WO2019084784A1 - Intelligent temperature control method and apparatus, storage medium, central temperature controller and server - Google Patents

Abstract

An intelligent temperature control method, comprising: a central temperature controller (120) receiving information, of a space where a temperature controller (110) is located, uploaded by multiple temperature controllers (110), wherein the information of the space where the temperature controller (110) is located comprises temperature information, humidity information, human body sensing information and user operation information; sending the received information to a server (130) so that the server (130) respectively learns the information, so as to generate a temperature control schedule corresponding to the space; and sending a control instruction to an air conditioning equipment (140) according to the temperature control schedule obtained by learning, so as to intelligently control the temperature of the corresponding space by means of the air conditioning equipment (140). In addition, also disclosed are an intelligent temperature control apparatus (1300), a storage medium, the central temperature controller (120) and a server (130).

Description

Intelligent temperature control method, device, storage medium, central temperature controller and server Technical field

The invention relates to the field of intelligent control technologies, in particular to an intelligent temperature control method, device, storage medium, central temperature controller and server.

Background technique

In the era of rapid development of the Internet and wireless communication technologies, many traditional home appliances are gradually becoming intelligent and networked, and smart home products and systems are gradually spreading to people's homes. Among them, in the field of intelligent temperature control, there are also some very good products. The main advantages and highlights of traditional intelligent thermostats are mostly focused on product design and user interaction design. They all focus on individual products, intelligent temperature control of individual spaces, and lack of systematic solutions to simultaneously implement multiple spaces. Collaborative intelligent temperature control, and the traditional intelligent temperature control method is limited to short-term intelligent temperature control and learning, lacking long-term intelligent temperature control and learning.

Summary of the invention

Based on this, it is necessary to provide an intelligent temperature control method, device, storage medium, central temperature controller and server for the above technical problems.

An intelligent temperature control method, the method comprising:

The central temperature controller receives information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information;

The central temperature controller sends the received information to the server to enable the server to separately learn the information, and generate a temperature control schedule corresponding to the space;

The central temperature controller sends a control command to the air conditioner according to the learned temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

An intelligent temperature control method, the method comprising:

The server receives information received by the central temperature controller from a plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located;

The server separately learns information about the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space;

The server feeds back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

An intelligent temperature control device, the device comprising:

The information receiving module is configured to receive information about a space where the temperature controller is uploaded by the plurality of temperature controllers, where the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information;

a temperature control schedule generating module, configured to send the received information to a server, so that the server separately learns the information, and generates a temperature control schedule corresponding to the space;

The space temperature intelligent control module is configured to send a control instruction to the air conditioning device according to the learned temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioning device.

An intelligent temperature control device, the device comprising:

The information receiving module is configured to receive information received by the central temperature controller and received from the plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located;

a temperature control schedule generation module is configured to separately learn information about a space in which each temperature controller is received, and generate a temperature control schedule corresponding to the space;

a space temperature intelligent control module, configured to feed back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the air conditioner Corresponding to the temperature of the space.

A computer readable storage medium having stored thereon computer readable instructions, the readable instructions being The intelligent temperature control method described above is implemented when the processor executes.

A central temperature controller, the central temperature controller including a display, a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor executing the computer The following steps are implemented when the instructions are readable:

The central temperature controller receives information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information;

The central temperature controller sends the received information to the server to enable the server to separately learn the information, and generate a temperature control schedule corresponding to the space;

The central temperature controller sends a control command to the air conditioner according to the learned temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

A server comprising a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, wherein when the processor executes the computer readable instructions Implement the following steps:

The server receives information received by the central temperature controller from a plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located;

The server separately learns information about the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space;

The server feeds back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

The above intelligent temperature control method, device, storage medium, central temperature controller and server, the central intelligent temperature controller receives information of a space where the temperature controller uploaded by the plurality of temperature controllers is located, and the information includes temperature information, humidity information, and human body sensing information. And user operation information. Sending the received information to the server, so that the server learns the information separately, generates a temperature control schedule corresponding to the space, and then sends a control command to the air conditioner according to the temperature control schedule obtained by the learning, and passes the air conditioner. To intelligently control the temperature of the corresponding space. Because the temperature controller is arranged in each space to collect the information of the corresponding space, the central intelligent temperature controller receives the information, and then analyzes and learns through the server to obtain a temperature control schedule for each space. Finally, the central intelligent temperature controller controls the temperature of each space according to the temperature control schedule, thus solving the problem of intelligent temperature control of multiple spaces at the same time.

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features, objects, and advantages of the invention will be apparent from the description and appended claims.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some embodiments of the present application, Those skilled in the art can also obtain other drawings based on these drawings without any creative work.

1A is an application environment diagram of an intelligent temperature control method in an embodiment;

Figure 1B is an internal structural view of a central temperature controller in one embodiment;

2 is a flow chart of an intelligent temperature control method based on a central temperature controller in one embodiment;

3 is a flow chart of an intelligent temperature control method based on a central temperature controller in still another embodiment;

4 is a flow chart of an intelligent temperature control method based on a central temperature controller in still another embodiment;

FIG. 5 is a schematic diagram of an application of an intelligent temperature control method in a home scene in an embodiment; FIG.

Figure 6 is a diagram showing the internal structure of a server in an embodiment;

7 is a flow chart of a server-based intelligent temperature control method in an embodiment;

8 is a flow chart of a server-based first cycle offline learning in one embodiment;

9 is a flow chart of server-based subsequent enhanced learning in one embodiment;

10 is a flow chart of server-based long-term learning in one embodiment;

Figure 11 is a schematic diagram showing the probability distribution of a plurality of temperature control schedules;

12 is a schematic diagram of intelligent switching of a temperature control schedule based on a directed connectivity graph;

FIG. 13 is a schematic structural diagram of an intelligent temperature control device based on a central temperature controller in one embodiment. Figure

14 is a schematic structural view of an intelligent temperature control device based on a central temperature controller in still another embodiment;

15 is a schematic structural view of an intelligent temperature control device based on a central temperature controller in still another embodiment;

16 is a schematic structural diagram of a server-based intelligent temperature control device in an embodiment;

17 is a schematic structural diagram of a temperature control schedule generation module of FIG. 16;

18 is a schematic structural diagram of the short-term learning module of FIG. 17;

19 is a schematic structural diagram of a subsequent enhanced learning module in FIG. 18;

20 is a schematic structural diagram of the long-term learning module of FIG. 17.

