Air conditioner and control method and device thereof, storage medium and computer program product

Abstract

The invention provides an air conditioner and a control method and device thereof, a storage medium and a computer program product, and the method comprises the steps that when a target user is in a sleep stage, current human body activity state parameters of the target user are obtained; inputting the obtained human body activity state parameters into a pre-trained prediction model, and predicting to obtain a current sleep stage of the target user; and according to the current sleep stage of the target user obtained through prediction, the indoor environment temperature is controlled, and / or the air gear of an inner draught fan of the air conditioner and / or starting of a new draught fan are / is controlled. According to the scheme provided by the invention, the requirements of the human body on the environmental comfort in different sleep stages can be more accurately met.

Description

Technical Field

[0001] The present invention relates to the field of control, and in particular to an air conditioner and a control method, device, storage medium and computer program product thereof. Background Art

[0002] Air conditioning control systems in related technologies usually adjust the temperature based on fixed temperature settings or simple environmental sensors, without considering the specific temperature needs of the human body in different sleep stages. They are usually unable to distinguish different stages of the human body during sleep, and therefore cannot provide personalized temperature adjustment. This may cause users to feel overheated or overcooled in certain sleep stages, affecting sleep quality. Summary of the invention

[0003] The main purpose of the present invention is to overcome the defects of the above-mentioned related technologies and to provide an air conditioner and its control method, device, storage medium and computer program product to solve the problem that the control of the air conditioner in the related technologies does not take into account the specific temperature requirements of the human body in different sleep stages.

[0004] On the one hand, the present invention provides a method for controlling an air conditioner, comprising: when a target user is in a sleeping stage, obtaining the current human activity state parameters of the target user; inputting the obtained human activity state parameters into a pre-trained prediction model to predict the current sleep stage of the target user; and controlling the indoor ambient temperature and / or controlling the opening of the internal fan windshield and / or fresh air fan of the air conditioner according to the predicted current sleep stage of the target user.

[0005] Optionally, obtaining the current human activity state parameters of the target user includes: detecting the current human activity state parameters of the target user by a bio-radar module provided on the air conditioner.

[0006] Optionally, the prediction model is trained in the following manner: different human activity state parameters in different sleep stages are obtained as sample data; the different human state parameters are used as input data and the different sleep stages are used as output data to train a neural network model to obtain a prediction model for predicting sleep stages.

[0007] Optionally, the indoor ambient temperature is controlled based on the predicted current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage or the eye movement stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to the set temperature; when it is predicted that the current sleep stage of the target user is the light sleep stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to a third temperature, the third temperature is equal to the difference between the set temperature of the air conditioner and the second preset temperature value; when it is predicted that the current sleep stage of the target user is the deep sleep stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to the first temperature, the first temperature is equal to the difference between the set temperature of the air conditioner and the first preset temperature value.

[0008] Optionally, the wind speed of the internal fan of the air conditioner is controlled based on the prediction of the current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage, the internal fan is controlled to operate at the set wind speed; when it is predicted that the current sleep stage of the target user is the light sleep stage, the deep sleep stage or the eye movement stage, the internal fan is controlled to operate at the preset lowest wind speed.

[0009] Optionally, the fresh air fan of the air conditioner is controlled to be turned on according to the prediction of the current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage or the eye movement stage, the fresh air fan of the air conditioner is controlled to be turned on.

[0010] Optionally, it also includes: when the target user is in the sleeping stage, controlling the indoor ambient temperature according to a first temperature change rate, so that the indoor ambient temperature is reduced to a first temperature, and the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value; and / or, when the target user is in the awakening stage, during the first t time of the awakening stage, controlling the indoor ambient temperature according to a second temperature change rate, so that the indoor ambient temperature reaches the set temperature of the air conditioner; during the remaining time of the awakening stage, controlling the indoor ambient temperature according to the second temperature change rate, so that the indoor ambient temperature is equal to a second temperature, and the second temperature is equal to the sum of the set temperature of the air conditioner and the first preset temperature value.

[0011] On the other hand, the present invention provides a control device for an air conditioner, comprising: an acquisition unit, used to acquire the current human activity state parameters of the target user when the target user is in the sleeping stage; a prediction unit, used to input the human activity state parameters acquired by the acquisition unit into a pre-trained prediction model, and predict the current sleep stage of the target user; a control unit, used to control the indoor ambient temperature and / or control the opening of the internal fan windshield and / or the fresh air fan of the air conditioner according to the current sleep stage of the target user predicted by the prediction unit.

