Air conditioner, control method thereof, and computer readable storage medium

Abstract

The application discloses a control method of an air conditioner, which comprises the following steps: obtaining a plurality of first human body motion characteristic values detected by the air conditioner in a sleep mode before a current time; adjusting a preset human body motion characteristic threshold according to the plurality of first human body motion characteristic values to obtain a target human body motion characteristic threshold; the preset human body motion characteristic threshold is a critical parameter of a human body motion characteristic value used for identifying a sleep state of an indoor human body in the sleep mode before the current time; when the air conditioner operates in the sleep mode, determining a target sleep state of the indoor human body according to a second human body motion characteristic value detected currently and the target human body motion characteristic threshold. The application also discloses an air conditioner and a computer readable storage medium. The application aims to improve the accuracy of the sleep state identification of the user by the air conditioner, to improve the regulation and control accuracy of the air conditioner in the sleep mode, and to effectively improve the sleep comfort of the air conditioner user.

Description

Technical Field

[0001] This invention relates to the field of air conditioning technology, and more particularly to a control method for an air conditioner, an air conditioner, and a computer-readable storage medium. Background Technology

[0002] With the development of economy and technology, air conditioners are being used more and more widely in daily life, and their application scenarios are becoming more and more diversified. Among them, most air conditioners have a sleep mode. In sleep mode, the air conditioner can collect the user's motion feature parameters, identify the user's sleep state based on the motion feature parameters, and operate according to the corresponding parameters of the sleep state.

[0003] Currently, in the process of identifying a user's sleep state based on motion feature parameters, air conditioners generally compare motion feature parameters with motion feature thresholds and determine the user's sleep state based on the comparison results. The motion feature thresholds are fixed parameters that are pre-set based on experience before the air conditioner leaves the factory. Regardless of how the sleep scenario changes, the motion feature thresholds remain fixed. However, this can easily lead to misjudgment of the sleep state, affecting the accuracy of the air conditioner's control in sleep mode and resulting in poor sleep comfort for air conditioner users. Summary of the Invention

[0004] The main objective of this invention is to provide a control method for an air conditioner, an air conditioner, and a computer-readable storage medium, aiming to improve the accuracy of the air conditioner in recognizing the user's sleep state, thereby improving the precision of the air conditioner's control in sleep mode and effectively enhancing the sleep comfort of air conditioner users.

[0005] To achieve the above objectives, the present invention provides a control method for an air conditioner, the control method comprising the following steps:

[0006] Obtain multiple first human motion feature values ​​detected by the air conditioner in sleep mode before the current moment;

[0007] The preset human motion feature threshold is adjusted based on the plurality of first human motion feature values ​​to obtain the target human motion feature threshold; the preset human motion feature threshold is a critical parameter of human motion feature values ​​used to identify the sleep state of a human in the room under the sleep mode before the current moment.

[0008] When the air conditioner is running the sleep mode, the target sleep state of the human body in the room is determined based on the currently detected second human motion feature value and the target human motion feature threshold.

[0009] Optionally, the step of adjusting a preset human motion feature threshold based on the plurality of first human motion feature values ​​to obtain a target human motion feature threshold includes:

[0010] A reference human motion feature threshold is determined based on the plurality of first human motion feature values;

[0011] The target human motion feature threshold is determined based on the reference human motion feature threshold and the preset human motion feature threshold.

[0012] Optionally, the step of determining the target human motion feature threshold based on the reference human motion feature threshold and the preset human motion feature threshold includes:

[0013] The target human motion feature threshold is calculated based on the reference human motion feature threshold and its corresponding first weight value, and the preset human motion feature threshold and its corresponding second weight value.

[0014] Optionally, before the step of calculating the target human motion feature threshold based on the reference human motion feature threshold and its corresponding first weight value, and the preset human motion feature threshold and its corresponding second weight value, the method further includes:

[0015] Get the number of times the air conditioner has run in sleep mode up to the current time:

[0016] The first weight value and the second weight value are determined based on the number of times; wherein the proportion of the first weight value in the sum of the first weight value and the second weight value is positively correlated with the number of times.

