Smart home control system and method based on wearable device

Abstract

The invention relates to the technical field of control systems, in particular to a smart home control system and method based on a wearable device, and the system comprises a behavior prediction module which collects physiological and behavior data generated by a user through the wearable device, calculates the behavior trend of the user in combination with time and activity types, and generates a behavior trend analysis result; and according to the behavior trend analysis result, predicting future use requirements of the household equipment of the user. According to the method, the behavior data and the physiological data of the user are combined, and the time and the activity type are fused, so that the calculation of the personalized behavior trend and the prediction of the future demand are realized. Through real-time acquisition and multi-dimensional analysis of environment data, a home environment state can be dynamically constructed, equipment requirements can be rapidly adjusted and matched, and the accuracy and adaptability of equipment operation are improved. Based on cooperative processing logic of behavior trend and environmental data, blindness of equipment response is avoided, and active response of user requirements and optimization of resource allocation are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems, and in particular to a smart home control system and method based on wearable devices. Background Art

[0002] Control system is an interdisciplinary technical field involving automation, electronics, computers, communications, and mechanical engineering. The core goal is to adjust and optimize the behavior or state of the target object by designing, analyzing, and implementing control devices or systems. Control systems usually consist of three main links: perception, decision-making, and execution. They obtain external environmental data through sensors, use control algorithms for real-time analysis and judgment, and achieve dynamic control of the system through actuators.

[0003] Existing smart home controls rely on a single variable when processing user behavior and environmental information, lacking comprehensive predictions of user behavior trends and environmental dynamics, making it difficult to accurately match device control with user needs. Environmental data processing is more of a static adjustment mode, lacking the ability to perceive and analyze in real time and in multiple dimensions. Device response lags are more obvious, especially in scenarios where user needs change rapidly or multiple devices are linked, making it difficult to ensure the immediacy and smoothness of operations. Therefore, improvements are needed. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a smart home control system and method based on wearable devices.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A smart home control system based on wearable devices comprises:

[0006] The behavior prediction module collects the physiological and behavioral data generated by the user through the wearable device, calculates the user's behavior trend in combination with the time and activity type, and generates a behavior trend analysis result; based on the behavior trend analysis result, predicts the user's future home device usage needs and generates predicted home demand information;

[0007] The environment perception module collects temperature, humidity and light data through environmental sensors deployed in the home, calculates the current environment status, and generates real-time environment status data; determines whether the home environment needs to be adjusted based on the predicted home demand information and the real-time environment status data, and generates environment adjustment instructions;

[0008] The device control module receives the environment adjustment instruction, analyzes the current status of each household device, configures the device status, and generates device configuration status data; outputs device control commands according to the device configuration status data, implements device control, and generates device operation results;

[0009] The data security module is used to encrypt the collected user data and device operation data and generate encrypted verification data.

[0010] Preferably, the steps of obtaining the behavior trend analysis results are:

[0011] Users obtain heart rate, activity frequency, sleep quality and duration through wearable devices, and associate the data with timestamps and activity types to form a user behavior data set;

[0012] Based on the user behavior data set, the behavior score is calculated using the following formula:

[0013]

[0014] Among them, f i is the frequency of the ith activity, t i is the duration of the ith activity, w i is the importance weight of the activity, r i is the average heart rate in the corresponding time period, n is the total number of activities during the observation period, α is the adjustment coefficient, and S is the behavioral score;

[0015] Based on the behavior score, the user's behavior pattern and activity trend are evaluated, and the activity pattern with the highest score is regarded as the user's main behavior trend to obtain a behavior trend analysis result.

[0016] Preferably, the steps of obtaining the predicted household demand information are:

[0017] Analyze the user's home device usage habits in different time periods based on the behavior trend analysis results, including the frequency and duration of use of lighting equipment, temperature control equipment, and entertainment equipment, extract the user's device usage preferences, and generate user device usage preference data;

[0018] Based on the user device usage preference data, combined with time periods and behavior patterns, predict the device usage demand in future time periods through time series analysis to obtain a device usage demand prediction result;

[0019] Based on the equipment usage demand prediction results, the equipment demand priorities and usage scenarios are analyzed to obtain predicted home demand information.

[0020] Preferably, the steps of acquiring the real-time environmental status data are:

[0021] The temperature, humidity and light raw data are collected through the environmental sensors deployed in the home, the temperature, humidity and light signals are sampled and quantified, and the signal amplitudes are converted using normalization to generate a normalized environmental data set;

[0022] Based on the normalized environment data set, the current environment state value is calculated using the following formula:

[0023]

[0024] Among them, T is the normalized temperature data, H is the normalized humidity data, L is the normalized light data, and E is the current environmental state value;

[0025] The current environmental state value is mapped to discrete state classifications, including comfortable, uncomfortable and extreme environments, to obtain real-time environmental state data.

[0026] Preferably, the steps of obtaining the environment adjustment instruction are:

[0027] According to the predicted home demand information and real-time environmental status data, the environmental adjustment priority value is calculated, and the calculation formula is:

[0028]

[0029] Among them, q1 is the predicted equipment demand intensity, q2 is the equipment operation frequency, E is the current environmental state value, q4 is the real-time environmental comfort, q5 is the expected equipment comfort value, q6 is the equipment operation energy consumption parameter, and P is the environmental adjustment priority value;

[0030] Based on the environment adjustment priority value and in combination with the dynamic constraints of the device operation, it is determined whether the home appliance needs to be adjusted to obtain an environment adjustment instruction.

[0031] Preferably, the steps of acquiring the device configuration status data are:

[0032] Receive the environment adjustment instruction, collect the operating status parameters of the household equipment in real time, including the current operating current, operating temperature, operating time and fault records of the equipment, and generate a device status feature data set;

[0033] Based on the device state feature data set, the device state adaptation value is calculated, and the calculation formula is:

[0034]

[0035] Where di is the current operating current of the device, t is the current operating time of the device, sf is the fault record count value of the device, k is the current operating temperature of the device, h is the target temperature value of the device, g is the power consumption value of the device, and A is the device state adaptation value;

[0036] Based on the device state adaptation value, the matching degree between the running state of the device and the target state is analyzed, and the configuration of the device is adjusted according to the matching degree to generate device configuration state data.

[0037] Preferably, the steps of obtaining the device operation result are:

[0038] Extracting the operation mode, target operation parameters and operation restriction conditions of the equipment according to the equipment configuration status data, analyzing the logical relationship between the parameters, and generating an equipment control parameter set;

[0039] Based on the device control parameter set, combined with the current device status information, a control command template is matched, and the control parameter set is mapped into an operation instruction executable by the device to generate a device control command set;

[0040] Based on the device control command set, the device control action is implemented, the device operation result is fed back in real time, and the device operation result is generated.

