Method for adjusting human living environment based on comfort perception

Abstract

The invention discloses a human living environment adjusting method based on comfort perception. The human living environment adjusting method comprises the following steps that environmental parameters are collected; collecting physiological data of a user; the collected physiological data of the user are processed, the attention concentration degree is obtained according to the brain wave data, the muscle tension degree is obtained according to the myoelectricity data, and the cognitive load degree is obtained according to the eye movement data; evaluating a comfort index of the user in the current environment according to the attention concentration degree, the muscle tension degree and the cognitive load degree; if the comfort level index is smaller than a threshold value, interacting with a user, and obtaining user feedback; and adjusting the environmental parameters according to the user feedback and the comfort index. According to the method, the comfort index of the user in the current environment is evaluated according to the attention concentration degree, the muscle tension degree and the cognitive load degree, and the user feeling is comprehensively and accurately reflected; user feedback is increased, personalized requirements of the user are met, and a more comfortable use environment is provided for the user.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer control systems, and particularly relates to a method for adjusting a human living environment based on comfort perception. Background Art

[0002] With the continuous improvement of people's living standards, the requirements for the usage environment are no longer limited to the space size and the configuration of basic facilities, but people pay more attention to the comfort of the usage environment. A comfortable usage environment can not only improve people's quality of life, but also help with learning and relieve fatigue. For example, the following two sets of environmental parameters are respectively suitable for learning and relieving fatigue. First: temperature from 20 to 24 °C, humidity from 40% to 60%; sufficient and appropriate natural light or artificial lighting with a color temperature of 4000 to 5000 K can reduce visual fatigue; noise controlled below 40 to 50 decibels can avoid interference; fresh air can ensure brain vitality and improve learning efficiency. Second: temperature from 22 to 25 °C, humidity from 45% to 55%, reduced light intensity, warm-colored light, gentle music or natural sounds below 30 to 40 decibels; good air quality can make people refreshed.

[0003] Therefore, the technology for adjusting the human usage environment based on comfort perception has emerged as the times require, aiming to create a more comfortable and healthy living space for residents through real-time monitoring and intelligent adjustment of usage environment parameters, realizing personalized adjustment of the usage environment and meeting the personalized needs of different residents. The technology for adjusting the human usage environment based on comfort perception mainly comprehensively utilizes physiological signal perception technology and environmental parameter perception technology. The usage environment adjustment technology based on comfort perception can automatically adjust environmental parameters such as indoor temperature, light, and humidity according to the real-time comfort needs of residents.

[0004] However, affected by various factors such as age, gender, and living habits, the perception and needs of different individuals for environmental comfort vary greatly. Most of the current adjustment algorithms are developed based on general models, and it is difficult to fully consider the unique preferences and physiological characteristics of each person, and it is impossible to achieve truly personalized and precise adjustment. How to consider the unique preferences of each person and accurately reflect the comfort needs of users is the key problem to be solved. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for adjusting a human living environment based on comfort perception in view of the deficiencies in the above-mentioned prior art. The method has a simple structure and reasonable design, and evaluates the comfort index of the user in the current environment according to the attention concentration, muscle tension, and cognitive load, comprehensively and accurately reflecting the overall feeling and state of the user in the environment; and by adding user feedback to meet the personalized needs of users, a more comfortable and healthy usage environment is provided for users.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: a method for adjusting a human living environment based on comfort perception, characterized in that it includes the following steps:

[0007] S1: Collect environmental parameters through the first data collection module and output real-time environmental parameters;

[0008] S2: Collect user physiological data through the second data collection module; the user physiological data at least includes electroencephalogram data, electromyogram data, and eye movement data;

[0009] S3: Judge whether the electroencephalogram data shows high stress. If so, go to step S4; otherwise, go to step S5.

[0010] S4: Adjust the light and temperature to the soothing mode;

[0011] S5: Process the collected user physiological data, obtain the attention concentration according to the electroencephalogram data, obtain the muscle tension according to the electromyogram data, and obtain the cognitive load according to the eye movement data;

[0012] S6: Evaluate the comfort index of the user in the current environment according to the attention concentration, muscle tension, and cognitive load;

[0013] S7: If the comfort index is less than the comfort index threshold, interact with the user to obtain user feedback;

[0014] S8: Adjust the environmental parameters according to the user feedback and the comfort index.

