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

Abstract

The application provides an air conditioner and a control method, device, storage medium and computer program product thereof. The method comprises: obtaining a desired running time and a corresponding desired temperature of the air conditioner, or obtaining a set running time and a set temperature of the air conditioner; taking the desired temperature or the set temperature as a target temperature, and determining an advance start time of the air conditioner according to the target temperature; starting the air conditioner in advance according to the determined advance start time, and setting a set temperature to the target temperature; obtaining a predicted heat load removal trend curve to determine whether the indoor temperature can reach the target temperature at the desired running time or the set running time; and if it is determined that the target temperature cannot be reached, adjusting the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the desired running time or the set running time. The scheme provided by the application can accurately control the desired temperature of the user and improve the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the control field, and particularly to an air conditioner and a control method, device, storage medium and computer program product thereof. BACKGROUND

[0002] With the continuous development of science and technology and household appliances, people have higher demand for the intelligentization of household appliances. At present, the intelligentization of air conditioners mostly learns the setting habits of users, only reduces the trouble of manual setting, and is prone to inaccurate grasping of the expected temperature of users, affecting the user experience of air conditioner intelligentization. SUMMARY

[0003] The main purpose of the present application is to overcome the defects of the above-mentioned related technologies, and to provide an air conditioner and a control method, device, storage medium and computer program product thereof, to solve the problem of inaccurate control of the expected temperature of users in the related art.

[0004] In one aspect, the present application provides a control method of an air conditioner, comprising: obtaining an expected running time and a corresponding expected temperature of the air conditioner, or obtaining a setting running time and a setting temperature of the air conditioner; taking the expected temperature or the setting temperature as a target temperature, and determining an advance start time of the air conditioner according to the target temperature; starting the air conditioner in advance before the expected running time or the setting running time arrives according to the determined advance start time, and setting a set temperature of the air conditioner to the target temperature; obtaining a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature, to determine whether the indoor temperature can reach the target temperature at the expected running time or the setting running time according to the predicted heat load removal trend curve; and if it is determined that the indoor temperature cannot reach the target temperature at the expected running time or the setting running time, adjusting the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the expected running time or the setting running time.

[0005] Optionally, obtaining the expected running time and the corresponding expected temperature of the air conditioner comprises: collecting user behavior data of a user using the air conditioner; performing model training based on the collected user behavior data to obtain a prediction model for predicting the expected running time and the corresponding expected temperature of the air conditioner; and predicting the expected running time and the corresponding expected temperature of the air conditioner by using the prediction model.

[0006] Optionally, the advance start time of the air conditioner is determined according to the obtained expected temperature or the set temperature, including: calculating a room heat load of the room according to a room volume of the room and a temperature difference between the current indoor temperature and the target temperature; and calculating the advance start time of the air conditioner according to the calculated room heat load and input power and refrigerating capacity of the air conditioner.

[0007] Optionally, the method further includes: before determining the advance start time of the air conditioner according to the obtained expected temperature or the set temperature, obtaining a current outdoor environment parameter, and determining whether the current outdoor environment meets a preset condition according to the outdoor environment parameter; if it is determined that the current outdoor environment meets the preset condition, controlling an indoor door and / or window to be opened for ventilation, and the air conditioner is not started, or controlling the air conditioner to be started to blow air at a preset air outlet opening degree to maintain the current indoor temperature; and if it is determined that the current outdoor environment does not meet the preset condition, taking the expected temperature or the set temperature as a target temperature, and determining the advance start time of the air conditioner according to the target temperature.

[0008] Optionally, the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is obtained by: inputting the current first environment parameter, the indoor temperature and the target temperature into a pre-trained heat load removal trend prediction model to obtain the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature.

[0009] Optionally, if it is determined that the indoor temperature cannot reach the target temperature at the expected running time or the set running time, the set temperature of the air conditioner is adjusted to make the indoor temperature reach the target temperature at the expected running time or the set running time, including: if it is determined that the indoor temperature cannot reach the target temperature at the expected running time or the set running time, obtaining a heat load removal trend curve corresponding to each temperature value in a preset temperature range for adjusting the indoor temperature to the target temperature; selecting a heat load removal trend curve that can reach the target temperature at the expected running time or the set running time from the obtained heat load removal trend curves corresponding to each temperature in the preset temperature range for adjusting the indoor temperature to the target temperature, and adjusting the set temperature of the air conditioner to a temperature corresponding to the heat load removal trend curve.

[0010] Optionally, the heat load removal trend prediction model is trained by: obtaining heat load removal data for adjusting different indoor temperatures to different target temperatures under different second environment parameters as sample data; constructing a heat load removal trend prediction model, and performing model training based on the obtained sample data; adjusting model parameters by using a back propagation algorithm, and fixing the model parameters to obtain the heat load removal trend prediction model.

[0011] In another aspect, the application provides a control device for an air conditioner, comprising: an obtaining unit configured to obtain a desired operation time and a corresponding desired temperature of the air conditioner, or to obtain a set operation time and a set temperature of the air conditioner; a first determining unit configured to determine an advance start time of the air conditioner according to the desired temperature or the set temperature obtained by the obtaining unit as a target temperature; a control unit configured to start the air conditioner in advance before the desired operation time or the set operation time arrives according to the advance start time determined by the first determining unit, and set a set temperature of the air conditioner to the target temperature; a second determining unit configured to obtain a predicted heat load removal trend curve for adjusting an indoor temperature to the target temperature, and determine whether the indoor temperature can reach the target temperature at the desired operation time or the set operation time according to the predicted heat load removal trend curve; and an adjusting unit configured to adjust the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the desired operation time or the set operation time if the second determining unit determines that the indoor temperature cannot reach the target temperature at the desired operation time or the set operation time.

[0012] Optionally, the obtaining unit obtains the desired operation time and the corresponding desired temperature of the air conditioner by: collecting user behavior data of a user using the air conditioner; performing model training based on the collected user behavior data to obtain a prediction model for predicting the desired operation time and the corresponding desired temperature of the air conditioner; and predicting the desired operation time and the corresponding desired temperature of the air conditioner by using the prediction model.

[0013] Optionally, the first determining unit determines the advance start time of the air conditioner according to the desired temperature or the set temperature obtained by the obtaining unit by: calculating a room heat load of a room according to a room volume of the room and a temperature difference between a current indoor temperature and the target temperature; and calculating the advance start time of the air conditioner according to the calculated room heat load and an input power and a refrigerating capacity of the air conditioner.

