Air conditioning apparatus and control method thereof

Abstract

This application belongs to the field of air conditioning technology and provides an air conditioning device and its control method. The control method acquires the user's respiratory and vital sign information; determines the user's current sleep stage based on the respiratory and vital sign information; predicts the user's wakefulness time within the current sleep stage based on a pre-established sleep pattern model and the user's fall-off time in the current sleep stage. The sleep pattern model is obtained by statistically modeling regular and irregular sleep cycles, derived from the user's fall-off time, wakefulness time, and the duration ratio of different sleep stages in multiple historical sleep cycles. Before the wakefulness time arrives, the air conditioning device adjusts its operating parameters based on the wakefulness time. This addresses the problem of lagging sleep control in existing air conditioning technologies, making it difficult to adapt to users' personalized needs, and improves user comfort and experience.

Description

Technical Field

[0001] This application belongs to the field of air conditioning technology, and more specifically, relates to an air conditioning device and its control method. Background Technology

[0002] Currently, most air conditioners on the market with sleep assistance functions adjust their operating status based on a preset fixed sleep mode curve, or simply adjust parameters based on sleep status detected by sensors.

[0003] However, the adjustment of sleep parameters in air conditioners often lags behind, making it difficult to adapt to the dynamic changes in the user's sleep state in real time. This results in the user facing discomfort from environmental parameters after waking up, affecting the user experience. Summary of the Invention

[0004] The purpose of this application is to provide an air conditioning device and its control method, which aims to solve the technical problem that the sleep control of air conditioners in the prior art is lagging and difficult to adapt to the personalized needs of users.

[0005] To achieve the above objectives, according to the first aspect of this application, a method for controlling an air conditioning device is provided, the method comprising: Obtain the user's respiratory and vital signs information; The user's current sleep stage is obtained based on the breathing information and the feature information; Based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, the user's wake-up time in the current sleep stage is predicted. The sleep pattern model is obtained by statistical modeling regular sleep cycles and irregular sleep cycles obtained by dividing the user's fall asleep time, wake-up time and duration of different sleep stages in each of the historical sleep cycles. Before the moment of awakening arrives, the air conditioning equipment is controlled to adjust its operating parameters based on the moment of awakening.

[0006] The beneficial effects of the embodiments in this application compared with the prior art are: By collecting user respiratory and vital sign information, relevant features are extracted to accurately identify the user's current sleep stage. Furthermore, based on multiple historical sleep cycles, regular and irregular sleep cycles are divided and statistically modeled to establish a sleep pattern model. This model, combined with the fall-off time of the current sleep cycle, predicts the corresponding wake-up time, addressing the problems of existing air conditioners' inability to accurately predict and adapt to the dynamic changes in the user's sleep state and sleep rhythm fluctuations. Moreover, before the predicted wake-up time arrives, the air conditioner's operating parameters are adjusted in advance, solving the problem of lagging sleep control in existing air conditioners and their inability to adapt to the user's real-time state, thus improving user comfort and experience.

[0007] According to a second aspect of this application, an air conditioning device is provided, the air conditioning device comprising: a controller, The controller, connected to sensors integrated within the air conditioning unit and / or external devices, is configured to: Obtain the user's respiratory and vital signs information; The user's current sleep stage is obtained based on the respiratory information and the vital signs information; Based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, the user's wake-up time in the current sleep stage is predicted. The sleep pattern model is obtained by statistically modeling regular sleep cycles and irregular sleep cycles obtained by dividing the user's fall asleep time, wake-up time and duration of different sleep stages in multiple historical sleep cycles. Before the moment of awakening arrives, the air conditioning equipment is controlled to adjust its operating parameters based on the moment of awakening.

[0008] According to a third aspect of this application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device causes the electronic device to perform the method as described in any one of the claims.

[0009] According to a fourth aspect of this application, a computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, implements the method as described in any one of the claims.

[0010] According to a fifth aspect of this application, a computer program product is provided that, when run on an electronic device, causes the electronic device to perform the method described in any one of the first aspects above.

[0011] It is understandable that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic flowchart of a control method for an air conditioning device provided in an embodiment of this application; Figure 2 This is a schematic flowchart of an optional air conditioning equipment control method provided in an embodiment of this application; Figure 3 This is a schematic flowchart of an optional air conditioning equipment control method provided in an embodiment of this application; Figure 4 This is a schematic flowchart of an optional air conditioning equipment control method provided in an embodiment of this application; Figure 5 This is a schematic flowchart of an optional air conditioning equipment control method provided in an embodiment of this application; Figure 6 This is a schematic flowchart of an optional air conditioning equipment control method provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a control device for an air conditioning equipment provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0016] It should also be understood that, in the description of this application, unless otherwise stated, the " / " used in the specification and appended claims indicates that the related objects are in an "or" relationship. For example, A / B can mean A or B. The "and / or" in this application is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0017] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, but are only used for distinguishing descriptions, and the terms "first" and "second" do not necessarily imply that they are different, nor should they be construed as indicating or implying relative importance.

[0018] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0019] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0020] First, it should be noted that the information collection process (such as the respiratory information collection process, the vital signs information collection process, etc.) / feature extraction process involved in this application is carried out with the user's knowledge and permission. That is, the information collection process / feature extraction process complies with the requirements of laws and regulations and does not constitute an act that harms the public interest.

[0021] This application provides an example of a control method for an air conditioning device. Please refer to... Figure 1 As shown, Figure 1 A schematic flowchart of a control method for an air conditioning device provided in this application is shown. This is an example and not a limitation; the method can be applied to or operated in electronic devices. The method includes: S101, obtain the user's respiratory and vital signs information.

[0022] S102, based on respiratory and vital signs information, obtains the user's current sleep stage.

[0023] S103, based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, predicts the user's wakefulness time in the current sleep stage.

[0024] S104, before the awakening moment arrives, control the air conditioning equipment to adjust operating parameters based on the awakening moment.

[0025] Among them, the sleep pattern model is obtained by statistically modeling regular sleep cycles and irregular sleep cycles based on the user's fall-off time, wake-up time and duration of different sleep stages in multiple historical sleep cycles.

[0026] This embodiment discloses a control method for an air conditioning device, which can be applied, but is not limited to, to scenarios where a user falls asleep and wakes up in an indoor area after turning on the air conditioning device. After the air conditioning device is turned on, when the user is preparing to fall asleep, for example, when the user turns on the air conditioning sleep mode, the radar sensor / millimeter-wave radar / millimeter-wave radar sensor integrated into the air conditioning device, or the user's external smart bracelet, sleep monitor, or other data collection device, will continuously collect the user's respiratory and vital sign information at preset time intervals. Among them, the respiratory information includes, but is not limited to, respiratory rate, respiratory rate variation coefficient, and respiratory stability, and the vital sign information includes, but is not limited to, the amplitude of body posture changes, the frequency of body posture changes, the interval of body posture changes, and the duration of body posture changes, adapting to the initial scenario of the user lying quietly before falling asleep, turning over, etc.

[0027] In some embodiments, after the user enters a sleep state, the acquisition device continuously acquires the user's respiratory and vital sign information. By fusing and analyzing the respiratory and vital sign information over multiple consecutive preset time intervals, the device extracts the user's respiratory and body movement change features. Combining the user's sleep stage at the previous moment with a preset stage transition threshold, a multi-feature fusion recognition algorithm is used to identify the user's current sleep stage.

