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. The method comprises the steps that the expected running time and the corresponding expected temperature of the air conditioner are obtained, or the set running time and the set temperature of the air conditioner are obtained; the expected temperature or the set temperature serves as a target temperature, and the advanced starting time of the air conditioner is determined according to the target temperature; the air conditioner is started in advance according to the determined advanced starting time, and the set temperature is set as the target temperature; a predicted heat load removal trend curve is obtained to determine whether the indoor temperature can reach the target temperature or not within the expected operation time or the set operation time; and if it is determined that the target temperature cannot be reached, the set temperature of the air conditioner is adjusted so that the indoor temperature can reach the target temperature within the expected operation time or the set operation time. According to the scheme provided by the invention, the expected temperature of the user can be accurately controlled, and the user experience is improved.

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] With the continuous development and improvement of technology and home appliances, people have a higher demand for the intelligence of home appliances. However, most of the current intelligent air conditioners only learn the user's setting habits, which only reduces the trouble of manual setting. It is easy to cause the user's expected temperature to be inaccurate, affecting the user experience of intelligent air conditioners. 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 of inaccurate control of the user's desired temperature by the air conditioner control in the related technologies.

[0004] On one hand, the present invention provides a method for controlling an air conditioner, comprising: obtaining an expected operating time and a corresponding expected temperature of the air conditioner, or obtaining a set operating time and a set temperature of the air conditioner; taking the expected temperature or the set temperature as a target temperature, and determining an advance start-up time of the air conditioner according to the target temperature; according to the determined advance start-up time, turning on the air conditioner in advance before the expected operating time or the set operating time arrives, and setting the 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, and determining whether the indoor temperature can reach the target temperature at the expected operating time or the set operating time according to the predicted heat load removal trend curve; if it is determined that the indoor temperature cannot reach the target temperature at the expected operating time or the set operating time, adjusting the set temperature of the air conditioner to make the indoor temperature reach the target temperature at the expected operating time or the set operating time.

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

[0006] Optionally, the advance start-up time of the air conditioner is determined based on the acquired expected temperature or the set temperature, including: calculating the room heat load of the room based on the room volume of the room and the temperature difference between the current indoor temperature and the target temperature; calculating the advance start-up time of the air conditioner based on the calculated room heat load and the input power and cooling capacity of the air conditioner.

[0007] Optionally, it also includes: before determining the advance start-up time of the air conditioner based on the acquired expected temperature or the set temperature, obtaining current outdoor environmental parameters, and judging whether the current outdoor environment meets preset conditions based on the outdoor environmental parameters; if it is judged that the current outdoor environment meets the preset conditions, controlling the indoor doors and / or windows to be opened for ventilation, and the air conditioner is not turned on, or controlling the air conditioner to be turned on and supply air according to the preset wind speed to maintain the current indoor temperature; if it is judged that the current outdoor environment does not meet the preset conditions, using the expected temperature or the set temperature as the target temperature, and determining the advance start-up time of the air conditioner according to the target temperature.

[0008] Optionally, obtaining a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature includes: inputting the current first environmental parameter, the indoor temperature, and the target temperature into a pre-trained heat load removal trend prediction model, and predicting a 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 during the expected operating time or the set operating time, the set temperature of the air conditioner is adjusted to make the indoor temperature reach the target temperature during the expected operating time or the set operating time, including: if it is determined that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, obtaining a heat load removal trend curve corresponding to each temperature value within a preset temperature range for adjusting the indoor temperature to the target temperature; among the heat load removal trend curves corresponding to each temperature within the preset temperature range for adjusting the indoor temperature to the target temperature obtained, selecting a heat load removal trend curve that can reach the target temperature during the expected operating time or the set operating time, and adjusting the set temperature of the air conditioner to the temperature corresponding to the heat load removal trend curve.

[0010] Optionally, the heat load removal trend prediction model is trained through the following steps: obtaining heat load removal data adjusted 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 acquired sample data; using a back propagation algorithm to adjust model parameters, fixing the model parameters, and obtaining the heat load removal trend prediction model.

