Intelligent Internet of Things home energy management system

Abstract

The invention discloses an intelligent Internet of Things home energy management system, and relates to the technical field of intelligent homes, the system comprises a multi-dimensional data sensing module which uses a sensor and an intelligent equipment interface to collect human physiological data, obtains environment and external data through an environment sensor and a weather API, and sends the environment and external data to a cloud server; historical physiological records, environmental regulation logs and user feedback data are called, timestamps and space coordinate information are added to all kinds of data at the same time, and the data are converted into data vectors and uploaded to a system database; through the multi-dimensional data sensing module, human body physiological data, environmental data and external data can be comprehensively collected, and a physiological state prediction model and a health risk identification model exclusive to a user are constructed in combination with historical records and user feedback, so that the personalized level of health management is improved, and the health risk of the user is improved. And through a chaos embedding biological rhythm prediction formula and a dynamic Bayesian health risk assessment formula, accurate prediction of the physiological state of the user and identification of the health risk are realized.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, specifically to a smart Internet of Things (IoT) home energy management system. Background Technology

[0002] With the rapid development of IoT technology, smart homes, as one of the important application areas of IoT, are gradually changing people's lifestyles. Smart home systems integrate various smart devices, such as sensors, controllers, and actuators, to achieve intelligent control and management of the home environment. Against this backdrop, home energy management systems, as an important component of smart homes, aim to improve energy efficiency by optimizing the operation of home devices, while ensuring user comfort and health and safety. As people's demands for quality of life continue to rise, how to achieve personalized, precise, and intelligent home energy management has become a research hotspot in the current smart home field.

[0003] A smart home energy management method based on the Internet of Things (IoT), application number 202410008292.7, achieves multi-dimensional judgment of energy consumption of smart home devices through comprehensive energy assessment value comparison. However, this method mainly focuses on the management and optimization of energy consumption itself, lacking linkage analysis of user physiological state, health risks, and home environment. In terms of data collection dimensions, it does not cover human physiological data (such as heart rate, body temperature, and sleep stage) and external environmental data (such as weather information and air quality), making it difficult to build a personalized health model for users. In terms of functional implementation, it does not involve the proactive identification and intervention of health risks, and cannot dynamically adjust home environment parameters according to the user's real-time physiological state to achieve the goal of improving health benefits. In addition, this method does not establish a correlation mechanism between environmental regulation and health risks, and cannot achieve efficient energy utilization while ensuring user health. It has obvious deficiencies in terms of intelligent and personalized health management.

[0004] Therefore, developing an intelligent IoT home energy management system can greatly improve the intelligence level of smart home systems and provide users with a more comfortable, healthy, and energy-efficient living environment. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an intelligent Internet of Things (IoT) home energy management system. This system achieves personalized, precise, and intelligent management of the home environment through five modules: multi-dimensional data perception, biorhythm modeling, predictive optimization decision-making, intelligent execution feedback, and health risk response. The system comprehensively collects and analyzes user physiological, environmental, and external data, builds exclusive predictive models, automatically adjusts home equipment to optimize comfort and health benefits, and effectively addresses health risks.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent Internet of Things (IoT) home energy management system, the system comprising: Multidimensional data perception module: used to collect human physiological data using sensor and smart device interfaces, obtain environmental and external data through environmental sensors and weather API, retrieve historical data: physiological records, environmental regulation logs and user feedback data, add timestamps and spatial coordinate information to various types of data, and convert the data into data vectors and upload them to the system database; Biorhythm Modeling Module: Based on the data collected by the multidimensional data perception module, it uses chaotic embedding biorhythm prediction formula to build a user-specific physiological state prediction model, and at the same time, it uses dynamic Bayesian health risk assessment formula to build a health risk identification model. Predictive optimization decision module: It is used to input real-time collected data into the biorhythm prediction model, calculate the prediction results of the user's future physiological state, calculate the comfort level in combination with the current environmental parameters, construct a multi-objective function by combining energy consumption and health benefits, and then combine the environmental regulation rule library to solve the optimal environmental regulation parameter vector using the particle swarm optimization algorithm to generate pre-regulation strategy instructions; The intelligent execution feedback module is used to receive pre-adjustment strategy instructions, control home devices to perform adjustment operations through smart home protocols, and collect device operating status and user physiological feedback data in real time, and transmit the data to the health risk response module. Health Risk Response Module: This module receives data from the intelligent execution feedback module, calculates the health risk probability using the health risk identification model, combines the risk probability with the intervention strategy library to generate intervention instructions, and then feeds them back to the intelligent execution feedback module.

[0007] Furthermore, the methods for collecting human physiological data, environmental data, external data, and historical data in the multidimensional data perception module are as follows: Human physiological data collection: Millimeter-wave radar sensors are deployed at the head of the bed to collect heart rate and respiratory rate data; infrared thermal imaging sensors are installed on the ceiling to obtain human body surface temperature distribution data; user movement data and sleep stage data are synchronized through smart device interfaces and smart bracelets; pressure sensor arrays are built into mattresses and / or sofas to capture body movement amplitude and frequency data; Environmental data collection: Temperature and humidity sensors are deployed in different areas of the room to collect ambient temperature and humidity data; air quality sensors, including PM2.5 sensors, PM10 sensors and VOC gas sensors, are installed to detect the concentration of particulate matter and volatile organic compounds in the air; light sensors are deployed to obtain indoor light intensity data; External data collection: Obtain external weather information hourly via the weather API interface, including current temperature, humidity, wind speed, wind direction, and weather forecast for the next 24 hours; Historical data collection: Retrieve users' past physiological records from local databases and cloud storage, including data on historical heart rate and body temperature fluctuation curves, obtain environmental adjustment logs, including information on the adjustment time, adjustment parameters, and runtime of each air conditioner and light adjustment, and extract feedback data on user manual intervention.

