A smart IoT sensing method for smart home

Through differentiated functional analysis and real-time data monitoring of smart homes, an intelligent perception layer is built, which solves the problem of inaccurate identification of human fatigue in traditional technologies, and realizes personalized control of smart homes and the provision of comfortable environments.

CN117850253BActive Publication Date: 2024-11-15JIANGSU SHENGSHIYUNTU IOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311458508.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-05
Publication Date
2024-11-15
Estimated Expiration
2043-11-05

AI Technical Summary

Technical Problem

Traditional intelligent IoT sensing technology cannot accurately identify the body's real-time fatigue state, and the response measures are inaccurate.

Method used

By performing differentiated functional analysis of smart homes, building an IoT perception control system, combining real-time monitoring of user posture and home environment data, an intelligent perception layer is built to achieve the assessment of skin fatigue and environmental sensory fatigue analysis, and personalized Intelligent linkage control.

Benefits of technology

Accurately identify and cope with the real-time fatigue state of the human body, improve the overall intelligence level of the smart home system, and provide a more comfortable and convenient living experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117850253B_ABST
    Figure CN117850253B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of intelligent Internet of Things perception technology, and in particular to an intelligent Internet of Things perception method for a smart home. The method comprises the following steps: performing functional differentiation analysis on the smart home and building an intelligent Internet of Things perception control system to obtain an Internet of Things perception control platform; performing human skin condition analysis on the user's body shape and fatigue assessment to obtain skin fatigue perception data; extracting environmental data from the real-time home environment to obtain real-time home environment data; performing sensory fatigue analysis on skin fatigue perception data based on the real-time home environment data to obtain sensory fatigue data; inputting skin fatigue perception data into the Internet of Things perception control platform to build a control platform perception layer to obtain a control platform intelligent perception layer; performing command linkage processing on the smart home to obtain an intelligent linkage home strategy. The present invention optimizes the processing of intelligent Internet of Things perception technology to achieve more accurate Internet of Things perception technology.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent Internet of Things sensing technology, and in particular to an intelligent Internet of Things sensing method for a smart home. Background Art

[0002] Smart home refers to a home lifestyle that uses the Internet of Things, artificial intelligence and automation technology to interconnect various devices, appliances and systems in the home, and realize remote control, automatic management and intelligent interaction in an intelligent way. The smart IoT sensing method is one of the important technologies to realize the function of smart home. It senses various information and data in the home environment, obtains, analyzes and processes these data in real time, thereby realizing intelligent control and management of home devices and systems. However, traditional smart IoT sensing technology has the problem of not being able to accurately identify the real-time fatigue state of the human body and the inaccurate response measures to the real-time fatigue state of the human body. Summary of the invention

[0003] Based on this, it is necessary to provide a smart IoT perception method for a smart home to solve at least one of the above technical problems.

[0004] To achieve the above object, a smart home intelligent IoT sensing method is provided, the method comprising the following steps:

[0005] Step S1: Perform functional differentiation analysis on smart homes to obtain a functional difference data set; build an intelligent IoT perception control system based on the functional difference data set to obtain an IoT perception control platform;

[0006] Step S2: Analyze the skin condition of the user's body to obtain skin condition perception data; evaluate the fatigue level of the skin condition perception data to obtain skin fatigue perception data;

[0007] Step S3: extracting environmental data of the real-time home environment to obtain real-time home environment data; performing sensory fatigue analysis on the skin fatigue perception data based on the real-time home environment data to obtain sensory fatigue data;

[0008] Step S4: Input the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer to obtain the control platform intelligent perception layer; perform command linkage processing on the smart home according to the control platform intelligent perception layer to obtain the smart linkage home strategy.

[0009] By performing functional differentiation analysis on smart homes, the present invention can clearly understand the functional characteristics and advantages of each smart device, which is conducive to the subsequent interconnection between smart homes. By building an Internet of Things perception control system based on the functional difference data set, the interconnection and collaborative work between multiple smart devices can be achieved, so that users can control and manage various smart devices through a unified platform, improving the overall efficiency and convenience of the smart home system. By performing human skin status analysis on the user's body shape, detailed data on the skin condition can be obtained, which is helpful to understand the user's skin health status and the user's current fatigue level at the same time. By performing fatigue evaluation on the skin status perception data, the fatigue level of the user's skin can be determined, which is helpful to remind the user to take corresponding maintenance and conditioning measures in time to avoid excessive skin fatigue and damage; data extraction is performed on the real-time home environment to obtain relevant The data of temperature, humidity and light can help the smart home system to make corresponding adjustments and controls according to environmental changes, and provide a more comfortable and suitable living environment; the sensory fatigue analysis of skin fatigue perception data based on the real-time home environment data can determine the degree of influence of the environment on the user's sensory fatigue, which can help the smart home system to provide corresponding adjustments and optimizations, and create a more comfortable and pleasant living environment. The skin fatigue perception data is input into the IoT perception control platform for perception layer construction, which can realize intelligent perception and response to user needs and environmental changes, which helps to provide personalized smart home experience and customized living environment; the command linkage processing of the smart home based on the control platform intelligent perception layer can realize the collaborative work and linkage control between smart devices, which helps to improve the overall intelligence level of the smart home system and bring users a more intelligent, convenient and comfortable living experience. Therefore, the intelligent IoT perception method of a smart home of the present invention is an optimization process made on the traditional intelligent IoT perception technology, which solves the problem that the real-time fatigue state of the human body cannot be accurately identified and the countermeasures to the real-time fatigue state of the human body are inaccurate, and the real-time fatigue state of the human body can be accurately identified, and accurate countermeasures can be made to identify the real-time fatigue state of the human body.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: functionally classify the smart home to obtain a functional category data set;

[0012] Step S12: performing functional differentiation analysis on the functional category data set to obtain a functional difference data set;

[0013] Step S13: formulating a connection protocol according to the functional difference data set to obtain connection protocol data;

[0014] Step S14: performing network port adaptation processing according to the connection protocol data to obtain network port adaptation data;

[0015] Step S15: Building a network transmission channel according to the network port adaptation data and the connection protocol data to obtain a network transmission channel;

[0016] Step S16: construct an intelligent IoT perception control system for the functional category data set according to the network transmission channel to obtain an IoT perception control platform.

[0017] By classifying the functions of smart homes, the present invention can divide and classify smart devices according to their functional characteristics and uses, which helps users better understand smart devices of different functional categories and choose devices that meet their own needs in a targeted manner; by performing functional differentiation analysis based on functional categories, the functional differences between different devices in each functional category can be deeply studied, which helps users to more clearly understand the characteristics and advantages of each device and provide specific references and bases for purchase and use; according to the functional difference data set, a connection protocol suitable for devices of each functional category is formulated, which helps to achieve connection and communication between different devices, so that they can cooperate and work together; according to the connection protocol According to the network port adaptation data and connection protocol data, network port adaptation processing is performed to ensure that the network ports of each device can be correctly matched and adapted, which helps to ensure smooth data transmission and communication between devices and improve the reliability and stability of the system; according to the network port adaptation data and connection protocol data, a network transmission channel suitable for each device is built, which helps to achieve effective connection of data transmission and communication between devices and provide a stable foundation for the overall operation of the system; based on the network transmission channel, an intelligent IoT perception control system is built for the functional category data set, which helps to integrate various smart devices into a unified platform, realize their centralized control and management, and improve the overall efficiency and convenience of the smart home system.

[0018] Preferably, step S12 comprises the following steps:

[0019] Step S121: extracting features from the function category data set to obtain function category feature data;

[0020] Step S122: performing maximum similarity evaluation on the functional category feature data to obtain functional category similarity data;

[0021] Step S123: performing cluster analysis on the functional category similarity data to obtain functional category cluster data;

[0022] Step S124: performing difference normal distribution division on the function category data set according to the function category clustering data to obtain function difference sample data;

[0023] Step S125: Calculate the sample variance of the functional difference sample data to obtain the functional difference sample variance data;

[0024] Step S126: performing unbiased estimation analysis of functional differences based on the functional difference sample variance data and the functional difference sample data to obtain a functional difference data set.

[0025] The present invention performs feature extraction on the function category data set, and can extract the key features describing each function category, which helps to accurately capture the differences and characteristics between devices of different function categories, and provides a basis for subsequent analysis and evaluation; by performing maximum similarity evaluation on the function category feature data, the similarity between the function categories can be determined, which helps to find the commonalities and similarities between the function categories, and provides guidance for subsequent cluster analysis; cluster analysis based on the function category similarity data can divide the function category data into different cluster clusters, which helps to classify devices with similar functional characteristics into the same category, and provide more detailed and accurate classification results for functional differentiation analysis; according to the function category Clustering data, dividing the functional category data set into normal distribution with differences, which helps to quantify and divide the degree of difference of equipment in different functional categories, and provide specific degree of difference data for subsequent analysis and evaluation; performing sample variance calculation on the functional difference sample data can measure the degree of difference between different functional categories in the functional category data set, which helps to more accurately evaluate the differences between equipment in different functional categories and provide a data basis for unbiased estimation of functional differences; performing unbiased estimation analysis of functional differences based on functional difference sample variance data and functional difference sample data helps to make more accurate and reliable estimates of the functional difference data set, and provide a more reliable basis for subsequent decision-making and selection.