[0028] For example, a user's current sleep stage can include the wakefulness stage (it should be understood that since a user may re-enter light sleep or deep sleep after a brief period of wakefulness, the wakefulness stage during sleep is also considered a sleep stage), the light sleep stage, and the deep sleep stage. Each stage corresponds to a unique threshold range for respiratory change characteristics and a threshold range for body movement characteristics. For example, when a user turns over less frequently at night and breathes steadily and at a lower frequency, it can be identified as entering the deep sleep stage. When a user turns over frequently and has large breathing fluctuations, it can be identified as entering the light sleep stage. This effectively ensures the accuracy of sleep stage identification and adapts to the fluctuations in a user's sleep state during the night.

[0029] It should be understood that the above sleep pattern model is based on the sleep stage data of multiple historical sleep cycles of the user. Specifically, it filters the time of falling asleep and waking up corresponding to each of the multiple historical sleep cycles, as well as the duration of different sleep stages in each historical sleep cycle. After removing abnormal data caused by external interference (such as temporary wake-up caused by sudden noise at night) and temporary user activities (such as getting up to drink water at night), it is divided into regular sleep cycles and irregular sleep cycles. Then, the normal distribution statistical method is used to model the two types of sleep cycles respectively. The model is formed by combining the weights corresponding to the two types of sleep cycles. The weight of regular sleep cycles is higher than that of irregular sleep cycles, which can accurately adapt to the actual scenario of users' regular work and rest on weekdays and irregular work and rest on weekends.

[0030] Furthermore, based on a pre-established sleep pattern model and the user's fall-off time in the current sleep cycle, the system predicts the user's wake-up time within the current sleep cycle, adapting to scenarios where the user's long-term sleep-wake cycle fluctuates. Specifically, when predicting wake-up time, the system combines the fall-off time of the current sleep cycle with relevant statistical data from regular or irregular sleep cycles in the sleep pattern model. For example, if the user falls asleep at 11 PM on a weekday (regular sleep cycle), the system predicts wake-up time based on the average sleep duration of regular sleep cycles; if the user falls asleep at midnight on a weekend (irregular sleep cycle), the system predicts wake-up time based on the average sleep duration of irregular sleep cycles. This allows for accurate prediction of the user's wake-up time, solving the problem that existing technologies cannot predict users' wake-up time in advance.

[0031] Finally, before the predicted wake-up time arrives, the air conditioning system adjusts its operating parameters based on that time to adapt to the user's environmental needs before waking up. For example, if the predicted wake-up time is 7:00 AM, the air conditioning controller can adjust the operating parameters around 6:40 AM: if it is summer, the temperature can be gradually adjusted from 26°C (during the user's sleep state) to 24°C, and the airflow can be adjusted from low to medium to prevent the user from feeling stuffy and uncomfortable after waking up due to excessively high indoor temperature and insufficient airflow; if it is winter, the temperature can be gradually adjusted from 20°C (during the user's sleep state) to 22°C to reduce the risk of catching a cold due to the large temperature difference after waking up. This ensures that the air conditioning system accurately adapts to the user's physiological needs upon waking, preventing discomfort caused by unsuitable environmental parameters, thereby improving the user's sleep quality and mental state after waking up, and achieving intelligent and personalized air conditioning sleep control.

[0032] By collecting user respiratory and vital sign information, the system accurately determines the user's current sleep stage. Based on a sleep pattern model formed by dual-classification of regular and irregular sleep cycles, and the user's fall-off time during the current sleep stage, it predicts the user's wake-up time within that stage. This allows for adaptation to different scenarios, such as regular weekday schedules and irregular weekend schedules. Compared to existing single static models that cannot adapt to fluctuations in user schedules, this system better matches the user's actual sleep characteristics, improving the accuracy of wake-up time prediction. Furthermore, by adjusting the air conditioning equipment's operating parameters before the wake-up time arrives, the system accurately matches the user's physiological needs during wakefulness, effectively improving sleep comfort and post-wake mental state. This achieves intelligent and personalized air conditioning sleep control, solving the technical problems of existing technologies such as the inability to predict user wake-up time in advance, insufficient control precision, and poor user experience.

[0033] Furthermore, it should be noted that this control method can be implemented using the air conditioner's integrated sensors or external wearable devices, without the need for additional dedicated hardware. This effectively controls implementation costs and is highly feasible, making it suitable for various sleep scenarios for ordinary families, hotels, and other users.

[0034] One possible implementation is, such as Figure 2 As shown, S102, based on respiratory and vital sign information, obtains the user's current sleep stage, including: S201, performs fusion analysis on respiratory information and vital sign information within multiple consecutive preset time intervals, and extracts the user's respiratory change characteristics and body movement change characteristics.

[0035] S202, based on respiratory and body movement characteristics, combined with the user's previous sleep stage and a preset stage transition threshold, uses a multi-feature fusion recognition algorithm to identify the user's current sleep stage.

[0036] The stage transition threshold is adaptively adjusted based on the duration ratio of different sleep stages within each of the user's historical sleep cycles.

[0037] In this embodiment of the disclosure, firstly, respiratory information and vital sign information within multiple consecutive preset time intervals are fused and analyzed to extract the user's respiratory change characteristics and body movement change characteristics. For example, the user's respiratory information and vital sign information can be collected using a millimeter-wave radar sensor integrated into the air conditioning unit, or a millimeter-wave radar sensor located in the same indoor area as the air conditioning unit.

[0038] Optionally, a preset time interval is set to T (e.g., 30 seconds, 1 minute). The millimeter-wave radar collects the user's respiratory and body movement data every time interval T, specifically including average respiratory rate, maximum respiratory rate, minimum respiratory rate, average body movement value, maximum displacement value, and body movement frequency. During the fusion analysis of respiratory and vital sign information over multiple consecutive preset time intervals, every time interval T, the above data collected over n consecutive preset time intervals (e.g., 10 minutes) are summarized and processed to analyze the fluctuation pattern of respiratory rate and the frequency and amplitude changes of body movement, thereby extracting respiratory and body movement change characteristics that can characterize the user's sleep state.

[0039] Subsequently, based on the extracted respiratory and body movement characteristics, combined with the user's previous sleep stage and a preset stage transition threshold, a multi-feature fusion recognition algorithm is used to identify the user's current sleep stage. For example, the multi-feature fusion recognition algorithm can be a weighted summation fusion algorithm, a support vector machine (SVM) fusion algorithm, or a neural network fusion algorithm (such as CNN or LSTM).

[0040] The sleep stages mainly include the waking stage, the light sleep stage, and the deep sleep stage. Each stage corresponds to a specific threshold range of respiratory and body movement characteristics. Specifically, the waking stage corresponds to a higher respiratory rate, a larger respiratory variability (i.e., respiratory coefficient of variation), and more body movement; the light sleep stage corresponds to a moderate respiratory rate, respiratory variability, and a small amount of body movement; and the deep sleep stage corresponds to a lower respiratory rate, a smaller respiratory variability, and very little body movement. The respiratory rate of adults is 12-20 breaths per minute during the waking stage, 10-14 breaths per minute during the light sleep stage, and 8-10 breaths per minute during the deep sleep stage.

