Air conditioner and control method thereof

Abstract

The invention provides an air conditioner and a control method thereof.The control method comprises the steps that a depth model based on a soft attention mechanism is obtained, and the depth model is used for obtaining air conditioner control data conforming to user habits according to environment data; and real-time environment data are obtained, and real-time air conditioner control data are obtained according to the depth model and the real-time environment data. And then the air conditioner adjusts the operation parameters of the air conditioner according to the real-time air conditioner control data, and the operation state of the air conditioner is adjusted to be the air conditioner state conforming to the current use habit of the user. On one hand, the problem that the air conditioner cannot automatically adjust the running state according to user requirements is solved, and the intelligence degree of the air conditioner is improved; and on the other hand, the time spent on manually adjusting the air conditioner by the user is shortened, and the experience feeling of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning automatic control, and in particular to a control method of an air-conditioner and the air-conditioner. Background Art

[0002] At present, users can usually only manually adjust the parameters of traditional air conditioners to meet their different needs. This method of manually adjusting the parameters of traditional air conditioners requires users to spend time and energy to set the air conditioner state, and as the surrounding environment changes, users also need to repeatedly adjust the air conditioner state according to their physical condition. It takes a lot of time for users to adjust the most suitable and comfortable air conditioner state; moreover, most air conditioners are not intelligent enough, and the air conditioners cannot automatically adjust the parameters according to the needs of users to meet the needs of users; in addition, the air conditioner cannot customize an exclusive automatic adjustment operation mechanism according to the usage of each user. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide an air conditioner and a control method thereof that overcome the above problems or at least partially solve the above problems, which can solve the problem that the air conditioner cannot automatically adjust the operating status according to user needs, thereby achieving the purpose of improving user experience.

[0004] Furthermore, the present invention reduces the operation time for a user to adjust the operating parameters of the air conditioner.

[0005] Furthermore, the present invention can customize an exclusive automatic operation mechanism according to the user's usage.

[0006] Specifically, the present invention provides a method for controlling an air conditioner, comprising:

[0007] Acquire a deep model based on a soft attention mechanism, wherein the deep model is used to obtain air conditioner control data that conforms to user habits according to environmental data;

[0008] Real-time environmental data is acquired, and real-time air conditioner control data is obtained according to the deep model and the real-time environmental data.

[0009] Optionally, the step of acquiring a deep model based on a soft attention mechanism includes:

[0010] Acquiring historical data, the historical data including historical environment data and historical air conditioner control data of the user under each of the historical environment data;

[0011] The historical environmental data is used as input and the corresponding historical air conditioner control data is used as output to train a preset neural network model to obtain the deep model.

[0012] Optionally, the acquiring of historical data includes:

[0013] Initial historical data is acquired, and the initial historical data is filtered according to the use time of the air conditioner to obtain the historical data.

[0014] Optionally, the deep model includes an attention mechanism layer and a multi-layer perception mechanism, and obtaining real-time air conditioner control data according to the deep model and the real-time environmental data includes:

[0015] Using the attention mechanism layer to weight the real-time environment data; and

[0016] The multi-layer perception mechanism is adopted to obtain the real-time air conditioner control data according to the weighted real-time environmental data.

[0017] Optionally, the historical environmental data includes one or more of user perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity;

[0018] The historical air conditioner control data includes one or more of the air conditioner switch state, the user-set air conditioner mode, the user-set temperature, the user-set wind speed, the air conditioner continuous power-on time, and the user's air conditioner usage time in different air conditioner states.

[0019] Optionally, the adopting the attention mechanism layer to weight the real-time environment data includes:

[0020] Performing linear mapping on the real-time environmental data to transform the real-time environmental data into a multi-dimensional domain;

[0021] Acquire the attention distribution, and perform weighted average calculation on the weighted real-time environment data according to the attention distribution.

[0022] Optionally, the multi-layer perception mechanism includes an input layer, a hidden layer and an output layer, and the method of using the multi-layer perception mechanism to obtain the real-time air conditioner control data according to the weighted real-time environmental data includes:

[0023] Acquire the weighted real-time environmental data through the input layer;

[0024] Obtaining intermediate output data according to the weighted real-time environmental data through the hidden layer;

[0025] The intermediate output data is sorted through the output layer to obtain the real-time air conditioner control data.