[0017] Optionally, both the preset human motion feature threshold and the target human motion feature threshold include critical values ​​for human motion feature values ​​used to distinguish at least two sleep states, and the step of determining the reference human motion feature threshold based on the plurality of first human motion feature values ​​includes:

[0018] The plurality of first human motion feature values ​​are classified according to the at least two sleep states to obtain classification results;

[0019] The reference human motion feature threshold is determined based on the classification results.

[0020] Optionally, the step of classifying the plurality of first human motion feature values ​​according to the at least two sleep states to obtain classification results includes:

[0021] Input the multiple first human motion feature values ​​into a preset classification model;

[0022] The result output by the preset classification model is used as the classification result;

[0023] The preset classification model is a machine learning model used to classify the plurality of first human motion feature values ​​according to the at least two sleep states.

[0024] Optionally, the preset classification model is a model constructed based on the K-means algorithm.

[0025] Optionally, the preset human motion feature threshold includes a first preset threshold, a second preset threshold, and a third preset threshold. The first preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a light sleep state. The second preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a deep sleep state. The third preset threshold is a critical parameter for distinguishing human motion feature values ​​between a light sleep state and a deep sleep state. The step of adjusting the preset human motion feature threshold according to the plurality of first human motion feature values ​​to obtain the target human motion feature threshold includes:

[0026] The first preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a first target threshold;

[0027] The second preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a second target threshold;

[0028] The third preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a third target threshold;

[0029] The target human motion feature threshold includes the first target threshold, the second target threshold, and the third target threshold;

[0030] And / or, the step of obtaining multiple first human motion feature values ​​detected by the air conditioner in sleep mode before the current time includes:

[0031] The system acquires multiple human motion amplitudes and / or multiple motion durations detected in the air conditioner's sleep mode prior to the current moment, wherein the multiple first human motion feature values ​​include the multiple human motion amplitudes and / or the multiple motion durations.

[0032] In addition, to achieve the above objectives, this application also proposes an air conditioner, the air conditioner comprising: a memory, a processor, and an air conditioner control program stored in the memory and executable on the processor, wherein when the air conditioner control program is executed by the processor, it implements the steps of the air conditioner control method as described in any of the preceding claims.

[0033] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a control program for an air conditioner, which, when executed by a processor, implements the steps of the control method for the air conditioner as described in any of the preceding claims.

[0034] This invention proposes a control method for an air conditioner. This method, based on multiple human motion feature values ​​detected in the air conditioner's sleep mode at a previous moment, adjusts a preset human motion feature threshold used to identify the sleep state of a person in the room to obtain a target human motion feature threshold. When the air conditioner restarts sleep mode, it identifies the target sleep state of the person in the current sleep mode based on the currently detected second human motion feature value and the target human motion feature threshold. Therefore, the human motion feature threshold used to identify the user's sleep state in sleep mode is no longer a fixed parameter, but can be adjusted to adapt to multiple human motion feature values ​​actually detected by the air conditioner in sleep mode in the past. These multiple human motion feature values ​​can accurately reflect the influence of the environment in which the air conditioner is located on the detection and identification of human motion feature values ​​in sleep mode, thereby improving the accuracy of the air conditioner in identifying the user's sleep state, enhancing the precision of air conditioner control in sleep mode, and effectively improving the sleep comfort of air conditioner users. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the hardware structure involved in the operation of an embodiment of the air conditioner of the present invention;

[0036] Figure 2 This is a flowchart illustrating an embodiment of the control method for an air conditioner according to the present invention;

[0037] Figure 3 This is a flowchart illustrating another embodiment of the control method for an air conditioner according to the present invention;

[0038] Figure 4 This is a flowchart illustrating another embodiment of the control method for the air conditioner of the present invention.

[0039] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0040] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0041] The main solution of this invention is as follows: acquiring multiple first human motion feature values ​​detected by the air conditioner in sleep mode before the current moment; adjusting a preset human motion feature threshold based on the multiple first human motion feature values ​​to obtain a target human motion feature threshold; the preset human motion feature threshold is a critical parameter for identifying the sleep state of the human body in the sleep mode before the current moment; when the air conditioner is running the sleep mode, determining the target sleep state of the human body in the room based on the currently detected second human motion feature value and the target human motion feature threshold.

