Property management and control system and method for smart park

Abstract

The invention relates to the technical field of park management, in particular to a property management and control system and method for a smart park, and the system comprises an information collection module, a data preprocessing module, a feature extraction module, a prediction analysis module and a decision optimization module. Wherein the information acquisition module is used for acquiring environment data, energy consumption data and personnel flow data in a park in real time; the feature extraction module is used for extracting related features from the processed data; the prediction analysis module is used for predicting the environment change trend, the energy consumption change condition and the personnel flow change of the park in a period of time in the future; and the decision optimization module is used for formulating a property management strategy by using an optimization algorithm. According to the invention, through intelligent data acquisition and analysis, fine management of park environment adjustment, energy distribution and personnel flow is realized in combination with an optimization algorithm, so that resource utilization efficiency is improved, energy waste is reduced, and park operation benefits are optimized.

Description

Technical Field

[0001] The present invention relates to the field of park management technology, and in particular to a property management and control system and method for a smart park. Background Art

[0002] With the continuous development of smart park construction, park management is gradually transforming towards digitalization and intelligence; park management involves many aspects, including environmental regulation, energy consumption management, and optimization of personnel flow; these management tasks usually rely on various sensors, monitoring equipment, and data acquisition systems to collect large amounts of real-time data to support management decisions.

[0003] However, existing park management systems face the following challenges: First, the collection of environmental data, energy consumption data, and personnel flow information is often conducted independently, lacking effective data integration and analysis methods; second, the amount of data is huge and complex, and traditional manual analysis methods cannot effectively handle it, resulting in delayed and inaccurate park management decisions; in addition, existing management solutions usually only focus on optimizing a single aspect, ignoring the relationship between multiple factors within the park, resulting in inefficient management of various resources, and even problems such as energy waste and substandard environmental comfort. Summary of the invention

[0004] Based on the above objectives, the present invention provides a property management and control system and method for a smart park.

[0005] A property management and control system for a smart park includes an information collection module, a data preprocessing module, a feature extraction module, a prediction analysis module, and a decision optimization module; wherein:

[0006] Information collection module: used to install various sensors and intelligent devices in the park to collect real-time environmental data, energy consumption data and personnel flow data in the park;

[0007] Data preprocessing module: used to clean, denoise and standardize the environmental data, energy consumption data and personnel flow information collected by the information collection module to generate a processed data set;

[0008] Feature extraction module: used to extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow;

[0009] Prediction and analysis module: used to analyze the relevant features extracted by the feature extraction module, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a comprehensive prediction report;

[0010] Decision-making optimization module: Based on the comprehensive forecast report of the forecast analysis module, combined with the current resource status and management goals of the park, an optimization algorithm is used to formulate property management strategies, including environmental adjustment plans, energy allocation strategies and personnel flow management plans.

[0011] Optionally, the information collection module includes a sensor installation unit, an environmental data collection unit, an energy consumption data collection unit, a personnel flow data collection unit, and a data summary transmission unit; wherein:

[0012] Sensor installation unit: used to deploy sensors and smart devices at the entrances and exits, public areas, office areas, and around energy equipment within the park;

[0013] Environmental data collection unit: including temperature sensor, humidity sensor and air quality sensor, which are used to collect environmental temperature and humidity data of various areas in the park in real time;

[0014] Energy consumption data collection unit: including electricity meter, water meter and gas meter, which are used to monitor and record the use of various energy sources in the park in real time to provide energy consumption data;

[0015] Personnel flow data collection unit: including access control system and video surveillance equipment, which are used to record the entry and exit time, number and flow path of personnel in the park to provide personnel flow data;

[0016] Data aggregation and transmission unit: used to aggregate the real-time data from the environmental data collection unit, the energy consumption data collection unit and the personnel flow data collection unit, and transmit the aggregated data to the data preprocessing module through a wired or wireless communication network.

[0017] Optionally, the data preprocessing module includes a data cleaning unit, a denoising processing unit, a standardization processing unit and a data integration unit; wherein:

[0018] Data cleaning unit: used to clean the environmental data, energy consumption data and personnel flow information collected by the information collection module, using a data cleaning algorithm based on the threshold method, by setting the threshold, and then automatically identifying and eliminating data points that do not meet the predetermined range;

[0019] De-noising unit: used to perform denoising on the cleaned data. It uses the median filtering algorithm to sort the neighborhood data around each data point, and takes the sorted median as the denoising value of the data point to reduce the impact of random noise.

[0020] Standardization processing unit: used to standardize the denoised data, using the Z-score standardization method to normalize the mean of each data point to 0 and the standard deviation to 1;

[0021] Data integration unit: used to integrate the processed environmental data, energy consumption data and personnel flow information to generate a comprehensive processed data set.

