Physiological state-based device adaptive control method, apparatus, and electronic device

Abstract

This invention provides a device, apparatus, and electronic device for adaptive control of devices based on physiological states, comprising: real-time acquisition of user physiological state data and indoor environmental parameter data; obtaining physiological state scores and environmental quality scores based on the physiological state data and indoor environmental parameter data, and generating a comprehensive comfort demand index based on the physiological state scores and environmental quality scores; identifying the currently applicable scenario mode through composite triggering logic based on the comprehensive comfort demand index, physiological state data, and indoor environmental parameter data, and determining the target control strategy corresponding to the scenario mode; and distributing the target control strategy to smart home devices to enable the smart home devices to adjust the indoor environment. This invention enables smart home control to better meet the actual comfort needs of users, significantly improving the user's living experience.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a device, apparatus, and electronic device with physiological state-based adaptive control. Background Technology

[0002] With the rapid development of IoT and AI technologies, smart home systems have gradually become common in ordinary households. By connecting various devices in the home (such as lights, air conditioners, curtains, audio systems, and ventilation systems) to the network, smart home systems enable remote control, timed control, and scene-based control, greatly improving the convenience and comfort of living.

[0003] Currently, existing smart home control systems mainly employ the following control methods: The first is manual control, where users manually adjust the parameters of various devices via a mobile app or voice assistant; the second is preset scene modes, where users pre-set multiple scene modes (such as home mode, sleep mode, movie mode, etc.), and switch to the preset device state with a single click when triggered; the third is automatic control based on environmental sensors, which automatically triggers corresponding device control when environmental parameters (such as temperature, humidity, light, etc.) reach preset thresholds. However, existing smart home control systems mostly use a binary logic of "environmental threshold trigger + manually preset scene," such as automatically turning on the air conditioner when the temperature exceeds 28℃, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a device, apparatus and electronic device based on physiological state adaptive control, which can make smart home control more in line with the actual comfort needs of users and significantly improve the user's living experience.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows: In a first aspect, embodiments of the present invention provide a device adaptive control method based on physiological state, comprising: real-time collection of user physiological state data and indoor environmental parameter data; obtaining a physiological state score and an environmental quality score based on the physiological state data and the indoor environmental parameter data, and generating a comprehensive comfort demand index based on the physiological state score and the environmental quality score; identifying the currently applicable scenario mode through a composite trigger logic based on the comprehensive comfort demand index, the physiological state data, and the indoor environmental parameter data, and determining the target control strategy corresponding to the scenario mode; and distributing the target control strategy to smart home devices so that the smart home devices can adjust the indoor environment.

[0006] Optionally, physiological state scores and environmental quality scores can be obtained based on physiological state data and indoor environmental parameter data, including: outputting physiological state scores through a physiological state assessment model based on physiological state data; and outputting environmental quality scores through an environmental quality assessment model based on environmental parameter data.

[0007] Optionally, based on physiological state data, a physiological state assessment model is used to output a physiological state score, including: calculating a heart rate abnormality score, heart rate variability score, sleep state score, and stress level score based on the physiological state data, and fusing the heart rate abnormality score, heart rate variability score, sleep state score, and stress level score based on a preset first weighting coefficient to obtain a physiological state score.

[0008] Optionally, based on environmental parameter data, an environmental quality score is output through an environmental quality assessment model, including: calculating thermal comfort score, light environment score, sound environment score and air quality score based on environmental parameter data respectively, and fusing the thermal comfort score, light environment score, sound environment score and air quality score based on a preset second weighting coefficient to obtain the environmental quality score.

[0009] Optionally, a comprehensive comfort demand index is generated based on physiological state scores and environmental quality scores, including: dynamically calculating physiological weight coefficients and environmental weight coefficients based on physiological state scores and a two-factor fusion model; and generating a comprehensive comfort demand index based on physiological state scores, environmental quality scores, physiological weight coefficients, and environmental weight coefficients.

[0010] Optionally, the physiological weight coefficient and environmental weight coefficient are dynamically calculated based on the physiological state score and the two-factor fusion model, including: when the physiological state score is less than or equal to a first preset threshold, the physiological weight coefficient is the maximum value of the physiological weight, and the environmental weight coefficient is the minimum value of the environmental weight; when the physiological state score is greater than or equal to a second preset threshold, the physiological weight coefficient is the minimum value of the physiological weight, and the environmental weight coefficient is the maximum value of the environmental weight; when the physiological state score is greater than the first preset threshold and less than the second preset threshold, the physiological weight coefficient and the environmental weight coefficient change with the physiological state score in a linear relationship; wherein, when the first preset threshold is less than the second preset threshold, the sum of the physiological weight coefficient and the environmental weight coefficient is 1.

[0011] Optionally, a comprehensive comfort demand index is generated based on physiological state scores, environmental quality scores, physiological weight coefficients, and environmental weight coefficients, including: calculating physiological demand deviation values ​​based on ideal physiological state scores and physiological state scores; calculating environmental demand deviation values ​​based on ideal environmental quality scores and environmental quality scores; and weighting and summing the physiological demand deviation values ​​and environmental demand deviation values ​​based on physiological weight coefficients and environmental weight coefficients to generate a comprehensive comfort demand index.

[0012] Optionally, it also includes: using a three-level hierarchical reminder mechanism to provide feedback to users on the control status of smart home devices via the smartwatch, and responding to user operations on the smartwatch to manually control the smart home devices.

