Intelligent piano room platform design and management system based on Internet of Things

Abstract

The invention relates to the technical field of intelligent guitar rooms, provides an intelligent guitar room platform design and management system based on the Internet of Things, and aims to solve the problems of low resource utilization efficiency, insufficient environment regulation and control and inaccurate data analysis in traditional guitar room management. A data statistics module of the system is based on an improved ARIMA model, stability verification is optimized by introducing an exogenous variable and a dynamic error term, the accuracy and practicability of room utilization rate prediction are improved, and a visual report is generated to assist an administrator in decision making; an environment monitoring module of the system adopts a particle swarm optimization gravity center method to enhance a fuzzy control algorithm, the temperature, humidity and air quality in the piano room are regulated in real time, the user experience is improved, and the service life of equipment is prolonged; the guitar room management efficiency and the environment regulation and control level are improved, and efficient, accurate and intelligent service support is provided for users and managers.

Description

Technical Field

[0001] The present invention relates to the technical field of smart piano rooms, and specifically to a smart piano room platform design and management system based on the Internet of Things. Background Art

[0002] With the advancement of science and technology and the rapid development of Internet of Things technology, the design and management system of smart piano room platform based on Internet of Things, as a system of integrated management and intelligent services, has gradually been applied in music education and entertainment industries; the system uses Internet of Things technology to provide users with efficient and convenient piano room use, reservation and management; however, the traditional piano room management system lacks sufficient sensitivity and accuracy in environmental quality monitoring, and the real-time feedback and automatic adjustment functions of the piano room environment are relatively weak, resulting in the failure to adjust environmental parameters in time, thus affecting the user's experience and equipment performance; for example: temperature, humidity and air quality environmental factors are not effectively monitored and adjusted in real time, resulting in users' discomfort in the piano room, and even affecting the use of musical instruments; In addition, the traditional system has not been able to effectively combine data statistics and predictive analysis methods, and the decision-making support in terms of piano room utilization, user behavior and equipment maintenance is relatively weak, making it difficult to provide administrators with scientific and accurate optimization plans. Summary of the invention

[0003] The present invention provides a smart piano room platform design and management system based on the Internet of Things. The system can realize piano room reservation, equipment monitoring, environmental adjustment and data statistics functions, and significantly improve the use efficiency and user experience of the piano room. First, the present invention improves the means of ARIMA stationarity verification by introducing exogenous variables and dynamic error terms, and optimizes the prediction effect of the piano room utilization rate; enhances the adaptability of the system to environmental changes. Through this optimization, the system can provide administrators with more forward-looking data support to help them optimize the reservation and use strategies of the piano room, thereby avoiding resource waste or uneven distribution; secondly, in terms of environmental adjustment, the present invention improves the defuzzification process of the piano room management system by introducing the centroid method in particle swarm optimization fuzzy control. The method can automatically adjust the temperature, humidity and air quality parameters in the piano room, especially in the face of complex or sudden environmental changes. The system can respond quickly and make corresponding equipment adjustments to ensure the stability and comfort of the piano room environment; through the above optimization, the present invention has higher accuracy, performance and intelligent characteristics, and effectively solves the shortcomings of the existing system in resource management, environmental adjustment and data analysis.

