Intelligent control system and method for scenic spot equipment

Abstract

The invention discloses an intelligent control system and method for scenic spot equipment. The system comprises an AI agent, an operation control platform, an intelligent navigation platform and a safety monitoring platform. The AI intelligent agent can analyze in real time, automatically integrate and process various data, intelligently make decisions and give feedback information; the operation control platform can centrally control and adjust parameters of each operation related hardware device in a scenic spot, can receive data of various sensors in real time, and sends the data to the AI intelligent agent; the intelligent navigation platform can receive various kinds of demand information of tourists in real time through the navigation terminal and send the information to the AI intelligent agent; and the safety monitoring platform can record tourist information at each position in real time and send the tourist information to the AI intelligent agent. According to the platform and equipment integrated intelligent control system, intelligent management and control of a scenic spot can be realized, the operation efficiency is improved, the tourist experience is improved, and safety and resource saving are effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the field where AI technology, automation technology and sensor technology intersect, and in particular to an intelligent control system and method for scenic spot equipment. Background Art

[0002] With the development of the economy and the rise of the cultural and tourism industry, traditional scenic spots are seeking changes, and building intelligent scenic spots with cultural characteristics has become a consensus among various scenic spots.

[0003] At present, most traditional scenic spots adopt manual management, but the subjective factors of manual management have a greater impact and are prone to problems such as fatigue, low efficiency, low resource utilization, slow emergency response, and insufficient tourist experience.

[0004] Therefore, in response to the above problems, it is necessary to provide an intelligent control system and method for scenic spot equipment with high operating efficiency, high degree of automation, which can enhance the tourist experience and effectively ensure safety and resource conservation. Summary of the invention

[0005] In view of the existing deficiencies, the object of the present invention is to provide an intelligent control system and method for scenic spot equipment.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] An intelligent control system and method for scenic spot equipment. The system includes: an AI agent, an operation control platform, an intelligent tour guide platform, and a security monitoring platform. The AI ​​agent can analyze in real time, automatically integrate and process various types of data, make intelligent decisions, and give feedback information; the operation control platform can centrally control and adjust the parameters of various operation-related hardware equipment in the scenic spot, and can receive various sensor data in real time and send it to the AI ​​agent; the intelligent tour guide platform can receive various demand information of tourists in real time through the tour guide terminal and send it to the AI ​​agent; the security monitoring platform can record the information of tourists everywhere in real time and send it to the AI ​​agent.

[0008] As a further improvement of the present invention, the AI ​​agent is a computer system and program connected to the Internet with certain autonomous behavior capabilities. The computer system and program have data processing capabilities, advanced analysis capabilities, data integration management capabilities, intelligent decision-making capabilities, user experience optimization capabilities, learning and adaptive capabilities, and can perceive its environment, make decisions and take actions to achieve specific goals.

[0009] As a further improvement of the present invention, the data processing capability can process and analyze data in real time, providing immediate insight and decision support.

[0010] As a further improvement of the present invention, the advanced analysis capability can perform predictive analysis and abnormal warning.

[0011] As a further improvement of the present invention, the data integration management capability can automatically process large amounts of data, automatically clean, deduplicate and complete the data, and improve data quality.

[0012] As a further improvement of the present invention, the intelligent decision-making capability can provide optimization suggestions and evaluate the potential impact of different decision-making solutions.

[0013] As a further improvement of the present invention, the capability of optimizing user experience supports natural language query and interaction, can analyze user behavior and preferences, and provide personalized recommendations and services.

[0014] As a further improvement of the present invention, the learning and adaptive capabilities can continuously optimize models and algorithms, and adaptively adjust analysis strategies and model parameters.