[0026] Preferably, step S2 comprises the following steps:

[0027] Step S21: performing infrared imaging scanning on the user's body to obtain infrared data of the user's body;

[0028] Step S22: extracting body temperature distribution data according to the user's body infrared data to obtain body temperature distribution data;

[0029] Step S23: dividing the body temperature distribution data into abnormal temperature regions to obtain abnormal temperature region data;

[0030] Step S24: Analyze the human skin condition based on the abnormal temperature area data to obtain skin condition perception data;

[0031] Step S25: Use a skin fatigue assessment algorithm to perform fatigue assessment on the skin state perception data to obtain skin fatigue perception data.

[0032] The present invention can obtain the user's body infrared data by performing infrared imaging scanning on the user's body, which helps to obtain the user's body temperature information and provide a data basis for subsequent analysis and judgment; based on the user's body infrared data, the body temperature distribution data is extracted, which helps to understand the distribution of the user's body temperature and grasp the user's overall body temperature condition; according to the body temperature distribution data, the abnormal temperature area is divided. This helps to identify the area where the user's body temperature is abnormal, which may indicate potential health problems; based on the abnormal temperature area data, the human skin state is analyzed, which helps to further understand the user's skin condition, and the skin fatigue assessment algorithm is used to assess the fatigue of the skin state perception data, which helps to assess the user's skin fatigue level and guide the user to take appropriate care and health care measures.

[0033] Preferably, step S24 includes the following steps:

[0034] Step S241: Analyze the skin microstructure based on the abnormal temperature area data to obtain skin microstructure data;

[0035] Step S242: monitoring skin humidity based on the skin microstructure data to obtain skin humidity data;

[0036] Step S243: performing stratum corneum analysis according to the skin microstructure data to obtain skin stratum corneum data;

[0037] Step S244: Calculate pH according to the skin stratum corneum data and the skin humidity data to obtain skin pH data;

[0038] Step S245: Analyze the distribution state of skin secretions according to the skin microstructure data to obtain skin secretion distribution data;

[0039] Step S246: performing skin sensitivity analysis according to the skin secretion distribution data and the skin pH data to obtain skin sensitivity data;

[0040] Step S247: Analyze the skin sensitivity data based on the human skin condition to obtain skin condition perception data.

[0041] The present invention analyzes the skin microstructure based on the abnormal temperature area data, which helps to understand the subtle structural characteristics of the skin, including pores and skin texture, and provides a basis for subsequent analysis. The skin humidity is monitored based on the skin microstructure data, which helps to understand the moisture content and humidity status of the skin, and provides a reference for skin moisturizing and care. The stratum corneum is analyzed based on the skin microstructure data, which helps to understand the thickness and health index of the stratum corneum, and evaluate the current body comfort. The pH is calculated based on the skin stratum corneum data and skin humidity data, which helps to evaluate the acid-base balance of the skin and provide a reference for the skin pH. It provides a reference for regulation and acid-base balance; it analyzes the distribution status of skin secretions based on skin microstructure data, which helps to understand the distribution of skin secretions, such as oil secretion and sweat secretion, and provides guidance for skin oil control and cleansing; it analyzes skin sensitivity based on skin secretion distribution data and skin pH data, which helps to assess skin sensitivity and guide users to choose appropriate skin care products and care methods; it perceives the state of human skin based on skin sensitivity data, which helps to fully understand the user's skin condition, including moisture balance, health of the stratum corneum, and sensitivity, and provides users with personalized skin care suggestions and maintenance plans.

[0042] Preferably, the skin fatigue evaluation algorithm in step S25 is as follows:

[0043]

[0044] Where f represents the skin fatigue perception result value, N represents the number of fatigue evaluation parameters, and a i represents the weight coefficient of the i-th skin condition perception data, b i represents the data redundancy of the i-th skin condition perception data, c i represents the structural correlation coefficient of the i-th skin condition perception data, x represents the number of algorithm operations, and ω represents the error adjustment value of the skin fatigue assessment algorithm.

[0045] The present invention constructs a skin fatigue assessment algorithm, which provides an assessment result of skin fatigue by integrating multiple skin state perception data and considering the weight, redundancy, structural correlation and number of iterations of the data, which helps to objectively and comprehensively assess the fatigue level of the skin and the fatigue level of the current user. The number of parameters N for fatigue assessment can adjust and balance the weights of different parameters by using multiple parameters. Different parameters may contribute differently to fatigue assessment, and some parameters may be more important. By integrating multiple parameters, the importance of each parameter can be comprehensively considered to obtain a more accurate skin fatigue assessment result; the weight coefficient a of the ith skin state perception data i, the weight coefficient indicates the importance of each skin condition perception data to the evaluation result. By adjusting the weight coefficient, the influence of certain data can be highlighted or weakened, thereby more accurately reflecting the skin fatigue degree. The data redundancy b of the i-th skin condition perception data i , the data redundancy parameter indicates the redundancy degree of each skin state perception data. By considering the redundancy of the data, the influence of redundant information on the evaluation results can be eliminated, and the accuracy and reliability of the evaluation can be improved. A higher redundancy value can reduce the weight of the data and reduce its influence in the calculation, thereby more accurately reflecting the fatigue degree; the structural correlation coefficient c of the i-th skin state perception data i , the structural correlation coefficient represents the degree of correlation between skin condition perception data. By considering the structural correlation of the data, the skin fatigue degree can be evaluated more accurately. A higher structural correlation coefficient indicates a stronger correlation between the data, which can increase its weight and make it play a greater role in the evaluation; the value of the number of algorithm operations x, the number of algorithm iterations represents the number of iterative operations of the algorithm. Through multiple iterative operations, the evaluation results can be gradually optimized and the accuracy and stability of the algorithm can be improved. A larger number of iterations can more fully consider the comprehensive effects of each data and obtain more reliable fatigue evaluation results; the error adjustment value ω of the skin fatigue evaluation algorithm, the error adjustment value is used to correct the error of the evaluation result. By adjusting the error value, the evaluation result can be corrected to further improve the accuracy and reliability of the evaluation. Appropriate error adjustment can overcome the deviation or error in the algorithm and make the evaluation result closer to the actual skin fatigue degree.

[0046] Preferably, step S3 comprises the following steps:

[0047] Step S31: extracting environmental data of the home real-time environment to obtain home real-time environmental data, wherein the home real-time environmental data includes body-sensing environmental data and sanitary environmental data;

[0048] Step S32: Obtain user historical activity trajectory data;

[0049] Step S33: performing a volatility analysis on the body-sensing environment data to obtain body-sensing environment volatility data;

[0050] Step S34: monitoring key sanitary environment areas according to the user's historical activity trajectory data to obtain key sanitary environment area data;

[0051] Step S35: performing environmental perception evaluation on the sanitary environment data according to the key sanitary environment area data to obtain an environmental perception coefficient;

[0052] Step S36: performing environmental perception compensation on the body-sensing environmental fluctuation data according to the environmental perception coefficient to obtain environmental perception data;

[0053] Step S37: Perform sensory fatigue analysis on the skin fatigue perception data based on the environmental perception data to obtain sensory fatigue data.

[0054] By extracting real-time home environment data, the present invention can obtain information on environmental parameters, including somatosensory environment data (such as temperature, humidity, and light) and sanitary environment data (such as air quality, noise level, and floor cleanliness). These data can be used as input for subsequent steps for analysis of environmental perception and skin fatigue perception; user historical activity trajectory data provides a record of users' activities in the home environment. These data can be used for key sanitary environment area monitoring and environmental perception evaluation in subsequent steps, helping to determine the areas where users often move at home, and conducting more targeted environmental perception and fatigue perception analysis; by performing volatility analysis on somatosensory environment data, the degree of change of the somatosensory environment can be evaluated, which helps to understand the stability and changes of the environment, and provides an important reference for subsequent environmental perception and fatigue perception analysis; by analyzing user historical activity trajectory data, it is possible to determine the user's activities at home. By monitoring the sanitary environment in key areas of activities, such as kitchens and bathrooms, we can pay more targeted attention to the sanitary conditions of key areas and improve the accuracy and reliability of fatigue perception. By evaluating the data of key sanitary environment areas, we can understand the status of the sanitary environment. The environmental perception coefficient obtained according to the evaluation results can be used for environmental perception compensation and fatigue perception analysis in subsequent steps to provide more accurate environmental perception data. By applying the environmental perception coefficient to the somatosensory environmental volatility data, the somatosensory environmental data can be compensated to further improve the accuracy and reliability of the environmental perception data, which helps to more comprehensively understand the impact of the environment on the skin and provide a more accurate data basis for subsequent fatigue perception analysis. Sensory fatigue analysis is performed on skin fatigue perception data based on environmental perception data to analyze the correlation between the two, which helps to understand the impact of the environment on sensory fatigue.

