Data learning server and method for generating and using learning model thereof
Through the data learning server, the learning model is generated and updated, and the setting of the air conditioner and the current temperature data are used to provide personalized recommended temperatures, which solves the problems of insufficient temperature control of air conditioners in the existing technology, and achieves more efficient Temperature management.
Patent Information
- Application Number
- CN202411080834.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2017-09-25
- Filing Date
- 2018-03-30
- Publication Date
- 2024-11-22
AI Technical Summary
The existing technology is difficult to effectively use artificial intelligence technology to automatically recommend and optimize the temperature settings of air conditioners, resulting in low convenience when controlling the temperature and insufficient recommended temperatures.
A data learning server is designed to generate or refresh the learning model by obtaining the set temperature and current temperature of the air conditioner, which is used to provide the most ideal recommended temperature, and send the recommended temperature to the user terminal or air conditioner for real-time adjustment through the network system. .
It improves the user convenience of air conditioning temperature control, can provide each user with the most suitable recommended temperature, and continuously improves the accuracy and personalization of temperature control through the update and optimization of learning models.
Smart Images

Figure CN118998917A_ABST
Abstract
Description
[0001] This application is a divisional application of the invention patent application with application date of March 30, 2018 and application number 201880022241.2. Technical Field
[0002] The present disclosure relates to a method for generating a learning model and a data learning server using the generated learning model. Background Art
[0003] In recent years, intelligent services that automatically recognize data, such as voices, images, moving images, and texts, to provide information related to the data or services related to the data have been used in various fields.
[0004] The artificial intelligence technology used in smart services is a technology that achieves human-level intelligence. Unlike existing rule-based intelligent systems, artificial intelligence technology allows machines to perform learning and judgment, and makes the machines themselves smart. As artificial intelligence technology is used, the recognition rate is getting higher and higher, and the user's taste can be understood more accurately, so that the existing rule-based technology is gradually replaced by artificial intelligence technology.
[0005] Artificial intelligence technology includes machine learning and element technology that utilizes machine learning.
[0006] Machine learning is an algorithmic technology that classifies / learns the characteristics of input data by itself. The basic technology is a technology that simulates functions such as recognition and judgment of the human brain using a machine learning algorithm, and includes technical fields such as language understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.
[0007] The applications of artificial intelligence technology are as follows. Language understanding is a technology for recognizing and applying / processing human language / characters, and includes natural language processing, machine translation, dialogue systems, query response, speech recognition / synthesis, etc. Visual understanding is a technology for recognizing and processing objects such as human vision, and includes object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, and image enhancement, etc. Inference prediction is a technology for judging and logically inferring and predicting information, and includes knowledge / probability-based inference, optimization prediction, preference-based planning, recommendation, etc. Knowledge representation is a technology for automating human experience information into knowledge data, and includes knowledge construction (data generation / classification), knowledge management (data utilization), etc. Motion control is a technology for controlling the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.
[0008] The above information is provided as background information only to assist in understanding the present disclosure. No determination has been made, and no assertion is made, as to whether any of the above might be applicable as prior art with respect to the present disclosure. Summary of the invention
[0009] Technical issues
[0010] The exemplary embodiments of the present disclosure overcome the above disadvantages and other disadvantages not described above. Also, the present invention is not required to overcome the above disadvantages, and the exemplary embodiments of the present disclosure may not overcome any of the above problems.
[0011] The present invention is used to set the temperature of an air conditioner using artificial intelligence technology.
[0012] Technical Solution
[0013] Therefore, the present disclosure provides a method for generating and using a learning model for setting the temperature of an air conditioner.
[0014] In addition, the technical subject matter of the present disclosure is not limited to the above-mentioned technical matters, and other technical subject matters not mentioned can be clearly understood from the following description by a person of ordinary skill in the art to which the present disclosure belongs.
