Internet of Things ecological smart space management system based on open standard

Abstract

The invention relates to the technical field of intelligent control, in particular to an internet of things ecological intelligent space management system based on an open standard, which comprises a sensing module, a data preprocessing module, a data analysis module, a rule engine module, an optimization algorithm module and a control module, wherein the sensing module is used for collecting environmental data in a smart space; the data preprocessing module is used for carrying out data preprocessing on the environment data; the data analysis module is used for identifying an environment change rule and a potential abnormal condition; the rule engine module is used for generating rule constraint conditions; and the optimization algorithm module is used for generating a space management strategy. According to the invention, by integrating the Internet of Things technology and the optimization algorithm, intelligent acquisition, analysis and dynamic adjustment of the environmental data in the smart space are realized, the energy efficiency, the comfort level and the resource utilization efficiency are optimized, the automation level of space management is significantly improved, the energy consumption is reduced, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an Internet of Things ecological smart space management system based on open standards. Background Art

[0002] With the continuous development of Internet of Things technology, the application scenarios of smart space are becoming increasingly extensive. Smart space uses sensors, Internet of Things devices and cloud computing technology to collect and analyze environmental data in real time to achieve automatic adjustment and management of the environment within the space. For example, in homes, offices, commercial buildings and other places, the comfort and energy efficiency of the space are improved through intelligent temperature control, lighting control, air conditioning adjustment and other measures. However, the existing smart space management systems generally have the problems of dispersion, limitation and high energy consumption in the collection, analysis and equipment control of environmental data. These systems usually use independent sensors and devices and lack a unified management framework, resulting in low resource utilization efficiency, difficulty in balancing comfort, excessive energy consumption, and difficulty in coping with complex environmental changes.

[0003] Although existing technologies provide basic intelligent control capabilities in certain specific scenarios, existing smart space management systems still face the following problems: First, most systems fail to effectively integrate data sharing and collaboration between IoT devices during data collection and processing, resulting in slow response speeds for decision-making and control; second, existing systems lack optimization solutions for multiple goals such as energy efficiency, comfort, and resource utilization during intelligent control, and are unable to dynamically adjust management strategies based on actual environmental changes; third, most existing systems rely on a single rule, lack sufficient flexibility and adaptability, and are difficult to cope with changing external environments and user needs. Therefore, there is an urgent need for an IoT ecological smart space management system based on open standards to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides an IoT ecological smart space management system based on open standards.

[0005] The IoT ecological smart space management system based on open standards includes a perception module, a data preprocessing module, a data analysis module, a rule engine module, an optimization algorithm module and a control module; among which: Perception module: used to collect environmental data in the smart space in real time through IoT sensors, including temperature, humidity and light intensity; Data preprocessing module: used to receive environmental data transmitted by the perception module and perform data preprocessing, including denoising, filtering and normalization, to generate standardized data; Data analysis module: used to perform statistical analysis and pattern recognition on the standardized data generated by the data preprocessing module, and identify the laws of environmental changes and potential abnormalities; Rule engine module: used to generate rule constraints based on preset space management rules and combined with the analysis results of the data analysis module; Optimization algorithm module: Based on the rule constraints provided by the rule engine module and the analysis results of the data analysis module, the optimization algorithm is applied to comprehensively consider energy consumption, comfort and resource utilization to generate space management strategies; Control module: used to control the start, stop and adjustment of various devices in the smart space according to the space management strategy provided by the decision module.

[0006] Optionally, the perception module includes a sensor interface unit, a data acquisition unit and a data transmission unit; wherein: Sensor interface unit: used to connect various IoT sensors through open standard interfaces, including temperature sensors, humidity sensors, and light sensors; the sensor interface unit exchanges data with the sensors through standardized communication protocols; Data acquisition unit: used to obtain real-time environmental data from various sensors, the environmental data including temperature, humidity and light intensity; Data transmission unit: used to transmit the collected environmental data to the data preprocessing module.