[0012] Optionally, the acquiring unit acquires the current human activity state parameters of the target user, including: detecting the current human activity state parameters of the target user by a bio-radar module provided on the air conditioner.

[0013] Optionally, it also includes: a training unit, used to train the prediction model, and the prediction model is trained in the following manner: obtaining different human activity state parameters in different sleep stages as sample data; using the different human state parameters as input data and the different sleep stages as output data, training a neural network model, and obtaining a prediction model for predicting sleep stages.

[0014] Optionally, the control unit controls the indoor ambient temperature according to the predicted current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage or the eye movement stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to the set temperature; when it is predicted that the current sleep stage of the target user is the light sleep stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to a third temperature, and the third temperature is equal to the difference between the set temperature of the air conditioner and the second preset temperature value; when it is predicted that the current sleep stage of the target user is the deep sleep stage, controlling the indoor ambient temperature according to the second temperature change rate so that the indoor ambient temperature is equal to the first temperature, and the first temperature is equal to the difference between the set temperature of the air conditioner and the first preset temperature value.

[0015] Optionally, the control unit controls the wind speed of the internal fan of the air conditioner according to the predicted current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage, controlling the internal fan to operate at the set wind speed; when it is predicted that the current sleep stage of the target user is the light sleep stage, the deep sleep stage or the eye movement stage, controlling the internal fan to operate at the preset lowest wind speed.

[0016] Optionally, the control unit controls turning on the fresh air fan of the air conditioner according to the predicted current sleep stage of the target user, including: when it is predicted that the current sleep stage of the target user is the awake stage or the eye movement stage, controlling the fresh air fan of the air conditioner to turn on.

[0017] Optionally, the control unit is also used to: when the target user is in the sleeping stage, control the indoor ambient temperature according to a first temperature change rate to reduce the indoor ambient temperature to a first temperature, wherein the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value; and / or, when the target user is in the awakening stage, during the first t time of the awakening stage, control the indoor ambient temperature according to a second temperature change rate to make the indoor ambient temperature reach the set temperature of the air conditioner; during the remaining time of the awakening stage, control the indoor ambient temperature according to the second temperature change rate to make the indoor ambient temperature equal to a second temperature, wherein the second temperature is equal to the sum of the set temperature of the air conditioner and the first preset temperature value.

[0018] Another aspect of the present invention provides a storage medium having a computer program stored thereon, wherein the program implements the steps of any of the aforementioned methods when executed by a processor.

[0019] In another aspect, the present invention provides an air conditioner, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the program.

[0020] In another aspect, the present invention provides an air conditioner, comprising any of the control devices described above.

[0021] In yet another aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0022] According to the technical solution of the present invention, by monitoring the user's sleep stage status and adjusting the temperature and wind speed settings of the air conditioner accordingly, the human body's needs for environmental comfort in different sleep stages can be more accurately met.

[0023] According to the technical solution of the present invention, the sleep stage status is monitored in real time through the bio-radar technology combined with the deep learning model, and the air-conditioning temperature is automatically adjusted according to the stage, which directly affects the sleep quality and user comfort.

[0024] According to the technical solution of the present invention, temperature control is performed according to different temperature adjustment strategies according to the sleep stage status, providing a more detailed personalized experience compared to a single or fixed temperature setting. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a method schematic diagram of an embodiment of the air conditioner control method provided by the present invention;

[0027] Figure 2 The figure shows the connection diagram between the biological radar module and the air conditioner mainboard;

[0028] Figure 3 A schematic diagram of a deep neural network model is shown;

[0029] Figure 4 is a method schematic diagram of another embodiment of the air conditioner control method provided by the present invention;

[0030] Figure 5 is a method schematic diagram of another embodiment of the air conditioner control method provided by the present invention;

[0031] Figure 6 shows a sleep control temperature curve according to the present invention;

[0032] Figure 7 The sleep stage curve and temperature control curve according to the present invention are shown;

[0033] Figure 8 It is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Some air-conditioning systems in the related art use simple sensors to monitor the presence or movement of the human body, but these systems usually do not have the ability to recognize the sleep stage state, lack real-time monitoring and analysis of the sleep stage state, and cannot dynamically adjust the air-conditioning settings to adapt to changes in human needs.

[0037] The present invention provides a control method for an air conditioner, wherein the air conditioner has a bio-radar module for collecting parameters of human activity status.

[0038] The bio-radar module includes: a radio frequency antenna, a radar chip and a high-speed main frequency MCU, which can extract human vital signs signals and obtain human activity status parameters. The bio-radar module can extract human activity status parameters such as distance, breathing rate, heart rate, signal strength (such as body movement status, body movement energy).