[0008] Furthermore, the multidimensional data perception module describes converting data into data vectors using a spatiotemporal correlation data fusion algorithm. Let physiological data be... Environmental data is External data is Integrate into a three-dimensional tensor Each data point is accompanied by a timestamp and spatial coordinates. Information, the fused data vector is The calculation formula is: ,in To fuse the weights, a dynamic attention mechanism is used for calculation, and the formula is as follows: ,in, It is the j-th feature of the i-th data type. These correspond to physiological, environmental, and external data, respectively. For feature number, It is a three-dimensional tensor that integrates physiological, environmental, and external data. These are spatial coordinates. It is the number of features of the i-th type of data. It is the total number of features participating in the integration. , It is a weight matrix used for calculation in dynamic attention mechanisms. , Bias vector, used for dynamic attention mechanism computation. It is the Hadamard product, which is the element-wise multiplication of matrices. Linear rectifier function, It is a natural exponential function.

[0009] Furthermore, the specific steps in the biorhythm modeling module for constructing a user-specific physiological state prediction model using chaotic embedding of biorhythm prediction formulas are as follows: Based on phase space reconstruction theory, the fused data... Embedded Construct delayed coordinate vectors in phase space. The formula is: Construct a chaotic time series prediction model, with the following formula: ,in, It is time. It is a time delay parameter. It is the phase space dimension. It is the predicted time interval. It is the number of kernel function arrays. It is The coefficients of each kernel function, It is A kernel function for chaotic time series prediction. It is the prediction error term. Indicates the index of the kernel function group. This represents the index of the merged data.

[0010] Furthermore, the specific steps for constructing a health risk identification model using the dynamic Bayesian health risk assessment formula, as described in the circadian rhythm modeling module, are as follows: Constructing a model that includes physiological indicators... Environmental factors Historical risks Bayesian networks, health risk probabilities The calculation formula is: ,in, It is a risky situation. In order to be at risk Physiological indicators at the time of occurrence The conditional probability is obtained through training with historical data. To represent the prior probability, a time-varying parameter is introduced. Dynamically adjust conditional probabilities: , It is the amount of change in the merged data. Indicates the index of merged data, when Intervention is triggered at the right time. This is a preset risk threshold.

[0011] Furthermore, the specific steps for constructing the multi-objective function in the prediction and optimization decision module are as follows: Let the comfort level be... Energy consumption is Health benefits are The formula for calculating the multi-objective function is: ,in, These are the current environmental parameters. For optimal parameters, It is the standard deviation parameter in comfort calculation. It is a multi-objective function value. , , It is a weighting coefficient for comfort, energy consumption, and health benefits.

[0012] Furthermore, the specific steps for generating pre-adjustment strategy instructions in the prediction and optimization decision module are as follows: (1) Randomly generate the initial position and velocity of the particle swarm, with each particle corresponding to a set of environmental adjustment parameters; (2) Calculate the fitness of each particle based on the multi-objective requirements and evaluate the overall performance of the adjustment scheme; (3) Compare the current fitness of the particle with its historical fitness and update the individual's optimal position; (4) Select the best particle in the particle swarm and determine the global optimal position; (5) Update the velocity and position of each particle; (6) Compare the updated parameter vector with the environmental regulation rule base and correct out-of-range parameters; (7) Determine whether the global optimal position has been reached without being updated multiple times. If not, continue iterating. (8) The optimal parameter vector is formed by the final global optimal position, and the pre-adjustment strategy instruction is generated.

[0013] Furthermore, the environmental regulation rule base mentioned in the prediction and optimization decision-making module includes the following: Equipment operating parameter constraints: air conditioning temperature adjustment range, fan speed adjustment range; lighting brightness adjustment range, color temperature adjustment range; ventilation equipment air exchange rate adjustment range; Environmental parameter safety threshold rules: Upper limit of PM2.5 concentration, formaldehyde concentration safety threshold; safe range of temperature and humidity; upper limit of light intensity. Scene adaptation rules: In the sleep scene, the temperature should be maintained at 24℃-26℃, the humidity at 40%-50%, the light brightness should be less than 5 lux, and the device operating noise should be controlled below 30 decibels; in the work scene, the temperature should be maintained at 22℃-25℃, the light brightness should be suitable for reading, and the air should be well circulated. Device collaborative operation rules: priority and collaborative logic when multiple devices are running simultaneously; startup order rules when multiple devices are running simultaneously; Energy-saving optimization rules: Extend the heating time of water heaters and reduce heating power during off-peak electricity consumption periods; automatically switch air conditioners to energy-saving mode after reaching the set temperature; automatically put equipment into sleep mode when idle; User-personalized rules: users can define their own lower temperature limit and special air quality threshold preferences, and store user-personalized scenario mode parameters.