[0015] The above method for adjusting a human living environment based on comfort perception is characterized in that: after adjusting the environmental parameters through step S8, return to step S2, re-collect user physiological data, and iteratively calculate the comfort index of the user in the current environment until the comfort index reaches the comfort index threshold or the user feedback is comfortable.

[0016] The above method for adjusting a human living environment based on comfort perception is characterized in that it further includes:

[0017] Integrate the user feedback to form a user preference data set;

[0018] The user preference data set is associated with the environmental parameter data set and the user physiological data set;

[0019] Set a condition-triggered user preference data set calling mechanism for adjusting environmental parameters.

[0020] The above method for adjusting a human living environment based on comfort perception is characterized in that: the specific method of "obtaining the attention concentration according to the electroencephalogram data" in step S5 includes:

[0021] S51. Brain wave data processing:

[0022] S511, according to formula S EEG =Butterworth(S raw , f low , f high ) to filter the EEG data; where S EEG represents the filtered EEG data, S raw represents the original EEG data, f low Indicates the lower cutoff frequency of the bandpass filter, f high Indicates the upper cutoff frequency of the bandpass filter;

[0023] S512, extracting the filtered brain wave data S EEG The frequency band energy;

[0024] S513. Calculate the concentration of attention C EEG , C EEG =C α ×ω α +C β ×ω β , where C α represents the energy proportion of α waves, ω α represents the weight of α wave, C β represents the energy proportion of β waves, ω β Represents the weight of the beta wave.

[0025] The above-mentioned method for adjusting the living environment of a person based on comfort perception is characterized in that: the specific method of "obtaining muscle tension according to electromyographic data" in step S5 includes:

[0026] S52, electromyography data processing:

[0027] S521, according to formula S EMG = abs(S raw )*LPF(f cutoff ) Process the original electromyographic signal S raw , get the envelope signal S EMG ;

[0028] S522, respectively calculate the root mean square value and the integrated electromyographic value: Where RMS represents the root mean square value of the electromyographic data, N represents the number of sampling points of the electromyographic data, and S EMGi represents the EMG data of the i-th sampling point, iEMG represents the integrated EMG value of the EMG data, and t 1 and t 2 represents the integration interval, S EMG(t) represents the expression of the change of electromyogram data over time;

[0029] S523. Calculate the muscle tension T EMG , T EMG = ω RMS × RMS + ω iEMG × iEMG, where ω RMS represents the weight of the root mean square value, ω iEMG represents the weight of the integrated electromyogram value.

[0030] The above-mentioned method for adjusting the human living environment based on comfort perception is characterized in that: the specific method of "obtaining the cognitive load degree according to the eye movement data" in step S5 includes:

[0031] S53. Eye movement data processing:

[0032] S531. Preprocessing of eye movement data;

[0033] S532. Calculate the fixation point entropy and saccade speed: The fixation point entropy H eye =-∑p j logp j , the saccade speed where p j represents the proportion of the fixation time in the jth area, represents the change in saccade angle;

[0034] S533. Calculate the cognitive load degree D eye , D eye = ω H × H eye + ω V × v saccade , where ω H represents the weight of the fixation point entropy, ω V represents the weight of the saccade speed.

[0035] The above-mentioned method for adjusting the human living environment based on comfort perception is characterized in that: the specific method of "evaluating the comfort index of the user in the current environment according to the attention concentration, muscle tension and cognitive load degree" in step S6 includes:

[0036] According to the formula CI actual = ω 1 · N(C EEG ) + ω 2 · N(T EMG ) + ω 3 · N(D eye ) calculate the comfort index CI actual , where ω 1 represents the weight of the attention concentration, v2 The weight representing muscle tension, ω 3 The weight representing the cognitive load, and N(·) represents the normalization function.

[0037] For the above-mentioned method for adjusting the human living environment based on comfort perception, it is characterized in that: the specific method of "adjusting environmental parameters according to user feedback and comfort index" in step S8 includes: when the user feedback is a comfortable feeling,

[0038] a. Update the weight according to the gradient descent method: where Loss = (CI target - CI actual ) 2 , CI target represents the comfort index threshold, represents the h-th weight at the t-th iteration, η represents the learning rate, which controls the step size of each weight update;

[0039] b. Convert the change in the comfort index into an environmental parameter adjustment amount for adjusting environmental parameters.