[0042] In existing technologies, the action feature thresholds used by air conditioners to identify a user's sleep state are fixed parameters pre-set based on experience before the air conditioner leaves the factory. Regardless of how the sleep scenario changes, the action feature thresholds remain unchanged. However, this can easily lead to misjudgment of the sleep state, affecting the accuracy of the air conditioner's control in sleep mode and resulting in poor sleep comfort for air conditioner users.

[0043] The present invention provides the above-mentioned solution, which aims to improve the accuracy of air conditioners in recognizing the user's sleep state, thereby improving the precision of air conditioner control in sleep mode and effectively improving the sleep comfort of air conditioner users.

[0044] This invention provides an air conditioner. The air conditioner can be any type, such as a wall-mounted air conditioner, a cabinet air conditioner, a window air conditioner, a portable air conditioner, a ceiling-mounted air conditioner, or a multi-split air conditioner.

[0045] In this embodiment, refer to Figure 1 The air conditioner includes a control device 1 and a human body detection module 2, which is used to detect human motion characteristic data. The control device 1 is connected to the human body detection module 2 and can be used to acquire the detection data from the human body detection module 2. In other embodiments, the human body detection module 2 may also be a detection module independent of the air conditioner and located outside the air conditioner, and the control device 1 may be communicatively connected to the human body detection module 2.

[0046] Specifically, in this embodiment, the human detection module 2 is a radar sensor, such as a millimeter-wave radar. In other embodiments, the human detection module 2 can also be configured as other types of detection modules, such as infrared sensors, depending on actual needs.

[0047] In this embodiment of the invention, reference is made to Figure 1 The control device 1 of the air conditioner includes: a processor 1001 (e.g., a CPU), a memory 1002, etc. The memory 1002 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk storage device. Optionally, the memory 1002 can also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] like Figure 1 As shown, the memory 1002, which is a computer-readable storage medium, may include a control program for an air conditioner. Figure 1In the device shown, the processor 1001 can be used to call the control program of the air conditioner stored in the memory 1002 and execute the relevant steps of the control method of the air conditioner in the following embodiments.

[0050] This invention also provides a control method for an air conditioner, applied to the aforementioned air conditioner.

[0051] Reference Figure 2 This application proposes an embodiment of a control method for an air conditioner. In this embodiment, the control method for the air conditioner includes:

[0052] Step S10: Obtain multiple first human action feature values ​​detected by the air conditioner in sleep mode before the current moment;

[0053] Sleep mode is an operating mode of the air conditioner designed to meet the user's sleep comfort. Sleep mode can be activated by a timer or upon receiving a user input command.

[0054] During the operation of the air conditioner in sleep mode, the air conditioner can detect human motion feature values ​​in its operating space at set intervals. By comparing each detected human motion feature value with a human motion feature threshold, the sleep state of the human body at different times in the air conditioner's operating space under sleep mode can be determined.

[0055] Here, the multiple first human motion feature values ​​can be human motion feature values ​​detected during one or more sleep modes when the air conditioner was running before the current time. In this embodiment, the multiple first human motion feature values ​​are multiple human motion feature values ​​detected during the last sleep mode run of the air conditioner before the current time (i.e., the sleep mode with the shortest interval among all previously run sleep modes).

[0056] It should be noted that the sleep state that the air conditioner allows to identify based on the detected human feature values ​​can be one or more. In other words, the multiple first human action feature values ​​here may be data corresponding to one sleep state, or may include data corresponding to multiple sleep states.

[0057] Among them, human movement feature values ​​are parameters characterizing human movement features during sleep. Human movement here may specifically include breathing movements and / or limb movements, etc. Human movement feature values ​​specifically include the amplitude of human movement, the duration of a preset human movement, the frequency of human movement, and / or the type of human movement, etc. In this embodiment, multiple human movement amplitudes and / or multiple movement durations detected in the sleep mode of the air conditioner before the current time are obtained, and the multiple first human movement feature values ​​include the multiple human movement amplitudes and / or the multiple movement durations. The movement duration specifically refers to the duration of different preset human movements, and different preset movements can be distinguished based on the amplitude of human movement, with different amplitudes corresponding to different durations.