[0039] The air conditioning control system is developed by reading data from the bio-radar module through serial communication. For example, the bio-radar module is connected to the air conditioning control motherboard communication interface through pins. Figure 2 The figure shows the connection diagram between the biological radar module and the air conditioner mainboard. Figure 2 As shown, the air conditioner main control RXD is connected to the radar's RX through uart and connected to the RX antenna; the air conditioner main control TXD is connected to the radar's TX through uart and connected to the TX antenna; the main control power interface VDD is connected to the radar VCC, and the GNDs of the two are connected.

[0040] Through analysis and selection, the important pin definitions of the biological radar module used in the development are shown in Table 1:

[0041] Table 1

[0042] Pinout describe illustrate 1 VCC Input power voltage 3V~5.5V 2 GND Grounding 3 UART_TX Serial port sending 4 UART_RX Serial port receiving

[0043] Figure 1 It is a method schematic diagram of an embodiment of the air conditioner control method provided by the present invention.

[0044] like Figure 1 As shown, according to an embodiment of the present invention, the air conditioner control method at least includes step S110, step S120 and step S130.

[0045] Step S110, when the target user is in the sleeping stage, obtaining the current human activity state parameters of the target user.

[0046] Specifically, the sleep stage is divided into the falling asleep stage, the sleeping stage and the waking stage. In the sleep stage, the first period of the preset time is the falling asleep stage, the second period of the preset time is the waking stage, and the middle period is the sleeping stage. For example, the sleep stage is 8 hours, and the three stages are divided according to 8 hours. The first 20 minutes of 8 hours are set as the falling asleep stage, and the temperature is lowered according to the temperature change rate 1. The last 20 minutes of 8 hours are set as the waking stage, and the control is executed according to the logic of the waking stage. The rest of the time (the period between the first 20 minutes and the last 20 minutes) is the sleeping stage. The current human activity state parameters of the target user can be detected by the bioradar module on the air conditioner. The human activity state parameters can specifically include: at least one of breathing, heart rate, distance (the distance from the bioradar antenna to the human chest), body movement state, and body movement energy.

[0047] Step S120: input the acquired current human activity state parameters of the target user into a pre-trained prediction model to predict the current sleep stage of the target user.

[0048] The prediction model is used to predict sleep stages. In a specific embodiment, the prediction model is trained in the following manner:

[0049] Step S1, obtaining different human activity state parameters in different sleep stages as sample data.

[0050] In a specific implementation, the sleep stage of a person is divided into the awake stage, the light sleep stage, the eye movement stage and the deep sleep stage. The sleep stage of the human body changes continuously during sleep, and the body requires different temperatures in each stage. For example, the basis for setting the air conditioning temperature control logic may be:

[0051] Awake stage: In this state, the ambient temperature usually needs to be around 26-28℃.

[0052] REM sleep: REM sleep is a relatively independent stage of sleep, and the required environmental temperature is similar to that of the waking period.

[0053] Light sleep stage: The ambient temperature required during the light sleep stage is slightly lower than that during the waking stage.

[0054] Deep sleep: The ambient temperature required during deep sleep is lower than that of other stages.

[0055] Different human activity state parameters in different sleep stages are obtained in advance as sample data for training the prediction model.

[0056] Step S2, using the different human body state parameters as input data and the different sleep stages as output data, training a neural network model to obtain a prediction model for predicting sleep stages.

[0057] For any human activity state parameter, n signal features at m different moments are collected respectively to obtain m*n features of the human activity state parameter; the n signal features may specifically include: any n of the signal maximum value, signal minimum value, signal mean value, signal median value, and signal standard deviation.

[0058] Specifically, in the data processing process, in order to ensure the accuracy of the prediction results and the stability of the model operation, the feature analysis is as comprehensive as possible. For each human body state parameter, the sampled signal data can include the current time t, the previous time t-1, ..., and the earlier time tm-1, a total of n features of m categories (the specific time step can be determined according to actual needs, experimental results and availability), and the dimensional data shown in the following table in the three categories are collected respectively. Therefore, the model input data contains the original m*n features, and the output is the sleep stage category (here taking 4 categories as an example).