Detailed ways

The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Numerous specific details are set forth in the description below in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar improvements without departing from the scope of the present application, and thus the present application is not limited by the specific embodiments disclosed below.

All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention applies, unless otherwise defined. The terminology used herein is for the purpose of describing particular embodiments, and is not intended to be limiting. The technical features of the above embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, It is considered to be the range described in this specification.

The intelligent temperature control method provided by the embodiment of the present invention can be applied to the environment as shown in FIG. 1A. Referring to FIG. 1, the temperature controller 110 is connected to the central temperature controller 120 via a network, the central temperature controller 120 is connected to the server 130 via a network, and the central temperature controller 120 is connected to the air conditioning device 140 via a network. The central temperature controller 120 may not necessarily be a PC battery The brain can also be an embedded hardware device with high performance of MPU. The input mode can also be a button, a touch screen or a combination of the two. The style can also be more diverse, and the installation can be more convenient, aesthetic and fashionable. The air conditioning unit 140 shown in the drawing is a separate air conditioner (the air conditioner and the air outlet are together), and may also be a central air conditioning system (air conditioner and vent independent) having a ventilation duct layout. For independent individual air conditioners, the central temperature controller 120 can be connected through a network or through a wiring connection; for a central air conditioning system, the central temperature controller 120 is generally controlled by communication with the air conditioner host, and through a local network. Control communication with the vents.

The temperature controller 110 is configured to acquire information about a space, such as temperature information, humidity information, human body sensing information, and user operation information, and a temperature controller 110 is disposed in each space. The user can manually operate the temperature controller 110 to input user operation information. The temperature controller 110 uploads the collected information of each space to the central temperature controller 120, and the central temperature controller 120 transmits the received information to the server 130. The server 130 receives the information and learns the information separately to generate a temperature control schedule corresponding to the space. The server 130 returns the generated temperature control schedule of the corresponding space to the central temperature controller 120, and the central temperature controller 120 sends a control command to the air conditioner 140 according to the learned temperature control schedule, and intelligently controls the corresponding by the air conditioner 140. The temperature of the space. The user can also manually operate the central temperature controller 120 directly. Of course, the user can communicate with the central temperature controller 120 indirectly through the server 130 via the mobile terminal 150.

In one embodiment, as shown in FIG. 1B, a central temperature controller is also provided, including a display, a memory, a processor coupled via a system bus, a network interface, and the like. The user can enter operational information directly on the display. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the central temperature controller stores an operating system, and can also store computer readable instructions that are executed by the processor. This allows the processor to perform an intelligent temperature control method. The central temperature controller's processor is used to increase computation and control capabilities to support the operation of the entire central temperature controller. The internal memory of the central temperature controller can store computer readable instructions that, when executed by the processor, cause the processor to perform an intelligent temperature control method. The network interface is used by the central temperature controller to receive information sent by the temperature controller, and Send information to the server, and send control commands to the air conditioner. It will be understood by those skilled in the art that the structure shown in FIG. 1B is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the central temperature controller to which the solution of the present application is applied, and the specific central The temperature controller may include more or fewer components than shown in the figures, or some components may be combined, or have different component arrangements.

In an embodiment, as shown in FIG. 2, an intelligent temperature control method is provided, which is applied to the central temperature controller in FIG. 1 as an example, and includes:

Step 202: The central temperature controller receives information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information.

Each space is provided with a temperature controller for obtaining information about the space in which it is located, such as temperature information, humidity information, human body sensing information, and user operation information. The human body sensing information refers to a kind of characteristic information acquired by a sensor capable of acquiring specific information that the human body may generate, including but not limited to infrared radiation information, sounds emitted by a person, images, and the like. The temperature controller has a simple visualization function and a basic temperature setting function. When the user is in the space, the user can directly input the temperature control information by manually operating the temperature controller. The temperature controller uploads information about the collected space to a central temperature controller that receives information uploaded by multiple temperature controllers. Centralized temperature control is performed uniformly by the central temperature controller.

Step 204: The central temperature controller sends the received information to the server to enable the server to separately learn the information, and generate a temperature control schedule corresponding to the space.

The central temperature controller sends the received information of each space, such as temperature information, humidity information, human body sensing information, and user operation information, to the server in the cloud. The visual information of the central temperature controller, the content that the user can set and view is more abundant, and the way the user interacts is more complicated. The server receives the information and learns the information of each space separately, and generates a temperature control schedule corresponding to the space after learning. The temperature control schedule records an instruction for predicting the temperature control of the current space according to the learning algorithm. The server sends the temperature control schedule of the corresponding space generated to the central temperature controller.

Step 206: The central temperature controller sends a control command to the air conditioner according to the learned temperature control schedule, and intelligently controls the temperature of the corresponding space by using the air conditioner.

The central temperature controller receives the temperature control schedule sent by the server, and the temperature control schedule records an instruction that predicts the temperature control of the current space according to the learning algorithm. The control command is sent to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. For centralized equipment of the central air conditioning type, the air temperature is used to control the indoor temperature, so the air conditioning equipment refers to the ventilation holes of the central air conditioner. For temperature control by air conditioners, fans, or heating units installed in each space, air conditioners refer to air conditioners, fans, or heating units installed in each space.

In this embodiment, the central intelligent temperature controller receives information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information includes temperature information, humidity information, human body sensing information, and user operation information. Sending the received information to the server, so that the server learns the information separately, generates a temperature control schedule corresponding to the space, and then sends a control command to the air conditioner according to the temperature control schedule obtained by the learning, and intelligently controls the corresponding space through the air conditioner. temperature. Because the temperature controller is arranged in each space to collect the information of the corresponding space, the central intelligent temperature controller receives the information, and then analyzes and learns through the server to obtain a temperature control schedule for each space. Finally, the central intelligent temperature controller controls the temperature of each space according to the temperature control information, thus solving the problem of intelligent temperature control of multiple spaces at the same time.

In an embodiment, as shown in FIG. 3, the method further includes: Step 208: The central temperature controller receives the user operation information sent by the mobile terminal, and sends the received information to the server.