[0058] Step S20: Adjust the preset human motion feature threshold according to the plurality of first human motion feature values ​​to obtain the target human motion feature threshold; the preset human motion feature threshold is the critical parameter of human motion feature values ​​used to identify the sleep state of the human body in the room under the sleep mode before the current time.

[0059] The preset human motion feature threshold can be a threshold used to identify whether a human body is in a preset sleep state, or it can be a threshold used to identify the preset sleep state a human body is in among multiple preset sleep states. In other words, the preset human motion feature threshold can be used to identify one or more sleep states. Specifically, the preset human motion feature threshold may include one or more thresholds for identifying the sleep state a human body is in. Based on this, the number and type of thresholds included in the target human motion feature threshold are the same as those in the preset human motion feature threshold. In both the preset and target human motion feature thresholds, different sleep states may each correspond to a separate threshold, or two sleep states may share a single threshold.

[0060] Specifically, an adjustment value for a preset human motion feature threshold can be determined based on multiple first human motion feature values. The target human motion feature threshold is obtained by increasing or decreasing the preset human motion feature threshold based on the adjustment value. Alternatively, a human motion feature threshold matching the actual use scenario of the air conditioner can be determined based on multiple first human motion feature values. The target human motion feature threshold is then formed by replacing the preset human motion feature threshold with the determined preset human motion feature threshold. Furthermore, a human motion feature threshold matching the actual use scenario of the air conditioner can be determined based on multiple first human motion feature values. The target human motion feature threshold is then determined based on the determined human motion feature threshold and the preset human motion feature threshold, and so on.

[0061] Step S30: When the air conditioner is running the sleep mode, determine the target sleep state of the human body in the room based on the currently detected second human motion feature value and the target human motion feature threshold.

[0062] After determining the target human motion feature threshold, if a sleep mode activation command is received, the air conditioner is controlled to start the sleep mode. When the air conditioner is in sleep mode, the target sleep state of the human body in the current sleep mode is determined based on the comparison result between the newly determined target human motion feature threshold and the second human motion feature value.

[0063] The definition, type, and other specific implementation details of the second human motion feature value are the same as those of the first human motion feature value mentioned above, and will not be repeated here.

[0064] For example, when the target human motion feature threshold includes a first threshold value for the amplitude of human motion and a second threshold value for the duration of motion used to distinguish between a waking state and a sleeping state, the amplitude of human motion and its corresponding duration are detected in the current air conditioner's operating space under the current sleep mode of the air conditioner. When the amplitude of human motion is greater than the first threshold value and the duration of motion is greater than the second threshold value, the target sleep state is determined to be a waking state; when the amplitude of human motion is less than the first threshold value and the duration of motion is greater than the second threshold value, the target sleep state is determined to be a sleeping state.

[0065] After step S30, you can return to step S10. Then, the multiple second human motion feature values ​​detected in the current sleep mode can be used as multiple new first human motion feature values, and the current target human motion feature threshold can be used as a new preset human motion feature threshold.

[0066] This invention proposes a control method for an air conditioner. Based on multiple human motion feature values ​​detected in the air conditioner's sleep mode prior to the current moment, the method adjusts a preset human motion feature threshold used to identify the sleep state of a person in the room to obtain a target human motion feature threshold. When the air conditioner restarts sleep mode, the target sleep state of the person in the current sleep mode is identified based on the currently detected second human motion feature value and the target human motion feature threshold. Therefore, the human motion feature threshold used to identify the user's sleep state in sleep mode is no longer a fixed parameter, but can be adjusted to adapt to multiple human motion feature values ​​actually detected by the air conditioner in sleep mode in the past. These multiple human motion feature values ​​can accurately reflect the influence of the scene in which the air conditioner is located on the detection and identification of human motion feature values ​​in sleep mode, thereby improving the accuracy of the air conditioner in identifying the user's sleep state, improving the precision of air conditioner control in sleep mode, and effectively improving the sleep comfort of air conditioner users.