[0022] Optionally, the feature extraction module includes an environmental parameter fluctuation pattern extraction unit, an energy usage peak and valley pattern extraction unit, and a personnel flow high-frequency area extraction unit; wherein:

[0023] Environmental parameter fluctuation pattern extraction unit: used to extract environmental parameter fluctuation patterns from the processed environmental data set, use Fourier transform method to analyze the change trend of environmental temperature and humidity over time, calculate the spectrum of data, and identify the fluctuation period;

[0024] Energy usage peak and valley pattern extraction unit: used to extract the peak and valley pattern of energy usage from the processed energy consumption data set, by calculating the peak and valley values ​​of the energy consumption data and analyzing its changing trend using the sliding window method, to identify the peak and valley periods of energy usage;

[0025] Personnel flow high-frequency area extraction unit: used to extract high-frequency areas from the processed personnel flow data, by counting the frequency of personnel in each area, using the K-means clustering algorithm to divide the park into multiple areas, and identify high-frequency areas with dense personnel flow.

[0026] Optionally, the personnel flow high-frequency area extraction unit includes:

[0027] Data preprocessing: Based on the personnel flow data collected by the information collection module, a data matrix is ​​constructed, in which each row represents the personnel flow information at a moment, and each column represents the number of personnel at different locations in the park;

[0028] Initialize cluster centers: randomly select k initial cluster centers and use them as the initial representatives of each region;

[0029] Assign data points: Assign each data point to the nearest cluster center according to the Euclidean distance formula;

[0030] Update cluster centers: Calculate the new location of each cluster center based on the assigned data points, i.e. the average personnel flow data of the area;

[0031] Iterate until convergence: Repeat the above steps until the cluster center no longer changes;

[0032] Identify high-frequency areas: Analyze the regional density of each cluster through clustering results, that is, calculate the frequency of personnel flow in each area, and select the area with the highest flow frequency as the high-frequency area.

[0033] Optionally, the prediction analysis module includes a data analysis unit, a prediction model unit and a comprehensive prediction report generation unit; wherein:

[0034] Data analysis unit: Use multivariate regression analysis to conduct correlation analysis on the fluctuation patterns of environmental parameters, the peak and valley patterns of energy use, and the characteristics of high-frequency areas of personnel flow, and establish a mathematical model between environmental changes, energy consumption, and personnel flow;

[0035] Prediction model unit: Based on the mathematical model established by the data analysis unit, it predicts the environmental change trend, energy consumption change and personnel flow change of the park in the future;

[0036] Comprehensive forecast report generation unit: used to summarize the forecast results generated by the forecast model unit, present the forecast results of environmental change trends, energy consumption changes and personnel flow changes in the form of charts and text descriptions, and generate a comprehensive forecast report.

[0037] Optionally, the data analysis unit includes:

[0038] Data preprocessing: Standardize the input environmental parameter fluctuation patterns, energy usage peak and valley patterns, and high-frequency regional characteristics of personnel flow to ensure that each feature has the same dimension and value range;

[0039] Correlation analysis: By calculating the correlation coefficient matrix between each feature, the relationship between the environmental parameter fluctuation pattern, the peak and valley pattern of energy use and the high-frequency area of ​​personnel flow is analyzed, and the Pearson correlation coefficient is calculated as a linear correlation measure between the features;

[0040] Regression analysis: Use multivariate regression analysis to establish a mathematical model between environmental changes, energy consumption and personnel flow, and use the least squares method to perform regression and fit the relationship between multiple variables. The mathematical expression of this mathematical model is: Y = β 0 +β 1 X 1 +β 2 X 2 +…+β j X j +∈, where Y is the predicted output variable, X 1 ,X 2 ,…,X j is the input feature variable, β 0 is a constant term, β 1 ,β 2 ,…,β j is the regression coefficient, ∈ is the error term;

[0041] Model optimization: Based on the mathematical model obtained by regression analysis, the regression coefficient is optimized and the gradient descent method is used to reduce the prediction error. The formula for updating the regression coefficient by the gradient descent method is: Among them, β j is the jth regression coefficient, α is the learning rate, is the loss function J(β) versus the regression coefficient β j The partial derivative of , which indicates the influence of the regression coefficient on the loss function.

[0042] Optionally, the decision optimization module includes an environment adjustment strategy formulation unit, an energy allocation strategy formulation unit and a personnel flow management plan formulation unit; wherein:

[0043] Environmental regulation strategy formulation unit: Based on the environmental change trend forecast report generated by the forecast analysis module and the current environmental resource status of the park, the linear programming algorithm is used to optimize the operation strategy of air conditioning, heating and ventilation equipment to achieve environmental comfort and efficient energy utilization in the park;

[0044] Energy distribution strategy formulation unit: Based on the energy consumption change forecast report generated by the forecast analysis module and combined with the current energy supply and demand conditions of the park, a genetic algorithm is used to optimize the energy distribution plan to ensure the stable energy supply of various equipment and facilities;

[0045] Personnel flow management plan formulation unit: Based on the personnel flow change forecast report generated by the forecast analysis module and the current human resource configuration of the park, the integer programming algorithm is used to optimize the personnel flow path and configuration.