[0004] The present invention provides a smart piano room platform design and management system based on the Internet of Things, the system comprising: an access control management module, a small program module, a data transmission module and a database, the access control management module transmits two-dimensional code data and face image data to the database through the data transmission module, and receives instructions from the database to automatically control the opening of the access control, the small program module is connected to the database through the data transmission module, the data transmission module connects the access control management module, the small program module and the database to realize data interaction, the database connects the access control management module and the small program module, and performs data storage and sharing; The mini-program module includes a piano room reservation module, a piano room return module, a data statistics module, an environment monitoring module and an equipment management module. The piano room reservation module, the piano room return module, the environment monitoring module and the equipment management module transmit data to a database through a data transmission module. The data statistics module extracts the stored data of the piano room reservation module, the piano room return module, the environment monitoring module and the equipment management module in the database through the data transmission module to perform data statistics. The environment monitoring module is electrically connected to the equipment management module and transmits the environment monitoring data to the equipment management module for equipment management and adjustment. The user uses the piano room reservation module to select the piano room number, date and time period, query the piano room status information in the database, filter out the idle piano room data, prioritize the idle piano room data according to the frequency of use, obtain the prioritized piano room data, confirm the reservation request according to the prioritized piano room data and store it in the database; The user uses the piano room return module to scan the QR code to query the reservation record and verify whether the return time exceeds the reservation period. If it exceeds the reservation period, the overtime length is recorded and the user's credit score is dynamically adjusted. At the same time, the actual usage time is recorded and stored in the database; The data statistics module optimizes the stationarity verification based on the ARIMA model, constructs an improved ARIMA model, extracts piano room usage data from the database, uses the improved ARIMA model to predict the piano room usage rate, and generates a visualization report; the visualization report includes a usage rate curve chart, a daily peak time distribution chart, and an idle rate analysis chart; The environmental monitoring module enhances the defuzzification effect through the centroid method in the particle swarm optimization fuzzy control algorithm, constructs an enhanced fuzzy control algorithm, monitors the environmental data of the piano room in real time, judges the environmental status in combination with the enhanced fuzzy control algorithm, and automatically adjusts the piano room equipment.

[0005] Furthermore, the data statistics module uses the improved ARIMA model to predict the piano room usage rate in the next week and generates a visual report, which specifically includes the following steps: Step M1: Data preprocessing: Arrange the piano room usage data in chronological order to obtain time series data, and then interpolate and complete the missing values ​​of the time series data to obtain preprocessed time series data; Step M2: Differentiation operation: perform differential processing on the preprocessed time series data to eliminate trend and periodic characteristics and obtain stable time series data; Step M3: Stationarity verification: introduce exogenous variables and dynamic error terms to improve the ADF model, build an improved ADF model, and test the stationarity of the stationary time series data through the improved ADF model to obtain complete stationary time series data. The improved ADF model specifically includes an exogenous variable introduction unit, a first-order difference calculation unit, a dynamic error term generation unit, and an improved ADF model unit; Step M4: Preliminary prediction: Based on the complete stationary time series data, combined with autoregression and moving average, the parameters of the improved ARIMA model are preliminarily determined through PACF and ACF graphs; Step M5: Model verification: The performance of the improved ARIMA model is verified through Bayesian information criterion, residual analysis and prediction error index to obtain verification results. The parameters of the improved ARIMA model are optimized according to the verification results, and the parameters are readjusted through the grid search method to obtain the corrected prediction feature data. Step M6: Forecast output: Based on the modified forecast feature data, the piano room usage rate data for the next week is obtained, and then a visual report is generated.

[0006] Furthermore, in step M3, the exogenous variable is introduced into the unit, and the steps performed specifically include: introducing policies, festivals and climate as exogenous variable items.

[0007] Furthermore, in step M3, the first-order difference calculation unit executes the following steps: performing a first-order difference operation on the stationary time series data to calculate the differential feature data.

[0008] Furthermore, in step M3, the steps performed by the dynamic error term generation unit specifically include: decomposing the traditional error term into fluctuation amplitude and standardized error, and introducing a dynamic modeling formula to iteratively update the fluctuation amplitude to reflect the dynamic characteristics of the error term, the dynamic characteristics include sudden changes and long-term characteristics of short-term fluctuations, and obtaining a dynamic error term. The formula used is as follows: Error term decomposition formula: ; in, is the time index, Indicates the dynamic fluctuation range, represents the standardized error, represents the dynamic error term; Dynamic modeling formula: ; in, represents the square of the fluctuation amplitude at the current moment, represents the base volatility level, and represents the weight coefficient, represents the square of the error term at the previous moment, Represents the square of the fluctuation amplitude at the previous moment.

[0009] Furthermore, in step M3, the steps performed by the improved ADF model unit specifically include: integrating the exogenous variable term, the differential characteristic data and the dynamic error term into the ADF model to test the stationarity of the stationary time series data and obtain the complete stationary time series data. The formula used is as follows: ; in, Represents the differential sequence data at the current moment, represents a constant term, represents the regression coefficient corresponding to the current moment, Represents the value of the previous moment in the time series. represents the coefficient, represents the lag order, represents the lag order index, represents the regression coefficient, Indicates hysteresis The differential data at time, represents the exogenous variable term, represents the coefficient of the exogenous variable term; represents the dynamic error term.