[0014] Optionally, the control device further comprises a judging unit configured to obtain a current outdoor environment parameter and determine whether a current outdoor environment satisfies a preset condition according to the outdoor environment parameter before the first determining unit determines the advance start time of the air conditioner according to the obtained desired temperature or set temperature; and the control unit is further configured to: control an indoor door and / or window to be opened for ventilation if the judging unit determines that the current outdoor environment satisfies the preset condition, and the air conditioner is not started, or control the air conditioner to be started to blow air at a preset air outlet opening degree to maintain a current indoor temperature.

[0015] Optionally, the second determining unit obtains a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature by inputting the current first environmental parameter, the indoor temperature and the target temperature into a pre-trained heat load removal trend prediction model.

[0016] Optionally, the adjusting unit adjusts the set temperature of the air conditioner to reach the target temperature at the expected operation time or the set operation time if the second determining unit determines that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, including: if the second determining unit determines that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, obtaining a heat load removal trend curve corresponding to each temperature value in a preset temperature range of the target temperature for adjusting the indoor temperature to the target temperature; selecting a heat load removal trend curve that can reach the target temperature at the expected operation time or the set operation time from the obtained heat load removal trend curves corresponding to each temperature in the preset temperature range of the target temperature for adjusting the indoor temperature to the target temperature, and adjusting the set temperature of the air conditioner to the temperature corresponding to the heat load removal trend curve.

[0017] Optionally, the heat load removal trend prediction model is trained by the following steps: obtaining heat load removal data from different indoor temperatures to different target temperatures under different second environmental parameters as sample data; constructing a heat load removal trend prediction model and performing model training based on the obtained sample data; adjusting the model parameters using a back propagation algorithm, and fixing the model parameters to obtain the heat load removal trend prediction model.

[0018] In still another aspect, the present application provides a storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of any of the above-mentioned methods.

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

[0020] In still another aspect, the present application provides an air conditioner comprising the control device of any of the above-mentioned control devices.

[0021] In still another aspect, the present application provides a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the above-mentioned methods.

[0022] According to the technical scheme of the present application, the expected running time of the air conditioner and the corresponding expected temperature of the user are obtained by learning the user behavior, or the setting running time and the setting temperature set by the user are obtained, the expected temperature or the setting temperature is taken as the target temperature, the advance start time of the air conditioner is determined, and the air conditioner is started in advance according to the determined advance start time, so that the expected temperature of the user can be accurately controlled, and the user experience is improved.

[0023] According to the technical scheme of the present application, the predicted heat load removal trend curve is obtained, and the set temperature of the air conditioner is adjusted according to the predicted heat load removal trend curve, so that the indoor temperature reaches the target temperature at the expected running time or the setting running time.

[0024] According to the technical scheme of the present application, the heat load removal trend is controlled according to the heat load removal trend model, the temperature is accurately adjusted, and the energy saving control is realized while ensuring the comfortable temperature of the user. BRIEF DESCRIPTION OF DRAWINGS

[0025] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

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

[0027] Figure 2 a flowchart of a specific embodiment of the step of obtaining the expected running time of the air conditioner and the corresponding predicted target temperature is shown;

[0028] Figure 3 a flowchart of a specific embodiment of the step of determining the advance start time of the air conditioner according to the target temperature is shown;

[0029] Figure 4 a heat load removal trend curve according to a specific embodiment of the present application is shown;

[0030] Figure 5 a training flowchart of a heat load trend prediction model according to a specific embodiment of the present application is shown;

[0031] Figure 6 a heat load removal trend curve according to another specific embodiment of the present application is shown;

[0032] Figure 7 is a method schematic diagram of a specific embodiment of the control method of the air conditioner provided by the present application;

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

[0034] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions will be described clearly and completely below with reference to the specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work belong to the protection scope of the present application.

[0035] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0036] Figure 1 is a method schematic diagram of an embodiment of the control method of the air conditioner provided by the present application.

[0037] As shown in Figure 1 , according to an embodiment of the present application, the control method of the air conditioner at least includes steps S110, S120, S130, S140 and S150.

[0038] Step S110, obtaining the expected running time and the corresponding expected temperature of the air conditioner, or obtaining the set running time and the set temperature of the air conditioner.

[0039] In a specific embodiment, the expected running time and the corresponding expected temperature of the air conditioner are predicted according to the user behavior data of the user using the air conditioner. Figure 2 A flow chart of a specific embodiment of the step of obtaining the expected running time and the corresponding predicted target temperature of the air conditioner of the present application is shown. As shown in Figure 2 , it includes steps S111-S113.

[0040] Step S111, collecting the user behavior data of the user using the air conditioner.

[0041] Specifically, user behavior data of using the air conditioner is collected each time the air conditioner is operated. Preferably, permission for collecting user behavior data is obtained after the air conditioner is turned on each time, and the user behavior data is collected after the permission is obtained. For example, the permission for collecting user behavior data can be obtained by asking.

[0042] In step S112, a prediction model for predicting the expected operation time and the corresponding expected temperature of the air conditioner is obtained based on the collected user behavior data.

[0043] Preferably, when the collected user behavior data reaches the minimum required data amount for model training (i.e., the minimum data amount required for model training), the prediction model for predicting the expected operation time and the corresponding expected temperature of the air conditioner is obtained based on the collected user behavior data. The expected operation time and the corresponding expected temperature refer to the time (time point) at which the user expects the air conditioner to operate and the temperature that the user expects to reach at that time. The user behavior data can specifically include the air conditioner turning-on time, the air conditioner continuous use time, the set temperature, and the temperature adjustment time (the time required for adjusting the indoor temperature from the current temperature to the target temperature). The above user behavior data is used as the input data of the model, and the expected temperature of the user at any time is used as the output of the model, and a deep neural network model is trained to obtain the prediction model.

[0044] In step S113, the expected operation time and the corresponding expected temperature of the air conditioner are predicted by the prediction model.

[0045] Specifically, after the prediction model is trained, the expected operation time and the corresponding expected temperature of the air conditioner can be predicted by the prediction model.

[0046] The set operation time and the set temperature of the air conditioner refer to the expected operation time (i.e., the set operation time) and the expected temperature (i.e., the set temperature) set by the user. In a preferred embodiment, if the prediction model is trained, the target temperature of the air conditioner at different times is predicted by the prediction model, i.e., the temperature that the user may wish to set at any time is predicted by the model. If the prediction model is not trained (e.g., the collected user behavior data does not reach the minimum required data amount for model training), the set operation time and the set temperature of the air conditioner set by the user are obtained, i.e., the operation time and the target temperature set by the user are obtained.

