Air conditioner control method, controller, storage medium and air conditioner

Abstract

The invention relates to the technical field of smart home, particularly provides an air conditioner control method, a controller, a storage medium and an air conditioner, and aims to solve the problem of how to improve the adaptivity, temperature accuracy and user comfort of air conditioner control. In order to achieve the purpose, the method comprises the steps that historical operation data and real-time environment information of the air conditioner are obtained, an air conditioner control instruction of the air conditioner is determined based on an intelligent agent according to the historical operation data and the real-time environment information, and the air conditioner is controlled to operate according to the air conditioner control instruction. In this way, the obtained real-time environment information and historical operation data can be utilized to effectively perceive the air conditioner environment change, the air conditioner control instruction is automatically generated, and the intelligence of air conditioner control is improved. And moreover, the intelligent agent can adaptively generate the air conditioner control instruction, so that air conditioner operation better conforms to user habits and user requirements, the accuracy of air conditioner temperature adjustment and the comfort optimization capability are improved, and the adaptability of air conditioner control is enhanced.

Description

Technical Field

[0001] This application relates to the technical field of smart home, and specifically relates to an air conditioner control method, a controller, a storage medium, and an air conditioner. Background Art

[0002] An air conditioner control system is an electronic device widely used in homes and workplaces, mainly used to control the operation of air conditioner equipment to achieve the purpose of adjusting indoor temperature and humidity. It can not only improve the comfort of the living environment but also help save energy, playing an important role in daily life. Currently, the air conditioner control system shows a development trend of intelligence, energy conservation, and networking, and demonstrates significant advantages in multiple application scenarios.

[0003] However, most current air conditioner control systems lack intelligence and adaptability and cannot dynamically adjust control strategies according to actual situations. That is to say, the air conditioner control system can only generate control instructions by using preset control logics and parameters, such as the actual working scenario and the type of indoor personnel, to control the operation of the central air conditioner or the fresh air unit. This static control method cannot effectively perceive environmental changes and user habits, let alone adaptively adjust control logics and parameters, thus unable to achieve precise temperature adjustment and comfort optimization, difficult to meet the comfort requirements under changing environments and user needs, and resulting in a decline in the control efficiency and user experience of the air conditioner system.

[0004] Correspondingly, a new solution is needed in this field to solve the above problems. Summary of the Invention

[0005] To overcome the above defects, this application is proposed to solve or at least partially solve the technical problem of how to improve the adaptability, temperature accuracy, and user comfort of air conditioner control.

[0006] In a first aspect, an air conditioner control method is provided, and the method includes:

[0007] Obtain historical operation data and real-time environment information of the air conditioner;

[0008] Based on an agent, determine an air conditioner control instruction for the air conditioner according to the historical operation data and the real-time environment information;

[0009] Control the operation of the air conditioner according to the air conditioner control instruction.

[0010] In a technical solution of the above air conditioner control method, the determining the air conditioner control instruction based on an agent according to the historical operation data and the real-time environment information includes:

[0011] Extract features from the historical operation data and the real-time environment information to obtain a feature extraction result;

[0012] Based on the agent, determine the target control strategy and target control parameters of the air conditioner according to the feature extraction result;

[0013] Determine the air conditioner control instruction according to the target control strategy and target control parameters.

[0014] In a technical solution of the above air conditioner control method, the agent is implemented based on at least one of a reinforcement learning algorithm, a machine learning algorithm, and a deep reinforcement learning algorithm.

[0015] In a technical solution of the above air conditioner control method, the target control strategy includes at least one of a temperature adjustment strategy, a wind speed adjustment strategy, and an operation mode switching strategy; and / or,

[0016] The target control parameters include at least one of a temperature setting range, a target operation mode, and a wind speed setting range.

[0017] In a technical solution of the above air conditioner control method, after controlling the air conditioner to operate according to the air conditioner control instruction, the method further includes:

[0018] Judge whether there is a user feedback instruction;

[0019] When there is a user feedback instruction, adjust the air conditioner control instruction according to the user feedback instruction.

[0020] In a technical solution of the above air conditioner control method, the method further includes:

[0021] Update the model parameters of the agent according to the user feedback instruction.