In this embodiment, when the user is not in the space, that is, remotely operated, the user operates on the mobile terminal, and the operation information is transmitted to the central temperature controller through the mobile terminal. For example, information interaction with a central intelligent temperature controller can be accomplished by application readable instructions installed on the mobile terminal. The central intelligent temperature controller receives this information and sends the received information to the server. The server learns information obtained from a plurality of temperature controllers together with information acquired from the mobile terminal. It solves the problem of remotely regulating the temperature in the space when the user is not in the space.

In one embodiment, as shown in FIG. 4, the method further includes: step 210, central temperature control The device feeds the learned temperature control schedule to the temperature controller of the corresponding space for display so that the user can know.

In this embodiment, the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. Each space is equipped with a temperature controller, and each temperature controller can display real-time temperature, humidity and other information in the current space. So that the user in the space can intuitively know the current temperature and humidity and other information in the space. If the user feels that the real-time temperature, humidity and other information in the current space displayed on the temperature controller is not suitable, it can be manually set directly through the temperature controller.

In one embodiment, an intelligent temperature control method is also provided, which is exemplified for application in the environment as shown in FIG.

Figure 5 shows an intelligent temperature control method used in a home scene. There are 4 rooms in the home scene, and a central air conditioner is installed in the home. Ventilation holes for the central air conditioner are installed in each room. User 1, User 2, and User 3 are each in their own room, User 4 is in the space where the central intelligent temperature controller is located, and User 5 is located in the remote outdoor. Among them, the users 1, 2, and 3 can directly operate the temperature controllers (referred to as temperature controllers) of the respective spaces to perform temperature regulation of the space. The user 4 can directly operate the central temperature controller manually to perform operational input and setting of the temperature controller for all spaces (including the space in which the user 4 is located), and to observe the operating state of the entire temperature control system. The user 5 can operate remotely on the mobile terminal, and then communicate with the central temperature controller indirectly through the cloud data server, thereby realizing remote control of the temperature of any space in the home. For example, information interaction with a central intelligent temperature controller can be accomplished by application readable instructions installed on the mobile terminal. Thereby, the purpose of controlling the temperature of the room in the home when the user is not in the home is realized. Finally, the central temperature controller sends a control command to each venting hole of the central air conditioner according to the received information, and the ventilating holes of the central air conditioner control the temperature of the corresponding room. Of course, it is also possible to install a fan in the room in the home, which is equivalent to the ventilation hole of the central air conditioner. Similarly, the central temperature controller sends a control command to the fans in each room according to the received information, and the fan is used to The temperature of the corresponding room is controlled.

In an embodiment, as shown in FIG. 6, a server is further provided, and the server includes A processor, memory, network interface, etc. connected to the system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the server stores an operating system, and can also store computer readable instructions. When the computer readable instructions are executed by the processor, The processor is caused to perform an intelligent temperature control method. The server's processor is used to increase computing and control capabilities and support the operation of the entire server. The computer's internal memory can store computer readable instructions that, when executed by the processor, cause the processor to perform an intelligent temperature control method. The network interface is used by the server to receive the information sent by the central temperature controller, and send the temperature control schedule of the corresponding space generated by the server to the central temperature controller, where the network interface is further configured to receive the user operation information sent by the mobile terminal and move to the mobile terminal. The terminal sends a message that the operation is successful. It will be understood by those skilled in the art that the structure shown in FIG. 6 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied. The specific server may include a ratio. More or fewer components are shown in the figures, or some components are combined, or have different component arrangements.

In an embodiment, as shown in FIG. 7, an intelligent temperature control method is further provided, which is applied to the server in FIG. 1 as an example, and includes:

Step 702: The server receives information received by the central temperature controller and received from the plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located.

Each space is provided with a temperature controller for obtaining information about the space in which it is located, such as temperature information, humidity information, human body sensing information, and user operation information. Multiple temperature controllers send the collected information to the central temperature controller, which then forwards the information to the server, which receives the information.

Step 704: The server separately learns information about the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space.

The server processes the received information. Specifically, the server performs short-term learning and long-term learning on the information of the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space. In the learning process, it is conducted on a weekly basis, and short-term learning includes the first cycle offline. Learn and follow up to strengthen learning. The first cycle of offline learning is the process of learning the information of the space collected in the first week after the intelligent temperature control is started. On the basis of being as close as possible to the user's usage, intelligent analysis and learning of the user's operation behavior is carried out to achieve appropriate analysis and adjustment learning on the basis of keeping the user's habits as constant as possible, and to generate the original temperature of the first cycle. Control the schedule. The core purpose of the follow-up reinforcement learning is to adapt and adjust the behavior of the user's subsequent temperature control habits, update the fusion of relevant learning results on the basis of the previously generated temperature control schedule, and generate a new temperature control schedule. To achieve intelligent tracking of changes in user behavior.

Due to the long-term seasonal changes, the user's behavior will change greatly. Therefore, a behavioral habit generated by the short-term learning algorithm cannot satisfy all the habit changes of the user in one year. A method for long-term learning of the information of the space in which each temperature controller is located is proposed, in particular, an intelligent switching algorithm based on an alternative temperature control schedule. During the use of the user within one year, the user will automatically or custom generate and save a number of temperature control schedules for a specific period of time as an alternative temperature control schedule according to the user's behavioral habits. The probability temperature distribution is adopted for the alternative temperature control schedule, and the temperature control schedule suitable for the current cycle is screened according to the effective probability of the candidate temperature control schedule in the current cycle. On the basis of the temperature control schedule, follow-up reinforcement learning is carried out, and when the user's subsequent temperature control habits change, the behavior is adapted and adjusted, and the fusion of relevant learning results is updated based on the previous temperature control schedule to generate new The temperature control schedule to achieve intelligent tracking of changes in user behavior habits.

Step 706: The server feeds back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

The server feeds back the latest temperature control schedule currently generated to the central temperature controller. The central temperature controller receives the latest temperature control schedule, sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner. Specifically, the air conditioning device can heat or cool the corresponding space. For example, the information for an office on Monday in a cycle recorded in the generated temperature control schedule is:

time temperature Relative humidity

9:00-12:00 25°C 30% 12:00-13:30 26°C 30% 13:30-18:00 23 ° C 50%

According to the information in the above table, the temperature of an office on Monday in the next cycle is controlled according to this temperature control schedule.

In one embodiment, the server separately learns information about the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space, including: information about the space in which each server receives the temperature controller. Conduct short-term and long-term learning to generate a temperature control schedule for the corresponding space.