[0015] The intelligent control method of scenic spot equipment according to the present invention comprises:

[0016] Step (1): The operation control platform collects sensor data arranged in various places in the scenic area, such as temperature T, humidity H, illuminance L, etc., in real time, and sends it as a sensor data packet to the AI ​​agent; the intelligent guide platform receives the demand information D sent by tourists through the guide terminal, packages it into a tourist demand data packet and sends it to the AI ​​agent; the security monitoring platform receives camera images, intelligent access control data, and garbage overflow data in real time, packages it into security monitoring data and sends it to the AI ​​agent.

[0017] Step (2): The AI ​​agent analyzes the received data in real time, identifies and extracts key data of the scenic spot, temperature T n 、Humidity n , illuminance L n 、Tourist demand m 、Number of people in scenic area P n The AI ​​agent compares the analyzed key data with the data received before and after and the historical normal data. If there is a data jump, it is judged as abnormal data, and the danger level is judged in combination with the monitoring screen, and the scenic area administrator is notified for warning; if there is no data jump, the AI ​​agent integrates multi-source data, obtains feedback data for the operating equipment through computer instruction algorithms, and sends the data back to the operation control platform; according to the needs of tourists, the location and environmental information of tourists are judged, the language keywords and actions of tourists are analyzed, and based on the language large model, the digital human tour guide image of the scenic area and the historical culture of the location are combined to give corresponding feedback data in the tone of the digital human tour guide and send it to the intelligent guide platform.

[0018] Step (3): The operation control platform adjusts the parameters of the scenic area operation hardware equipment according to the received feedback data, such as the brightness of various screens and lighting equipment, the switch of audio equipment, and the start and stop of irrigation equipment; the intelligent guide platform distributes the received feedback data to the guide terminal to achieve real-time interaction with tourists.

[0019] As a further improvement of the present invention, according to the instruction algorithm of claim 1, the operating equipment feedback data is calculated according to the following formula:

[0020] B=α(1-L / L max )+βP / P max +γf(T,H)

[0021] Where B is the adjustment parameter in the feedback data, α is the weight coefficient of illumination, β is the weight coefficient of the number of tourists, γ is the weight coefficient of temperature and humidity, and L max is the maximum value of the illuminance, P max is the maximum number of tourists, and f(T,H) is the adjustment function based on temperature and humidity.

[0022] As a further improvement of the present invention, the weight coefficients correspond to different weight coefficients for different operating hardware devices in the scenic area; the AI ​​agent can continuously optimize the weight coefficients by learning Internet data and historical data of the scenic area and relying on adaptive capabilities.

[0023] As a further improvement of the present invention, the operation control platform is an Internet of Things platform that collects various types of Internet of Things sensor data in real time; it is also a centralized control platform for the AI ​​agent to communicate with the operation hardware equipment.

[0024] As a further improvement of the present invention, the various types of Internet of Things sensors include temperature and humidity sensors, light sensors, and air quality sensors; the operating hardware equipment includes scenic area outdoor screen equipment, audio equipment, lighting equipment, and irrigation equipment.

[0025] As a further improvement of the present invention, the various types of IoT sensor data are divided into n areas according to the actual area size of the scenic area, and each area is equipped with a set of IoT sensors. The operation control platform is packaged into n sensor data packets A according to the area. n , A n Including temperature T n 、Humidity n , illuminance L n 、Air Quality Q n .

[0026] As a further improvement of the present invention, the intelligent tour guide platform manages the communication of each tour guide terminal and serves as a transfer platform for the AI ​​agent to transmit information to tourists. The tour guide terminal includes tour guide equipment, tourist service equipment, digital human tour guides and intelligent portable explanation equipment distributed in various areas of the scenic area.

[0027] As a further improvement of the present invention, the demand information sent by the guide terminal includes the gesture and language information of the tourist, which is distinguished by the guide terminal identification number m and packaged into a tourist demand data packet D m , the tourist feedback data contains the identification number m.

[0028] As a further improvement of the present invention, the security monitoring data is packaged into security monitoring data C according to the scenic area n where the camera, smart access control, and garbage overflow detection device are located and the device hardware number i. ni , the number of people in the scenic area P n By C ni Analyzed.