[0022] In a technical solution of the above air conditioner control method, the air conditioner includes an environmental information detection unit and a historical data storage unit, and the obtaining of the historical operation data and real-time environmental information of the air conditioner includes:

[0023] Obtain the real-time environmental information through the environmental information collection unit;

[0024] Obtain the historical operation data through the historical data storage unit;

[0025] Among them, the environmental acquisition unit includes at least one of a temperature sensor, a humidity sensor, an air velocity sensor, a human body heat release sensor, and a human body infrared sensor; the real-time environmental information includes at least one of indoor humidity information, outdoor humidity information, indoor temperature information, outdoor temperature information, indoor air velocity information, outdoor air velocity information, and indoor personnel activity information of the environment where the air conditioner is located; the historical operation data includes at least one of the historical temperature setting value, historical operation mode, and historical air velocity setting value of the air conditioner.

[0026] In a second aspect, a controller is provided, which includes at least one processor; and a memory communicatively connected to the at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any one of the technical solutions of the above air conditioner control method is implemented.

[0027] In a third aspect, a computer-readable storage medium is provided, which stores multiple program codes, and the program codes are adapted to be loaded and run by a processor to execute the method described in any one of the technical solutions of the above air conditioner control method.

[0028] In a fourth aspect, an air conditioner is provided, which includes a controller, and the controller is used to execute the method described in any one of the technical solutions of the above air conditioner control method.

[0029] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:

[0030] In implementing the technical solution provided by the present application, the present application can obtain the historical operation data and real-time environmental information of the air conditioner, and based on the intelligent agent, determine the air conditioner control instruction of the air conditioner according to the historical operation data and real-time environmental information, and control the operation of the air conditioner according to the air conditioner control instruction. Through the above configuration method, the obtained real-time environmental information and historical operation data can be used to effectively sense the change of the air conditioner environment, automatically generate the air conditioner control instruction, and improve the intelligence of the air conditioner control. Moreover, the intelligent agent can adaptively generate the air conditioner control instruction, making the operation of the air conditioner more in line with the user's habits and user needs, improving the accuracy and comfort optimization ability of the air conditioner temperature adjustment, enhancing the adaptability of the air conditioner control, and improving the user experience. Description of the Drawings

[0031] Referring to the drawings, the disclosure of the present application will become easier to understand. It is easy for those skilled in the art to understand that: these drawings are only for the purpose of illustration and are not intended to limit the protection scope of the present application. Among them:

[0032] Figure 1It is a schematic diagram of the main steps of an air conditioner control method according to an embodiment of the present application;

[0033] Figure 2 It is a schematic diagram of the main steps of an implementation manner of an air conditioner control method according to an embodiment of the present application;

[0034] Figure 3 It is a schematic diagram of the main steps of an implementation manner of determining the control strategy and control parameters of an air conditioner according to an embodiment of the present application;

[0035] Figure 4 It is a schematic diagram of the main structure of a controller according to an embodiment of the present application.

[0036] Reference numerals:

[0037] 11: Memory; 12: Processor. Detailed implementation manners

[0038] The following describes some implementation manners of the present application with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.

[0039] In the description of the present application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, a memory, and may also include a software part, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, in hardware, or in a combination of the two. A computer-readable storage medium includes any suitable medium for storing program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and so on. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "this" may also include the plural form.

[0040] Here, some terms related to the present application are first explained.

[0041] An Agent refers to an entity that can perceive the environment and take actions to achieve specific goals. An Agent can be in the form of software, hardware, or a system. An Agent has autonomy, adaptability, and interaction capabilities. It can sense changes in the environment, such as through sensors or data input, make judgments and decisions based on the knowledge and algorithms it has learned, and then execute actions to achieve the predetermined goals.

[0042] Refer to the appendix Figure 1 , Figure 1 It is a schematic diagram of the main steps of an air conditioner control method according to an embodiment of the present application. As Figure 1 shown, the air conditioner control method in the embodiment of the present application mainly includes the following steps S101 to S103.

[0043] Step S101: Obtain the historical operation data and real-time environment information of the air conditioner.

[0044] In this embodiment, an air conditioner refers to an air conditioner, which is a device that uses artificial means to partially or fully adjust the temperature, humidity, flow rate, and cleanliness of the air in a closed space, enabling the air parameters of the target environment to meet the requirements.