[0010] Furthermore, the environmental monitoring module, in combination with the enhanced fuzzy control algorithm, determines the environmental status and automatically adjusts the piano room equipment, specifically including the following steps: Step B1: Setting target values: Setting piano room environment target values, which include temperature target value, humidity target value, air quality target value, lighting target value, noise level target value and air circulation target value; Step B2: A / D conversion: collect environmental data in real time through environmental sensors, and convert the analog signals of the environmental data into digital signals through A / D converters to obtain digital environmental data; Step B3: Control variable calculation: Calculate the difference between the digital environmental data and the piano room environmental target value to obtain environmental state error data; Step B4: Fuzzy quantization: converting the environmental state error data into fuzzy quantization data through membership function; Step B5: Fuzzy control decision: Based on the fuzzy rule base, the fuzzy quantized data is combined for reasoning to generate fuzzy control decision data; Step B6: Defuzzification: Through the centroid method of particle swarm optimization, the fuzzy control decision data is defuzzified and converted into precise control signals to obtain device control commands; Step B7: Control output: adjust the piano room equipment according to the equipment control command to maintain the piano room environment.

[0011] Further, step B6 specifically includes the following steps: Step B61: define a Gaussian function as a membership function, and set an initial mean and standard deviation as a membership function parameter set; Step B62: Initialize the particle swarm, each particle represents a membership function parameter set, and randomly generate the position and velocity of the particle; Step B63: Calculate the control output using the particle membership function parameter set, calculate the fitness value based on the control output, and evaluate the quality of the current particle solution; Step B64: According to the update formula of the particle swarm optimization algorithm, the speed and position of each particle are updated. The particle guides the local exploration through the personal best position and guides the global search through the global best position, explores new solutions in the search space, and gradually approaches the global optimal solution. The formula used is as follows: Particle velocity update formula: ; in, represents the iteration index, represents the particle index, Represents particles In the The speed of generation, Represents particles In the The speed of generation, represents the inertia weight, and is the acceleration constant, and Represents a random number, Represents particles The best location in history, represents the global optimal position; Represents particles In the The position of the generation; Particle position update formula: ; in, Represents particles In the The position of the generation; Step B65: After each particle updates its position, the fitness value of the current particle is calculated and compared with the historical best fitness value to update the personal best position. By comparing the personal best positions of all particles, the global best position is updated until the particle swarm optimization algorithm converges and the optimized membership function parameter set is obtained; Step B66: Use the optimized membership function parameter set to calculate the defuzzification result through the centroid method to generate an accurate control signal.

[0012] By adopting the above scheme, the beneficial effects achieved by the present invention are as follows: The present invention provides a smart piano room platform design and management system based on the Internet of Things. The system enhances the stability verification capability by introducing exogenous variables and dynamic error terms, and significantly improves the accuracy and reliability of the piano room usage rate prediction. Combined with external factors (such as holidays and climate dynamic variables), the system can more sensitively reflect the impact of the external environment on the piano room usage trend. At the same time, the system uses dynamic error terms to capture short-term fluctuations and long-term characteristics, further improving the prediction accuracy. Especially in emergencies or special time periods, the system can intelligently adjust the prediction results, provide administrators with more accurate data support, optimize the allocation and scheduling of piano room resources, thereby improving the efficiency and scientificity of piano room management, avoiding resource waste and uneven distribution, and ensuring the efficient use of piano rooms in different time periods. In terms of environmental monitoring, the system enhances the defuzzification process by introducing the particle swarm optimization method. With this method, the system can monitor the environmental data in the piano room in real time, quickly determine the environmental status, and automatically generate equipment adjustment plans to accurately adjust the equipment operating parameters to ensure that the piano room environment is always maintained in the best state. This optimization method significantly improves the system's response speed to complex environmental changes, effectively improves user comfort, reduces user dissatisfaction caused by environmental problems, improves the overall user experience, and also reduces the risk of equipment damage caused by environmental problems. In summary, by introducing the above-mentioned optimization methods, the system has achieved dual optimization in piano room resource management and environmental monitoring; its data statistics function provides a scientific basis for resource allocation and greatly reduces human intervention; its environmental adjustment capability ensures efficient utilization of the piano room and a good user experience; at the same time, the system effectively reduces resource waste and equipment loss, significantly improves the intelligence level of piano room management, and provides an efficient and reliable solution for smart piano room management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a system framework diagram of a smart piano room platform design and management system based on the Internet of Things proposed by the present invention; Figure 2This is a flow chart of the improved ARIMA model in the data statistics module proposed in the present invention; Figure 3 This is a flow chart of the enhanced fuzzy control algorithm in the environmental monitoring module proposed in the present invention.

