layers further transform the features to gradually approach the optimal strategy. Insert random dropout layers between fully connected layers to randomly discard the output of a portion of neurons; this helps prevent the model from overfitting the training data during training and improves the generalization ability of the model; the output of the last fully connected layer is used as the predicted strategy; the cross entropy loss function is used to calculate the difference between the predicted strategy and the actual optimal strategy, and the predicted strategy is optimized through back propagation to get closer to the actual optimal strategy.

[0042] In the present invention, the collaborative rehearsal agent includes a communication interaction unit, an information sharing unit, a cooperative rehearsal unit and a comprehensive management unit; the cooperative rehearsal unit uses a rehearsal decision algorithm to design and implement a cooperative strategy between agents for museum risk events according to a multimodal emergency plan, and ensures that the collaborative work between agents proceeds smoothly; the comprehensive management unit uses a state monitoring algorithm to manage the operating state and collaborative relationship of the agents, and ensures effective collaboration between the agents to generate an event emergency rehearsal report; the communication interaction unit uses a communication protocol to be responsible for the communication operation between multiple agents; the information sharing unit uses an information tracking algorithm to identify and record information between multiple agents, and shares the information; In this embodiment, the rehearsal decision algorithm, the state monitoring algorithm and the information tracking algorithm are all commonly used technical means by personnel in this field and will not be described in detail here.

[0043] Example: The environmental monitoring agent uses wireless sensor networks (temperature sensors, humidity sensors, gas sensors, noise sensors, infrared pyroelectric sensors, fiber grating sensors, geomagnetic sensors and tilt sensors) and intelligent surveillance cameras to collect comprehensive internal data of the museum (temperature, humidity, air quality, light intensity, noise decibel value, crowd density, visitor behavior and oxygen concentration), and uses data analysis tools and remote sensing meteorological satellites to collect comprehensive surrounding data (wind speed, rainfall, lightning warnings, public security incidents and geological activities), and records the data collection time; The environmental monitoring agent uses a data segmentation algorithm to divide the internal comprehensive data and the surrounding comprehensive data into several original data blocks according to the data collection time; the environmental monitoring agent uses a data cleaning algorithm to deduplicate the information data in each original data block, verify the data consistency and standardize the data, and obtain several standard data blocks; the environmental monitoring agent uses a data classification algorithm to cluster the information data in each standard data block according to the data type, and obtains several set data blocks; the environmental monitoring agent uses a data association algorithm to associate and normalize the set data blocks of the internal environment and the surrounding environment according to the data collection time, and obtains the museum monitoring data; at the same time, the data anomaly detection algorithm is used to aggregate the abnormal information data in the set data block into an abnormal data set; the environmental monitoring agent uses a three-dimensional modeling algorithm to build a digital virtual museum based on the museum building information and cultural relics display information, and combines the museum monitoring data; The event warning agent first extracts the tourist quantity behavior data from the museum monitoring data, and combines the cultural relics display information with the human body reconstruction algorithm to reshape all tourists within the range of X1 to X2 cm near each cultural relics exhibition stand according to the characteristics of tourist behavior, and generates virtual visitors; then the event warning agent uses the action redirection algorithm to combine the tourist behavior with the virtual visitor to generate a set of tourist action vectors; then the event warning agent simulates various risk events of the digital virtual museum based on the virtual visitors and the tourist action vector set, and combines the exhibition hall distribution information and the display environment data in the museum monitoring data to predict the probability of risk events (vandalism and graffiti, fire and explosion, contraband entry, natural disasters and security failures), and then generates a risk warning report; finally, the event warning agent simulates and improves the alarm level of the risk event according to the risk warning report, and generates corresponding security control information for the museum as the alarm level changes; The resource scheduling agent first classifies and counts the security resources (fire extinguishers, fire hydrants, smoke alarms, access control equipment, inspection equipment and explosion-proof equipment) to obtain a security resource list; then, it adaptively allocates various types of resources in the security resource list according to the security control information to obtain a proposed resource allocation table; then, it uses the expert prior model to modify the proposed resource allocation table according to the characteristics of each control node in the security control information to obtain a node resource allocation list; at the same time, it uses the path planning algorithm to arrange and plan the resource allocation sequence of each control node according to the node resource allocation list to obtain a resource allocation path; finally, it uses the redundant fusion algorithm to fuse and judge the node resource allocation list and the resource allocation path to generate a proposed resource allocation table; The data extraction unit of the emergency response agent extracts the museum monitoring data according to the alarm level and event type, using the information extraction algorithm combined with the risk warning report to obtain the key feature data of the event; the event simulation unit uses the generative adversarial network model to generate risk events with different alarm levels in the virtual museum according to the key feature data of the event; the strategy handling unit uses the expert prior model combined with the handling method and handling basis of historical risk events, and uses the game consensus algorithm to combine the risk events to be handled with the proposed resource allocation table and the abnormal data set to generate the corresponding event handling report; the plan generation unit uses the multimodal large model to convert the final strategy plan into a multimodal emergency plan; the multimodal emergency plan includes text plan, image plan and video plan; the emergency assistance unit performs real-time correction and supervision of the emergency process of risk events according to the real-time status of the risk event combined with the multimodal emergency plan; Among them, the strategy handling unit first uses the expert prior model combined with the feature extraction layer to extract the core elements of the historical risk event data, and generates an event core list in combination with the event sequence code; the core elements include event type, time and place, target object, alarm level, event cause, scale assessment, handling measures and responsibility determination; then the expert prior model uses the context word vector function combined with the first learning and training branch to convert each core element in the event core list into a corresponding word vector, and uses the polymorphic fitting function to construct several functional utility functions and several event handling strategy functions according to the event type and the functional department; then the strategy handling unit uses the game consensus algorithm combined with the second learning and training branch to determine the strategy plan of each functional department according to the resource allocation table and the abnormal data set; then the update output layer is used to optimize the strategy plan of each functional department according to the processing time of various historical risk events, combined with the functional utility function and the event handling strategy function, to obtain the optimal strategy plan of each functional department; finally, the optimal strategy plan is converted into consensus according to the strategy consensus point to obtain the final strategy plan; At the same time, the communication interaction unit of the collaborative rehearsal agent uses the communication protocol to be responsible for the communication operations between multiple agents; the information sharing unit uses the information tracking algorithm to identify and record the information between multiple agents, and share the information; the collaborative rehearsal unit uses the rehearsal decision algorithm to design and implement the cooperation strategy between agents for museum risk events based on the multimodal emergency plan, and ensures the smooth collaboration between agents; the comprehensive management unit uses the status monitoring algorithm to manage the operating status and collaborative relationship of the agents, and ensures effective collaboration between agents to generate event emergency rehearsal reports.