[0045] In this embodiment, during each air conditioner control process, the air conditioner needs to actively obtain the historical operation data and the real-time environment information where the air conditioner is located to effectively sense the changes in the environment where the air conditioner is located and the user control habits of the air conditioner, and autonomously generate an adaptive air conditioner control instruction to improve the temperature adjustment accuracy of the air conditioner control and user comfort.

[0046] In one embodiment, the air conditioner may include an environment information detection unit and a historical data storage unit. Then, step S101 may further include steps S1011 to S1012:

[0047] Step S1011: Obtain the real-time environment information through the environment information collection unit.

[0048] In this embodiment, the environment collection unit may include at least one of a temperature sensor, a humidity sensor, a wind speed sensor, a human body heat release sensor, and a human body infrared sensor.

[0049] In this embodiment, the real-time environment information may include at least one of the indoor humidity information, outdoor humidity information, indoor temperature information, outdoor temperature information, indoor air flow rate information, outdoor air flow rate information, and indoor personnel activity information of the environment where the air conditioner is located.

[0050] Step S1012: Obtain the historical operation data through the historical data storage unit.

[0051] In this embodiment, the historical operation data includes at least one of the historical temperature setting value, the historical operation mode, and the historical wind speed setting value of the air conditioner.

[0052] In one embodiment, the historical operation data may further include the historical environmental information of the air conditioner and the corresponding historical control strategy and historical control parameters.

[0053] In some other embodiments, the historical operation data may be the historical operation data of the air conditioner within a preset time period from now, or may be all the historical operation data of the air conditioner, or may be the historical operation data of a preset data volume updated regularly, which does not affect the normal implementation of this embodiment.

[0054] In one embodiment, the historical data storage unit may specifically be a cloud database. Among them, a cloud database refers to a database optimized or deployed to a virtual computing environment, and realizes data storage and management through cloud computing technology.

[0055] Step S102: Based on the agent, determine the air conditioner control instruction of the air conditioner according to the historical operation data and the real-time environmental information.

[0056] In this embodiment, the air conditioner control instruction may be an instruction for realizing functions such as temperature adjustment, mode selection, wind speed adjustment, and timing of the air conditioner.

[0057] Among them, the air conditioner control instruction may include a target control strategy and target control parameters. The target control strategy may be the type of air conditioner control set by the air conditioner control instruction, and the target control parameter may be the target value of the control parameter corresponding to the target control strategy set by the air conditioner.

[0058] In one embodiment, the target control strategy may include at least one of a temperature adjustment strategy, an air conditioner wind speed adjustment strategy, and an operation mode switching strategy.

[0059] In this embodiment, the temperature adjustment strategy may include one of increasing the temperature and decreasing the temperature; the wind speed adjustment strategy may include one of increasing the wind speed and decreasing the wind speed.

[0060] In one embodiment, the target control parameter may include at least one of a temperature setting range, a target operation mode, and a wind speed setting range.

[0061] As an example, the temperature setting range may be 18-28 degrees Celsius (°C), the target operation mode may be one of cooling, heating, and dehumidifying, and the wind speed setting range may be from level 1 to level 5.

[0062] In one embodiment, the air conditioner control instruction may also only include a target control strategy, and the target control strategy contains target control parameters, which does not affect the normal implementation of this embodiment either.

[0063] In one embodiment, the agent is implemented based on at least one of a reinforcement learning algorithm, a machine learning algorithm, and a deep reinforcement learning algorithm.

[0064] Among them, the machine learning algorithm is a type of algorithm that automatically analyzes and obtains rules from data and uses the rules to predict unknown data. The reinforcement learning algorithm is an algorithm that obtains feedback by interacting with the environment to maximize the cumulative reward. The deep reinforcement learning algorithm combines the perception ability of deep learning and the decision-making ability of reinforcement learning, and is a machine learning method that uses a deep neural network to approximate the policy or value function in reinforcement learning to solve complex decision-making problems.

[0065] In one embodiment, the agent may specifically be a reinforcement learning model. An agent can be obtained in advance, interact with the environment by performing actions, receive rewards and feedback from the environment, and adjust the model parameters of the agent based on the rewards and feedback, so as to obtain a trained agent. Among them, the interaction process may include perceiving the environmental state, making decisions, and receiving environmental feedback.

[0066] In one embodiment, the agent can learn the user habits of air conditioner control based on historical operation data to predict the air conditioner control instruction corresponding to the real-time environmental data, or can also predict the air conditioner control instruction corresponding to the historical operation data and the real-time environmental data according to the own logic of the agent, which does not affect the normal implementation of this embodiment either.