[0046] Optionally, the personnel flow management plan formulation unit includes:

[0047] Define flow paths and personnel: Divide all areas in the park into multiple flow paths, each path corresponds to a group of personnel. Assuming there are g flow paths, define the flow of personnel on each path as y i , i=1,2,…,g;

[0048] Objective function setting: Set the objective function to maximize the efficiency of personnel flow. The formula is: Among them, W is the total staff turnover efficiency, p i is the efficiency coefficient of the i-th flow path, y i Assign the number of people to the i-th flow path, with the goal of maximizing the total flow efficiency;

[0049] Constraint setting: Set the constraints on the flow of personnel to ensure that the number of people on each path does not exceed the maximum load of the path, and the total number of people does not exceed the number of people that can be allocated in the park; specifically, let P be the total number of people in the park, P max,iis the maximum load of the i-th flow path, then the constraint condition is:

[0050]

[0051] 0≤y i ≤P max,i ,

[0052] Integer programming solution: The above objective function and constraints are solved by the integer programming algorithm to obtain the optimal personnel allocation for each flow path, thereby determining the optimal personnel flow path and configuration plan.

[0053] A property management method for a smart park is implemented by the property management system for a smart park, and includes the following steps:

[0054] S1: Install various sensors and smart devices in the park to collect real-time environmental data, energy consumption data and personnel flow data in the park;

[0055] S2: Preprocess the environmental data, energy consumption data and personnel flow data collected by S1, using cleaning, denoising and standardization to generate a processed data set;

[0056] S3: Extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow;

[0057] S4: Use multivariate regression analysis to conduct correlation analysis on the extracted relevant features and establish a mathematical model between environmental changes, energy consumption and personnel flow;

[0058] S5: Based on the mathematical model established in S4, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a forecast report;

[0059] S6: Based on the forecast report in S5, combined with the current resource status and management objectives of the park, an optimization algorithm is used to formulate a property management strategy, including an environmental adjustment plan, an energy allocation strategy, and a personnel flow management plan.

[0060] Beneficial effects of the present invention:

[0061] The present invention can effectively integrate various types of data in the park through comprehensive collection and processing of environmental data, energy consumption data and personnel flow information, eliminating the problem of independent management of various data in the prior art; through multi-dimensional data analysis and precise feature extraction, it can not only capture the changing trend of park resources, but also identify the key operating modes in the park, thereby providing real-time and accurate decision-making basis for park managers.

[0062] The present invention, by adopting an optimization algorithm to formulate property management strategies, can automatically adjust environmental regulation, energy distribution and personnel flow management according to real-time changes in the park; through precise prediction and intelligent adjustment, it can not only improve the efficiency of park resource utilization and reduce energy waste, but also optimize personnel flow paths while ensuring environmental comfort, thereby improving the overall operating efficiency of the park. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 A schematic diagram of a property management system for a smart park according to an embodiment of the present invention;

[0065] Figure 2 Schematic diagram of a property management method for a smart park according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0067] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0068] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0069] like Figure 1 As shown, a property management system and method for a smart park includes an information collection module, a data preprocessing module, a feature extraction module, a prediction analysis module, and a decision optimization module; wherein:

[0070] Information collection module: used to install various sensors and intelligent devices in the park to collect real-time environmental data (including temperature and humidity), energy consumption data (including real-time usage of electricity, water, gas and other energy sources) and personnel flow data (including the number of people entering and leaving, flow paths, etc.) in the park, providing basic data support for subsequent data processing;

[0071] Data preprocessing module: used to clean, denoise and standardize the environmental data, energy consumption data and personnel flow information collected by the information collection module to generate a processed data set;

[0072] Feature extraction module: used to extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow;

[0073] Prediction and analysis module: used to analyze the relevant features extracted by the feature extraction module, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a comprehensive prediction report;

[0074] Decision-making optimization module: Based on the comprehensive forecast report of the forecast analysis module, combined with the current resource status and management objectives of the park, an optimization algorithm is used to formulate property management strategies, including environmental adjustment plans, energy allocation strategies and personnel flow management plans, to achieve high efficiency, energy saving and safety of park management.

[0075] The information collection module includes a sensor installation unit, an environmental data collection unit, an energy consumption data collection unit, a personnel flow data collection unit, and a data summary transmission unit; wherein:

[0076] Sensor installation unit: used to deploy sensors and smart devices at the entrances and exits, public areas, office areas and around energy equipment in the park to ensure comprehensive coverage and real-time monitoring of environmental parameters, energy usage and personnel flow in the park;

[0077] Environmental data collection unit: including temperature sensors, humidity sensors and air quality sensors, which are used to collect environmental temperature and humidity data of various areas in the park in real time to ensure accurate understanding of the environmental conditions in the park;

[0078] Energy consumption data collection unit: including electricity meter, water meter and gas meter, which are used to monitor and record the use of various energy sources in the park in real time to provide energy consumption data;

[0079] Personnel flow data collection unit: including access control system and video surveillance equipment, which are used to record the entry and exit time, number and flow path of personnel in the park to provide personnel flow data;

[0080] Data aggregation and transmission unit: used to aggregate the real-time data from the environmental data collection unit, energy consumption data collection unit and personnel flow data collection unit, and transmit the aggregated data to the data preprocessing module through a wired or wireless communication network to ensure the timeliness and integrity of the data; the above-mentioned units realize the orderly transmission and integration of data through the internal communication interface, ensuring that the information collection module can efficiently and accurately obtain multi-dimensional data within the park, providing a solid data foundation for subsequent data processing and decision optimization.