[0041] It should be noted that respiratory variability (i.e., the coefficient of respiratory variation) can be calculated using the following formula: ; ; in, It is the rate of a single breath. It is the average respiratory rate. It is used to measure the dispersion of a single respiratory rate from the average respiratory rate over a period of time. The higher the value, the greater the respiratory variability. This means that the standard deviation is divided by the average respiratory rate, which eliminates the influence of the average respiratory rate itself, making it easier to compare between different individuals or different states.

[0042] This means that by measuring the dispersion of a single respiratory rate from the average respiratory rate, and combining the ratio of the standard deviation to the average respiratory rate, the influence of the average respiratory rate itself is eliminated, making it easier to compare between different individuals and different states. For example, the respiratory variability during wakefulness is 7-15%, during light sleep it is 5-10%, and during deep sleep it is less than 5%. Body movement characteristics are based on the measured output values ​​of millimeter-wave radar, using a quantization range of 1-100 to characterize the amplitude of body movement changes, combined with the frequency of body movements (for example, a body movement frequency of more than 10 times corresponds to a quantization value greater than 50), and then comprehensively judging the user's body movement characteristics.

[0043] It should be understood that the stage transition threshold is adaptively adjusted based on the duration ratio of different sleep stages in each of the user's historical sleep cycles. Specifically, it can be combined with sleep data from multiple historical sleep cycles of the user, including the breathing characteristics, body movement characteristics and state transitions of each sleep stage. The stage transition threshold is continuously optimized and adjusted through statistical analysis to adapt to individual sleep differences of users, take into account the differences in breathing frequency between the elderly, children and adults, and avoid recognition bias caused by a fixed threshold.

[0044] In some embodiments, during the execution of the multi-feature fusion recognition algorithm, the user's sleep stage at the previous moment is used to predict the state first, following a preset state transition logic. That is, the awake stage will not directly enter the deep sleep stage, the deep sleep stage and the light sleep stage can be interchanged, and the awake stage and the light sleep stage can be interchanged. Combining the user's real-time extracted breathing change features, body movement change features, and adaptively adjusted stage transition thresholds, the probability of the user being in each sleep stage is comprehensively calculated. Finally, the sleep stage of the user at the current moment is determined based on the maximum probability, ensuring the accuracy and stability of the recognition results.

[0045] Furthermore, if the air conditioning unit is linked with external devices such as the user's smartwatch, it can also obtain the user's heart rate information with the user's permission. By combining the heart rate information with respiratory and vital sign information, the extraction accuracy of respiratory and body movement characteristics can be further optimized, improving the accuracy of sleep stage recognition and adapting to more user scenarios. It can also continuously collect the user's sleep data and update the user's historical sleep cycle information to achieve dynamic adaptive adjustment of the stage transition threshold, further aligning with the user's personalized sleep patterns.

[0046] One possible implementation is, such as Figure 3 As shown in S202, based on respiratory and body movement characteristics, combined with the user's sleep stage at the previous moment and a preset stage transition threshold, a multi-feature fusion recognition algorithm is used to identify the user's current sleep stage at the current moment, including: S301, normalize the respiratory and body movement characteristics to obtain normalized respiratory and body movement characteristics.

[0047] The normalization process is used to map respiratory and body movement characteristics to a preset threshold range.

[0048] S302, the weighted normalized features are obtained by weighting the normalized respiratory change features and the normalized body movement change features according to their respective weight values.

[0049] Among them, the first weight value corresponding to the respiratory change feature is higher than the second weight value corresponding to the body movement change feature.

[0050] S303 takes the normalized features, substitutes them into the multi-feature fusion recognition algorithm, and calculates the recognition probability of the user being in each sleep stage at the current moment by combining the user's sleep stage at the previous moment and the preset stage transition threshold.

[0051] S304. Based on the ranking of the recognition probabilities of the user being in each sleep stage at the current moment, select the sleep stage corresponding to the highest recognition probability as the current sleep stage of the user at the current moment.

[0052] In some embodiments, the extracted respiratory change features and body movement change features are first normalized to obtain normalized respiratory change features and normalized body movement change features. That is, the respiratory change features and body movement change features are uniformly mapped to a preset threshold range to eliminate the dimensional differences between different feature dimensions and avoid interference with subsequent weighted calculations and recognition probability analysis due to the value of a single feature being too large or too small, thus ensuring that the two types of feature parameters are in the same comparison dimension.

[0053] Among them, respiratory change characteristics include parameters such as respiratory rate and respiratory variability, while body movement change characteristics include parameters such as body movement frequency, body movement amplitude, and body movement interval. Both of these can be obtained by collecting data from the millimeter-wave radar integrated into the air conditioning equipment.

[0054] After obtaining the normalized respiratory and body movement variation features, a weighted average is calculated based on the respective weight values ​​of the two types of features to obtain the weighted normalized features. The first weight value for respiratory variation features is higher than the second weight value for body movement variation features. This is because respiratory variation features (especially respiratory variability) differ more significantly across different sleep stages and contribute more to sleep stage identification, while body movement variation features are relatively more affected by external interference and contribute slightly less. This weight allocation highlights the role of respiratory variation features and improves the accuracy of the identification results.

[0055] Subsequently, the weighted normalized features are substituted into the multi-feature fusion recognition algorithm. At the same time, the recognition probability of the user being in each sleep stage at the current moment is calculated by combining the user's sleep stage at the previous moment and the preset stage transition threshold.

[0056] The multi-feature fusion recognition algorithm is trained on a large number of user sleep samples and can accurately adapt to the feature differences of the waking, light sleep, and deep sleep stages. The stage transition threshold is adaptively adjusted according to different stages of the user's historical sleep cycle, taking into account the differences in breathing and body movement characteristics of adults, the elderly, and children, and avoiding recognition bias caused by fixed thresholds. The multi-feature fusion recognition model is based on weighted normalized features, combined with the user's sleep stage at the previous moment and the preset stage transition threshold, and follows the preset state transition logic: the waking stage does not directly enter the deep sleep stage, the deep sleep stage and the light sleep stage can be mutually transitioned, and the waking stage and the light sleep stage can be mutually transitioned, so as to obtain the recognition probability of the user being in each sleep stage at the current moment, further optimizing the calculation accuracy of the recognition probability and reducing misjudgments.

[0057] Finally, based on the ranking of the recognition probabilities of the user being in each sleep stage at the current moment, the sleep stage corresponding to the highest recognition probability is selected as the user's current sleep stage. In the special case where multiple sleep stages have the same recognition probability, the current sleep stage can be further determined by combining the user's sleep stage at the previous moment, the stage transition threshold, and the real-time extracted respiratory and body movement characteristics, ensuring the stability and accuracy of the recognition results.

[0058] In one possible implementation, the current sleep stage includes at least one of a wakefulness stage, a light sleep stage, and a deep sleep stage, and each sleep stage corresponds to a unique threshold range for respiratory change characteristics and a threshold range for body movement changes. The deep sleep stage corresponds to the lowest respiratory rate, the smallest respiratory rate variation coefficient, the highest respiratory stability, the lowest frequency of body posture changes, the smallest amplitude of body posture changes, the longest interval between body posture changes, and the shortest duration of body posture changes. In combination with actual detection scenarios, during the deep sleep stage, the user's breathing is slow and stable, with almost no obvious body movement. For example, the respiratory variability is less than 5%, the respiratory rate of adults during deep sleep is 8-10 breaths per minute, the body movement quantification value (range 1-100) is less than 20, and the frequency of body movement is extremely low, which is consistent with the physiological characteristics of users during the deep sleep stage.