[0029] The beneficial effects of the present invention are:

[0030] The intelligent control system and method designed based on AI intelligent agent can integrate multi-source data of various types of information, conduct real-time analysis, make intelligent decisions, improve the operational efficiency of scenic spots, reduce dependence on manual labor, and reduce labor costs.

[0031] Based on AI intelligent body, environmental sensor data is collected through the operation control platform to control various operation hardware equipment such as screens, lights, and audio, improve the tourist experience, realize intelligent management of scenic spot equipment, and effectively save resources for the scenic spot.

[0032] Based on AI intelligent body, it can communicate and interact with tourists one-on-one through the intelligent guide platform, provide personalized services based on the different needs of tourists and combine the history and culture of the scenic spot to enhance the tourist experience.

[0033] Based on AI agents, the safety monitoring platform can realize all-round monitoring of scenic spots, detect problems in time and respond quickly. Combined with machine learning models, it can warn of dangers and effectively ensure the safety of scenic spots and tourists. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention, 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 be obtained based on these drawings without paying creative work.

[0035] Figure 1A block diagram of an intelligent control system for scenic spot equipment provided by an embodiment of the present invention;

[0036] Figure 2 A flowchart of the operation control platform provided by an embodiment of the present invention;

[0037] Figure 3 A flowchart of the intelligent navigation platform provided by an embodiment of the present invention;

[0038] Figure 4 A workflow diagram of a security monitoring platform provided by an embodiment of the present invention;

[0039] Figure 5 A working block diagram of an AI agent provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0041] like Figure 1 As shown, the embodiment of the present application provides an intelligent control system for scenic spot equipment. The system includes: an AI agent, an operation control platform, an intelligent guide platform, and a security monitoring platform.

[0042] like Figure 5 As shown in Figure 1, AI agents are computer systems and programs with certain autonomous behavior capabilities. Computer systems and programs have data processing capabilities, advanced analysis capabilities, data integration and management capabilities, intelligent decision-making capabilities, user experience optimization capabilities, learning and adaptive capabilities, and can perceive their environment, make decisions, and take actions to achieve specific goals.

[0043] Preferably, data processing capabilities can process and analyze data in real time, providing timely insights and decision-making support; data integration management capabilities can automatically process large amounts of data of different types, automatically clean, deduplicate and complete data, and improve data quality; advanced analysis capabilities rely on historical data and Internet data to perform predictive analysis and abnormal warnings; intelligent decision-making capabilities can optimize suggestions and evaluate the potential impact of different decision-making plans based on historical decisions and satisfaction feedback; the ability to optimize user experience refers to supporting AI agents to interact with tourists in natural language, analyze semantics and user behavior preferences, and provide personalized recommendations and services; learning and adaptive capabilities can enable AI agents to continuously optimize models and algorithms, and adaptively adjust analysis strategies and model parameter weights.

[0044] In this embodiment, the AI ​​agent can analyze and automatically integrate various data such as sensors, tourist needs, security monitoring, etc. in real time, combine Internet big data with historical data of the scenic spot, make intelligent decisions, and package the feedback data and send it back.

[0045] like Figure 1 As shown in the figure, the operation control platform is equipped with a processor, memory and network transceiver in hardware, and transmits relevant data with the AI ​​agent through its own protocol. The operation control platform can receive various sensor data with IoT functions in real time through the network, and can also centrally control and adjust the parameters of various operation-related hardware equipment in the scenic area.

[0046] The intelligent tour guide platform is equipped with a processor, memory and network transceiver, and transmits relevant data with the AI ​​agent through its own protocol. The intelligent tour guide platform can receive various demand information from tourists using the tour guide terminal in real time through the network, and send it to the AI ​​agent according to the protocol. It can also receive feedback data sent back by the AI ​​agent and distribute it to the corresponding tour guide equipment.