[0081] The data preprocessing module includes a data cleaning unit, a denoising processing unit, a standardization processing unit and a data integration unit; wherein:

[0082] Data cleaning unit: used to clean the environmental data, energy consumption data and personnel flow information collected by the information collection module. It adopts a data cleaning algorithm based on the threshold method, sets a threshold, and then automatically identifies and removes data points that do not meet the predetermined range. Specifically, for each piece of data, calculate its deviation from the mean of the data set. If the deviation exceeds the preset threshold, the data is considered to be an outlier and removed.

[0083] De-noising unit: used to perform denoising on the cleaned data. It uses the median filtering algorithm to sort the neighborhood data around each data point and take the median of the sorting as the denoising value of the data point to reduce the impact of random noise. Specifically, for each data point, take the N data points x in its neighborhood. 1 ,x 2 ,…,x N , calculate the median x m , replace the original data point;

[0084] Standardization processing unit: used to standardize the denoised data. The Z-score standardization method is used to normalize the mean of each data point to 0 and the standard deviation to 1. The formula is: Among them, x i is the original data point, μ is the mean of the data set, σ is the standard deviation of the data set, z i is the standardized data point;

[0085] Data integration unit: used to integrate the processed environmental data, energy consumption data and personnel flow information to generate a comprehensive processed data set. By merging various processed data and unifying the format, it ensures that subsequent modules can effectively use the processed data set. The above units realize the orderly transmission and processing of data through internal data interfaces, ensuring that the data preprocessing module can efficiently and accurately generate high-quality processed data sets, providing a solid data foundation for subsequent feature extraction and predictive analysis.

[0086] The feature extraction module includes an environmental parameter fluctuation pattern extraction unit, an energy usage peak and valley pattern extraction unit, and a personnel flow high-frequency area extraction unit; wherein:

[0087] Environmental parameter fluctuation pattern extraction unit: used to extract environmental parameter fluctuation patterns from the processed environmental data set, use Fourier transform method to analyze the change trend of environmental temperature and humidity over time, calculate the spectrum of data, and identify the fluctuation period; the specific calculation formula is: Among them, X(f) is the environmental parameter fluctuation pattern expressed in the frequency domain, x(t) is the environmental data point in the time domain, f is the frequency, and N is the total number of data points; by calculating the Fourier transform, the main fluctuation period can be identified, thereby extracting the fluctuation pattern characteristics of the environmental parameters;

[0088] Energy usage peak and valley pattern extraction unit: used to extract the peak and valley pattern of energy usage from the processed energy consumption data set, by calculating the peak and valley values ​​of the energy consumption data and using the sliding window method to analyze its changing trend, to identify the peak and valley periods of energy usage; the specific formula is as follows:

[0089] x peak (t)=max{x(tw),x(t-w+1),...,x(t+w)};

[0090] x valley (t)=min{x(tw),x(t-w+1),...,x(t+w)}; where, x peak (t) is the peak energy consumption in time period t, x valley (t) is the valley energy consumption in period t, x(t) is the energy consumption data in period t, and w is the size of the sliding window;

[0091] Personnel flow high-frequency area extraction unit: used to extract high-frequency areas from the processed personnel flow data, count the frequency of personnel in each area, use the K-means clustering algorithm to divide the park into multiple areas, and identify high-frequency areas with dense personnel flow; the above units realize orderly transmission and processing of data through internal data interfaces, ensuring that the feature extraction module can efficiently and accurately extract various useful features from the processed data set for use by subsequent prediction and analysis modules.

[0092] The personnel flow high-frequency area extraction unit includes:

[0093] Data preprocessing: Based on the personnel flow data collected by the information collection module, a data matrix D is constructed, in which each row represents the personnel flow information at a moment, and each column represents the number of personnel in different locations (areas) in the park. The formula is expressed as:

[0094] Among them, d ij is the personnel flow data of area j at the i-th moment, n is the total number of data points, and m is the number of areas;

[0095] Initialize cluster centers: randomly select k initial cluster centers C 1 ,C 2 ,…,C k , and the cluster center is used as the initial representative of each region. The initialization process can be achieved by randomly selecting k points from the data set;