[0059] The light sleep stage is characterized by respiratory rate, respiratory rate variation coefficient, respiratory stability, frequency of body posture changes, amplitude of body posture changes, interval of body posture changes, and duration of body posture changes, all of which fall between the deep sleep and wakefulness stages. In practical testing scenarios, during the light sleep stage, the user's breathing is relatively stable but slightly higher than that during the deep sleep stage, accompanied by a small amount of body movement. The respiratory variability can be set at 5-10%. For adults, the respiratory rate during the light sleep stage is 10-14 breaths per minute, and the body movement quantification value is between 20-50. The moderate frequency of body movement can effectively distinguish it from the deep sleep and wakefulness stages.

[0060] The conscious phase is characterized by the highest respiratory rate, the largest coefficient of variation in respiratory rate, the lowest respiratory stability, the highest frequency of body posture changes, the largest amplitude of body posture changes, the shortest interval between body posture changes, and the longest duration of body posture changes. In practical testing scenarios, during the conscious phase, users exhibit significant fluctuations in respiratory rate, frequent and large-amplitude body movements, and a respiratory variability of 7-15%. For adults in the conscious phase, the respiratory rate is typically 12-20 breaths per minute, the body movement quantification value is above 50, and the frequency of body movements exceeds 10 times per minute. These characteristics can accurately determine whether a user is in a conscious state.

[0061] The characteristic threshold ranges for each sleep stage mentioned above are determined based on long-term measured data from millimeter-wave radar. They take into account the differences in respiratory and body movement characteristics among different groups (adults, the elderly, and children). By coordinating the determination of respiratory and body movement changes, the bias of single feature determination can be effectively avoided. This provides a clear and accurate threshold basis for the operation of subsequent multi-feature fusion recognition algorithms, ensuring the accuracy and stability of sleep stage recognition and adapting to the personalized sleep characteristics of different users.

[0062] In one possible implementation, respiratory information is used to characterize at least one of the user's respiratory rate, respiratory rate coefficient of variation, and respiratory stability; vital sign information is used to characterize at least one of the user's body posture change amplitude, body posture change frequency, body posture change interval, and body posture change duration. Figure 4 As shown, S101, acquire the user's respiratory and vital signs information, including: S401 collects the user's respiratory and vital signs information at preset time intervals using sensors integrated within the air conditioning unit and / or external devices.

[0063] S402, based on the synchronously acquired current environmental parameters, adaptively corrects the acquired respiratory and vital sign information respectively to obtain the final respiratory and vital sign information.

[0064] The current environmental parameters include at least one of the following: ambient temperature, ambient humidity, and ambient noise intensity.

[0065] In this embodiment, firstly, the specific representation scope of respiratory information and vital sign information is defined: respiratory information is used to represent at least one of the user's respiratory rate, respiratory rate coefficient of variation, and respiratory stability, wherein respiratory rate is the number of times the user breathes per unit time, respiratory rate coefficient of variation is used to measure the dispersion of respiratory rate around the average value over a period of time, and respiratory stability is used to represent the uniformity of the user's breathing; vital sign information is used to represent at least one of the user's body posture change amplitude, body posture change frequency, body posture change interval, and body posture change duration, wherein body posture change amplitude is the magnitude of the user's body displacement, body posture change frequency is the number of times body posture changes per unit time, body posture change interval is the time difference between two body posture changes, and body posture change duration is the duration of a single body posture change.

[0066] Subsequently, the system collects the user's respiratory and vital signs information at preset time intervals using sensors integrated within the air conditioning unit and / or external devices. The sensors integrated into the air conditioning unit primarily utilize millimeter-wave radar, which can accurately detect the user's breathing and body movement information, adapting to various scenarios during sleep. It can also be paired with other human body sensors such as array thermopile and RGB cameras to achieve multi-sensor collaborative data collection, improving the comprehensiveness of information acquisition. External devices can include smart bracelets, sleep monitors, etc., which can be linked with the air conditioning unit to supplement the collection of the user's heart rate information, adapting to different user habits. The preset time interval can be set according to the actual usage scenario, such as setting it to 1 minute, to ensure real-time capture of changes in the user's breathing and body posture, avoiding increased device energy consumption and data redundancy due to excessively high collection frequency.

[0067] After collecting initial respiratory and vital sign information, adaptive corrections are performed on the initial respiratory and vital sign information based on the current environmental parameters of the air conditioning unit and the user's indoor area, obtained as a result. The final respiratory and vital sign information is then obtained. The current environmental parameters include at least one of ambient temperature, ambient humidity, and ambient noise level. These environmental parameters can be synchronously collected by the environmental sensors integrated into the air conditioning unit, ensuring that the collection timing is consistent with the collection timing of respiratory and vital sign information, thus improving correction accuracy.

[0068] In some embodiments, adjustments can be made during the specific calibration process based on the influence of different environmental parameters on the collected data. For example, excessively high or low ambient temperatures can affect the user's respiratory rate, abnormal ambient humidity can lead to deviations in respiratory stability detection, and excessive ambient noise can interfere with the acquisition of body movement information by millimeter-wave radar. Through a preset calibration algorithm, the original collected data is compensated and adjusted according to the specific values ​​of the current environmental parameters to eliminate errors caused by environmental interference and ensure that the final respiratory and vital sign information can truly reflect the user's physiological and body movement status.

[0069] In addition, cross-validation can be performed on data from the same source during the collection process. If the same type of data is also collected simultaneously through the air conditioner integrated sensor and external devices, the deviation of the data collected by the two can be compared, and abnormal deviation data can be eliminated to further improve the reliability of data collection. Furthermore, during continuous collection, the adaptive correction algorithm can be continuously optimized based on the user's historical sleep data and the changing patterns of environmental parameters to ensure that accurate respiratory and vital sign information can be collected in different environmental scenarios.

[0070] One possible implementation is, such as Figure 5 As shown, S103, based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep cycle, predicts the user's wakefulness time within the current sleep cycle, including: S501, calculate the deviation between the user's fall-off time in the current sleep cycle and the average fall-off time corresponding to the regular sleep cycle; S502, if the deviation value is less than a preset threshold, add the user's fall-off time in the current sleep cycle to the average sleep duration corresponding to regular sleep cycles to predict the wake-up time in the current sleep cycle; or, S503, if the deviation value is greater than or equal to the preset threshold, adds the user's fall asleep time in the current sleep cycle to the average sleep duration corresponding to irregular sleep cycles, and predicts the wake-up time of the current sleep cycle.

[0071] In this embodiment, firstly, a pre-established sleep pattern model and the user's current sleep cycle's fall-off time are obtained. The sleep pattern model is established through prior abnormal data screening, sleep cycle classification, normal distribution statistics, and weighted fusion. This model stores statistical results corresponding to regular and irregular sleep cycles, including the average fall-off time and average sleep duration for regular sleep cycles, as well as the average fall-off time and average sleep duration for irregular sleep cycles.