[0013] Secondly, embodiments of the present invention provide a device adaptive control apparatus based on physiological state, comprising: a data acquisition module for real-time acquisition of user physiological state data and indoor environmental parameter data; an evaluation module for obtaining a physiological state score and an environmental quality score based on the physiological state data and the indoor environmental parameter data, and generating a comprehensive comfort demand index based on the physiological state score and the environmental quality score; a control strategy generation module for identifying the currently applicable scenario mode through composite triggering logic based on the comprehensive comfort demand index, physiological state data, and indoor environmental parameter data, and determining the target control strategy corresponding to the scenario mode; and a control strategy module for distributing the target control strategy to smart home devices so that the smart home devices can adjust the indoor environment.

[0014] Thirdly, embodiments of the present invention provide an electronic device including a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of any of the methods provided in the first aspect above.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method provided in any of the first aspects above.

[0016] The embodiments of the present invention bring the following beneficial effects: The above-mentioned device adaptive control method, apparatus, and electronic device based on physiological state provided by this invention first collects user physiological state data and indoor environmental parameter data in real time; secondly, it obtains physiological state scores and environmental quality scores based on the physiological state data and indoor environmental parameter data, and generates a comprehensive comfort demand index based on the physiological state scores and environmental quality scores; then, based on the comprehensive comfort demand index, physiological state data, and indoor environmental parameter data, it identifies the currently applicable scenario mode through composite triggering logic and determines the target control strategy corresponding to the scenario mode; finally, it sends the target control strategy to the smart home device so that the smart home device can adjust the indoor environment. In the above method, by scoring the user's physiological state data and indoor environmental parameter data and generating a comprehensive comfort demand index, and by combining the comprehensive comfort demand index, physiological state data, and indoor environmental parameter data to generate a target control strategy through composite triggering logic, a dual-factor fusion decision based on physiological state and environmental parameters is achieved. This enables smart home control to better meet the user's actual comfort needs and significantly improves the user's living experience.

[0017] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

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

[0020] Figure 1 A flowchart of a device adaptive control method based on physiological state provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a two-factor fusion model provided in an embodiment of the present invention; Figure 3 A schematic diagram of a composite triggering logic architecture provided in an embodiment of the present invention; Figure 4 A flowchart illustrating a physiological state-based adaptive control method for devices that combines physiological state and environmental parameters, provided in an embodiment of the present invention. Figure 5 An architecture diagram of a local edge gateway provided in an embodiment of the present invention; Figure 6 A schematic diagram of a device adaptive control device based on physiological state provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

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

[0022] Currently, existing smart home control systems mainly employ the following control methods: The first is manual control, where users manually adjust the parameters of various devices via a mobile app or voice assistant; the second is preset scene modes, where users pre-set various scene modes (such as home mode, sleep mode, movie mode, etc.), and switch to the preset device state with a single click when triggered; the third is automatic control based on environmental sensors, which automatically triggers corresponding device control when environmental parameters (such as temperature, humidity, light, etc.) reach preset thresholds. However, most existing smart home control systems use a binary logic of "environmental threshold trigger + manually preset scene," such as automatically turning on the air conditioner when the temperature exceeds 28℃, resulting in a poor user experience.

[0023] Based on this, the present invention provides a device, apparatus and electronic device based on physiological state adaptive control, which enables smart home control to better meet the actual comfort needs of users and significantly improve the user's living experience.

[0024] To facilitate understanding of this embodiment, a device adaptive control method based on physiological state disclosed in this invention will first be described in detail. This method can be executed by electronic devices, such as smartphones and tablets. See also Figure 1 The flowchart shown illustrates a device adaptive control method based on physiological state, which mainly includes the following steps S101 to S104: Step S101: Collect user's physiological status data and indoor environmental parameter data in real time.

[0025] In one implementation, wearable devices (such as smartwatches and smart bracelets) are used to collect users' physiological state data. This physiological state data includes, but is not limited to, heart rate (HR), heart rate variability (HRV), sleep status, stress level, skin conductance response (GSR), and respiratory rate. The collection process includes: collecting heart rate and heart rate variability data using a photoelectric sensor (PPG) built into the wearable device; collecting body movement data using an accelerometer and gyroscope, and combining this with heart rate data to identify sleep stages; and assessing the user's stress level through a fusion analysis of heart rate variability, skin conductance response, and respiratory rate. Furthermore, the collected raw physiological data is preprocessed, and the preprocessed physiological state data is transmitted to a smart home control center via Bluetooth, Wi-Fi, or other secure communication protocols.

[0026] Environmental parameter data is collected through multiple indoor environmental sensors. These parameters include, but are not limited to: light intensity (lux), noise level (dB), temperature (°C), humidity (%RH), and air quality (PM2.5, CO2, VOCs, etc.). The environmental sensors can be standalone all-in-one environmental monitoring devices or integrated into smart home devices (such as air conditioners, ventilation systems, and smart lighting). Each sensor transmits its collected data to the smart home control center via Zigbee, Bluetooth Mesh, or Wi-Fi networks. The environmental data undergoes a 30-second moving average filtering process to smooth out instantaneous fluctuations.

[0027] Step S102: Obtain physiological state scores and environmental quality scores based on physiological state data and indoor environmental parameter data, and generate a comprehensive comfort demand index based on physiological state scores and environmental quality scores.

[0028] In one implementation, physiological state scores and environmental quality scores are obtained through physiological state assessment models and environmental quality assessment models, respectively. Then, physiological weight coefficients and environmental weight coefficients are dynamically calculated based on the physiological state scores using a two-factor fusion model. Finally, a comprehensive comfort demand index (CDI) is generated based on the physiological state scores, environmental quality scores, and corresponding weight coefficients.