The traditional intelligent temperature control method is limited to short-term intelligent temperature control and learning, but due to the seasonal changes in the long period of one year, the user's behavior will change greatly. Short-term learning focuses only on changes in recent user behavior and does not quickly sense this seasonal change. Therefore, a long-term learning algorithm based on the alternative temperature control schedule for intelligent switching is proposed. The temperature control schedule of a particular node within one year is marked with an alternative temperature control schedule, for example, 4 temperature control can be used. The schedule represents the basic temperature control schedule for the four seasons of spring, summer, autumn and winter, and marks the use of the corresponding temperature control schedule at a specific time of the year. Of course, you can also set up more than four temperature-controlled schedules for more precise marking of the temperature change schedules that occur during the year. For example, the alternate temperature control schedule may include an original temperature control schedule for the first cycle, a temperature control schedule learned to be generated when a user's large fluctuation adjustment behavior occurs, a temperature control schedule generated when the user selects to relearn, and The temperature control schedule generated by learning when small fluctuation adjustment behavior occurs in consecutive cycles. Using short-term learning combined with long-term learning for temperature control, it can realize real-time learning of user behavior in a short period of time, and can adjust the temperature control schedule in a timely manner within a long period of one year, so that it can sense the season. A change or a mutation in some other user's operational behavior.

In an embodiment, the server performs short-term learning on the information of the space in which each temperature controller is received, including: the server performs the first cycle offline learning and subsequent information on the space of each temperature controller received. Enhance learning.

Short-term study is divided into 2 steps. The first step is offline learning in the first cycle, which is the first week. The information received (in cycles) is learned to generate the original temperature control schedule for the first cycle. The second step is to strengthen learning in the subsequent step, that is, based on the original temperature control schedule of the first cycle generated, on the basis of which the subsequent information is received in real time, and learning is performed, and a cycle temperature control is generated in each cycle. schedule. So for a week, I have been learning.

In one embodiment, the server performs the first periodic offline learning on the information of the space in which each temperature controller is received, including: the server receives the first cycle obtained by the central temperature controller and obtained from multiple temperature controllers. The historical information of the space where the temperature controller is located; the server sorts the historical information according to the preset rules to the original temperature control schedule of the first cycle.

Please refer to Figure 8 for the flow chart of the first cycle offline learning. As shown in FIG. 8 , when the server performs intelligent temperature control on the scene as shown in FIG. 1 , firstly, system parameter initialization and user parameter initialization are performed on the entire temperature control system described in the scenario, and the temperature control schedule is initialized. Then, the central temperature controller receives real-time information about the space in which each temperature controller is located, such as temperature information, humidity information, human body sensing information, and user operation information. The received information is organized and learned through rules such as basic rules, error correction rules, compensation rules, and similar operation rules. Determine whether a cycle of learning is completed, and if so, generate a temperature control schedule for the first cycle, and if not, continue to receive information on the space in which each temperature controller is located in real time, and pass basic rules, error correction rules, Compensatory rules, similar operational rules and other rules organize the learning of the received information until one cycle, one week of learning, is completed, and the final temperature control schedule is generated as the original temperature control schedule for the first cycle.

In one embodiment, as shown in the figure, the server separately performs subsequent reinforcement learning on the information of the space in which each temperature controller is received, including:

Step 902: The server receives the information of the space of the temperature controller of the next cycle acquired by the central temperature controller from the plurality of temperature controllers in real time.

After the first cycle of offline learning, the original temperature control schedule for the first cycle is generated, and then the subsequent enhanced learning begins. Like the first cycle, multiple pieces of information are sent to the central temperature controller, which then forwards the information to the server, which receives the information.

In step 904, the server sorts the information according to a preset rule.

After the server receives the information, it sorts the information. Specifically, the received information is organized and learned according to rules such as basic rules, error correction rules, compensation rules, and similar operation rules. The basic rule refers to automatically saving each time the temperature input value and the duration time setting information, and recording the corresponding date and time information, and modifying the corresponding initial desired temperature in the temperature control schedule according to the three pieces of information. The initial desired temperature is the preset initial temperature at which the temperature control schedule is initialized. Generally, the initial temperature is a temperature value that is slightly higher (cooling mode) or lower (heating and heating) than the human body comfort temperature, that is, a temperature value that is not comfortable. There are two reasons for this design: First, the initial stage requires the user to make multiple adjustments according to their own habits, so that the learning information is more accurate and sufficient; second, such initial temperature will be more biased towards the concept of energy saving.

The error correction rule means that if the time of setting the action twice is too short, the interval time range may be any value between 30-60 minutes. Of course, other time ranges less than 30 minutes or more than 60 minutes may be set according to actual conditions. . And the latter setting is within the previous set time range, then the user's desired temperature value is learned according to the subsequent setting behavior. The error correction rule is used to correct some operation errors of the user, and avoids the user's wrong operation, thereby affecting the accuracy of the learning result.

The compensation rule means that if the end of the two adjacent adjustment actions is short and the start time interval is short, the interval is ignored, and the desired temperature between the two adjacent adjustment actions is compensated according to the latter set temperature. The interval can be set to no more than 30 minutes. Of course, it can be set to not exceed the other durations according to the actual situation.

For the input of the user in a preset period, the temperature control schedule is organized according to the basic rules, the error correction rules, and the compensation rules, and then the temperature control schedule after the finishing is learned. The human body sensing rule learning is triggered when a similar user setting is detected. If it is not a similar user setting, no more modifications will be made, and online reinforcement learning will continue to adapt and adjust. If, within one cycle, the user has performed user setting operations on the temperature controller for more than three days at the same time period, and the temperature range set by the user does not exceed 5 °C, these operations are said to be similar user operations. Specifically, the length of the same time period can be set to 60 minutes, and of course, it can be set to other durations. Temperature range is not the same More than 5 ° C, can also be other values. For example, if the user performs user setting operations on the temperature controller for 3 consecutive days of AM: 7:00-8:00, these operations are said to be similar user operations. The human body induction rule learning includes the home adjustment rule and the home adjustment rule, wherein the home adjustment rule refers to setting the user if a human body sudden change occurs, and the user setting is performed within half an hour near the sudden change point. 20 minutes in advance. The home adjustment rule means that if a home-induced human mutation occurs and the user setting is made within half an hour after the sudden change point, the user set point is advanced by 20 minutes. The human body induction mutation refers to the change of the signal of the human body sensing sensor, such as the sensing signal is no one becomes a human, or the sensing signal changes from a human to a human. When the inductive signal is turned into a human being, the human body has a sudden change in the human body, and the sensor signal changes from human to human. By learning from the home adjustment rules and the home adjustment rules, the user's operation can be automatically advanced or pushed back automatically, so that the user has turned off or reduced the operation of the air conditioner before leaving the home, and the air conditioner has been turned on before the user returns home. Equipment to achieve intelligent energy-saving effects.