[0014] Furthermore, the intervention strategy library described in the health risk response module includes the following: Stress risk intervention: If abnormally high resting heart rate, shallow and rapid breathing and moderate ambient temperature are detected, instructions are generated to reduce ambient light, start white noise equipment to play 40-60Hz sound effects, and control the air conditioner to release 1000-2000 negative ions / cm³. Sleep health risk intervention: If the user's deep sleep rate is below 20% for three consecutive nights and their nighttime body movement exceeds 8 times per hour, and the ambient temperature and humidity are normal, adjust the bedroom lights and set the air conditioner humidity to 50-55% before bedtime; Safety risk intervention: For the elderly, if they are out of bed for more than 60 minutes at night, the bathroom path lights will be automatically turned on and linked to the smart night light; if they are out of bed for more than 2 hours, an abnormal warning notification will be pushed to the emergency contact's mobile phone. Sub-health intervention: When multiple physiological indicators of the user continue to fluctuate abnormally, the air purifier is activated in sterilization and disinfection mode, and the fresh air system is adjusted to increase the number of air exchanges. Post-exercise recovery intervention: Predicting the user's post-exercise state, the living room air conditioner ventilation mode is activated in advance, starting with a low fan speed and gradually adjusting to a comfortable level, and the lights are adjusted; Disease prevention and intervention support: During flu season, if a slight increase in a user's body temperature is detected, the air purifier filter replacement reminder level will be increased, the release of negative ions will be increased, and the indoor humidity will be adjusted to 40%-50%; Cardiovascular risk intervention: When the resting heart rate deviates from the individual's baseline by ±10 beats / minute for more than 30 minutes, the blood pressure monitoring device is activated to collect data; if the blood pressure data is abnormal, the indoor temperature is reduced by 1-2℃; Child safety intervention: If the ambient temperature in the child's activity area exceeds 30℃, the air conditioner in the child's room is automatically turned on and the fan speed is reduced; if a child is detected to be in a fixed position for a long time without obvious physical movement, the safety situation is confirmed through image recognition by a smart camera; Allergy prevention intervention: During peak allergy season, when the indoor air quality sensor detects excessive pollen concentration, the exterior windows are automatically closed, the allergy prevention mode of the air purifier is activated, and the filter is strengthened.

[0015] Furthermore, the specific steps for generating intervention instructions in the health risk response module are as follows: Let the health risk probability be... The preset threshold is The strategy set in the intervention strategy library is , It represents the total number of intervention strategies in the intervention strategy library, with each strategy corresponding to a unique identifier. The generated intervention instructions are The calculation formula is: Among them, Priority For each strategy in the intervention strategy library The priority function sets priority values ​​based on risk type and urgency. This indicates that the highest priority strategy is selected from the strategy set as the execution instruction. It is an index used to iterate through the set of intervention strategies. This indicates an empty value, and no specific intervention instruction is generated. When the risk probability exceeds the threshold, the highest priority strategy is selected to generate an intervention instruction; when the risk probability does not exceed the threshold, an empty instruction is generated and no intervention operation is performed.

[0016] Compared with existing technologies, this intelligent IoT home energy management system has the following advantages: 1. This invention, through a multi-dimensional data perception module, can comprehensively collect human physiological data, environmental data, and external data. Combined with historical records and user feedback, it constructs a user-specific physiological state prediction model and health risk identification model, improving the personalization level of health management. Furthermore, by embedding a chaotic biorhythm prediction formula and a dynamic Bayesian health risk assessment formula, it achieves accurate prediction of the user's physiological state and identification of health risks. The system can automatically adjust home environment parameters based on the user's real-time data to optimize user comfort and health benefits. This personalized and precise health management and environmental regulation approach not only improves the user's quality of life but also effectively prevents potential health risks.

[0017] 2. This invention, through a predictive optimization decision-making module, enables the system to construct a multi-objective function by combining real-time data, environmental parameters, and historical user data. It then uses a particle swarm optimization algorithm to solve for the optimal environmental regulation parameter vector, achieving efficient energy utilization and maximizing comfort. Simultaneously, a health risk response module monitors user physiological data in real time. Upon detecting a health risk, it immediately generates corresponding intervention instructions based on an intervention strategy library and feeds them back to the intelligent execution feedback module, enabling rapid response and effective intervention. This intelligent and adaptive energy management and risk response approach not only reduces home energy consumption and improves energy efficiency but also provides users with a safer and healthier living environment.

[0018] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0020] Figure 1 A flowchart of a smart IoT home energy management system; Figure 2 This is a framework diagram of a smart IoT home energy management system. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] According to an embodiment of the present invention, an intelligent IoT home energy management system is proposed. Through a multi-dimensional data sensing module, it can comprehensively collect human physiological data, environmental data, and external data. Combined with historical records and user feedback, it constructs a user-specific physiological state prediction model and health risk identification model, thereby improving the personalization level of health management. By using a chaotic embedded biorhythm prediction formula and a dynamic Bayesian health risk assessment formula, it achieves accurate prediction of the user's physiological state and identification of health risks. The system can automatically adjust home environment parameters based on the user's real-time data to optimize the user's comfort and health benefits. This personalized and precise health management and environmental regulation method not only improves the user's quality of life but also effectively prevents potential health risks.