[0029] The two-factor fusion model employs a piecewise linear dynamic weight allocation mechanism: when the physiological state score is below a preset physiological abnormality threshold, the physiological weight coefficient is increased to prioritize the control strategy's adaptation to human sensory needs; when the physiological state score is above a preset physiological stability threshold, the environmental weight coefficient is increased to prioritize the optimization of environmental quality and energy efficiency. The sum of the physiological weight coefficient and the environmental weight coefficient is 1, with the physiological weight coefficient ranging from 0.3 to 0.9 and the environmental weight coefficient ranging from 0.1 to 0.7.

[0030] Step S103: Based on the comprehensive comfort demand index, physiological state data and indoor environmental parameter data, identify the currently applicable scenario mode through composite trigger logic, and determine the target control strategy corresponding to the scenario mode.

[0031] In one implementation, the composite triggering logic includes the automatic identification of multiple scene modes: office relaxation mode, sleep mode, and exercise recovery mode. Each scene mode corresponds to a different device control strategy, which can automatically match the most suitable control scheme according to the user's physiological state and environmental parameters; among them, the sleep mode supports fine-tuning of environmental parameters according to sleep stages. In this embodiment of the invention, the applicable scene mode is identified based on the comprehensive comfort demand index and by combining physiological state data and indoor environmental parameter data, thereby determining the target control strategy corresponding to the scene mode.

[0032] Step S104: Send the target control strategy to smart home devices so that the smart home devices can adjust the indoor environment.

[0033] In one implementation, the device linkage control is achieved through a six-layer technical link: strategy parsing and decomposition, device capability mapping, multi-device timing orchestration, multi-protocol conversion and distribution, execution feedback closed-loop verification, and anomaly fallback and degradation, to ensure the orderliness and stability of multi-device collaboration.

[0034] Specifically, the system first analyzes and breaks down the target control strategy to form a list of control tasks for each device. Second, based on the capabilities of each device, the control tasks are adapted, verified, and parameters are corrected. Then, the control tasks for multiple devices are time-sequentially arranged, divided into synchronous execution groups, sequential execution groups, and gradual execution groups. Next, standardized control commands are converted into command formats corresponding to the communication protocol and transmitted through the appropriate radio frequency module. Simultaneously, device execution feedback is received, and commands that are unresponsive or fail to execute are retransmitted. Parameter changes are continuously monitored based on environmental sensors to verify the control effect and perform closed-loop correction. When some devices malfunction or data is interrupted, the system automatically skips the malfunctioning devices or degrades to a pure environmental parameter control mode, maintaining the system's basic functions.

[0035] The above-mentioned device adaptive control method based on physiological state provided in this embodiment of the invention scores the user's physiological state data and indoor environmental parameter data, and generates a comprehensive comfort demand index. At the same time, it combines the comprehensive comfort demand index, physiological state data and indoor environmental parameter data, and generates a target control strategy through composite triggering logic. This realizes the dual-factor fusion decision of physiological state and environmental parameters, which enables smart home control to better meet the user's actual comfort needs and significantly improves the user's living experience.

[0036] In one implementation, for the aforementioned step S102, i.e., when obtaining the physiological state score and environmental quality score based on physiological state data and indoor environmental parameter data, the following methods may be used, including but not limited to: (1) Based on physiological state data, output physiological state scores through physiological state assessment models.

[0037] In one implementation, a heart rate abnormality score, heart rate variability score, sleep state score, and stress level score are calculated based on physiological state data, and the heart rate abnormality score, heart rate variability score, sleep state score, and stress level score are fused based on a preset first weighting coefficient to obtain a physiological state score.

[0038] In practice, the physiological state assessment model is a multi-dimensional comprehensive assessment model, with the output physiological state score ranging from 0 to 100. A higher score indicates a more stable and healthier physiological state. The physiological state score is a weighted fusion of four sub-dimensions, with each indicator set according to medical standards. ① Heart rate abnormality score (weight 25%): The user's personalized resting heart rate is used as the baseline value HRbase, the real-time heart rate is HRreal, and the deviation rate ΔHR = |HRreal HRbase | / HRbase.

[0039] When ΔHR≤20%, the heart rate abnormality score is 100. When 20% < ΔHR ≤ 50%, the score decreases linearly from 100 points to 60 points; When ΔHR>50%, a score below 60 is considered a significant heart rate abnormality.

[0040] ② Heart Rate Variability (HRV) Score (weight 30%): The core time-domain indicators SDNN (standard deviation of all sinus RR intervals) and RMSSD (root mean square of the difference between adjacent intervals) are selected, combined with the frequency-domain indicator LF / HF ratio for comprehensive evaluation. Reference standards for healthy adults: normal SDNN value is 141±39ms, normal RMSSD value is 27±12ms, and normal LF / HF ratio range is 1.5~2.0.

[0041] When SDNN≥100ms, RMSSD≥20ms, and LF / HF are within the normal range, the HRV score is 90~100 points (good autonomic balance). When SDNN is in the range of 50-100ms and RMSSD is in the range of 15-20ms, the score is 60-89 (moderately reduced). When SDNN < 50ms and RMSSD < 15ms, the score is < 60 points (severely reduced, indicating stress overload or fatigue).