Claims

1. A museum event handling platform based on multi-agent, characterized by: It includes environmental monitoring agents, event warning agents, resource scheduling agents, emergency response agents and collaborative rehearsal agents; among them, The environment monitoring agent is used to build a digital virtual museum based on the museum's architecture and exhibition information. On the other hand, it collects the museum's internal and surrounding comprehensive data in real time to obtain the museum's comprehensive monitoring data, and combines the preset abnormality judgment rules to obtain the abnormal data set. Then, a dynamic virtual museum is obtained based on the digital virtual museum and the abnormal data set. Among them, the internal comprehensive data includes display environment data and visitor quantity behavior data; display environment data includes temperature, humidity, air quality, light intensity, oxygen concentration and noise decibel value; visitor quantity behavior data includes crowd density and visitor behavior; surrounding comprehensive data includes weather data, public activity data and natural disaster data; The event warning agent is used to simulate the risk anomalies of the abnormal data set based on the museum monitoring data and the abnormal data set, and obtain risk warning reports and security control information; Resource scheduling agent, used to schedule the physical museum's security resources according to the risk warning report, and to allocate security resources according to the security control information, and obtain the resource allocation table; The emergency response agent is used to use the spatiotemporal data analysis algorithm or the game consensus algorithm to simulate and process risk events of the dynamic virtual museum based on the proposed resource allocation table and the abnormal data set to obtain a multimodal emergency plan; The collaborative rehearsal agent is used to coordinate the museum risk events through the above four agents according to the multimodal emergency plan and obtain the event emergency rehearsal report.

2. The multi-agent based museum event handling platform according to claim 1, characterized in that: On the one hand, the environment monitoring agent constructs a digital virtual museum based on the museum's architecture and exhibition information; on the other hand, the environment monitoring agent first collects the museum's internal and surrounding comprehensive data and records the data collection time; Then, the environmental monitoring agent divides the internal comprehensive data and the surrounding comprehensive data into several original data blocks according to the data collection time; the environmental monitoring agent then performs data deduplication, data consistency verification and data standardization on the information data in each original data block to obtain several standard data blocks; Subsequently, the environmental monitoring agent clusters the information data in each standard data block according to the data type to obtain several aggregate data blocks; after that, the environmental monitoring agent associates and normalizes the aggregate data blocks of the internal environment and the surrounding environment according to the data collection time to obtain the comprehensive monitoring data of the museum; finally, the abnormal information data in the aggregate data block is aggregated into an abnormal data set, that is, the abnormal data set is obtained; at that time, the environmental monitoring agent integrates the abnormal data set into the digital virtual museum to obtain a dynamic virtual museum.