Similar user setting detection rules refer to checking similar user settings. If there are similar user settings, and the range of user setting temperatures does not exceed 5 degrees, the human body sensing rule learning is triggered.

Step 906: On the basis of the original temperature control schedule, the server learns the user small fluctuation adjustment behavior occurring within one day in the collated information, and filters the user according to the similar operation rule in the current period in the collated information. The similar operation is performed, and the temperature fluctuation schedule of the corresponding space in the current period is learned by learning the large fluctuation adjustment behavior of the user occurring in the current period in the collated information.

Based on the original temperature control schedule, the server learns the collated information. Specifically, the server checks the small fluctuation adjustment behavior of the user through the small fluctuation adjustment rule every day, and checks whether the similar user operation occurs in the previous cycle after each period ends, and checks the user's large fluctuation adjustment behavior through the large fluctuation rule to learn. . The small fluctuation adjustment rule means that if the user performs a plurality of control inputs (for example, 5 times) on a single day, the learning adjustment is automatically performed for the temperature control schedule of the day. The large fluctuation adjustment rule means that if the user performs a plurality of manual setting learning operations (for example, 30 times) in a complete cycle, the periodic learning of the cycle is automatically performed based on the operation in the cycle to generate a new temperature control schedule. . The above user operation can be by setting the temperature in the room The controller can also be a central temperature controller or a mobile terminal.

In step 908, the server feeds back the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner.

Step 910: The server loops into the real-time receiving information of the space of the temperature controller of the next cycle acquired by the central temperature controller and sent by the plurality of temperature controllers, and sorts the information according to a preset rule, and performs temperature control in the previous cycle. Based on the schedule, the steps of learning are performed until the temperature control schedule of the corresponding space in the current period is obtained, and the learned temperature control schedule is fed back to the central temperature controller, so that the central temperature controller according to the temperature control schedule The air conditioner sends a control command to intelligently control the temperature of the corresponding space through the air conditioner.

After the learning of the second cycle, the server feeds back the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls through the air conditioner. Corresponding to the temperature of the space. Then the server starts the third cycle of learning, so loop learning. Specifically, each time, based on the temperature control schedule generated in the previous cycle, the subsequent enhanced learning is performed until the temperature control schedule of the corresponding space in the current cycle is obtained, and the temperature control is performed according to the temperature control schedule in real time. .

In one embodiment, as shown in FIG. 10, the server separately learns the information of the space in which each temperature controller is received, including:

Step 1002: Obtain an optional temperature control schedule, where the optional temperature control schedule includes an original temperature control schedule of the first period, a temperature control schedule generated by learning when a user's large fluctuation adjustment behavior occurs, and a re-learning at the user selection The temperature control schedule generated at the time and the temperature control schedule generated when the small fluctuation adjustment behavior occurs in consecutive cycles.

The temperature control schedules generated by these four methods reflect the changes in user behavior habits, so information such as temperature control data, table generation date, and maintenance work time of these temperature control schedules can be saved as follow-up on similar dates. The basis for automatic switching.

In step 1004, the server calculates an effective probability of distribution of each of the candidate temperature control schedules over time in the preset period.

Since each specific temperature control schedule, that is, the learning and formation date of the schedule, generally lags behind the user's behavior habits, and the duration is not necessarily the same, the scheme considers the intelligent switching method based on the probability distribution. Specifically, the algorithm first needs to calculate the effective probability size P of each schedule over time, and then compares the effective probability of all candidate schedules. When the schedule with the highest probability changes, the user is prompted to automatically schedule the schedule. Switch.

FIG. 11 is a schematic diagram of a probability distribution of a plurality of schedules. The form of the probability distribution curve is just a description. The effective probability value of each schedule can be designed and calculated according to the following functions:

P _{schedule x} (day)=F(M,T _start ,T _end ,change)

Day,T _start ,T _end ∈[0,365],x=a,...,b,...,m,...n

Among them, :P _{schedule x} (day) indicates the effective probability of Schedule x on the first day of the year.

F(M, T _start , T _end , change) represents the function of calculating P, which is mainly related to the following parameters:

M: the way to generate Schedule x, T _start : the start time of Schedule x, and the end time of _{End of} Schedule x;

Change: Schedule x is constantly modified and adjusted during the period of use. The basic logic is: As the number of times of modification is increased, the effective probability P of Schedule x decreases continuously, and the effective probability P of the next Schedule increases.

Step 1006: The server obtains the temperature control schedule with the highest effective probability from the candidate temperature control schedule by comparing the effective probability of the candidate temperature control schedule in the current cycle, and uses the temperature control schedule as the temperature control schedule of the current cycle. The table feeds the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner.

Converting the schematic diagram of the probability distribution of the plurality of schedules shown in FIG. 11 above into The schematic diagram of the intelligent control schedule of the directed connected graph is shown in FIG. In the current cycle, by comparing the effective probability of the alternative temperature control schedule, the server can filter out the temperature control schedule with the highest effective probability as the temperature control schedule of the current cycle. For the long-cycle situation, when the user's temperature control habits change greatly, the demand for long-term intelligent temperature control is realized through the intelligent transition switching scheme based on the temperature-controlled schedule of the directed connectivity graph. The traditional intelligent temperature control method is only limited to short-term intelligent temperature control and learning, and can not achieve long-term intelligent temperature control.

In one embodiment, the preset rules include basic rules, error correction rules, make-up rules, and similar operational rules.

The basic rule refers to automatically saving each time the temperature input value and the duration time setting information, and recording the corresponding date and time information, and modifying the corresponding initial desired temperature in the temperature control schedule according to the three pieces of information. The initial desired temperature is the preset initial temperature at which the temperature control schedule is initialized.