[0067] Furthermore, in this embodiment, the preset human motion feature threshold includes a first preset threshold, a second preset threshold, and a third preset threshold. The first preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a light sleep state. The second preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a deep sleep state. The third preset threshold is a critical parameter for distinguishing human motion feature values ​​between a light sleep state and a deep sleep state. The step of adjusting the preset human motion feature threshold according to the plurality of first human motion feature values ​​to obtain the target human motion feature threshold includes:

[0068] The first preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a first target threshold;

[0069] The second preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a second target threshold;

[0070] The third preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a third target threshold;

[0071] The target human motion feature threshold includes the first target threshold, the second target threshold, and the third target threshold;

[0072] Specifically, a first adjustment value corresponding to a first preset threshold, a second adjustment value corresponding to a second preset threshold, and a third adjustment value corresponding to a third preset threshold can be determined based on multiple first human motion feature values. The first preset threshold is adjusted according to the first adjustment value to obtain a first target threshold; the second preset threshold is adjusted according to the second adjustment value to obtain a second target threshold; and the third preset threshold is adjusted according to the third adjustment value to obtain a third target threshold. The first, second, and third adjustment values ​​can be the same adjustment value determined based on multiple first human motion feature values; alternatively, they can be different adjustment values ​​determined based on multiple first human motion feature values.

[0073] In this embodiment, the human motion characteristic values ​​detected in the previous sleep mode are adjusted by means of the above method to distinguish between the awake state, light sleep state and deep sleep state. This ensures that the air conditioner can accurately distinguish between the awake state, light sleep state and deep sleep state when entering sleep mode, so as to ensure that the air conditioner can accurately regulate the user's comfort needs in these different sleep states and further improve the user's sleep comfort.

[0074] Furthermore, based on the above embodiments, another embodiment of the control method for the air conditioner of this application is proposed. In this embodiment, reference is made to... Figure 3 Step S20 includes:

[0075] Step S21: Determine a reference human motion feature threshold based on the plurality of first human motion feature values;

[0076] The reference human motion feature threshold is specifically a human motion feature threshold that matches the actual sleep scenario (such as the number of people, the space between the human body and the air conditioner, the size of the space where the air conditioner is located) in the air conditioner's sleep mode before the current moment, obtained based on the analysis of multiple first human motion feature values.

[0077] Specifically, the numerical characteristics of multiple first human motion feature values ​​can be analyzed based on pre-set data analysis rules, and the reference human motion feature threshold can be determined based on the analysis results.

[0078] In one implementation, each of the multiple first human motion feature values ​​can be associated with the recognition result of its corresponding human sleep state (i.e., the sleep state of the human body determined by comparing the first human motion feature value with the aforementioned preset human motion feature threshold). Based on the recognition result, several first human motion feature values ​​corresponding to the preset sleep state can be determined, and target data corresponding to the preset sleep state can be obtained. Based on the feature parameters (such as variance, mean, standard deviation, and / or the difference between the maximum and minimum values) corresponding to the several first human motion feature values ​​in the target data corresponding to the preset sleep state, a reference human motion feature threshold for identifying whether the user is in the preset sleep state can be determined. There can be one or more preset sleep states. When there is more than one preset sleep state, the recognition threshold corresponding to each preset sleep state can be determined based on the above method. The reference human motion feature threshold includes more than one recognition threshold.

[0079] Step S22: Determine the target human motion feature threshold based on the reference human motion feature threshold and the preset human motion feature threshold.

[0080] Different reference human motion feature thresholds and different preset human motion feature thresholds can correspond to different target human motion feature thresholds. The correspondence between the reference human motion feature thresholds, preset human motion feature thresholds, and target human motion feature thresholds can be preset, such as calculation formulas or mapping relationships. Based on this, the target human motion feature value can be obtained by substituting the reference human motion feature thresholds and preset human motion feature thresholds into a preset formula or by querying a preset mapping table.