[0047] The security monitoring platform is equipped with a processor, memory and network transceiver, and transmits relevant data with the AI ​​agent through its own protocol. The security monitoring platform can be connected to various access control systems, security systems, and monitoring systems. It manages various system data in a unified manner and sends various data to the AI ​​agent in real time.

[0048] like Figure 2 As shown, the operation control platform workflow diagram provided by the embodiment of the present application. The operation control platform collects various sensor data in real time and serves as a centralized control platform for AI agents to communicate with various operation hardware devices.

[0049] Preferably, the sensors include temperature and humidity sensors, light sensors, and air quality sensors; the operating hardware equipment includes outdoor screen equipment, audio equipment, lighting equipment, and irrigation equipment.

[0050] According to the actual area of ​​the scenic spot, the scenic spot is divided into n areas, and a set of IoT sensors is installed in each area. The execution subject of the embodiment of the present application is the operation control platform, which is described in detail as follows:

[0051] Step S1: Various IoT sensors deployed in various places in the scenic area send the collected data such as temperature T, humidity H, illuminance L, air quality Q, etc. to the operation control platform through the network based on the real-time network communication module.

[0052] Each type of sensor data carries an identification number to distinguish the area where the sensor is located.

[0053] Step S2: After receiving the data, the operation control platform identifies the data number, classifies it by region, integrates the data of various sensors, and sorts the regional temperature T n 、Humidity n , illuminance L n 、Air Quality Q n , according to the communication protocol between the intelligent agent AI, packaged into regional environment parameters A n Send to the AI ​​agent.

[0054] Step S3: The AI ​​agent analyzes the received environmental parameters A in real time n , combined with the number of tourists in each region P n Through multi-source data integration and analysis, decision-making is optimized and the calculated feedback parameters are sent to the operation control platform.

[0055] Preferably, the number of tourists P n By C ni The analysis shows that C ni It is the security monitoring data recorded by the monitoring device with hardware number i in the scenic area n. The AI ​​agent uses the pre-trained object detection model to detect tourists in each frame in the real-time video stream, and recognizes and counts the human objects in the image through the convolutional neural network and deduplication algorithm. In this step, the object detection model, convolutional neural network, deduplication algorithm, etc. used can all be implemented using the existing known technologies in the field.

[0056] Preferably, multi-source data integration, analysis, and decision optimization refer to comparing the analyzed key data with the data received before and after and the historical normal data.

[0057] If there is no data jump, AI intelligently combines the collected data A n , for the operating equipment, the feedback data Z is obtained through the following computer instruction algorithm n :

[0058] B=α(1-L / L max )+βP / Pmax +γf(T,H)

[0059] Where B is the adjustment parameter in the feedback data, α is the weight coefficient of illumination, β is the weight coefficient of the number of tourists, γ is the weight coefficient of temperature and humidity, and L max is the maximum value of the illuminance, P max is the maximum number of tourists, and f(T,H) is an adjustment function based on temperature and humidity. The values ​​of various weight coefficients in the algorithm are determined by historical feedback data O n And tourist satisfaction data S n The result is obtained through combined analysis and adjustment.

[0060] Preferably, in order to determine the optimal values ​​of these weights, a machine learning method can be used to find the best matching relationship between them from historical data through data analysis, so that the system can always maintain the best performance under different environmental conditions. The specific process of determining the weight coefficients α, β and γ in this embodiment is as follows:

[0061] 1. Collect historical feedback data over a period of time n And the tourist satisfaction data S of the corresponding time period n .

[0062] 2. Clean the data to remove outliers and noise while ensuring the time synchronization of the data. Normalize each variable (such as light intensity, number of tourists, temperature, humidity) to facilitate comparison and calculation.

[0063] 3. Analyze the relationship between each variable and satisfaction through visualization methods such as scatter plots and heat maps. Use correlation analysis to evaluate the linear relationship between each variable (illuminance, number of tourists, temperature and humidity) and satisfaction.