The error correction rule means that if the time of setting the action twice is too short, the interval time range may be any value between 30-60 minutes. Of course, other time ranges less than 30 minutes or more than 60 minutes may be set according to actual conditions. . And the latter setting is within the previous set time range, then the user's desired temperature value is learned according to the subsequent setting behavior. For example, the user sets AM at 9:00 am on a certain day of the cycle: 21°C at 9:00-12:00, and AM at 9:30-12:00 at 9:30. It is 25 ° C. The preset interval length is up to 40 minutes, because only 30 minutes are separated between 9:00 and 9:30, which is less than the preset interval duration, and the time range set by the user at 9:30 is set in the previous time. Within the time range, it is suitable for the error correction rule, that is, the user's desired temperature is determined to be 25 ° C according to the temperature set at 9:30. The error correction rule is used to correct some operation errors of the user, and avoids the user's wrong operation, thereby affecting the accuracy of the learning result.

The compensation rule means that if the end of the two adjacent adjustment actions is short and the start time interval is short, the interval is ignored, and the desired temperature between the two adjacent adjustment actions is compensated according to the latter set temperature. The interval can be set to no more than 30 minutes. Of course, it can be set to not exceed the other durations according to the actual situation. For example, the user's first setting is AM: 9:00-12:00, temperature is 25 °C, second The secondary setting is PM: 12:10-17:00 and the temperature is 20 °C. Because the middle is only 10 minutes apart and less than 30 minutes can be ignored, so the next set of 20 ° C to define the temperature of 10 minutes.

The similar operation rule means that if the user has performed user setting operation on the temperature controller for more than three days in one cycle, and the temperature range set by the user does not exceed 5 °C.

In one embodiment, as shown in FIG. 13, an intelligent temperature control device 1300 is provided, the device comprising:

The information receiving module 1302 is configured to receive information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information about the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information.

The temperature control schedule generation module 1304 is configured to send the received information to the server, so that the server separately learns the information, and generates a temperature control schedule corresponding to the space.

The space temperature intelligent control module 1306 is configured to send a control instruction to the air conditioner according to the learned temperature control schedule, and intelligently control the temperature of the corresponding space by using the air conditioner.

In an embodiment, as shown in FIG. 14, an intelligent temperature control apparatus 1300 further includes: a mobile terminal information sending module 1308, configured to receive user operation information sent by the mobile terminal, and send the received information to server.

In an embodiment, as shown in FIG. 15, an intelligent temperature control device 1300 further includes: a display module 1310, configured to feed back the learned temperature control schedule to a temperature controller of the corresponding space for display. Make the user aware.

In one embodiment, as shown in FIG. 16, an intelligent temperature control device 1600 is also provided, the device comprising:

The information receiving module 1620 is configured to receive information received by the central temperature controller from a plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located.

The temperature control schedule generation module 1640 is configured to separately learn information about the space in which each temperature controller is received, and generate a temperature control schedule corresponding to the space.

The space temperature intelligent control module 1660 is used for feeding back the temperature control schedule to the central temperature controller. The central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

In one embodiment, as shown in FIG. 17, the temperature control schedule generation module 1640 includes: a short-term learning module 1641 and a long-term learning module 1642, configured to perform short-term information on the space in which each of the received temperature controllers is received by the server. Learning and long-term learning, generating a temperature control schedule for the corresponding space.

In an embodiment, as shown in FIG. 18, the short-term learning module 1641 includes: a first periodic offline learning module 1643, configured to perform, by the server, the first periodic offline learning information of the space in which each of the received temperature controllers is located; The subsequent enhanced learning module 1644 is configured to perform subsequent enhanced learning on the information of the space in which each of the received temperature controllers is received by the server.

In one embodiment, the first periodic offline learning module 1643 is configured to receive historical information of a space where the first periodic temperature controller is obtained from the plurality of temperature controllers sent by the central temperature controller; and the historical information is according to a preset rule. Organize the original temperature control schedule for the first cycle.

In one embodiment, as shown in FIG. 19, the subsequent enhanced learning module 1644 includes:

The next period information receiving module 1644a is configured to receive, in real time, information of a space where the temperature controller of the next cycle acquired by the central temperature controller is sent from the plurality of temperature controllers.

The collating module 1644b is configured to sort the information according to a preset rule.

The learning module 1644c is configured to learn, according to the original temperature control schedule, the small fluctuation adjustment behavior of the user occurring within one day in the collated information, and filter out the information according to the similar operation rules in the current period in the collated information. The user similar operation performs learning, and learns the temperature fluctuation schedule of the corresponding space in the current period by learning the large fluctuation adjustment behavior of the user occurring in the current period in the collated information.

The control module 1644b is configured to feed back the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

The loop module 1644e is configured to cycle into the real-time receiving information of the space of the temperature controller of the next cycle acquired by the central temperature controller and sent by the plurality of temperature controllers, according to a preset rule The information is collated, and the learning step is performed on the basis of the previous cycle temperature control schedule until the temperature control schedule of the corresponding space in the current cycle is obtained, and the learned temperature control schedule is fed back to the central temperature controller to The central temperature controller is sent a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner.

In one embodiment, as shown in FIG. 20, the long term learning module 1642 includes:

The optional temperature control schedule acquisition module 1642a is configured to obtain an alternate temperature control schedule, where the alternate temperature control schedule includes an original temperature control schedule of the first period, and the temperature generated by learning when the user has large fluctuation adjustment behavior occurs. Control the schedule, the temperature control schedule generated when the user chooses to relearn, and the temperature control schedule that is learned when small fluctuation adjustment behavior occurs in consecutive cycles.

The alternative temperature control schedule effective probability calculation module 1642b is configured to calculate an effective probability of distribution of each of the candidate temperature control schedules over time in the preset period.

The screening module 1642c is configured to obtain the temperature control schedule with the highest effective probability from the candidate temperature control schedule by comparing the effective probability of the candidate temperature control schedule in the current period, and use the temperature control schedule as the temperature of the current period. The control schedule feeds the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner.

In one embodiment, a computer readable storage medium is provided having stored thereon computer readable instructions that, when executed by a processor, implement the steps of: receiving, by a central temperature controller, a plurality of temperature controllers The information of the space where the temperature controller is located, the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information; the central temperature controller sends the received information to the server to enable the server to separately learn the information. A temperature control schedule corresponding to the space is generated; the central temperature controller sends a control command to the air conditioner according to the learned temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner.