[0023] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0024] Figure 1 This is a schematic diagram of an intelligent IoT home energy management system according to an embodiment of the present invention. The system includes: Multidimensional data perception module: used to collect human physiological data using sensor and smart device interfaces, obtain environmental and external data through environmental sensors and weather API, retrieve historical data: physiological records, environmental regulation logs and user feedback data, add timestamps and spatial coordinate information to various types of data, and convert the data into data vectors and upload them to the system database; Biorhythm Modeling Module: Based on the data collected by the multidimensional data perception module, it uses chaotic embedding biorhythm prediction formula to build a user-specific physiological state prediction model, and at the same time, it uses dynamic Bayesian health risk assessment formula to build a health risk identification model. Predictive optimization decision module: It is used to input real-time collected data into the biorhythm prediction model, calculate the prediction results of the user's future physiological state, calculate the comfort level in combination with the current environmental parameters, construct a multi-objective function by combining energy consumption and health benefits, and then combine the environmental regulation rule library to solve the optimal environmental regulation parameter vector using the particle swarm optimization algorithm to generate pre-regulation strategy instructions; The intelligent execution feedback module is used to receive pre-adjustment strategy instructions, control home devices to perform adjustment operations through smart home protocols, and collect device operating status and user physiological feedback data in real time, and transmit the data to the health risk response module. Health Risk Response Module: This module receives data from the intelligent execution feedback module, calculates the health risk probability using the health risk identification model, combines the risk probability with the intervention strategy library to generate intervention instructions, and then feeds them back to the intelligent execution feedback module.

[0025] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the drawings, not all structures. Moreover, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0026] It should also be noted that, for ease of description, the accompanying drawings show only the parts relevant to the invention and not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the drawings. The process may correspond to a method, function, procedure, subroutine, subroutine, etc.

[0027] The following two specific examples will further illustrate the underground high-temperature composite fluid heating system in more detail: Example 1: Optimize the nighttime sleep environment in the family bedroom.

[0028] Multi-dimensional data sensing module: The system activates a data acquisition network. A millimeter-wave radar sensor at the head of the bed continuously captures fluctuations in the user's heart rate and respiratory rate during sleep; a pressure sensor array built into the mattress records the amplitude and frequency of body movements; and an infrared thermal imaging sensor on the ceiling collects real-time data on the human body surface temperature. Simultaneously, temperature and humidity sensors and air quality sensors distributed in the corners of the bedroom collect real-time environmental data, including PM2.5, PM10, and VOC gas sensors to monitor PM2.5 and VOC levels. A light sensor is deployed to obtain indoor light intensity data. Weather data is collected in real-time via a weather API, providing hourly external weather information, including current temperature, humidity, wind speed, wind direction, and a 24-hour weather forecast. The system also retrieves historical data, including the user's past physiological records from local databases and cloud storage, covering historical heart rate and body temperature fluctuation curves. It also obtains environmental adjustment logs, including the time, parameters, and duration of each air conditioning and lighting adjustment, and extracts feedback data from user manual interventions.

[0029] In this embodiment, the system retrieves the user's past sleep stage data, historical air conditioning settings (e.g., the temperature is often set to 26°C in the first half of the night), and manually provided comfort ratings. All data is assigned precise timestamps and spatial coordinates, and converted into data vectors using a specific algorithm. Let the physiological data be... Environmental data is External data is Integrate into a three-dimensional tensor Each data point is accompanied by a timestamp and spatial coordinates. Information, the fused data vector is The calculation formula is: ,in To fuse the weights, a dynamic attention mechanism is used for calculation, and the formula is as follows: ,in, It is the j-th feature of the i-th data type. These correspond to physiological, environmental, and external data, respectively. For feature number, It is a three-dimensional tensor that integrates physiological, environmental, and external data. These are spatial coordinates. It is the number of features of the i-th type of data. It is the total number of features participating in the integration. , It is a weight matrix used for calculation in dynamic attention mechanisms. , Bias vector, used for dynamic attention mechanism computation. It is the Hadamard product, which is the element-wise multiplication of matrices. Linear rectifier function, It is a natural exponential function, imported into the system database for further analysis, such as... Figure 1 As shown.

[0030] Biorhythm Modeling Module: Based on fused multidimensional data, the system uses chaotic embedding biorhythm prediction formulas to construct user-specific physiological state prediction models. Based on phase space reconstruction theory, it integrates the fused data... Embedded Construct delayed coordinate vectors in phase space. The formula is: Construct a chaotic time series prediction model, with the following formula: ,in, It is time. It is a time delay parameter. It is the phase space dimension. It is the predicted time interval. It is the number of kernel function arrays. It is The coefficients of each kernel function, It is A kernel function for chaotic time series prediction. It is the prediction error term. Indicates the index of the kernel function group. This represents an index of fused data, which deeply analyzes the fluctuation patterns of users' heart rate and body temperature after falling asleep, predicts the possible periods of deep sleep, and simultaneously constructs a health risk identification model using a dynamic Bayesian health risk assessment formula, incorporating physiological indicators. Environmental factors Historical risks Bayesian networks, health risk probabilities The calculation formula is: ,in, It is a risky situation. In order to be at risk Physiological indicators at the time of occurrence The conditional probability is obtained through training with historical data. To represent the prior probability, a time-varying parameter is introduced. Dynamically adjust conditional probabilities: , It is the amount of change in the merged data. Indicates the index of merged data, when Intervention is triggered at the right time. Using a preset risk threshold, and taking into account current heart rate variability, bedroom temperature and humidity, as well as historical records of abnormal breathing during sleep, the probability of nighttime health risks is accurately assessed, providing a scientific basis for subsequent adjustments.