[0026] Optionally, the activation function of the hidden layer is a sigmoid function or a tanh function.

[0027] Optionally, the acquiring of real-time environmental data and obtaining real-time air conditioner control data according to the deep model and the real-time environmental data includes:

[0028] The real-time environment data is acquired once at a set time interval, and after the real-time environment data is acquired each time, the real-time air conditioner control data is obtained according to the deep model and the real-time environment data.

[0029] The present invention also provides an air conditioner, which includes a controller, the controller includes a memory, a processor and a machine executable program stored in the memory and running on the processor, and the processor implements any of the control methods described above when executing the machine executable program.

[0030] In the control method of the air conditioner of the present invention, a control method for the air conditioner to automatically adjust the operating parameters according to the user's usage habits is proposed, and the real-time air conditioner control data that conforms to the user's usage habits is obtained by inputting the acquired real-time environmental data into the deep model based on the soft attention mechanism. Among them, the soft attention mechanism can assign weights to the real-time environmental data, so that the deep model based on the soft attention mechanism will obtain the air conditioner control data that conforms to the user's usage habits based on the weights of the real-time environmental data calculated by the soft attention mechanism. On the one hand, the present invention solves the problem that the air conditioner cannot automatically adjust the operating state according to user needs, thereby improving the intelligence of the air conditioner. On the other hand, it reduces the time spent by the user on manually adjusting the air conditioner, thereby improving the user experience.

[0031] Furthermore, the present invention can train a dedicated automatic adjustment operation mechanism according to the usage of each user to meet the user's own personalized needs.

[0032] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0034] Figure 1 is a schematic flow chart of a method for controlling an air conditioner according to an embodiment of the present invention;

[0035] Figure 2 is a schematic flow chart of generating a depth model according to an embodiment of the present invention;

[0036] Figure 3 is a schematic flow chart of a method for controlling an air conditioner according to another embodiment of the present invention;

[0037] Figure 4 is a schematic structural diagram of a controller in an air conditioner according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] Refer to the following Figures 1 to 4 To describe the air conditioner and the control method thereof of the embodiment of the present invention. In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features, that is, include one or more of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. When a feature "includes or contains" one or some of the features it covers, unless otherwise specifically described, this indicates that other features are not excluded and may further include other features.

[0039] In the description of the present embodiment, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0040] Figure 1 1 is a schematic flow chart of a control method for an air conditioner according to an embodiment of the present invention, the control method comprising the following steps:

[0041] Step S101: Acquire a deep model based on a soft attention mechanism, where the deep model is used to obtain air conditioner control data that conforms to user habits based on environmental data.

[0042] Step S102: Acquire real-time environmental data, and obtain real-time air conditioner control data based on the deep model and the real-time environmental data.

[0043] Specifically, when the air conditioner enters the adaptive function mode, the air conditioner will obtain a deep model based on the soft attention mechanism and real-time environmental data detected in real time, and then input the real-time environmental data into the deep model. The deep model will obtain real-time air conditioner control data based on the real-time environmental data. Then, the air conditioner will adjust the operating parameters of the air conditioner according to the real-time air conditioner control data, and adjust the state of the air conditioner to an air conditioner state that conforms to the user's current usage habits.

[0044] The present invention obtains real-time air conditioner control data that conforms to the user's usage habits by inputting the acquired real-time environmental data into a deep model based on a soft attention mechanism. The deep model uses a soft attention mechanism to calculate the weight of the real-time environmental data, and then obtains the air conditioner control data frequently used by the user based on the real-time environmental data after calculating the weight. On the one hand, the present invention solves the problem that the air conditioner cannot automatically adjust the operating state according to user needs, thereby improving the intelligence of the air conditioner. On the other hand, it reduces the time and number of adjustments spent by the user on manually adjusting the air conditioner, thereby improving the user experience.

[0045] Furthermore, the present invention can adjust the deep model according to the user's usage data, so that the air conditioner control data output by the deep model is consistent with the air conditioner control data manually adjusted by the user when the air conditioner is in a non-adaptive mode or is less than a preset ratio value, and the air conditioner adjustment time is consistent with or less than a preset ratio value, thereby achieving "personal customization". The user no longer needs to manually adjust the control data of the air conditioner, saving the user's operation times and improving the user's experience and comfort.