[0059] Train the multi-layer perceptron and use TensorFlow for training. Input layer: contains m*n inputs (depending on the specific radar needs, the inputs are signals such as breathing, heart rate, distance, body movement state, body movement energy, and their maximum signal value, minimum signal value, signal mean, signal median, signal standard deviation, etc.); Output layer: contains 4 neurons, and uses the softmax function to convert the activation value of the output layer neuron into a probability distribution. There are 3 hidden layers, which have 128, 64 and 32 neurons respectively. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer. The initial learning rate is set to 0.002, the number of training rounds is 150, and the batch size is 32. For specific neural network structure reference Figure 3 shown. Figure 3 A schematic diagram of a deep neural network model is shown.

[0060] Step S130, according to the predicted current sleep stage of the target user, controlling the indoor ambient temperature, and / or controlling the air damper of the internal fan of the air conditioner and / or turning on the fresh air fan.

[0061] In a specific implementation, according to the predicted sleep stage of the target user, controlling the indoor ambient temperature includes the following situations:

[0062] (1) When it is predicted that the target user is currently in the sleep stage of the awake stage or the eye movement stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the set temperature.

[0063] Specifically, when the sleep stage is awake or eye movement, the initial set temperature is maintained, even if the indoor ambient temperature T is equal to the set temperature T 0 , that is, T = T 0 . Execute the second temperature change rate to make the indoor ambient temperature T equal to the set temperature T 0 The second temperature change rate, for example, may be initially 0.1°C / 1min.

[0064] (2) When it is predicted that the target user is currently in a light sleep stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the third temperature.

[0065] The third temperature is equal to the difference between the set temperature of the air conditioner and the second preset temperature value. Specifically, when the sleep stage is a light sleep stage, the indoor ambient temperature is controlled to decrease to the third temperature according to the second temperature change rate. For example, the second preset temperature difference is 0.5°C, that is, the indoor ambient temperature T=T0-0.5°C, and the second temperature change rate, for example, can be 0.1°C / 1min initially.

[0066] (3) When it is predicted that the target user is currently in a deep sleep stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the first temperature.

[0067] The first temperature is the deep sleep temperature. The first temperature is equal to the difference between the set temperature of the air conditioner and the first preset temperature value. Specifically, when the sleep stage is the deep sleep stage, the indoor ambient temperature is controlled to drop to the first temperature according to the second temperature change rate. For example, the first preset temperature difference is 1°C, that is, the indoor ambient temperature T=T 0 -1.0°C, the second temperature change rate, for example, may be 0.1°C / 1min initially.

[0068] In a specific implementation, the wind speed of the internal fan is controlled according to the predicted sleep stage of the target user, including the following situations:

[0069] (1) When it is predicted that the target user is currently in the awake stage of sleep, the internal fan is controlled to operate according to the set wind speed.

[0070] For example, when the sleep stage is awake, the wind speed is controlled according to the original setting of the remote controller.

[0071] (2) When it is predicted that the target user is currently in a light sleep stage, a deep sleep stage, or an eye movement sleep stage, the internal fan is controlled to operate at a preset minimum wind speed.

[0072] For example, when the sleep stage is light sleep, deep sleep or REM sleep, keep the windshield silent.

[0073] In a specific implementation, based on the prediction of the current sleep stage of the target user, controlling the start and stop of the fresh air fan includes: when it is predicted that the current sleep stage of the target user is the awake stage or the eye movement stage, controlling the fresh air fan of the air conditioner to turn on.

[0074] For example, when the sleep stage is light sleep, deep sleep or REM sleep, turn on the fresh air switch.

[0075] Figure 4 It is a method schematic diagram of another embodiment of the air conditioner control method provided by the present invention.

[0076] like Figure 4 As shown, according to another embodiment of the present invention, the air conditioner control method further includes step S100.

[0077] Step S100, when the target user is in the sleeping stage, the indoor environment temperature is controlled according to the first temperature change rate to reduce the indoor environment temperature to a first temperature. The first temperature is the deep sleep temperature, and the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value.

[0078] Specifically, in the sleeping stage, the cooling operation is performed according to the first temperature change rate (for example, the first temperature change rate is initially 0.1°C / 2min) until the temperature drops to the first temperature, for example, the preset temperature is T0, and the first preset temperature value is 1°C, that is, it drops to T 0 -1℃, the time to complete the cooling process according to the initial setting is 20min.

[0079] Figure 5 It is a method schematic diagram of another embodiment of the air conditioner control method provided by the present invention.

[0080] like Figure 5 As shown, according to another embodiment of the present invention, the air conditioner control method further includes step S140.

[0081] Step S140, when the target user is in the wake-up stage, during the first t time of the wake-up stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature reaches the set temperature of the air conditioner; during the remaining time of the wake-up stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the second temperature.