[0041] Preferably, the steps of obtaining the encrypted verification data are:

[0042] Classify and organize the collected user data and device operation data, including user behavior data, device operation records, and device operation logs, and form a standardized data set through data normalization and coding;

[0043] Based on the standardized data set, asymmetric encryption is used to encrypt the user data and the device operation data, and a digital signature for verification is generated to form an encrypted data set;

[0044] Based on the encrypted data set, the encryption result is integrated with the digital signature, the encryption integrity is verified, and the encrypted verification data is obtained.

[0045] The present invention provides a smart home control method based on a wearable device, comprising the following steps:

[0046] Collect users' physiological and behavioral data through wearable devices, record the time and activity category of data collection, and generate behavioral trend analysis results;

[0047] Based on the results of behavioral trend analysis, predict the user's future demand for home appliances in different time periods, combine the usage data to obtain the user's preference pattern, and generate predicted home demand information;

[0048] Collect temperature, humidity and light data of the home environment, conduct real-time evaluation of the environmental status, and generate real-time environmental status data; based on the predicted home demand information and real-time environmental status data, determine whether home equipment needs to be adjusted and generate environmental adjustment instructions;

[0049] Receive environmental adjustment instructions, analyze the current operating status of home appliances, adjust the equipment to meet preset environmental conditions, and generate equipment configuration status data based on equipment response and equipment adjustment requirements.

[0050] Compared with the prior art, the advantages and positive effects of the present invention are:

[0051] In the present invention, by combining the user's behavioral data and physiological data, and integrating time and activity type, the calculation of personalized behavioral trends and the prediction of future needs are realized. The real-time collection and multi-dimensional analysis of environmental data can dynamically construct the home environment status and quickly adjust and match the equipment requirements, thereby improving the accuracy and adaptability of equipment operation. The collaborative processing logic based on behavioral trends and environmental data avoids the blindness of equipment response, achieves active response to user needs and optimization of resource allocation. The comprehensive analysis of the equipment operation status ensures the collaborative efficiency between devices, reduces the situation of equipment overload or inefficient operation, and ensures the smoothness of equipment switching and the coordination of resource allocation. The data security processing logic strengthens privacy security and transmission reliability by encrypting and protecting user data and equipment operation instructions, and reduces the possibility of data leakage and operation risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a system flow chart of the present invention;

[0053] Figure 2 This is a flow chart of the steps for obtaining predicted household demand information in the present invention;

[0054] Figure 3 The figure is a flow chart of the steps for obtaining the operation results of the device in the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] See also Figure 1-3 The present invention provides a technical solution: a smart home control system based on a wearable device comprises:

[0057] The behavior prediction module collects the physiological and behavioral data generated by the user through the wearable device, combines the time and activity type, calculates the user's behavior trend, and generates the behavior trend analysis results; based on the behavior trend analysis results, it predicts the user's future home device usage needs and generates predicted home demand information;

[0058] The environmental perception module collects temperature, humidity and light data through environmental sensors deployed in the home, calculates the current environmental status, and generates real-time environmental status data; based on the predicted home demand information and real-time environmental status data, it determines whether the home environment needs to be adjusted and generates environmental adjustment instructions;

[0059] The device control module receives the environment adjustment instruction, analyzes the current status of each home appliance, configures the device status, and generates device configuration status data; according to the device configuration status data, outputs the device control command, implements the device control, and generates the device operation result;

[0060] The data security module is used to encrypt the collected user data and device operation data and generate encrypted verification data.

[0061] The steps to obtain the behavior trend analysis results are as follows:

[0062] Users obtain heart rate, activity frequency, sleep quality and duration through wearable devices, and associate the data with timestamps and activity types to form a user behavior data set;

[0063] Based on the user behavior data set, the behavior score is calculated using the following formula:

[0064]

[0065] Among them, f i is the frequency of the ith activity, t i is the duration of the ith activity, w i is the importance weight of the activity, r i is the average heart rate in the corresponding time period, n is the total number of activities during the observation period, α is the adjustment coefficient, and S is the behavioral score;

[0066] Based on the behavior score, the user's behavior pattern and activity trend are evaluated, and the activity pattern with the highest score is regarded as the user's main behavior trend to obtain the behavior trend analysis result.

[0067] Specifically, users obtain heart rate, activity frequency, sleep quality and duration through wearable devices, and record data in combination with timestamps and activity types. First, the heart rate collection process can be monitored once a minute, and the value range between 40 and 200bpm is recorded. Any value outside this range will be marked as abnormal and recorded separately. The activity frequency is monitored based on the real-time acceleration value obtained by the accelerometer, and then the acceleration data collected per second is compared with the established motion feature comparison table to confirm that the action is standing, walking or running. At the same time, the obtained motion frequency is converted into the form of times per minute. The sleep quality monitoring is based on the number of body movements in the lying state at night and the range of heart rate fluctuations at night. The body movement and heart rate data collected throughout the night are compared with the reference interval. For example, the body movement frequency is set The interval of 0 to 10 times per hour is judged, and the interval of 50 to 100bpm is set for night heart rate. Once the number of body movements is higher than 10 times per hour or the night heart rate is higher than 100bpm, the period is marked as a low-quality sleep period and recorded. The duration data comes from the time stamp of the previous heart rate and body movement information. By accumulating each time segment, the activity duration data can be formed hourly or minute by minute. Finally, the multiple numerical entries such as heart rate value, activity frequency, sleep quality and duration obtained through the above collection and recording process are integrated into a unified data structure with the corresponding timestamp and activity type. The time series distribution of each parameter is recorded and summarized and proofread to ensure the integrity of the correspondence between time and activity type. After all data are sorted, a user behavior data set is formed.