[0047] In step S120, the expected temperature or the set temperature is used as the target temperature, and the advance start time of the air conditioner is determined according to the target temperature.

[0048] Preferably, before determining the advance start time of the air conditioner according to the target temperature, the current outdoor environment parameter is acquired, and it is determined whether the current outdoor environment meets a preset condition according to the outdoor environment parameter. If it is determined that the current outdoor environment meets the preset condition, the indoor door and / or window is controlled to be opened for ventilation, the air conditioner is not started, or the air conditioner is controlled to be started to blow air at a preset air outlet opening degree to maintain the current indoor temperature. If it is determined that the current outdoor environment does not meet the preset condition, the advance start time t of the air conditioner is determined according to the target temperature (i.e., the expected temperature or the set temperature).

[0049] In a specific embodiment, the preset condition includes at least one of the following conditions: whether the outdoor temperature is within a preset temperature range, whether the air pollution index is lower than a preset index threshold, and / or whether the outdoor humidity is within a preset humidity range. Specifically, the outdoor environment parameter is acquired, which can specifically include the indoor environment temperature, the indoor relative humidity, and the air pollution index. It is determined whether the current outdoor environment meets the standard, and the detailed rules are as follows: it is determined whether the outdoor temperature is within a preset temperature range, i.e., whether the outdoor temperature is a suitable temperature for human body; it is determined whether the air quality meets the standard, i.e., whether the air pollution index is lower than a preset index threshold, for example, whether the air pollution index ≤ 100 is met; it is determined whether the outdoor humidity meets the standard, i.e., whether the outdoor humidity is within a preset humidity range, for example, whether the outdoor humidity is within a normal humidity range (e.g., 40%-80%). If all indicators of the current outdoor environment meet the standard, and the indoor door and / or window is controllable, the window and / or door is controlled to be opened for ventilation, and the air conditioner is not started. If all indicators of the current outdoor environment meet the standard, but the indoor door and / or window is not controllable, the indoor fan of the air conditioner is controlled to blow air at a preset air outlet opening degree to maintain the current indoor temperature.

[0050] Figure 3 A flowchart of a specific embodiment of the step of determining the advance start time of the air conditioner according to the target temperature is shown. As shown in Figure 3 the step of determining the advance start time of the air conditioner according to the target temperature includes the following steps:

[0051] In step S121, the room heat load of the room is calculated according to the room volume of the room and the temperature difference between the current indoor temperature and the target temperature.

[0052] In one specific embodiment, the room heat load = room volume x air density x specific heat capacity x temperature difference. The temperature difference is the temperature difference between the current indoor temperature and the target temperature, i.e. the temperature difference between the current indoor temperature and the desired temperature, or the temperature difference between the current indoor temperature and the set temperature. The room volume can be obtained in advance, for example by a user setting the room volume, or by detecting the length, width and height of the room to calculate the room volume.

[0053] Step S122, according to the calculated room heat load and the input power and refrigerating capacity of the air conditioner, calculate the advance start time of the air conditioner.

[0054] Specifically, according to the calculated room heat load of the room, calculate the time T required for the air conditioner to adjust the room from the current indoor temperature to the target temperature (the desired temperature or the set temperature) in the normal mode (for example, the air conditioner runs at rated power):

[0055] In one specific embodiment, the time T1 required for the air conditioner to adjust the room from the current indoor temperature to the target temperature in the normal mode is calculated according to the following formula:

[0056]

[0057] According to the energy efficiency ratio, when the indoor temperature approaches the target temperature, the efficiency is the highest, the air conditioning system is in a higher energy efficiency ratio state, and the overall power consumption is lower, therefore, the time t required for the air conditioner to adjust the room from the current indoor temperature to the target temperature (the desired temperature or the set temperature) in the energy saving mode (for example, the air conditioner runs at a preset proportion of rated power, for example, at 80% of rated power) is:

[0058]

[0059] Therefore, according to the room heat load of the room and the input power and refrigerating capacity of the air conditioner, the time required for the air conditioner to adjust the room from the current indoor temperature to the target temperature, i.e. the time t of advance starting the air conditioner, can be obtained:

[0060]

[0061] Step S130, according to the determined advance start time, start the air conditioner in advance before the desired operation time or the set operation time arrives, and set the set temperature of the air conditioner to the target temperature.

[0062] Specifically, after obtaining the time t for turning on the air conditioner in advance, the air conditioner is turned on in advance according to the obtained expected running time or the set running time, and according to the determined time t for turning on the air conditioner in advance, that is, the air conditioner is turned on t in advance relative to the predicted expected running time or the obtained set running time, and the set temperature of the air conditioner is set to the target temperature.

[0063] Step S140: Obtain the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature, so as to determine whether the indoor temperature can reach the target temperature at the expected operating time or the set operating time based on the predicted heat load removal trend curve.

[0064] In one specific implementation, the current first environmental parameter, indoor temperature, and target temperature are input into a pre-trained heat load removal trend prediction model to predict a heat load removal trend curve that will adjust the indoor temperature to the target temperature. Preferably, after the air conditioner is turned on, the predicted heat load removal trend curve that will adjust the indoor temperature to the target temperature is acquired at preset time intervals, and the indoor temperature is determined based on the predicted heat load removal trend curve at the desired operating time or the set operating time to whether the target temperature can be reached. For example, the current first environmental parameter, indoor temperature, and target temperature are input into a pre-trained heat load removal trend prediction model at preset time intervals to predict a heat load removal trend curve that will adjust the indoor temperature to the target temperature. For example, using... As one cycle, turn on the air conditioner and run it at the target temperature, in advance. When the time is right, the heat load change trend is predicted. The current first environmental parameter, indoor temperature and target temperature are input into the pre-trained heat load removal trend prediction model to predict the heat load removal trend curve that will adjust the indoor temperature to the target temperature.

[0065] In one specific embodiment, the first environmental parameter includes at least one of the following: location, climate type, sunshine duration, and outdoor temperature. The heat load removal trend prediction model is used to predict the heat load removal trend curve for adjusting the indoor temperature to any temperature under the control of the air conditioner; that is, to predict the heat load removal amount required to adjust the indoor temperature to any temperature over time. The heat load removal amount is the amount of heat removed required to adjust the indoor temperature to any temperature. The current first environmental parameter, indoor temperature, and target temperature are input into the heat load removal trend prediction model, and the model outputs the heat load removal trend curve for adjusting the indoor temperature to the target temperature, where the target temperature is the desired temperature or the set temperature.