[0046] In some embodiments of the present invention, obtaining a deep model based on a soft attention mechanism comprises the following steps:

[0047] Step S201: Acquire historical data, which includes historical environment data and historical air conditioner control data of the user under each historical environment data.

[0048] Step S202: Taking the historical environmental data as input and the corresponding historical air conditioner control data as output, the preset neural network model is trained to obtain a deep model.

[0049] In this embodiment, historical environmental data includes user-perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity; historical air conditioner control data includes at least air conditioner switch status, user-set air conditioning mode, user-set temperature, user-set wind speed, air conditioner continuous power-on time, and user-set air conditioner usage time under different air conditioning states.

[0050] In this embodiment, the training of the preset neural network model includes two processes, wherein the first process is: inputting historical environmental data into the preset neural network model to obtain preset air conditioner control data, and calculating the difference between the historical air conditioner control data and the preset air conditioner control data; the second process is: judging whether the above difference is less than the set value of the corresponding data, when the difference is less than the set value of the corresponding data, the preset neural network model is trained into a deep model; when the difference is not less than the set value of the corresponding data, returning to execute the above first process, until the difference between the historical air conditioner control data and the preset air conditioner control data is less than the set value, the preset neural network model is trained into a deep model that conforms to the user's usage habits.

[0051] The present invention trains a preset neural network model into a deep model that conforms to the user's usage habits through historical data. The deep model can obtain air conditioner control data that conforms to the user's usage habits based on the input real-time environmental data, so that the obtained air conditioner control data is more accurate and more in line with the user's usage habits. There is no need for manual operation by the user, which improves the intelligence of the air conditioner and at the same time improves the user's comfort and experience.

[0052] In some embodiments of the present invention, the method of acquiring historical data is to acquire initial historical data and filter the initial historical data according to the use time of the air conditioner to obtain historical data.

[0053] In this embodiment, the initially collected historical data is all the data of the air conditioner operating parameter changes, including the data of multiple adjustments by the user in a short period of time. Some of this data does not conform to the user's usage habits and needs to be screened and deleted from the air conditioner's memory or from the cloud database. For example, if the proportion of the air conditioner usage time of a certain data user in this air conditioner state to the continuous air conditioner on time is less than the set value, the data is deleted from the database or deleted from the air conditioner's memory.

[0054] The present invention obtains historical data by screening initial historical data, so that the deep model trained based on the historical data is more accurate, and then the air conditioner control data obtained by inputting real-time environmental data into the deep model is more accurate and more in line with the user's usage habits. There is no need for manual operation by the user, which reduces the number of user operations.

[0055] In some embodiments of the present invention, the historical environmental data includes one or more of the user's perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity.

[0056] The historical air conditioner control data includes one or more of the air conditioner switch state, the user-set air conditioner mode, the user-set temperature, the user-set wind speed, the air conditioner continuous power-on time, and the user's air conditioner usage time in different air conditioner states.

[0057] In this embodiment, some parameters of historical environmental data and historical air conditioner control data are shown. In the air conditioner control method of the present invention, historical environmental data and historical air conditioner control data include but are not limited to the above parameters. According to actual needs or differences in geographical locations, the parameters of historical environmental data and historical air conditioner control data can be changed, added or deleted.

[0058] Correspondingly, the real-time environmental data in the above step S102 includes one or more of the user's perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity; the real-time air conditioner control data includes one or more of the air conditioner switch status, the user-set air conditioner mode, the user-set temperature, and the user-set wind speed.

[0059] The present invention trains a preset neural network model into a deep model based on historical data. The more historical data there is, the closer the deep model trained by the preset neural network model is to the user's usage habits. Then, the real-time air conditioner control data obtained after the real-time environmental data is input into the deep model is more accurate, and there is no need for manual adjustment by the user, which improves the user's comfort and reduces the number of user operations.

[0060] In some embodiments of the present invention, the deep model includes an attention mechanism layer and a multi-layer perception mechanism; according to the deep model and the real-time environmental data, real-time air conditioner control data is obtained, including:

[0061] An attention mechanism layer is used to weight the real-time environmental data; and a multi-layer perception mechanism is used to obtain real-time air conditioner control data based on the weighted real-time environmental data.