[0007] Optionally, the data preprocessing module includes a denoising unit, a filtering unit, a normalization unit and a data conversion unit; wherein: De-noising unit: used to remove noise from the received environmental data. It uses a moving average filtering algorithm to calculate the average value of multiple consecutive data points to eliminate the random noise generated during the sensor acquisition process. Filtering unit: used to filter the denoised environmental data and screen the data according to the set maximum and minimum value ranges; by checking each data point, the data that exceeds the preset threshold range is eliminated; Normalization unit: used to normalize the filtered environmental data, convert data of different dimensions into a unified standardized range, and use the minimum-maximum normalization method to scale the data to [0, 1] so that different types of data are comparable; Data conversion unit: used to convert the normalized environmental data into JSON format or XML format to ensure the compatibility and consistency of data among various modules of the system.

[0008] Optionally, the data analysis module includes a statistical analysis unit, a pattern recognition unit and an anomaly detection unit; wherein: Statistical analysis unit: used to perform statistical analysis on the standardized data generated by the data preprocessing module, evaluate the distribution characteristics of various environmental data by calculating the basic statistics of the mean, standard deviation and variance of the data, and use time series analysis methods to identify the trend and periodicity of environmental data over time, so as to determine the overall pattern of environmental changes; Pattern recognition unit: used to perform pattern recognition on the environmental data provided by the statistical analysis unit, using the K-means clustering algorithm to divide the environmental data into several different clusters to identify different environmental status patterns, including high temperature or low humidity, to identify the changing rules of the environment; Anomaly detection unit: It is used to identify potential anomalies based on the results of statistical analysis and pattern recognition, and adopts a threshold-based method combined with the mean and standard deviation of the standardized data to determine the detection range of anomalies and automatically mark environmental data that exceeds the normal range.

[0009] Optionally, the statistical analysis unit specifically includes: calculating the mean: used to calculate the mean of the environmental data, the formula is: ,in, is the mean of the environmental data, is the number of environmental data points, For the The value of each environmental data point; Calculate standard deviation: used to calculate the standard deviation of environmental data. The standard deviation calculation formula is: in, is the standard deviation of the environmental data, For the Environmental data points, is the mean; Calculate variance: used to calculate the variance of environmental data. The variance is the square of the standard deviation. The expression is: ,in, is the variance of the environmental data, is the standard deviation of environmental data; Time series analysis: An autoregressive moving average model is used to identify trends and periodic patterns in environmental data over time.

[0010] Optionally, the pattern recognition unit specifically includes: an initialization step: selecting K cluster center points, denoted as , where K is the preset number of clusters, and each cluster center point Indicates the center position of the Kth cluster; Assignment step: For each environmental data point , calculate its correlation with all cluster centers The Euclidean distance between the environmental data points Assign to the cluster center with the smallest distance ; Update step: After all environmental data points are assigned, update the centroid of each cluster and set the new cluster center to , the formula is: ,in: is the new centroid of the Kth cluster; is the number of data points in the Kth cluster; is the first Environmental data points; Convergence judgment step: repeat the above allocation step and update step until the predetermined convergence condition is reached; Convergence condition 1: The change in the centroid position is less than the preset threshold ; Convergence condition 2: reaching the preset maximum number of iterations T.

[0011] Optionally, the anomaly detection unit includes: threshold setting: for setting the mean of the standardized environmental data provided by the statistical analysis unit and standard deviation , set the upper and lower thresholds for abnormal detection. The calculation formula for the upper and lower thresholds is: Upper threshold ; Lower threshold ,in, is the preset threshold multiplier coefficient; Outlier Identification: It is used to identify outliers in standardized environmental data and determine whether a data point is an outlier based on the following conditions: The upper threshold, or Lower threshold, then mark is an outlier, among which For the standardized environmental data points.

[0012] Optionally, the rule engine module includes a rule parsing unit and a rule matching unit; wherein: the rule parsing unit is used to parse preset space management rules, and the space management rules include: Rule 1: Temperature control rule, which stipulates that the temperature in the smart space should be maintained between 18°C ​​and 26°C; Rule 2: Humidity control rule, which stipulates that the humidity in the smart space should be maintained between 30% and 60%; Rule 3: Light intensity control rule, which stipulates that the light intensity in the smart space should be maintained between 200 lux and 800 lux; The rule parsing unit parses the above rules into computable rule constraints, including: Constraint 1: The temperature constraint is expressed as: ,in, Indicates the temperature in the smart space; Constraint 2: The humidity constraint is expressed as: ,in, Indicates the humidity in the smart space; Constraints: The light intensity constraint is expressed as: ,in, Indicates the light intensity in the smart space; Rule matching unit: used to make matching judgments based on the environmental data analysis results provided by the data analysis module and the rule constraints generated by the rule parsing unit to determine whether the current environmental status meets the preset rules.