[0014] 1. Access control management module; 2. Mini program module, 20. Piano room reservation module, 21. Piano room return module, 22. Data statistics module, 23. Environmental monitoring module, 24. Equipment management module; 3. Data transmission module; 4. Database. DETAILED DESCRIPTION

[0015] 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, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0016] Embodiment 1, according to Figure 1 The present invention provides a smart piano room platform design and management system based on the Internet of Things, the system includes: an access control management module, a small program module, a data transmission module and a database, the access control management module transmits the two-dimensional code data and the face image data to the database through the data transmission module, and receives the instruction of the database to automatically control the access control to open, the small program module is connected to the database through the data transmission module, the data transmission module connects the access control management module, the small program module and the database to realize data interaction, the database connects the access control management module and the small program module, and performs data storage and sharing; The mini-program module includes a piano room reservation module, a piano room return module, a data statistics module, an environment monitoring module and an equipment management module. The piano room reservation module, the piano room return module, the environment monitoring module and the equipment management module transmit data to a database through a data transmission module. The data statistics module extracts the stored data of the piano room reservation module, the piano room return module, the environment monitoring module and the equipment management module in the database through the data transmission module to perform data statistics. The environment monitoring module is electrically connected to the equipment management module and transmits the environment monitoring data to the equipment management module for equipment management and adjustment. The user uses the piano room reservation module to select the piano room number, date and time period, query the piano room status information in the database, filter out the idle piano room data, prioritize the idle piano room data according to the frequency of use, obtain the prioritized piano room data, confirm the reservation request according to the prioritized piano room data and store it in the database; The user uses the piano room return module to scan the QR code to query the reservation record and verify whether the return time exceeds the reservation period. If it exceeds the reservation period, the overtime length is recorded and the user's credit score is dynamically adjusted. At the same time, the actual usage time is recorded and stored in the database; The data statistics module optimizes the stationarity verification based on the ARIMA model, constructs an improved ARIMA model, extracts piano room usage data from the database, uses the improved ARIMA model to predict the piano room usage rate, and generates a visualization report; the visualization report includes a usage rate curve chart, a daily peak time distribution chart, and an idle rate analysis chart; The environmental monitoring module enhances the defuzzification effect through the centroid method in the particle swarm optimization fuzzy control algorithm, constructs an enhanced fuzzy control algorithm, monitors the environmental data of the piano room in real time, judges the environmental status in combination with the enhanced fuzzy control algorithm, and automatically adjusts the piano room equipment.

[0017] Embodiment 2, according to Figure 2 This embodiment is based on the above embodiment. The data statistics module uses the improved ARIMA model to predict the piano room usage rate in the next week and generates a visualization report, which specifically includes the following steps: Step M1: Data preprocessing: Arrange the piano room usage data in chronological order to obtain time series data, and then interpolate and complete the missing values ​​of the time series data to obtain preprocessed time series data; Step M2: Differentiation operation: perform differential processing on the preprocessed time series data to eliminate trend and periodic characteristics and obtain stable time series data; Step M3: Stationarity verification: introduce exogenous variables and dynamic error terms to improve the ADF model, build an improved ADF model, and test the stationarity of the stationary time series data through the improved ADF model to obtain complete stationary time series data. The improved ADF model specifically includes an exogenous variable introduction unit, a first-order difference calculation unit, a dynamic error term generation unit, and an improved ADF model unit; Step M4: Preliminary prediction: Based on the complete stationary time series data, combined with autoregression and moving average, the parameters of the improved ARIMA model are preliminarily determined through PACF and ACF graphs; Step M5: Model verification: The performance of the improved ARIMA model is verified through Bayesian information criterion, residual analysis and prediction error index to obtain verification results. The parameters of the improved ARIMA model are optimized according to the verification results, and the parameters are readjusted through the grid search method to obtain the corrected prediction feature data. Step M6: Forecast output: According to the modified forecast feature data, the piano room usage rate data for the next week is obtained, and then a visual report is generated; By introducing exogenous variables and dynamic error terms, the stationarity verification capability is enhanced, and the accuracy and reliability of the piano room usage rate prediction are significantly improved; combined with external factors (such as holidays and climate dynamic variables), the system can more sensitively reflect the impact of the external environment on the piano room usage trend; at the same time, the system uses dynamic error terms to capture short-term fluctuations and long-term characteristics to further improve the prediction accuracy; especially in emergencies or special periods, the system can intelligently adjust the prediction results, provide administrators with more accurate data support, and optimize the allocation and scheduling of piano room resources, thereby improving the efficiency and scientificity of piano room management, avoiding resource waste and uneven distribution, and ensuring the efficient use of piano rooms in different time periods.