[0066] In an embodiment, the heat load removal trend prediction model is trained by the following steps:

[0067] In step S1, sample data of heat load removal from different indoor temperatures to different target temperatures under different second environment parameters is obtained.

[0068] The second environment parameters include at least one of a region, a climate type, a sunshine time, and an outdoor temperature. The heat load removal data is specifically the amount of heat load removal (i.e., the amount of heat to be removed) required for removing heat from different indoor temperatures to different target temperatures under different second environment parameters. For example, heat load removal data corresponding to different regions, different climate types, different sunshine times, different indoor temperatures, different outdoor temperatures, and different target temperatures is obtained.

[0069] Figure 4 A heat load removal trend curve according to an embodiment of the present application is shown. Referring to FIG. 1, the horizontal axis represents time, and the vertical axis represents the amount of removed heat load (unit: KJ). a is a predicted heat load removal trend curve, and b is an actual heat load removal trend curve. Figure 4

[0070] In step S2, a heat load removal trend prediction model is constructed, and model training is performed based on the obtained sample data.

[0071] In an embodiment, a Transformer neural network model is constructed using TensorFlow, and an input layer, a hidden layer, and an output layer of the model are designed. Different environment parameters, indoor temperatures, and target temperatures in the sample data are used as inputs of the model, and the amount of heat load removal is used as a target output of the model, and neural network model training is performed.

[0072] Preferably, after obtaining the sample data, the obtained sample data is preprocessed to obtain a standard sample data set for model training. The preprocessing may, for example, include data cleaning of the sample data, maximum and minimum value normalization of sample data with inconsistent dimensions, interpolation filling or similar filling for missing values, and deletion or replacement of abnormal values to obtain a standard sample data set, and the heat load removal model is trained using the standard sample data set.

[0073] Specifically, a mean squared error loss function tf.keras.losses.MeanSquaredError (MSE) is used to measure the difference between the model output and the true label.

[0074]

[0075] ​Wherein, y1 is the true value, y2 is the predicted value output by the model, and the two are input into the loss function to measure the difference.

[0076] Then, the model is trained on the training set using the fit function: model.fit(train_data, epochs=epochs, validation_data=val_data).

[0077] Preferably, the Meta-Self-Supervised Learning learning method is embedded, and the model is pre-trained using self-supervised learning to learn the feature representation of the data, and then trained on multiple tasks under the meta-learning framework to optimize the model parameters and quickly adapt to new tasks.

[0078] Step S3, adjust the model parameters using the back propagation algorithm, fix the model parameters, and obtain the heat load removal trend prediction model.

[0079] Specifically, the output deviation of the actual output of the model from the target value is calculated, and it is judged whether the deviation is within the allowed range; if the output deviation q is within the allowed range, the training is ended, the value of the model parameter is determined, and the model is output. If the output deviation q is not within the allowed range, the parameter error is calculated, the error gradient is calculated, the weight is updated, and the model design and model training are returned to be performed again.

[0080] Preferably, after obtaining the heat load removal trend prediction model, the performance of the model on the validation set is monitored and evaluated using model.evaluate(test_data).

[0081] The training process of the heat load removal trend prediction model described above can also refer to Figure 5 . Figure 5 A training flowchart of a heat load trend prediction model according to a specific embodiment of the present application is shown. As Figure 5 shown, heat load removal data corresponding to different climates, different sunshine times, different indoor and outdoor temperatures, and different refrigeration temperatures in different regions are collected; the data is preprocessed to obtain a standard data set; a Transformer neural network model is selected and constructed using TensorFlow, the input layer, hidden layer, and output layer of the model are designed, and the training model is trained; the loss is calculated and the parameters are updated, and the deviation between the target value and the actual value is calculated; if the output deviation is not within the allowed range, the training is ended, the weight and other related parameters are fixed, and the model is output; if the output deviation is not within the allowed range, the model design is returned to be performed again.

[0082] According to the determined early start time, after the air conditioner is started early before the expected operation time or the set operation time, the air conditioner is controlled to operate according to the target temperature (i.e., the expected temperature or the set temperature). Before the expected operation time or the set operation time, every preset time, the current first environmental parameter, indoor temperature and target temperature are input into the pre-trained heat load removal trend prediction model to obtain a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature. According to the predicted heat load removal trend curve, it is determined whether the indoor temperature can reach the target temperature at the expected operation time or the set operation time.

[0083] For example, Figure 6 A heat load removal trend curve according to another specific embodiment of the present application is shown. The horizontal axis represents time, and the vertical axis represents the amount of removed heat load (unit: KJ). If it is predicted that the current user wants the indoor temperature to reach 26℃ at 18:00, 270 KJ of heat load needs to be removed. The current time is 17:00, the predicted heat load removal trend curve is obtained by the model, and it is determined whether the indoor temperature can reach 26℃ at 18:00 according to the obtained predicted heat load removal trend curve (curve 1 in the middle). If the amount of removed heat load can reach 270 KJ at 18:00 according to the predicted heat load removal trend curve, that is, the user's expected temperature (target temperature) can be reached, the original set parameters are maintained unchanged. Figure 6

[0084] Step S150, if it is determined that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, the set temperature of the air conditioner is adjusted to make the indoor temperature reach the target temperature at the expected operation time or the set operation time.

[0085] In one specific embodiment, if it is determined that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, the heat load removal trend curves corresponding to each temperature value in the preset temperature range for adjusting the indoor temperature to the target temperature are obtained. In the obtained heat load removal trend curves corresponding to each temperature in the preset temperature range for adjusting the indoor temperature to the target temperature, the heat load removal trend curve that can reach the target temperature at the expected operation time or the set operation time is selected, and the set temperature of the air conditioner is adjusted to the temperature corresponding to the heat load removal trend curve.

[0086] ​Specifically, if it is determined that the indoor temperature can reach the target temperature during the expected operating time or the set operating time, the current setting parameters of the air conditioner remain unchanged; if it is determined that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, the heat load removal trend curve corresponding to each temperature value within the preset temperature range of the target temperature is obtained.

[0087] That is, if the predicted heat load removal trend curve cannot reach the desired temperature at the user's desired time (i.e., the desired running time or the set running time), the heat load removal trend curve in the temperature range near the current target temperature is recalculated, the heat load curve that can reach the desired temperature at the user's desired time is selected, and the set temperature of the air conditioner is adjusted to the temperature corresponding to the heat load removal trend curve.