[0068] The benefit of the formula is that it enables a quantitative assessment of user behavior patterns by simultaneously considering multiple parameters such as activity frequency, duration, activity importance weight, and average heart rate, thereby more accurately identifying major activity trends in subsequent steps;

[0069] f i The steps for obtaining the parameters are as follows: statistically analyzing the acceleration data collected every minute, dividing the number of identified activities by the length of the time period, obtaining the number of times per minute, and obtaining the activity frequency of each activity by summarizing the entire observation period;

[0070] t i The steps for obtaining the parameters are to use the time recording function of the wearable device to record the duration of each activity in seconds, and convert the sum of these times into minutes, and remove or mark the too short time periods in the continuity test;

[0071] w iThe parameter acquisition step is to assign different weight values ​​to each activity based on the activity types obtained above, the measured frequency of the importance of each activity in the user's daily life, and the statistical results of the user's subjective preference questionnaire, and make appropriate adjustments when the activity intensity or duration fluctuates greatly;

[0072] r i The parameter acquisition step is to average the heart rate samples in the corresponding period of the activity through the heart rate monitoring data obtained above, store the abnormal heart rate segments separately and remove them from the average value statistics, and finally form the average heart rate of each period;

[0073] n represents the total number of activities during the observation period, which is derived from the count of all activities completed by the user during an observation period;

[0074] α is the adjustment coefficient, which is set based on the trade-offs made by researchers after comparing the physiological effects of different behavioral intensities, and changes dynamically with indicators such as the user's age and physical fitness;

[0075] Calculation process:

[0076] To give example values, assume that there are n=3 activities in the observation period, corresponding to f1=3.2 (times / minute), f2=2.1, f3=1.5, and the corresponding activity duration is t1=20 minutes, t2=30 minutes, t3=60 minutes. Through the weight parameter acquisition step, w1=1.5, w2=2.0, w3=0.8 are obtained. The average heart rate is obtained by heart rate recording r1=90bpm, r2=85bpm, r3=80bpm, and the adjustment coefficient α is 2.0. First, calculate the numerator:

[0077]

[0078] Calculate one by one:

[0079] (3.2×20)=64.0,64.0 2.0 =4096.0, 1.5×4096.0=6144.0;

[0080] (2.1×30)=63.0,63.0 2.0 =3969.0, 2.0×3969.0=7938.0;

[0081] (1.5×60)=90.0,90.0 2.0 =8100.0, 0.8×8100.0=6480.0;

[0082] Therefore, the sum of the numerators is 6144.0+7938.0+6480.0=20562.0, and then calculate the denominator:

[0083]

[0084] In summary,

[0085] The results show that for the three activities observed, under the specific values ​​of the above-mentioned weights, activity frequency, duration and average heart rate parameters, the behavior score is approximately 80.64, which means that the user's overall activity intensity is high. Subsequent evaluations will compare this value with the established threshold range. For example, the evaluation threshold range can be set between 40 and 90. If the score exceeds 90, it means that the activity level is extremely high. If the value is lower than 40, it indicates that the activity intensity is low or the behavior pattern is weak.

[0086] Based on the behavior score, the user's behavior pattern and activity trend are evaluated. First, the daily or weekly high-frequency activity scores are selected from the existing behavior score distribution, and these activity scores are compared with the previously established interval ranges. For example, the score range is divided into three levels: 0 to 30, 30 to 60, and 60 to 90. Combined with the activity type, it is determined whether it belongs to a mild, moderate or high-intensity behavior category. Then the distribution of each behavior category is statistically analyzed. For the situation where the high-intensity activity distribution is concentrated in certain time periods, the activity values ​​of the score-concentrated time period are compared with the lower intensity time period. If the difference exceeds the threshold range determined earlier, it can be marked as a special interest time period. Then a user activity trend chart is generated, and the score waveform of daily activities is superimposed on the timeline for display. The fluctuation in the morning, noon or evening is analyzed, and the time when the high-score segment appears is marked. After confirming the most prominent segment, the activity information and activity environment information corresponding to the behavior are read, and compared with the performance of other activities in parallel. Finally, it can be determined which action and time period the activity pattern with the highest score corresponds to, and this is used as the main behavior trend to obtain the behavior trend analysis result.

[0087] The steps to obtain the predicted home demand information are as follows:

[0088] Based on the results of behavioral trend analysis, analyze the user's home device usage habits in different time periods, including the frequency and duration of use of lighting equipment, temperature control equipment, and entertainment equipment, extract the user's device usage preferences, and generate user device usage preference data;

[0089] Based on the user's device usage preference data, combined with time periods and behavior patterns, the device usage demand in the future time period is predicted through time series analysis to obtain the device usage demand prediction result;

[0090] Based on the equipment usage demand prediction results, analyze the equipment demand priority and usage scenarios to obtain predicted home demand information.

[0091] Specifically, according to the behavioral trend analysis results obtained previously, the usage of lighting equipment, temperature control equipment and entertainment equipment by users in different time periods will include numerical items such as usage frequency and duration. Users start and operate various types of equipment in the three main time periods of morning, noon and evening every day, and record whether they are turned on for a long time in special time periods such as early morning or late at night. The lighting time and light-off time of the lighting equipment are counted, and the number of times different temperature settings or gear switching are used for temperature control equipment is recorded. The cumulative startup time of the entertainment equipment is synchronously recorded in the same general table. By comparing with the user behavior trend analysis results obtained previously, the distribution of the equipment operation characteristics in each time period is analyzed. If the equipment usage frequency or operating time exceeds the predetermined range, for example, 0 to 5 times a day Or if the running time of each time is in the range of 0 minutes to 120 minutes, the corresponding entry will be marked as abnormal and counted separately. The same method will be used to screen the distribution trends of various types of equipment at all times of the day, and then the record volume of different time periods will be compared. The corresponding peak usage sections will be associated with the user's previous activity types and durations. The device types that appear multiple times in the peak sections will be further subdivided and summarized. If the proportion exceeds the established empirical threshold, the device is deemed to be a more commonly used device by the user. The empirical threshold can be obtained by collecting the device startup records for one month and then counting their average and median. Finally, the data items screened and counted through these steps will be summarized, the frequency and duration of use of all devices will be classified and matched with the user's activity types in each time period to obtain the user's device usage preference data.

[0092] Based on the user's device usage preference data, by comparing the time period and behavior pattern, and comparing the peak and trough intervals of device usage at different times such as morning, evening and afternoon, the time series analysis method is used to monitor the cumulative number of device operations in each time period, and these cumulative times are included in the same sequence together with other related values ​​recorded previously. The data index is pushed back one by one according to a fixed time step and the periodicity or trend is found. A minimum observation window length is set, such as 7 days, and the difference in device usage on weekdays and weekends is counted within the window. If the number of times the entertainment device is used at the same time is between 7 and 15 times If the equipment usage frequency in a certain period deviates too much from the average value obtained by previous statistics, it is marked as abnormal distribution. By summarizing the occurrence frequency and corresponding conditions of abnormal distribution and combining its distribution form in long-term series, its impact on equipment demand forecast is judged. If the abnormal distribution accounts for less than 3% of the entire observation interval, it is classified as a rare case and does not affect the overall forecast process. Then, the above statistical results are gradually input into the selected time series analysis strategy, and the equipment usage demand in the next week or month is gradually calculated to obtain the equipment usage demand forecast result.