[0040] For the above-mentioned method for adjusting the human living environment based on comfort perception, it is characterized in that: the specific method of converting the change in the comfort index into an environmental parameter adjustment amount is:

[0041] Calculate the environmental parameter adjustment amount according to the formula where ΔT represents the temperature adjustment amount, k T represents the temperature adjustment coefficient, ΔHU represents the humidity adjustment amount, k HU represents the humidity adjustment coefficient, ΔI represents the light adjustment amount, k I represents the light adjustment coefficient.

[0042] For the above-mentioned method for adjusting the human living environment based on comfort perception, it is characterized in that: when adjusting the light and temperature to the soothing mode in step S4, the weight ω EEG of the attention concentration is increased.

[0043] The present invention has the following advantages compared with the prior art:

[0044] 1. The structure of the present invention is simple, the design is reasonable, and the implementation and use operations are convenient.

[0045] 2. While using the physiological signal perception technology to sense the comfort index of the user for the environment, the present invention increases user feedback to meet the personalized needs of users, and has a good use effect.

[0046] 3. The present invention obtains the attention concentration based on electroencephalogram data, obtains the muscle tension based on electromyogram data, and obtains the cognitive load based on eye movement data; evaluates the comfort index of the user in the current environment according to the attention concentration, muscle tension, and cognitive load; and comprehensively evaluates these three dimensions, which can more comprehensively and accurately reflect the overall feeling and state of the user in the environment and avoid the deviation of subjective judgment.

[0047] 4. The present invention integrates user feedback, establishes an association and call mechanism for the user preference data set, so as to obtain the comfort feeling of the user in a specific environment and respond in a timely manner, providing a more comfortable and healthy use environment for the user.

[0048] In summary, the present invention has a simple structure and reasonable design. It evaluates the comfort index of the user in the current environment according to the attention concentration, muscle tension, and cognitive load, comprehensively and accurately reflecting the overall feeling and state of the user in the environment; and increases user feedback to meet the personalized needs of the user, providing a more comfortable and healthy use environment for the user.

[0049] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0050] Figure 1 is the flowchart of the method of the present invention.

[0051] Figure 2 is the flowchart of the method for calculating the comfort index of the present invention. Detailed Embodiments

[0052] The method of the present invention will be further described in detail below in conjunction with the accompanying drawings and the embodiments of the present invention.

[0053] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0054] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless otherwise clearly specified in the context, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or their combinations.

[0055] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of the present application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0056] For ease of description, spatial relative terms such as "above", "over", "on the upper surface", "above" etc. may be used here to describe the spatial positional relationship of one device or feature shown in the figure with other devices or features. It should be understood that spatial relative terms are intended to include different orientations in use or operation in addition to the orientation of the device described in the figure. For example, if the device in the figure is inverted, the device described as "above" or "over" other devices or structures will then be positioned "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both the orientations of "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and corresponding interpretations are made for the spatial relative descriptions used here.

[0057] As Figure 1 and Figure 2 shown, a method for adjusting a human living environment based on comfort perception of the present invention includes the following steps:

[0058] S1: Collect environmental parameters through a first data collection module and output real-time environmental parameters;

[0059] S2: Collect user physiological data through a second data collection module; the user physiological data at least includes electroencephalogram data, electromyogram data and eye movement data;

[0060] S3: Determine whether the electroencephalogram data shows high stress. If so, go to step S4; otherwise, go to step S5. If C β ≥40%, it means that the electroencephalogram data shows high stress, and C β represents the energy proportion of β waves.

[0061] S4: Adjust the light and temperature to a soothing mode; at the same time, increase the weight ω EEG .

[0062] S5: Process the collected user physiological data, obtain the attention concentration based on the electroencephalogram data, obtain the muscle tension based on the electromyogram data, and obtain the cognitive load based on the eye movement data;

[0063] The specific method of "obtaining the attention concentration based on the electroencephalogram data" in step S5 includes:

[0064] S51. Electroencephalogram data processing:

[0065] S511. According to the formula S EEG = Butterworth(S raw , f low , f high ), filter the electroencephalogram data; where S EEG represents the filtered electroencephalogram data, S raw represents the original electroencephalogram data, and the original electroencephalogram data S raw is filtered using the Butterworth filter Butterworth. The low-pass and high-pass of the Butterworth filter Butterworth are f low and f high respectively. In a possible embodiment, f low = 0.5HZ, f high = 50HZ.