[0072] Subsequently, the deviation between the user's current sleep onset time and the average sleep onset time for regular sleep cycles is calculated. For example, the absolute difference between the current sleep onset time and the average sleep onset time for regular sleep cycles can be used as the deviation value. This calculation method can intuitively reflect the degree of deviation between the current sleep onset time and the user's sleep onset time under regular sleep patterns. The smaller the deviation value, the closer the current user's sleep pattern is to a regular sleep pattern; the larger the deviation value, the closer the current user's sleep pattern is to an irregular sleep pattern.

[0073] The average time to fall asleep corresponding to a regular sleep cycle is the average value calculated by using a normal distribution statistical method for the time to fall asleep in multiple regular sleep cycles. It can stably reflect the sleep characteristics of users with regular sleep patterns.

[0074] After obtaining the deviation between the user's fall-off time in the current sleep cycle and the average fall-off time for a regular sleep cycle, this deviation is compared with a preset deviation threshold. Based on the comparison result, different prediction methods are used to determine the wake-up time for the current sleep cycle. It should be understood that this preset deviation threshold is consistent with the preset deviation threshold used to previously divide regular and irregular sleep cycles (e.g., 30 minutes) to ensure the consistency of the judgment logic and avoid prediction errors caused by inconsistent thresholds.

[0075] In some embodiments, if the calculated deviation value is less than a preset threshold, it indicates that the current time when the user falls asleep is in line with their regular sleep habits. In this case, the user's time when falling asleep in the current sleep cycle is added to the average sleep duration corresponding to the regular sleep cycle, and the wake-up time of the current sleep cycle can be predicted.

[0076] It should be noted that the average sleep duration corresponding to a regular sleep cycle is calculated by using a normal distribution statistical method to calculate the average value of the sleep duration of multiple regular sleep cycles. This method can accurately reflect the sleep duration characteristics of a user under a regular sleep schedule. Using this method to predict can ensure that the wakefulness time is highly matched with the user's wakefulness habits under a regular sleep schedule.

[0077] In some other embodiments, if the calculated deviation value is greater than or equal to a preset threshold, it indicates that the current user's sleep time deviates from their regular sleep habits and belongs to an irregular sleep scenario. In this case, the user's sleep time in the current sleep cycle is added to the average sleep duration corresponding to the irregular sleep cycle to predict the wake time of the current sleep cycle.

[0078] It should be noted that the average sleep duration corresponding to irregular sleep cycles is the average value calculated by using a normal distribution statistical method on the sleep duration of multiple irregular sleep cycles. This value can adapt to the sleep duration characteristics when the user's work and rest schedule fluctuates, ensuring that even when the user's work and rest schedule is irregular, it can accurately predict the user's awake time in the current sleep cycle.

[0079] It should be noted that if the user wakes up before the predicted wake-up time, meaning the millimeter-wave radar detects that the user is already awake, the predicted wake-up time automatically becomes invalid. The air conditioner will then switch to a parameter adjustment mode based on the user's real-time wakefulness, ensuring that the air conditioner's operating parameters are adapted to the user's actual sleep state, further improving the user experience. Furthermore, as sleep cycle data is continuously collected and the sleep pattern model is constantly updated, the average sleep onset time and average sleep duration corresponding to regular and irregular sleep cycles will also be optimized simultaneously, thereby continuously improving the accuracy of wake-up time prediction.

[0080] One possible implementation is, such as Figure 6 As shown, before obtaining the user's current sleep stage based on respiratory and vital sign information, the method further includes: S601 uses an adaptive abnormal data filtering algorithm to filter the time when a user falls asleep, the time when they wake up, and the duration of different sleep stages for each of the multiple sleep cycles, resulting in multiple filtered sleep cycles.

[0081] S602 categorizes multiple filtered sleep cycles into regular sleep cycles and irregular sleep cycles based on the user's sleep onset time, wake-up time, and duration of different sleep stages across multiple historical sleep cycles.

[0082] Among them, regular sleep cycles are used to characterize sleep cycles in which the deviation values ​​corresponding to the time of falling asleep, the time of waking up, and the duration of each sleep stage are less than or equal to a preset deviation threshold. Irregular sleep cycles are sleep cycles in which at least one of the deviation values ​​corresponding to the time of falling asleep, the time of waking up, and the duration of each sleep stage is greater than or equal to a preset deviation threshold.

[0083] S603, the statistical results were obtained by using the normal distribution statistical method to calculate the regular sleep cycle and the irregular sleep cycle respectively.

[0084] The statistical results include: the average time to fall asleep, the average time to wake up, the average sleep duration, and the percentage of average duration of each sleep stage corresponding to regular sleep cycles; and the average time to fall asleep, the average time to wake up, the average sleep duration, and the percentage of average duration of each sleep stage corresponding to irregular sleep cycles.

[0085] S604, based on statistical results, integrates the weight values ​​corresponding to regular and irregular sleep cycles to establish a user's sleep pattern model.

[0086] Among them, the third weight value corresponding to regular sleep cycles is higher than the fourth weight value corresponding to irregular sleep cycles.

[0087] In this embodiment, firstly, an adaptive abnormal data filtering algorithm, such as the adaptive threshold method, the sliding window anomaly detection algorithm, or the isolated forest algorithm, is used to filter the sleep time, wake-up time, and duration ratio of each sleep stage for each user corresponding to multiple sleep cycles, thereby obtaining multiple filtered sleep cycles.

[0088] The number of multiple sleep cycles can be set to N days (e.g., 28 days, i.e., 4 weeks, or an integer multiple of 7 days) to ensure sufficient sample size and to truly reflect the user's long-term sleep patterns. The time of falling asleep, the time of waking up, and the duration of each sleep stage corresponding to each sleep cycle are all calculated by the sleep stage recognition algorithm provided in this application embodiment after collecting user sleep data through a millimeter-wave radar sensor.

[0089] It should be noted that the adaptive abnormal data filtering algorithm can use any one or more abnormal data filtering methods. It is mainly used to remove abnormal data caused by external interference and temporary user activities. For example, the deviation of the time of falling asleep and waking up caused by sudden noise at night, temporary activities such as getting up to drink water at night, and abnormal duration of each sleep stage, so as to ensure that the filtered sleep cycle data can truly reflect the user's normal sleep pattern.

[0090] After obtaining multiple filtered sleep cycles, the sleep cycles are divided into regular sleep cycles and irregular sleep cycles based on the deviations in the user's sleep onset time, wakefulness time, and the duration of each sleep stage across multiple historical sleep cycles. Specifically, the process first calculates the sleep onset time, wakefulness time, and duration of each sleep stage for each of the multiple historical sleep cycles. Then, based on a pre-set deviation threshold (e.g., 30 minutes), sleep cycles where the deviations in sleep onset time, wakefulness time, and the duration of each sleep stage are all less than the pre-set deviation threshold are classified as regular sleep cycles; sleep cycles where at least one of these deviations is greater than or equal to the pre-set deviation threshold are classified as irregular sleep cycles.

[0091] Regular sleep cycles mainly correspond to scenarios where users' daily routines are relatively fixed (such as weekdays), while irregular sleep cycles mainly correspond to scenarios where users' daily routines fluctuate greatly (such as weekends and holidays). By classifying these, we can accurately distinguish different user routines and improve the targeting of subsequent statistical calculations and model building.