[0042] ③ Sleep status score (weight 25%): Sleep stages are identified based on the fusion of multiple features including heart rate, body movement, and HRV. Sleep onset criteria: heart rate drops to below 90% of resting heart rate, body acceleration amplitude is <0.1g, and RMSSD is more than 15% higher than that of the waking state; Deep sleep stage: Heart rate stabilizes at 80%~85% of resting heart rate, SDNN decreases compared to light sleep stage, and body movement is minimal; Sleep efficiency = actual sleep duration / time spent in bed, combined with the percentage of deep sleep (normally 20%~30%) for a comprehensive score.

[0043] ④ Stress level score (weight 20%): The core is the LF / HF ratio of HRV frequency domain characteristics, combined with heart rate variability and respiratory rate: LF / HF>2.0 indicates sympathetic nerve excitation and increased stress; LF / HF<1.0 indicates parasympathetic dominance and relaxed state.

[0044] The scores of the above four sub-dimensions are weighted and summed according to the first preset weight to obtain the final physiological state score Sp.

[0045] In this embodiment of the invention, the physiological state assessment model is constructed as a two-layer attention mechanism network: the first layer of attention extracts local key events from the time series of multiple physiological signals, and the second layer of attention performs global correlation weighting on the cooperative change patterns between signals; and while the model outputs a physiological state score, it also outputs a physiological instability index, which is used to dynamically adjust the update frequency of the physiological state score in subsequent steps. When the instability exceeds the threshold, the data collection interval is shortened.

[0046] (2) Based on environmental parameter data, output environmental quality score through environmental quality assessment model.

[0047] In one implementation, thermal comfort score, light environment score, sound environment score and air quality score are calculated based on environmental parameter data, and the thermal comfort score, light environment score, sound environment score and air quality score are fused based on a preset second weighting coefficient to obtain an environmental quality score.

[0048] In practice, the environmental quality assessment model is a multi-parameter comprehensive assessment model, outputting an environmental quality score ranging from 0 to 100 points. A higher score indicates better and more comfortable environmental quality. The score is constructed with reference to indoor environmental standards and the PMV thermal comfort theory. The environmental quality score is a weighted fusion of four sub-dimensions: ① Thermal comfort score (weight 35%): Based on the simplified adaptation of the PMV (predicted average vote) thermal comfort model, the core inputs are air temperature, relative humidity, and wind speed. The default human metabolic rate is sitting state (1.0met) and normal indoor clothing (0.6clo).

[0049] When the PMV value is in the range of -0.5 to +0.5, the thermal comfort score is 90 to 100 points (comfortable for the vast majority of people). The optimal range corresponds to a room temperature of 22~26℃ and a relative humidity of 40%~60%. The further the range deviates from this range, the lower the score. When the temperature is above 28℃ and the humidity is above 65%, the score is below 60 points, indicating a stuffy and uncomfortable condition.

[0050] ② Lighting environment score (weight 20%): Referencing the "Standard for Architectural Lighting Design", the target value is dynamically adjusted based on the scene: Office scenarios: Optimal desktop illuminance is 500~750 lux and color temperature is 4000~5000K; Relaxation scenario: Ambient illuminance of 100~300 lux and color temperature of 2700~3000K warm light are optimal; Sleep scenario: Ambient illuminance <5 lux is optimal.

[0051] ③ Acoustic environment score (weight 20%) Daytime noise levels ≤40dB are considered excellent (100 points), 40~55dB are considered good (70~90 points), and scores >55dB show a significant decrease. Nighttime sleep scenario: Noise ≤30dB is excellent, >40dB is considered sleep disturbance.

[0052] ④ Air quality score (weight 25%) PM2.5≤35μg / m³, CO2≤800ppm, and TVOC≤0.6mg / m³ are considered excellent (100 points). When CO2 > 1000 ppm, the score is below 70, indicating air pollution. When PM2.5 > 75 μg / m³, the air quality score is below 60, triggering the need for air purification.

[0053] The scores of the above four sub-dimensions are weighted and summed according to preset weights to obtain the final environmental quality score Se.

[0054] In this embodiment of the invention, the environmental quality assessment model adopts a combination of fuzzy logic and physical constraints: first, independent membership functions are generated based on the national standard comfort range of each environmental parameter; then, the coupling influence factors between each parameter are fused through a Bayesian network to output an environmental quality score; furthermore, the model has a built-in seasonal offset compensation module that automatically corrects the center value and boundary slope of the comfort range of each parameter according to the current date and geographical location.

[0055] The system maintains a "seasonal-climate offset table" based on geographic location and current date. This table provides the temperature comfort range correction amount for each month or solar term (e.g., the comfort temperature center value is adjusted upward by 1.5℃ in winter and downward by 1.0℃ in summer), humidity preference offset, and light preference offset based on local historical meteorological data.

[0056] Before performing Bayesian inference, the compensation module first reads the system clock and GPS location, calculates the offset coefficient corresponding to the current date, and then dynamically adjusts the center point and boundary slope of each fuzzy set (for example, the membership function center of the "comfortable" temperature in winter moves from 24℃ to 25.5℃). This adjustment allows the same measured temperature to be mapped to different fuzzy sets in different seasons, thus enabling the environmental quality score to reflect people's adaptive preferences to the environment.

[0057] In one embodiment, for the aforementioned step S102, that is, when generating the comprehensive comfort demand index based on the physiological state score and the environmental quality score, the following methods may be adopted including but not limited to: First, the physiological weight coefficient and the environmental weight coefficient are dynamically calculated based on the physiological state score and the two-factor fusion model.