[0093] Based on the equipment usage demand prediction results, refer to the equipment demand priority and usage scenarios recorded previously, divide the appropriate operation range for each device, and quantify the usage demand differences of similar devices in adjacent time periods. If the usage intensity of any device exceeds the preset critical range in a certain period of time, such as the number of temperature control device adjustments in a day is greater than 10 times or the total operating time of entertainment equipment exceeds 300 minutes, it will be counted separately and marked as a high demand situation. The critical range can be obtained by weighting the average value of the equipment usage history data in the past several months. If a device has a higher demand priority than other devices in the current period, the occupancy rate of the device in this period is recorded and classified. If there are multiple devices with high priorities in the same period of time, their demand values ​​are listed separately and a corresponding usage scenario matching list is established. Then, according to the comparison results of each device and the scenario, the specific demand level interval is determined. If it matches the scenario conditions recorded previously, it is included in the same sub-category and deeply compared. After all the steps are combined to complete the matching process of equipment demand priority and usage scenario within a fixed time, the predicted home demand information is obtained.

[0094] The steps for obtaining real-time environmental status data are as follows:

[0095] The temperature, humidity and light raw data are collected through the environmental sensors deployed in the home, the temperature, humidity and light signals are sampled and quantified, and the signal amplitudes are converted using normalization to generate a normalized environmental data set;

[0096] Based on the normalized environment data set, the current environment state value is calculated using the following formula:

[0097]

[0098] Among them, T is the normalized temperature data, H is the normalized humidity data, L is the normalized light data, and E is the current environmental state value;

[0099] The current environmental state value is mapped to discrete state classifications, including comfortable, uncomfortable, and extreme environments, to obtain real-time environmental state data.

[0100] Specifically, the temperature, humidity and light raw data are collected through environmental sensors deployed in the home. Several temperature and humidity sensors can be installed in various places in the home, and light intensity sensors can be set in areas where the indoor light source is relatively concentrated or where obvious light changes may occur. The sampling frequency is determined to be per second or per minute based on the preliminary investigation. The measured temperature value is usually within the range of -20℃ to 70℃, and the extreme over-limit values ​​caused by equipment failure are excluded. The humidity is also recorded in the range of 0% to 100%, and occasional jumps are marked separately. The raw light data can be compared between 0 and 2000 lux to see if it falls within the valid range. The temperature, humidity and light intensity of each record with the same timestamp are recorded. The values ​​are combined together and stored uniformly. The stability of the sensor working state is determined by comparing the total number of daily or weekly samples with the number of abnormal marks. If the number of abnormal data exceeds the threshold obtained by prior statistics, the sensor is checked. The threshold can be determined by summarizing the statistics of the average abnormal rate obtained by accumulating records over several months and then floating upward by a certain proportion. For the data within the qualified range, mapping and scaling are performed based on the corresponding maximum and minimum intervals. For example, the temperature value is converted to the interval of 0 to 1, the humidity value is converted to the interval of 0 to 1, and the light value is converted to the interval of 0 to 1. The converted amplitude is called the normalized value and recorded in a normalized environmental data set to generate a normalized environmental data set.

[0101] The benefit of the formula is that it combines the product relationship between temperature and humidity, the ratio relationship between light and temperature, and the absolute value of the difference between humidity and light, so that the calculation of environmental conditions can take into account both mutual coupling and the magnitude of changes in a single factor;

[0102] The steps to obtain the T parameter are as follows: using the normalized temperature value obtained above, which is derived from the value obtained by linearly mapping the daily measured temperature range between -20℃ and 70℃. The specific process is to first record all temperature data and find the lowest and highest temperatures on the day or in a period, and then calculate the ratio of each temperature data relative to this interval to obtain T;

[0103] The steps for obtaining the H parameter are to limit the collected humidity data to the range of 0% to 100%, find the minimum and maximum humidity during the observation period, calculate the normalized humidity to obtain H through the same mapping method as temperature, and if extreme value points appear, analyze them separately and confirm them as records of equipment failure or extreme indoor environment;

[0104] The steps for obtaining the L parameter are as follows: collect the light intensity data in the common range of 0 to 2000 lux and perform value statistics. For the light data outside this range, first mark it as abnormal and process it during the equipment inspection. Find the current minimum and maximum light within the normal range as a reference, and map the light data to a normalized value from 0 to 1 to obtain L.

[0105] Calculation process:

[0106] For example, T = 0.40, H = 0.65, L = 0.50, first calculate the product part (T·H) 2 =(0.40×0.65) 2 ,

[0107] 0.40×0.65=0.26,0.26 2 =0.0676,

[0108] Then calculate 1.25 2 =1.5625,

[0109] Then calculate |HL|=|0.65-0.50|=0.15,

[0110] Add these three parts and take the square root:

[0111]

[0112] The results show that when the normalized values ​​of temperature, humidity and light are 0.40, 0.65 and 0.50 respectively, the environmental state value is approximately 1.334. The larger the value, the more obvious the overall deviation of these three factors in the environment. For example, when E exceeds 2, it means that the temperature and humidity or light are quite different. When it is less than 1, it means that the relative differences among the three factors are small.

[0113] The current environmental state value is mapped to discrete state classifications, including comfortable, uncomfortable and extreme environments. Users usually compare the previously obtained environmental state value E with the existing statistical intervals. For example, 0 to 1.0 is defined as a lower range and marked as a comfortable interval, 1.0 to 2.0 is defined as a medium range and marked as an uncomfortable interval, and greater than 2.0 is classified as an extreme environment range. The E calculated last time is compared with these preset thresholds. If E falls between 1.0 and 2.0, it is recorded as an uncomfortable state. At the same time, a parallel comparison is made between the time point of occurrence and the detailed temperature, humidity and light values ​​measured by the sensor. If an E value If it exceeds 2.0, it is recorded as an extreme environmental state. Samples whose E value has not exceeded 1.0 are marked as a comfortable state. By comparing the E value change trend at different time points in a day, all E value samples within 24 hours are arranged in the form of a time series with the above interval mapping results and the distribution ratio in each interval is checked. If the proportion of extreme environment in a certain time period exceeds the empirical threshold established based on previous statistical data, the sensor is inspected again. The empirical threshold can be obtained by weighted averaging the ratio of extreme environment generation in the past few weeks or months. After all E value sampling and mapping are completed, real-time environmental status data is obtained.