[0064] 4. Build a model using a linear regression model, S n =αX1+βX2+γX3+∈, where X1, X2, X3 represent the values ​​of illumination adjustment, number of tourists adjustment and temperature and humidity function, and ∈ is the error term. Train the model and use historical data to fit the best α, β and γ.

[0065] 5. Use cross-validation to evaluate the performance of the model to ensure the stability and generalization ability of the model, and adjust the weight coefficient according to the model performance until the satisfaction prediction effect is optimized.

[0066] 6. Apply the obtained optimal weight coefficient to the actual system for real-time parameter adjustment, monitor the feedback during the actual operation of the system, and continue to accumulate data for further adjustment and optimization of the weight.

[0067] 7. Continuously update the data set and optimize the model on a quarterly basis to adapt to the dynamic changes in the environment and tourist behavior.

[0068] If there is a data jump, it will be judged as abnormal data, and the danger level will be determined in combination with the monitoring screen, and the scenic area administrator will be notified for warning.

[0069] Preferably, the AI ​​agent relies on the deployed edge computing devices to perform real-time video analysis and uses computer vision technology to detect abnormal activities or situations in the monitoring screen. In this embodiment, object detection and motion detection technology are applied to identify crowding, abnormal crowd behavior, fire smoke, etc. In this step, the computer vision technology, object detection, motion detection technology, etc. used can be implemented using existing known technologies in the field.

[0070] Preferably, the AI ​​agent combines sensor data with video surveillance data, and uses multimodal data fusion technology to comprehensively analyze multi-source data through time, space, and event consistency. Based on the fused data, the AI ​​agent simultaneously uses the rule engine and machine learning model to comprehensively evaluate different risk factors, compares the evaluation results with the system's preset danger level, and makes corresponding response measures. In this step, the multimodal data fusion technology, rule engine, machine learning model, etc. used can all be implemented using existing publicly known technologies in the field.

[0071] Step S4: The operation control platform receives feedback data Z from each region. n The device number and adjustment parameters in the system are used to rewrite the parameters of the operating hardware equipment corresponding to each area, so as to automatically adjust the brightness of the screens in each area of ​​the scenic area, the brightness of the lighting equipment, the volume of the audio equipment, and the start and stop of the irrigation equipment.

[0072] Preferably, in one of the cases of this embodiment, when there are many people in the area during the day in winter, the screen brightness is increased in the area, the lighting equipment brightness is reduced, the sound equipment volume is increased, and the irrigation equipment is turned off; in one of the cases of this embodiment, when there are no people in the area at night in summer, the screen brightness is reduced, the lighting equipment brightness is reduced, the sound equipment volume is reduced, and the irrigation equipment is turned on; in one of the cases of this embodiment, when there are many people in the area at night in summer, the screen brightness is reduced, the lighting equipment brightness is increased, the sound equipment volume is appropriately reduced, and the irrigation equipment is turned off. According to different environmental data and the number of tourists, the AI ​​agent can realize automatic adjustment of various operating hardware equipment parameters.

[0073] like Figure 3 As shown, another embodiment of the present application provides a workflow diagram of an intelligent tour guide platform. The intelligent tour guide platform manages the communication of each tour guide terminal and serves as a transfer platform for the AI ​​agent to transmit information to tourists.

[0074] Preferably, the tour guide terminal includes tour guidance equipment, tourist service equipment, digital humans and intelligent portable explanation equipment distributed in various areas of the scenic area.

[0075] Step S11: Tourists use the tour guide terminal to send their personal needs to the intelligent tour guide platform through voice, text, etc.

[0076] The tourist demand data sent by the tour guide device carries the tour guide device identification number m and location information.

[0077] Step S12: The intelligent tour guide platform packages the demand data of each tourist, the location data of the tourist and the tour guide terminal number into tourist tour data D m , and send the sorted data to the AI ​​agent.