[0015] According to one aspect of the present disclosure, a data learning server is provided. The data learning server includes: a communicator configured to communicate with an external device; at least one processor configured to: acquire a set temperature set in an air conditioner and a current temperature of the air conditioner at the set temperature via the communicator, and generate or refresh a learning model using the set temperature and the current temperature; and a storage configured to store the generated or refreshed learning model to provide a recommended temperature to be set in the air conditioner as a result of generating or refreshing the learning model.
[0016] According to another aspect of the present disclosure, a data learning server is provided. The data learning server includes: a storage configured to store a learned learning model to provide a recommended temperature to be set in an air conditioner; at least one processor configured to: obtain a current temperature of the air conditioner, and input the current temperature to the learning model to obtain a recommended temperature to be set in the air conditioner; and a communicator configured to send the recommended temperature to an external device.
[0017] According to another aspect of the present disclosure, a network system is provided. The system includes: an air conditioner; and a learning model server configured to generate a learning model using learning data acquired from the air conditioner, wherein the air conditioner includes: a temperature sensor configured to sense the current temperature around the air conditioner, a blower fan configured to discharge cooling air to the outside based on a set temperature set in the air conditioner, and an air conditioner communicator configured to communicate with an external device, and at least one air conditioner processor configured to control the air conditioner communicator to send the sensed current temperature and set temperature to the external device, and the learning model server includes at least one server processor that acquires the current temperature and the set temperature, and generates a learning model using the acquired set temperature and the current temperature, and a storage configured to store the generated learning model to provide a recommended temperature of the air conditioner as a result of generating the learning model.
[0018] According to another aspect of the present disclosure, a network system is provided. The network system includes: an air conditioner; and a learning model server configured to provide a recommended temperature using identification data obtained from the air conditioner, wherein the air conditioner includes: a temperature sensor configured to sense the current temperature of the air conditioner, a blower fan configured to discharge the cooling air generated by the air purifier to the outside, and an air conditioner communicator that sends the current temperature to a first external device, wherein the learning model server includes: a storage configured to store a learned learning model to provide a recommended temperature of the air conditioner, at least one server processor configured to: obtain the current temperature, and input the current temperature into the learning model to obtain the recommended temperature of the air conditioner, and a server communicator configured to send the recommended temperature to a second external device.
[0019] According to another aspect of the present disclosure, an air conditioner is provided. The air conditioner includes: a blower fan configured to discharge cooling air to the outside; a temperature sensor configured to sense the current temperature around the air conditioner; a communicator configured to communicate with an external device; and at least one processor configured to: control the communicator to send the current temperature to the external device, control the communicator to receive a recommended temperature from the external device depending on the sending of the current temperature, the recommended temperature being a result obtained by applying the current temperature to a learning model, and setting the received recommended temperature in the air conditioner, wherein the learning model is a learning model learned using a plurality of set temperatures and a plurality of current temperatures previously set in the air conditioner.
[0020] According to another aspect of the present disclosure, a user terminal is provided. The user terminal includes: a display configured to display a screen; a communicator configured to communicate with an external device; an input configured to receive a user input; and at least one processor configured to: control the communicator to send an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner in response to a user input signal depending on a user input received via the input and selecting the artificial intelligence operation UI included in the screen, and control the display to display the acquired recommended temperature in response to the recommended temperature set in the air conditioner being acquired, the recommended temperature being a result obtained by applying the current temperature of the air conditioner to the learning model depending on the artificial intelligence operation request signal via the communicator.
[0021] According to another aspect of the present disclosure, a method for generating a learning model of a data learning server is provided. The method includes: acquiring a set temperature set in an air conditioner and a current temperature of the air conditioner at the time of setting the temperature; generating or refreshing a learning model using the set temperature and the current temperature; and storing the generated or refreshed learning model to provide a recommended temperature set in the air conditioner as a result of generating or refreshing the learning model.
[0022] According to another aspect of the present disclosure, a method for learning a model using a data learning server is provided. The method includes: storing a learned learning model to provide a recommended temperature to be set in an air conditioner; acquiring a current temperature of the air conditioner; inputting the current temperature to the learned learning model to acquire a recommended temperature to be set in the air conditioner; and sending the recommended temperature to an external device.