[0114] The steps to obtain the environment adjustment instructions are:

[0115] According to the predicted home demand information and real-time environmental status data, the environmental adjustment priority value is calculated. The calculation formula is:

[0116]

[0117] Among them, q1 is the predicted equipment demand intensity, q2 is the equipment operation frequency, E is the current environmental state value, q4 is the real-time environmental comfort, q5 is the expected equipment comfort value, q6 is the equipment operation energy consumption parameter, and P is the environmental adjustment priority value;

[0118] Based on the environment adjustment priority value and combined with the dynamic constraints of the device operation, it is determined whether the home device needs to be adjusted to obtain the environment adjustment instruction.

[0119] Specifically, the formula is beneficial in that it can reflect environmental adjustment needs in multiple dimensions by comprehensively calculating the product relationship between the predicted equipment demand intensity and the equipment operation frequency, the impact of the current environmental state value, the difference between the real-time environmental comfort and the expected equipment comfort value, and the energy consumption parameters;

[0120] The steps for obtaining the q1 parameter are as follows: using the items recording the intensity of equipment use demand in the previously obtained predicted household demand information, counting the equipment demand level in a predetermined time period, quantifying the demand level into a numerical range of 0 to 10, and taking a weighted average value after repeated measurements in a month or longer period to obtain q1;

[0121] The steps to obtain the q2 parameter are as follows: referring to the number of times the equipment is used in the same period, combined with the records of each equipment startup and operation, the startup frequency per unit time is mapped to the interval of 0 to 20, and after multiple days of observation, a frequency distribution sequence is obtained, and the average number of times for this sequence is calculated to obtain q2;

[0122] The steps for obtaining the E parameter are: using the current environmental state value obtained above, normalizing the temperature, humidity, and light and calculating the value in the relevant formula; if the data is stable over a long period of time, the value is processed by sliding average, and the environmental state value in the latest time segment is finally determined as E;

[0123] The steps to obtain the q4 parameter are to observe the user's real-time environmental comfort in the current period, extract the comfort evaluation from parameters such as temperature, humidity and light through questionnaires or comprehensive measurements, define it in the range of 0 to 1, and take the average value of multiple observation points to obtain q4;

[0124] The steps for obtaining the q5 parameter are to determine the comfort score under the target state through the preset configuration of the device itself and the user's historical preference query, which is also defined in the numerical range of 0 to 1, and to perform weighted calculation on the set values ​​of the diverse devices and take the average result as q5;

[0125] The steps for obtaining the q6 parameter are to record the energy consumption information of the equipment during the actual operation stage, perform cumulative calculations through power and operation time, map the energy consumption ratio in the entire period to the range of 0 to 100, and convert the final mapping value to the range of 0 to 10 to form q6;

[0126] Calculation process:

[0127] Let q1 = 6.0, q2 = 12.0, E = 1.2, q4 = 0.55, q5 = 0.65, q6 = 3.0,

[0128] First calculate (q1·q2) 2 =(6.0×12.0) 2 ,

[0129] 6.0×12.0=72.0,72.0 2 =5184.0,

[0130] Divide the result by E,

[0131] Recalculate

[0132] Add these three parts: 4320.0+0.10+0.23=4320.33,

[0133] Take the square root:

[0134] The result shows that when the parameters q1, q2, E, q4, q5, and q6 take the above values, the environmental adjustment priority value is about 65.73. When this value is in a higher range, it can be regarded as a relatively prominent demand for environmental adjustment. If the value is low, it means that the comprehensive demand is weak.

[0135] Among them, q1 is the predicted equipment demand intensity, which is numerically processed with reference to the demand information items obtained above, compared with the data of multiple days or weeks, and the abnormal peaks are marked separately. The value is obtained by counting the average demand intensity of multiple time periods and the proportion of high-frequency demand periods. q2 is the equipment operation frequency, which is obtained by checking the cumulative number of times the equipment is turned on and off every day and comparing it with the pre-established range of 0 to 20 times. When the actual record exceeds this range, the corresponding data is classified into the abnormal category and the time period when the abnormality occurs is summarized. The final value is generated using the frequency average of all valid data. E is the current environmental state value, which is obtained by comparing the temperature record value of 0℃ to 90℃, the humidity record value of 0% to 100%, and the light record value of 0 lux to 2000. The value of the lux interval is obtained by executing the environmental status calculation process introduced above. q4 is the real-time environmental comfort, which is obtained through a quantification process based on the temperature, humidity and light measurement results set indoors and the perception factor actually reflected by the user. The perception factor is mapped to the interval of 0 to 1 and the numerical average is calculated to determine the value. q5 is the expected comfort value of the device, which is obtained by querying the ideal temperature and light range pre-recorded in the device database and comparing and analyzing with the user's customized preferences. q6 is the energy consumption parameter of the device operation. The energy consumption percentage of the device in one day or a longer period is calculated in combination with the device nameplate power and operating time, and the value is assigned in the range of 0 to 10. When all parameter values ​​are prepared, the corresponding relationship between them is recorded and uniformly proofread to obtain a corresponding list between each item.

[0136] Based on the environment adjustment priority value, combined with the dynamic constraints of the device operation, the dynamic constraints of the device operation can include the available power quota of the device and the idle time period of the current task schedule, and when counting the number of operations, the distribution differences of similar devices in different time periods of the day will be recorded. If it is found that the usage of some devices in a specific time period has exceeded the threshold range established according to the previous observation results, such as the total number of multiple starts and stops is greater than 20 and the continuous start time period is more than 2 hours, the corresponding device will be included in the potential conflict list, and then the items in the potential conflict list are compared with the previously obtained environment adjustment priority value and sorted internally from high to low according to the value, and then they are checked one by one according to the restrictions of the device in the time period, such as power consumption indicators or the maximum allowed parallelism. If some items cannot be met temporarily at this stage, they are listed as waiting or reallocation options and the sorting results are recorded in a unified list. Finally, for devices with relatively high priority values ​​and no obvious dynamic constraint obstacles, further operations are triggered, that is, related home device adjustment control commands are generated. Through these steps, it can be determined whether to adjust the home device in the current time period and obtain the environment adjustment instruction.

[0137] The steps to obtain device configuration status data are as follows:

[0138] Receive environmental adjustment instructions, collect the operating status parameters of home appliances in real time, including the current operating current, operating temperature, operating time and fault records of the appliances, and generate an appliance status feature data set;

[0139] Based on the device status feature data set, the device status adaptation value is calculated using the following formula:

[0140]

[0141] Where di is the current operating current of the device, t is the current operating time of the device, sf is the fault record count value of the device, k is the current operating temperature of the device, h is the target temperature value of the device, g is the power consumption value of the device, and A is the device state adaptation value;

[0142] Based on the device status adaptation value, the matching degree between the device's operating status and the target status is analyzed, and the device configuration is adjusted according to the matching degree to generate device configuration status data.