[0018] Embodiment 3: This embodiment is based on the above embodiment. In step M3, the exogenous variable introduction unit performs the following steps: introducing holidays, festivals and climate as exogenous variable items.

[0019] Embodiment 4: This embodiment is based on the above embodiment. In step M3, the first-order difference calculation unit executes the following steps: performing a first-order difference operation on the stationary time series data to calculate the differential feature data.

[0020] Embodiment 5, based on the above embodiment, in step M3, the steps performed by the dynamic error term generation unit specifically include: decomposing the traditional error term into fluctuation amplitude and standardized error, and introducing a dynamic modeling formula to iteratively update the fluctuation amplitude to reflect the dynamic characteristics of the error term, the dynamic characteristics include sudden changes and long-term characteristics of short-term fluctuations, and obtaining a dynamic error term. The formula used is as follows: Error term decomposition formula: ; in, is the time index, Indicates the dynamic fluctuation range, represents the standardized error, represents the dynamic error term; Dynamic modeling formula: ; in, represents the square of the fluctuation amplitude at the current moment, represents the base volatility level, and represents the weight coefficient, represents the square of the error term at the previous moment, Represents the square of the fluctuation amplitude at the previous moment.

[0021] Embodiment 6, based on the above embodiment, in step M3, the improved ADF model unit performs the following steps: integrating the exogenous variable term, differential characteristic data and dynamic error term into the ADF model to test the stationarity of the stationary time series data and obtain the complete stationary time series data. The formula used is as follows: ; in, Represents the differential sequence data at the current moment, represents a constant term, represents the regression coefficient corresponding to the current moment, Represents the value of the previous moment in the time series. represents the coefficient, represents the lag order, represents the lag order index, represents the regression coefficient, Indicates hysteresis The differential data at time, represents the exogenous variable term, represents the coefficient of the exogenous variable term; represents the dynamic error term.

[0022] Embodiment seven, according to Figure 3 This embodiment is based on the above embodiment. The environment monitoring module combines the enhanced fuzzy control algorithm to judge the environment state and automatically adjust the piano room equipment. The process specifically includes the following steps: Step B1: Setting target values: Setting piano room environment target values, which include temperature target value, humidity target value, air quality target value, lighting target value, noise level target value and air circulation target value; Step B2: A / D conversion: collect environmental data in real time through environmental sensors, and convert the analog signals of the environmental data into digital signals through A / D converters to obtain digital environmental data; Step B3: Control variable calculation: Calculate the difference between the digital environmental data and the piano room environmental target value to obtain environmental state error data; Step B4: Fuzzy quantization: converting the environmental state error data into fuzzy quantization data through membership function; Step B5: Fuzzy control decision: Based on the fuzzy rule base, the fuzzy quantized data is combined for reasoning to generate fuzzy control decision data; Step B6: Defuzzification: Through the centroid method of particle swarm optimization, the fuzzy control decision data is defuzzified and converted into precise control signals to obtain device control commands; Step B7: Control output: adjust the piano room equipment according to the equipment control command to maintain the piano room environment; In terms of environmental monitoring, the system enhances the defuzzification process by introducing particle swarm optimization methods. With this method, the system can monitor the environmental data in the piano room in real time, quickly determine the environmental status, and automatically generate equipment adjustment plans to accurately adjust the equipment operating parameters to ensure that the piano room environment is always maintained in the best state. This optimization method significantly improves the system's response speed to complex environmental changes, effectively improves user comfort, reduces user dissatisfaction caused by environmental problems, improves the overall user experience, and also reduces the risk of equipment damage caused by environmental problems.