[0062] In this embodiment, the deep model includes two parts, namely, the first part is an attention mechanism layer and the second part is a multi-layer perception mechanism, wherein the attention mechanism layer of the first part is used to perform weighted averaging on the input real-time environmental data, calculate the weights of each parameter of the real-time environmental data, obtain weighted real-time environmental data, and use the weighted real-time environmental data as the input of the multi-layer perception mechanism. The multi-layer perception mechanism processes and analyzes the weighted real-time environmental data to obtain real-time air conditioner control data that conforms to the user's usage habits, and then changes the operating parameters of the air conditioner according to the real-time air conditioner control data, and adjusts the operating state of the air conditioner to an air conditioner state that conforms to the user's current usage habits.

[0063] The attention mechanism layer used in the present invention performs weighted averaging on the input real-time environmental data and calculates the weights of various parameters of the real-time environmental data, which can make the air conditioner control data obtained by the deep model more accurate and make the operating state of the air conditioner closer to the user's usage habits. The multi-layer perception mechanism used in the present invention can process the weighted real-time environmental data into air conditioner control data that conforms to the user's usage habits, so that the air conditioner can adjust the operating state of the air conditioner according to the air conditioner control data and improve the user's comfort.

[0064] In some embodiments of the present invention, an attention mechanism layer is used to weight real-time environmental data, including:

[0065] The real-time environment data is linearly mapped to transform the real-time environment data into a multi-dimensional domain.

[0066] The attention distribution is obtained, and the weighted average of the weighted real-time environment data is calculated according to the attention distribution.

[0067] In this embodiment, the real-time environmental data includes one or more of the user's perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity. The attention mechanism layer includes a soft attention mechanism. The attention mechanism layer uses the principle of the soft attention mechanism to perform weighted averaging on the input real-time environmental data and calculate the weights of different input real-time environmental data. The method used is: when selecting real-time environmental data, instead of selecting one from n real-time environmental data, a weighted average of the n input real-time environmental data is calculated, and then the weighted average of the n input real-time environmental data is input into the multi-layer perception mechanism for calculation.

[0068] For example, when a scene enters the human field of vision, people tend to focus on some key points in the scene first, such as dynamic points or abrupt colors, and the remaining static scenes may be temporarily ignored. Or when people need to find information about people in a picture, they will pay more attention to the areas of the picture that match the characteristics of the people, and ignore those areas of the picture that do not match the characteristics of the people. This is a reasonable and effective allocation of attention.

[0069] The soft attention mechanism adopted in the control method of the air conditioner of the present invention includes three parts, namely, calculating the attention score, calculating the attention distribution, and calculating the weighted average. The common models for calculating the attention score include the additive model, the dot product model, the scaled dot product model, and the bilinear model. The model adopted in the control method of the air conditioner of the present invention can be replaced according to actual needs to achieve the same output effect; wherein the attention distribution is calculated by using the softmax function to convert the attention score to 0-1 to obtain the attention distribution of each real-time environmental data; the weighted average is calculated by using the weighted summation method to perform a weighted average on the output result of the attention distribution and the input real-time environmental data to obtain the weighted real-time environmental data.

[0070] The softmax function is:

[0071]

[0072] Among them, s i and j is the output of the model for calculating the attention score, s i Yes 1 to n The i-th output result in s j Yes 1 to n The jth output result in .

[0073] For example, a data X=[x 1 , x 2 , x 3 , …, x n ].

[0074] Among them, x 1 is the first type of environmental data, x 2 is the second type of environmental data, x 3 is the third type of environmental data, x n This is the Nth type of environmental data, which includes but is not limited to user-perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity.

[0075] Step 1: Perform a linear mapping on X and transform it into a multidimensional domain to obtain Y.

[0076] Step 2: Calculate the attention distribution of X and obtain the attention distribution sequence a:

[0077] a=[a 1 , a 2 , a 3 , …, a n ].

[0078] where a 1 , a2 , a 3 , …, a n For x 1 , x 2 , x 3 , …, x n The corresponding attention distribution.

[0079] Step 3: Calculate the weighted average of the input information:

[0080]

[0081] x i is the i-th data in data X, a i is the ith data in the attention distribution sequence a. The real-time environment data is weighted averaged according to the input real-time environment data and the obtained attention distribution to obtain the weighted real-time environment data.

[0082] The present invention uses an attention mechanism layer to weight the real-time environmental data, and can obtain weighted real-time environmental data. Weighting the real-time environmental data can distribute the real-time environmental data according to the weight, highlighting the key real-time environmental data, so that the real-time air conditioner control data obtained after the weighted real-time environmental data is input into the multi-layer perception mechanism is more accurate, more in line with the user's usage habits, and improves the user's comfort.