[0066] S512. Extract the band energy of the filtered electroencephalogram data S EEG .

[0067] S513. Calculate the attention concentration C EEG , C EEG = C α × ω α + C β × ω β , where C α represents the energy proportion of the α wave, ω α represents the weight of the α wave, C β represents the energy proportion of the β wave, and ω β represents the weight of the β wave. In a possible embodiment, ω α = 0.7, ω β = 0.3.

[0068] It should be noted that the frequency bands include the δ wave with a band frequency of 0.5 - 4Hz, the θ wave with a band frequency of 4 - 8Hz, the α wave with a band frequency of 8 - 13Hz, the β wave with a band frequency of 13 - 30Hz, and the γ wave with a band frequency of 30 - 50Hz. First, calculate the power spectral density of each frequency band, and then calculate the energy proportion.

[0069] The frequency range of alpha waves is usually between 8 and 13 Hz, and it is more obvious when a person is in a relaxed, awake, and eyes-closed state. When people are physically and mentally relaxed, the brain generates more alpha waves. When the attention is highly concentrated on a specific task, the energy of alpha waves will decrease. The frequency range of beta waves is generally between 13 and 30 Hz. When people are in a state of tension, thinking, problem-solving, or highly focused on a task, the brain generates more beta waves. A higher proportion of beta wave energy usually indicates that the brain is in a state of highly concentrated attention and can actively perceive, analyze, and process external stimuli.

[0070] By comprehensively considering the energy proportions of both and calculating the attention concentration C based on the weighted energy proportions of both EEG , it is possible to more comprehensively understand the balance state of the brain between relaxation and excitement, and thus more accurately judge the degree of attention concentration.

[0071] The specific method of "obtaining muscle tension based on electromyogram data" in step S5 includes:

[0072] S52. Electromyogram data processing:

[0073] S521. Process the original electromyogram signal S EMG = abs(S raw ) * LPF(f cutoff ) to obtain the envelope signal S raw ; EMG

[0074] Using the abs() function to perform full-wave rectification on the original electromyogram signal S raw means flipping the negative half-cycle part of the signal to the positive half-cycle, so that the signal is entirely on the non-negative half-axis on the time axis. This can convert all fluctuations of the electromyogram signal into positive values, facilitating subsequent analysis of signal features such as amplitude and preparing for extracting the envelope line.

[0075] Using a 5 Hz low-pass filter LPF to process the full-wave rectified signal abs(S raw ) to extract the envelope. f cutoff represents the cut-off frequency. f cutoff = 5 Hz.

[0076] S522. Calculate the root mean square value and the integrated electromyogram value respectively: where RMS represents the root mean square value of the electromyogram data, N represents the number of sampling points of the electromyogram data, S EMGi represents the electromyogram data of the i-th sampling point, iEMG represents the integrated electromyogram value of the electromyogram data, t 1 and t 2 represent the integration interval, S EMG(t) represents the expression of the change of electromyography data over time.

[0077] The root mean square value RMS of electromyography data is the square root of the average of the squares of the electromyography signal over a period of time. It mainly reflects the average power or intensity of the electromyography signal, and its magnitude is related to the number of recruited motor units and the discharge frequency during muscle contraction. The RMS value will increase correspondingly with the increase of the training intensity, so that the change of muscle contraction intensity can be intuitively understood.

[0078] The integrated electromyography value iEMG of electromyography data is the integral of the electromyography signal over a period of time. It reflects the total activity of the muscle during this period and is of great significance for evaluating muscle fatigue degree and endurance. For example, as the exercise time extends, the IEMG value will gradually increase, indicating the accumulation of muscle fatigue.

[0079] S523. Calculate the muscle tension T EMG , T EMG = ω RMS × RMS + ω iEMG × iEMG, where ω RMS represents the weight of the root mean square value, and ω iEMG represents the weight of the integrated electromyography value. In a possible embodiment, v RMS = 0.6, ω iEMG = 0.4.