[0078] Step S13: The AI ​​agent parses the received guide data, determines the location of the tourists, analyzes the tourists' language keywords, semantics, and actions, and combines historical data of similar needs. n The surrounding environment data of the tourist location A n 、Number of surrounding tourists P n ,Based on the decision analysis of the language large model, feedback data is given and sent to the intelligent navigation platform.

[0079] Preferably, the smart tour guide platform uses speech recognition technology to convert tourists' voices into text. The AI ​​agent can extract keywords from the text and use natural language processing technology to analyze the text semantics, understand tourists' intentions and emotions, detect tourists' movements and behaviors through video analysis technology, and identify movements such as pointing and waving to supplement language analysis. n Learning, establishing a mapping relationship between demand data and feedback data. When the scenic spot is operating, the AI ​​agent uses a multi-factor decision-making model, combines tourists' current language intentions, historical demand records, environment and traffic data, conducts decision analysis through a large language model, and generates feedback. In this step, the speech recognition technology, natural language processing technology, video analysis technology, machine learning algorithm, etc. used can all be implemented using existing publicly known technologies in the field.

[0080] Preferably, the feedback data can be given in the tone of the digital human tour guide, combining the image of the scenic spot digital human tour guide with the history and culture of the location. The AI ​​agent can collect historical and cultural information of the scenic spot location, establish a text library containing these cultural contents, provide materials for natural language generation, and use the NLG (natural language generation) algorithm to generate dynamic text, integrating tourists' immediate demand data and cultural background. Corresponding to the image of the scenic spot digital human tour guide, the AI ​​agent can use TTS (speech synthesis) technology, combined with specific intonation and pronunciation, to create a natural and fluent digital human voice. In this step, the NLG (natural language generation) algorithm, TTS technology, etc. used can all be implemented using existing known technologies in the field.

[0081] Step S14: After receiving the feedback data, the intelligent tour guide platform distributes each feedback data to the corresponding tour guide terminal according to the tour guide terminal identification number m contained in the feedback data, so as to realize real-time interaction with tourists and meet the needs of tourists.

[0082] Preferably, one of the scenarios of this embodiment is that tourists use the tour guide terminal to propose the need to plan a personal tour route. After the intelligent tour guide platform collects the tourist demand data, it packages the corresponding tour guide device identification code m and the tourist location information into the tourist demand data D m The AI ​​agent performs semantic analysis based on the language model, confirms the location of tourists and the real-time flow of people in various places in the scenic area, and infers the best tour route based on the changes in the historical tourist tour data during this period. The best tour route is packaged as feedback data based on the language model and sent to the intelligent tour guide platform. The intelligent tour guide platform sends the feedback data to the corresponding tour guide device based on the tour terminal identification number m in the feedback data to meet the personalized needs of tourists.

[0083] like Figure 4 As shown, another embodiment of the present application provides a workflow diagram of a security monitoring platform. The security monitoring platform serves as a communication platform between hardware devices and AI agents.

[0084] Preferably, the hardware devices controlled by the security monitoring platform include smart access control, garbage overflow detection equipment, and various cameras.

[0085] Step 21: The smart access control systems and various cameras deployed in various locations in the scenic area send the monitored images and other data to the security monitoring platform in real time.

[0086] Preferably, the security monitoring platform can be connected to the original scenic area monitoring system through an interface, including but not limited to an RJ45 network interface. The security monitoring platform can receive real-time images obtained by the original monitoring system.

[0087] Step 22: The security monitoring platform classifies the areas and sends security monitoring data such as video images to the AI ​​agent.

[0088] Step 23: The AI ​​agent analyzes the received security monitoring data and compares the key frame of the image with the data images received before and after. If there is no abnormal jump in the key frame, no data will be fed back; if there is an abnormal jump in the key frame, it will be judged as abnormal data, combined with the real-time sensor parameters A in the area n The system uses the previous and subsequent jumps and various image database data that have undergone deep machine learning to determine the status of the scenic area and notify the scenic area administrator of an early warning.