[0081] In this embodiment, the reference human motion feature threshold obtained based on actual detection data is easily affected by environmental factors, while the preset human motion feature threshold obtained based on experience has better stability in recognizing sleep states. Therefore, combining the reference human motion feature threshold and the preset human motion feature threshold to determine the target human motion feature threshold can ensure that the determined target human motion feature threshold can reflect the current usage scenario of the air conditioner and is not easily affected by accidental fluctuations in the environment. This is conducive to effectively improving the accuracy of the determined target human motion feature threshold, thereby further improving the accuracy of user sleep state recognition and air conditioner sleep regulation, and ensuring user sleep comfort.

[0082] Furthermore, in this embodiment, the target human motion feature threshold is calculated based on the reference human motion feature threshold and its corresponding first weight value, as well as the preset human motion feature threshold and its corresponding second weight value.

[0083] The first and second weight values ​​here can be preset fixed values; alternatively, the first and second weight values ​​can also be parameters determined based on the actual operating conditions of the air conditioner. For example, T new =a T temp +(1-a) T old , among which, T new T is the threshold value for the target human motion features. old To preset the threshold for human motion features, T temp The threshold is used as a reference for human motion characteristics.

[0084] Here, the result of the weighted average calculation of the reference human motion feature threshold and the preset human motion feature threshold is used as the target human motion feature threshold, which is beneficial to further improve the accuracy of sleep state recognition based on the target human motion feature threshold.

[0085] In other embodiments, a reference human motion feature threshold and a preset human motion feature threshold may be compared, and one of the reference human motion feature threshold and the preset human motion feature threshold may be determined as the target human motion feature threshold based on the comparison result. For example, the preset human motion feature threshold is a threshold used to distinguish between a waking state and a sleeping state, and the larger value of the reference human motion feature threshold and the preset human motion feature threshold is determined as the target human motion feature threshold based on the comparison result.

[0086] Furthermore, in this embodiment, before calculating the target human motion feature threshold by weighted average, the number of times the air conditioner has run in sleep mode before the current time is obtained: the first weight value and the second weight value are determined based on the number of times; wherein, the proportion of the first weight value in the sum of the first weight value and the second weight value is positively correlated with the number of times.

[0087] Here, the number of times the air conditioner has run in sleep mode before the current moment can be the total number of times since the air conditioner left the factory, or the number of times counted after the air conditioner has run to the preset condition (such as receiving a preset command or the time interval between two consecutive sleep modes being greater than the set duration), and so on.

[0088] Different counts correspond to different first and second weight values. Specifically, the first weight value can be determined based on the count, and the second weight value can be determined by the preset sum (e.g., 1) between the first and second weight values ​​and the first weight value. When the count is less than the set value, the first weight value can be less than the second weight value; when the count is greater than the set value, the first weight value can be greater than the second weight value.

[0089] Alternatively, a mapping relationship between the number of times and the first and second weight values ​​can be established in advance, and the first and second weight values ​​corresponding to the current number of times can be determined based on the preset mapping relationship.

[0090] In this embodiment, the number of times the sleep mode has been run before the current time is used to determine the first weight value and the second weight value. This helps to ensure that the determined target human motion feature threshold is more in line with the actual application scenario of the air conditioner, so as to further improve the accuracy of user sleep state recognition and sleep parameter regulation in subsequent sleep modes.

[0091] In other embodiments, the set temperature and airflow speed of the air conditioner in sleep mode before the current moment can also be obtained. The first weight value and the second weight value are determined based on the set temperature and airflow speed. The set temperature and airflow speed can reflect the impact of the air conditioner's operation on the accuracy of user action feature detection, so as to ensure that the accuracy of the target human action feature threshold calculated based on the determined first weight value and second weight value for user sleep state recognition is effectively improved.

[0092] Furthermore, in this embodiment, when the preset human motion feature thresholds include the aforementioned first preset threshold, second preset threshold, and third preset threshold, a first reference human motion feature threshold corresponding to the first preset threshold, a second reference human motion feature threshold corresponding to the second preset threshold, and a third reference human motion feature threshold corresponding to the third preset threshold can be determined based on multiple first human motion feature values. A first target threshold is determined based on the first preset threshold and the first reference human motion feature threshold, a second target threshold is determined based on the second preset threshold and the second reference human motion feature threshold, and a third target threshold is determined based on the third preset threshold and the third reference human motion feature threshold. Each target human motion feature threshold can be determined using the corresponding preset threshold and reference human motion feature threshold in the manner mentioned above (such as weighted average calculation, mapping relationship), which will not be elaborated here.