[0088] For example, if a user wants the room temperature to reach 26°C by 6:00 PM, 270 kJ of heat load needs to be removed. (Reference) Figure 6 As shown, at 17:00, the current air conditioner setting temperature (desired temperature) is 26℃. Curve 1 is the predicted heat load removal trend curve for the target temperature of 26℃. According to this curve, it is predicted that 270KJ cannot be reached at 18:00. Therefore, the heat load removal trend curves of temperatures within 2℃ of 26℃ (such as 24℃ and 25℃) as the target temperature are obtained. By comparison, it is found that curve 2 (24℃) can reach 270KJ at 18:00, while curve 3 (25℃) cannot reach 270KJ at 18:00. Therefore, the air conditioner setting temperature is adjusted to 24℃.

[0089] Furthermore, once the indoor temperature reaches the target temperature, the air conditioner's set temperature is adjusted back to the target temperature. That is, after the temperature reaches the user's desired temperature, the air conditioner temperature is set back to the desired temperature, and the compressor reduces its power. When the indoor temperature rises slightly due to external heat input (such as heat emitted by people or equipment), the air conditioner will briefly start the compressor to remove a small amount of heat load, maintaining the temperature at the desired level.

[0090] Historical data and user-adjusted settings are all recorded in a database that collects user behavior data. This data will be used to train and adjust the model, making the output more relevant to users' lives. If users frequently adjust certain settings, the system will learn and adjust its algorithm accordingly.

[0091] To clearly illustrate the technical solution of the present invention, the execution flow of the air conditioner control method provided by the present invention will be described below with reference to a specific embodiment.

[0092] Figure 7 This is a schematic diagram of a specific embodiment of the air conditioner control method provided by the present invention. Figure 7As shown, after the air conditioner is turned on, the system queries and obtains user data permissions; it collects user behavior data (air conditioner on / off time, temperature and airflow adjustment frequency, etc.) to reach the minimum training requirement for model training, and then trains the model to predict the user's setting preferences. If the current user model is trained, it directly enters intelligent mode, using the model to predict the user's desired temperature setting at any given time. If the current user model is not trained, the user sets the desired running time and desired temperature range. The system acquires indoor and outdoor temperatures and environmental indices. If the current outdoor environment meets the standards, detailed rules are as follows: including whether the temperature is suitable for the human body and whether the air quality meets the standards. If all indicators of the current outdoor environment meet the standards and doors and windows can be intelligently controlled, then windows are opened for ventilation, and the air conditioner is not turned on; otherwise, the fan is used to maintain a stable temperature. If the outdoor environmental index does not meet the standards, the system calculates the time t before the air conditioner is turned on, and turns on the air conditioner t time in advance according to the user's desired time. This is done within a fixed period (here, t is used as the reference point). Taking one cycle as an example, in At that time, the predicted heat load change curve is obtained based on the heat load removal trend model. If the predicted temperature can be reached at the expected time, the current setting parameters remain unchanged; if the predicted temperature cannot be reached at the expected time, the heat load trend curve for the temperature range near the current setting temperature is recalculated, and the heat load curve that can reach the expected temperature at the user's expected time is selected, and the air conditioning temperature is adjusted to the temperature corresponding to that heat load curve. time, Repeat the above steps at all times. Once the temperature reaches the user's desired temperature, set the air conditioner temperature back to the desired temperature. Record the setting data for training and adjusting the prediction model.

[0093] Figure 8 This is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention. Figure 8 As shown, the control device 100 of the air conditioner includes: an acquisition unit 110, a first determination unit 120, a control unit 130, a second determination unit 140, and an adjustment unit 150.

[0094] The acquisition unit 110 is used to acquire the expected operating time and corresponding expected temperature of the air conditioner, or to acquire the set operating time and set temperature of the air conditioner.

[0095] In one specific implementation, the expected operating time and corresponding expected temperature of the air conditioner are predicted based on user behavior data of the user using the air conditioner. Specifically, user behavior data of the user using the air conditioner is collected; a model is trained based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and corresponding expected temperature of the air conditioner; the expected operating time and corresponding expected temperature of the air conditioner are predicted using the prediction model.

[0096] Specifically, user behavior data of using the air conditioner is collected each time the air conditioner is operated. Preferably, the permission for collecting user behavior data is obtained after the air conditioner is turned on each time, and the user behavior data is collected after the permission is obtained. For example, the permission for collecting user behavior data can be obtained by asking.

[0097] When the collected user behavior data reaches the minimum required data amount for model training (i.e., the minimum data amount required for model training), model training is performed based on the collected user behavior data to obtain a prediction model for predicting the expected operation time of the air conditioner and the corresponding expected temperature. The expected operation time and the corresponding expected temperature refer to the time (time point) at which the user expects the air conditioner to be operated and the temperature that the user expects to reach at that time; the user behavior data can specifically include: air conditioner turning-on time, air conditioner continuous use time, set temperature, temperature adjustment time (time required for adjusting the indoor temperature from the current temperature to the target temperature). The above user behavior data is used as the input data of the model, and the expected temperature of the user at any time is used as the output of the model, and deep neural network model training is performed to obtain the prediction model.

[0098] After the prediction model is trained, the expected operation time of the air conditioner and the corresponding expected temperature can be predicted by the prediction model. The set operation time and the set temperature of the air conditioner refer to the expected operation time (i.e., set operation time) and the expected temperature (i.e., set temperature) set by the user. In a preferred embodiment, if the current prediction model is trained, the target temperature of the air conditioner at different times is predicted by the prediction model, i.e., the temperature that the user may wish to set at any time is predicted by the model. If the prediction model is not trained (for example, the collected user behavior data does not reach the minimum required data amount for model training), the set operation time and the set temperature of the air conditioner set by the user are obtained, i.e., the operation time and the target temperature set by the user.

[0099] The first determination unit 120 is configured to determine the advance start time of the air conditioner according to the target temperature obtained by the obtaining unit.

[0100] Preferably, the device 100 further comprises a judging unit (not shown). The judging unit is configured to acquire a current outdoor environment parameter before the first determining unit determines the pre-start time of the air conditioner according to the acquired expected temperature or the set temperature, and determine whether the current outdoor environment meets a preset condition according to the outdoor environment parameter; and the control unit 130 is further configured to: if the judging unit determines that the current outdoor environment meets the preset condition, control the indoor door and / or window to be opened for ventilation, and the air conditioner is not started, or control the air conditioner to be started to blow air at a preset air volume to maintain the current indoor temperature; and if the judging unit determines that the current outdoor environment does not meet the preset condition, take the expected temperature or the set temperature as a target temperature to determine the pre-start time t of the air conditioner.