[0023] According to another aspect of the present disclosure, a method for providing a recommended temperature of an air conditioner is provided. The method includes: sensing a current temperature of the air conditioner; transmitting the sensed current temperature to an external device; receiving a recommended temperature from the external device depending on the transmission of the current temperature, the recommended temperature being a result obtained by applying the current temperature to a learning model; and setting the received recommended temperature in the air conditioner, wherein the learning model is a learning model learned using a plurality of set temperatures previously set in the air conditioner and a plurality of current temperatures.
[0024] According to another aspect of the present disclosure, a method for controlling an air controller of a user terminal is provided. The method includes: receiving a user input signal depending on a user input selecting an artificial intelligence operation UI; sending an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to an air conditioner; acquiring a recommended temperature set in the air conditioner, the recommended temperature being a result obtained by applying a current temperature of the air conditioner to a learning model depending on the artificial intelligence operation request signal; and displaying the acquired recommended temperature on a screen.
[0025] According to another aspect of the present disclosure, a method for generating a learning model of a network system including an air conditioner and a learning model server is provided. The method includes: receiving a user control signal of a set temperature by the air conditioner; sending the set temperature and the current temperature of the air conditioner to an operation of an external device by the air conditioner; generating a learning model using the set temperature and the current temperature by the learning model server; and storing the generated learning model by the learning model server to provide a recommended temperature of the air conditioner.
[0026] According to another aspect of the present disclosure, a method for providing a recommended temperature in a network system including an air conditioner and a learning model server is provided. The method includes: the air conditioner sends the current temperature of the air conditioner to an external device; the learning model server obtains the recommended temperature of the air conditioner by applying the current temperature to the learning model; and the air conditioner sends the recommended temperature to the external device.
[0027] According to another aspect of the present disclosure, a method for controlling an air conditioner of a network system including an air conditioner and a user terminal is provided. The method includes: receiving, by the user terminal, a user input signal depending on a user input selecting an artificial intelligence operation UI; sending, by the user terminal, an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner; if the artificial intelligence operation request signal is received, sending, by the air conditioner, the current temperature of the air conditioner to an external device; receiving, by the air conditioner, a recommended temperature from the external device depending on the sending of the current temperature, the recommended temperature being a result obtained by applying the current temperature to a learning model; and setting, by the air conditioner, the received recommended temperature in the air conditioner, wherein the learning model is a learning model learned using a plurality of set temperatures and a plurality of current temperatures previously set in the air conditioner.
[0028] According to an embodiment of the present disclosure, when the temperature set in the air conditioner is automatically recommended using artificial intelligence technology, the convenience of the user who controls the temperature can be greatly improved. In particular, the user can be provided with the most ideal recommended temperature for the user.
[0029] In addition, according to the method for using a learning model disclosed in the present invention, the learning model can be continuously updated based on the temperature setting history of the user who sets the air conditioner, and the performance of the learning model can be improved so that the most ideal recommended temperature can be provided to the user when using the learning model according to the present invention.
[0030] That is, a learning model customized for each of the users who use the air conditioner can be generated, and thus an optimal recommended temperature suitable for each of the plurality of users can be provided.
[0031] In addition, the effects that can be obtained or expected by various embodiments of the present disclosure should be disclosed directly or implicitly in the detailed description of the present disclosure. For example, various effects that can be expected by various embodiments of the present disclosure will be disclosed in the detailed description to be described below.