[0023] Embodiment 8, based on the above embodiment, step B6 specifically includes the following steps: Step B61: define a Gaussian function as a membership function, and set an initial mean and standard deviation as a membership function parameter set; Step B62: Initialize the particle swarm, each particle represents a membership function parameter set, and randomly generate the position and velocity of the particle; Step B63: Calculate the control output using the particle membership function parameter set, calculate the fitness value based on the control output, and evaluate the quality of the current particle solution; Step B64: According to the update formula of the particle swarm optimization algorithm, the speed and position of each particle are updated. The particle guides the local exploration through the personal best position and guides the global search through the global best position, explores new solutions in the search space, and gradually approaches the global optimal solution. The formula used is as follows: Particle velocity update formula: ; in, represents the iteration index, represents the particle index, Represents particles In the The speed of generation, Represents particles In the The speed of generation, represents the inertia weight, and is the acceleration constant, and Represents a random number, Represents particles The best location in history, represents the global optimal position; Represents particles In the The position of the generation; Particle position update formula: ; in, Represents particles In the The position of the generation; Step B65: After each particle updates its position, the fitness value of the current particle is calculated and compared with the historical best fitness value to update the personal best position. By comparing the personal best positions of all particles, the global best position is updated until the particle swarm optimization algorithm converges and the optimized membership function parameter set is obtained; Step B66: Use the optimized membership function parameter set to calculate the defuzzification result through the centroid method to generate an accurate control signal.

[0024] The present invention and its embodiments are described above, which is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual structure is not limited to this. In short, if ordinary technicians in this field are inspired by it and do not deviate from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical solution, which should all fall within the scope of protection of the present invention.

Claims

1. A smart piano room platform design and management system based on the Internet of Things, including a data transmission module, a database, a piano room reservation module, a piano room return module and an equipment management module, characterized in that: It also includes a data statistics module and an environment monitoring module. The data statistics module extracts the stored data in the database of the piano room reservation module, the piano room return module, the environment monitoring module and the equipment management module through the data transmission module to perform data statistics. The environment monitoring module is electrically connected to the equipment management module to transmit the environment monitoring data to the equipment management module for equipment management and adjustment. The data statistics module optimizes the stationarity verification based on the ARIMA model, constructs an improved ARIMA model, extracts piano room usage data from the database, uses the improved ARIMA model to predict the piano room usage rate, and generates a visualization report. The process of generating the visualization report includes the following steps: Step M1: data preprocessing; Step M2: differential operation; Step M3: stationarity verification; Step M4: Preliminary prediction; Step M5: Model verification; Step M6: predict output; The data statistics module uses the improved ARIMA model to predict the piano room utilization rate and generate a visual report, which specifically includes the following steps: The data preprocessing process in step M1 is: arranging the piano room usage data in chronological order to obtain time series data, and then interpolating and completing the missing values ​​of the time series data to obtain preprocessed time series data; The process of the differential operation in step M2 is: performing differential processing on the pre-processed time series data to eliminate trend and periodic characteristics and obtain stationary time series data; The process of stationarity verification in step M3 is: introducing exogenous variables and dynamic error terms to improve the ADF model, constructing an improved ADF model, and testing the stationarity of the stationary time series data through the improved ADF model to obtain complete stationary time series data. The improved ADF model specifically includes an exogenous variable introduction unit, a first-order difference calculation unit, a dynamic error term generation unit, and an improved ADF model unit; The process of preliminary prediction in step M4 is: based on the complete stationary time series data, combined with autoregression and moving average, the parameters of the improved ARIMA model are preliminarily determined through PACF and ACF graphs; The process of model verification in step M5 is: verifying the performance of the improved ARIMA model through Bayesian information criterion, residual analysis and prediction error index to obtain verification results, optimizing the parameters of the improved ARIMA model according to the verification results, and readjusting the parameters through grid search method to obtain corrected prediction feature data; The process of prediction output in step M6 is: according to the modified prediction feature data, the piano room usage rate data for the next week is obtained, and then a visualization report is generated.