[0082] The second temperature is the wake-up temperature, which is equal to the sum of the set temperature of the air conditioner and the first preset temperature value. Specifically, when the target user is in the wake-up stage, this stage is divided into two sub-stages for control. The first sub-stage time is td (for example, initially 10 minutes). If the current indoor ambient temperature is not equal to the set temperature, that is, T≠T 0 , execute the second temperature change rate so that the indoor ambient temperature T = T 0 If the current indoor ambient temperature is not equal to the set temperature, that is, T = T0, no control is required and the temperature is maintained for a duration of td. The second sub-stage executes the second temperature change rate (initial 0.1°C / 1min) so that the indoor ambient temperature T = T 0 +1.0℃.

[0083] The above control of the present invention can refer to Figure 6 shown. Figure 6 FIG. 2 shows a sleep control temperature curve according to the present invention. Figure 6 As shown, the horizontal axis represents time and the vertical axis represents indoor temperature. In cooling mode, the initial set temperature is T 0 The overall control is divided into the falling asleep stage, the mid-sleep stage, and the awakening stage. In the falling asleep stage, the temperature is lowered according to the first temperature change rate until it reaches the deep sleep temperature (the first temperature is equal to the difference between the set temperature and the low preset temperature value); in the mid-sleep stage, the temperature is controlled according to the sleep stage detection result; when entering the awakening stage, the indoor temperature is equal to the set temperature in the first stage, and in the second stage, the indoor temperature reaches the awakening temperature (the second temperature is equal to the sum of the set temperature of the air conditioner and the first preset temperature value).

[0084] Figure 7 A sleep staging curve and a temperature control curve according to the present invention are shown.

[0085] The horizontal axis is the sleep time, which is 8 hours in total, and the temperature data is collected 10 times per hour. Of the two curves, curve 1 is the sleep stage curve detected by the radar in real time, and curve 2 is the collected temperature data curve. The left vertical axis represents the temperature in °C, and the right vertical axis represents the sleep stage. The temperature curve is based on Figure 6 The logic is executed, the first stage is cooling, the second stage is executed according to the detection results of sleep stages, and the third stage starts to heat up.

[0086] The present invention also provides a control device for an air conditioner. The air conditioner has a bio-radar module for collecting parameters of human activity status.

[0087] The bio-radar module includes: a radio frequency antenna, a radar chip and a high-speed main frequency MCU, which can extract human vital signs signals and obtain human activity status parameters. The bio-radar module can extract human activity status parameters such as distance, breathing rate, heart rate, signal strength (such as body movement status, body movement energy).

[0088] The air conditioning control system is developed by reading data from the bio-radar module through serial communication. For example, the bio-radar module is connected to the air conditioning control motherboard communication interface through pins. Figure 2 The figure shows the connection diagram between the biological radar module and the air conditioner mainboard. Figure 2 As shown, the air conditioner main control RXD is connected to the radar's RX through uart and connected to the RX antenna; the air conditioner main control TXD is connected to the radar's TX through uart and connected to the TX antenna; the main control power interface VDD is connected to the radar VCC, and the GNDs of the two are connected.

[0089] Through analysis and selection, the important pin definitions of the biological radar module used in the development are shown in Table 1:

[0090] Table 1

[0091] Pinout describe illustrate 1 VCC Input power voltage 3V~5.5V 2 GND Grounding 3 UART_TX Serial port sending 4 UART_RX Serial port receiving

[0092] Figure 8 FIG. 1 is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention. Figure 8 As shown, the air conditioner control device 100 includes: an acquisition unit 110 , a prediction unit 120 and a control unit 130 .

[0093] The acquisition unit 110 is used to acquire the current human activity state parameters of the target user when the target user is in the sleeping stage.

[0094] Specifically, the sleep stage is divided into the falling asleep stage, the sleeping stage and the waking stage. In the sleep stage, the first period of the preset time is the falling asleep stage, the second period of the preset time is the waking stage, and the middle period is the sleeping stage. For example, the sleep stage is 8 hours, and the three stages are divided according to 8 hours. The first 20 minutes of 8 hours are set as the falling asleep stage, and the temperature is lowered according to the temperature change rate 1. The last 20 minutes of 8 hours are set as the waking stage, and the control is executed according to the logic of the waking stage. The rest of the time (the period between the first 20 minutes and the last 20 minutes) is the sleeping stage. The current human activity state parameters of the target user can be detected by the bioradar module on the air conditioner. The human activity state parameters can specifically include: at least one of breathing, heart rate, distance (the distance from the bioradar antenna to the human chest), body movement state, and body movement energy.