[0083] In some embodiments of the present invention, the multi-layer perception mechanism includes an input layer, a hidden layer, and an output layer; the multi-layer perception mechanism is used to obtain real-time air conditioner control data according to the weighted real-time environmental data, including:

[0084] Obtain weighted real-time environmental data through the input layer.

[0085] Through the hidden layer, the intermediate output data is obtained according to the weighted real-time environmental data.

[0086] The intermediate output data is sorted through the output layer to obtain real-time air conditioner control data.

[0087] In this embodiment, the output data of the first part of the attention mechanism layer is weighted real-time environmental data, including weighted user body temperature, weighted indoor temperature, weighted indoor humidity, weighted outdoor temperature, and weighted indoor humidity. The output data of the hidden layer is the intermediate data output by the multi-layer perception mechanism.

[0088] The second part of the deep model of the present invention is a multi-layer perception mechanism, which includes three parts, namely, an input layer, a hidden layer and an output layer, wherein the input layer receives the weighted real-time environmental data of the first part of the attention mechanism layer. The hidden layer processes and analyzes the weighted real-time environmental data to obtain intermediate output data that conforms to user habits. The intermediate output data cannot be directly transmitted to the air conditioner to allow the air conditioner to adjust the operating state of the air conditioner according to the intermediate output data. Instead, the intermediate output data needs to be converted into air conditioner control instructions through the output layer, and then the output layer processes and integrates the air conditioner control instructions into real-time air conditioner control data that conforms to user usage habits.

[0089] The present invention processes weighted real-time environmental data through the input layer, hidden layer and output layer in a multi-layer perception mechanism to obtain real-time air conditioner control data that conforms to the user's usage habits. The air conditioner automatically adjusts the operating state of the air conditioner based on the air conditioner control data, without the need for the user to manually adjust the operating state of the air conditioner, thereby reducing the number of user operations and improving the intelligence of the air conditioner.

[0090] In some embodiments of the present invention, the activation function of the hidden layer is a sigmoid function or a tanh function.

[0091] The hidden layer and the input layer are fully connected. Assuming that the data of the input layer is represented by vector Z, the output of the hidden layer is f(W 1 Z+b 1 ), W 1 is the weight coefficient, b 1 is the bias, and the activation function f can be the commonly used sigmoid function or tanh function.

[0092] The sigmoid function is:

[0093] The tanh function is:

[0094] The y in S(y) and the i in tanh(i) are both W. 1 Z+b 1 , W 1 is the weight coefficient, Z is a vector, b 1 is bias.

[0095] The present invention calculates the intermediate output data of the hidden layer through the activation function sigmoid function or tanh function in the hidden layer. The intermediate output data cannot be directly transmitted to the air conditioner. In order for the air conditioner to directly adjust the operating state of the air conditioner according to the intermediate output data, the intermediate output data needs to be converted into air conditioner control instructions through the output layer, and then the output layer processes and integrates the air conditioner control instructions into real-time air conditioner control data that conforms to the user's usage habits.

[0096] The present invention adopts an activation function in the hidden layer so that the air conditioner control data obtained by the hidden layer is more accurate, more in line with the user's usage habits, and reduces the number of user operations.

[0097] In some embodiments of the present invention, real-time environmental data is acquired, and real-time air conditioner control data is obtained based on a deep model and the real-time environmental data, including acquiring real-time environmental data once every set time interval, and after each acquisition of real-time environmental data, obtaining real-time air conditioner control data based on the deep model and the real-time environmental data.

[0098] Specifically, the air conditioner obtains real-time environmental data once at a set interval, and inputs the real-time environmental data into the deep model after each acquisition. The deep model uses the attention mechanism layer and the multi-layer perception mechanism in sequence to obtain real-time air conditioner control data and send the real-time air conditioner control data to the air conditioner. Then the air conditioner adjusts the operating parameters of the air conditioner according to the real-time air conditioner control data to ensure that the operating status of the air conditioner conforms to the user's usage habits.

[0099] Each time real-time environmental data is input into the deep model, the deep model will be updated according to the real-time environmental data to obtain a deep model that conforms to the user's current usage habits, and then obtain air conditioner control data that conforms to the current user's usage habits. The air conditioner then adjusts its operating parameters according to the air conditioner control data and adjusts the operating state of the air conditioner to an air conditioner state that conforms to the user's current usage habits.