[0058] In one embodiment, when the physiological state score is less than or equal to a first preset threshold, the physiological weight coefficient takes the maximum physiological weight value, and the environmental weight coefficient takes the minimum environmental weight value; when the physiological state score is greater than or equal to a second preset threshold, the physiological weight coefficient takes the minimum physiological weight value, and the environmental weight coefficient takes the maximum environmental weight value; when the physiological state score is greater than the first preset threshold and less than the second preset threshold, the physiological weight coefficient and the environmental weight coefficient vary with the physiological state score in a linear relationship; wherein the first preset threshold is less than the second preset threshold, and the sum of the physiological weight coefficient and the environmental weight coefficient is 1.

[0059] In specific implementation, refer to Figure 2 the shown schematic structural diagram of a two-factor fusion model. The core of the two-factor fusion model is a piecewise linear dynamic weight allocation mechanism.

[0060] The physiological weight coefficient (Wp) and the environmental weight coefficient (We) satisfy the following relationship: Wp+We=1. A physiological abnormality threshold (i.e., the first preset threshold) T1=60 points is set, and a physiological stability threshold (i.e., the second preset threshold) T2=85 points is set; the maximum physiological weight value Wp_max=0.9, the minimum physiological weight value Wp_min=0.3, the maximum environmental weight value We_max=0.7, and the minimum environmental weight value We_min=0.1. The dynamic weight allocation rules are as follows: For the physiological abnormality interval (Sp≤60 points, that is, the physiological state score is less than or equal to the first preset threshold): the physiological weight coefficient takes the maximum physiological weight value of 0.9, and the environmental weight coefficient takes the minimum environmental weight value of 0.1, so as to fully prioritize the adaptation to human body somatosensory perception.

[0061] For the transition interval (60<Sp<85 points, that is, the physiological state score is greater than the first preset threshold and less than the second preset threshold): the weight varies linearly with the physiological score, and the calculation formula is: Wp=Wp_max-(Wp_max-Wp_min) / (T2-T1)×(Sp-T1). Substituting the values gives: Wp=0.9-(0.6 / 25)×(Sp-60). For example, when Sp=72, Wp=0.9-0.024×12=0.612, corresponding to We=0.388.

[0062] For the physiological stability range (Sp≥85 points, i.e., the physiological state score is greater than or equal to the second preset threshold): the physiological weight coefficient is taken as the minimum physiological weight of 0.3, and the environmental weight coefficient is taken as the maximum environmental weight of 0.7, prioritizing the optimization of environmental quality and energy efficiency.

[0063] It should be noted that the above thresholds and weight ranges can be adjusted according to the user's personalized needs.

[0064] Then, a comprehensive comfort demand index is generated based on physiological state scores, environmental quality scores, physiological weight coefficients, and environmental weight coefficients.

[0065] In one implementation, firstly, a physiological demand deviation value is calculated based on the ideal physiological state score and the physiological state score; secondly, an environmental demand deviation value is calculated based on the ideal environmental quality score and the environmental quality score; finally, the physiological demand deviation value and the environmental demand deviation value are weighted and summed based on the physiological weight coefficient and the environmental weight coefficient to generate a comprehensive comfort demand index.

[0066] In practice, the comprehensive comfort demand index reflects the degree of deviation between the current environment and the user's ideal comfort state; a higher index indicates a more urgent comfort need. The calculation method for the comprehensive comfort demand index is as follows: Dp = 100 - Sp (Physiological Demand Deviation) De = 100 - Se (Environmental Demand Deviation) CDI = Wp × Dp + We × De The CDI value ranges from 0 to 100. The higher the value, the more urgent the need for comfort improvement: CDI>40 triggers strong intervention, 20~40 triggers moderate adjustment, and <15 enters the energy-saving maintenance mode.

[0067] This calculation method takes into account both the degree of abnormality in physiological state and the quality of environment, and achieves a balance between the two through dynamic weighting.

[0068] See Figure 3 The diagram shows an architecture of a composite triggering logic, which includes two stages: scene recognition and policy generation.

[0069] Scene recognition stage: The comprehensive comfort demand index is compared with multiple preset trigger thresholds, and physiological and environmental parameter features are combined to match the corresponding scene mode.

[0070] In this embodiment of the invention, the scene modes include, but are not limited to, the following three: (1) Office relaxation mode Triggering conditions: CDI≥35, and pressure score<60, HRV score<65, while the environment meets at least two of the following: temperature>28℃, CO2>1000ppm, or illuminance>800lux.

[0071] Control strategy: Automatically turn on the fresh air system to medium fan speed, with the target CO2 concentration controlled below 800ppm; adjust the air conditioner to cooling mode, with a target temperature of 24℃, relative humidity of 50%, and low fan speed to avoid direct airflow; reduce the brightness of the main light to 200lux and switch the color temperature to 3000K warm white light; selectively play alpha wave background music with the volume controlled at 30~35dB.

[0072] (2) Sleep mode Triggering conditions: The wearable device identifies the user as "asleep", or during the nighttime period, the heart rate decreases continuously with a CDI ≥ 30.

[0073] Phased control strategy: Sleep period: Turn off the main light, leave the night light at 5 lux or less, completely close the curtains, and set the air conditioner to 26℃ silent mode; Deep sleep period: Increase the temperature by 0.5~1℃ and set the fresh air intake to the lowest setting to further reduce operating noise; Light sleep / REM phase: Temperature drops to 25℃, maintain low wind speed; Awakening period: Slowly open the curtains 10%~20%, gradually brighten the lights to simulate sunrise, and assist in natural awakening.