[0055] Preferably, step S36 includes the following steps:

[0056] Step S361: performing a fluctuation dispersion degree analysis on the somatosensory environment fluctuation data to obtain somatosensory fluctuation dispersion degree data;

[0057] Step S362: Analyze the data fluctuation distribution law according to the somatosensory fluctuation dispersion data to obtain somatosensory fluctuation distribution law data;

[0058] Step S363: constructing a minimum spanning tree for the somatosensory fluctuation regularity distribution data to obtain somatosensory regularity distribution graph data;

[0059] Step S364: dividing the body sense regularity distribution map data into weight subsets to obtain distribution map weight subset data;

[0060] Step S365: performing fitting evaluation on the distribution graph weight subset data to obtain body sense fitting distribution data;

[0061] Step S366: Perform environmental perception compensation on the body sense fitting distribution data according to the environmental perception coefficient to obtain environmental perception data.

[0062] The present invention can evaluate the degree of fluctuation of the somatosensory environment by analyzing the degree of fluctuation dispersion of the somatosensory environment fluctuation data. The somatosensory fluctuation dispersion data provides information on environmental fluctuation, which helps to understand the changes in the environment and provides a basis for data analysis in subsequent steps; by analyzing the somatosensory fluctuation dispersion data, the distribution law of somatosensory fluctuations can be understood, and the somatosensory fluctuation law distribution data provides the distribution of fluctuations in different time periods or regions, which helps to further understand the volatility characteristics of the environment; by constructing a minimum spanning tree, the somatosensory fluctuation law distribution data can be converted into a graphical representation, and the somatosensory law distribution graph data can reflect the correlation of environmental fluctuations, help identify important fluctuation paths and nodes, and provide more comprehensive visual information for subsequent analysis; By performing weighted subset division on the sensory law distribution map data, the nodes in the map can be divided into different subsets according to their importance in the fluctuation law. The weighted subset data of the distribution map provides information on important nodes of volatility, which is helpful for further analysis and understanding of the characteristics of the environment; by performing fitting evaluation on the weighted subset data of the distribution map, the distribution of volatility can be further evaluated and optimized. The somatosensory fitting distribution data provides a more accurate fitting result for volatility, providing an accurate data basis for subsequent environmental perception compensation; by applying the environmental perception coefficient to the somatosensory fitting distribution data, the data can be compensated to improve the accuracy of the environmental perception data. The environmental perception data provides more accurate somatosensory environmental data, which is helpful for further analysis and understanding of the impact of the environment on the skin.

[0063] Preferably, step S4 comprises the following steps:

[0064] Step S41: inputting the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer, thereby obtaining the control platform intelligent perception layer; issuing the initial perception instruction according to the control platform intelligent perception layer, thereby obtaining the initial perception instruction data;

[0065] Step S42: performing instruction parsing on the initial sensing instruction data to obtain sensing instruction parsing data;

[0066] Step S43: performing instruction modularization processing on the perception instruction parsing data to obtain perception modularization instruction data;

[0067] Step S44: inputting the sensory fatigue data into the IoT perception control platform for instruction operation adaptation based on the perception modularization instruction data to obtain standard IoT perception instruction data;

[0068] Step S45: Perform command linkage processing on the smart home according to the standard IoT sensing command data to obtain a smart linkage home strategy.

[0069] The present invention can construct an intelligent perception layer of the control platform by inputting skin fatigue perception data into the Internet of Things perception control platform. The intelligent perception layer of the control platform uses the fatigue perception data to issue initial perception instructions and generate initial perception instruction data, which helps to connect the perception data with the control platform and provides a basis for subsequent instruction processing and intelligent linkage; by performing instruction parsing on the initial perception instruction data, the instruction data can be parsed and extracted, and the perception instruction parsed data provides detailed information on the instructions, including instruction type, parameters and target devices, which helps to understand and process the meaning of the instructions and provides an accurate data basis for subsequent instruction processing; by performing modular processing on the perception instruction parsed data, the instruction data can be classified and organized according to modules, and the perception modular instruction data divides the instructions into different modules, which helps to process the instructions. More refined and flexible processing can be performed, which is conducive to improving the maintainability and scalability of instructions, and providing a better foundation for subsequent instruction operation adaptation; by inputting sensory fatigue data into the Internet of Things perception control platform for instruction operation adaptation based on perception modular instruction data, the perception data can be matched with the instruction operation. The standard Internet of Things perception instruction data provides the instruction format and requirements that adapt to the Internet of Things control platform, which helps to achieve accurate execution and adaptation of instructions, which helps to convert perception data into operation instructions for smart homes; according to the standard Internet of Things perception instruction data, the command linkage processing of smart homes can realize the automated operation of smart homes. The smart linkage home strategy links smart home devices according to the instruction data to achieve coordinated operation and response, which helps to improve the comfort and convenience of the living environment and meet the personalized needs of users.

[0070] Preferably, step S41 is specifically:

[0071] Step S411: inputting the skin fatigue perception data into the IoT perception control platform for parameter extraction to obtain fatigue perception parameters;

[0072] Step S412: performing data dimensionality reduction on the fatigue perception parameters to obtain fatigue perception dimensionality reduction data;

[0073] Step S413: performing cluster analysis on the fatigue perception dimensionality reduction data to obtain fatigue perception cluster data;

[0074] Step S414: performing association analysis on the fatigue perception clustering data to obtain fatigue association perception data;

[0075] Step S415: constructing a control platform perception layer for fatigue-related perception data based on a convolutional neural network to obtain an intelligent perception layer for the control platform;

[0076] Step S416: Issue initial perception instructions according to the intelligent perception layer of the control platform to obtain initial perception instruction data.

[0077] The present invention can extract relevant fatigue perception parameters by inputting skin fatigue perception data into the IoT perception control platform, and these parameters can provide quantitative information about the degree and state of skin fatigue, and help understand the skin condition; by performing data dimension reduction on fatigue perception parameters, high-dimensional data can be converted into low-dimensional representations, which helps to reduce the redundancy and complexity of data and simplify the process of data analysis and processing; by performing cluster analysis on fatigue perception dimension reduction data, similar data can be classified and organized, and cluster analysis can help discover potential patterns and groups between skin fatigue states, providing a more comprehensive understanding; by performing association analysis on fatigue perception cluster data, the association relationship and interaction between different data can be discovered, and association analysis helps to reveal the correlation between skin fatigue perception data and help identify factors and features related to fatigue; by using a convolutional neural network-based method, fatigue association perception data is used to build an intelligent perception layer of the control platform, and such a perception layer can extract key features and patterns, help perceive the skin fatigue state and perform higher-level analysis and understanding; according to the analysis results of the intelligent perception layer of the control platform, initial perception instructions are formulated and issued. These instructions can provide initial control guidance based on the perception of the skin fatigue state, such as adjusting the environment, providing comfort, or performing specific interventions.

[0078] The beneficial effect of the present invention is that by performing functional differentiation analysis on smart homes, the functional characteristics and advantages of each smart device can be clearly understood, which is conducive to the subsequent interconnection between smart homes. By building an Internet of Things perception control system based on the functional difference data set, the interconnection and collaborative work between multiple smart devices can be achieved, so that users can control and manage various smart devices through a unified platform, improving the overall efficiency and convenience of the smart home system. By performing human skin condition analysis on the user's body shape, detailed data on the skin condition can be obtained, which is helpful to understand the user's skin health status and the user's current fatigue level at the same time. By performing fatigue evaluation on the skin condition perception data, the fatigue level of the user's skin can be determined, which is helpful to remind the user to take corresponding maintenance and conditioning measures in time to avoid excessive skin fatigue and damage; data extraction is performed on the real-time home environment to obtain Taking data about temperature, humidity, and light, this helps the smart home system to make corresponding adjustments and controls according to environmental changes, and provide a more comfortable and suitable living environment; based on the real-time home environment parameter data, the skin fatigue perception data is analyzed for sensory fatigue, and the degree of influence of the environment on the user's sensory fatigue can be judged, which helps the smart home system to provide corresponding adjustments and optimizations, and create a more comfortable and pleasant living environment. The skin fatigue perception data is input into the IoT perception control platform for perception layer construction, which can realize intelligent perception and response to user needs and environmental changes, which helps to provide personalized smart home experience and customized living environment; based on the control platform intelligent perception layer, the smart home is processed by command linkage, which can realize the collaborative work and linkage control between smart devices, which helps to improve the overall intelligence level of the smart home system and bring users a more intelligent, convenient and comfortable living experience. Therefore, the intelligent IoT perception method of a smart home of the present invention is an optimization process made on the traditional intelligent IoT perception technology, which solves the problem that the real-time fatigue state of the human body cannot be accurately identified, and the countermeasures to the real-time fatigue state of the human body are inaccurate, and the real-time fatigue state of the human body can be accurately identified, and accurate countermeasures can be made to identify the real-time fatigue state of the human body. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A schematic diagram of the steps of a smart IoT sensing method for a smart home;

[0080] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0081] Figure 3 for Figure 2 Detailed implementation steps of step S24 are shown in the flowchart.