[0013] Optionally, the optimization algorithm module includes an energy consumption optimization unit, a comfort optimization unit, a resource utilization optimization unit and a strategy generation unit; wherein: the energy consumption optimization unit is used to calculate the energy consumption of each device under the current environmental state, and use a linear programming algorithm to minimize the overall energy consumption, and its optimization objective function is expressed as: , where E represents the total energy consumption; is the total number of devices; is the unit energy consumption coefficient of the Kth device; is the operating status of the Kth device; Comfort optimization unit: used to optimize the comfort of the space, using a multi-objective optimization algorithm, the optimization goal is to maximize the overall comfort score, the objective function expression is: ,in, Indicates the overall comfort rating; , , represent the comfort scores of temperature, humidity and light intensity respectively; , , The weight coefficient for each comfort score; Resource utilization optimization unit: used to optimize the utilization of resources in the space, using integer programming algorithm to maximize the utilization efficiency of resources. Its optimization objective function is expressed as: ,in, Indicates the total resource utilization; For the The utilization efficiency coefficient of each resource; For the The usage status of a resource; Strategy generation unit: It is used to synthesize the output results of each optimization unit and generate the final space management strategy by weighted synthesis. The comprehensive formula is expressed as: ,in, Indicates the final generated space management strategy; Minimized energy consumption results for energy consumption optimization units; The maximum comfort score result of the comfort optimization unit; A maximized resource utilization result for a resource utilization optimization unit; , , is the weight coefficient of each optimization objective.

[0014] Optionally, the control module includes a device control unit and a communication interface unit; wherein: Equipment control unit: used to generate and send control instructions to various devices in the smart space according to the space management strategy provided by the optimization algorithm module; Communication interface unit: Supporting multiple communication protocols, including Wi-Fi, Zigbee and Bluetooth, the communication interface unit ensures accurate transmission of control instructions by communicating with various devices.

[0015] Beneficial effects of the present invention: The present invention realizes comprehensive monitoring and dynamic adjustment of the environment in the smart space by integrating a perception module, a data preprocessing module, a data analysis module, a rule engine module, an optimization algorithm module and a control module. Compared with the prior art, it can more efficiently collect and process environmental data in the space, and grasp the changes in temperature, humidity, light and other aspects in the space in real time, providing an accurate basis for subsequent data analysis and decision-making. Through intelligent data processing and analysis, the automation level of space management is significantly improved, and the need for human intervention is reduced.

[0016] The present invention combines multiple objectives such as energy efficiency, comfort and resource utilization through an optimization algorithm module. It can dynamically adjust the space management strategy according to different environmental conditions and user needs, fully optimize energy consumption and resource allocation, thereby effectively reducing overall energy consumption, while improving the comfort and resource utilization of the space; in addition, the design of the control module ensures that various types of equipment can be precisely controlled according to the optimization strategy, whether it is temperature control equipment, lighting system or air conditioning equipment, all can achieve optimal performance through intelligent adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 This is a schematic diagram of an IoT ecological smart space management system according to an embodiment of the present invention; Figure 2 Schematic diagram of a data analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] like Figure 1-Figure 2 As shown, the IoT ecological smart space management system based on open standards includes a perception module, a data preprocessing module, a data analysis module, a rule engine module, an optimization algorithm module and a control module; among which: Perception module: used to collect environmental data in the smart space in real time through IoT sensors, including temperature, humidity and light intensity; Data preprocessing module: used to receive environmental data transmitted by the perception module and perform data preprocessing, including denoising, filtering and normalization, to generate standardized data; Data analysis module: used to perform statistical analysis and pattern recognition on the standardized data generated by the data preprocessing module, and identify the laws of environmental changes and potential abnormalities; Rule engine module: used to generate rule constraints based on preset space management rules and combined with the analysis results of the data analysis module; Optimization algorithm module: Based on the rule constraints provided by the rule engine module and the analysis results of the data analysis module, the optimization algorithm is applied to comprehensively consider energy consumption, comfort and resource utilization to generate space management strategies; Control module: used to control the start, stop and adjustment of various devices in the smart space according to the space management strategy provided by the decision module.