[0092] Subsequently, the normal distribution statistical method was used to calculate the corresponding statistical results for both regular and irregular sleep cycles. During the statistical calculation, for regular sleep cycles, the average time to fall asleep, average time to wake up, average sleep duration, and average percentage of each sleep stage were calculated using the normal distribution statistical method. For irregular sleep cycles, the same normal distribution statistical method was used to simultaneously calculate the corresponding average time to fall asleep, average time to wake up, average sleep duration, and average percentage of each sleep stage.

[0093] It should be understood that the above statistical results can accurately extract the circadian rhythm characteristics of the two types of sleep cycles. The average sleep duration is calculated by the difference between the average wakefulness time and the average sleep onset time, and the average proportion of each sleep stage is obtained by statistically analyzing the average of the duration of each sleep stage in each type of sleep cycle as a percentage of the total sleep duration.

[0094] Finally, based on the above statistical results, a sleep pattern model for users was established by integrating the weight values ​​corresponding to regular and irregular sleep cycles. The third weight value for regular sleep cycles is higher than the fourth weight value for irregular sleep cycles. This is because this weight allocation is based on the characteristics of the user's sleep-wake cycle; regular sleep cycles can more realistically and stably reflect the user's long-term sleep habits and contribute more to the prediction of waking moments. Irregular sleep cycles serve only as a supplement, adapting to scenarios of fluctuating user sleep-wake cycles.

[0095] Furthermore, in the process of integrating the weight values ​​corresponding to regular and irregular sleep cycles based on statistical results, the statistical results corresponding to regular and irregular sleep cycles are multiplied by their respective weight values ​​and then summarized to form a complete sleep pattern model. This model can then adapt to both regular and irregular sleep scenarios and accurately store the characteristics of falling asleep, waking up, and sleep stages under different sleep conditions.

[0096] Furthermore, the sleep pattern model is not fixed after it is established. Instead, it can continuously repeat the above steps of abnormal data screening, cycle classification, statistical calculation and weight fusion as the user's subsequent sleep cycle data is continuously collected. This allows the model parameters to be continuously updated, ensuring that the model always fits the user's latest sleep patterns and improves the accuracy of subsequent wakefulness predictions.

[0097] In one possible implementation, after obtaining the user's current sleep stage based on respiratory and vital sign information, the method further includes: If no sleep pattern model for the user is established, the user's sleep duration is superimposed with the user's fall-off time in the current sleep cycle to predict the wake-up time in the current sleep cycle. Before the anticipated moment of wakefulness arrives, the operating parameters of the air conditioning equipment are adjusted based on the moment of wakefulness.

[0098] In this embodiment, after obtaining the user's current sleep stage based on respiratory and vital sign information, it can first determine whether the user's sleep pattern model has been established. For scenarios where a sleep pattern model has not been established, the wake-up time can be predicted by preset default sleep duration, and the air conditioning operating parameters can be adjusted in advance to ensure that the user has a good sleep and wake-up experience.

[0099] After identifying the user's current sleep stage, the air conditioner automatically checks whether a sleep pattern model has been established. Establishing a sleep pattern model involves steps such as anomaly data filtering, sleep cycle classification, normal distribution statistics, and weighted fusion. It requires accumulating valid sleep data from multiple sleep cycles (e.g., 28 days, or 4 weeks). Therefore, if the air conditioner is used for the first time, the user is using the sleep control function for the first time, or sufficient sleep data has not been accumulated, it will be determined that a sleep pattern model has not been established. In this case, a preset default sleep duration will be used to predict wakefulness.

[0100] If no sleep pattern model has been established for the user, a preset default sleep duration is added to the user's sleep onset time in the current sleep cycle to predict the wake-up time for that cycle. The preset default sleep duration is set based on normal human sleep needs; for example, it can be set to 8 hours, suitable for most adults' typical sleep duration, and can be flexibly adjusted according to actual application scenarios to accommodate differences in sleep duration for the elderly and children. User sleep data is collected by millimeter-wave radar integrated into the air conditioning unit, and combined with a sleep stage recognition algorithm to accurately determine the user's sleep onset time in the current sleep cycle, thus ensuring the reasonableness of the predicted wake-up time. During the prediction process, the predicted wake-up time for the current sleep cycle is obtained by directly adding the sleep onset time to the preset default sleep duration. This calculation method is simple and efficient, enabling rapid prediction and meeting the immediate control needs when a model has not been established.

[0101] After determining the predicted moment of wakefulness, the air conditioning system adjusts its operating parameters based on this predicted wakefulness time. The system will pre-set the adjustment time (e.g., 10-30 minutes in advance, such as 20 minutes) to adjust operating parameters such as temperature (supply air temperature, cooling temperature, heating temperature), humidity, and airflow to suit the user's physiological needs when awake. For example, in summer, the air conditioning temperature will be gradually adjusted from the suitable temperature for the user's sleep stage (e.g., 26℃) to the comfortable temperature when awake (e.g., 24℃), and the airflow will be gradually adjusted from low to medium. In winter, the temperature will be gradually adjusted from 20℃ during sleep to 22℃ to reduce discomfort caused by temperature differences, ensuring the user is in a comfortable environment when awake and improving their mental state after waking up.

[0102] In addition, while using the preset default sleep duration to predict wakefulness, the air conditioning device will continuously collect the user's sleep data, including the time of falling asleep, the time of waking up, and the duration of each sleep stage in each sleep cycle. It will also simultaneously perform steps such as abnormal data screening and sleep cycle classification to gradually accumulate effective sleep data. Once the model establishment conditions are met, the user's sleep pattern model will be automatically established. Subsequently, it will switch to the wakefulness prediction method based on the sleep pattern model to achieve personalized sleep control and further improve the user experience.

[0103] In one possible implementation, the method further includes: If the system detects that the user is awake before the predicted moment of awakening arrives, it will stop controlling the air conditioning equipment to adjust its operating parameters based on the moment of awakening and switch to controlling the air conditioning equipment to adjust its operating parameters based on the user's real-time awakening status.

[0104] In this embodiment, during the process of adjusting the operating parameters of the air conditioning equipment based on the predicted wakefulness time, the user's real-time sleep status will be continuously monitored. If the user is detected to be awake before the predicted wakefulness time arrives, the air conditioning parameter adjustment mode will be switched in time to ensure that the air conditioning operating parameters are adapted to the user's real-time status and improve the user experience.

[0105] After obtaining the predicted wake-up time of the current sleep cycle, the air conditioning equipment will start pre-adjusting the operating parameters according to the preset plan before the predicted wake-up time arrives. The operating parameters such as temperature, humidity, and air volume of the air conditioning equipment will be gradually adjusted to adapt to the physiological needs of the user when awake. The specific operating parameters can be flexibly adjusted in terms of adjustment range and timing according to seasonal changes and user sleep habits.

[0106] During the pre-conditioning process, the millimeter-wave radar integrated into the air conditioning unit continuously collects the user's breathing and vital signs information, monitors the user's sleep status in real time, and simultaneously determines whether the user is currently awake through a multi-feature fusion recognition algorithm.

[0107] If, before the predicted moment of wakefulness arrives, real-time monitoring detects that the user is already in the waking stage—for example, if the respiratory and vital signs information collected by millimeter-wave radar matches the characteristic threshold range of the waking stage, with the highest respiratory rate, the largest respiratory rate variation coefficient, the lowest respiratory stability, and the highest frequency, the largest amplitude, the shortest interval, and the longest duration of body posture changes—then the adjustment of air conditioning operating parameters based on the predicted moment of wakefulness will be stopped immediately.