[0101] In a specific embodiment, the preset condition comprises at least one of the following conditions: whether the outdoor temperature is within a preset temperature range, whether the air pollution index is lower than a preset index threshold, and / or whether the outdoor humidity is within a preset humidity range. Specifically, the outdoor environment parameter is acquired, and the outdoor environment parameter can specifically include: an indoor environment temperature, an indoor relative humidity, and an air pollution index. It is determined whether the current outdoor environment meets the standard, and the detailed rules are as follows: it is determined whether the outdoor temperature is within a preset temperature range, i.e., whether the outdoor temperature is a suitable temperature for the human body; it is determined whether the air quality meets the standard, i.e., whether the air pollution index is lower than a preset index threshold, for example, whether the air pollution index ≤ 100 is met; it is determined whether the outdoor humidity meets the standard, i.e., whether the outdoor humidity is within a preset humidity range, for example, whether the outdoor humidity is within a normal humidity range (e.g., 40%-80%). If all indicators of the current outdoor environment meet the standard, and the indoor door and / or window are controllable, the window and / or door are controlled to be opened for ventilation, and the air conditioner is not started. If all indicators of the current outdoor environment meet the standard, but the indoor door and / or window are not controllable, the indoor fan of the air conditioner is controlled to blow air at a preset air volume to maintain the current indoor temperature.

[0102] In a specific embodiment, the first determining unit 120 determines the pre-start time of the air conditioner according to the target temperature, and the step comprises: calculating a room heat load of a room in which the air conditioner is located according to a room volume of the room and a temperature difference between the current indoor temperature and the target temperature; and calculating the pre-start time of the air conditioner according to the calculated room heat load and an input power and a refrigerating capacity of the air conditioner.

[0103] In one specific embodiment, the room heat load = room volume x air density x specific heat capacity x temperature difference. The temperature difference is the temperature difference between the current indoor temperature and the target temperature, i.e. the temperature difference between the current indoor temperature and the desired temperature, or the temperature difference between the current indoor temperature and the set temperature. The room volume can be obtained in advance, for example by a user setting the room volume, or by detecting the length, width and height of the room to calculate the room volume.

[0104] According to the calculated room heat load of the room, the time T required for the air conditioner to adjust the room from the current indoor temperature to the target temperature (the desired temperature or the set temperature) in the normal mode (e.g. the air conditioner running at rated power) is calculated:

[0105] In one specific embodiment, the time T1 required for the air conditioner to adjust the room from the current indoor temperature to the target temperature in the normal mode is calculated according to the following formula:

[0106]

[0107] According to the energy efficiency ratio, the efficiency is highest when the indoor temperature approaches the target temperature, the air conditioning system is in a higher energy efficiency ratio state, and the overall power consumption is lower. Therefore, the time t required for the air conditioner to adjust the room from the current indoor temperature to the target temperature (the desired temperature or the set temperature) in the energy saving mode (e.g. the air conditioner running at a preset proportion of rated power, e.g. 80% of rated power) is:

[0108]

[0109] Therefore, according to the room heat load of the room and the input power and refrigeration capacity of the air conditioner, the time required for the air conditioner to adjust the room from the current indoor temperature to the target temperature, i.e. the time t of starting the air conditioner in advance, can be obtained:

[0110]

[0111] The control unit 130 is configured to start the air conditioner in advance before the desired operation time or the set operation time arrives according to the start time in advance determined by the first determination unit 120, and set the set temperature of the air conditioner to the target temperature.

[0112] Specifically, after the time t of starting the air conditioner in advance is obtained, the air conditioner is started in advance according to the obtained expected running time or the set running time and the determined time t of starting the air conditioner in advance, that is, the air conditioner is started t time in advance relative to the expected running time or the set running time, and the set temperature of the air conditioner is set to the target temperature.

[0113] The second determination unit 140 is configured to obtain a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature, and determine whether the indoor temperature can reach the target temperature at the expected running time or the set running time according to the predicted heat load removal trend curve.

[0114] In a specific embodiment, the current first environmental parameter, the indoor temperature and the target temperature are input into a pre-trained heat load removal trend prediction model to predict a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature. Preferably, after the air conditioner is started, the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is obtained every preset time, and whether the indoor temperature can reach the target temperature at the expected running time or the set running time is determined according to the predicted heat load removal trend curve. For example, the current first environmental parameter, the indoor temperature and the target temperature are input into the pre-trained heat load removal trend prediction model every preset time to predict a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature.

[0115] The predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature. For example, the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is obtained every preset time. The air conditioner is started and runs at the target temperature for one period, and the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted at the time t in advance. The air conditioner is started and runs at the target temperature for one period, and the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted at the time t in advance.

[0116] In a specific embodiment, the first environmental parameter includes at least one of a region, a climate type, a sunshine time and an outdoor temperature. The heat load removal trend prediction model is configured to predict a heat load removal trend curve for adjusting the indoor temperature to an arbitrary temperature under the adjustment of the air conditioner, that is, to predict a curve of the heat load removal amount required for adjusting the indoor temperature to an arbitrary temperature with time. The heat load removal amount is the heat amount required for adjusting the indoor temperature to an arbitrary temperature. The current first environmental parameter, the indoor temperature and the target temperature are input into the heat load removal trend prediction model, and a heat load removal trend curve for adjusting the indoor temperature to the target temperature is output, the target temperature being the expected temperature or the set temperature.

[0117] In an embodiment, the heat load removal trend prediction model is trained by the following steps:

[0118] In step S1, sample data is obtained by acquiring heat load removal data from different indoor temperature adjustments to different target temperatures under different second environment parameters.

[0119] The second environment parameters include at least one of a region, a climate type, a sunshine time, and an outdoor temperature. The heat load removal data is specifically the amount of heat load removal (i.e., the amount of heat to be removed) required for adjusting from different indoor temperatures to different target temperatures under different second environment parameters. For example, heat load removal data corresponding to different regions, different climate types, different sunshine times, different indoor temperatures, different outdoor temperatures, and different target temperatures is obtained.

[0120] Figure 4 A heat load removal trend curve according to an embodiment of the present application is shown. Referring to FIG. 2, the horizontal axis represents time, and the vertical axis represents the amount of removed heat load (unit: KJ). a is a predicted heat load removal trend curve, and b is an actual heat load removal trend curve. Figure 4

[0121] In step S2, a heat load removal trend prediction model is constructed, and model training is performed based on the obtained sample data.