[0080] By performing weighted calculation on the root mean square value RMS of electromyography data and the integrated electromyography value iEMG of electromyography data, not only can the advantages of these two indicators be comprehensively utilized to comprehensively and accurately evaluate muscle tension, but also the weights of the root mean square value RMS of electromyography data and the integrated electromyography value iEMG of electromyography data can be adjusted according to the individual muscle strength difference to achieve personalized muscle state monitoring, and the use effect is good.

[0081] The specific method of "obtaining the cognitive load degree according to the eye movement data" in step S5 includes:

[0082] S53. Eye movement data processing:

[0083] S531. Preprocessing of eye movement data;

[0084] S532. Calculate the fixation point entropy and saccade speed: The fixation point entropy H eye = -∑p j logp j , the saccade speed where p j represents the proportion of the fixation time in the jth area, represents the change of the saccade angle;

[0085] The fixation point entropy Heye measures the dispersion degree of the fixation point distribution. Fixation point entropy H eye can reflect the attention distribution of an individual during the information search and processing process, and embody the attention range and dispersion degree of the brain to different information. When the cognitive load is low, the attention of an individual is often more concentrated, and more fixation points may be concentrated in the key information area, and the fixation point entropy is lower at this time; otherwise, it is the opposite.

[0086] Saccade speed v saccade refers to the speed at which the eyes move quickly between different fixation points. Saccade speed v saccade can reflect the rhythm and efficiency of an individual during the information acquisition process, and embody the processing speed and demand of the brain for information. When the cognitive load is low, the individual processes information more easily, and the saccade speed may be relatively stable and moderate; while when the cognitive load is high, the individual may need to quickly switch between different information, the saccade speed will increase, or the saccade speed is unstable due to the complexity of the information.

[0087] S533. Calculate the cognitive load degree D eye , D eye = ω H ×H eye + ω V ×v saccade , where ω H represents the weight of the fixation point entropy, and ω V represents the weight of the saccade speed.

[0088] By performing weighted calculation on the fixation point entropy H eye and the saccade speed v saccade to calculate the cognitive load degree D eye , the cognitive load degree D eye is used to reflect the attention distribution and information processing efficiency of the user in the cognitive task, can comprehensively consider the two aspects of attention distribution and information acquisition rhythm in the cognitive process, and more comprehensively and accurately reflect the cognitive load degree D of the individual eye .

[0089] S6: Evaluate the comfort index of the user in the current environment according to the attention concentration, muscle tension and cognitive load degree;

[0090] The specific method of "evaluating the comfort index of the user in the current environment according to the attention concentration, muscle tension and cognitive load degree" in step S6 includes:

[0091] According to the formula CI actual = ω 1 ·N(C EEG ) + ω 2 ·N(T EMG ) + ω 3·N(D eye ) Calculate the comfort index CI actual , where ω 1 represents the weight of the attention concentration, ω 2 represents the weight of the muscle tension, ω 3 represents the weight of the cognitive load, and N(·) represents the normalization function. In a possible embodiment, ω 1 = 0.5, ω 2 = 0.3, ω 3 = 0.2.

[0092] Obtain the attention concentration based on the electroencephalogram data, obtain the muscle tension based on the electromyogram data, and obtain the cognitive load based on the eye movement data; evaluate the comfort index of the user in the current environment according to the attention concentration, muscle tension, and cognitive load; evaluating through these three dimensions comprehensively and accurately reflects the overall feeling and state of the user in the environment and avoids the deviation of subjective judgment.

[0093] S7: If the comfort index is less than the comfort index threshold, interact with the user to obtain the user feedback, and the user feedback is the comfort feeling or the desired environmental parameters; in a possible embodiment, the comfort index threshold CI target = 0.7. While using the physiological signal perception technology to sense the comfort index of the user for the environment, adding user feedback to meet the personalized needs of the user has a good use effect.

[0094] S8: Adjust the environmental parameters according to the user feedback and the comfort index.

[0095] The specific method of "adjusting the environmental parameters according to the user feedback and the comfort index" in step S8 includes: when the user feedback is a comfort feeling,

[0096] a. Update the weights by the gradient descent method: where Loss = (CI target - CI actual ) 2 , CI target represents the comfort index threshold, represents the h-th weight at the t-th iteration, η represents the learning rate, which controls the step size of each weight update; thus updating the weights ω actual participating in the calculation formula of the comfort index CI 1 , the weight ω 2 and the weight ω 3 .