2. According to the design and management system of a smart piano room platform based on the Internet of Things according to claim 1, it is characterized by: The environmental monitoring module enhances the defuzzification effect by using the centroid method in the particle swarm optimization fuzzy control algorithm, and constructs an enhanced fuzzy control algorithm; monitors the environmental data of the piano room in real time, judges the environmental state in combination with the enhanced fuzzy control algorithm, and automatically adjusts the piano room equipment; the process of judging the environmental state and automatically adjusting the piano room equipment includes the following steps: Step B1: Set target value; Step B2: A / D conversion; Step B3: Calculation of control variables; Step B4: fuzzy quantization; Step B5: fuzzy control decision; Step B6: Defuzzification; Step B7: control output; The environmental monitoring module combines the enhanced fuzzy control algorithm to judge the environmental status and automatically adjust the piano room equipment, which specifically includes the following steps: The process of setting the target value in step B1 is: setting the target value of the piano room environment; The process of A / D conversion in step B2 is: collecting environmental data in real time through environmental sensors, and converting analog signals of environmental data into digital signals through A / D converters to obtain digital environmental data; The process of calculating the control variable in step B3 is: calculating the difference between the digital environmental data and the piano room environmental target value to obtain environmental state error data; The process of fuzzy quantization in step B4 is: converting the environmental state error data into fuzzy quantized data through a membership function; The process of fuzzy control decision in step B5 is: according to the fuzzy rule base, reasoning is performed in combination with fuzzy quantized data to generate fuzzy control decision data; The defuzzification process in step B6 is: by using the centroid method of particle swarm optimization, the fuzzy control decision data is defuzzified and converted into a precise control signal to obtain a device control command; The process of controlling the output in step B7 is: adjusting the piano room equipment according to the equipment control command to maintain the piano room environment; Step B6 specifically comprises the following steps: Step B61: define a Gaussian function as a membership function, and set an initial mean and standard deviation as a membership function parameter set; Step B62: Initialize the particle swarm, each particle represents a membership function parameter set, and randomly generate the position and velocity of the particle; Step B63: Calculate the control output using the particle membership function parameter set, calculate the fitness value based on the control output, and evaluate the quality of the current particle solution; Step B64: According to the update formula of the particle swarm optimization algorithm, the speed and position of each particle are updated. The particle guides the local exploration through the personal best position and guides the global search through the global best position, explores new solutions in the search space, and gradually approaches the global optimal solution. Step B65: After each particle updates its position, the fitness value of the current particle is calculated and compared with the historical best fitness value to update the personal best position. By comparing the personal best positions of all particles, the global best position is updated until the particle swarm optimization algorithm converges and the optimized membership function parameter set is obtained; Step B66: Use the optimized membership function parameter set to calculate the defuzzification result through the centroid method to generate an accurate control signal.

3. According to the design and management system of a smart piano room platform based on the Internet of Things as claimed in claim 1, it is characterized by: In step M3, the exogenous variable introduction unit performs the following steps: introducing festivals and climate as exogenous variable items.

4. According to the design and management system of a smart piano room platform based on the Internet of Things as claimed in claim 1, it is characterized by: In step M3, the first-order difference calculation unit executes the following steps: performing a first-order difference operation on the stationary time series data to calculate the difference feature data.

5. According to the design and management system of a smart piano room platform based on the Internet of Things according to claim 1, it is characterized by: In step M3, the steps performed in the dynamic error term generation unit specifically include: decomposing the traditional error term into fluctuation amplitude and standardized error, and introducing a dynamic modeling formula to iteratively update the fluctuation amplitude to reflect the dynamic characteristics of the error term, the dynamic characteristics include sudden changes in short-term fluctuations and long-term characteristics, and obtaining a dynamic error term.

6. According to the design and management system of a smart piano room platform based on the Internet of Things according to claim 5, it is characterized by: In step M3, the improved ADF model unit specifically performs the following steps: integrating the exogenous variable term, differential characteristic data and dynamic error term into the ADF model to test the stationarity of the stationary time series data and obtain complete stationary time series data.

Images