[0096] Assign data points: According to the Euclidean distance formula, each data point d i Assigned to the nearest cluster center, the formula is: Among them, d i is the data point, C j is the cluster center, m is the number of regions, t is the tth region, and the data point d i Assigned to the cluster center C with the minimum distance j , get a new group S j ;

[0097] Update cluster centers: Based on the assigned data points, calculate the new location of each cluster center, that is, the average personnel flow data of the area. The update formula is as follows: Among them, |S j | represents cluster S j The number of data points in , d i By recalculating the location of the cluster center for each data point in the cluster, the quality of the clustering is gradually improved;

[0098] Iterate until convergence: Repeat the above steps until the cluster center no longer changes;

[0099] Identify high-frequency areas: Analyze the regional density of each cluster through clustering results, that is, calculate the personnel flow frequency of each area, and select the area with the highest flow frequency as the high-frequency area. The frequency calculation formula is: Among them, F j is the flow frequency of region j, Frequency(d i ) for each data point d i The corresponding personnel turnover frequency, |S j | is cluster S j Through the above steps, the personnel flow high-frequency area extraction unit can accurately identify the areas with dense personnel flow in the park through the K-means clustering algorithm. Through the clustering analysis of personnel flow data, the high-frequency areas can be effectively identified, thus providing a reliable basis for subsequent decision-making optimization.

[0100] The forecast analysis module includes a data analysis unit, a forecast model unit and a comprehensive forecast report generation unit; wherein:

[0101] Data analysis unit: Use multivariate regression analysis to conduct correlation analysis on the fluctuation patterns of environmental parameters, the peak and valley patterns of energy use, and the characteristics of high-frequency areas of personnel flow, and establish a mathematical model between environmental changes, energy consumption, and personnel flow;

[0102] Prediction model unit: Based on the mathematical model established by the data analysis unit, it predicts the environmental change trend, energy consumption change and personnel flow change of the park in the future;

[0103] Comprehensive forecast report generation unit: used to summarize the forecast results generated by the forecast model unit, present the forecast results of environmental change trends, energy consumption changes and personnel flow changes in the form of charts and text descriptions, generate a comprehensive forecast report, and ensure the readability and practicality of the report. The above units realize the orderly transmission and processing of data through the internal data interface, ensuring that the forecast analysis module can efficiently and accurately analyze and predict the extracted features, and generate a detailed comprehensive forecast report, providing a reliable decision-making basis for the decision optimization module.

[0104] The data analysis unit includes:

[0105] Data preprocessing: Standardize the input environmental parameter fluctuation patterns, energy usage peak and valley patterns, and high-frequency regional characteristics of personnel flow to ensure that each feature has the same dimension and value range, thereby eliminating the impact of different dimensions on the analysis results;

[0106] Correlation analysis: By calculating the correlation coefficient matrix between each feature, analyzing the relationship between the environmental parameter fluctuation pattern, the peak and valley pattern of energy use and the high-frequency area of ​​personnel flow, the Pearson Correlation Coefficient (PCC) is calculated as a linear correlation measure between the features. The formula is: Among them, X i and Y i are the i-th observation values ​​of the environmental parameter fluctuation pattern and energy usage peak and valley pattern, respectively. and is the mean of each feature, PCC(X, Y) is the correlation coefficient between the two features;

[0107] Regression analysis: Use multivariate regression analysis to establish a mathematical model between environmental changes, energy consumption and personnel flow, and use the least squares method to perform regression and fit the relationship between multiple variables. The mathematical expression of this mathematical model is: Y = β 0 +β 1 X 1 +β 2 X 2 +…+β j X j +∈, where Y is the predicted output variable (such as environmental change, energy consumption or personnel flow), X 1 ,X 2 ,…,X j is the characteristic variable of the input (such as the fluctuation pattern of environmental parameters, the peak and valley pattern of energy use, and the high-frequency area of ​​personnel flow), β 0 is a constant term, β 1 ,β 2 ,…,β j is the regression coefficient, ∈ is the error term;

[0108] Model optimization: Based on the mathematical model obtained by regression analysis, the regression coefficient is optimized and the gradient descent method is used to reduce the prediction error. The formula for updating the regression coefficient by the gradient descent method is: Among them, β j is the jth regression coefficient, α is the learning rate, is the loss function J(β) versus the regression coefficient β j The partial derivative of represents the influence of the regression coefficient on the loss function. By continuously updating the regression coefficient, the error is reduced and the accuracy of the prediction model is improved. Through the above steps, the data analysis unit can establish and optimize the mathematical model between environmental changes, energy consumption and personnel flow based on the correlation between environmental parameter fluctuation patterns, energy usage peak and valley patterns and high-frequency areas of personnel flow, so as to provide an accurate analysis basis for subsequent predictions and decisions.