[0031] Predictive Optimization Decision Module: The system inputs real-time collected physiological data and environmental parameters into the biorhythm prediction model to calculate the user's likely deep sleep state during the midnight to early morning hours. Combining this with current environmental parameters and comfort levels, and taking into account the energy costs of air conditioning operation and the health benefits of improving deep sleep, a multi-objective function is constructed, with comfort set as... Energy consumption is Health benefits are The formula for calculating the multi-objective function is: ,in, These are the current environmental parameters. For optimal parameters, It is the standard deviation parameter in comfort calculation. It is a multi-objective function value. , , These are weighted coefficients for comfort, energy consumption, and health benefits, combined with an environmental regulation rule base, including: Equipment operating parameter constraints: air conditioning temperature adjustment range, fan speed adjustment range; lighting brightness adjustment range, color temperature adjustment range; ventilation equipment air exchange rate adjustment range; Environmental parameter safety threshold rules: Upper limit of PM2.5 concentration, formaldehyde concentration safety threshold; safe range of temperature and humidity; upper limit of light intensity. Scene adaptation rules: In the sleep scene, the temperature should be maintained at 24℃-26℃, the humidity at 40%-50%, the light brightness should be less than 5 lux, and the device operating noise should be controlled below 30 decibels; in the work scene, the temperature should be maintained at 22℃-25℃, the light brightness should be suitable for reading, and the air should be well circulated. Device collaborative operation rules: priority and collaborative logic when multiple devices are running simultaneously; startup order rules when multiple devices are running simultaneously; Energy-saving optimization rules: Extend the heating time of water heaters and reduce heating power during off-peak electricity consumption periods; automatically switch air conditioners to energy-saving mode after reaching the set temperature; automatically put equipment into sleep mode when idle; User-personalized rules: users can define their own lower temperature limit and special air quality threshold preferences, and store user-personalized scenario mode parameters.

[0032] The optimal environmental regulation parameter vector is solved by using the particle swarm optimization algorithm, and the optimal environmental regulation scheme is finally determined, such as adjusting the air conditioner temperature to a slightly lower comfort range and dimming the lights to 3 lux, generating detailed pre-regulation strategy instructions.

[0033] Specifically, the steps for generating pre-adjustment strategy instructions are as follows: (1) Randomly generate the initial position and velocity of the particle swarm, with each particle corresponding to a set of environmental adjustment parameters; (2) Calculate the fitness of each particle based on the multi-objective requirements and evaluate the overall performance of the adjustment scheme; (3) Compare the current fitness of the particle with its historical fitness and update the individual's optimal position; (4) Select the best particle in the particle swarm and determine the global optimal position; (5) Update the velocity and position of each particle; (6) Compare the updated parameter vector with the environmental regulation rule base and correct out-of-range parameters; (7) Determine whether the global optimal position has been reached without being updated multiple times. If not, continue iterating. (8) The optimal parameter vector is formed by the final global optimal position, and the pre-adjustment strategy instruction is generated.

[0034] Intelligent Execution Feedback Module: After the command is issued, the smart home protocol quickly transmits the adjustment signal to the air conditioning and lighting devices, which then adjust accordingly. During this process, the real-time operating status of the devices (such as the actual output power of the air conditioner and the brightness of the lights) and the user's physiological feedback data (whether the body movement frequency decreases due to temperature changes) are collected in real time and simultaneously sent to the health risk response module. Figure 2 As shown, this provides a basis for subsequent dynamic adjustments.

[0035] Health Risk Response Module: Continuously receives and analyzes feedback data. If it detects that a user's deep sleep percentage is below normal for several consecutive nights, and their body movement frequency is abnormally high, it will immediately invoke the health risk response algorithm. This algorithm, combined with the calculation results from the health risk identification model, will generate intervention instructions, assuming a health risk probability of [value missing]. The preset threshold is The strategy set in the intervention strategy library is , It represents the total number of intervention strategies in the intervention strategy library, with each strategy corresponding to a unique identifier. The generated intervention instructions are The calculation formula is: Among them, Priority For each strategy in the intervention strategy library The priority function sets priority values ​​based on risk type and urgency. This indicates that the highest priority strategy is selected from the strategy set as the execution instruction. It is an index used to iterate through the set of intervention strategies. This indicates a null value, meaning no specific intervention instruction is generated. When the risk probability exceeds a preset threshold, a sleep health risk intervention strategy is precisely matched from the intervention strategy library. For example, the lights are automatically switched to a warm yellow 2700K 30 minutes before bedtime, and the air conditioner humidity is adjusted to a comfortable range of 50-55%. When the risk probability does not exceed the threshold, a null instruction is generated, and no intervention operation is performed.

[0036] Specifically, the intervention strategy library contains the following: Stress risk intervention: If abnormally high resting heart rate, shallow and rapid breathing and moderate ambient temperature are detected, an instruction is generated to reduce ambient light brightness to 30%, start white noise equipment to play 40-60Hz sound effects, and control the air conditioner to release 1000-2000 negative ions / cm³. Sleep health risk intervention: If the user's deep sleep rate is below 20% for three consecutive nights and their nighttime body movement exceeds 8 times per hour, and the ambient temperature and humidity are normal, adjust the bedroom lights to a warm yellow 2700K and the air conditioner humidity to 50-55% 30 minutes before bedtime; Safety risk intervention: For the elderly, the time they can leave the bed at night is extended from the usual 10 minutes to more than 60 minutes, the bathroom path lights are automatically brightened to 8-10 lux, and the smart night light is activated; if they leave the bed for more than 2 hours, an abnormal warning notification is pushed to the emergency contact's mobile phone. Sub-health intervention: When multiple physiological indicators of the user continue to fluctuate abnormally, the air purifier is activated in sterilization and disinfection mode, and the fresh air system is adjusted to increase the number of air exchanges. Post-exercise recovery intervention: Predicting that the user is in a post-exercise state, the living room air conditioner ventilation mode is activated in advance, starting with a low fan speed and gradually adjusting to a comfortable level, and the lights are adjusted to a 5000K cool color scheme; Disease prevention and intervention support: During flu season, if a slight increase in a user's body temperature is detected, the air purifier filter replacement reminder level will be increased, the release of negative ions will be increased, and the indoor humidity will be adjusted to 40%-50%; Cardiovascular risk intervention: When the resting heart rate deviates from the individual's baseline by ±10 beats / minute for more than 30 minutes, the blood pressure monitoring device is activated to collect data; if the blood pressure data is abnormal, the indoor temperature is reduced by 1-2℃; Child safety intervention: If the ambient temperature in the child's activity area exceeds 30℃, the air conditioner in the child's room is automatically turned on to 24-26℃ and the fan speed is reduced; if a child is detected to be in a fixed position for a long time without obvious physical movement, the safety situation is confirmed through image recognition by a smart camera; Allergy prevention intervention: During peak allergy season, when the indoor air quality sensor detects excessive pollen concentration, the exterior windows are automatically closed, the allergy prevention mode of the air purifier is activated, and the filter is strengthened.