[0067] In one embodiment, step S102 may further include steps S1021 to S1023:

[0068] Step S1021: Extract features from the historical operation data and the real-time environmental information to obtain a feature extraction result.

[0069] Step S1022: Based on the agent, determine the target control strategy and target control parameters of the air conditioner according to the feature extraction result.

[0070] Step S1023: Determine the air conditioner control instruction according to the target control strategy and the target control parameters.

[0071] In this embodiment, the feature extraction in step S1021 can effectively reduce the data dimension by extracting useful information from the historical operation data and the real-time environmental information to obtain a feature extraction result. Therefore, inputting the feature extraction result into the agent can help improve the computing efficiency of the agent and reduce the consumption of computing resources.

[0072] In one embodiment, before step S1021, data processing may also be performed on historical operation data and real-time environment information to clean, transform, and integrate the historical operation data and real-time environment information, ensuring data quality.

[0073] In this embodiment, data processing may include operations such as data cleaning, data transformation, data denoising, standardization, and normalization.

[0074] Step S103: Control the operation of the air conditioner according to the air conditioner control instruction.

[0075] In one embodiment, step S103 may further include controlling the operation of the air conditioner according to the target control strategy and target control parameters in the air conditioner control instruction.

[0076] In one embodiment, after step S103, this embodiment may further include step S104 and step S105:

[0077] Step S104: Determine whether there is a user feedback instruction.

[0078] Step S105: When there is a user feedback instruction, adjust the air conditioner control instruction according to the user feedback instruction.

[0079] In this embodiment, the user feedback instruction may be an instruction feedback by the user according to the execution result of the air conditioner control instruction. For example, the user feedback instruction may include an instruction for one or more control strategies such as adjusting the temperature, switching the operation mode, and adjusting the wind speed.

[0080] In one embodiment, the air conditioner may further include a feedback detection module, and step S104 may specifically include:

[0081] Through the feedback detection module, detect whether the air conditioner receives an instruction sent by the user's mobile terminal or a user voice instruction. If so, determine whether the received instruction is used to adjust the operation state of the air conditioner. If so, use the received instruction as the user feedback instruction.

[0082] In one embodiment, step S105 may specifically include: obtaining the control parameters and control strategies set by the user according to the user feedback instruction, and adjusting the air conditioner control instruction according to the control parameters and the control strategies.

[0083] In one embodiment, when there is a user feedback instruction, this embodiment may further include step S106:

[0084] Step S106: Update the model parameters of the agent according to the user feedback instruction.

[0085] In this embodiment, step S106 may further include step S1061 and step S1062:

[0086] Step S1061: Obtain the air conditioner control instruction adjusted according to the user feedback instruction.

[0087] Step S1062: Update the model parameters of the agent according to the control strategy or control parameters of the adjusted air conditioner control instruction and the real-time environment information.

[0088] In this embodiment, the model parameters of the agent may include the learning rate, the discount factor, and other model parameters. For example, when the agent is a reinforcement learning model, other model parameters may also include the relevant parameters of the action-value function in the model, etc.

[0089] In an application scenario according to an embodiment of the present application, reference may be made to the appendix Figure 2 , appendix Figure 2 is a schematic diagram of the main step flow of an embodiment of the air conditioner control method according to an embodiment of the present application. As Figure 2 shown, this method may include steps S201 to S204:

[0090] Step S201: Obtain the environmental information where the air conditioner is located and the historical operation data of the air conditioner.

[0091] In this embodiment, the environmental information may include indoor temperature, outdoor temperature, indoor humidity, outdoor humidity, and indoor personnel activity conditions, etc. Among them, the indoor personnel activity conditions can affect the operation effect of the air conditioner by affecting the air flow and temperature distribution indoors. Therefore, when controlling the air conditioner, it is necessary to consider the influencing factors of the indoor personnel activity conditions to improve the control accuracy of the air conditioner control.

[0092] In one embodiment, the environmental information may be obtained through environmental sensors. Among them, the environmental sensors may include temperature sensors, humidity sensors, human infrared sensors, human heat release sensors, and other sensors.