[0074] (3) Exercise recovery mode Triggering conditions: The wearable device recognizes that within 5 minutes after the end of exercise, the heart rate is still higher than 120% of the resting heart rate, and the indoor temperature is >26℃.

[0075] Control strategy: Automatically activate ventilation and cooling mode, open windows or start the fresh air system for high-speed ventilation; set the air conditioner to cooling 25℃ and natural wind mode, with the fan speed gradually reduced from medium to low to avoid direct airflow; maintain soft, warm light and avoid strong light stimulation; when the heart rate drops to below 110% of the resting heart rate, automatically switch to normal comfort mode.

[0076] In one embodiment, the method further includes: using a three-level hierarchical reminder mechanism on the smart watch to provide feedback on the control status of the smart home devices, and responding to the user's operations on the smart watch to manually control the smart home devices.

[0077] In practical implementation, the smartwatch serves as a portable interaction portal, employing a three-level hierarchical reminder mechanism to provide feedback on control status, and automatically remaining silent and undisturbed during sleep scenarios. It also provides a lightweight UI control interface, supporting one-click scene switching and fine-tuning of individual devices, thus achieving a complete interactive closed loop of data collection, decision-making, control, and feedback.

[0078] Specifically, users can access the scene master control page via the quick access on the watch face or the control center to trigger preset scene modes with one click; they can also access the single device details control page to finely adjust the brightness and color temperature of lights, the temperature and operating mode of air conditioning, the opening and closing degree of curtains, and the level of the fresh air system; all manual control commands are executed by the local edge gateway after identity authentication and anti-replay verification, and the status displayed on the watch is updated synchronously.

[0079] Furthermore, the three-tiered alert mechanism includes: In strong alert mode, continuous vibration and full-screen pop-up windows will be used to notify the device of execution failure, abnormal parameters alarm, or user-controlled confirmation matters. In the weak reminder mode, a single short vibration and a full-screen pop-up will indicate that the strategy for the regular scenario has been executed, and an option to cancel the operation will be provided. In silent alert mode, no vibration or pop-up is triggered; only the execution log is recorded in the message center. The alert mode is automatically matched by the local edge gateway based on the scenario type, event level, and the user's current physiological state.

[0080] For ease of understanding, this embodiment of the invention also provides a flowchart illustrating a physiological state-based adaptive control method for devices that combines physiological states with environmental parameters. (See attached diagram.) Figure 4 As shown, the main steps include: Step 1: Collect user physiological status data and indoor environmental parameter data in real time.

[0081] Step 2: Obtain physiological state scores and environmental quality scores using the physiological state assessment model and the environmental quality assessment model, respectively.

[0082] Step 3: Based on the physiological state score, dynamically calculate the physiological weight coefficient and environmental weight coefficient using a two-factor fusion model.

[0083] Step 4: Generate a comprehensive comfort demand index based on physiological state scores, environmental quality scores, and corresponding weighting coefficients.

[0084] Step 5: Determine the target control strategy through composite triggering logic.

[0085] Step 6: Send control commands to smart home devices to adjust the indoor environment; at the same time, realize hierarchical reminders of control status and manual control on the go through the smartwatch.

[0086] In this embodiment of the invention, the generation of the target control strategy adopts a two-level deployment architecture of local edge gateway as the main decision-maker and cloud service platform as the auxiliary optimization: the local edge gateway is the core physical carrier, responsible for all real-time calculations and command issuance, ensuring low latency and data privacy; the cloud platform is responsible for non-real-time preference model training and parameter calibration, continuously optimizing the control effect.

[0087] See Figure 5 The diagram shown represents the architecture of a local edge gateway, which mainly includes: a data acquisition layer, an evaluation layer, a decision-making layer, an interaction layer, an execution layer, and an output layer.

[0088] The acquisition layer includes a physiological data acquisition module and an environmental data acquisition module, which are used to collect users' physiological state data and indoor environmental parameter data, respectively.

[0089] The assessment layer includes a physiological state assessment module and an environmental quality assessment module, which are used to obtain physiological state scores and environmental quality scores through the physiological state assessment model and the environmental quality assessment model, respectively.

[0090] The decision-making layer includes a two-factor fusion module and a control strategy decision-making module. The two-factor fusion module comprises a dynamic weight adjustment unit and a comprehensive index calculation unit. The dynamic weight adjustment unit dynamically calculates physiological and environmental weight coefficients based on physiological state scores using a two-factor fusion model. The comprehensive index calculation unit generates a comprehensive comfort demand index based on physiological state scores, environmental quality scores, and corresponding weight coefficients. The control strategy decision-making module includes a scenario identification unit and a strategy generation unit, used to determine the target control strategy through composite triggering logic.

[0091] The interaction layer includes a smartwatch interaction module, which enables hierarchical reminders of control status and manual control on the go.

[0092] The execution layer includes a device control module, which comprises a strategy parsing unit, a device adaptation unit, a timing orchestration unit, a protocol conversion unit, and a feedback verification unit. The strategy parsing unit parses and decomposes the target control strategy to form a single-device control task list. The device adaptation unit performs adaptation verification and parameter correction for control tasks based on the capabilities of each device. The timing orchestration unit orchestrates the control tasks of multiple devices, dividing them into synchronous execution groups, sequential execution groups, and gradual execution groups. The protocol conversion unit converts standardized control commands into the command format of the corresponding communication protocol and sends them through the corresponding radio frequency module. The feedback verification unit receives device execution feedback, retransmits unresponsive or failed commands, continuously monitors parameter changes based on environmental sensors, verifies the control effect, and performs closed-loop correction.