[0109] The decision optimization module includes an environmental regulation strategy formulation unit, an energy allocation strategy formulation unit, and a personnel flow management plan formulation unit; among which:

[0110] Environmental regulation strategy formulation unit: Based on the environmental change trend forecast report generated by the forecast analysis module and the current environmental resource status of the park, the linear programming algorithm is used to optimize the operation strategy of air conditioning, heating and ventilation equipment to achieve environmental comfort and efficient energy utilization in the park;

[0111] The specific steps of the linear programming algorithm include:

[0112] Objective function setting: Set the objective function of minimizing energy consumption, the formula is expressed as: Where Z is the total energy consumption, c i is the unit energy consumption cost of the i-th equipment, x i is the running time of the i-th device, and n is the number of devices;

[0113] Definition of constraint conditions: According to the requirements of environmental comfort, set the upper and lower limits of temperature and humidity to ensure that the adjusted environmental parameters are within the set range; the expression is: Among them, T min and T max are the lower and upper limits of the ambient temperature, respectively, i is the regulating effect coefficient of the i-th equipment on the ambient temperature;

[0114] Linear programming solution: Use linear programming algorithms (such as the simplex method) to solve the above objective function and constraints to obtain the optimal operating time of each device, thereby formulating the optimal environmental adjustment plan.

[0115] Energy distribution strategy formulation unit: Based on the energy consumption change forecast report generated by the forecast analysis module and combined with the current energy supply and demand conditions of the park, a genetic algorithm is used to optimize the energy distribution plan to ensure the stable energy supply of each equipment and facility, and reduce energy waste and operating costs;

[0116] The specific steps of genetic algorithm include:

[0117] Initial population generation: randomly generate a set of initial energy allocation schemes, each of which is represented by a gene sequence containing the energy allocation ratio;

[0118] Fitness function setting: Set the fitness function to evaluate the pros and cons of each energy allocation scheme. The formula is: Among them, EnergyWaste is the amount of energy waste, Cost is the total cost of energy allocation, and Fitness is the fitness value;

[0119] Selection operation: select the energy allocation scheme with the highest fitness value according to the fitness function and enter the next generation;

[0120] Crossover and mutation: Perform crossover and mutation operations on the selected energy allocation scheme to generate a new energy allocation scheme and maintain the diversity of the population;

[0121] Iterative optimization: Repeat the selection, crossover and mutation steps until the predetermined number of iterations is reached or the fitness converges, and finally the optimal energy allocation solution is obtained.

[0122] Personnel flow management plan formulation unit: Based on the personnel flow change forecast report generated by the prediction and analysis module and the current human resource allocation of the park, the integer programming algorithm is used to optimize the personnel flow path and configuration, thereby improving the efficiency and safety of personnel management within the park; the above-mentioned units work together through information interfaces, and formulate scientific and reasonable property management strategies based on comprehensive prediction data and optimization algorithms, thereby improving the overall management level and operational efficiency of the park.

[0123] The staff flow management plan development unit includes:

[0124] Define flow paths and personnel: Divide all areas in the park into multiple flow paths, each path corresponds to a group of personnel. Assuming there are g flow paths, define the flow of personnel on each path as y i , i=1,2,…,g;

[0125] Objective function setting: Set the objective function to maximize the efficiency of personnel flow. The formula is: Among them, W is the total staff turnover efficiency, p i is the efficiency coefficient of the i-th flow path, y i Assign the number of people to the i-th flow path, with the goal of maximizing the total flow efficiency;

[0126] Constraint setting: Set the constraints on the flow of personnel to ensure that the number of people on each path does not exceed the maximum load of the path, and the total number of people does not exceed the number of people that can be allocated in the park; specifically, let P be the total number of people in the park, P max,i is the maximum load of the i-th flow path, then the constraint condition is:

[0127]

[0128] 0≤y i ≤P max,i ,

[0129] Integer programming solution: The objective function and constraints mentioned above are solved by integer programming algorithms (such as branch and bound method or dynamic programming method) to obtain the optimal personnel allocation for each flow path, thereby determining the optimal personnel flow path and configuration plan; through the above steps, the integer programming algorithm is used to optimize the personnel flow path and configuration, which can accurately allocate the personnel distribution within the park and improve the personnel flow efficiency and management security within the park.

[0130] like Figure 2 As shown, a property management method for a smart park is implemented by the above-mentioned property management system for a smart park, and includes the following steps:

[0131] S1: Install various sensors and smart devices in the park to collect real-time environmental data, energy consumption data and personnel flow data in the park;

[0132] S2: Preprocess the environmental data, energy consumption data and personnel flow data collected by S1, using cleaning, denoising and standardization to generate a processed data set;

[0133] S3: Extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow;

[0134] S4: Use multivariate regression analysis to conduct correlation analysis on the extracted relevant features and establish a mathematical model between environmental changes, energy consumption and personnel flow;

[0135] S5: Based on the mathematical model established in S4, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a forecast report;

[0136] S6: Based on the forecast report in S5, combined with the current resource status and management objectives of the park, an optimization algorithm is used to formulate a property management strategy, including an environmental adjustment plan, an energy allocation strategy, and a personnel flow management plan.