[0082] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0083] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0084] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0085] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0086] To achieve this, please refer to Figures 1 to 3 , a smart home intelligent Internet of Things perception method, the method comprising the following steps:

[0087] Step S1: Perform functional differentiation analysis on smart homes to obtain a functional difference data set; build an intelligent IoT perception control system based on the functional difference data set to obtain an IoT perception control platform;

[0088] Step S2: Analyze the skin condition of the user's body to obtain skin condition perception data; evaluate the fatigue level of the skin condition perception data to obtain skin fatigue perception data;

[0089] Step S3: extracting environmental data of the real-time home environment to obtain real-time home environment data; performing sensory fatigue analysis on the skin fatigue perception data based on the real-time home environment data to obtain sensory fatigue data;

[0090] Step S4: Input the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer to obtain the control platform intelligent perception layer; perform command linkage processing on the smart home according to the control platform intelligent perception layer to obtain the smart linkage home strategy.

[0091] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a smart home intelligent IoT perception method of the present invention. In this example, the smart home intelligent IoT perception method includes the following steps:

[0092] Step S1: Perform functional differentiation analysis on smart homes to obtain a functional difference data set; build an intelligent IoT perception control system based on the functional difference data set to obtain an IoT perception control platform;

[0093] In an embodiment of the present invention, relevant information and function lists of smart homes are collected through smart home factory manuals, functional differentiation analysis is performed, functional differences of different smart home products are compared, and they are organized into a functional difference data set. Based on the functional difference data set, an intelligent Internet of Things perception control system is designed and built, and an Internet of Things perception control platform is created for integrating and managing smart home devices and their functions.

[0094] Step S2: Analyze the skin condition of the user's body to obtain skin condition perception data; evaluate the fatigue level of the skin condition perception data to obtain skin fatigue perception data;

[0095] In an embodiment of the present invention, a user posture analysis is performed, and appropriate methods and technologies, such as computer vision or sensor technology, are used to analyze the user's human skin condition, and human skin condition perception data, such as skin moisture, temperature, and light-related indicators, are collected and recorded. Fatigue assessment is performed based on the skin condition perception data, and the skin fatigue degree is analyzed and calculated using an appropriate algorithm or model to obtain skin fatigue perception data.

[0096] Step S3: extracting environmental data of the real-time home environment to obtain real-time home environment data; performing sensory fatigue analysis on the skin fatigue perception data based on the real-time home environment data to obtain sensory fatigue data;

[0097] In an embodiment of the present invention, the real-time home environment, such as indoor temperature, humidity, noise level, and air quality, is monitored and extracted, the real-time home environment data is collected and recorded, a corresponding data set is established, and sensory fatigue analysis is performed on skin fatigue perception data based on the real-time home environment data. The correlation between environmental parameters and skin fatigue is explored through a model or algorithm to obtain sensory fatigue data.

[0098] Step S4: Input the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer to obtain the control platform intelligent perception layer; perform command linkage processing on the smart home according to the control platform intelligent perception layer to obtain the smart linkage home strategy.

[0099] In an embodiment of the present invention, skin fatigue perception data is transmitted to the Internet of Things perception control platform to ensure the security and reliability of the data. Based on the skin fatigue perception data, an intelligent perception layer of the control platform is constructed, and appropriate algorithms and models are used to analyze and process the data to extract key features and patterns. According to the analysis results of the intelligent perception layer of the control platform, a smart linkage home strategy is formulated, including the command linkage processing of smart home devices, so as to achieve optimization and improvement of the home environment.

[0100] By performing functional differentiation analysis on smart homes, the present invention can clearly understand the functional characteristics and advantages of each smart device, which is conducive to the subsequent interconnection between smart homes. By building an Internet of Things perception control system based on the functional difference data set, the interconnection and collaborative work between multiple smart devices can be achieved, so that users can control and manage various smart devices through a unified platform, improving the overall efficiency and convenience of the smart home system. By performing human skin condition analysis on the user's body shape, detailed data on the skin condition can be obtained, which is helpful to understand the user's skin health status and the user's current fatigue level at the same time. By performing fatigue evaluation on the skin condition perception data, the fatigue level of the user's skin can be determined, which is helpful to remind the user to take corresponding maintenance and conditioning measures in time to avoid excessive skin fatigue and damage; data extraction is performed on the real-time home environment to obtain information about Temperature, humidity, and light data, which helps the smart home system to make corresponding adjustments and controls according to environmental changes, and provide a more comfortable and suitable living environment; sensory fatigue analysis of skin fatigue perception data based on home real-time environmental parameter data can determine the degree of influence of the environment on user sensory fatigue, which helps the smart home system to provide corresponding adjustments and optimizations, and create a more comfortable and pleasant living environment. The skin fatigue perception data is input into the IoT perception control platform for perception layer construction, which can realize intelligent perception and response to user needs and environmental changes, which helps to provide personalized smart home experience and customized living environment; based on the control platform intelligent perception layer, the smart home is processed by command linkage, which can realize the collaborative work and linkage control between smart devices, which helps to improve the overall intelligence level of the smart home system and bring users a more intelligent, convenient and comfortable living experience. Therefore, the intelligent IoT perception method of a smart home of the present invention is an optimization process made on the traditional intelligent IoT perception technology, which solves the problem of not being able to accurately identify the real-time fatigue state of the human body and the inaccurate response measures to the real-time fatigue state of the human body, accurately identifies the real-time fatigue state of the human body, and makes accurate response measures to identify the real-time fatigue state of the human body.

[0101] Preferably, step S1 comprises the following steps:

[0102] Step S11: functionally classify the smart home to obtain a functional category data set;

[0103] Step S12: performing functional differentiation analysis on the functional category data set to obtain a functional difference data set;

[0104] Step S13: formulating a connection protocol according to the functional difference data set to obtain connection protocol data;

[0105] Step S14: performing network port adaptation processing according to the connection protocol data to obtain network port adaptation data;

[0106] Step S15: Building a network transmission channel according to the network port adaptation data and the connection protocol data to obtain a network transmission channel;

[0107] Step S16: construct an intelligent IoT perception control system for the functional category data set according to the network transmission channel to obtain an IoT perception control platform.

[0108] In an embodiment of the present invention, relevant information and a function list of smart homes are collected through the smart home factory manual, and the smart homes are classified according to their functional characteristics and attributes into different functional categories, a functional category data set is established, and the functional category to which each smart home device belongs is recorded; according to the functional category data set, the differences and characteristics between different functional categories are compared, the functional differences between devices within each functional category are analyzed, the functional difference data are recorded, and a functional difference data set is established, including the characteristics and differences of each functional category; according to the functional difference data set, the connection protocol required for each functional category is determined, and a corresponding connection protocol is formulated for each functional category to ensure that different devices can communicate and interoperate, and a connection protocol data set is established to record the connection protocol used by each functional category; according to the connection protocol data set, the connection protocol required for each functional category is determined Network ports and communication methods, perform network port adaptation processing on devices of each functional category to ensure that devices can communicate through the corresponding network ports, establish a network port adaptation data set, and record the network ports and adaptation methods required for devices of each functional category; combine connection protocol data and network port adaptation data to build a network transmission channel to ensure data transmission and communication between devices, configure network equipment and routers, and establish a stable network connection to support the communication needs between smart home devices, ensure the security and reliability of the network transmission channel, and prevent data leakage and interference; based on the established network transmission channel, build an intelligent Internet of Things perception control system, associate the functional category data set with the network transmission channel, realize data collection, transmission and control of smart home devices, and create an Internet of Things perception control platform for integrating and managing smart home devices and their functions.

[0109] By classifying the functions of smart homes, the present invention can divide and classify smart devices according to their functional characteristics and uses, which helps users better understand smart devices of different functional categories and choose devices that meet their own needs in a targeted manner; by performing functional differentiation analysis based on functional categories, the functional differences between different devices in each functional category can be deeply studied, which helps users to more clearly understand the characteristics and advantages of each device and provide specific references and bases for purchase and use; according to the functional difference data set, a connection protocol suitable for devices of each functional category is formulated, which helps to achieve connection and communication between different devices, so that they can cooperate and work together; according to the connection protocol According to the network port adaptation data and connection protocol data, network port adaptation processing is performed to ensure that the network ports of each device can be correctly matched and adapted, which helps to ensure smooth data transmission and communication between devices and improve the reliability and stability of the system; according to the network port adaptation data and connection protocol data, a network transmission channel suitable for each device is built, which helps to achieve effective connection of data transmission and communication between devices and provide a stable foundation for the overall operation of the system; based on the network transmission channel, an intelligent IoT perception control system is built for the functional category data set, which helps to integrate various smart devices into a unified platform, realize their centralized control and management, and improve the overall efficiency and convenience of the smart home system.