[0021] The perception module includes a sensor interface unit, a data acquisition unit and a data transmission unit; wherein: Sensor interface unit: used to connect various IoT sensors through open standard interfaces, including temperature sensors, humidity sensors and light sensors; the sensor interface unit exchanges data with the sensors through standardized communication protocols to ensure real-time transmission and accuracy of data; Data acquisition unit: used to obtain real-time environmental data from various sensors, including temperature, humidity and light intensity; this unit collects data regularly or on demand to ensure real-time update of environmental information in the smart space; Data transmission unit: used to transmit the collected environmental data to the data preprocessing module to ensure that the data is processed correctly in the next step according to the standardized format; through the design of the above-mentioned perception module, the system can accurately and stably collect various environmental data in the smart space in real time, and communicate and exchange data efficiently with sensors through standardized interfaces, ensuring the accuracy and reliability of the data, and providing high-quality original data for subsequent data preprocessing.

[0022] The data preprocessing module includes a denoising unit, a filtering unit, a normalization unit and a data conversion unit; wherein: De-noising unit: used to remove noise from the received environmental data. It uses a moving average filtering algorithm to calculate the average value of multiple consecutive data points to eliminate the random noise generated during the sensor acquisition process, ensuring the purity and accuracy of the data. Filtering unit: used to filter the denoised environmental data and screen the data according to the set maximum and minimum value ranges; by checking each data point, the data that exceeds the preset threshold range is eliminated to ensure that only valid data enters the next step of processing; for example, when the temperature data exceeds the valid range of -40℃ to 80℃, the data will be discarded to eliminate the impact of equipment failure or environmental abnormalities; Normalization unit: used to normalize the filtered environmental data, convert data of different dimensions (such as temperature, humidity, and light intensity) into a unified standardized range, and use the minimum-maximum normalization method to scale the data to [0, 1] to make different types of data comparable, thereby reducing the impact of dimensional differences between data; Data conversion unit: used to convert the normalized environmental data into JSON format or XML format to ensure the compatibility and consistency of data among various modules of the system. This unit parses each data field to generate a structured data format containing information such as timestamp, data type, data value, etc., to ensure seamless connection of subsequent data transmission and processing processes. Through the design of the above-mentioned data preprocessing module, the system can efficiently and accurately denoise, filter and normalize the environmental data collected by the perception module to generate high-quality standardized data, providing a reliable data foundation for subsequent data analysis and optimization decisions.

[0023] The data analysis module includes a statistical analysis unit, a pattern recognition unit and an anomaly detection unit; wherein: Statistical analysis unit: used to perform statistical analysis on the standardized data generated by the data preprocessing module, evaluate the distribution characteristics of various environmental data by calculating the basic statistics of the mean, standard deviation and variance of the data, and use time series analysis methods to identify the trend and periodicity of environmental data over time, so as to determine the overall pattern of environmental changes; Pattern recognition unit: used to perform pattern recognition on the environmental data provided by the statistical analysis unit, using the K-means clustering algorithm to divide the environmental data into several different clusters to identify different environmental status patterns, including high temperature or low humidity, to identify the changing rules of the environment; Anomaly detection unit: used to identify potential anomalies based on the results of statistical analysis and pattern recognition, using a threshold-based method combined with the mean and standard deviation of standardized data to determine the detection range of anomalies, and automatically mark environmental data that exceeds the normal range for subsequent processing; through the design of the above data analysis module, the system can efficiently perform statistical analysis and pattern recognition on the data, accurately identify the laws of environmental changes and potential anomalies; through time series analysis and K-means clustering algorithm and other technologies, the system can capture the long-term change trend of the environment, identify different environmental patterns, and detect abnormal changes in a timely manner, providing reliable data support for subsequent optimization algorithms and control modules.