[0011] On the other hand, the present invention provides a control device for an air conditioner, comprising: an acquisition unit, used to acquire an expected operating time and a corresponding expected temperature of the air conditioner, or to acquire a set operating time and a set temperature of the air conditioner; a first determination unit, used to take the expected temperature or the set temperature acquired by the acquisition unit as a target temperature, and determine an advance start-up time of the air conditioner according to the target temperature; a control unit, used to start the air conditioner in advance before the expected operating time or the set operating time arrives according to the advance start-up time determined by the first determination unit, and set the set temperature of the air conditioner to the target temperature; a second determination unit, used to acquire a 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 according to the predicted heat load removal trend curve; an adjustment unit, used to adjust the set temperature of the air conditioner if the second determination unit determines that the indoor temperature cannot reach the target temperature at the expected operating time or the set operating time, so as to make the indoor temperature reach the target temperature at the expected operating time or the set operating time.

[0012] Optionally, the acquisition unit acquires the expected operating time and the corresponding expected temperature of the air conditioner, including: collecting user behavior data of users using the air conditioner; performing model training based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and the corresponding expected temperature of the air conditioner; and predicting the expected operating time and the corresponding expected temperature of the air conditioner through the prediction model.

[0013] Optionally, the first determination unit determines the advance start-up time of the air conditioner according to the expected temperature or the set temperature obtained by the acquisition unit, including: calculating the room heat load of the room according to the room volume of the room and the temperature difference between the current indoor temperature and the target temperature; calculating the advance start-up time of the air conditioner according to the calculated room heat load and the input power and cooling capacity of the air conditioner.

[0014] Optionally, it also includes: a judgment unit, which is used to obtain current outdoor environmental parameters before the first determination unit determines the advance start-up time of the air conditioner according to the acquired expected temperature or the set temperature, and judge whether the current outdoor environment meets the preset conditions according to the outdoor environmental parameters; the control unit is also used to: if the judgment unit judges that the current outdoor environment meets the preset conditions, control the indoor doors and / or windows to open for ventilation, the air conditioner is not turned on, or control the air conditioner to be turned on and supply air according to the preset wind speed to maintain the current indoor temperature.

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

[0016] Optionally, if the second determination unit determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, the adjustment unit adjusts the set temperature of the air conditioner to make the indoor temperature reach the target temperature during the expected operating time or the set operating time, including: if the second determination unit determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, obtaining a heat load removal trend curve corresponding to each temperature value within a preset temperature range for adjusting the indoor temperature to the target temperature; among the heat load removal trend curves corresponding to each temperature within the preset temperature range for adjusting the indoor temperature to the target temperature, a heat load removal trend curve that can reach the target temperature during the expected operating time or the set operating time is selected, and the set temperature of the air conditioner is adjusted to the temperature corresponding to the heat load removal trend curve.

[0017] Optionally, the heat load removal trend prediction model is trained through the following steps: obtaining heat load removal data adjusted 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 acquired sample data; using a back propagation algorithm to adjust model parameters, fixing the model parameters, and obtaining the heat load removal trend prediction model.

[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 aforementioned control devices.

[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, the user's expected air-conditioning operating time and the corresponding expected temperature are obtained by learning the user's behavior, or the set operating time and set temperature set by the user are obtained, the expected temperature or the set temperature is used as the target temperature, the advance start-up time of the air-conditioner is determined, and the air-conditioner is turned on in advance according to the determined advance start-up time, so as to accurately control the user's expected temperature and improve the user experience.

[0023] According to the technical solution of the present invention, a 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 operating time or the set operating time.

[0024] According to the technical solution of the present invention, the heat load removal trend is controlled according to the heat load removal trend model to achieve precise temperature adjustment, ensuring energy-saving control while ensuring a comfortable temperature for users. 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 A flowchart showing a specific implementation of step 1 of obtaining the expected operating time of the air conditioner and the corresponding predicted target temperature;

[0028] Figure 3 A flow chart showing a specific implementation of the step of determining the advance start time of the air conditioner according to the target temperature;

[0029] Figure 4 shows a heat load removal trend curve according to a specific embodiment of the present invention;

[0030] Figure 5 A schematic diagram of a training process of a heat load trend prediction model according to a specific embodiment of the present invention is shown;

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

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

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

[0037] like Figure 1 As shown, according to one embodiment of the present invention, the air conditioner control method at least includes step S110, step S120, step S130, step S140 and step S150.

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

[0039] In a specific implementation, the expected operating time and the corresponding expected temperature of the air conditioner are predicted based on user behavior data of the user using the air conditioner. Figure 2 The flowchart of the specific implementation of the step of obtaining the expected operating time of the air conditioner and the corresponding predicted target temperature of the present invention is shown. Figure 2 As shown, it includes steps S111 to S113.