[0143] Specifically, it receives the environment adjustment instruction and collects the operating status parameters of the household appliances in real time, including the current operating current, operating temperature, operating time and fault records of the equipment, and records them. Combined with the distribution of the equipment current between 0A and 5A, if it exceeds 5A or is lower than 0A, it is marked as abnormal data and temporarily stored. By comparing the current temperature in the range of 0℃ to 90℃, it is judged whether it exceeds the reasonable range. If the abnormality occurs frequently, the average temperature value of the previous equipment operation cycle is referred to locate the potential overload situation. The operating time is also referenced to the range of 0 minutes to 480 minutes and the duration exceeds the range is recorded. The fault record is collected according to the fault code recorded in the previous equipment maintenance manual and its frequency of occurrence during operation. When the cumulative value of the number of faults exceeds the empirical threshold obtained from the previous statistics, such as the result of summarizing the statistics of the same fault code many times, the threshold can be set between 3 and 5 and varies according to the specific equipment type. The number of faults will be listed separately to identify whether it is a key inspection object. Finally, the current operating current, operating temperature, operating time and fault code records are summarized, and the valid values ​​obtained are stored in a device status feature data set to generate a device status feature data set.

[0144] The formula is useful in that it takes into account the multiplication relationship between current and duration, the impact of fault records, the difference between current temperature and target temperature, and the coupling term between device power consumption and operating time or current, thereby being able to measure whether the device operating status deviates from the target setting under multiple factors;

[0145] The steps for obtaining the di parameter are to collect the current operating current of the equipment, take the value between 0A and 5A and make daily cumulative records, remove the instantaneous overload data or analyze it separately, and then calculate the average value or short-time peak value, and finally use this processed value as di;

[0146] The steps for obtaining the t parameter are to obtain the minute interval from the previously recorded startup and continuous operation time of the equipment, which can usually be in the range of 0 minutes to 480 minutes, and obtain the corresponding t by summing or comparing the short-period data;

[0147] The steps for obtaining the sf parameter are as follows: the number of fault events within a period is summarized in the maintenance document through the fault record count values ​​collected in the early stage. If the user finds that the equipment has N faults in 100 hours of continuous operation, then N is compared with the average number of faults obtained by the same equipment in other similar operating environments. After the statistics are completed, the fault record count value is obtained for sf;

[0148] The steps to obtain the k parameter are as follows: based on the current operating temperature collection value of the equipment, take the acceptable range of 0°C to 90°C as a reference, perform weighted calculation on the temperature samples observed every day, and use the latest or most recent monitoring value as k;

[0149] The step of obtaining the h parameter is to obtain it from the target temperature value setting of the device, and form a temperature range by combining the manufacturer's recommendations and the user's configuration requirements. If there is a setting interval such as 30°C to 60°C, a specific value can be selected according to the user's expectations and recorded in the device configuration table to obtain h;

[0150] The steps to obtain the g parameter are to multiply the nameplate power and the actual operating power of the device by time intervals to obtain the power consumption data for the entire period and map it, express the power consumption value of the device in a numerical form of 0 to 10, and finally determine g;

[0151] Calculation process:

[0152] Let di = 2.4A, t = 120 minutes, sf = 2 times, k = 45°C, h = 40°C, g = 7.0 (this value is mapped after the energy consumption of the equipment is measured).

[0153] First calculate the numerator di·t=2.4×120=288.0, then divide it by (1+sf) which is 1+2=3. Then square 96.0 to get 96.0 2 =9216.0,

[0154] Then calculate |kh|=|45-40|=5.0,

[0155] Recalculate

[0156] Add the above three parts: 9216.0+5.0+0.400=9221.4,

[0157] Take the square root of this:

[0158] The result shows that the current device state adaptation value is about 95.99. If the result is higher than a higher threshold, such as 100, it means that the current operation of the device is significantly different from the target parameters, and it is necessary to consider the various values ​​obtained above and further investigate or adjust them. If the value is in a lower range, it can indicate that the device state is relatively stable.

[0159] Based on the device status adaptation value, the degree of match between the device's operating status and the target status is analyzed, and the device configuration is adjusted according to the degree of match. If the device status adaptation value that appears in the previous statistical period is repeatedly in the range of 80 to 100, the average and peak values ​​of current, temperature and operating time are compared one by one with reference to the determined device target temperature and power consumption requirements. When it is found that the current peak or the cumulative fault value exceeds the upper limit threshold determined during data statistics, such as the number of faults exceeds 5 times or the current peak is higher than 5A, the corresponding device is subjected to load reduction or time-sharing scheduling, and the operating behavior originally concentrated in a certain period of time is split into other time periods. At the same time, a more conservative value is adopted in the target temperature setting of the device to prevent long-term high-temperature operation from causing greater pressure on the hardware. Finally, the device configuration status data is output according to the corresponding situation of all parameters.

[0160] The steps to obtain the device operation results are as follows:

[0161] According to the equipment configuration status data, extract the equipment's operating mode, target operating parameters and equipment operating constraints, analyze the logical relationship between parameters, and generate equipment control parameter sets;

[0162] Based on the device control parameter set and combined with the current device status information, the control command template is matched, and the control parameter set is mapped into an operation instruction executable by the device to generate a device control command set;

[0163] Based on the equipment control command set, implement equipment control actions, provide real-time feedback on equipment operation results, and generate equipment operation results.

[0164] Specifically, according to the previously obtained equipment configuration status data, the equipment operation mode, target operation parameters and equipment operation restriction conditions are extracted, and the logical relationship between the parameters is analyzed. First, the operation period and the corresponding load level under each mode are disassembled from the previously recorded equipment operation mode, and compared with the target operation parameters one by one. If there is an obvious gap between the current operating temperature of the equipment and the target temperature, the gap value is recorded and the current, voltage and available energy consumption range at the same time are marked in the restriction list. By comparing these items, it is determined whether there is a situation exceeding the preset threshold. For example, the voltage is set to a range of 0V to 24V. If a record higher than 24V appears, it is classified as a temporary conflict and its occurrence period is counted. Then, the results of all logical comparisons are combined with the equipment's operation frequency, startup time and number of faults in a day. Data such as data are summarized. After confirming that each record is within an acceptable range, it is mapped one by one with the previously sorted target operation parameters and the relevant operation restriction conditions of the equipment are supplemented. If it is found that the load peak conflicts with the load upper limit in the equipment limit, it is included in the warning list. Finally, a parameter set containing the corresponding relationship between the operation mode, target parameter and restriction conditions is constructed according to all the sorted logical matching relationships to generate a device control parameter set.