[0100] Preferably, the duration is set to 5 minutes, which can be changed according to the actual needs of the user.

[0101] The present invention obtains air conditioner control data by inputting the deep model according to the acquired real-time environmental data at set intervals, and adjusts the operating state of the air conditioner based on the obtained air conditioner control data, so that the operating state of the air conditioner conforms to the user's current usage habits, improves the user's comfort, and saves the user's operation times, thereby improving the user's experience. And as the number of updates increases, the air conditioner can be continuously intelligentized, improving the convenience, comfort and intelligence of the air conditioner.

[0102] In some optional embodiments of the present invention, the deep model is stored in the cloud, and the historical environmental data, historical air conditioner control data, as well as the collected real-time environmental data and the air conditioner control data output by the deep model are stored in a database in the cloud.

[0103] In some optional embodiments of the present invention, the deep model, historical environmental data, historical air conditioner control data, as well as real-time collected environmental data and air conditioner control data output by the deep model are stored in the air conditioner's memory 520. When the storage quantity of the air conditioner's memory 520 reaches a set value, the air conditioner will filter and delete some data, maintain the weight ratio of the stored data, and increase the available storage space.

[0104] In some optional embodiments of the present invention, the way in which the air conditioner enters the adaptive function mode includes but is not limited to an adaptive function mode button on the remote control of the air conditioner, a display screen operation button of the air conditioner, a mobile device to which the air conditioner is connected via Bluetooth or WiFi, and an APP operation button on the mobile device.

[0105] In some embodiments of the present invention, there is a public depth model trained based on public data in the cloud or the air conditioner's memory 520, so that when there is less data in the database, the user can also use the air conditioner's adaptive function mode.

[0106] In some embodiments of the present invention, reference Figure 3 After the user turns on the air conditioner, the air conditioner will prompt the user whether to choose to enter the adaptive function mode.

[0107] If No is selected, the user can manually adjust the operating parameters of the air conditioner and adjust the operating status of the air conditioner.

[0108] If you select Yes, the air conditioner will enter the adaptive function mode. And when entering the adaptive function mode:

[0109] First, the air conditioner will obtain real-time environmental data of the surrounding environment, and the environmental data obtained includes one or more of the user's perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity.

[0110] The air conditioner will then upload the acquired environmental data to the cloud. The deep model stored in the cloud will receive the environmental data, process and analyze it to obtain air conditioner control data that conforms to the user's usage habits. The cloud will then send the obtained air conditioner control data to the air conditioner.

[0111] Finally, the air conditioner adjusts operating parameters and operating status according to the obtained air conditioner control data to conform to the user's usage habits and meet the user's needs, thereby improving the user's experience.

[0112] The adaptive function mode refers to a mode for executing the control method of the air conditioner of the present invention. A database of deep models and user usage data is stored in the cloud or memory 520. The air conditioner control data includes one or more of the air conditioner switch status, the user-set air conditioner mode, the user-set temperature, and the user-set wind speed.

[0113] In addition, on the one hand, the present invention can automatically learn and match the appropriate air-conditioning state according to the user's usage habits, thereby reducing the complexity of user operation; on the other hand, as the number of times the user uses increases, the air conditioner can continue to become intelligent, thereby improving the convenience, comfort and intelligence of the air conditioner.

[0114] The present invention also provides an air conditioner, which includes a controller 500, wherein the controller 500 includes a memory 520, a processor 510, and a machine executable program 41 stored in the memory 520 and running on the processor 510, and when the processor 510 executes the machine executable program 41, the control method described in any one of the above items is implemented.

[0115] In this embodiment, the air conditioner includes a controller 500, so that the controller 500 controls various parameters of the air conditioner, including one or more of an air conditioner switch state, a user-set air conditioner mode, a user-set temperature, and a user-set wind speed.

[0116] In addition, the controller 500 can control the indoor temperature sensor to detect the indoor temperature, the outdoor temperature sensor to detect the outdoor temperature, the outdoor humidity sensor to detect the outdoor humidity, the indoor humidity sensor to detect the indoor environmental humidity, and the indoor infrared sensor to detect the user's body surface temperature.