[0122] In an embodiment, a Transformer neural network model is constructed using TensorFlow, and an input layer, a hidden layer, and an output layer of the model are designed. Different environment parameters, indoor temperatures, and target temperatures in the sample data are used as inputs of the model, and the amount of heat load removal is used as a target output of the model, and neural network model training is performed.

[0123] Preferably, after obtaining the sample data, the obtained sample data is preprocessed to obtain a standard sample data set for model training. The preprocessing may, for example, include data cleaning of the sample data, maximum and minimum normalization of sample data with inconsistent dimensions, interpolation filling or similar filling for missing values, and deletion or replacement of abnormal values to obtain a standard sample data set, and the heat load removal model is trained using the standard sample data set.

[0124] Specifically, a mean squared error loss function tf.keras.losses.MeanSquaredError (MSE) is used to measure the difference between the model output and the true label.

[0125]

[0126] ​Wherein, y1 is the true value, y2 is the predicted value output by the model, and the difference is measured by inputting both into the loss function.

[0127] Then, the model is trained on the training set using the fit function: model.fit(train_data, epochs=epochs, validation_data=val_data).

[0128] Preferably, the Meta-Self-Supervised Learning learning method is embedded, and the model is pre-trained using self-supervised learning to learn the feature representation of the data, and then trained on multiple tasks under the meta-learning framework to optimize the model parameters and quickly adapt to new tasks.

[0129] Step S3, adjust the model parameters using the back propagation algorithm, fix the model parameters, and obtain the heat load removal trend prediction model.

[0130] Specifically, the output deviation of the actual output of the model and the target value is calculated, and it is judged whether the deviation is within the allowed range; if the output deviation q is within the allowed range, the training is ended, the value of the model parameter is determined, and the model is output. If the output deviation q is not within the allowed range, calculate the parameter error, find the error gradient, update the weight, and return to redesign the model and train the model.

[0131] Preferably, after obtaining the heat load removal trend prediction model, the performance of the model on the validation set is monitored and evaluated using model.evaluate(test_data).

[0132] After the determined advance start time, the air conditioner is started in advance before the expected running time or the set running time arrives. According to the target temperature (i.e. the expected temperature or the set temperature), the air conditioner is controlled to run. Before the expected running time or the set running time arrives, every preset time, the current first environmental parameter, indoor temperature and target temperature are input into the pre-trained heat load removal trend prediction model to predict the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature. According to the predicted heat load removal trend curve, it is determined whether the indoor temperature can reach the target temperature at the expected running time or the set running time.

[0133] For example, Figure 6A heat load removal trend curve according to another embodiment of the present application is shown. The horizontal axis represents time, and the vertical axis represents the amount of removed heat load (unit: KJ). If it is predicted that the current user wants the indoor temperature to reach 26°C at 18:00, 270 KJ of heat load needs to be removed. The current time is 17:00, the predicted heat load removal trend curve is predicted by the model, and it is determined according to the obtained predicted heat load removal trend curve (curve 1) whether the indoor temperature can reach 26°C at 18:00. If the amount of removed heat load at 18:00 can reach 270 KJ according to the predicted heat load removal trend curve, that is, the user's expected temperature (target temperature) can be reached, the original set parameters are maintained unchanged. Figure 6

[0134] The adjusting unit 150 is configured to adjust the set temperature of the air conditioner so that the indoor temperature reaches the target temperature at the expected operation time or the set operation time if the second determining unit determines that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time.

[0135] In one embodiment, the adjusting unit 150 adjusts the set temperature of the air conditioner so that the indoor temperature reaches the target temperature at the expected operation time or the set operation time if the second determining unit 140 determines that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, including: if the second determining unit determines that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, obtaining a heat load removal trend curve corresponding to each temperature value in a preset temperature range for adjusting the indoor temperature to the target temperature; selecting a heat load removal trend curve that can reach the target temperature at the expected operation time or the set operation time from the obtained heat load removal trend curves corresponding to each temperature in the preset temperature range for adjusting the indoor temperature to the target temperature, and adjusting the set temperature of the air conditioner to the temperature corresponding to the heat load removal trend curve.

[0136] Specifically, if it is determined that the indoor temperature can reach the target temperature at the expected operation time or the set operation time, the current set parameters of the air conditioner remain unchanged; if it is determined that the indoor temperature cannot reach the target temperature at the expected operation time or the set operation time, a heat load removal trend curve corresponding to each temperature value in a preset temperature range for adjusting the indoor temperature to the target temperature is obtained.

[0137] ​That is, if the predicted heat load removal trend curve cannot reach the expected temperature at the user's desired time (i.e. the expected running time or the set running time), the heat load removal trend curve in the temperature range near the current target temperature is recalculated, the heat load curve that can reach the expected temperature at the user's desired time is selected, and the set temperature of the air conditioner is adjusted to the temperature corresponding to the heat load removal trend curve.

[0138] For example, the current user wants the room temperature to reach 26℃ at 18:00, and needs to remove a heat load of 270KJ. Referring to FIG. 1, at this time, it is 17:00, the current set temperature (expected temperature) of the air conditioner is 26℃, and curve 1 is the predicted heat load removal trend curve with a target temperature of 26℃. According to the curve, it is predicted that 270KJ cannot be reached at 18:00, so the heat load removal trend curves with temperatures (such as 24℃ and 25℃) near 26℃ within 2℃ are obtained as target temperatures, and it is obtained by comparison that curve 2 (24℃) can reach 270KJ at 18:00, and curve 3 (25℃) cannot reach 270KJ at 18:00, so the set temperature of the air conditioner is adjusted to 24℃. Figure 6

[0139] Further, after the indoor temperature reaches the target temperature, the set temperature of the air conditioner is adjusted back to the target temperature. That is, after the temperature reaches the expected temperature of the user, the temperature of the air conditioner is set back to the expected temperature, and the power of the compressor is reduced. When the indoor temperature slightly rises due to external heat input (such as heat emitted by people or equipment), the air conditioner will temporarily start the compressor to remove a small amount of heat load, so that the temperature is maintained at the expected temperature.

[0140] The historical data and the set data manually adjusted by the user in subsequent use are all counted into the database for collecting user behavior data, and the subsequent model will be trained and adjusted to make the output result closer to the user's life. If the user frequently adjusts some settings, the system will learn and adjust the algorithm.

[0141] The application also provides a storage medium corresponding to the control method of the air conditioner, which stores a computer program, and the computer program is executed by a processor to realize the steps of the method.