[0037] In summary, this invention, in the context of nighttime sleep in a home bedroom, collects human physiological and environmental data through a multi-dimensional data sensing module, models the data using a chaotic embedded biorhythm prediction formula and a dynamic Bayesian health risk assessment formula, and generates a pre-regulation strategy by combining a multi-objective function and a particle swarm optimization algorithm. This strategy controls the device to execute and respond to health risks, thereby optimizing the comfort, energy consumption, and health benefits of the sleep environment.

[0038] Example 2: Intelligent adjustment of the daily home environment for elderly users.

[0039] Multi-dimensional data sensing module: In the daily activity space of elderly users, the system constructs a comprehensive sensing network. Millimeter-wave radar sensors at the bedside collect heart rate changes when the elderly are sitting; pressure sensor arrays under the mattress and sofa record body movement data; smart bracelets synchronize daily step counts and activity intensity information; temperature and humidity sensors sense the ambient temperature and humidity in real time; air quality sensors monitor PM2.5 and formaldehyde levels to prevent excessive concentrations of harmful substances; weather conditions outside the window are updated in real time via a weather API, such as high-temperature weather warnings. The system also retrieves the elderly's past baseline heart rate data, such as a resting heart rate typically of 70 beats / minute, air conditioning usage records from the past week, such as the temperature often being set to 25℃ in the afternoon, and previously submitted feedback data. All data is transformed into data vectors through a spatiotemporal correlation data fusion algorithm. The calculation formula is as follows: The data is then uploaded to the database to lay the foundation for subsequent analysis.

[0040] Biorhythm Modeling Module: Based on the fused multidimensional data, the system uses a chaotic embedding biorhythm prediction formula to build a personalized physiological state prediction model for elderly users. The calculation formula is as follows: The study analyzed the fluctuation patterns of heart rate and blood pressure at different times, including after breakfast and during afternoon nap. Simultaneously, a health risk identification model was constructed using a dynamic Bayesian health risk assessment formula, with the following calculation formula: By combining factors such as whether the current resting heart rate deviates from the baseline and whether the indoor temperature exceeds 30°C with historical records of nighttime dizziness, the probability of health risks can be accurately calculated, with particular attention to potential cardiovascular risks, providing scientific support for early intervention.

[0041] Predictive optimization decision-making module: When the system detects that the elderly person's resting heart rate is persistently high and the indoor temperature reaches 28℃, it will input this real-time data into the biorhythm prediction model. Combined with the comfort model (the discomfort caused by high temperatures), energy consumption considerations (the electricity consumption of the fan), and the health benefits of reducing cardiovascular risk), a multi-objective function is constructed. The calculation formula for the multi-objective function is as follows: At this point, the particle swarm optimization algorithm quickly searches for the optimal solution within the environmental regulation rule base, under constraints such as the temperature in the elderly's activity area should be below 26℃ and PM2.5 should be controlled within a safe threshold. For example, it suggests turning on the fan and setting the air conditioner temperature to 25℃, generating detailed pre-regulation strategy instructions that both ensure health and save energy.

[0042] Intelligent execution feedback module: After the command is issued, the air conditioner and fan quickly adjust. The system collects the operating power of the air conditioner and the speed and status data of the fan in real time. At the same time, it continuously tracks the elderly's heart rate changes and body movement frequency. This feedback data is like a constantly updated health report and is promptly transmitted to the health risk response module so that the strategy can be dynamically adjusted according to the actual situation.

[0043] Health Risk Response Module: If an elderly person is detected to be out of bed for more than 60 minutes at night, far exceeding the usual 10 minutes, the health risk response module will immediately activate the health risk response algorithm. This algorithm combines the calculation results from the health risk identification model with the intervention strategy library to generate intervention instructions. The calculation formula is as follows: When a safety risk is detected, the system quickly retrieves safety risk intervention strategies from the intervention strategy library. For example, it automatically brightens the bathroom path lights to 8-10 lux and simultaneously links with smart nightlights to provide soft lighting, providing a clear path for the elderly to walk. If the elderly are out of bed for more than 2 hours, the system will immediately send an abnormal warning notification to the emergency contact and continuously adjust environmental parameters, such as maintaining a suitable indoor temperature, until the elderly are confirmed to be safe.

[0044] In summary, this invention utilizes multiple sensors to collect physiological and environmental data in the home environment of the elderly, constructs a model using chaotic embedded biological rhythm prediction formulas and dynamic Bayesian formulas, and makes decisions through multi-objective functions combined with particle swarm optimization algorithms to implement adjustments and respond to risks, such as turning on lights and sending alerts if the elderly are out of bed for too long at night, thus ensuring the safety and health of the elderly at home.