[0024] The statistical analysis unit specifically includes: Calculate mean: Used to calculate the mean (average) of environmental data. The formula is: ,in, is the mean of the environmental data, is the number of environmental data points, For the The values ​​of environmental data points (including temperature, humidity, light intensity, etc.); Calculate standard deviation: used to calculate the standard deviation of environmental data. The standard deviation calculation formula is: in, is the standard deviation of the environmental data, For the Environmental data points, is the mean; the standard deviation calculation unit calculates the data fluctuation range through this formula to reflect the stability or volatility of environmental data; Calculate variance: used to calculate the variance of environmental data. The variance is the square of the standard deviation. The expression is: ,in, is the variance of the environmental data, is the standard deviation of the environmental data; the variance calculation unit provides further fluctuation assessment for the environmental data through this formula; Time series analysis: The autoregressive moving average (ARMA) model is used to identify the trend and periodicity of environmental data over time. The expression of the autoregressive moving average model is: ,in, For time Environmental data at all times (temperature, humidity, light, etc.), is the autoregression coefficient, is the moving average coefficient, is the white noise error term, and They are the autoregressive order and the moving average order respectively. The model identifies the changing trend and periodicity of environmental data through regression analysis of historical environmental data, providing a basis for subsequent analysis of the system. Through the design of the above-mentioned statistical analysis unit, the mean, standard deviation and variance of environmental data can be accurately calculated, providing basic data support for subsequent pattern recognition and anomaly detection. At the same time, combined with the time series analysis method, the system can accurately identify the trend and periodicity of environmental data over time, which helps to capture the changing patterns of the environment in the long and short term and provide a scientific basis for smart space management.

[0025] The pattern recognition unit specifically includes: Initialization step: Select K cluster centers (centroids), denoted as , where K is the preset number of clusters, and each cluster center point Indicates the center position of the Kth cluster, which can be randomly selected during initialization data points as initial centroids, or selected by some heuristic method; Assignment step: For each environmental data point , calculate its relationship with all cluster centers The Euclidean distance between them is: in, For the Environmental data points With Cluster Centers The distance between is the number of characteristics of environmental data (e.g., temperature, humidity, light intensity); For the The environmental data point is in is the value of the feature; is the value of the cluster center on the feature; and the environmental data point Assign to the cluster center with the smallest distance ,Right now: ; Update step: After all environmental data points are assigned, update the centroid of each cluster and set the new cluster center to , obtained by calculating the mean value of all data points in the cluster, the formula is: ,in: is the new centroid of the Kth cluster; is the number of data points in the Kth cluster; is the first Environmental data points; Convergence judgment step: repeat the above allocation step and update step until the predetermined convergence condition is reached; Convergence condition 1: The change in the centroid position is less than the preset threshold ; Convergence condition 2, reaching the preset maximum number of iterations T. Through the above-mentioned K-means clustering algorithm, the pattern recognition unit can effectively divide the environmental data into several different clusters, so as to accurately identify different environmental state patterns; the Euclidean distance calculation ensures the precise matching of data points and cluster centers, the mean update step ensures the reasonable adjustment of cluster centers, and the convergence judgment ensures the stability and efficiency of the algorithm; these technical means jointly improve the accuracy and responsiveness of the system in environmental monitoring, and provide solid data support for subsequent anomaly detection and optimization decisions.

[0026] The anomaly detection unit includes: Threshold setting: used to set the mean of the standardized environmental data provided by the statistical analysis unit and standard deviation , set the upper and lower thresholds for abnormal detection. The calculation formula for the upper and lower thresholds is: Upper threshold ; Lower threshold ,in, It is a preset threshold multiplier coefficient used to adjust the sensitivity of anomaly detection; Outlier Identification: It is used to identify outliers in standardized environmental data and determine whether a data point is an outlier based on the following conditions: The upper threshold, or Lower threshold, then mark is an outlier, among which For the standardized environmental data points (such as temperature, humidity, light intensity, etc.); through the design of the above-mentioned anomaly detection unit, it is possible to accurately identify abnormal values ​​beyond the normal range based on the mean and standard deviation of the standardized data combined with the set upper and lower thresholds. This method helps to detect and handle abnormal situations in a timely manner.