[0110] Preferably, step S12 comprises the following steps:

[0111] Step S121: extracting features from the function category data set to obtain function category feature data;

[0112] Step S122: performing maximum similarity evaluation on the functional category feature data to obtain functional category similarity data;

[0113] Step S123: performing cluster analysis on the functional category similarity data to obtain functional category cluster data;

[0114] Step S124: performing difference normal distribution division on the function category data set according to the function category clustering data to obtain function difference sample data;

[0115] Step S125: Calculate the sample variance of the functional difference sample data to obtain the functional difference sample variance data;

[0116] Step S126: performing unbiased estimation analysis of functional differences based on the functional difference sample variance data and the functional difference sample data to obtain a functional difference data set.

[0117] In an embodiment of the present invention, the features of each functional category are extracted from a functional category data set, and the features may include functional descriptions, technical specifications, and performance parameters of the device. A functional category feature data set is established to record feature information of each functional category. Based on the functional category feature data set, the similarity between different functional categories is calculated, and the functional category features are compared and analyzed using a similarity evaluation method (such as cosine similarity and Euclidean distance), and a functional category similarity data set is established to record the degree of similarity between different functional categories. Based on the functional category similarity data set, a clustering algorithm (such as K-means and hierarchical clustering) is applied to group the functional categories, and the functional categories are divided into different clusters according to similarity measurement indicators and the results of the clustering algorithm, and a functional category clustering data set is established to record the similarity of each cluster. Functional category, according to the functional category clustering data set, the functional category data set is divided into difference normal distribution, and the degree of difference of functional category is determined by statistical analysis methods, such as normal distribution, mean and standard deviation, etc. The functional category data set is divided into different difference samples, each sample represents a degree of functional difference, and the variance of each sample is calculated based on the functional difference sample data. The variance reflects the degree of data variation within the functional difference sample, and a functional difference sample variance data set is established to record the variance value of each sample; the functional difference sample variance data and the functional difference sample data are combined to perform unbiased estimation analysis of functional differences, and statistical methods, such as confidence interval and hypothesis test, are used to infer and estimate the functional difference data, and a functional difference data set is established to record the estimation results and confidence levels of functional differences.

[0118] The present invention performs feature extraction on the function category data set, and can extract the key features describing each function category, which helps to accurately capture the differences and characteristics between devices of different function categories, and provides a basis for subsequent analysis and evaluation; by performing maximum similarity evaluation on the function category feature data, the similarity between the function categories can be determined, which helps to find the commonalities and similarities between the function categories, and provides guidance for subsequent cluster analysis; cluster analysis based on the function category similarity data can divide the function category data into different cluster clusters, which helps to classify devices with similar functional characteristics into the same category, and provide more detailed and accurate classification results for functional differentiation analysis; according to the function category Clustering data, dividing the functional category data set into normal distribution with differences, which helps to quantify and divide the degree of difference of equipment in different functional categories, and provide specific degree of difference data for subsequent analysis and evaluation; performing sample variance calculation on the functional difference sample data can measure the degree of difference between different functional categories in the functional category data set, which helps to more accurately evaluate the differences between equipment in different functional categories and provide a data basis for unbiased estimation of functional differences; performing unbiased estimation analysis of functional differences based on functional difference sample variance data and functional difference sample data helps to make more accurate and reliable estimates of the functional difference data set, and provide a more reliable basis for subsequent decision-making and selection.

[0119] Preferably, step S2 comprises the following steps:

[0120] Step S21: performing infrared imaging scanning on the user's body to obtain infrared data of the user's body;

[0121] Step S22: extracting body temperature distribution data according to the user's body infrared data to obtain body temperature distribution data;

[0122] Step S23: dividing the body temperature distribution data into abnormal temperature regions to obtain abnormal temperature region data;

[0123] Step S24: Analyze the human skin condition based on the abnormal temperature area data to obtain skin condition perception data;

[0124] Step S25: Use a skin fatigue assessment algorithm to perform fatigue assessment on the skin state perception data to obtain skin fatigue perception data.

[0125] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0126] Step S21: performing infrared imaging scanning on the user's body to obtain infrared data of the user's body;

[0127] In the embodiment of the present invention, an infrared imaging device is used to scan the user's body. The infrared imaging device can detect infrared radiation emitted by the human body, obtain infrared data of the user's body, and record and save the infrared data for subsequent processing and analysis.

[0128] Step S22: extracting body temperature distribution data according to the user's body infrared data to obtain body temperature distribution data;

[0129] In an embodiment of the present invention, based on the user's body infrared data, the body temperature information of each area is extracted, and image processing and computer vision technology are used to analyze the infrared data and extract the body temperature distribution information, establish a body temperature distribution data set, and record the body temperature value of each area.

[0130] Step S23: dividing the body temperature distribution data into abnormal temperature regions to obtain abnormal temperature region data;

[0131] In an embodiment of the present invention, a threshold range of abnormal temperature is determined based on a body temperature distribution data set, the body temperature distribution is divided by thresholds, areas exceeding the thresholds are marked as abnormal temperature areas, an abnormal temperature area data set is established, and the location and size of each abnormal temperature area are recorded.

[0132] Step S24: Analyze the human skin condition based on the abnormal temperature area data to obtain skin condition perception data;

[0133] In the embodiment of the present invention, the abnormal temperature area data is used to analyze the human skin condition, and the fatigue level of the skin at that time is inferred based on the location and size of the abnormal temperature area, and a skin condition perception data set is established to record information related to the skin condition.

[0134] Step S25: Use a skin fatigue assessment algorithm to perform fatigue assessment on the skin state perception data to obtain skin fatigue perception data.

[0135] In an embodiment of the present invention, a skin fatigue assessment algorithm is applied to assess skin fatigue based on a skin state perception data set. The fatigue assessment algorithm may use statistical analysis or machine learning methods to determine the degree of fatigue based on skin state data, establish a skin fatigue perception data set, and record the degree of skin fatigue and related assessment results.

[0136] The present invention can obtain the user's body infrared data by performing infrared imaging scanning on the user's body, which helps to obtain the user's body temperature information and provide a data basis for subsequent analysis and judgment; based on the user's body infrared data, the body temperature distribution data is extracted, which helps to understand the distribution of the user's body temperature and grasp the user's overall body temperature condition; according to the body temperature distribution data, the abnormal temperature area is divided. This helps to identify the area where the user's body temperature is abnormal, which may indicate potential health problems; based on the abnormal temperature area data, the human skin state is analyzed, which helps to further understand the user's skin condition, and the skin fatigue assessment algorithm is used to assess the fatigue of the skin state perception data, which helps to assess the user's skin fatigue level and guide the user to take appropriate care and health care measures.

[0137] Preferably, step S24 comprises the following steps:

[0138] Step S241: Analyze the skin microstructure based on the abnormal temperature area data to obtain skin microstructure data;

[0139] Step S242: monitoring skin humidity based on the skin microstructure data to obtain skin humidity data;

[0140] Step S243: performing stratum corneum analysis according to the skin microstructure data to obtain skin stratum corneum data;

[0141] Step S244: Calculate pH according to the skin stratum corneum data and the skin humidity data to obtain skin pH data;

[0142] Step S245: Analyze the distribution state of skin secretions according to the skin microstructure data to obtain skin secretion distribution data;

[0143] Step S246: performing skin sensitivity analysis according to the skin secretion distribution data and the skin pH data to obtain skin sensitivity data;

[0144] Step S247: Analyze the skin sensitivity data based on the human skin condition to obtain skin condition perception data.

[0145] As an example of the present invention, refer to Figure 3 As shown, in this example, step S24 includes:

[0146] Step S241: Analyze the skin microstructure based on the abnormal temperature area data to obtain skin microstructure data;

[0147] In the embodiment of the present invention, the skin microstructure analysis of the abnormal area can be performed using a dermatoscope or a microscope device to observe the details and structure of the skin, and record and save the skin microstructure data, including pore conditions, skin texture, and subcutaneous tissue information.

[0148] Step S242: monitoring skin humidity based on the skin microstructure data to obtain skin humidity data;

[0149] In the embodiment of the present invention, the skin microstructure data is used to analyze the moisture condition of the skin, a humidity measuring device or sensor is used to monitor the moisture of the skin, and the skin moisture data, including the moisture values ​​of different parts, are recorded and saved.

[0150] Step S243: performing stratum corneum analysis according to the skin microstructure data to obtain skin stratum corneum data;

[0151] In an embodiment of the present invention, the condition of the stratum corneum of the skin is analyzed based on the skin microstructure data, and a stratum corneum analysis device or method is used to measure and evaluate the thickness and smoothness index of the stratum corneum, and the skin stratum corneum data is recorded and saved, including the stratum corneum index values ​​of different areas.

[0152] Step S244: Calculate pH according to the skin stratum corneum data and the skin humidity data to obtain skin pH data;

[0153] In an embodiment of the present invention, the pH of the skin is calculated based on the skin stratum corneum data and the skin moisture data. The pH calculation method is used to calculate the pH level of the skin in combination with the stratum corneum index and the moisture value. The skin pH data is recorded and saved, including the pH values ​​of different parts.