[0032] Other aspects, advantages and salient features of the present disclosure will become apparent to those skilled in the art through the following detailed description which discloses various embodiments of the present disclosure in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The above and / or other aspects of the present disclosure will become more apparent by describing certain embodiments of the present disclosure with reference to the accompanying drawings, in which:
[0034] Figure 1A and Figure 1B is a diagram illustrating a network system for generating and using a learning model according to an embodiment of the present disclosure;
[0035] Figure 2A and Figure 2B is a diagram showing a configuration of a data learning server according to an embodiment of the present disclosure;
[0036] Figure 3A and Figure 3B is a flow chart of a network system according to an embodiment of the present disclosure;
[0037] Figure 4 is a table showing an example of generation of a learning model according to an embodiment of the present disclosure;
[0038] Figure 5 is a diagram showing an example of assigning weights to learning data according to an embodiment of the present disclosure;
[0039] Figure 6 is a diagram showing a structure of a cloud server according to an embodiment of the present disclosure;
[0040] Fig. 7A and Figure 7B is a diagram illustrating a procedure for generating a learning model according to an embodiment of the present disclosure;
[0041] Figure 8 is a block diagram showing a configuration of an air conditioner according to an embodiment of the present disclosure;
[0042] Fig. 9 is a block diagram showing a configuration of a user terminal U according to an embodiment of the present disclosure;
[0043] Fig. 10A and Fig. 10B is a diagram illustrating a screen of a user terminal on which a recommended temperature is displayed according to an embodiment of the present disclosure;
[0044] Fig.11 is a flowchart of a method for generating a learning model of a data learning server according to an embodiment of the present disclosure;
[0045] Fig.12 is a flowchart illustrating a method for learning a learning model of a server using data according to an embodiment of the present disclosure;
[0046] Fig.13 is a flowchart illustrating a method for providing a recommended temperature of an air conditioner according to an embodiment of the present disclosure;
[0047] Fig.14 is a flowchart illustrating a method for controlling an air conditioner of a user terminal according to an embodiment of the present disclosure; and
[0048] Fig.15 is a flow chart of a network system including a user terminal and an air conditioner according to an embodiment of the present disclosure.
[0049] Throughout the drawings, like reference numerals will be understood to refer to like parts, components and structures. DETAILED DESCRIPTION
[0050] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of the various embodiments of the present disclosure as defined by the claims and their equivalents. It includes various specific details to assist in understanding, but these specific details are to be regarded as exemplary only. Therefore, it will be appreciated by those of ordinary skill in the art that various changes and modifications may be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and structures may be omitted for clarity and conciseness.
[0051] In the above, the present disclosure is described based on an exemplary method. The terms and words used herein are only used for description and are not limited to the written meaning, but are only used by the inventor to enable a clear and consistent understanding of the present disclosure. Various modifications and changes can be made to the present disclosure based on the above. Therefore, unless otherwise mentioned, the present disclosure can be freely implemented within the scope of the claims.
[0052] The various embodiments described in the configurations shown in the specification and the drawings are merely preferred examples of the present disclosure disclosed, and there may be various modifications that may replace the various embodiments of the specification and the drawings at the time of filing the present application.
[0053] In addition, the same reference numerals or symbols in each of the drawings of this specification represent parts or components that perform substantially the same function.
[0054] In addition, the terms used in this specification are only used to describe specific embodiments rather than to limit the disclosed disclosure. Unless the context clearly states otherwise, the singular form used herein is intended to include the plural form. Throughout the specification, it should be understood that the term "include" and its variants, such as "include" and "comprising", specify the presence of features, numbers, steps, operations, components, parts or combinations thereof described in the specification, but do not exclude the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.
[0055] In addition, terms used herein including serial numbers such as "first" and "second" may be used to describe various components, but components are not limited by these terms, and these terms are only used for the purpose of distinguishing one component from other components. For example, without departing from the scope of the present disclosure, a "first" component may be named a "second" component, and a "second" component may also be similarly named a "first" component. The term "and / or" includes a combination of multiple items or any one of the multiple items.
[0056] In addition, if any (e.g., a first) component is "(functionally or communicatively) connected" or "coupled" to another (e.g., a second) component, any component may be directly connected to the other component or may be connected to the other component via yet another component (e.g., a third component).
[0057] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.
[0058] Figure 1A and Figure 1B is a diagram illustrating a network system for generating and using a learning model according to an embodiment of the present disclosure.