[0165] Based on the device control parameter set, combined with the current device status information, the control command template is matched, and the control parameter set is mapped to an executable operation instruction for the device. First, the temperature, current and power consumption levels in the current device status information are checked one by one according to the previously obtained operation mode and the corresponding target operation parameters. If the current measured temperature is found to be too high when the temperature is compared with the range of 0°C to 90°C, the temperature value is recorded during the template comparison and positioned as a high temperature control mode. Then, it is checked whether the power consumption load of the control is within the mapping range of 0 to 10. If it exceeds the mapping range, it is marked as a load overload situation and a specific load reduction or time-sharing command template is selected. These control strategies are matched one by one with the parameter basis obtained previously. In this process, items such as current and duration need to be taken into consideration. If the device frequently starts and stops more than 20 times, a command template that is sensitive to the start and stop frequency is selected. Finally, all the matched data are mapped and processed to obtain a set of command item lists, and executable instructions such as voltage, current, and power consumption are assembled into executable operation instructions for the device to generate a device control command set.

[0166] Based on the device control command set, the device control action is implemented and the device operation results are fed back in real time. When executing these operation instructions, the device will read the core parameters in the control command set, such as the target temperature and the corresponding loadable current, and compare the previously recorded operation time interval of 0 minutes to 480 minutes. If the current time is already high and close to the upper limit of the device limit, the load reduction operation is automatically performed in segments and the execution results of each segment are recorded in the same record sequence. During the execution, if the current peak exceeds the range of 0A to 5A, it will be included in the abnormal monitoring list and the relevant command entries will be retrieved to determine whether to temporarily pause or switch to power reduction mode. Then continue to execute the remaining commands until all operations are completed. After each instruction is executed, the device updates the device status data. By collecting the temperature, power consumption and current one by one, the results are compared with the previously set limits or target parameters. If no further conflicts are found, all matched data are summarized with the current execution time as a mark to obtain the device operation effect data. Finally, the operation effect data is organized into a device control result snapshot and regarded as the end signal of the entire instruction set to generate the device operation result.

[0167] The steps to obtain encrypted verification data are:

[0168] Classify and organize the collected user data and device operation data, including user behavior data, device operation records, and device operation logs, and form a standardized data set through data normalization and coding;

[0169] Based on the standardized data set, asymmetric encryption is used to encrypt user data and device operation data, and a digital signature for verification is generated to form an encrypted data set;

[0170] Based on the encrypted data set, the encryption result is integrated with the digital signature, the encryption integrity is verified, and the encrypted verification data is obtained.

[0171] Specifically, the collected user data and equipment operation data are classified and organized, including user behavior data, equipment operation records and equipment operation logs. After each data collection is completed, the recorded user behavior items are compared with the corresponding timestamps or event numbers to separate the user behavior level and the equipment operation level. The user behavior data is concentrated on daily behavior patterns and abnormal state identification. The equipment operation data mainly covers information such as equipment operating current, temperature, duration and number of failures, and is sorted on the time axis according to the order of records. Then, the basic fields such as behavior category, equipment type, key attributes, etc. are compared with the previously agreed index items through a unified numbering method, so as to maintain the label of each data item in an aggregate structure. If any data does not match the set range, such as the temperature is outside the range of 0℃ to 90℃ or the operating current exceeds 0A 5A are listed separately and their occurrence times are marked. There is no need to remove these abnormal records, but to centrally summarize and list the frequency and distribution. After completing such classification and sorting, all records are divided into user behavior groups and device operation groups according to their types, and an associated index is established for each group separately. Then, the text descriptions or multi-valued fields that may exist in each record are encoded, such as converting the device type into a digital mapping value or dividing the fault description text into several keywords and mapping the keywords to numbers. In this way, each field can maintain the same format as the same field in subsequent processing. Finally, vertical and horizontal sorting and merging are performed in the same data structure, and the time series features are split and extracted to ensure that each record is indexed with a unified coordinate or label. After completion, the results are placed in a standardized data set to form a standardized data set.

[0172] Based on the standardized data set, asymmetric encryption is used to encrypt user data and device operation data, and a digital signature is generated for verification. First, the user behavior record and device operation record are read from the standardized data obtained after the previous classification and coding processing, and each record is arranged in sequence and concatenated with the marked timestamp to confirm that all records are within the valid range, such as 0A to 5A for current, 0℃ to 90℃ for temperature, 0% to 100% for humidity, etc. After comparing with the set upper and lower limits, the records that meet the requirements are merged into the same data segment, and then the data segment is asymmetric encrypted. It is required to import the encryption process and use the public key and private key prepared in advance to process the data in blocks. For each block, the encrypted ciphertext is calculated according to the corresponding plaintext data and the public key. At the same time, the digital signature is calculated after the encryption is completed, and the signature information is inserted into the metadata structure corresponding to the block. After each encrypted block is completed, it is superimposed in sequence to form an overall encryption sequence. If there are conflicts such as data length being too large during this period, it will be recorded in a troubleshooting list. After confirming that the encryption process is normal, all block ciphertexts and their signature information are merged to obtain the ciphertext and digital signature combination structure required for asymmetric encryption, which is the encrypted data set.

[0173] Based on the encrypted data set, the encryption result is integrated with the digital signature to verify the encryption integrity. First, it is confirmed that the digital signature of each encrypted block in the previous stage has been successfully generated according to the public key and private key pairing. The length of the ciphertext segment and the digital signature segment are compared to exclude the incomplete structure caused by data missing. Then, each block is decrypted in sequence and the summary value recorded in the digital signature is compared with the actual content of the decrypted data segment. If the decrypted data segment is consistent with the signature summary, the block is marked as passed the verification. If the summary does not match, the specific location is recorded in a contradiction list to check whether it is caused by data damage or splicing errors during the transmission process. Combined with the initial timestamp and device number of the plaintext, try to locate the point where the conflict occurs. After completing the decryption and signature verification of all blocks, the statistical results are summarized for the last time to confirm whether there is a large-scale block verification failure. If there is no abnormality, all the blocks that have passed the verification are integrated into a complete data structure and the information that the verification has passed successfully is recorded. If there are errors in a small number of local blocks, the subsequent troubleshooting procedure can be entered. Finally, the integrity report of the encrypted data set and the corresponding integration results are obtained, and the encrypted verification data are obtained.