[0154] Step S245: Analyze the distribution state of skin secretions according to the skin microstructure data to obtain skin secretion distribution data;

[0155] In an embodiment of the present invention, skin microstructure data is used to observe and analyze the distribution status of skin secretions. A microscope or other appropriate equipment is used to observe the distribution of skin secretions, such as oil and sweat, and the skin secretion distribution data is recorded and saved, including secretion status information in different areas.

[0156] Step S246: performing skin sensitivity analysis according to the skin secretion distribution data and the skin pH data to obtain skin sensitivity data;

[0157] In an embodiment of the present invention, the sensitivity of the skin is analyzed based on the skin secretion distribution data and the skin pH data, and the skin sensitivity to external stimuli is evaluated by combining the secretion distribution and pH information. The skin sensitivity data is recorded and saved, including the sensitivity evaluation results of different parts.

[0158] Step S247: Analyze the skin sensitivity data based on the human skin condition to obtain skin condition perception data.

[0159] In the embodiment of the present invention, skin sensitivity data is used to analyze the state of human skin. Based on the evaluation results of the sensitivity data, it is determined whether the skin is in a sensitive state or has other skin problems. A skin state perception data set is established to record information related to the skin state.

[0160] The present invention analyzes the skin microstructure based on the abnormal temperature area data, which helps to understand the subtle structural characteristics of the skin, including pores and skin texture, and provides a basis for subsequent analysis. The skin humidity is monitored based on the skin microstructure data, which helps to understand the moisture content and humidity status of the skin, and provides a reference for skin moisturizing and care. The stratum corneum is analyzed based on the skin microstructure data, which helps to understand the thickness and health index of the stratum corneum, and evaluate the current body comfort. The pH is calculated based on the skin stratum corneum data and skin humidity data, which helps to evaluate the acid-base balance of the skin and provide a reference for the skin pH. It provides a reference for regulation and acid-base balance; it analyzes the distribution status of skin secretions based on skin microstructure data, which helps to understand the distribution of skin secretions, such as oil secretion and sweat secretion, and provides guidance for skin oil control and cleansing; it analyzes skin sensitivity based on skin secretion distribution data and skin pH data, which helps to assess skin sensitivity and guide users to choose appropriate skin care products and care methods; it perceives the state of human skin based on skin sensitivity data, which helps to fully understand the user's skin condition, including moisture balance, health of the stratum corneum, and sensitivity, and provides users with personalized skin care suggestions and maintenance plans.

[0161] Preferably, the skin fatigue evaluation algorithm in step S25 is as follows:

[0162]

[0163] Where f represents the skin fatigue perception result value, N represents the number of fatigue evaluation parameters, and a i represents the weight coefficient of the i-th skin condition perception data, b i represents the data redundancy of the i-th skin condition perception data, c i represents the structural correlation coefficient of the i-th skin condition perception data, x represents the number of algorithm operations, and ω represents the error adjustment value of the skin fatigue assessment algorithm.

[0164] The present invention constructs a skin fatigue assessment algorithm, which provides an assessment result of skin fatigue by integrating multiple skin state perception data and considering the weight, redundancy, structural correlation and number of iterations of the data, which helps to objectively and comprehensively assess the fatigue level of the skin and the fatigue level of the current user. The number of parameters N for fatigue assessment can adjust and balance the weights of different parameters by using multiple parameters. Different parameters may contribute differently to fatigue assessment, and some parameters may be more important. By integrating multiple parameters, the importance of each parameter can be comprehensively considered to obtain a more accurate skin fatigue assessment result; the weight coefficient a of the ith skin state perception data i , the weight coefficient indicates the importance of each skin condition perception data to the evaluation result. By adjusting the weight coefficient, the influence of certain data can be highlighted or weakened, thereby more accurately reflecting the skin fatigue degree. The data redundancy b of the i-th skin condition perception data i , the data redundancy parameter indicates the redundancy degree of each skin state perception data. By considering the redundancy of the data, the influence of redundant information on the evaluation results can be eliminated, and the accuracy and reliability of the evaluation can be improved. A higher redundancy value can reduce the weight of the data and reduce its influence in the calculation, thereby more accurately reflecting the fatigue degree; the structural correlation coefficient c of the i-th skin state perception data i , the structural correlation coefficient represents the degree of correlation between skin condition perception data. By considering the structural correlation of the data, the skin fatigue degree can be evaluated more accurately. A higher structural correlation coefficient indicates a stronger correlation between the data, which can increase its weight and make it play a greater role in the evaluation; the value of the number of algorithm operations x, the number of algorithm iterations represents the number of iterative operations of the algorithm. Through multiple iterative operations, the evaluation results can be gradually optimized and the accuracy and stability of the algorithm can be improved. A larger number of iterations can more fully consider the comprehensive effects of each data and obtain more reliable fatigue evaluation results; the error adjustment value ω of the skin fatigue evaluation algorithm, the error adjustment value is used to correct the error of the evaluation result. By adjusting the error value, the evaluation result can be corrected to further improve the accuracy and reliability of the evaluation. Appropriate error adjustment can overcome the deviation or error in the algorithm and make the evaluation result closer to the actual skin fatigue degree.

[0165] Preferably, step S3 comprises the following steps:

[0166] Step S31: extracting environmental data of the home real-time environment to obtain home real-time environmental data, wherein the home real-time environmental data includes body-sensing environmental data and sanitary environmental data;

[0167] Step S32: Obtain user historical activity trajectory data;

[0168] Step S33: performing a volatility analysis on the body-sensing environment data to obtain body-sensing environment volatility data;

[0169] Step S34: monitoring key sanitary environment areas according to the user's historical activity trajectory data to obtain key sanitary environment area data;

[0170] Step S35: performing environmental perception evaluation on the sanitary environment data according to the key sanitary environment area data to obtain an environmental perception coefficient;

[0171] Step S36: performing environmental perception compensation on the body-sensing environmental fluctuation data according to the environmental perception coefficient to obtain environmental perception data;

[0172] Step S37: Perform sensory fatigue analysis on the skin fatigue perception data based on the environmental perception data to obtain sensory fatigue data.

[0173] In an embodiment of the present invention, sensors or devices are deployed in a home environment to monitor the environment, and real-time environmental data are extracted from the sensors or devices, including temperature, humidity, light intensity, air quality somatosensory environmental data, as well as noise level, air pollution level, room cleanliness, and sanitary environmental data; real-time home environmental data, including somatosensory environmental data and sanitary environmental data, are recorded and saved; historical activity trajectory data of users are obtained, and user historical activity trajectory data can be collected, stored, and managed through mobile devices, smart home devices, or other related systems, including user movement paths and activity area information in the home environment; somatosensory environmental data are used to perform volatility analysis to evaluate changes in environmental parameters; statistical or data analysis methods are used to calculate volatility indicators of somatosensory environmental parameters, such as the temperature change range and humidity fluctuation degree; somatosensory environmental volatility data are generated and recorded to reflect the fluctuation of environmental parameters; based on the user's historical activity trajectory data, key sanitary environmental areas, such as kitchens and bathrooms, that may have health effects are identified. For areas with important impact, sensors or equipment are deployed in key areas to monitor relevant sanitary environment parameters, such as air quality and bacterial concentration; data of key sanitary environment areas are extracted and recorded, including the values ​​of sanitary environment parameters of key areas; based on the data of key sanitary environment areas, the overall sanitary environment data is evaluated; according to the sanitary environment parameters of key areas, the environmental perception coefficient is calculated to quantify the impact of the sanitary environment on the overall environment; the environmental perception coefficient is recorded and saved to reflect the perception of the sanitary environment on the overall environment; the somatosensory environmental volatility data is compensated by using the environmental perception coefficient; the somatosensory environmental volatility data is adjusted according to the environmental perception coefficient to accurately reflect the impact of the environment on human perception; the environmental perception data is generated and recorded, including the compensated somatosensory environmental volatility data; the environmental perception data and other relevant data are used to conduct sensory fatigue analysis; data analysis and model algorithms are used to evaluate the impact of environmental factors on skin fatigue perception; sensory fatigue data is generated and recorded to reflect the impact of the environment on skin fatigue.

[0174] By extracting real-time home environment data, the present invention can obtain information on environmental parameters, including somatosensory environment data (such as temperature, humidity, and light) and sanitary environment data (such as air quality, noise level, and floor cleanliness). These data can be used as input for subsequent steps for analysis of environmental perception and skin fatigue perception; user historical activity trajectory data provides a record of users' activities in the home environment. These data can be used for key sanitary environment area monitoring and environmental perception evaluation in subsequent steps, helping to determine the areas where users often move at home, and conducting more targeted environmental perception and fatigue perception analysis; by performing volatility analysis on somatosensory environment data, the degree of change of the somatosensory environment can be evaluated, which helps to understand the stability and changes of the environment, and provides an important reference for subsequent environmental perception and fatigue perception analysis; by analyzing user historical activity trajectory data, it is possible to determine the user's activities at home. By monitoring the sanitary environment in key areas of activities, such as kitchens and bathrooms, we can pay more targeted attention to the sanitary conditions of key areas and improve the accuracy and reliability of fatigue perception. By evaluating the data of key sanitary environment areas, we can understand the status of the sanitary environment. The environmental perception coefficient obtained according to the evaluation results can be used for environmental perception compensation and fatigue perception analysis in subsequent steps to provide more accurate environmental perception data. By applying the environmental perception coefficient to the somatosensory environmental volatility data, the somatosensory environmental data can be compensated to further improve the accuracy and reliability of the environmental perception data, which helps to more comprehensively understand the impact of the environment on the skin and provide a more accurate data basis for subsequent fatigue perception analysis. Sensory fatigue analysis is performed on skin fatigue perception data based on environmental perception data to analyze the correlation between the two, which helps to understand the impact of the environment on sensory fatigue.