[0059] refer to Figure 1A , the network system may include an air conditioner A (Aa or Ab), a user terminal U (Ua or Ub) and a cloud server C. The air conditioner A may be a household appliance for controlling the temperature or humidity of an indoor environment. The air conditioner A may be divided into a wall-mounted type (such as the air conditioner Aa) and a bracket type (such as the air conditioner Ab).
[0060] The user terminal U may be a device for remotely controlling the air conditioner A. Similar to the user terminal Ua, the user terminal U may be a smart phone, a cellular phone, or a tablet PC installed with an air conditioner control application (or app). Alternatively, similar to the user terminal Ub, the user terminal U may be a remote controller (or remote controller) dedicated to the air conditioner. In addition, the user terminal U may be a smart TV, a digital camera, a personal digital assistant (PDA), a portable multimedia player (PMP), a notebook computer, a desktop computer, etc., but is not limited to the above examples.
[0061] The user terminal U can remotely control the air conditioner A. For example, the user terminal U can send a control command to the air conditioner A using RF communication technologies such as ZigBee, WIFI, Bluetooth, mobile communication, local area network (LAN), wide area network (WAN), infrared data association (IrDA), UHF, and VHF.
[0062] The cloud server C may be connected to the air conditioner A via a third device (eg, access point (AP), repeater, router, gateway, hub, etc.) or directly connected to the air conditioner A.
[0063] The cloud server C may include one or more servers. For example, the cloud server C may include at least one of a bridge server BS, a smart home service server SS, and a data learning server DS. In this case, two or more of the bridge server BS, the smart home service server SS, and the data learning server DS may be integrated into one server. Alternatively, at least one of the bridge server BS, the smart home service server SS, and the data learning server DS may be divided into a plurality of sub-servers.
[0064] The bridge server BS (or the device status information importing server) may import status information of smart home appliances (eg, air conditioners, washing machines, refrigerators, cleaners, ovens, etc.).
[0065] The bridge server BS may include a connection API BS1 and a device status data DB BS2.
[0066] The connection API BS1 may include an application programming interface (hereinafter, referred to as an API) that serves as an interface between different devices operating according to heterogeneous protocols. The API may be defined as a set of subroutines or functions that can be called from any one protocol for any processing of another protocol. That is, the API may provide an environment in which operations of another protocol may be performed in any one protocol.
[0067] The bridge server BS may import the status information of the air conditioner using the connection API BS1. Then, the bridge server BS may store the imported status information of the air conditioner in the device status data DB BS2.
[0068] The smart home service server SS (or external environment information import server) can import external environment information. The external environment information may include, for example, at least one of external temperature and external humidity as weather information provided by an external content server CP (e.g., a weather station server, a weather eye server, etc.).
[0069] The data learning server DS may generate a learning model and obtain a learning model application result using the learned generation model.
[0070] The data learning server DS includes a data import API DS1, a data analysis engine DS2, an analysis DB (DS3) and a data service API (DS4).
[0071] Figure 1A A network system is shown in which a data learning server DS generates a learning model, and Figure 1B A network system in which a generated learning model of a data learning server DS is used is shown.
[0072] First, refer to Figure 1A A procedure of a network system in which a data learning server DS generates a learning model is described.
[0073] In operation ①, the air conditioner A can send the status information of the air conditioner A (e.g., set temperature, current temperature, etc.) to the cloud server C via a third device (e.g., access point AP, repeater, router, gateway, hub, etc.). The bridge server BS of the cloud server C can import the status information of the air conditioner A sent from the air conditioner A using the connection API BS1, and store the imported status information of the air conditioner A in the device status data DB BS2.
[0074] Depending on the user's desired temperature, the state information of the air conditioner A may include a set temperature set in the air conditioner A and a current temperature of the air conditioner (eg, room temperature and ambient temperature) at the time of setting the temperature.
[0075] The user's desired temperature may generally be the same as the set temperature set in the air conditioner A, but may also be a set temperature that is set step by step by the air conditioner A until the desired temperature is reached.