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

[0041] Specifically, user behavior data of the user using the air conditioner is collected each time the air conditioner is running. Preferably, after the air conditioner is turned on each time, the permission to collect user behavior data is first obtained, and the user behavior data is collected after obtaining the permission. For example, the permission to collect user behavior data can be obtained by asking.

[0042] Step S112: Perform model training based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and the corresponding expected temperature of the air conditioner.

[0043] Preferably, when the collected user behavior data reaches the minimum required data volume for model training (i.e., the minimum data volume required for model training), model training is performed based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and the corresponding expected temperature of the air conditioner. The expected operating time and the corresponding expected temperature are the time (moment) when the user expects the air conditioner to operate and the temperature that the user expects to reach at that time; the user behavior data may specifically include: the time to turn the air conditioner on and off, the continuous use time of the air conditioner, the set temperature, and the time required for temperature adjustment (the time required to adjust 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 user's expected temperature at any time is used as the output of the model. A deep neural network model is trained to obtain a prediction model.

[0044] Step S113, predicting the expected operating time and the corresponding expected temperature of the air conditioner through the prediction model.

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

[0046] The set operating time and set temperature of the air conditioner are the expected operating time (i.e., the set operating time) and the expected temperature (i.e., the 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, that is, the temperature that the user may want 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 volume for model training), the set operating time and set temperature of the air conditioner set by the user are obtained, that is, the operating time and target temperature set by the user.

[0047] Step S120: taking the expected temperature or the set temperature as a target temperature, and determining an advance start time of the air conditioner 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 parameters are obtained, and it is determined whether the current outdoor environment meets the preset conditions according to the outdoor environment parameters. If it is determined that the current outdoor environment meets the preset conditions, the indoor doors and / or windows are controlled to be opened for ventilation, and the air conditioner is not turned on, or the air conditioner is controlled to be turned on to supply air according to the preset wind speed to maintain the current indoor temperature. If it is determined that the current outdoor environment does not meet the preset conditions, 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 environmental parameters are obtained, and the indoor and outdoor environmental parameters may specifically include: indoor environmental temperature, indoor relative humidity air pollution index, and whether the current outdoor environment meets the standard. The detailed rules are as follows: whether the outdoor temperature is within a preset temperature range, that is, whether the outdoor temperature is a suitable temperature for the human body, whether the air quality meets the standard, that is, whether the air pollution index is lower than a preset index threshold, for example, whether the air pollution index is ≤100, whether the outdoor humidity meets the standard, that is, whether the outdoor humidity is within a preset humidity range, for example, whether the outdoor humidity is within a normal humidity range (for example, 40%-80%), if all indicators of the current outdoor environment meet the standard, and the indoor doors and / or windows are controllable, then control the window and / or door to open for ventilation, and the air conditioner is not turned on; if all indicators of the current outdoor environment meet the standard, but the indoor doors and / or windows are not controllable, then control the indoor fan of the air conditioner to supply air according to the preset wind speed to maintain the current indoor temperature.

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

[0051] Step S121, calculating the room heat load of the room according to the room volume of the room and the temperature difference between the current indoor temperature and the target temperature.

[0052] In a specific implementation, room heat load = room volume × air density × specific heat capacity × temperature difference. The temperature difference is the temperature difference between the current indoor temperature and the target temperature, that is, 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, the room volume is set by the user, or the room volume is calculated by detecting the length, width, and height of the room.

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

[0054] Specifically, 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 a normal mode (the normal mode is, for example, the air conditioner is running at rated power) is calculated according to the calculated room heat load of the room:

[0055] In a specific implementation, 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, the efficiency is highest when the indoor temperature is close to the target temperature, the air conditioning system is in a state of high energy efficiency ratio, and the overall power consumption is lower. Therefore, in the energy-saving mode (the energy-saving mode is, for example, the air conditioner is operated at a preset ratio of the rated power, for example, at 80% of the rated power), 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) is:

[0058]

[0059] Therefore, according to the room heat load of the room and the input power and cooling 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 can be obtained, that is, the time t for starting the air conditioner in advance:

[0060]

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

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

[0063] Step S140, obtaining a 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 during the expected operation time or the set operation time according to the predicted heat load removal trend curve.