[0093] The output layer includes a group of smart home devices used to receive target control policies and adjust the indoor environment.

[0094] The method provided in the embodiments of the present invention has the following effects: (1) It realizes the dual-factor fusion decision of physiological state and environmental parameters, making smart home control more in line with the actual comfort needs of users and significantly improving the living experience; (2) Through a piecewise linear dynamic weight allocation mechanism, human comfort is prioritized when physiological abnormalities occur, while energy efficiency is optimized when physiological stability is achieved, thus realizing a dynamic balance between comfort and energy saving. (3) The two-level deployment architecture of local edge gateway + cloud is adopted, which not only ensures low latency of real-time control and the privacy and security of physiological data, but also has the ability to continuously iterate and optimize. (4) Automatic recognition and adaptive control of multiple scenarios. No need for users to manually switch scenario modes. The system can automatically match the optimal control strategy according to physiological-environmental characteristics. Sleep scenarios support phased and refined adjustment. (5) The improved multi-device linkage control link, through timing arrangement, multi-protocol adaptation and closed-loop verification, solves the problems of conflict and false triggering in multi-device collaboration, and greatly improves the system stability and reliability; (6) A hierarchical reminder and manual control system for smartwatches has been constructed, upgrading wearable devices from simple data collection terminals to interactive feedback terminals, forming a complete human-computer interaction closed loop. Users can obtain status and quickly adjust control without relying on mobile phones or central control screens. (7) The closed-loop linkage between wearable devices and smart home devices expands the application scenarios of wearable devices and improves the intelligence level of smart home systems. (8) The improved data preprocessing and anti-interference mechanism ensures the stability and accuracy of control decisions and avoids false triggering caused by instantaneous fluctuations.

[0095] In addition to the physiological state-based adaptive control method for devices provided in the foregoing embodiments, this invention also provides a physiological state-based adaptive control device. (See attached document.) Figure 6 The diagram shows a structural schematic of a device adaptive control system based on physiological state. This device may include the following components: The data acquisition module 601 is used to collect users' physiological status data and indoor environmental parameter data in real time.

[0096] The assessment module 602 is used to obtain physiological state scores and environmental quality scores based on physiological state data and indoor environmental parameter data, and to generate a comprehensive comfort demand index based on the physiological state scores and environmental quality scores.

[0097] The control strategy generation module 603 is used to identify the currently applicable scenario mode based on the comprehensive comfort demand index, physiological state data and indoor environmental parameter data, and determine the target control strategy corresponding to the scenario mode through composite triggering logic.

[0098] The control strategy module 604 is used to send the target control strategy to smart home devices so that the smart home devices can adjust the indoor environment.

[0099] The device adaptive control based on physiological state provided in this embodiment of the invention scores the user's physiological state data and indoor environmental parameter data, and generates a comprehensive comfort demand index. At the same time, it combines the comprehensive comfort demand index, physiological state data and indoor environmental parameter data, and generates a target control strategy through composite triggering logic. This realizes the dual-factor fusion decision of physiological state and environmental parameters, which enables smart home control to better meet the user's actual comfort needs and significantly improves the user's living experience.

[0100] In one implementation, the assessment module 602 is specifically used to: output a physiological state score based on physiological state data through a physiological state assessment model; and output an environmental quality score based on environmental parameter data through an environmental quality assessment model.

[0101] In one embodiment, the assessment module 602 is specifically used to: calculate the abnormal heart rate score, heart rate variability score, sleep state score and stress level score based on physiological state data, and fuse the abnormal heart rate score, heart rate variability score, sleep state score and stress level score based on a preset first weighting coefficient to obtain the physiological state score.

[0102] In one embodiment, the evaluation module 602 is specifically used to: calculate thermal comfort score, light environment score, sound environment score and air quality score based on environmental parameter data, and fuse the thermal comfort score, light environment score, sound environment score and air quality score based on a preset second weighting coefficient to obtain an environmental quality score.

[0103] In one implementation, the assessment module 602 is specifically used to: dynamically calculate the physiological weight coefficient and the environmental weight coefficient based on the physiological state score and the two-factor fusion model; and generate a comprehensive comfort demand index based on the physiological state score, the environmental quality score, the physiological weight coefficient, and the environmental weight coefficient.

[0104] In one embodiment, the evaluation module 602 is specifically used to: when the physiological state score is less than or equal to a first preset threshold, the physiological weight coefficient is taken as the maximum physiological weight and the environmental weight coefficient is taken as the minimum environmental weight; when the physiological state score is greater than or equal to a second preset threshold, the physiological weight coefficient is taken as the minimum physiological weight and the environmental weight coefficient is taken as the maximum environmental weight; when the physiological state score is greater than the first preset threshold and less than the second preset threshold, the physiological weight coefficient and the environmental weight coefficient change with the physiological state score in a linear relationship; wherein, when the first preset threshold is less than the second preset threshold, the sum of the physiological weight coefficient and the environmental weight coefficient is 1.

[0105] In one implementation, the assessment module 602 is specifically used to: calculate the physiological demand deviation value based on the ideal physiological state score and the physiological state score; calculate the environmental demand deviation value based on the ideal environmental quality score and the environmental quality score; and generate a comprehensive comfort demand index by weighted summation of the physiological demand deviation value and the environmental demand deviation value based on the physiological weight coefficient and the environmental weight coefficient.