3. The multi-agent based museum event handling platform according to claim 1, characterized in that: The event warning agent first extracts the tourist quantity behavior data from the museum monitoring data, and uses the human body reconstruction algorithm in combination with the cultural relics display information to reshape all tourists within the range of X1 to X2 centimeters near each cultural relics exhibition stand according to the tourist behavior characteristics to generate virtual visitors; then the event warning agent uses the action redirection algorithm to combine the tourist behavior with the virtual visitors to generate a set of tourist action vectors; then the event warning agent performs derivative simulations on various risk events of the digital virtual museum based on the virtual visitors and the tourist action vector set, and at the same time combines the exhibition hall distribution information and the display environment data in the museum monitoring data to predict the probability of occurrence of risk events, and then generates a risk warning report; Finally, the event warning agent simulates and upgrades the alarm level of the risk event based on the risk warning report, and generates corresponding security control information for the museum as the alarm level changes.

4. The multi-agent based museum event handling platform according to claim 1, characterized in that: The resource scheduling agent first classifies and counts the security resources to obtain a security resource list; then adaptively allocates various types of resources in the security resource list according to the security control information to obtain a resource allocation table; Subsequently, the expert prior model is used to modify the proposed resource allocation table according to the characteristics of each control node in the security control information to obtain the node resource allocation list; at the same time, the path planning algorithm is used to arrange and plan the resource allocation order of each control node according to the node resource allocation list to obtain the resource allocation path; finally, the redundant fusion algorithm is used to fuse and judge the node resource allocation list and the resource allocation path to generate the proposed resource allocation table.

5. The multi-agent based museum event handling platform according to claim 1, characterized in that: The emergency response agent includes a data extraction unit, an event simulation unit and a strategy handling unit; the data extraction unit extracts data from the museum monitoring data table according to the alarm level and event type using an information extraction algorithm combined with a risk warning report to obtain key feature data of the event; the event simulation unit generates risk events to be processed with different alarm levels in a dynamic virtual museum according to the key feature data of the event using a generative adversarial network model; The strategy handling unit uses the expert prior model combined with the handling methods and handling basis of historical risk events, and uses the game consensus algorithm to combine the risk events to be processed with the resource allocation table and the abnormal behavior information table to generate the corresponding event handling report.

6. The multi-agent based museum event handling platform according to claim 5 is characterized by: The strategy handling unit first uses the expert prior model combined with the feature extraction layer to extract the core elements of the historical risk event data, and generates an event core list in combination with the event sequence code; Then, the expert prior model uses the context word vector function combined with the first learning and training branch to convert the core elements in the event core list into corresponding word vectors, and uses the polymorphic fitting function to combine the functional departments according to the event type to construct several functional utility functions and several event handling strategy functions; then the strategy handling unit uses the game consensus algorithm combined with the second learning and training branch to determine the strategy plans of each functional department according to the proposed resource allocation table and the abnormal behavior information table; then, the update output layer is used to optimize the strategy plans of each functional department according to the processing time of various historical risk events, combined with the functional utility function and the event handling strategy function, to obtain the optimal strategy plan of each functional department; finally, the optimal strategy plan is converted into consensus according to the strategy consensus point to obtain the final strategy plan.

7. The multi-agent based museum event handling platform according to claim 6 is characterized by: The feature extraction layer includes 3 5X5 convolutional layers with a step size of 2, 2 3X3 convolutional layers with a step size of 1, and 2 batch normalization layers; the first learning and training branch includes 2 InceptionV3 blocks of different depths, 3 residual blocks, 2 inverted residual blocks, 3 batch normalization layers, and a MISH activation function; the second learning and training branch includes 2 CBR blocks, 2 residual blocks, 2 InceptionV4 blocks, 3 Transformer encoding blocks, 1 batch standard layer, and a Silu activation function; the CBR block includes 3 5X5 convolutional layers with a step size of 1, 4 batch standard layers, and a Relu activation function; the update output layer includes 3 fully connected layers, 2 random dropout layers, and a cross entropy loss function.

8. The multi-agent based museum event handling platform according to claim 1, characterized in that: The emergency response agent also includes a plan generation unit and an emergency assistance unit; the plan generation unit uses a multimodal large model to convert the final strategy plan into a multimodal emergency plan; the multimodal emergency plan includes a text plan, an image plan and a video plan; The emergency assistance unit conducts real-time correction and supervision of the emergency process of risk events based on the real-time status of risk events and multimodal emergency plans.

9. The multi-agent based museum event handling platform according to claim 1, characterized in that: The collaborative rehearsal agent includes a communication interaction unit and an information sharing unit; the communication interaction unit uses a communication protocol to be responsible for communication operations between multiple agents; the information sharing unit uses an information tracking algorithm to identify and record information between multiple agents and share the information.

10. The multi-agent based museum event handling platform according to claim 1, characterized in that: The collaborative rehearsal intelligent agent also includes a collaborative rehearsal unit and an integrated management unit; the collaborative rehearsal unit uses a rehearsal decision algorithm to design and implement cooperation strategies between intelligent agents based on a multimodal emergency plan, and ensures smooth collaborative work between intelligent agents; the integrated management unit uses a state monitoring algorithm to manage the operating state and collaborative relationship of the intelligent agents, and ensures effective collaboration between intelligent agents to generate event emergency rehearsal reports.

Images