[0045] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A smart IoT home energy management system, characterized in that, The system includes: Multidimensional data perception module: used to collect human physiological data using sensor and smart device interfaces, obtain environmental and external data through environmental sensors and weather API, retrieve historical data: physiological records, environmental regulation logs and user feedback data, add timestamps and spatial coordinate information to various types of data, and convert the data into data vectors and upload them to the system database; Biorhythm Modeling Module: Based on the data collected by the multidimensional data perception module, it uses chaotic embedding biorhythm prediction formula to build a user-specific physiological state prediction model, and at the same time, it uses dynamic Bayesian health risk assessment formula to build a health risk identification model. Predictive optimization decision module: It is used to input real-time collected data into the biorhythm prediction model, calculate the prediction results of the user's future physiological state, calculate the comfort level in combination with the current environmental parameters, construct a multi-objective function by combining energy consumption and health benefits, and then combine the environmental regulation rule library to solve the optimal environmental regulation parameter vector using the particle swarm optimization algorithm to generate pre-regulation strategy instructions; The intelligent execution feedback module is used to receive pre-adjustment strategy instructions, control home devices to perform adjustment operations through smart home protocols, and collect device operating status and user physiological feedback data in real time, and transmit the data to the health risk response module. Health Risk Response Module: This module receives data from the intelligent execution feedback module, calculates the health risk probability using the health risk identification model, combines the risk probability with the intervention strategy library to generate intervention instructions, and then feeds them back to the intelligent execution feedback module.

2. The intelligent IoT home energy management system according to claim 1, characterized in that, The methods for collecting human physiological data, environmental data, external data, and historical data in the multidimensional data perception module are as follows: Human physiological data collection: Millimeter-wave radar sensors are deployed at the head of the bed to collect heart rate and respiratory rate data; infrared thermal imaging sensors are installed on the ceiling to obtain human body surface temperature distribution data; user movement data and sleep stage data are synchronized through smart device interfaces and smart bracelets; pressure sensor arrays are built into mattresses and / or sofas to capture body movement amplitude and frequency data; Environmental data collection: Temperature and humidity sensors are deployed in different areas of the room to collect ambient temperature and humidity data; air quality sensors, including PM2.5 sensors, PM10 sensors and VOC gas sensors, are installed to detect the concentration of particulate matter and volatile organic compounds in the air; light sensors are deployed to obtain indoor light intensity data; External data collection: Obtain external weather information hourly via the weather API interface, including current temperature, humidity, wind speed, wind direction, and weather forecast for the next 24 hours; Historical data collection: Retrieve users' past physiological records from local databases and cloud storage, including data on historical heart rate and body temperature fluctuation curves, obtain environmental adjustment logs, including information on the adjustment time, adjustment parameters, and runtime of each air conditioner and light adjustment, and extract feedback data on user manual intervention.

3. The intelligent IoT home energy management system according to claim 1, characterized in that, The multidimensional data perception module describes the transformation of data into data vectors through a spatiotemporal correlation data fusion algorithm. Let physiological data be an example. Environmental data is External data is Integrate into a three-dimensional tensor Each data point is accompanied by a timestamp and spatial coordinates. Information, the fused data vector is The calculation formula is: ,in To fuse the weights, a dynamic attention mechanism is used for calculation, and the formula is as follows: ,in, It is the j-th feature of the i-th data type. These correspond to physiological, environmental, and external data, respectively. For feature number, It is a three-dimensional tensor that integrates physiological, environmental, and external data. These are spatial coordinates. It is the number of features of the i-th type of data. It is the total number of features participating in the integration. , It is a weight matrix used for calculation in dynamic attention mechanisms. , Bias vector, used for dynamic attention mechanism computation. It is the Hadamard product, which is the element-wise multiplication of matrices. Linear rectifier function, It is a natural exponential function.

4. The intelligent IoT home energy management system according to claim 1, characterized in that, The specific steps in the biorhythm modeling module for constructing a user-specific physiological state prediction model using chaotic embedding biorhythm prediction formulas are as follows: Based on phase space reconstruction theory, the fused data... Embedded Construct delayed coordinate vectors in phase space. The formula is: Construct a chaotic time series prediction model, with the following formula: ,in, It is time. It is a time delay parameter. It is the phase space dimension. It is the predicted time interval. It is the number of kernel function arrays. It is The coefficients of each kernel function, It is A kernel function for chaotic time series prediction. It is the prediction error term. Indicates the index of the kernel function group. This represents the index of the merged data.

5. The intelligent IoT home energy management system according to claim 4, characterized in that, The specific steps for constructing a health risk identification model using the dynamic Bayesian health risk assessment formula, as described in the circadian rhythm modeling module, are as follows: Constructing a model that includes physiological indicators... Environmental factors Historical risks Bayesian networks, health risk probabilities The calculation formula is: ,in, It is a risky situation. In order to be at risk Physiological indicators at the time of occurrence The conditional probability is obtained through training with historical data. To represent the prior probability, a time-varying parameter is introduced. Dynamically adjust conditional probabilities: , It is the amount of change in the merged data. Indicates the index of merged data, when Intervention is triggered at the right time. This is a preset risk threshold.

6. The intelligent IoT home energy management system according to claim 1, characterized in that, The specific steps for constructing the multi-objective function described in the prediction and optimization decision module are as follows: Let the comfort level be... Energy consumption is Health benefits are The formula for calculating the multi-objective function is: ,in, These are the current environmental parameters. For optimal parameters, It is the standard deviation parameter in comfort calculation. It is a multi-objective function value. , , It is a weighting coefficient for comfort, energy consumption, and health benefits.