[0027] The rule engine module includes a rule parsing unit and a rule matching unit; wherein: Rule parsing unit: used to parse preset space management rules. Space management rules include: Rule 1: Temperature control rule, which stipulates that the temperature in the smart space should be maintained between 18°C ​​and 26°C; Rule 2: Humidity control rule, which stipulates that the humidity in the smart space should be maintained between 30% and 60%; Rule 3: Light intensity control rule, which stipulates that the light intensity in the smart space should be maintained between 200 lux and 800 lux; The rule parsing unit parses the above rules into computable rule constraints, including: Constraint 1: The temperature constraint is expressed as: ,in, Indicates the temperature in the smart space; Constraint 2: The humidity constraint is expressed as: ,in, Indicates the humidity in the smart space; Constraints: The light intensity constraint is expressed as: ,in, Indicates the light intensity in the smart space (unit: lux); Rule matching unit: used to make matching judgments based on the environmental data analysis results provided by the data analysis module and the rule constraints generated by the rule parsing unit to determine whether the current environmental status meets the preset rules; through the design of the above units, the rule engine module can evaluate the current environmental status in real time and generate corresponding space management decisions based on the rule constraints.

[0028] The optimization algorithm module includes energy consumption optimization unit, comfort optimization unit, resource utilization optimization unit and strategy generation unit; among which: Energy consumption optimization unit: used to calculate the energy consumption of each device under the current environmental state, and use linear programming algorithm to minimize the overall energy consumption. The optimization objective function is expressed as: , where E represents the total energy consumption; is the total number of devices; is the unit energy consumption coefficient of the Kth device; is the operating state of the Kth device (on = 1, off = 0); through this objective function, the overall energy consumption is minimized while satisfying other constraints; Comfort optimization unit: used to optimize the comfort of the space, using a multi-objective optimization algorithm, the optimization goal is to maximize the overall comfort score, the objective function expression is: ,in, Indicates the overall comfort rating; , , represent the comfort scores of temperature, humidity and light intensity respectively; , , is the weight coefficient of each comfort score; ; The comfort optimization unit maximizes the overall comfort score through this formula while satisfying other constraints; Resource utilization optimization unit: used to optimize the utilization of resources in the space, using integer programming algorithm to maximize the utilization efficiency of resources. Its optimization objective function is expressed as: ,in, Indicates the total resource utilization; For the The utilization efficiency coefficient of each resource; For the The resource utilization optimization unit uses this formula to maximize the resource utilization efficiency while satisfying other constraints. Strategy generation unit: It is used to synthesize the output results of each optimization unit and generate the final space management strategy by weighted synthesis. The comprehensive formula is expressed as: ,in, Indicates the final generated space management strategy; Minimized energy consumption results for energy consumption optimization units; The maximum comfort score result of the comfort optimization unit; A maximized resource utilization result for a resource utilization optimization unit; , , is the weight coefficient of each optimization objective, satisfying ; Through this formula, energy consumption, comfort and resource utilization are comprehensively considered to generate the optimal space management strategy; through the design of the above-mentioned optimization algorithm module, the system can apply optimization algorithms such as linear programming, multi-objective optimization and integer programming on the basis of the rule constraints provided by the rule engine module and the analysis results of the data analysis module, and comprehensively consider energy consumption, comfort and resource utilization to generate the optimal space management strategy.

[0029] The control module includes a device control unit and a communication interface unit; wherein: Equipment control unit: used to generate and send control instructions to various devices in the smart space according to the space management strategy provided by the optimization algorithm module; Communication interface unit: supports multiple communication protocols, including Wi-Fi, Zigbee and Bluetooth. The communication interface unit communicates with various devices to ensure the accurate transmission of control instructions. Through the design of the above control module, the system can accurately generate and send control instructions to various devices in the smart space according to the space management strategy generated by the optimization algorithm module, thereby realizing automatic start and stop and parameter adjustment of the equipment.

[0030] 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.