[0064] 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, and a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted. Preferably, after the air conditioner is turned on, the predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is obtained at preset time intervals, and whether the indoor temperature can reach the target temperature during the expected operating time or the set operating time is determined based on the predicted heat load removal trend curve. For example, the current first environmental parameter, the indoor temperature, and the target temperature are input into a pre-trained heat load removal trend prediction model at preset time intervals, and a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted. For example, For one cycle, turn on the air conditioner and run it according to the target temperature. When the time comes, the heat load change trend is predicted, the current first environmental parameter, indoor temperature and target temperature are input into a pre-trained heat load removal trend prediction model, and a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted.

[0065] In a specific embodiment, the first environmental parameter includes at least one of the region, climate type, sunshine time, 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 regulation of the air conditioner, that is, to predict the time-varying curve of the heat load removal amount required to adjust the indoor temperature to any temperature. The heat load removal amount is the amount of heat required to remove 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 heat load removal trend curve for adjusting the indoor temperature to the target temperature is output, and the target temperature is the expected temperature or the set temperature.

[0066] In a specific implementation, the heat load removal trend prediction model is trained by the following steps:

[0067] Step S1, obtaining heat load removal data adjusted from different indoor temperatures to different target temperatures under different second environmental parameters as sample data.

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

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

[0070] Step S2: construct a heat load removal trend prediction model, and perform model training based on the acquired sample data.

[0071] In a specific implementation, a Transformer neural network model is constructed using TensorFlow, and the input layer, hidden layer, and output layer of the model are designed. Different environmental parameters, indoor temperature, and target temperature in the sample data are used as inputs of the model, and the heat load removal amount is used as the target output of the model to train the neural network model.

[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 includes, for example: cleaning the sample data; normalizing the sample data with inconsistent dimensions by the maximum value; filling missing values ​​with interpolation or similarity; deleting or replacing abnormal values ​​to obtain a standard sample data set, and using the standard sample data set to train the heat load removal model.

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

[0074]

[0075] Among them, y1 is the true value, and y2 is the predicted value output by the model. By inputting the two into the loss function, the difference measurement can be completed.

[0076] After that, use the fit function to train the model on the training set: model.fit(train_data,epochs=epochs,validation_data=val_data).

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

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

[0079] Specifically, the output deviation between the actual model output and the target value is calculated, and it is determined whether the deviation is within the allowable range; if the output deviation q is within the allowable range, the training ends, the value of the model parameter is determined, and the model is output. If the output deviation q is not within the allowable range, the parameter error is calculated, the error gradient is calculated, the weight is updated, and the model design and model training are repeated.

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

[0081] The training process of the above heat load removal trend prediction model can also be referred to Figure 5 . Figure 5 FIG. 2 shows a schematic diagram of a training process of a heat load trend prediction model according to a specific embodiment of the present invention. Figure 5 As shown in the figure, the heat load removal data corresponding to different climates, different sunshine hours, different indoor and outdoor temperatures, and different cooling temperatures in different regions are collected; the data is preprocessed to obtain a standard data set; TensorFlow is used to select and build a Transformer neural network model, and the input layer, hidden layer, and output layer of the model are designed to train the model; the loss is calculated and the parameters are updated to find the deviation between the target value and the actual value; if the output deviation is not within the allowable range, the training ends, the weights and other related parameters are fixed, and the model is output; if the output deviation is not within the allowable range, the model is returned and redesigned.

[0082] According to the determined advance start time, after the air conditioner is turned on in advance before the expected operation time or the set operation time arrives, 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 arrives, every preset time, the current first environmental parameter, indoor temperature and target temperature are input into a 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 operation time or the set operation time.

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

[0084] Step S150: If it is determined that the indoor temperature cannot reach the target temperature during 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 during the expected operation time or the set operation time.

[0085] In a specific implementation, if it is determined that the indoor temperature cannot reach the target temperature during the expected operation time or the set operation time, a heat load removal trend curve corresponding to each temperature value within a preset temperature range for adjusting the indoor temperature to the target temperature is obtained. Among the heat load removal trend curves corresponding to each temperature within the preset temperature range for adjusting the indoor temperature to the target temperature obtained, a heat load removal trend curve that can reach the target temperature during 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, a heat load removal trend curve corresponding to each temperature value within the preset temperature range of adjusting the indoor temperature to the target temperature is obtained.