[0108] After the pre-adjustment operation is stopped, the system directly switches to the air conditioning operation parameter control mode based on the user's real-time wakefulness state. Combining the user's physiological needs in their real-time wakefulness state, the system accurately adjusts the air conditioning's operating parameters such as temperature, humidity, and airflow. For example, if the user wakes up in summer, the air conditioning temperature can be quickly adjusted to around 24℃ and the airflow to medium speed to prevent the user from feeling stuffy due to incomplete pre-adjustment or unsuitable parameters; if it is winter, the temperature can be adjusted to around 22℃ to ensure the user can quickly adapt to the ambient temperature after waking up, improving their mental state.

[0109] Furthermore, after switching to the adjustment mode corresponding to the real-time wakefulness state, the air conditioning unit will continuously monitor the user's real-time status and environmental parameters. Based on the user's activity status (such as getting up and walking) and changes in ambient temperature and humidity, it will dynamically optimize the operating parameters to ensure that the air conditioning unit's operating parameters are always within the user's comfort range. In addition, relevant data on the user's early wakefulness (including the time of early wakefulness and environmental parameters at the time of wakefulness) can be stored and recorded as a basis for subsequent updates to the sleep pattern model, in order to further optimize the personalized control effect.

[0110] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0111] According to an embodiment of this application, an air conditioning device embodiment is also provided. The air conditioning device includes a controller, which is connected to sensors integrated within the air conditioning device and / or external devices, and is configured to: Obtain the user's respiratory and vital signs information; The user's current sleep stage is determined based on respiratory and vital sign information. Based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, the user's wake time in the current sleep stage is predicted. The sleep pattern model is obtained by statistically modeling regular sleep cycles and irregular sleep cycles based on the user's fall asleep time, wake time and duration of different sleep stages in multiple historical sleep cycles. Before the moment of wakefulness arrives, the operating parameters of the air conditioning equipment are adjusted based on the moment of wakefulness.

[0112] In some embodiments, the controller has a built-in processor and memory. The memory stores a preset database and a computer program. The preset database stores a pre-established sleep pattern model, which can be updated and improved by collecting the user's respiratory and vital sign information. When the controller is configured to execute the computer program, it calls the user's respiratory and vital sign information collected by sensors (such as radar sensors) and / or external devices (such as radar sensors, smart bracelets, sleep monitors) and sequentially executes the method steps of the air conditioning equipment control method in the preceding embodiments.

[0113] It is understood that the embodiments of the control device for the air conditioning equipment and any implementation thereof correspond to the embodiments of the control method for the air conditioning equipment and any implementation thereof. The technical effects corresponding to the embodiments of the control device for the air conditioning equipment and any implementation thereof can be found in the above-mentioned technical effects corresponding to the embodiments of the control method for the air conditioning equipment and any implementation thereof, and will not be repeated here.

[0114] Corresponding to the control method of the air conditioning equipment in the above embodiment, Figure 7 This is a schematic diagram of the structure of a control device for an air conditioning unit provided in an embodiment of this application. This device can be implemented as part or all of a computer device, which can be software, hardware, or a combination of both. Figure 8 The electronic device shown.

[0115] Reference Figure 7 The control device for the air conditioning equipment includes: The first acquisition unit 701 is used to acquire the user's respiratory information and vital signs information.

[0116] The second acquisition unit 702 is used to acquire the current sleep stage of the user based on respiratory information and vital sign information.

[0117] The prediction unit 703 is used to predict the user's wakefulness time during the current sleep stage based on a pre-established sleep pattern model and the user's fall asleep time during the current sleep stage.

[0118] Among them, the sleep pattern model is obtained by statistically modeling regular sleep cycles and irregular sleep cycles based on the user's fall-off time, wake-up time and duration of different sleep stages in multiple historical sleep cycles.

[0119] Control unit 704 is used to control the air conditioning equipment to adjust operating parameters based on the wakefulness state before the wakefulness state arrives.

[0120] It is understood that the embodiments of the control device for the air conditioning equipment and any implementation thereof correspond to the embodiments of the control method for the air conditioning equipment and any implementation thereof. The technical effects corresponding to the embodiments of the control device for the air conditioning equipment and any implementation thereof can be found in the above-mentioned technical effects corresponding to the embodiments of the control method for the air conditioning equipment and any implementation thereof, and will not be repeated here.

[0121] It should be noted that the control device for the air conditioning equipment provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0122] The functional units and modules in the above embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of the embodiments of this application.

[0123] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0124] This application also provides an electronic device, which includes one or more processors and a memory; The memory is coupled to one or more processors. The memory is used to store computer program code, which includes computer instructions. One or more processors invoke the computer instructions to cause the electronic device to perform the control method of the air conditioning device described above.

[0125] Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 800 can be a mobile phone, smart screen, tablet computer, wearable electronic device, in-vehicle electronic device, augmented reality (AR) device, virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), projector, or a communication device such as a server, storage device, or base station, or a smart car, etc. This application embodiment does not impose any limitations on the specific type of electronic device.

[0126] The memory 801 can be used to store computer software programs 802 and modules. The processor 803 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 801. The memory 801 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as audio data, telephone book, etc.). In addition, the memory 801 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0127] The processor 803 may include one or more processors such as a central processing unit (CPU), an application processor (AP), and a baseband processor. The processor can serve as the nerve center and command center of the wireless router. The processor 803 can generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution. The memory 801 can be used to store executable program code, including instructions. The processor 803 executes various functional applications and data processing of the network device by running the instructions stored in the memory. The memory 801 may include a program storage area and a data storage area, such as storing data for audio signals to be played. For example, the memory may be Double Data Rate Synchronous Dynamic Random Access Memory (DDR) or Flash memory.

[0128] This application also provides a computer-readable storage medium storing computer instructions; when the computer-readable storage medium is used on an electronic device, it causes the electronic device to execute the control method for the air conditioning device described above.

[0129] The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or can include one or more data storage devices such as servers or data centers that can be integrated with media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media, or semiconductor media (e.g., solid-state disks (SSDs)).

[0130] This application also provides a computer program product containing computer instructions, which, when run on an electronic device, enables the electronic device to execute the aforementioned control method for the air conditioning equipment.

[0131] The computer storage medium and computer program product provided in the embodiments of this application are used to execute the methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects corresponding to the methods provided above, and will not be repeated here.

[0132] In the above embodiments, implementation can also be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line, DSL) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc., and the storage medium can also include combinations of the above types of memory.

[0133] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0134] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments claimed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0135] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications 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 this application, and should all be included within the protection scope of this application.

Claims

1. A control method for an air conditioning device, characterized in that, include: Obtain the user's respiratory and vital signs information; The user's current sleep stage is obtained based on the respiratory information and the vital signs information; Based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, the user's wake-up time in the current sleep stage is predicted. The sleep pattern model is obtained by statistical modeling regular sleep cycles and irregular sleep cycles obtained by dividing the user's fall asleep time, wake-up time and duration of different sleep stages in each of the historical sleep cycles. Before the moment of awakening arrives, the air conditioning equipment is controlled to adjust its operating parameters based on the moment of awakening.