[0093] In this embodiment, the historical operation data may include data such as the historical temperature setting value of the air conditioner, the historical operation mode, and the user temperature preference. Among them, the user temperature preference may be one or more temperature setting concentration ranges. For example, the user temperature preference in the air conditioner historical data may be in the range of 25-28 °C.

[0094] In one embodiment, the historical operation data of the air conditioner can be obtained from the storage module of the air conditioner. Among them, the storage module can be in the form of a database or a cloud database to store the historical data of the air conditioner.

[0095] In one embodiment, step S201 may further include performing data preprocessing and feature extraction on the acquired environmental information and historical operation data. Among them, data preprocessing may include data cleaning, standardization, denoising and other processing methods, and feature extraction may adopt extraction methods such as principal component analysis, statistical feature extraction, and feature selection.

[0096] Step S202: Based on the intelligent agent adopted by the air conditioner, generate control strategies and control parameters corresponding to the environmental information and historical operation data.

[0097] In this embodiment, the "control strategies and control parameters" may be equivalent to or can be used to determine the "air conditioner control instruction" in the above embodiments.

[0098] In this embodiment, the intelligent agent can be an intelligent Agent model. Among them, the intelligent Agent model can specifically be any one of a deep learning model, a reinforcement learning model, a machine learning model, and a deep reinforcement learning model.

[0099] In one embodiment, reference can be made to the appendix Figure 3 as shown. The appendix Figure 3 is a schematic diagram of the main step flow of one embodiment for determining the control strategy and control parameters of the air conditioner according to the embodiments of the present application. As Figure 3 shown, step S202 may further include steps S2021 to S2023:

[0100] Step S2021: Input the feature extraction results of the environmental information and historical operation data into the intelligent Agent model.

[0101] Step S2022: The intelligent Agent model generates control strategies through machine learning algorithms based on the feature extraction results.

[0102] Step S2023: The intelligent Agent model determines control parameters based on the feature extraction results.

[0103] In this embodiment, the control strategies may include control strategies such as temperature adjustment strategies and operation mode switching strategies, which can make the air conditioner control results more adaptable to the current environment and user habits.

[0104] In this embodiment, the control parameters may include the temperature setting range, the operating mode to be switched to, the wind speed setting range, etc. For example, the control parameters may include a temperature setting value range of 18 - 28°C, the operating mode being any one of cooling, heating, air supply, etc., and the wind speed range being 1 - 5 levels. Another example is a temperature setting value range of 20 - 26°C, the operating mode being any one of cooling, heating, dehumidifying, etc., and the wind speed range being 2 - 4 levels.

[0105] Step S203: Control the operation of the air conditioner according to the generated control strategy and control parameters.

[0106] In this embodiment, the control module or execution unit of the air conditioner may receive the generated control strategy and control parameters, and perform corresponding control operations to control the operation of the air conditioner.

[0107] Step S204: Determine whether it is necessary to adjust the control strategy of the air conditioner. If so, return to step S201; if not, continue to execute step S203.

[0108] In one embodiment, step S204 may further include steps S2041 to S2043:

[0109] Step S2041: Detect whether there is user feedback on the operating state of the air conditioner through the feedback detection module.

[0110] In this embodiment, the feedback detection module may be a module in the air conditioner for detecting user feedback. Among them, the feedback detection module may detect whether there is user feedback on the operating state of the air conditioner by detecting whether an instruction sent by the user's mobile terminal is received, or whether a user voice control instruction is received.

[0111] In this embodiment, the user's feedback on the operating state of the air conditioner may include instructions sent to the air conditioner through means such as an application (APP) on the mobile terminal, voice control, and manual operation. For example, the user's feedback may include operation instructions such as manually adjusting the temperature and switching the operating mode.

[0112] Step S2042: If so, adjust the control strategy and control parameters according to the user feedback.

[0113] In this embodiment, the operation of the air conditioner can be directly controlled according to the adjusted control strategy and control parameters of the user, so that the operating state of the air conditioner better meets the user's needs and is more adaptable to environmental changes.

[0114] In one embodiment, the air conditioner can operate according to the adjusted control strategy and control parameters until the next air conditioner control process is entered, and then return to step S201.

[0115] Step S2043: Update the intelligent Agent model according to user feedback.

[0116] In this embodiment, step S2043 may specifically include: updating the model parameters in the intelligent Agent model according to user feedback and environmental information.