7. The intelligent IoT home energy management system according to claim 6, characterized in that, The specific steps for generating pre-adjustment strategy instructions in the predictive optimization decision module are as follows: (1) Randomly generate the initial position and velocity of the particle swarm, with each particle corresponding to a set of environmental adjustment parameters; (2) Calculate the fitness of each particle based on the multi-objective requirements and evaluate the overall performance of the adjustment scheme; (3) Compare the current fitness of the particle with its historical fitness and update the individual's optimal position; (4) Select the best particle in the particle swarm and determine the global optimal position; (5) Update the velocity and position of each particle; (6) Compare the updated parameter vector with the environmental regulation rule base and correct out-of-range parameters; (7) Determine whether the global optimal position has been reached without being updated multiple times. If not, continue iterating. (8) The optimal parameter vector is formed by the final global optimal position, and the pre-adjustment strategy instruction is generated.

8. The intelligent IoT home energy management system according to claim 1, characterized in that, The environmental regulation rule base mentioned in the predictive optimization decision module includes the following: Equipment operating parameter constraints: air conditioning temperature adjustment range, fan speed adjustment range; lighting brightness adjustment range, color temperature adjustment range; ventilation equipment air exchange rate adjustment range; Environmental parameter safety threshold rules: Upper limit of PM2.5 concentration, formaldehyde concentration safety threshold; safe range of temperature and humidity; upper limit of light intensity. Scene adaptation rules: In the sleep scene, the temperature should be maintained at 24℃-26℃, the humidity at 40%-50%, the light brightness should be less than 5 lux, and the device operating noise should be controlled below 30 decibels; in the work scene, the temperature should be maintained at 22℃-25℃, the light brightness should be suitable for reading, and the air should be well circulated. Device collaborative operation rules: priority and collaborative logic when multiple devices are running simultaneously; startup order rules when multiple devices are running simultaneously; Energy-saving optimization rules: Extend the heating time of water heaters and reduce heating power during off-peak electricity consumption periods; automatically switch air conditioners to energy-saving mode after reaching the set temperature; automatically put equipment into sleep mode when idle; User-personalized rules: users can define their own lower temperature limit and special air quality threshold preferences, and store user-personalized scenario mode parameters.

9. A smart IoT home energy management system according to claim 1, characterized in that, The intervention strategy library described in the health risk response module contains the following: Stress risk intervention: If abnormally high resting heart rate, shallow and rapid breathing and moderate ambient temperature are detected, instructions are generated to reduce ambient light, start white noise equipment to play 40-60Hz sound effects, and control the air conditioner to release 1000-2000 negative ions / cm³. Sleep health risk intervention: If the user's deep sleep rate is below 20% for three consecutive nights and their nighttime body movement exceeds 8 times per hour, and the ambient temperature and humidity are normal, adjust the bedroom lights and set the air conditioner humidity to 50-55% before bedtime; Safety risk intervention: For the elderly, if they are out of bed for more than 60 minutes at night, the bathroom path lights will be automatically turned on and linked to the smart night light; if they are out of bed for more than 2 hours, an abnormal warning notification will be pushed to the emergency contact's mobile phone. Sub-health intervention: When multiple physiological indicators of the user continue to fluctuate abnormally, the air purifier is activated in sterilization and disinfection mode, and the fresh air system is adjusted to increase the number of air exchanges. Post-exercise recovery intervention: Predicting the user's post-exercise state, the living room air conditioner ventilation mode is activated in advance, starting with a low fan speed and gradually adjusting to a comfortable level, and the lights are adjusted; Disease prevention and intervention support: During flu season, if a slight increase in a user's body temperature is detected, the air purifier filter replacement reminder level will be increased, the release of negative ions will be increased, and the indoor humidity will be adjusted to 40%-50%; Cardiovascular risk intervention: When the resting heart rate deviates from the individual's baseline by ±10 beats / minute for more than 30 minutes, the blood pressure monitoring device will be activated to collect data; if the blood pressure data is abnormal, the indoor temperature will be reduced by 1-2℃; Child safety intervention: If the ambient temperature in the child's activity area exceeds 30℃, the air conditioner in the child's room will be automatically turned on and the fan speed will be reduced. If a child is detected to be in a fixed position for an extended period of time without any obvious physical movement, the safety situation can be confirmed by image recognition through a smart camera. Allergy prevention intervention: During peak allergy season, when the indoor air quality sensor detects excessive pollen concentration, the exterior windows are automatically closed, the allergy prevention mode of the air purifier is activated, and the filter is strengthened.

10. A smart IoT home energy management system according to claim 1, characterized in that, The specific steps for generating intervention instructions in the health risk response module are as follows: Let the health risk probability be... The preset threshold is The strategy set in the intervention strategy library is , It represents the total number of intervention strategies in the intervention strategy library, with each strategy corresponding to a unique identifier. The generated intervention instructions are The calculation formula is: Among them, Priority For each strategy in the intervention strategy library The priority function sets priority values ​​based on risk type and urgency. This indicates that the highest priority strategy is selected from the strategy set as the execution instruction. It is an index used to iterate through the set of intervention strategies. This indicates an empty value, and no specific intervention instruction is generated. When the risk probability exceeds the threshold, the highest priority strategy is selected to generate an intervention instruction; when the risk probability does not exceed the threshold, an empty instruction is generated and no intervention operation is performed.

Images