[0093] Furthermore, based on any of the above embodiments, another embodiment of the control method for the air conditioner of this application is proposed. In this embodiment, both the preset human motion characteristic threshold and the target human motion characteristic threshold include critical values ​​for human motion characteristic values ​​used to distinguish at least two sleep states. Here, the at least two sleep states may specifically include the aforementioned awake state, light sleep state, and deep sleep state. More or fewer states may also be included depending on actual needs. (Refer to...) Figure 4 Step S21 includes:

[0094] Step S211: Classify the plurality of first human motion feature values ​​according to at least two sleep states to obtain classification results;

[0095] The classification results specifically include sub-data corresponding to each of at least two sleep states. The sub-data corresponding to each sleep state specifically includes all first human motion feature values ​​representing the user's sleep state identification results before the current moment, indicating that the user was in that sleep state.

[0096] In this embodiment, the plurality of first human motion feature values ​​are input to a preset classification model; the output of the preset classification model is obtained as the classification result; wherein, the preset classification model is a machine learning model used to classify the plurality of first human motion feature values ​​according to the at least two sleep states. Specifically, the preset classification model can be trained using samples collected during sleep modes in different spaces used by different air conditioners. In this embodiment, the preset classification model is a model built based on the K-means algorithm. In other embodiments, the preset classification model can also be a classification model built using other algorithms, such as a model built based on the AdaBoost algorithm. Classifying the plurality of first human motion feature values ​​according to different sleep states using the preset classification model helps to quickly and accurately determine the human motion feature data representing different sleep states when the air conditioner was in sleep mode, which is beneficial for quickly and accurately obtaining reference human motion feature thresholds subsequently.

[0097] In other embodiments, several first human motion feature values ​​corresponding to each sleep state can also be determined based on data detected by other detection modules within the air conditioner's operating space. For example, if the first human motion feature values ​​are detected by a radar sensor, then multiple first human motion feature values ​​can be classified according to different sleep states based on the sleep state identification results detected by infrared sensors and / or image sensors.

[0098] Step S212: Determine the reference human motion feature threshold based on the classification result.

[0099] Specifically, the extreme values ​​(such as maximum and / or minimum values) of several first human motion feature values ​​corresponding to each sleep state in the classification results can be determined, and the reference human motion feature threshold is determined based on the extreme values ​​corresponding to each sleep state. Each threshold value in the preset human motion threshold is defined as distinguishing two sleep states: a first state and a second state. The human motion feature value corresponding to the first state is less than the corresponding threshold value, and the human motion feature value corresponding to the second state is greater than the corresponding threshold value. The threshold values ​​corresponding to the first and second states can be determined based on the maximum value of several first human motion feature values ​​corresponding to the first state and the minimum value of several first human motion feature values ​​corresponding to the second state, as determined by the classification results. For example, the average of the maximum and minimum values ​​can be used as the threshold value. For instance, the preset human motion threshold includes the aforementioned first preset threshold. Multiple first human motion feature values ​​are classified according to awake state and light sleep state to obtain first data corresponding to the awake state and second data corresponding to the light sleep state. The minimum first human motion feature value in the first data is determined as the first target value, and the maximum second human motion feature value in the second data is determined as the second target value. The average of the first target value and the second target value can then be used as the first target threshold. When the preset human motion threshold includes preset thresholds for any other two sleep states, the corresponding target threshold can also be determined by analogy to the method mentioned here, which will not be elaborated here.

[0100] In this embodiment, the above method facilitates the accurate adjustment of the human motion feature threshold used to distinguish different sleep states, ensuring that the determined target human motion feature threshold can accurately distinguish different sleep states in subsequent sleep states.

[0101] Furthermore, this invention also proposes a computer-readable storage medium storing a control program for an air conditioner. When the control program is executed by a processor, it implements the relevant steps of any of the above-described air conditioner control methods.