[0106] In one embodiment, the device further includes an interaction module for: providing feedback on the control status of smart home devices to the user via a three-level hierarchical reminder mechanism on the smart watch, and manually controlling the smart home devices in response to the user's operations on the smart watch.

[0107] It should be noted that in all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limitations; therefore, other examples of exemplary embodiments may have different values.

[0108] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0109] This invention also provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program, when run by the processor, executes the method described in any of the above embodiments.

[0110] Figure 7 The present invention provides a schematic diagram of the structure of an electronic device 100, which includes a processor 70, a memory 71, a bus 72 and a communication interface 73. The processor 70, the communication interface 73 and the memory 71 are connected through the bus 72. The processor 70 is used to execute executable modules, such as computer programs, stored in the memory 71.

[0111] The memory 71 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 73 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0112] Bus 72 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0113] The memory 71 is used to store programs. After receiving an execution instruction, the processor 70 executes the programs. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 70 or implemented by the processor 70.

[0114] The processor 70 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 70 or by instructions in software form. The processor 70 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 71. Processor 70 reads the information in memory 71 and, in conjunction with its hardware, completes the steps of the above method.

[0115] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A device adaptive control method based on physiological state, characterized in that, include: Real-time collection of users' physiological status data and indoor environmental parameter data; Physiological state scores and environmental quality scores are obtained based on the physiological state data and the indoor environmental parameter data, and a comprehensive comfort demand index is generated based on the physiological state scores and the environmental quality scores. Based on the comprehensive comfort demand index, the physiological state data, and the indoor environmental parameter data, the applicable scenario mode is identified through composite triggering logic, and the target control strategy corresponding to the scenario mode is determined. The target control strategy is sent to smart home devices so that the smart home devices can adjust the indoor environment.

2. The method according to claim 1, characterized in that, Based on the physiological state data and the indoor environmental parameter data, physiological state scores and environmental quality scores are obtained, including: Based on the physiological state data, a physiological state score is output through a physiological state assessment model; Based on the environmental parameter data, an environmental quality score is output through an environmental quality assessment model.

3. The method according to claim 2, characterized in that, Based on the physiological state data, a physiological state score is output through a physiological state assessment model, including: Based on the physiological state data, heart rate abnormality score, heart rate variability score, sleep state score and stress level score are calculated respectively. The heart rate abnormality score, heart rate variability score, sleep state score and stress level score are then fused based on a preset first weighting coefficient to obtain the physiological state score.

4. The method according to claim 2, characterized in that, Based on the aforementioned environmental parameter data, an environmental quality score is output through an environmental quality assessment model, including: Based on the environmental parameter data, thermal comfort score, light environment score, sound environment score and air quality score are calculated respectively. The thermal comfort score, light environment score, sound environment score and air quality score are then fused based on a preset second weighting coefficient to obtain the environmental quality score.

5. The method according to claim 1, characterized in that, A comprehensive comfort demand index is generated based on the physiological state score and the environmental quality score, including: Based on the physiological state score and the two-factor fusion model, the physiological weight coefficient and the environmental weight coefficient are dynamically calculated. A comprehensive comfort demand index is generated based on the physiological state score, the environmental quality score, the physiological weight coefficient, and the environmental weight coefficient.

6. The method according to claim 5, characterized in that, Based on the aforementioned physiological state score and the two-factor fusion model, the physiological weight coefficient and environmental weight coefficient are dynamically calculated, including: When the physiological state score is less than or equal to the first preset threshold, the physiological weight coefficient takes the maximum value of the physiological weight, and the environmental weight coefficient takes the minimum value of the environmental weight. When the physiological state score is greater than or equal to the second preset threshold, the physiological weight coefficient takes the minimum physiological weight, and the environmental weight coefficient takes the maximum environmental weight. When the physiological state score is greater than the first preset threshold and less than the second preset threshold, the physiological weight coefficient and the environmental weight coefficient change with the physiological state score in a linear relationship; wherein, the first preset threshold is less than the second preset threshold, and the sum of the physiological weight coefficient and the environmental weight coefficient is 1.

7. The method according to claim 5, characterized in that, A comprehensive comfort demand index is generated based on the physiological state score, the environmental quality score, the physiological weighting coefficient, and the environmental weighting coefficient, including: Based on the ideal physiological state score and the physiological state score, the physiological demand deviation value is calculated; Based on the ideal environmental quality score and the environmental quality score, calculate the environmental demand deviation value; Based on the physiological weight coefficient and the environmental weight coefficient, the physiological demand deviation value and the environmental demand deviation value are weighted and summed to generate a comprehensive comfort demand index.

8. The method according to claim 1, characterized in that, Also includes: The smartwatch uses a three-level hierarchical reminder mechanism to provide feedback to the user on the control status of the smart home devices and responds to the user's operations on the smartwatch to manually control the smart home devices.

9. A device adaptive control system based on physiological state, characterized in that, include: The data acquisition module is used to collect users' physiological status data and indoor environmental parameter data in real time; The assessment module is used to obtain physiological state scores and environmental quality scores based on the physiological state data and the indoor environmental parameter data, and to generate a comprehensive comfort demand index based on the physiological state scores and the environmental quality scores. The control strategy generation module is used to identify the currently applicable scenario mode based on the comprehensive comfort demand index, the physiological state data, and the indoor environmental parameter data, and to determine the target control strategy corresponding to the scenario mode through composite triggering logic. The control strategy module is used to send the target control strategy to smart home devices so that the smart home devices can adjust the indoor environment.

10. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 8.

Images