[0095] The prediction unit 120 is used to input the human activity state parameters acquired by the acquisition unit into a pre-trained prediction model to predict the current sleep stage of the target user.

[0096] The air conditioner further includes a training unit (not shown) for training the prediction model. The prediction model is used to predict sleep stages. In a specific embodiment, the training unit trains the prediction model in the following manner:

[0097] Step S1, obtaining different human activity state parameters in different sleep stages as sample data.

[0098] In a specific implementation, the sleep stage of a person is divided into the awake stage, the light sleep stage, the eye movement stage and the deep sleep stage. The sleep stage of the human body changes continuously during sleep, and the body requires different temperatures in each stage. For example, the basis for setting the air conditioning temperature control logic may be:

[0099] Awake stage: In this state, the ambient temperature usually needs to be around 26-28℃.

[0100] REM sleep: REM sleep is a relatively independent stage of sleep, and the required environmental temperature is similar to that of the waking period.

[0101] Light sleep stage: The ambient temperature required during the light sleep stage is slightly lower than that during the waking stage.

[0102] Deep sleep: The ambient temperature required during deep sleep is lower than that of other stages.

[0103] Different human activity state parameters in different sleep stages are obtained in advance as sample data for training the prediction model.

[0104] Step S2, using the different human body state parameters as input data and the different sleep stages as output data, training a neural network model to obtain a prediction model for predicting sleep stages.

[0105] For any human activity state parameter, n signal features at m different moments are collected respectively to obtain m*n features of the human activity state parameter; the n signal features may specifically include: any n of the signal maximum value, signal minimum value, signal mean value, signal median value, and signal standard deviation.

[0106] Specifically, in the data processing process, in order to ensure the accuracy of the prediction results and the stability of the model operation, the feature analysis is as comprehensive as possible. For each human body state parameter, the sampled signal data can include the current time t, the previous time t-1, ..., and the earlier time tm-1, a total of n features of m categories (the specific time step can be determined according to actual needs, experimental results and availability), and the dimensional data shown in the following table in the three categories are collected respectively. Therefore, the model input data contains the original m*n features, and the output is the sleep stage category (here taking 4 categories as an example).

[0107] Train the multi-layer perceptron and use TensorFlow for training. Input layer: contains m*n inputs (depending on the specific radar needs, the inputs are signals such as breathing, heart rate, distance, body movement state, body movement energy, and their maximum signal value, minimum signal value, signal mean, signal median, signal standard deviation, etc.); Output layer: contains 4 neurons, and uses the softmax function to convert the activation value of the output layer neuron into a probability distribution. There are 3 hidden layers, which have 128, 64 and 32 neurons respectively. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer. The initial learning rate is set to 0.002, the number of training rounds is 150, and the batch size is 32. For specific neural network structure reference Figure 3 shown. Figure 3 A schematic diagram of a deep neural network model is shown.

[0108] The control unit 130 is used to control the indoor ambient temperature and / or control the air speed of the internal fan of the air conditioner and / or the opening of the fresh air fan according to the prediction of the current sleep stage of the target user by the prediction unit.

[0109] In a specific implementation, the control unit 130 controls the indoor environment temperature according to the predicted sleep stage of the target user, including the following situations:

[0110] (1) When it is predicted that the target user is currently in the sleep stage of the awake stage or the eye movement stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the set temperature.

[0111] Specifically, when the sleep stage is awake or eye movement, the initial set temperature is maintained, even if the indoor ambient temperature T is equal to the set temperature T 0 , that is, T = T 0 . Execute the second temperature change rate to make the indoor ambient temperature T equal to the set temperature T 0 The second temperature change rate, for example, may be initially 0.1°C / 1min.

[0112] (2) When it is predicted that the target user is currently in a light sleep stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the third temperature.

[0113] The third temperature is equal to the difference between the set temperature of the air conditioner and the second preset temperature value. Specifically, when the sleep stage is a light sleep stage, the indoor ambient temperature is controlled to decrease to the third temperature according to the second temperature change rate. For example, the second preset temperature difference is 0.5°C, that is, the indoor ambient temperature T=T0-0.5°C, and the second temperature change rate, for example, can be 0.1°C / 1min initially.

[0114] (3) When it is predicted that the target user is currently in a deep sleep stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to the first temperature.

[0115] The first temperature is the deep sleep temperature. The first temperature is equal to the difference between the set temperature of the air conditioner and the first preset temperature value. Specifically, when the sleep stage is the deep sleep stage, the indoor ambient temperature is controlled to drop to the first temperature according to the second temperature change rate. For example, the first preset temperature difference is 1°C, that is, the indoor ambient temperature T=T 0 -1.0°C, the second temperature change rate, for example, may be 0.1°C / 1min initially.