In one embodiment, when the readable instructions are executed by the processor, the following steps are further implemented: the central temperature controller receives user operation information sent by the mobile terminal, and transmits the received information to the server.

In one embodiment, the readable instructions described above are further executed by the processor to implement the following steps: The temperature controller feeds the learned temperature control schedule to the temperature controller of the corresponding space for display so that the user can know.

In one embodiment, there is also provided a computer readable storage medium having stored thereon computer readable instructions that, when executed by a processor, implement the steps of: receiving, by a server, a plurality of transmissions from a central temperature controller The information received by the temperature controller includes temperature information, humidity information, human body sensing information and user operation information of the space where the temperature controller is located; the server separately learns the information of the space in which each temperature controller is received, and generates a corresponding space. The temperature control schedule; the server feeds the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner.

In one embodiment, when the readable instructions are executed by the processor, the server further implements the following steps: the server separately performs short-term learning and long-term learning on the information of the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space. .

In one embodiment, when the readable instructions are executed by the processor, the following steps are further performed: the server performs the first periodic offline learning and the subsequent enhanced learning on the information of the space in which each of the received temperature controllers is received.

In one embodiment, when the readable instructions are executed by the processor, the following steps are further performed: the server receives historical information of a space where the first periodic temperature controller is obtained from the plurality of temperature controllers and sent by the central temperature controller; According to the preset rules, the historical information is sorted out of the original temperature control schedule of the first cycle.

In one embodiment, when the readable instructions are executed by the processor, the following steps are further implemented: the server receives, in real time, information about a space of a temperature controller of a next cycle acquired by the central temperature controller and sent by the plurality of temperature controllers; According to the preset rules, the information is sorted; on the basis of the original temperature control schedule, the server learns the small fluctuation adjustment behavior of the user occurring within one day in the collated information, and the similar information in the current period is similar according to the collated information. The user-like operation selected by the operation rule learns, learns the user's large fluctuation adjustment behavior occurring in the current period in the collated information, and generates a temperature control schedule corresponding to the space in the current period; the server will learn The temperature control schedule is fed back to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the temperature of the corresponding space through the air conditioner; the server loops into the real-time receiving central temperature controller. Sending the information of the space of the temperature controller of the next cycle acquired from the plurality of temperature controllers, sorting the information according to the preset rule, and performing the learning step on the basis of the previous cycle temperature control schedule until the The temperature control schedule of the corresponding space in the current cycle feeds the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls through the air conditioner. Corresponding to the temperature of the space.

In one embodiment, when the readable instructions are executed by the processor, the following steps are further implemented: the server obtains an alternate temperature control schedule, the alternate temperature control schedule includes an original temperature control schedule of the first period, and the user occurs The temperature control schedule generated by the learning when the large fluctuation adjustment behavior is performed, the temperature control schedule generated when the user selects the re-learning, and the temperature control schedule generated when the small fluctuation adjustment behavior occurs in consecutive periods; the server calculates the preset The effective probability of each alternative temperature control schedule distributed over time in the cycle; the server obtains the temperature control schedule with the highest effective probability from the alternative temperature control schedule by comparing the effective probability of the alternative temperature control schedule in the current cycle The temperature control schedule is used as the temperature control schedule of the current cycle, and the learned temperature control schedule is fed back to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, Air conditioning equipment to intelligently control the temperature of the corresponding space.

In one embodiment, the readable instructions are further executed by the processor to implement the following steps: the preset rules include basic rules, error correction rules, make-up rules, and similar operational rules.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiments can be completed by computer readable instructions, and the readable instructions can be stored in a non-volatile computer readable. In a storage medium, as in an embodiment of the invention, the readable instructions are stored in a storage medium of a computer system and executed by at least one processor in the computer system to implement a process comprising an embodiment of the methods described above . The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The technical features of the above embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, It is considered to be the range described in this specification.

The above-described embodiments are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the scope of the invention should be determined by the appended claims.

Claims (23)