[0089] Preferably, the AI ​​agent uses a trained convolutional neural network model to classify and detect images, such as identifying common risks in scenic spots: crowding, fire sources, and water accumulation, and continuously optimizes and improves the generalization ability of the model. The AI ​​agent integrates the sensor data with the image analysis results, uses an association algorithm based on spatiotemporal features to analyze the relationship between the data, and evaluates the regional conditions through a multimodal learning method. The use of an association algorithm based on spatiotemporal features ensures that the data collected by various sensors and monitoring are from the same area at the same time. In this step, the association algorithm based on spatiotemporal features, the multimodal learning method, etc., can all be implemented using existing known technologies in the field.

[0090] Preferably, the sensor parameter A n Contains the area temperature T after sorting n 、Humidity n , illuminance L n 、Air Quality Q n .

[0091] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0092] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An intelligent control system for scenic spot equipment, characterized in that: The system comprises: AI intelligent body, operation control platform, intelligent navigation platform, security monitoring platform; The AI ​​agent is used for real-time analysis, automatic integration and processing of various data, intelligent decision-making, and providing feedback information; The operation control platform is used to centrally control and adjust the parameters of various operation-related hardware equipment in the scenic area, receive various sensor data in real time, and send them to the AI ​​agent; The intelligent tour guide platform is used to receive various demand information of tourists in real time through the tour guide terminal and send it to the AI ​​agent; The security monitoring platform is used to record the information of tourists in various places in real time and send it to the AI ​​agent.

2. An intelligent control method for scenic spot equipment according to the system of claim 1, characterized in that: include: Step (1): The operation control platform collects sensor data arranged in various places in the scenic area in real time, including temperature T, humidity H, and illuminance L, and sends it to the AI ​​agent as a sensor data packet; the intelligent tour guide platform receives the demand information D sent by tourists through the tour guide terminal, packages it into a tourist demand data packet and sends it to the AI ​​agent; the security monitoring platform receives camera images, intelligent access control data, and garbage overflow data in real time, packages it into security monitoring data and sends it to the AI ​​agent; Step (2): The AI ​​agent analyzes the received data in real time and identifies and extracts key data of the scenic spot, including temperature T n 、Humidity n , illuminance L n 、Tourist demand m 、Number of people in scenic area P n The AI ​​agent compares the parsed key data with the received data and historical normal data. If there is a data jump, it is judged as abnormal data, and the danger level is determined in combination with the monitoring screen, and the scenic area administrator is notified for warning; If there is no data jump, the AI ​​agent integrates multi-source data, obtains feedback data for the operating equipment through computer instruction algorithms, and sends the feedback data back to the operation control platform; according to the needs of tourists, the location and environmental information of tourists are judged, and the language keywords, semantics, and actions of tourists are analyzed. Based on the language model, combined with the image of the digital human tour guide in the scenic area and the history and culture of the location, the corresponding feedback data is given in the tone of the digital human tour guide and sent to the intelligent guide platform; Step (3): the operation control platform adjusts the scenic spot operation hardware equipment parameters according to the received feedback data; The intelligent tour guide platform distributes the received feedback data to the tour guide terminals to achieve real-time interaction with tourists.

3. The method according to claim 2, characterized in that In the feedback data obtained by the computer instruction algorithm for the operating equipment, the feedback data of the operating equipment is calculated according to the following formula: B=α(1-L / L max )+βP / P max +γf(T,H) Where B is the adjustment parameter in the feedback data, α is the weight coefficient of illumination, β is the weight coefficient of the number of tourists, γ is the weight coefficient of temperature and humidity, and L max is the maximum value of the illuminance, P max is the maximum number of tourists, P is the number of tourists, and f(T,H) is the adjustment function based on temperature and humidity.

4. The method according to claim 3, characterized in that Different operating hardware devices correspond to different weight coefficients; the AI ​​agent continuously optimizes the weight coefficients by relying on its adaptive ability through deep learning of historical feedback data of scenic spots and tourist satisfaction data.