[0117] Through the above-mentioned detection method, the air conditioner can obtain one or more of the indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity in real time when the air conditioner is in the adaptive function mode, and the air conditioner can adjust one or more of the air conditioning switch state, the user-set air conditioning mode, the user-set temperature, and the user-set wind speed, to ensure that the operating parameters of the air conditioner are in line with the user's usage habits and enhance the user experience.

[0118] The controller 500 includes a memory 520 and a processor 510. The memory 520 stores at least the air conditioner switch state, the user-set air conditioner mode, the user-set temperature, the user-set wind speed, the indoor temperature, the indoor humidity, the outdoor temperature, the outdoor humidity, and the machine executable program 41 corresponding to the above-mentioned control method. The machine executable program 41 running on the processor 510 can implement the control method described in any of the above-mentioned embodiments to ensure that the air conditioner is in an operating state that conforms to the user's usage habits.

[0119] It should be noted that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or equipment (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or equipment and execute instructions), or used in combination with these instruction execution systems, devices or equipment.

[0120] For the purposes of the description of this embodiment, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or apparatus or in conjunction with such instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection having one or more wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, a computer-readable medium may even be paper or other suitable medium on which the program may be printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] At this point, those skilled in the art should recognize that, although multiple exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications that conform to the principles of the present invention can still be directly determined or derived based on the content disclosed in the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and recognized as covering all these other variations or modifications.

Claims

1. A method for controlling an air conditioner, characterized in that: include: Acquire a deep model based on a soft attention mechanism, wherein the deep model is used to obtain air conditioner control data that conforms to user habits according to environmental data; Real-time environmental data is acquired, and real-time air conditioner control data is obtained according to the deep model and the real-time environmental data.

2. The control method according to claim 1, characterized in that: The acquisition of the deep model based on the soft attention mechanism includes: Acquiring historical data, the historical data including historical environment data and historical air conditioner control data of the user under each of the historical environment data; The historical environmental data is used as input and the corresponding historical air conditioner control data is used as output to train a preset neural network model to obtain the deep model.

3. The control method according to claim 2, characterized in that: The acquisition of historical data includes: Initial historical data is acquired, and the initial historical data is filtered according to the use time of the air conditioner to obtain the historical data.

4. The control method according to claim 2, characterized in that: The historical environmental data includes one or more of the user's perceived temperature, indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity; The historical air conditioner control data includes one or more of the air conditioner switch state, the user-set air conditioner mode, the user-set temperature, the user-set wind speed, the air conditioner continuous power-on time, and the user's air conditioner usage time in different air conditioner states.

5. The control method according to claim 1, characterized in that: The deep model includes an attention mechanism layer and a multi-layer perception mechanism, and obtaining real-time air conditioner control data according to the deep model and the real-time environmental data includes: Using the attention mechanism layer to weight the real-time environment data; and The multi-layer perception mechanism is adopted to obtain the real-time air conditioner control data according to the weighted real-time environmental data.

6. The control method according to claim 5, characterized in that: The step of using the attention mechanism layer to weight the real-time environment data includes: Performing linear mapping on the real-time environmental data to transform the real-time environmental data into a multi-dimensional domain; Acquire the attention distribution, and perform weighted average calculation on the weighted real-time environment data according to the attention distribution.

7. The control method according to claim 5, characterized in that: The multi-layer perception mechanism includes an input layer, a hidden layer and an output layer. The multi-layer perception mechanism is used to obtain the real-time air conditioner control data according to the weighted real-time environmental data, including: Acquire the weighted real-time environmental data through the input layer; Obtaining intermediate output data according to the weighted real-time environmental data through the hidden layer; The intermediate output data is sorted through the output layer to obtain the real-time air conditioner control data.

8. The control method according to claim 7, characterized in that: The activation function of the hidden layer is a sigmoid function or a tanh function.

9. The control method according to claim 1, characterized in that: The acquiring of real-time environmental data and obtaining real-time air conditioner control data according to the deep model and the real-time environmental data includes: The real-time environment data is acquired once at a set time interval, and after the real-time environment data is acquired each time, the real-time air conditioner control data is obtained according to the deep model and the real-time environment data.

10. An air conditioner, characterized in that: include: A controller, the controller comprising a memory, a processor and a machine executable program stored in the memory and running on the processor, and the processor implements the control method according to any one of claims 1 to 9 when executing the machine executable program.

Images