[0087] That is, if the predicted heat load removal trend curve cannot reach the expected temperature at the user's expected time (i.e., the expected operating time or the set operating time), the heat load removal trend curve in the temperature range near the current target temperature is recalculated, and the heat load curve that can reach the expected temperature at the user's expected 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 the user wants the room temperature to reach 26°C at 18:00, 270KJ of heat load needs to be removed. Figure 6 As shown, it is 17:00 at this time, and the current air-conditioning setting temperature (expected temperature) is 26°C. Curve 1 is the predicted heat load removal trend curve with the predicted target temperature of 26°C. According to the curve, it is predicted that 270KJ cannot be reached at 18:00. Therefore, the heat load removal trend curve with the temperature within 2°C around 26°C (such as 24°C, 25°C) as the target temperature is obtained. By comparison, it is obtained that curve 2 (24°C) can reach 270KJ at 18:00, and curve 3 (25°C) cannot reach 270KJ at 18:00, so the air-conditioning setting temperature is adjusted to 24°C.

[0089] Furthermore, when the indoor temperature reaches the target temperature, the set temperature of the air conditioner is adjusted back to the target temperature. That is, when the temperature reaches the user's desired temperature, the air conditioner temperature is set back to the desired temperature, and the compressor reduces 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 the trace heat load to keep the temperature at the desired temperature.

[0090] Historical data and the data that users can manually adjust in subsequent use are all included in the database that collects user behavior data. Subsequent models will be trained and adjusted to make the output results closer to the user's life. If users frequently adjust certain settings, the system will learn and adjust its algorithm.

[0091] In order to clearly illustrate the technical solution of the present invention, the execution process of the air conditioner control method provided by the present invention is described below with reference to a specific embodiment.

[0092] Figure 7 FIG. 1 is a schematic diagram of a specific embodiment of the air conditioning control method provided by the present invention. Figure 7As shown, after the air conditioner is turned on, the user is asked for data permission and the permission is obtained; user behavior data (time to turn the air conditioner on and off, frequency of temperature and air volume adjustment, etc.) is collected, and model training is performed after the minimum required amount of model training is reached to predict the user's setting preferences. If the current user model training is completed, the intelligent mode is directly entered, and the model is used to predict the temperature setting that the user may expect at any time point. If the current user model training is not completed, the user sets the expected operating time and expected temperature range. Obtain the indoor and outdoor temperature and environmental index. If the current outdoor environment meets the standard, the detailed rules are as follows: including whether the temperature is suitable for the human body and whether the air quality meets the standard. If all indicators of the current outdoor environment meet the standard and the doors and windows can be intelligently adjusted, the windows are controlled for ventilation and the air conditioner is not turned on; otherwise, the fan is used to maintain temperature stability. If the outdoor environmental index does not meet the standard, the time t to turn on the air conditioner in advance is calculated, and the air conditioner is turned on t time in advance according to the user's expected time. In a fixed period (here Take one cycle as an example), When the heat load removal trend model is used, the currently predicted heat load change curve is obtained. If the expected temperature can be reached at the expected time, the current setting parameters remain unchanged; if the expected temperature cannot be reached at the expected time, the heat load trend curve in 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 the heat load curve. time, At each time, the above steps are repeated. When the temperature reaches the user's desired temperature, the air conditioner setting temperature is set back to the desired temperature. The setting data is recorded for training and adjusting the prediction model.

[0093] 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 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 operation time and the corresponding expected temperature of the air conditioner, or acquire the set operation time and the set temperature of the air conditioner.

[0095] In a specific implementation, the expected operating time and the corresponding expected temperature of the air conditioner are predicted based on the user behavior data of the user using the air conditioner. Specifically, the 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 the corresponding expected temperature of the air conditioner; and the expected operating time and the corresponding expected temperature of the air conditioner are predicted by the prediction model.

[0096] Specifically, user behavior data of the user using the air conditioner is collected each time the air conditioner is running. Preferably, after the air conditioner is turned on each time, the permission to collect user behavior data is first obtained, and the user behavior data is collected after obtaining the permission. For example, the permission to collect user behavior data can be obtained by asking.

[0097] When the collected user behavior data reaches the minimum required data volume for model training (i.e., the minimum data volume required for model training), model training is performed based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and the corresponding expected temperature of the air conditioner. The expected operating time and the corresponding expected temperature are the time (moment) when the user expects the air conditioner to operate and the temperature that the user expects to reach at that time; the user behavior data may specifically include: the time to turn the air conditioner on and off, the continuous use time of the air conditioner, the set temperature, and the time required for temperature adjustment (the time required to adjust 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 user's expected temperature at any time is used as the output of the model. A deep neural network model is trained to obtain a prediction model.