[0117] Based on the method described in steps S101 to S103 above, this application can effectively perceive changes in the air-conditioning environment by using the obtained real-time environmental information and historical operation data, automatically generate air-conditioning control instructions, and improve the intelligence of air-conditioning control. Moreover, the intelligent agent can adaptively generate air-conditioning control instructions, making the operation of the air conditioner more in line with user habits and user needs, improving the accuracy of air-conditioning temperature adjustment and the comfort optimization ability, enhancing the adaptability of air-conditioning control, and improving the user experience.

[0118] It should be noted that although the above steps are described in a specific order in the above embodiments, those skilled in the art can understand that in order to achieve the effects of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted solutions are equivalent technical solutions to the technical solutions described in this application, and therefore will also fall within the protection scope of this application.

[0119] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments of this application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code.

[0120] On the other hand, this application also provides a computer-readable storage medium.

[0121] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium may be configured to store a program for executing the air conditioner control method in the above method embodiment. This program can be loaded and run by a processor to implement the above air conditioner control method. For ease of description, only parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium may be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0122] Another aspect of the present application also provides a controller.

[0123] In an embodiment of a controller according to the present application, the controller may include at least one processor; and a memory communicatively connected to the at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any of the above embodiments is implemented. Reference may be made to the Figure 4 , Figure 4 in which the memory 11 and the processor 12 are communicatively connected via a bus is exemplarily shown.

[0124] Another aspect of the present application also provides an air conditioner.

[0125] In an embodiment of an air conditioner according to the present application, the air conditioner may include the controller in the above controller embodiment.

[0126] So far, the technical solution of the present application has been described in conjunction with an embodiment shown in the accompanying drawings. However, those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present application.

Claims

1. An air conditioner control method, characterized in that, The method includes: Obtaining the historical operation data and real-time environmental information of the air conditioner; Based on the agent, determining the air conditioner control instruction of the air conditioner according to the historical operation data and the real-time environmental information; Controlling the operation of the air conditioner according to the air conditioner control instruction.

2. The air conditioner control method according to claim 1, wherein The determining the air conditioner control instruction based on the agent according to the historical operation data and the real-time environmental information includes: Performing feature extraction on the historical operation data and the real-time environmental information to obtain a feature extraction result; Based on the agent, determining the target control strategy and target control parameters of the air conditioner according to the feature extraction result; Determining the air conditioner control instruction according to the target control strategy and the target control parameters.

3. The air conditioner control method according to claim 2, wherein The agent is implemented based on at least one of a reinforcement learning algorithm, a machine learning algorithm, and a deep reinforcement learning algorithm.

4. The air conditioner control method according to claim 2, wherein The target control strategy includes at least one of a temperature adjustment strategy, a wind speed adjustment strategy, and an operation mode switching strategy; and / or, The target control parameters include at least one of a temperature setting range, a target operation mode, and a wind speed setting range.

5. The air conditioner control method according to claim 1, wherein After controlling the operation of the air conditioner according to the air conditioner control instruction, the method further includes: Judging whether there is a user feedback instruction; When there is a user feedback instruction, adjusting the air conditioner control instruction according to the user feedback instruction.

6. The air conditioner control method according to claim 5, wherein, The method further includes: Updating the model parameters of the agent according to the user feedback instruction.

7. The air conditioner control method according to claim 1, wherein, The air conditioner includes an environmental information detection unit and a historical data storage unit. The obtaining the historical operation data and the real-time environmental information of the air conditioner includes: Obtaining the real-time environmental information through the environmental information collection unit; Obtaining the historical operation data through the historical data storage unit; Wherein, the environmental collection unit includes at least one of a temperature sensor, a humidity sensor, a wind speed sensor, a human body heat release sensor, and a human body infrared sensor; the real-time environmental information includes at least one of indoor humidity information, outdoor humidity information, indoor temperature information, outdoor temperature information, indoor air flow rate information, outdoor air flow rate information, and indoor personnel activity information of the environment where the air conditioner is located; the historical operation data includes at least one of the historical temperature setting value, the historical operation mode, and the historical wind speed setting value of the air conditioner.

8. A controller, characterized in that, Includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the air conditioner control method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium storing multiple program codes, characterized in that, The program code is adapted to be loaded and run by a processor to execute the air conditioner control method according to any one of claims 1 to 7.

10. An air conditioner, characterized in that, The air conditioner includes the controller described in claim 8.

Images