[0076] In addition, the current temperature (or room temperature and ambient temperature) when the temperature is set may include, for example, the temperature sensed by air conditioner A at the temperature setting time (for example, when the user's operation of setting the temperature of the air conditioner is performed), the temperature sensed by air conditioner A within a certain time (for example, 10 minutes) after the temperature is set, and at least one of the most recent temperature sensed in advance before the temperature is set and stored.
[0077] The state information of the air conditioner A may include operation mode information set in the air conditioner A. The operation mode may include, for example, smart comfort mode, tropical night sleep mode, windless tropical night sleep mode, 2-step cooling mode, etc., but is not limited to the above modes.
[0078] According to various embodiments, time information when the temperature of the air conditioner A is set may also be stored in the device state data DB BS2. The time information when the temperature is set includes, for example, at least one of the operation time of the user who sets the temperature, the time when the bridge server BS receives the set temperature, and the time when the set temperature is stored in the device state data DB BS2.
[0079] According to various embodiments, the location information of the air conditioner A may also be stored in the device state data DB BS2. In this case, the location information of the air conditioner A may be stored by being received when setting the temperature or may be stored in advance.
[0080] In operation ②, the smart home service server SS may import external environment information (or weather information) from the communication external content server CP every predetermined period (eg, between 5 minutes and 30 minutes), and store the imported external environment information in the weather data DB SS1.
[0081] The external environment information may include at least one of outdoor temperature, outdoor humidity, dust concentration, precipitation, and sunshine, but is not limited to the above examples.
[0082] In operations ③ and ③', the data learning server DS can use the data import API DS1 to obtain the status information of the air conditioner A stored in the device status data DB BS2 of the bridge server BS. In addition, the data learning server DS can use the data import API DS1 to obtain the external environment information stored in the weather data DB SS1 in the smart home service server SS.
[0083] In this case, the external environment information is external environment information when the temperature of the air conditioner A is set, and may be information searched from the weather data DBSS1 based on time information when the temperature of the air conditioner A is set stored in the device state data DB BS2 .
[0084] Specifically, the external environment information when setting the temperature may include, for example, the external environment information when the user sets the temperature, the external environment information in the time zone when the user sets the temperature (for example, morning / daytime / evening or am / pm), and at least one of the external environment information in the month or season when the user sets the temperature.
[0085] In addition, the external environment information may be weather information acquired based on the position information of the air conditioner A. For example, the external environment information may be weather information searched from the weather data DB SS1 based on the position information of the air conditioner A stored in the device state data DB BS2.
[0086] In operation ④, the data analysis engine DS2 of the data learning server DS may generate a learning model using the acquired state information of the air conditioner A and the external environment information as learning data.
[0087] According to various embodiments, the data analysis engine DS2 of the data learning server DS may also generate a learning model using time information when the temperature of the air conditioner A is set as learning data.
[0088] In addition, the data analysis engine DS2 can also generate multiple learning models for each operating mode of air conditioner A when setting the temperature of air conditioner A.
[0089] For example, the data analysis engine DS2 may respectively generate a learning model available in the smart comfort mode, a learning model available in the tropical nighttime deep sleep mode, a learning model available in the windless tropical nighttime deep sleep mode, and a learning model available in the two-step cooling mode.
[0090] In addition, the data learning server DS can be executed in units of modeling periods such as time, day, and month, during which the data learning server DS uses learning data to generate a learning model (or refreshes the learning model), or can be executed when an event is generated, but the modeling period is not limited to the above period.
[0091] Will refer to it later Figure 4 , Figure 5 7 describe in more detail the process of the data learning server DS generating a learning model.
[0092] In operation ⑤, the data learning server DS may store the generated learning model in the analysis DB DS3. In this case, the learning model may not be a general learning model but may be a learning model configured or constructed to provide a recommended temperature for the air conditioner A.