[0031] 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. An IoT ecological smart space management system based on open standards, characterized by: It includes a perception module, a data preprocessing module, a data analysis module, a rule engine module, an optimization algorithm module and a control module; among which: Perception module: used to collect environmental data in the smart space in real time through IoT sensors, including temperature, humidity and light intensity; Data preprocessing module: used to receive environmental data transmitted by the perception module and perform data preprocessing, including denoising, filtering and normalization, to generate standardized data; Data analysis module: used to perform statistical analysis and pattern recognition on the standardized data generated by the data preprocessing module, and identify the laws of environmental changes and potential abnormalities; Rule engine module: used to generate rule constraints based on preset space management rules and combined with the analysis results of the data analysis module; The rule engine module includes a rule parsing unit and a rule matching unit; wherein: Rule parsing unit: used to parse preset space management rules and parse the space management rules into corresponding rule constraints; Rule matching unit: performs matching judgment based on the rule constraints generated by the rule parsing unit; Optimization algorithm module: Based on the rule constraints provided by the rule engine module and the analysis results of the data analysis module, the optimization algorithm is applied to comprehensively consider energy consumption, comfort and resource utilization to generate space management strategies; Control module: used to control the start, stop and adjustment of various devices in the smart space according to the space management strategy provided by the decision module.

2. The open standard-based IoT ecological smart space management system according to claim 1 is characterized in that: The perception module includes a sensor interface unit, a data acquisition unit and a data transmission unit; wherein: Sensor interface unit: used to connect various IoT sensors through open standard interfaces, including temperature sensors, humidity sensors, and light sensors; the sensor interface unit exchanges data with the sensors through standardized communication protocols; Data acquisition unit: used to obtain real-time environmental data from various sensors, the environmental data including temperature, humidity and light intensity; Data transmission unit: used to transmit the collected environmental data to the data preprocessing module.

3. The open standard-based IoT ecological smart space management system according to claim 1 is characterized in that: The data preprocessing module includes a denoising unit, a filtering unit, a normalization unit and a data conversion unit; wherein: De-noising unit: used to remove noise from the received environmental data. It uses a moving average filtering algorithm to calculate the average value of multiple consecutive data points to eliminate the random noise generated during the sensor acquisition process. Filtering unit: used to filter the denoised environmental data and screen the data according to the set maximum and minimum value ranges; by checking each data point, the data that exceeds the preset threshold range is eliminated; Normalization unit: used to normalize the filtered environmental data, convert data of different dimensions into a unified standardized range, and use the minimum-maximum normalization method to scale the data to [0, 1] so that different types of data are comparable; Data conversion unit: used to convert the normalized environmental data into JSON format or XML format to ensure the compatibility and consistency of data among various modules of the system.

4. The open standard-based IoT ecological smart space management system according to claim 1 is characterized in that: The data analysis module includes a statistical analysis unit, a pattern recognition unit and an anomaly detection unit; wherein: Statistical analysis unit: used to perform statistical analysis on the standardized data generated by the data preprocessing module, evaluate the distribution characteristics of various environmental data by calculating the basic statistics of the mean, standard deviation and variance of the data, and use time series analysis methods to identify the trend and periodicity of environmental data over time, so as to determine the overall pattern of environmental changes; Pattern recognition unit: used to perform pattern recognition on the environmental data provided by the statistical analysis unit, using the K-means clustering algorithm to divide the environmental data into several different clusters to identify different environmental status patterns, including high temperature or low humidity, to identify the changing rules of the environment; Anomaly detection unit: It is used to identify potential anomalies based on the results of statistical analysis and pattern recognition, and adopts a threshold-based method combined with the mean and standard deviation of the standardized data to determine the detection range of anomalies and automatically mark environmental data that exceeds the normal range.

5. The open standard-based IoT ecological smart space management system according to claim 4 is characterized in that: The statistical analysis unit specifically includes: Calculate mean: used to calculate the mean of environmental data. The formula is: ,in, is the mean of the environmental data, is the number of environmental data points, For the The value of each environmental data point; Calculate standard deviation: used to calculate the standard deviation of environmental data. The standard deviation calculation formula is: in, is the standard deviation of the environmental data, For the Environmental data points, is the mean; Calculate variance: used to calculate the variance of environmental data. The variance is the square of the standard deviation. The expression is: ,in, is the variance of the environmental data, is the standard deviation of environmental data; Time series analysis: An autoregressive moving average model is used to identify trends and periodic patterns in environmental data over time.