[0174] The present invention provides a smart home control method based on a wearable device, comprising the following steps:

[0175] Collect users' physiological and behavioral data through wearable devices, record the time and activity category of data collection, and generate behavioral trend analysis results;

[0176] Based on the results of behavioral trend analysis, predict the user's future demand for home appliances in different time periods, combine the usage data to obtain the user's preference pattern, and generate predicted home demand information;

[0177] Collect temperature, humidity and light data of the home environment, conduct real-time evaluation of the environmental status, and generate real-time environmental status data; based on the predicted home demand information and real-time environmental status data, determine whether home equipment needs to be adjusted and generate environmental adjustment instructions;

[0178] Receive environmental adjustment instructions, analyze the current operating status of home appliances, adjust the equipment to meet preset environmental conditions, and generate equipment configuration status data based on equipment response and equipment adjustment requirements.

Claims

1. A smart home control system based on wearable devices, characterized in that: The system comprises: The behavior prediction module collects the physiological and behavioral data generated by the user through the wearable device, calculates the user's behavior trend in combination with the time and activity type, and generates a behavior trend analysis result; based on the behavior trend analysis result, predicts the user's future home device usage needs and generates predicted home demand information; The environment perception module collects temperature, humidity and light data through environmental sensors deployed in the home, calculates the current environment status, and generates real-time environment status data; based on the predicted home demand information and the real-time environment status data, determines whether the home environment needs to be adjusted and generates environment adjustment instructions; The device control module receives the environment adjustment instruction, analyzes the current status of each household device, configures the device status, and generates device configuration status data; outputs device control commands according to the device configuration status data, implements device control, and generates device operation results; The data security module is used to encrypt the collected user data and device operation data and generate encrypted verification data.

2. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for obtaining the behavior trend analysis result are: Users obtain heart rate, activity frequency, sleep quality and duration through wearable devices, and associate the data with timestamps and activity types to form a user behavior data set; Based on the user behavior data set, the behavior score is calculated using the following formula: Among them, f i is the frequency of the ith activity, t i is the duration of the ith activity, w i is the importance weight of the activity, r i is the average heart rate in the corresponding time period, n is the total number of activities during the observation period, α is the adjustment coefficient, and S is the behavioral score; Based on the behavior score, the user's behavior pattern and activity trend are evaluated, and the activity pattern with the highest score is regarded as the user's main behavior trend to obtain a behavior trend analysis result.

3. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for obtaining the predicted household demand information are as follows: Analyze the user's home device usage habits in different time periods based on the behavior trend analysis results, including the frequency and duration of use of lighting equipment, temperature control equipment, and entertainment equipment, extract the user's device usage preferences, and generate user device usage preference data; Based on the user device usage preference data, combined with time periods and behavior patterns, predict the device usage demand in future time periods through time series analysis to obtain a device usage demand prediction result; Based on the equipment usage demand prediction results, the equipment demand priorities and usage scenarios are analyzed to obtain predicted home demand information.

4. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for acquiring the real-time environmental status data are as follows: The temperature, humidity and light raw data are collected through the environmental sensors deployed in the home, the temperature, humidity and light signals are sampled and quantified, and the signal amplitudes are converted using normalization to generate a normalized environmental data set; Based on the normalized environment data set, the current environment state value is calculated using the following formula: Among them, T is the normalized temperature data, H is the normalized humidity data, L is the normalized light data, and E is the current environmental state value; The current environmental state value is mapped to discrete state classifications, including comfortable, uncomfortable and extreme environments, to obtain real-time environmental state data.

5. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps of obtaining the environment adjustment instruction are as follows: According to the predicted home demand information and real-time environmental status data, the environmental adjustment priority value is calculated, and the calculation formula is: Among them, q1 is the predicted equipment demand intensity, q2 is the equipment operation frequency, E is the current environmental state value, q4 is the real-time environmental comfort, q5 is the expected equipment comfort value, q6 is the equipment operation energy consumption parameter, and P is the environmental adjustment priority value; Based on the environment adjustment priority value and in combination with the dynamic constraints of the device operation, it is determined whether the home appliance needs to be adjusted to obtain an environment adjustment instruction.

6. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for acquiring the device configuration status data are as follows: Receive the environment adjustment instruction, collect the operating status parameters of the household equipment in real time, including the current operating current, operating temperature, operating time and fault records of the equipment, and generate a device status feature data set; Based on the device state feature data set, the device state adaptation value is calculated, and the calculation formula is: Where di is the current operating current of the device, t is the current operating time of the device, sf is the fault record count value of the device, k is the current operating temperature of the device, h is the target temperature value of the device, g is the power consumption value of the device, and A is the device state adaptation value; Based on the device state adaptation value, the matching degree between the running state of the device and the target state is analyzed, and the configuration of the device is adjusted according to the matching degree to generate device configuration state data.

7. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for obtaining the device operation result are: Extracting the operation mode, target operation parameters and operation restriction conditions of the equipment according to the equipment configuration status data, analyzing the logical relationship between the parameters, and generating an equipment control parameter set; Based on the device control parameter set, combined with the current device status information, a control command template is matched, and the control parameter set is mapped into an operation instruction executable by the device to generate a device control command set; Based on the device control command set, the device control action is implemented, the device operation result is fed back in real time, and the device operation result is generated.

8. The smart home control system based on wearable devices according to claim 1, characterized in that: The steps for obtaining the encrypted verification data are: Classify and organize the collected user data and device operation data, including user behavior data, device operation records, and device operation logs, and form a standardized data set through data normalization and coding; Based on the standardized data set, asymmetric encryption is used to encrypt the user data and the device operation data, and a digital signature for verification is generated to form an encrypted data set; Based on the encrypted data set, the encryption result is integrated with the digital signature, the encryption integrity is verified, and the encrypted verification data is obtained.

9. A smart home control method based on wearable devices, characterized in that: The smart home control system based on a wearable device according to any one of claims 1 to 8 comprises the following steps: Collect users' physiological and behavioral data through wearable devices, record the time and activity category of data collection, and generate behavioral trend analysis results; Based on the results of behavioral trend analysis, predict the user's future demand for home appliances in different time periods, combine the usage data to obtain the user's preference pattern, and generate predicted home demand information; Collect temperature, humidity and light data of the home environment, conduct real-time evaluation of the environmental status, and generate real-time environmental status data; based on the predicted home demand information and real-time environmental status data, determine whether home equipment needs to be adjusted and generate environmental adjustment instructions; Receive environmental adjustment instructions, analyze the current operating status of home appliances, adjust the equipment to meet preset environmental conditions, and generate equipment configuration status data based on equipment response and equipment adjustment requirements.

Images