[0097] b. Convert the change of the comfort index into the environmental parameter adjustment amount for adjusting the environmental parameters.

[0098] It should be noted that after the weight update, the change of the comfort index is converted into the environmental parameter adjustment amount through the linear mapping formula.

[0099] Specifically, according to the formula calculate the environmental parameter adjustment amount, where ΔT represents the temperature adjustment amount, and k T represents the temperature adjustment coefficient, ΔHU represents the humidity adjustment amount, and k HU represents the humidity adjustment coefficient, ΔI represents the light adjustment amount, and k I represents the light adjustment coefficient.

[0100] In a possible embodiment, k T = 0.5, k HU = 2, k I = 50.

[0101] In a possible embodiment, the user feedback is the desired environmental parameters. The desired environmental parameters include fuzzy instructions such as a higher temperature and a darker light. For fuzzy instructions, they are adjusted up or down according to a preset percentage or step size.

[0102] In a possible embodiment, the user feedback is the desired environmental parameters. The desired environmental parameters include clear instructions such as setting the temperature to 25°C. For clear instructions, they are directly executed.

[0103] After adjusting the environmental parameters through step S8, return to step S2 to re-collect the user's physiological data, and iteratively calculate the comfort index of the user in the current environment until the comfort index reaches the comfort index threshold or the user feedback is comfortable. Closed-loop control is used to achieve precise adjustment of environmental parameters.

[0104] This embodiment also includes:

[0105] Integrate the user feedback to form a user preference data set;

[0106] The user preference data set is associated with the environmental parameter data set and the user physiological data set;

[0107] Set a user preference data set calling mechanism triggered by conditions for adjusting environmental parameters.

[0108] The triggering conditions are: all the monitored user physiological data fall into the same user physiological data interval, or a certain user physiological data falls into a specific interval, or the label obtained from the monitored user physiological data is the same as the label of a certain user physiological data set. For example, the labels are tense and learning.

[0109] In a possible embodiment, the upper and lower limits of the user's physiological data set are widened to obtain the user's physiological data range. The user's physiological data obtained by real-time monitoring is matched with the user's physiological data range. If all the monitored user's physiological data fall into the same user's physiological data range, or a certain user's physiological data falls into a specific range, it is considered that the condition is matched, and the condition for triggering the call of the user's preference data set is satisfied. At this time, the user's preference data set corresponding to the user's physiological data set is called to adjust the environmental parameters. The environmental preferences of users in different physiological states can be grasped more accurately, so as to provide an environment that highly meets their personalized needs for users.

[0110] The above are only embodiments of the present invention and do not impose any limitations on the present invention. Any simple modifications, changes, and equivalent structural changes made to the above embodiments according to the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for adjusting a human living environment based on comfort perception, characterized in that: The following steps are involved: S1: Collect environmental parameters through the first data acquisition module and output real-time environmental parameters; S2: Collecting user physiological data through a second data collection module; the user physiological data at least includes brain wave data, electromyography data and eye movement data; S3: Determine whether the EEG data shows high stress, if so, proceed to step S4, otherwise proceed to step S5; S4: Adjust the light and temperature to soothing mode; S5: Processing the collected user physiological data, obtaining the concentration degree according to the brain wave data, obtaining the muscle tension degree according to the electromyography data, and obtaining the cognitive load degree according to the eye movement data; S6: Evaluate the user's comfort index in the current environment based on concentration, muscle tension and cognitive load; S7: If the comfort index is less than the comfort index threshold, interact with the user to obtain user feedback, where the user feedback includes comfort feeling or expected environmental parameters; S8: Adjust environmental parameters based on user feedback and comfort index.

2. A method for adjusting a living environment based on comfort perception according to claim 1, characterized in that: After adjusting the environmental parameters in step S8, return to step S2 to re-collect the user's physiological data and iteratively calculate the user's comfort index in the current environment until the comfort index reaches the comfort index threshold or the user feedback is comfortable.