[0142] The application also provides an air conditioner corresponding to the control method of the air conditioner, which comprises a processor, a memory, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to realize the steps of the method.

[0143] The application also provides an air conditioner corresponding to the control device of the air conditioner, which comprises the control device.

[0144] ​The application also provides a computer program product corresponding to the control method of the air conditioner, comprising a computer program, which realizes the steps of any of the foregoing methods when executed by a processor.

[0145] Accordingly, the scheme provided by the application can accurately control the expected temperature of the user by learning the user behavior to obtain the expected air conditioner running time and the corresponding expected temperature, and improve the user experience. The predicted heat load removal trend curve is obtained, and the set temperature of the air conditioner is adjusted according to the predicted heat load removal trend curve, so that the indoor temperature reaches the target temperature at the expected running time or the set running time. According to the heat load removal trend model, the heat load removal trend is controlled, the temperature is accurately adjusted, and energy saving control is realized while ensuring the comfortable temperature of the user.

[0146] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored on or transferred over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Also, each of the functions can be implemented as a separate process or combined as a single process. Further, the functions can be implemented at least in part outside an associated processor or individual functional units.

[0147] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0148] The units described as separate components can or can not be physically separate, and the components of the control device can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0149] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that make contributions to the related art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0150] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A control method of an air conditioner, characterized by, The method comprises the following steps: obtaining a desired running time and a corresponding desired temperature of the air conditioner, or obtaining a set running time and a set temperature of the air conditioner; taking the desired temperature or the set temperature as a target temperature, and determining an advance start time of the air conditioner according to the target temperature; starting the air conditioner in advance before the desired running time or the set running time arrives according to the determined advance start time, and setting a set temperature of the air conditioner to the target temperature; obtaining a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature, to determine whether the indoor temperature can reach the target temperature at the desired running time or the set running time according to the predicted heat load removal trend curve, wherein the obtaining of the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature comprises: inputting a current first environmental parameter, an indoor temperature and the target temperature into a pre-trained heat load removal trend prediction model to predict a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature; if it is determined that the indoor temperature cannot reach the target temperature at the desired running time or the set running time, adjusting the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the desired running time or the set running time, comprising: if it is determined that the indoor temperature cannot reach the target temperature at the desired running time or the set running time, obtaining a heat load removal trend curve corresponding to each temperature value in a preset temperature range for adjusting the indoor temperature to the target temperature; in the obtained heat load removal trend curves corresponding to each temperature value in the preset temperature range for adjusting the indoor temperature to the target temperature, selecting a heat load removal trend curve that can reach the target temperature at the desired running time or the set running time, and adjusting the set temperature of the air conditioner to the temperature corresponding to the heat load removal trend curve.

2. The method of claim 1, wherein, The obtaining of the desired running time and the corresponding desired temperature of the air conditioner comprises: collecting user behavior data of a user using the air conditioner; based on the collected user behavior data, performing model training to obtain a prediction model for predicting the desired running time and the corresponding desired temperature of the air conditioner; predicting the desired running time and the corresponding desired temperature of the air conditioner by using the prediction model.

3. The method of claim 1, wherein, The determining of the advance start time of the air conditioner according to the obtained desired temperature or set temperature comprises: calculating a room heat load of the room according to a room volume of the room and a temperature difference between a current indoor temperature and the target temperature; calculating the advance start time of the air conditioner according to the calculated room heat load and an input power and a refrigerating capacity of the air conditioner.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises the following steps: before the determining of the advance start time of the air conditioner according to the obtained desired temperature or set temperature, obtaining a current outdoor environmental parameter, and determining whether the current outdoor environment meets a preset condition according to the outdoor environmental parameter. If it is judged that the current outdoor environment meets the preset condition, the indoor door and / or window are controlled to open for ventilation, the air conditioner is not turned on, or the air conditioner is controlled to be turned on to maintain the current indoor temperature according to a preset air outlet mode; If it is judged that the current outdoor environment does not meet the preset condition, the expected temperature or the set temperature is taken as a target temperature, and the advance start time of the air conditioner is determined according to the target temperature.

5. The method of claim 1, wherein, The heat load removal trend prediction model is trained by the following steps: Obtain heat load removal data from different indoor temperature adjustments to different target temperatures under different second environment parameters as sample data; Construct a heat load removal trend prediction model and perform model training based on the obtained sample data; Adjust the model parameters by using a back propagation algorithm, fix the model parameters, and obtain the heat load removal trend prediction model.

6. A control device of an air conditioner, characterized by comprising: Comprise: An acquisition unit is configured to acquire an expected running time and a corresponding expected temperature of the air conditioner, or acquire a set running time and a set temperature of the air conditioner; A first determination unit is configured to take the expected temperature or the set temperature acquired by the acquisition unit as a target temperature, and determine an advance start time of the air conditioner according to the target temperature; A control unit is configured to start the air conditioner in advance before the expected running time or the set running time according to the advance start time determined by the first determination unit, and set a set temperature of the air conditioner to the target temperature; A second determination unit is configured to acquire a predicted heat load removal trend curve for adjusting an indoor temperature to the target temperature, so as to determine whether the indoor temperature can reach the target temperature at the expected running time or the set running time according to the predicted heat load removal trend curve, wherein acquiring the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature comprises: Inputting a current first environment parameter, an indoor temperature and the target temperature into a pre-trained heat load removal trend prediction model to predict a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature; An adjustment unit is configured to adjust the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the expected running time or the set running time if the second determination unit determines that the indoor temperature cannot reach the target temperature at the expected running time or the set running time, comprising: If the second determination unit determines that the indoor temperature cannot reach the target temperature at the expected running time or the set running time, acquiring heat load removal trend curves corresponding to each temperature value in a preset temperature range of the target temperature for adjusting the indoor temperature to the target temperature; In the acquired heat load removal trend curves corresponding to each temperature in the preset temperature range of the target temperature for adjusting the indoor temperature to the target temperature, selecting a heat load removal trend curve that can reach the target temperature at the expected running time or the set running time, and adjusting the set temperature of the air conditioner to a temperature corresponding to the heat load removal trend curve.

7. A storage medium, characterized by A computer program product comprising a computer program stored on a computer readable medium, the program being executable by a processor to implement the steps of the method of any of claims 1-5.

8. An air conditioner characterized by comprising: A control device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor to implement the steps of the method of any of claims 1-5, or as claimed in claim 6.

9. A computer program product, characterised in that, A computer program product comprising a computer program, the program being executable by a processor to implement the steps of the method of any of claims 1-5.

Images