[0102] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0103] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0105] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A control method for an air conditioner, characterized in that, The control method for the air conditioner includes the following steps: Obtain multiple first human motion feature values ​​detected by the air conditioner in sleep mode before the current moment; The preset human motion feature threshold is adjusted based on the plurality of first human motion feature values ​​to obtain the target human motion feature threshold; the preset human motion feature threshold is a critical parameter of human motion feature values ​​used to identify the sleep state of a human body in the room under the sleep mode before the current time. When the air conditioner is running the sleep mode, the target sleep state of the human body in the room is determined based on the currently detected second human motion feature value and the target human motion feature threshold.

2. The control method for an air conditioner as described in claim 1, characterized in that, The step of adjusting the preset human motion feature threshold based on the plurality of first human motion feature values ​​to obtain the target human motion feature threshold includes: A reference human motion feature threshold is determined based on the plurality of first human motion feature values; The target human motion feature threshold is determined based on the reference human motion feature threshold and the preset human motion feature threshold.

3. The control method for an air conditioner as described in claim 2, characterized in that, The step of determining the target human motion feature threshold based on the reference human motion feature threshold and the preset human motion feature threshold includes: The target human motion feature threshold is calculated based on the reference human motion feature threshold and its corresponding first weight value, and the preset human motion feature threshold and its corresponding second weight value.

4. The control method for an air conditioner as described in claim 3, characterized in that, Before the step of calculating the target human motion feature threshold based on the reference human motion feature threshold and its corresponding first weight value, and the preset human motion feature threshold and its corresponding second weight value, the method further includes: Get the number of times the air conditioner has run in sleep mode up to the current time: The first weight value and the second weight value are determined based on the number of times; wherein the proportion of the first weight value in the sum of the first weight value and the second weight value is positively correlated with the number of times.

5. The control method for an air conditioner as described in any one of claims 2 to 4, characterized in that, Both the preset human motion feature threshold and the target human motion feature threshold include critical values ​​for human motion feature values ​​used to distinguish at least two sleep states. The step of determining the reference human motion feature threshold based on the plurality of first human motion feature values ​​includes: The plurality of first human motion feature values ​​are classified according to the at least two sleep states to obtain classification results; The reference human motion feature threshold is determined based on the classification results.

6. The control method for an air conditioner as described in claim 5, characterized in that, The step of classifying the plurality of first human motion feature values ​​according to the at least two sleep states to obtain classification results includes: Input the multiple first human motion feature values ​​into a preset classification model; The result output by the preset classification model is used as the classification result; The preset classification model is a machine learning model used to classify the plurality of first human motion feature values ​​according to the at least two sleep states.

7. The control method for an air conditioner as described in claim 6, characterized in that, The preset classification model is a model built based on the K-means algorithm.

8. The control method for an air conditioner as described in any one of claims 1 to 4, characterized in that, The preset human motion feature thresholds include a first preset threshold, a second preset threshold, and a third preset threshold. The first preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a light sleep state. The second preset threshold is a critical parameter for distinguishing human motion feature values ​​between a waking state and a deep sleep state. The third preset threshold is a critical parameter for distinguishing human motion feature values ​​between a light sleep state and a deep sleep state. The step of adjusting the preset human motion feature thresholds according to the plurality of first human motion feature values ​​to obtain the target human motion feature threshold includes: The first preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a first target threshold; The second preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a second target threshold; The third preset threshold is adjusted based on the plurality of first human motion feature values ​​to obtain a third target threshold; The target human motion feature threshold includes the first target threshold, the second target threshold, and the third target threshold; And / or, the step of obtaining multiple first human motion feature values ​​detected by the air conditioner in sleep mode before the current time includes: The system acquires multiple human motion amplitudes and / or multiple motion durations detected in the air conditioner's sleep mode prior to the current moment, wherein the multiple first human motion feature values ​​include the multiple human motion amplitudes and / or the multiple motion durations.

9. An air conditioner, characterized in that, The air conditioner includes: a memory, a processor, and a control program for the air conditioner stored in the memory and executable on the processor. When the control program for the air conditioner is executed by the processor, it implements the steps of the control method for the air conditioner as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a control program for an air conditioner, which, when executed by a processor, implements the steps of the control method for an air conditioner as described in any one of claims 1 to 8.

Images