[0175] Preferably, step S36 includes the following steps:

[0176] Step S361: performing a fluctuation dispersion degree analysis on the somatosensory environment fluctuation data to obtain somatosensory fluctuation dispersion degree data;

[0177] Step S362: Analyze the data fluctuation distribution law according to the somatosensory fluctuation dispersion data to obtain somatosensory fluctuation distribution law data;

[0178] Step S363: constructing a minimum spanning tree for the somatosensory fluctuation regularity distribution data to obtain somatosensory regularity distribution graph data;

[0179] Step S364: dividing the body sense regularity distribution map data into weight subsets to obtain distribution map weight subset data;

[0180] Step S365: performing fitting evaluation on the distribution graph weight subset data to obtain body sense fitting distribution data;

[0181] Step S366: Perform environmental perception compensation on the body sense fitting distribution data according to the environmental perception coefficient to obtain environmental perception data.

[0182] In an embodiment of the present invention, a statistical or data analysis method is used to analyze the degree of dispersion of the somatosensory environment volatility data, calculate the dispersion index of the somatosensory environment volatility data, such as the standard deviation and variance, generate and record the somatosensory fluctuation dispersion data, and reflect the degree of dispersion of the somatosensory environment volatility; based on the somatosensory fluctuation dispersion data, the distribution law of the somatosensory environment volatility is analyzed, and the statistical characteristics and distribution form of the somatosensory fluctuation dispersion data are explored by using the data analysis method, and the somatosensory fluctuation law distribution data is generated and recorded to describe the distribution law of the somatosensory environment volatility; based on the somatosensory fluctuation law distribution data, a minimum spanning tree is constructed, and the data points in the somatosensory fluctuation law distribution data are regarded as nodes of the graph, and the nodes are connected by the minimum spanning tree algorithm to construct a somatosensory law distribution graph, and the somatosensory law distribution graph data is generated and recorded to reflect the distribution of the somatosensory fluctuation law. Structure, based on the somatosensory law distribution map data, weight subset division is performed, the nodes in the somatosensory law distribution map are divided into different weight subsets, and the division can be performed according to the position and connection relationship of the nodes, and the distribution map weight subset data is generated and recorded to describe the weight subset structure of the somatosensory law distribution map; based on the distribution map weight subset data, fitting evaluation is performed, and the distribution map weight subset data is fitted with an appropriate mathematical model using a fitting method to evaluate the degree of fit with the model, and somatosensory fitting distribution data is generated and recorded to reflect the fitting of the distribution map weight subset data, and the somatosensory fitting distribution data is compensated by using the environmental perception coefficient, and the somatosensory fitting distribution data is adjusted according to the environmental perception coefficient to accurately reflect the degree of influence of the environment on human perception, and the environmental perception data is generated and recorded, including the compensated somatosensory fitting distribution data.

[0183] The present invention can evaluate the degree of fluctuation of the somatosensory environment by analyzing the degree of fluctuation dispersion of the somatosensory environment fluctuation data. The somatosensory fluctuation dispersion data provides information on environmental fluctuation, which helps to understand the changes in the environment and provides a basis for data analysis in subsequent steps; by analyzing the somatosensory fluctuation dispersion data, the distribution law of somatosensory fluctuations can be understood, and the somatosensory fluctuation law distribution data provides the distribution of fluctuations in different time periods or regions, which helps to further understand the volatility characteristics of the environment; by constructing a minimum spanning tree, the somatosensory fluctuation law distribution data can be converted into a graphical representation, and the somatosensory law distribution graph data can reflect the correlation of environmental fluctuations, help identify important fluctuation paths and nodes, and provide more comprehensive visual information for subsequent analysis; By performing weighted subset division on the sensory law distribution map data, the nodes in the map can be divided into different subsets according to their importance in the fluctuation law. The weighted subset data of the distribution map provides information on important nodes of volatility, which is helpful for further analysis and understanding of the characteristics of the environment; by performing fitting evaluation on the weighted subset data of the distribution map, the distribution of volatility can be further evaluated and optimized. The somatosensory fitting distribution data provides a more accurate fitting result for volatility, providing an accurate data basis for subsequent environmental perception compensation; by applying the environmental perception coefficient to the somatosensory fitting distribution data, the data can be compensated to improve the accuracy of the environmental perception data. The environmental perception data provides more accurate somatosensory environmental data, which is helpful for further analysis and understanding of the impact of the environment on the skin.

[0184] Preferably, step S4 comprises the following steps:

[0185] Step S41: inputting the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer, thereby obtaining the control platform intelligent perception layer; issuing the initial perception instruction according to the control platform intelligent perception layer, thereby obtaining the initial perception instruction data;

[0186] Step S42: performing instruction parsing on the initial sensing instruction data to obtain sensing instruction parsing data;

[0187] Step S43: performing instruction modularization processing on the perception instruction parsing data to obtain perception modularization instruction data;

[0188] Step S44: inputting the sensory fatigue data into the IoT perception control platform for instruction operation adaptation based on the perception modularization instruction data to obtain standard IoT perception instruction data;

[0189] Step S45: Perform command linkage processing on the smart home according to the standard IoT sensing command data to obtain a smart linkage home strategy.

[0190] In an embodiment of the present invention, skin fatigue perception data is transmitted to an IoT perception control platform, and an intelligent perception layer of a control platform is constructed on the IoT perception control platform. The layer is used to process and analyze the input perception data. Based on the analysis results of the intelligent perception layer of the control platform, an initial perception instruction is issued. The instruction is used to further process and control the perception data, generate and record initial perception instruction data, including the analysis results and initial instruction information of the intelligent perception layer of the control platform; parse the initial perception instruction data to extract key information and instruction content therein, process the initial perception instruction data to convert it into perception instruction parsed data that is easy to understand and operate, generate and record perception instruction parsed data, including key information and parsed results extracted from the initial instruction; modularize the instructions based on the perception instruction parsed data, decompose and classify the instruction content in the perception instruction parsed data, divide it into different modules or functional blocks, generate and record the perception instruction parsed data, and process the initial perception instruction data to extract key information and instruction content from the initial instruction. The method comprises the following steps: first, the sensory fatigue data is combined with the perception modular instruction data, and the sensory fatigue data is used as input to match and combine the sensory fatigue data with the perception modular instruction data through appropriate operation and adaptation methods; second, the instruction operation is adapted on the IoT perception control platform to generate standard IoT perception instruction data suitable for execution by IoT devices, and the standard IoT perception instruction data is generated and recorded for subsequent intelligent linkage processing. Based on the standard IoT perception instruction data, the smart home is subjected to instruction linkage processing, and the corresponding operations and linkage behaviors of the smart home devices are triggered according to the instruction content and device information in the instruction data, and the intelligent linkage home strategy is implemented to enable the smart home devices to be automatically controlled and coordinated according to the perception instruction data, and the intelligent linkage home strategy is generated and recorded to reflect the intelligent perception home linkage processing based on the standard IoT perception instruction data.

[0191] The present invention can construct an intelligent perception layer of the control platform by inputting skin fatigue perception data into the Internet of Things perception control platform. The intelligent perception layer of the control platform uses the fatigue perception data to issue initial perception instructions and generate initial perception instruction data, which helps to connect the perception data with the control platform and provides a basis for subsequent instruction processing and intelligent linkage; by performing instruction parsing on the initial perception instruction data, the instruction data can be parsed and extracted, and the perception instruction parsed data provides detailed information on the instructions, including instruction type, parameters and target devices, which helps to understand and process the meaning of the instructions and provides an accurate data basis for subsequent instruction processing; by performing modular processing on the perception instruction parsed data, the instruction data can be classified and organized according to modules, and the perception modular instruction data divides the instructions into different modules, which helps to process the instructions. More refined and flexible processing can be performed, which is conducive to improving the maintainability and scalability of instructions, and providing a better foundation for subsequent instruction operation adaptation; by inputting sensory fatigue data into the Internet of Things perception control platform for instruction operation adaptation based on perception modular instruction data, the perception data can be matched with the instruction operation. The standard Internet of Things perception instruction data provides the instruction format and requirements that adapt to the Internet of Things control platform, which helps to achieve accurate execution and adaptation of instructions, which helps to convert perception data into operation instructions for smart homes; according to the standard Internet of Things perception instruction data, the command linkage processing of smart homes can realize the automated operation of smart homes. The smart linkage home strategy links smart home devices according to the instruction data to achieve coordinated operation and response, which helps to improve the comfort and convenience of the living environment and meet the personalized needs of users.