[0116] In a specific implementation, the control unit 130 controls the wind speed of the internal fan according to the predicted current sleep stage of the target user, including the following situations:

[0117] (1) When it is predicted that the target user is currently in the awake stage of sleep, the internal fan is controlled to operate according to the set wind speed.

[0118] For example, when the sleep stage is awake, the wind speed is controlled according to the original setting of the remote controller.

[0119] (2) When it is predicted that the target user is currently in a light sleep stage, a deep sleep stage, or an eye movement sleep stage, the internal fan is controlled to operate at a preset minimum wind speed.

[0120] For example, when the sleep stage is light sleep, deep sleep or REM sleep, keep the windshield silent.

[0121] In a specific implementation, the control unit 130 controls the start and stop of the fresh air blower according to the predicted sleep stage of the target user, including: when the predicted sleep stage of the target user is the awake stage or the eye movement stage, controlling the fresh air blower of the air conditioner to start. For example, when the sleep stage is the light sleep stage, the deep sleep stage or the eye movement stage, the fresh air switch is turned on.

[0122] Optionally, the control unit 130 is also used to: when the target user is in the sleeping stage, control the indoor ambient temperature according to a first temperature change rate to reduce the indoor ambient temperature to a first temperature, and the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value.

[0123] Specifically, in the sleeping stage, the cooling operation is performed according to the first temperature change rate (for example, the first temperature change rate is initially 0.1°C / 2min) until the temperature drops to the first temperature, for example, the preset temperature is T0, and the first preset temperature value is 1°C, that is, it drops to T 0 -1℃, the time to complete the cooling process according to the initial setting is 20min.

[0124] Optionally, the control unit 130 is further configured to: when the target user is in the wake-up stage, control the indoor ambient temperature according to the second temperature change rate during the first t time of the wake-up stage so that the indoor ambient temperature reaches the set temperature of the air conditioner; and control the indoor ambient temperature according to the second temperature change rate during the rest of the wake-up stage so that the indoor ambient temperature is equal to a second temperature. The second temperature is equal to the sum of the set temperature of the air conditioner and the first preset temperature value.

[0125] The second temperature is the wake-up temperature, which is equal to the sum of the set temperature of the air conditioner and the first preset temperature value. Specifically, when the target user is in the wake-up stage, this stage is divided into two sub-stages for control. The first sub-stage time is td (for example, initially 10 minutes). If the current indoor ambient temperature is not equal to the set temperature, that is, T≠T 0 , execute the second temperature change rate so that the indoor ambient temperature T = T 0 If the current indoor ambient temperature is not equal to the set temperature, that is, T = T0, no control is required and the temperature is maintained for a duration of td. The second sub-stage executes the second temperature change rate (initial 0.1°C / 1min) so that the indoor ambient temperature T = T 0 +1.0℃.

[0126] The present invention also provides a storage medium corresponding to the air conditioner control method, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0127] The present invention also provides an air conditioner corresponding to the air conditioner control method, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the computer program.

[0128] The present invention also provides an air conditioner corresponding to the control device of the air conditioner, comprising any of the control devices of the air conditioner described above.

[0129] The present invention also provides a computer program product corresponding to the air conditioner control method, comprising a computer program, and when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0130] Accordingly, the solution provided by the present invention can more accurately meet the human body's needs for environmental comfort in different sleep stages by monitoring the user's sleep stage status and adjusting the temperature and wind speed settings of the air conditioner accordingly.

[0131] According to the technical solution of the present invention, the sleep stage status is monitored in real time through the bio-radar technology combined with the deep learning model, and the air-conditioning temperature is automatically adjusted according to the stage, which directly affects the sleep quality and user comfort.

[0132] According to the technical solution of the present invention, temperature control is performed according to different temperature adjustment strategies according to the sleep stage status, providing a more detailed personalized experience compared to a single or fixed temperature setting.

[0133] Related technologies mostly rely on simple sensors to identify sleep states, and have low recognition accuracy and stability. The technical solution of the present invention utilizes deep learning to train a prediction model, which can improve the accuracy of sleep stage state recognition.

[0134] The related art usually only focuses on a single environmental factor. The technical solution of the present invention, in addition to temperature regulation, also includes wind speed and fresh air system control.