An intelligent temperature control method, the method comprising: The central temperature controller receives information about a space where the temperature controller is uploaded by the plurality of temperature controllers, and the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information; The central temperature controller sends the received information to the server to enable the server to separately learn the information, and generate a temperature control schedule corresponding to the space; The central temperature controller sends a control command to the air conditioner according to the learned temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. The method of claim 1 further comprising: The central temperature controller receives the user operation information sent by the mobile terminal, and sends the received information to the server. The method of claim 1 further comprising: The central temperature controller feeds back the learned temperature control schedule to the temperature controller of the corresponding space for display so that the user can know. An intelligent temperature control method, the method comprising: The server receives information received by the central temperature controller from a plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located; The server separately learns information about the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space; The server feeds back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. The method according to claim 4, wherein the server separately learns the information of the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space, including: The server separately performs short-term learning and long-term learning on the information of the space in which each temperature controller is received, and generates a temperature control schedule corresponding to the space. The method according to claim 5, wherein the server separately performs short-term learning on the information of the space in which each temperature controller is received, including: The server performs the first periodic offline learning and subsequent enhanced learning on the information of the space in which each temperature controller is received. The method according to claim 6, wherein the server performs the first periodic offline learning on the information of the space in which each temperature controller is received, including: The server receives historical information of a space where the temperature controller is located in a first cycle obtained by the central temperature controller and sent from the plurality of temperature controllers; The server sorts the historical information according to a preset rule to the original temperature control schedule of the first cycle. The method according to claim 6, wherein the server separately performs subsequent reinforcement learning on the information of the space in which each temperature controller is received, including: The server receives the information of the space of the temperature controller of the next cycle acquired by the central temperature controller from the plurality of temperature controllers in real time; The server sorts the information according to a preset rule; On the basis of the original temperature control schedule, the server learns the small fluctuation adjustment behavior of the user occurring within one day in the collated information, and filters the similar information in the current period in the collated information. The user-like operation is performed to learn, and the user's large fluctuation adjustment behavior occurring in the current period in the collated information is learned to generate a temperature control schedule corresponding to the space in the current period; The server feeds the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control instruction to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner; The server loops into the real-time receiving information of the space of the temperature controller of the next cycle acquired from the plurality of temperature controllers sent by the central temperature controller, and the information is compared according to a preset rule. Organize and perform the learning step on the basis of the previous cycle temperature control schedule until the temperature control schedule of the corresponding space in the current cycle is obtained, and the learned temperature control schedule is fed back to the central temperature controller, so that The central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. The method according to claim 7, wherein the server separately performs long-term learning on the information of the space in which each temperature controller is received, including: The server obtains an alternate temperature control schedule, the alternate temperature control schedule including an original temperature control schedule of the first period, a temperature control schedule generated by learning when a user large fluctuation adjustment behavior occurs, and a re-learning at the user selection The temperature control schedule generated at the time and the temperature control schedule generated by learning when small fluctuation adjustment behavior occurs in consecutive cycles; The server calculates an effective probability of distribution of each candidate temperature control schedule over time in a preset period; The server obtains the temperature control schedule with the highest effective probability from the candidate temperature control schedule by comparing the effective probability of the candidate temperature control schedule in the current cycle, and uses the temperature control schedule as the temperature control schedule of the current cycle. And feeding the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control instruction to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. The method according to claim 7, wherein the preset rules include basic rules, error correction rules, compensation rules, and similar operation rules. An intelligent temperature control device, characterized in that the device comprises: The information receiving module is configured to receive information about a space where the temperature controller is uploaded by the plurality of temperature controllers, where the information of the space where the temperature controller is located includes temperature information, humidity information, human body sensing information, and user operation information; a temperature control schedule generating module, configured to send the received information to a server, so that the server separately learns the information, and generates a temperature control schedule corresponding to the space; The space temperature intelligent control module is configured to send a control instruction to the air conditioning device according to the learned temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioning device. The device according to claim 11, wherein the device further comprises: The mobile terminal information sending module is configured to receive user operation information sent by the mobile terminal, and send the received information to the server. The device according to claim 11, wherein the device further comprises: And a display module, configured to feed back the learned temperature control schedule to a temperature controller of the corresponding space for display so that the user can know. An intelligent temperature control device, characterized in that the device comprises: The information receiving module is configured to receive information received by the central temperature controller and received from the plurality of temperature controllers, where the information includes temperature information, humidity information, human body sensing information, and user operation information of a space where the temperature controller is located; a temperature control schedule generation module is configured to separately learn information about a space in which each temperature controller is received, and generate a temperature control schedule corresponding to the space; a space temperature intelligent control module, configured to feed back the temperature control schedule to the central temperature controller, so that the central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and intelligently controls the air conditioner Corresponding to the temperature of the space. The device according to claim 14, wherein the temperature control schedule generation module comprises: The short-term learning module and the long-term learning module are used by the server to perform short-term learning and long-term learning on the information of the space in which each temperature controller is received, and generate a temperature control schedule corresponding to the space. The device according to claim 15, wherein the short-term learning module comprises: The first periodic offline learning module is configured to perform the first periodic offline learning on the information of the space in which each temperature controller is received by the server; The subsequent enhanced learning module is used by the server to perform subsequent enhanced learning on the information of the space in which each temperature controller is received. The apparatus according to claim 16, wherein said first periodic offline learning module is configured to receive a space of a temperature controller in a first cycle acquired from a plurality of temperature controllers sent by a central temperature controller Historical information; the historical information is sorted out according to a preset rule to the original temperature control schedule of the first cycle. The device according to claim 16, wherein the subsequent enhanced learning module comprises: a next period information receiving module, configured to receive, in real time, information of a space in which the temperature controller is located in a next cycle acquired by the central temperature controller and sent from the plurality of temperature controllers; a sorting module, configured to sort the information according to a preset rule; a learning module, configured to learn, according to the original temperature control schedule, the user small fluctuation adjustment behavior occurring within one day in the collated information, and the current period according to the collated information The user-similar operation filtered by the similar operation rule learns, and learns the user's large fluctuation adjustment behavior occurring in the current period in the collated information to generate a temperature control schedule corresponding to the space in the current period; a control module, configured to feed back the learned temperature control schedule to the central temperature controller, so that the central temperature controller sends a control instruction to the air conditioner according to the temperature control schedule, and the corresponding space is intelligently controlled by the air conditioner temperature; a looping module, configured to cycle into the real-time receiving information of the space of the temperature controller of the next cycle acquired by the central temperature controller and sent from the plurality of temperature controllers, and sort the information according to a preset rule, and The learning step is performed on the basis of the previous cycle temperature control schedule until the temperature control schedule of the corresponding space in the current cycle is obtained, and the learned temperature control schedule is fed back to the central temperature controller so that the central temperature controller is based on The temperature control schedule sends a control command to the air conditioner, and the temperature of the corresponding space is intelligently controlled by the air conditioner. The apparatus of claim 17, wherein the long term learning module comprises: An optional temperature control schedule acquisition module is configured to obtain an alternate temperature control schedule, where the alternate temperature control schedule includes an original temperature control schedule of the first period, and is learned and generated when a user large fluctuation adjustment behavior occurs The temperature control schedule, the temperature control schedule generated when the user selects re-learning, and the temperature control schedule learned when the small fluctuation adjustment behavior occurs in consecutive periods; An alternative temperature control schedule effective probability calculation module is configured to calculate an effective probability of distribution of each candidate temperature control schedule over time in a preset period; A screening module for comparing the effective probability of an alternate temperature control schedule in the current cycle, Obtaining the temperature control schedule with the highest effective probability in the alternative temperature control schedule, using the temperature control schedule as the temperature control schedule of the current cycle, and feeding back the learned temperature control schedule to the central temperature controller, so that The central temperature controller sends a control command to the air conditioner according to the temperature control schedule, and the temperature of the corresponding space is intelligently controlled by the air conditioner. A computer readable storage medium having stored thereon computer readable instructions, wherein the readable instructions are executed by a processor to implement the intelligent temperature control method of any one of claims 1 to 3. A computer readable storage medium having stored thereon computer readable instructions, wherein the readable instructions are executed by a processor to implement the intelligent temperature control method of any one of claims 4 to 10. A central temperature controller, the central temperature controller including a display, a memory, a processor, and computer readable instructions stored on the memory and operative on the processor, wherein the processor The intelligent temperature control method according to any one of claims 1 to 3 is implemented when the computer readable instructions are executed. A server comprising a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, wherein when the processor executes the computer readable instructions The intelligent temperature control method according to any one of claims 4 to 10 is implemented.

Images