[0137] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A property management and control system for a smart park, characterized in that: It includes information collection module, data preprocessing module, feature extraction module, prediction analysis module and decision optimization module; among which: Information collection module: used to install various sensors and intelligent devices in the park to collect environmental data, energy consumption data and personnel flow data in the park in real time; Data preprocessing module: used to clean, denoise and standardize the environmental data, energy consumption data and personnel flow information collected by the information collection module to generate a processed data set; Feature extraction module: used to extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow; Prediction and analysis module: used to analyze the relevant features extracted by the feature extraction module, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a comprehensive prediction report; Decision-making optimization module: Based on the comprehensive forecast report of the forecast analysis module, combined with the current resource status and management goals of the park, an optimization algorithm is used to formulate property management strategies, including environmental adjustment plans, energy allocation strategies and personnel flow management plans.

2. A property management system for a smart park according to claim 1, characterized in that: The information collection module includes a sensor installation unit, an environmental data collection unit, an energy consumption data collection unit, a personnel flow data collection unit and a data summary transmission unit; wherein: Sensor installation unit: used to deploy sensors and smart devices at the entrances and exits, public areas, office areas, and around energy equipment within the park; Environmental data collection unit: including temperature sensor, humidity sensor and air quality sensor, which are used to collect environmental temperature and humidity data of various areas in the park in real time; Energy consumption data collection unit: including electricity meter, water meter and gas meter, which are used to monitor and record the use of various energy sources in the park in real time to provide energy consumption data; Personnel flow data collection unit: including access control system and video surveillance equipment, which are used to record the entry and exit time, number and flow path of personnel in the park to provide personnel flow data; Data aggregation and transmission unit: used to aggregate the real-time data from the environmental data collection unit, the energy consumption data collection unit and the personnel flow data collection unit, and transmit the aggregated data to the data preprocessing module through a wired or wireless communication network.

3. A property management and control system for a smart park according to claim 1, characterized in that: The data preprocessing module includes a data cleaning unit, a denoising processing unit, a standardization processing unit and a data integration unit; wherein: Data cleaning unit: used to clean the environmental data, energy consumption data and personnel flow information collected by the information collection module, using a data cleaning algorithm based on the threshold method, by setting the threshold, and then automatically identifying and eliminating data points that do not meet the predetermined range; De-noising unit: used to perform denoising on the cleaned data. It uses the median filtering algorithm to sort the neighborhood data around each data point, and takes the sorted median as the denoising value of the data point to reduce the impact of random noise. Standardization processing unit: used to standardize the denoised data, using the Z-score standardization method to normalize the mean of each data point to 0 and the standard deviation to 1; Data integration unit: used to integrate the processed environmental data, energy consumption data and personnel flow information to generate a comprehensive processed data set.

4. The property management system of a smart park according to claim 1, characterized in that: The feature extraction module includes an environmental parameter fluctuation pattern extraction unit, an energy usage peak and valley pattern extraction unit, and a personnel flow high-frequency area extraction unit; wherein: Environmental parameter fluctuation pattern extraction unit: used to extract environmental parameter fluctuation patterns from the processed environmental data set, use Fourier transform method to analyze the change trend of environmental temperature and humidity over time, calculate the spectrum of data, and identify the fluctuation period; Energy usage peak and valley pattern extraction unit: used to extract the peak and valley pattern of energy usage from the processed energy consumption data set, by calculating the peak and valley values ​​of the energy consumption data and analyzing its changing trend using the sliding window method, to identify the peak and valley periods of energy usage; Personnel flow high-frequency area extraction unit: used to extract high-frequency areas from the processed personnel flow data, by counting the frequency of personnel in each area, using the K-means clustering algorithm to divide the park into multiple areas, and identify high-frequency areas with dense personnel flow.

5. A property management and control system for a smart park according to claim 4, characterized in that: The personnel flow high-frequency area extraction unit comprises: Data preprocessing: Based on the personnel flow data collected by the information collection module, a data matrix is ​​constructed, in which each row represents the personnel flow information at a moment, and each column represents the number of personnel at different locations in the park; Initialize cluster centers: randomly select k initial cluster centers and use them as the initial representatives of each region; Assign data points: Assign each data point to the nearest cluster center according to the Euclidean distance formula; Update cluster centers: Calculate the new location of each cluster center based on the assigned data points, i.e. the average personnel flow data of the area; Iterate until convergence: Repeat the above steps until the cluster center no longer changes; Identify high-frequency areas: Analyze the regional density of each cluster through clustering results, that is, calculate the frequency of personnel flow in each area, and select the area with the highest flow frequency as the high-frequency area.