2. The method according to claim 1, characterized in that, The step of obtaining the user's current sleep stage based on the respiratory information and the vital signs information includes: The respiratory information and vital sign information within multiple consecutive preset time intervals are fused and analyzed to extract the user's respiratory change characteristics and body movement change characteristics; Based on the respiratory and body movement characteristics, combined with the user's previous sleep stage and a preset stage transition threshold, a multi-feature fusion recognition algorithm is used to identify the user's current sleep stage at the current moment; the stage transition threshold is adaptively adjusted according to the duration ratio of different sleep stages in each of the user's historical sleep cycles.

3. The method according to claim 2, characterized in that, Based on the respiratory and body movement characteristics, combined with the user's previous sleep stage and a preset stage transition threshold, a multi-feature fusion recognition algorithm is used to identify the user's current sleep stage at the current moment, including: The respiratory change features and the body movement change features are normalized to obtain normalized respiratory change features and normalized body movement change features. The normalization process is used to uniformly map the respiratory change features and body movement change features to a preset threshold range. The weighted normalized features are calculated by weighting the normalized respiratory change features and the normalized body movement change features respectively. The first weight value of the respiratory change features is higher than the second weight value of the body movement change features. The normalized features are substituted into the multi-feature fusion recognition algorithm, and combined with the user's sleep stage at the previous moment and the preset stage transition threshold, the recognition probability of the user being in each sleep stage at the current moment is calculated. Based on the ranking of the recognition probabilities of the user being in each sleep stage at the current moment, the sleep stage corresponding to the highest recognition probability is selected as the current sleep stage of the user at the current moment.

4. The method according to claim 3, characterized in that, The current sleep stage includes at least one of the following: wakefulness, light sleep, and deep sleep, and each sleep stage corresponds to a unique threshold range for respiratory changes and a threshold range for body movement changes: The deep sleep stage corresponds to the lowest respiratory rate, the smallest coefficient of variation of respiratory rate, the highest respiratory stability, the lowest frequency of body posture changes, the smallest amplitude of body posture changes, the longest interval of body posture changes, and the shortest duration of body posture changes. The light sleep stage corresponds to a respiratory rate, respiratory rate variation coefficient, respiratory stability, frequency of body posture changes, amplitude of body posture changes, interval of body posture changes, and duration of body posture changes, all of which are between the deep sleep stage and the wakefulness stage. The waking phase corresponds to the highest respiratory rate, the largest respiratory rate variation coefficient, the lowest respiratory stability, the highest frequency of body posture changes, the largest amplitude of body posture changes, the shortest interval between body posture changes, and the longest duration of body posture changes.

5. The method according to any one of claims 1 to 4, characterized in that, The respiratory information is used to characterize at least one of the user's respiratory rate, respiratory rate coefficient of variation, and respiratory stability; the vital signs information is used to characterize at least one of the user's body posture change amplitude, body posture change frequency, body posture change interval, and body posture change duration; obtaining the user's respiratory and vital signs information includes: The user's respiratory and vital signs information are collected at preset time intervals using sensors integrated within the air conditioning unit and / or external devices. Based on the synchronously collected current environmental parameters, the collected respiratory information and vital signs information are adaptively corrected to obtain the final respiratory information and vital signs information. The current environmental parameters include at least one of the following: ambient temperature, ambient humidity, and ambient noise intensity.

6. The method according to any one of claims 1 to 4, characterized in that, The method of predicting the user's wakefulness time within the current sleep cycle based on a pre-established sleep pattern model and the user's fall-off time in the current sleep cycle includes: Calculate the deviation between the user's sleep onset time in the current sleep cycle and the average sleep onset time corresponding to the regular sleep cycle; If the deviation value is less than a preset threshold, the user's fall-off time in the current sleep cycle is added to the average sleep duration corresponding to the regular sleep cycle to predict the wake-up time of the current sleep cycle; or, If the deviation value is greater than or equal to a preset threshold, the user's fall asleep time in the current sleep cycle is added to the average sleep duration corresponding to the irregular sleep cycle to predict the wake-up time of the current sleep cycle.

7. The method according to any one of claims 1 to 4, characterized in that, Before determining the user's current sleep stage based on the respiratory information and the vital signs information, the method further includes: An adaptive abnormal data filtering algorithm is used to filter the user's sleep onset time, wake-up time, and duration ratio of different sleep stages for each of the multiple sleep cycles, resulting in multiple filtered sleep cycles. Based on the user's multiple historical sleep cycles, including the time of falling asleep, the time of waking up, and the duration of different sleep stages, the multiple filtered sleep cycles are divided into regular sleep cycles and irregular sleep cycles. The regular sleep cycle is characterized by a sleep cycle in which the deviation values ​​corresponding to the time of falling asleep, the time of waking up, and the duration of each sleep stage are less than or equal to a preset deviation threshold. The irregular sleep cycle is a sleep cycle in which at least one of the deviation values ​​corresponding to the time of falling asleep, the time of waking up, and the duration of each sleep stage is greater than or equal to the preset deviation threshold. The regular sleep cycle and the irregular sleep cycle are calculated using the normal distribution statistical method to obtain statistical results. The statistical results include: the average time to fall asleep, the average time to wake up, the average sleep duration and the average duration of each sleep stage corresponding to the regular sleep cycle, and the average time to fall asleep, the average time to wake up, the average sleep duration and the average duration of each sleep stage corresponding to the irregular sleep cycle. Based on the statistical results, the user's sleep pattern model is established by integrating the weight values ​​corresponding to the regular sleep cycle and the irregular sleep cycle. The third weight value corresponding to the regular sleep cycle is higher than the fourth weight value corresponding to the irregular sleep cycle.

8. The method according to any one of claims 1 to 4, characterized in that, After obtaining the user's current sleep stage based on the respiratory information and the vital signs information, the method further includes: If a sleep pattern model for the user is not established, the wakefulness time of the current sleep cycle is predicted by superimposing the user's sleep duration with the default sleep duration in the current sleep cycle. Before the predicted moment of wakefulness arrives, the air conditioning equipment is controlled to adjust its operating parameters based on the predicted moment of wakefulness.

9. The method according to any one of claims 1 to 4, characterized in that, The method further includes: If the user is detected to be awake before the predicted awakening time arrives, the system stops controlling the air conditioning equipment to adjust its operating parameters based on the predicted awakening time and switches to controlling the air conditioning equipment to adjust its operating parameters based on the user's real-time awakening state; the operating parameters include at least one of temperature, humidity, and airflow.

10. An air conditioning device, characterized in that, include: Controller The controller, connected to sensors integrated within the air conditioning unit and / or external devices, is configured to: Obtain the user's respiratory and vital signs information; The user's current sleep stage is obtained based on the respiratory information and the vital signs information; Based on a pre-established sleep pattern model and the user's fall asleep time in the current sleep stage, the user's wake-up time in the current sleep stage is predicted. The sleep pattern model is obtained by statistically modeling regular sleep cycles and irregular sleep cycles obtained by dividing the user's fall asleep time, wake-up time and duration of different sleep stages in multiple historical sleep cycles. Before the moment of awakening arrives, the air conditioning equipment is controlled to adjust its operating parameters based on the moment of awakening.

Images