[0135] According to the technical solution of the present invention, the human body's sleep state is monitored in real time through bio-radar technology, and combined with a deep learning model, the air-conditioning temperature can be adjusted in real time according to the sleep stage state, providing personalized temperature control, thereby improving sleep comfort. This advantage is obtained.

[0136] According to the technical solution of the present invention, a biological radar module integrating a radio frequency antenna, a radar chip and a high-speed main frequency MCU is used to monitor and analyze the human body's sleep state in real time to achieve intelligent control.

[0137] According to the technical solution of the present invention, the user's sleep quality can be effectively improved; the biological radar monitoring, deep learning model and intelligent control logic are highly integrated to form a coordinated system.

[0138] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0142] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A method for controlling an air conditioner, characterized in that: include: When the target user is in the sleeping stage, obtaining the current human activity state parameters of the target user; Inputting the acquired human activity state parameters into a pre-trained prediction model to predict the current sleep stage of the target user; According to the prediction of the current sleep stage of the target user, the indoor ambient temperature is controlled, and / or the internal fan wind gear of the air conditioner and / or the opening of the fresh air fan is controlled.

2. The method according to claim 1, characterized in that Obtaining the current human activity state parameters of the target user includes: The current human activity state parameters of the target user are detected by the bio-radar module arranged on the air conditioner.

3. The method according to claim 1, characterized in that The prediction model is trained as follows: Obtain different human activity state parameters in different sleep stages as sample data; The different human body state parameters are used as input data, and the different sleep stages are used as output data to train a neural network model to obtain a prediction model for predicting sleep stages.

4. The method according to any one of claims 1 to 3, characterized in that: According to the prediction, the current sleep stage of the target user is obtained, and the indoor environment temperature is controlled, including: When it is predicted that the target user is currently in the sleep stage of the awake stage or the eye movement stage, the indoor environment temperature is controlled according to the second temperature change rate so that the indoor environment temperature is equal to the set temperature; When it is predicted that the target user is currently in a light sleep stage, the indoor ambient temperature is controlled according to the second temperature change rate so that the indoor ambient temperature is equal to a third temperature, and the third temperature is equal to the difference between the set temperature of the air conditioner and the second preset temperature value; When it is predicted that the target user is currently in a deep sleep stage, the indoor ambient temperature is controlled according to a second temperature change rate so that the indoor ambient temperature is equal to a first temperature, and the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value.

5. The method according to any one of claims 1 to 3, characterized in that: According to the prediction of the current sleep stage of the target user, the wind speed of the internal fan of the air conditioner is controlled, including: When it is predicted that the target user is currently in the awake stage of sleep, the internal fan is controlled to operate at a set wind speed; When it is predicted that the target user is currently in a light sleep stage, a deep sleep stage, or an eye movement stage, the internal fan is controlled to operate at a preset minimum wind speed.

6. The method according to any one of claims 1 to 3, characterized in that: According to the prediction of the current sleep stage of the target user, the fresh air fan of the air conditioner is controlled to be turned on, including: When it is predicted that the target user's current sleep stage is the awake stage or the eye movement stage, the fresh air fan of the air conditioner is controlled to turn on.

7. The method according to any one of claims 1 to 3, characterized in that: Also includes: When the target user is in the sleeping stage, the indoor ambient temperature is controlled according to the first temperature change rate to reduce the indoor ambient temperature to a first temperature, where the first temperature is equal to the difference between the set temperature of the air conditioner and a first preset temperature value; and / or, When the target user is in the awakening stage, the indoor ambient temperature is controlled according to the second temperature change rate during the first t time of the awakening stage, so that the indoor ambient temperature reaches the set temperature of the air conditioner; During the rest of the wake-up phase, the indoor ambient temperature is controlled at a second temperature change rate so that the indoor ambient temperature is equal to a second temperature, which is equal to the sum of the set temperature of the air conditioner and a first preset temperature value.

8. A control device for an air conditioner, characterized in that: include: An acquisition unit, used for acquiring a current human activity state parameter of the target user when the target user is in a sleeping stage; A prediction unit, configured to input the human activity state parameter acquired by the acquisition unit into a pre-trained prediction model to predict the current sleep stage of the target user; A control unit is used to obtain the current sleep stage of the target user according to the prediction of the prediction unit, control the indoor ambient temperature, and / or control the air damper of the air conditioner and / or the opening of the fresh air fan.

9. A storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the steps of any method described in claims 1-7 are implemented.

10. An air conditioner, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any method described in claims 1 to 7 when executing the program, or comprises the control device described in claim 8.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of any one of the methods of claims 1 to 7 when being executed by a processor.

Images