6. The property management system of a smart park according to claim 1, characterized in that: The prediction analysis module includes a data analysis unit, a prediction model unit and a comprehensive prediction report generation unit; wherein: Data analysis unit: Use multivariate regression analysis to conduct correlation analysis on the fluctuation patterns of environmental parameters, the peak and valley patterns of energy use, and the characteristics of high-frequency areas of personnel flow, and establish a mathematical model between environmental changes, energy consumption, and personnel flow; Prediction model unit: Based on the mathematical model established by the data analysis unit, it predicts the environmental change trend, energy consumption change and personnel flow change of the park in the future; Comprehensive forecast report generation unit: used to summarize the forecast results generated by the forecast model unit, present the forecast results of environmental change trends, energy consumption changes and personnel flow changes in the form of charts and text descriptions, and generate a comprehensive forecast report.

7. A property management and control system for a smart park according to claim 6, characterized in that: The data analysis unit comprises: Data preprocessing: Standardize the input environmental parameter fluctuation patterns, energy usage peak and valley patterns, and high-frequency regional characteristics of personnel flow to ensure that each feature has the same dimension and value range; Correlation analysis: By calculating the correlation coefficient matrix between each feature, the relationship between the environmental parameter fluctuation pattern, the peak and valley pattern of energy use and the high-frequency area of ​​personnel flow is analyzed, and the Pearson correlation coefficient is calculated as a linear correlation measure between the features; Regression analysis: Use multivariate regression analysis to establish a mathematical model between environmental changes, energy consumption and personnel flow, and use the least squares method to perform regression and fit the relationship between multiple variables. The mathematical expression of this mathematical model is: Y = β0 + β1X1 + β2X2 + … + β j X j +∈, where Y is the predicted output variable, X1,X2,…,X j is the input feature variable, β0 is a constant term, β1,β2,…,β j is the regression coefficient, ∈ is the error term; Model optimization: Based on the mathematical model obtained by regression analysis, the regression coefficient is optimized and the gradient descent method is used to reduce the prediction error. The formula for updating the regression coefficient by the gradient descent method is: Among them, β j is the jth regression coefficient, α is the learning rate, is the loss function J(β) versus the regression coefficient β j The partial derivative of , which indicates the influence of the regression coefficient on the loss function.

8. The property management system of a smart park according to claim 1, characterized in that: The decision optimization module includes an environmental adjustment strategy formulation unit, an energy allocation strategy formulation unit and a personnel flow management plan formulation unit; wherein: Environmental regulation strategy formulation unit: Based on the environmental change trend forecast report generated by the forecast analysis module and the current environmental resource status of the park, the linear programming algorithm is used to optimize the operation strategy of air conditioning, heating and ventilation equipment to achieve environmental comfort and efficient energy utilization in the park; Energy distribution strategy formulation unit: Based on the energy consumption change forecast report generated by the forecast analysis module and combined with the current energy supply and demand conditions of the park, a genetic algorithm is used to optimize the energy distribution plan to ensure the stable energy supply of various equipment and facilities; Personnel flow management plan formulation unit: Based on the personnel flow change forecast report generated by the forecast analysis module and the current human resource configuration of the park, the integer programming algorithm is used to optimize the personnel flow path and configuration.

9. A property management and control system for a smart park according to claim 8, characterized in that: The personnel flow management plan formulation unit includes: Define flow paths and personnel: Divide all areas in the park into multiple flow paths, each path corresponds to a group of personnel. Assuming there are g flow paths, define the flow of personnel on each path as y i , i=1,2,…,g; Objective function setting: Set the objective function to maximize the efficiency of personnel flow. The formula is: Among them, W is the total staff turnover efficiency, p i is the efficiency coefficient of the i-th flow path, y i Assign the number of people to the i-th flow path, with the goal of maximizing the total flow efficiency; Constraint setting: Set the constraints on the flow of personnel to ensure that the number of people on each path does not exceed the maximum load of the path, and the total number of people does not exceed the number of people that can be allocated in the park; specifically, let P be the total number of people in the park, P max,i is the maximum load of the i-th flow path, then the constraint condition is: Integer programming solution: The above objective function and constraints are solved by the integer programming algorithm to obtain the optimal personnel allocation for each flow path, thereby determining the optimal personnel flow path and configuration plan.

10. A property management method for a smart park, implemented by a property management system for a smart park according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Install various sensors and smart devices in the park to collect real-time environmental data, energy consumption data and personnel flow data in the park; S2: Preprocess the environmental data, energy consumption data and personnel flow data collected by S1, using cleaning, denoising and standardization to generate a processed data set; S3: Extract relevant features from the processed data set, including environmental parameter fluctuation patterns, peak and valley patterns of energy use, and high-frequency areas of personnel flow; S4: Use multivariate regression analysis to conduct correlation analysis on the extracted relevant features and establish a mathematical model between environmental changes, energy consumption and personnel flow; S5: Based on the mathematical model established in S4, predict the environmental change trend, energy consumption change and personnel flow change of the park in the future, and generate a forecast report; S6: Based on the forecast report in S5, combined with the current resource status and management objectives of the park, an optimization algorithm is used to formulate a property management strategy, including an environmental adjustment plan, an energy allocation strategy, and a personnel flow management plan.

Images