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

[0099] The first determining unit 120 is configured to use the expected temperature or the set temperature obtained by the obtaining unit as a target temperature, and determine an advance start time of the air conditioner according to the target temperature.

[0100] Preferably, the device 100 further includes: a judgment unit (not shown). The judgment unit is used to obtain the current outdoor environment parameters before the first determination unit determines the advance start time of the air conditioner according to the obtained expected temperature or the set temperature, and judge whether the current outdoor environment meets the preset conditions according to the outdoor environment parameters; the control unit 130 is also used to: if the judgment unit determines that the current outdoor environment meets the preset conditions, control the indoor doors and / or windows to open for ventilation, and the air conditioner is not turned on, or control the air conditioner to start and supply air according to the preset wind speed to maintain the current indoor temperature; if the judgment unit determines that the current outdoor environment does not meet the preset conditions, the expected temperature or the set temperature is used as the target temperature to determine the advance start time t of the air conditioner.

[0101] 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 environmental parameters are obtained, and the indoor and outdoor environmental parameters may specifically include: indoor environmental temperature, indoor relative humidity air pollution index, and whether the current outdoor environment meets the standard. The detailed rules are as follows: whether the outdoor temperature is within a preset temperature range, that is, whether the outdoor temperature is a suitable temperature for the human body, whether the air quality meets the standard, that is, whether the air pollution index is lower than a preset index threshold, for example, whether the air pollution index is ≤100, whether the outdoor humidity meets the standard, that is, whether the outdoor humidity is within a preset humidity range, for example, whether the outdoor humidity is within a normal humidity range (for example, 40%-80%), if all indicators of the current outdoor environment meet the standard, and the indoor doors and / or windows are controllable, then control the window and / or door to open for ventilation, and the air conditioner is not turned on; if all indicators of the current outdoor environment meet the standard, but the indoor doors and / or windows are not controllable, then control the indoor fan of the air conditioner to supply air according to the preset wind speed to maintain the current indoor temperature.

[0102] In a specific embodiment, the first determination unit 120, the step of determining the advance start time of the air conditioner according to the target temperature includes: calculating the room heat load of the room according to the room volume of the room and the temperature difference between the current indoor temperature and the target temperature; calculating the advance start time of the air conditioner according to the calculated room heat load and the input power and cooling capacity of the air conditioner.

[0103] In a specific implementation, room heat load = room volume × air density × specific heat capacity × temperature difference. The temperature difference is the temperature difference between the current indoor temperature and the target temperature, that is, 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, the room volume is set by the user, or the room volume is calculated by detecting the length, width, and height of the room.

[0104] 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 (the normal mode is, for example, the air conditioner is running at rated power) is calculated according to the calculated room heat load of the room:

[0105] In a specific implementation, 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 is close to the target temperature, the air conditioning system is in a state of high energy efficiency ratio, and the overall power consumption is lower. Therefore, in the energy-saving mode (the energy-saving mode is, for example, the air conditioner is operated at a preset ratio of the rated power, for example, at 80% of the rated power), 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) is:

[0108]

[0109] Therefore, according to the room heat load of the room and the input power and cooling 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 can be obtained, that is, the time t for starting the air conditioner in advance:

[0110]

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

[0112] Specifically, after obtaining the advance time t for turning on the air conditioner, the air conditioner is turned on in advance according to the obtained expected operating time or the set operating time and the determined advance starting time t of the air conditioner, that is, the air conditioner is turned on t in advance relative to the predicted expected operating time or the obtained set operating 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, so as to determine whether the indoor temperature can reach the target temperature during the expected operation time or the set operation time according to the predicted heat load removal trend curve.

[0114] In a specific embodiment, the current first environmental parameter, indoor temperature and target temperature are input into a pre-trained heat load removal trend prediction model, and a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted. Preferably, after the air conditioner is turned on, a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is obtained at preset time intervals, and whether the indoor temperature can reach the target temperature during the expected operating time or the set operating time is determined based on the predicted heat load removal trend curve. 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, and a predicted heat load removal trend curve is obtained.

[0115] The predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature. For one cycle, turn on the air conditioner and run it according to the target temperature. When the time comes, the heat load change trend is predicted, the current first environmental parameter, indoor temperature and target temperature are input into a pre-trained heat load removal trend prediction model, and a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature is predicted.