6. The open standard-based IoT ecological smart space management system according to claim 5 is characterized in that: The pattern recognition unit specifically includes: Initialization step: Select K cluster centers, denoted as , where K is the preset number of clusters, and each cluster center point Indicates the center position of the Kth cluster; Assignment step: For each environmental data point , calculate its relationship with all cluster centers The Euclidean distance between the environmental data points Assign to the cluster center with the smallest distance ; Update step: After all environmental data points are assigned, update the centroid of each cluster and set the new cluster center to , the formula is: ,in: is the new centroid of the Kth cluster; is the number of data points in the Kth cluster; is the first Environmental data points; Convergence judgment step: repeat the above allocation step and update step until the predetermined convergence condition is reached; Convergence condition 1: The change in the centroid position is less than the preset threshold ; Convergence condition 2: reaching the preset maximum number of iterations T.

7. The open standard-based IoT ecological smart space management system according to claim 6 is characterized in that: The abnormality detection unit comprises: Threshold setting: used to set the mean of the standardized environmental data provided by the statistical analysis unit and standard deviation , set the upper and lower thresholds for abnormal detection. The calculation formula for the upper and lower thresholds is: Upper threshold ; Lower threshold ,in, is the preset threshold multiplier coefficient; Outlier Identification: It is used to identify outliers in standardized environmental data and determine whether a data point is an outlier based on the following conditions: The upper threshold, or Lower threshold, then mark is an outlier, among which For the standardized environmental data points.

8. The open standard-based IoT ecological smart space management system according to claim 1 is characterized in that: The space management rules include: Rule 1: Temperature control rule, which stipulates that the temperature in the smart space should be maintained between 18°C ​​and 26°C; Rule 2: Humidity control rule, which stipulates that the humidity in the smart space should be maintained between 30% and 60%; Rule 3: Light intensity control rule, which stipulates that the light intensity in the smart space should be maintained between 200 lux and 800 lux; The rule constraints specifically include: Constraint 1: The temperature constraint is expressed as: ,in, Indicates the temperature in the smart space; Constraint 2: The humidity constraint is expressed as: ,in, Indicates the humidity in the smart space; Constraints: The light intensity constraint is expressed as: ,in, Indicates the light intensity in the smart space; Rule matching unit: used to make matching judgments based on the environmental data analysis results provided by the data analysis module and the rule constraints generated by the rule parsing unit to determine whether the current environmental status meets the preset rules.

9. The open standard-based IoT ecological smart space management system according to claim 1 is characterized in that: The optimization algorithm module includes an energy consumption optimization unit, a comfort optimization unit, a resource utilization optimization unit and a strategy generation unit; wherein: Energy consumption optimization unit: used to calculate the energy consumption of each device under the current environmental state, and use linear programming algorithm to minimize the overall energy consumption. The optimization objective function is expressed as: , where E represents the total energy consumption; is the total number of devices; is the unit energy consumption coefficient of the Kth device; is the operating status of the Kth device; Comfort optimization unit: used to optimize the comfort of the space, using a multi-objective optimization algorithm, the optimization goal is to maximize the overall comfort score, the objective function expression is: ,in, Indicates the overall comfort rating; , , represent the comfort scores of temperature, humidity and light intensity respectively; , , The weight coefficient for each comfort score; Resource utilization optimization unit: used to optimize the utilization of resources in the space, using integer programming algorithm to maximize the utilization efficiency of resources. Its optimization objective function is expressed as: ,in, Indicates the total resource utilization; For the The utilization efficiency coefficient of each resource; For the The usage status of a resource; Strategy generation unit: It is used to synthesize the output results of each optimization unit and generate the final space management strategy by weighted synthesis. The comprehensive formula is expressed as: ,in, Indicates the final generated space management strategy; Minimized energy consumption results for energy consumption optimization units; The maximum comfort score result of the comfort optimization unit; A maximized resource utilization result for a resource utilization optimization unit; , , is the weight coefficient of each optimization objective.

10. The open standard-based IoT ecological smart space management system according to claim 1, characterized in that: The control module includes a device control unit and a communication interface unit; wherein: Equipment control unit: used to generate and send control instructions to various devices in the smart space according to the space management strategy provided by the optimization algorithm module; Communication interface unit: Supporting multiple communication protocols, including Wi-Fi, Zigbee and Bluetooth, the communication interface unit communicates with various devices to ensure accurate transmission of control instructions.

Images