5. The method according to claim 4, characterized in that The specific process of optimizing weight coefficients α, β and γ is as follows: Collect historical feedback data over a period of time n And the tourist satisfaction data S of the corresponding time period n ; Under the premise of ensuring the time synchronization of data, clean the data, remove outliers and noise, and normalize each variable; Analyze the relationship between each variable and satisfaction through visualization, and evaluate the linear relationship between each variable and satisfaction; Build a model using linear regression model S n =αX1+βX2+γX3+∈, where X1, X2, X3 represent the values ​​of illumination adjustment, number of tourists adjustment and temperature and humidity function respectively, and ∈ is the error term; train the linear regression model and use historical data to fit the best α, β and γ; Use cross-validation to evaluate the performance of the model and adjust the weight coefficient according to the model performance until the satisfaction prediction effect is optimized; Apply the obtained optimal weight coefficients to the actual system for real-time parameter adjustment, monitor the feedback during the actual operation of the system, and continue to accumulate data for further adjustment and optimization of the weights; The dataset is continuously updated and the model is optimized on a quarterly basis to adapt to the dynamic changes in the environment and tourist behavior.

6. The method according to claim 2, characterized in that The step of judging the danger level in combination with the monitoring screen includes: The AI ​​agent combines sensor data with video surveillance data, and uses multimodal data fusion technology to comprehensively analyze multi-source data through time, space, and event consistency. Based on the fused data, the AI ​​agent simultaneously uses rule engines and machine learning models to comprehensively evaluate different risk factors, compares the evaluation results with the system's preset danger levels, and makes corresponding response measures.

7. The method according to claim 2, characterized in that The security monitoring data is packaged into security monitoring data C according to the scenic area n where the camera, smart access control, and garbage overflow detection equipment are located and the equipment hardware number i. ni , the number of people in the scenic area P n By C ni The analysis shows that the analysis process is as follows: The AI ​​agent uses a pre-trained object detection model to detect tourists in each frame in the real-time video stream, and uses a convolutional neural network and a deduplication algorithm to identify and count human objects in the image.

8. The method according to claim 2, characterized in that: The above-mentioned judgment of the location and environmental information of tourists, analysis of the tourists' language keywords, semantics, and actions, based on the language big model, combined with the image of the digital human tour guide in the scenic area and the historical culture of the location, gives corresponding feedback data in the tone of the digital human tour guide, including: The smart tour guide platform uses speech recognition technology to convert tourists' voices into text. The AI ​​agent extracts keywords from the text and uses natural language processing technology to analyze the text semantics, understand tourists' intentions and emotions, and detects tourists' movements and behaviors through video analysis technology, identifying movements to supplement language analysis. The AI ​​agent uses machine learning algorithms to analyze historical feedback data in advance. n Learning, establishing a mapping relationship between demand data and feedback data; when operating in the scenic area, the AI ​​agent uses a multi-factor decision-making model, combines tourists' current language intentions, historical demand records, environment and crowd flow data, conducts decision analysis through a large language model, and generates feedback data.

9. The method according to claim 8, characterized in that Further including: The AI ​​agent collects historical and cultural data of the scenic spot, establishes a text library containing the content of the historical and cultural data, provides materials for natural language generation, and uses the natural language generation algorithm to generate dynamic text, integrating tourists' real-time demand data and cultural background; Corresponding to the image of the digital human tour guide in the scenic area, the AI ​​agent uses speech synthesis technology, combined with preset intonation and pronunciation, to create the digital human voice.

10. The method according to claim 2, characterized in that The AI ​​agent compares the parsed key data with the received data and historical normal data. If there is a data jump, it is determined to be abnormal data, including: The AI ​​agent uses a trained convolutional neural network model to classify and detect images. The AI ​​agent integrates sensor data with image analysis results, uses a correlation algorithm based on spatiotemporal features to analyze the relationship between data, and evaluates regional conditions through multimodal learning methods.

Images