[0116] In a specific embodiment, the first environmental parameter includes at least one of the region, climate type, sunshine time, 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 regulation of the air conditioner, that is, to predict the time-varying curve of the heat load removal amount required to adjust the indoor temperature to any temperature. The heat load removal amount is the amount of heat required to remove 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 heat load removal trend curve for adjusting the indoor temperature to the target temperature is output, and the target temperature is the expected temperature or the set temperature.

[0117] In a specific implementation, the heat load removal trend prediction model is trained by the following steps:

[0118] Step S1, obtaining heat load removal data adjusted from different indoor temperatures to different target temperatures under different second environmental parameters as sample data.

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

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

[0121] Step S2: construct a heat load removal trend prediction model, and perform model training based on the acquired sample data.

[0122] In a specific implementation, a Transformer neural network model is constructed using TensorFlow, and the input layer, hidden layer, and output layer of the model are designed. Different environmental parameters, indoor temperature, and target temperature in the sample data are used as inputs of the model, and the heat load removal amount is used as the target output of the model to train the neural network model.

[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 includes, for example: cleaning the sample data; normalizing the sample data with inconsistent dimensions by the maximum value; filling missing values ​​with interpolation or similarity; deleting or replacing abnormal values ​​to obtain a standard sample data set, and using the standard sample data set to train the heat load removal model.

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

[0125]

[0126] Among them, y1 is the true value, and y2 is the predicted value output by the model. By inputting the two into the loss function, the difference measurement can be completed.

[0127] After that, use the fit function to train the model on the training set: model.fit(train_data,epochs=epochs,validation_data=val_data).

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

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

[0130] Specifically, the output deviation between the actual model output and the target value is calculated, and it is determined whether the deviation is within the allowable range; if the output deviation q is within the allowable range, the training ends, the value of the model parameter is determined, and the model is output. If the output deviation q is not within the allowable range, the parameter error is calculated, the error gradient is calculated, the weight is updated, and the model design and model training are repeated.

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

[0132] According to the determined advance start time, after the air conditioner is turned on in advance before the expected operation time or the set operation time arrives, 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 arrives, every preset time, the current first environmental parameter, indoor temperature and target temperature are input into a 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 operation time or the set operation time.

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

[0134] The adjustment unit 150 is used to adjust the set temperature of the air conditioner so that the indoor temperature reaches the target temperature during the expected operating time or the set operating time if the second determination unit determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time.

[0135] In a specific embodiment, if the second determination unit 140 determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, the adjustment unit 150 adjusts the set temperature of the air conditioner to make the indoor temperature reach the target temperature during the expected operating time or the set operating time, including: if the second determination unit determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, obtain a heat load removal trend curve corresponding to each temperature value within a preset temperature range for adjusting the indoor temperature to the target temperature; among the heat load removal trend curves corresponding to each temperature within the preset temperature range for adjusting the indoor temperature to the target temperature, select a heat load removal trend curve that can reach the target temperature during the expected operating time or the set operating time, and adjust 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 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, a heat load removal trend curve corresponding to each temperature value within the preset temperature range of 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 expected time (i.e., the expected operating time or the set operating time), the heat load removal trend curve in the temperature range near the current target temperature is recalculated, and the heat load curve that can reach the expected temperature at the user's expected 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, if the user wants the room temperature to reach 26°C at 18:00, 270KJ of heat load needs to be removed. Figure 6 As shown, it is 17:00 at this time, and the current air-conditioning setting temperature (expected temperature) is 26°C. Curve 1 is the predicted heat load removal trend curve with the predicted target temperature of 26°C. According to the curve, it is predicted that 270KJ cannot be reached at 18:00. Therefore, the heat load removal trend curve with the temperature within 2°C around 26°C (such as 24°C, 25°C) as the target temperature is obtained. By comparison, it is obtained that curve 2 (24°C) can reach 270KJ at 18:00, and curve 3 (25°C) cannot reach 270KJ at 18:00, so the air-conditioning setting temperature is adjusted to 24°C.

[0139] Furthermore, when the indoor temperature reaches the target temperature, the set temperature of the air conditioner is adjusted back to the target temperature. That is, when the temperature reaches the user's desired temperature, the air conditioner temperature is set back to the desired temperature, and the compressor reduces 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 the trace heat load to keep the temperature at the desired temperature.

[0140] Historical data and the data that users can manually adjust in subsequent use are all included in the database that collects user behavior data. Subsequent models will be trained and adjusted to make the output results closer to the user's life. If users frequently adjust certain settings, the system will learn and adjust its algorithm.

[0141] 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.

[0142] 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.