[0192] Preferably, step S41 is specifically:

[0193] Step S411: inputting the skin fatigue perception data into the IoT perception control platform for parameter extraction to obtain fatigue perception parameters;

[0194] Step S412: performing data dimensionality reduction on the fatigue perception parameters to obtain fatigue perception dimensionality reduction data;

[0195] Step S413: performing cluster analysis on the fatigue perception dimensionality reduction data to obtain fatigue perception cluster data;

[0196] Step S414: performing association analysis on the fatigue perception clustering data to obtain fatigue association perception data;

[0197] Step S415: constructing a control platform perception layer for fatigue-related perception data based on a convolutional neural network to obtain an intelligent perception layer for the control platform;

[0198] Step S416: Issue initial perception instructions according to the intelligent perception layer of the control platform to obtain initial perception instruction data.

[0199] In an embodiment of the present invention, skin fatigue perception data is transmitted to an IoT perception control platform, a parameter extraction operation is performed on the IoT perception control platform, parameters related to fatigue perception are extracted from the input perception data, the fatigue perception parameters are sorted and processed to obtain accurate and useful fatigue perception parameter information, fatigue perception parameters are generated and recorded, including relevant parameter information extracted from the perception data, data dimensionality reduction processing is performed on the fatigue perception parameters to reduce the data dimension and retain key information, the fatigue perception parameters are processed to convert them into fatigue perception reduced dimensionality data with a lower dimension but still retaining meaningfulness, fatigue perception reduced dimensionality data is generated and recorded, including parameter information after dimensionality reduction, a clustering analysis operation is performed based on the fatigue perception reduced dimensionality data to group and classify the data, and the fatigue perception reduced dimensionality data is processed using an appropriate clustering algorithm or method to divide it into different clusters. Clustering, generate and record fatigue perception clustering data, including clustering results and corresponding cluster label information, perform association analysis operations based on fatigue perception clustering data, explore the association relationship between different clusters, process fatigue perception clustering data, find out the association rules and correlations therein, generate and record fatigue association perception data, including association rules and correlation information, use convolutional neural network (CNN) to process and analyze fatigue association perception data, build an appropriate CNN model, use fatigue association perception data as input, and obtain the control platform intelligent perception layer after processing and training at the network layer. The control platform intelligent perception layer can extract and learn fatigue-related features and patterns. Based on the analysis results and learning ability of the control platform intelligent perception layer, issue initial perception instructions, and generate initial perception instruction data based on the control platform intelligent perception layer's understanding and analysis of fatigue perception data.

[0200] The present invention can extract relevant fatigue perception parameters by inputting skin fatigue perception data into the IoT perception control platform, and these parameters can provide quantitative information about the degree and state of skin fatigue, and help understand the skin condition; by performing data dimension reduction on fatigue perception parameters, high-dimensional data can be converted into low-dimensional representations, which helps to reduce the redundancy and complexity of data and simplify the process of data analysis and processing; by performing cluster analysis on fatigue perception dimension reduction data, similar data can be classified and organized, and cluster analysis can help discover potential patterns and groups between skin fatigue states, providing a more comprehensive understanding; by performing association analysis on fatigue perception cluster data, the association relationship and interaction between different data can be discovered, and association analysis helps to reveal the correlation between skin fatigue perception data and help identify factors and features related to fatigue; by using a convolutional neural network-based method, fatigue association perception data is used to build an intelligent perception layer of the control platform, and such a perception layer can extract key features and patterns, help perceive the skin fatigue state and perform higher-level analysis and understanding; according to the analysis results of the intelligent perception layer of the control platform, initial perception instructions are formulated and issued. These instructions can provide initial control guidance based on the perception of the skin fatigue state, such as adjusting the environment, providing comfort, or performing specific interventions.

[0201] By performing functional differentiation analysis on smart homes, the present invention can clearly understand the functional characteristics and advantages of each smart device, which is conducive to the subsequent interconnection between smart homes. By building an Internet of Things perception control system based on the functional difference data set, the interconnection and collaborative work between multiple smart devices can be achieved, so that users can control and manage various smart devices through a unified platform, improving the overall efficiency and convenience of the smart home system. By performing human skin condition analysis on the user's body shape, detailed data on the skin condition can be obtained, which is helpful to understand the user's skin health status and the user's current fatigue level at the same time. By performing fatigue evaluation on the skin condition perception data, the fatigue level of the user's skin can be determined, which is helpful to remind the user to take corresponding maintenance and conditioning measures in time to avoid excessive skin fatigue and damage; data extraction is performed on the real-time home environment to obtain information about Temperature, humidity, and light data, which helps the smart home system to make corresponding adjustments and controls according to environmental changes, and provide a more comfortable and suitable living environment; sensory fatigue analysis of skin fatigue perception data based on home real-time environmental parameter data can determine the degree of influence of the environment on user sensory fatigue, which helps the smart home system to provide corresponding adjustments and optimizations, and create a more comfortable and pleasant living environment. The skin fatigue perception data is input into the IoT perception control platform for perception layer construction, which can realize intelligent perception and response to user needs and environmental changes, which helps to provide personalized smart home experience and customized living environment; based on the control platform intelligent perception layer, the smart home is processed by command linkage, which can realize the collaborative work and linkage control between smart devices, which helps to improve the overall intelligence level of the smart home system and bring users a more intelligent, convenient and comfortable living experience. Therefore, the intelligent IoT perception method of a smart home of the present invention is an optimization process made on the traditional intelligent IoT perception technology, which solves the problem of not being able to accurately identify the real-time fatigue state of the human body and the inaccurate response measures to the real-time fatigue state of the human body, accurately identifies the real-time fatigue state of the human body, and makes accurate response measures to identify the real-time fatigue state of the human body.

[0202] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0203] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A smart home intelligent Internet of Things perception method, characterized in that: The following steps are involved: Step S1: Perform functional differentiation analysis on smart homes to obtain a functional difference data set; build an intelligent IoT perception control system based on the functional difference data set to obtain an IoT perception control platform; Step S2: Analyze the skin condition of the user's body to obtain skin condition perception data; evaluate the fatigue level of the skin condition perception data to obtain skin fatigue perception data; Step S3: extracting environmental data of the real-time home environment to obtain real-time home environment data; performing sensory fatigue analysis on the skin fatigue perception data based on the real-time home environment data to obtain sensory fatigue data; Step S4: Input the skin fatigue perception data into the IoT perception control platform to construct the control platform perception layer to obtain the control platform intelligent perception layer; perform command linkage processing on the smart home according to the control platform intelligent perception layer to obtain the smart linkage home strategy; Step S1 includes the following steps: Step S11: functionally classify the smart home to obtain a functional category data set; Step S12: performing functional differentiation analysis on the functional category data set to obtain a functional difference data set; Step S13: formulating a connection protocol according to the functional difference data set to obtain connection protocol data; Step S14: performing network port adaptation processing according to the connection protocol data to obtain network port adaptation data; Step S15: Building a network transmission channel according to the network port adaptation data and the connection protocol data to obtain a network transmission channel; Step S16: Build an intelligent IoT perception control system for the functional category data set according to the network transmission channel to obtain an IoT perception control platform; Step S12 includes the following steps: Step S121: extracting features from the function category data set to obtain function category feature data; Step S122: performing maximum similarity evaluation on the functional category feature data to obtain functional category similarity data; Step S123: performing cluster analysis on the functional category similarity data to obtain functional category cluster data; Step S124: performing difference normal distribution division on the function category data set according to the function category clustering data to obtain function difference sample data; Step S125: Calculate the sample variance of the functional difference sample data to obtain the functional difference sample variance data; Step S126: Perform unbiased estimation analysis of functional differences based on functional difference sample variance data and functional difference sample data to obtain a functional difference data set; Step S2 includes the following steps: Step S21: performing infrared imaging scanning on the user's body to obtain infrared data of the user's body; Step S22: extracting body temperature distribution data according to the user's body infrared data to obtain body temperature distribution data; Step S23: dividing the body temperature distribution data into abnormal temperature regions to obtain abnormal temperature region data; Step S24: Analyze the human skin condition based on the abnormal temperature area data to obtain skin condition perception data; Step S25: Using the skin fatigue assessment algorithm to assess the fatigue of the skin state perception data to obtain skin fatigue perception data; Step S24 includes the following steps: Step S241: Analyze the skin microstructure based on the abnormal temperature area data to obtain skin microstructure data; Step S242: monitoring skin humidity based on the skin microstructure data to obtain skin humidity data; Step S243: performing stratum corneum analysis according to the skin microstructure data to obtain skin stratum corneum data; Step S244: Calculate pH according to the skin stratum corneum data and the skin humidity data to obtain skin pH data; Step S245: Analyze the distribution state of skin secretions according to the skin microstructure data to obtain skin secretion distribution data; Step S246: performing skin sensitivity analysis according to the skin secretion distribution data and the skin pH data to obtain skin sensitivity data; Step S247: Analyze the skin sensitivity data based on the human skin condition to obtain skin condition perception data.