3. A method for adjusting a living environment based on comfort perception according to claim 1 or 2, characterized in that: Also includes: Integrate user feedback to form a user preference dataset; The user preference dataset is associated with the environmental parameter dataset and the user physiological dataset; Set up a conditionally triggered user preference dataset calling mechanism to adjust environmental parameters.

4. A method for adjusting a living environment based on comfort perception according to claim 1, characterized in that: The specific method of "obtaining the degree of concentration according to brain wave data" in step S5 includes: S51. Brain wave data processing: S511, according to formula S EEG =Butterworth(S raw , f low , f high ) to filter the EEG data; where S EEG represents the filtered EEG data, S raw represents the original EEG data, f low Indicates the lower cutoff frequency of the bandpass filter, f high Indicates the upper cutoff frequency of the bandpass filter; S512, extracting the filtered brain wave data S EEG The frequency band energy; S513. Calculate the concentration of attention C EEG , C EEG =C α ×ω α +C β ×ω β , where C α represents the energy proportion of α waves, ω α represents the weight of α wave, C β represents the energy proportion of β waves, ω β Represents the weight of the beta wave.

5. A method for adjusting a living environment based on comfort perception according to claim 1, characterized in that: The specific method of "obtaining muscle tension according to electromyographic data" in step S5 includes: S52, electromyography data processing: S521, according to formula S EMG = abs(S raw )*LPF(f cutoff ) Process the original electromyographic signal S raw , get the envelope signal S EMG ; S522, respectively calculate the root mean square value and the integrated electromyographic value: Where RMS represents the root mean square value of the electromyographic data, N represents the number of sampling points of the electromyographic data, and S EMGi represents the EMG data of the i-th sampling point, iEMG represents the integrated EMG value of the EMG data, t1 and t2 represent the integration interval, S EMG (t) represents the expression of the change of electromyographic data over time; S523. Calculate muscle tension T EMG , T EMG =ω RMS ×RMS+ω iEMG ×iEMG, where ω RMS represents the weight of the RMS value, ω iEMG Represents the weight of the integrated EMG value.

6. A method for adjusting a living environment based on comfort perception according to claim 1, characterized in that: The specific method of "obtaining cognitive load according to eye movement data" in step S5 includes: S53. Eye movement data processing: S531, eye movement data preprocessing; S532, calculate the gaze point entropy and the scanning speed: the gaze point entropy H eye =-∑p j log p j , scanning speed where p j represents the proportion of fixation time in the jth region, Indicates changes in scanning angle; S533, Calculate cognitive load D eye , D eye =ω H ×H eye +ω V ×v saccade , where ω H represents the weight of gaze point entropy, ω V The weight representing the scanning speed.

7. A method for adjusting a human living environment based on comfort perception according to claim 1, characterized in that: The specific method of "evaluating the user's comfort index in the current environment according to attention concentration, muscle tension and cognitive load" in step S6 includes: According to the formula CI actual =ω1·N(C EEG )+ω2·N(T EMG )+ω3·N(D eye ) Calculate the comfort index CI actual , where ω1 represents the weight of attention concentration, ω2 represents the weight of muscle tension, ω3 represents the weight of cognitive load, and N(·) represents the normalization function.

8. A method for adjusting a human living environment based on comfort perception according to claim 1, characterized in that: The specific method of "adjusting environmental parameters according to user feedback and comfort index" in step S8 includes: when the user feedback is a comfortable feeling, a. Update weights by gradient descent: Where Loss = (CI target -CI actual ) 2 , CI target represents the comfort index threshold, represents the hth weight at the tth iteration, η represents the learning rate, which controls the step size of each weight update; b. Convert the change of comfort index into environmental parameter adjustment amount for adjusting environmental parameters.

9. A method for adjusting a human living environment based on comfort perception according to claim 8, characterized in that: The specific method of converting the change of comfort index into the adjustment amount of environmental parameters is: According to the formula Calculate the environmental parameter adjustment amount, where ΔT represents the temperature adjustment amount, k T represents the temperature adjustment coefficient, ΔHU represents the humidity adjustment amount, k HU represents the humidity adjustment coefficient, ΔI represents the light adjustment amount, k I Represents the light adjustment coefficient.

10. A method for adjusting a human living environment based on comfort perception according to claim 7, characterized in that: In step S4, while adjusting the light and temperature to the soothing mode, the weight ω1 of the concentration is increased.

Images