[0143] The present invention also provides an air conditioner corresponding to the control device of the air conditioner, comprising any of the control devices described above.

[0144] 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.

[0145] Based on this, the solution provided by the present invention can accurately control the user's expected air conditioning operation time and the corresponding expected temperature by learning user behavior, thereby improving 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 operation time or the set operation time. According to the heat load removal trend model, the heat load removal trend is controlled to achieve accurate temperature adjustment, ensuring energy-saving control while ensuring the user's comfortable temperature.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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: Obtaining the expected operating time and the corresponding expected temperature of the air conditioner, or obtaining the set operating time and the set temperature of the air conditioner; Taking the expected temperature or the set temperature as the target temperature, and determining the advance start time of the air conditioner according to the target temperature; According to the determined advance start time, the air conditioner is started in advance before the expected operation time or the set operation time arrives, and the set temperature of the air conditioner is set to the target temperature; obtaining a 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 operation time or the set operation time according to the predicted heat load removal trend curve; If it is determined that the indoor temperature cannot reach the target temperature during 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 during the expected operation time or the set operation time.

2. The method according to claim 1, characterized in that Obtaining the expected operating time of the air conditioner and the corresponding expected temperature, including: Collecting user behavior data of users using the air conditioner; Performing model training based on the collected user behavior data to obtain a prediction model for predicting the expected operating time and the corresponding expected temperature of the air conditioner; The expected operation time and the corresponding expected temperature of the air conditioner are predicted by the prediction model.

3. The method according to claim 1, characterized in that Determining the advance start time of the air conditioner according to the acquired expected temperature or the set temperature includes: Calculating the room heat load of the room according to the room volume of the room and the temperature difference between the current indoor temperature and the target temperature; The advance start time of the air conditioner is calculated according to the calculated room heat load and the input power and cooling capacity of the air conditioner.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: Before determining the advance start time of the air conditioner according to the acquired expected temperature or the set temperature, obtaining current outdoor environment parameters, and judging whether the current outdoor environment meets the preset conditions according to the outdoor environment parameters; If it is determined that the current outdoor environment meets the preset conditions, the indoor doors and / or windows are controlled to be opened for ventilation, and the air conditioner is not turned on, or the air conditioner is controlled to be turned on to supply air according to the preset wind speed to maintain the current indoor temperature; If it is determined that the current outdoor environment does not meet the preset conditions, 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.

5. The method according to any one of claims 1 to 3, characterized in that: Obtaining a predicted heat load removal trend curve for adjusting the indoor temperature to the target temperature, including: 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 heat load removal trend curve for adjusting the indoor temperature to the target temperature.

6. The method according to claim 5, characterized in that If it is determined that the indoor temperature cannot reach the target temperature during the expected operation time or the set operation time, adjusting the set temperature of the air conditioner so that the indoor temperature reaches the target temperature during the expected operation time or the set operation time, including: If it is determined that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time, a heat load removal trend curve corresponding to each temperature value within a preset temperature range of the target temperature is obtained; Among the heat load removal trend curves corresponding to various temperatures within the preset temperature range for adjusting the indoor temperature to the target temperature, a heat load removal trend curve that can reach the target temperature within the expected operating time or the set operating time is selected, and the set temperature of the air conditioner is adjusted to the temperature corresponding to the heat load removal trend curve.

7. The method according to claim 5, characterized in that The heat load removal trend prediction model is trained by the following steps: Acquire heat load removal data adjusted 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 acquired sample data; The back propagation algorithm is used to adjust the model parameters, and the model parameters are fixed to obtain the heat load removal trend prediction model.

8. A control device for an air conditioner, characterized in that: include: an acquisition unit, configured to acquire an expected operating time and a corresponding expected temperature of the air conditioner, or acquire a set operating time and a set temperature of the air conditioner; a first determining unit, configured to use the desired temperature or the set temperature acquired by the acquiring unit as a target temperature, and determine an advance start time of the air conditioner according to the target temperature; a control unit, configured to start the air conditioner in advance before the expected operation time or the set operation time arrives according to the advance start time determined by the first determination unit, and set the set temperature of the air conditioner to the target temperature; a second determination unit, configured to obtain a 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 operation time or the set operation time according to the predicted heat load removal trend curve; an adjusting unit for adjusting the set temperature of the air conditioner so as to make the indoor temperature reach the target temperature during the expected operating time or the set operating time if the second determining unit determines that the indoor temperature cannot reach the target temperature during the expected operating time or the set operating time.

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