[0093] refer to Figure 1B , a procedure of a network system using a learning model generated by a data learning server DS will be described.
[0094] In operation ⑥, the air conditioner A may receive a control command from the user terminal U requesting execution of an artificial intelligence function (eg, AI mode on).
[0095] In operation ⑦, the air conditioner A can send the status information of the air conditioner A (eg, current temperature, operation mode, etc.) to the cloud server C via a third device (eg, access point AP). The data learning server DS of the cloud server C can obtain the status information of the air conditioner A using the data service API DS4.
[0096] In operation ⑧, the data learning server DS may input the acquired state information of the air conditioner A as the learned learning model to provide a recommended temperature of the air conditioner A stored in the analysis DB DS3.
[0097] In operation ⑨, the data learning server DS may obtain the recommended temperature of the air conditioner A as a result of applying the learning model.
[0098] In operation ⑩, the data learning server DS may transmit the acquired recommended temperature of the air conditioner A to the air conditioner A via a third device (eg, access point AP). In addition, in step ⑩′, the data learning server DS may transmit the acquired recommended temperature of the air conditioner A to the user terminal U.
[0099] In operation In the example, the air conditioner A having received the recommended temperature may set the temperature of the air conditioner A to the received recommended temperature.
[0100] In addition, during operation In the example of FIG. 1 , the user terminal U having received the recommended temperature may display the received recommended temperature so that the user can confirm the received recommended temperature. As in the example above, the user terminal U having received the recommended temperature may display visual information indicating that the preferred recommended temperature is adopted compared with the set temperature history predetermined by the user.
[0101] Figure 2A and Figure 2B is a diagram illustrating a configuration of a data learning server according to an embodiment of the present disclosure.
[0102] Figure 2AThe data learning server DS is a functional block diagram for generating a learning model, and Figure 2B The data learning server DS is a functional block diagram using the generated learning model.
[0103] exist Figure 2A and Figure 2B In the embodiment, the data learning server DS may include a communication unit 201 , a storage 202 and a processor 203 .
[0104] The communication unit 201 may perform communication with an external device.
[0105] The external device may include at least one of an external server (e.g., a bridge server, a smart home service server, etc.) and the air conditioner A.
[0106] The communication unit 201 can perform communication with an external device in a wired or wireless communication mode. Wireless communication may include, for example, cellular communication, near field communication, or global navigation satellite system (GNSS) communication. Cellular communication may include, for example, long-term evolution (LTE), advanced LTE (LTE-advance, LTE-A), code division multiple access (code division multiple access, CDMA), wideband CDMA (wideband CDMA, WCDMA), universal mobile telecommunication system (universal mobile telecommunication system, UMTS), wireless broadband (wireless broadband, WiBro), global system for mobile communications (global system for mobile communications, GSM), etc. Near field communication may include, for example, wireless fidelity (WiFi), WiFi direct connection, light fidelity (LiFi), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (near field communication, NFC), magnetic security transmission, radio frequency (radio frequency, RF) and body area network (BAN). The communication unit 201 may also be referred to as a communicator.
[0107] The data learning server DS may include a storage 202. The storage 202 may store a learning model generated by the data learning server DS.
[0108] The storage 202 may include volatile and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) (e.g., DRAM, SRAM, or SDRAM). Non-volatile memory may include, for example, one-time programmable read-only memory (OTPROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), mask ROM, flash ROM, flash memory, hard disk drive, or solid status drive (SSD).
[0109] The processor 203 may include one or more of a central processing unit, an application processor, a graphics processing unit (GPU), a camera image signal processor, and a communication processor (CP). According to an embodiment, the processor 203 may be implemented as a system on chip (SoC) or a system in package (SiP). The processor 203 may drive, for example, an operating system or an application to control at least one other component (e.g., a hardware or software component) of a data learning server (DS) connected to the processor 203, and may perform various data processing and operations. The processor 203 may load commands or data received from other components (e.g., the communication unit 201) into a volatile memory, process the loaded commands or data, and may store the resulting data in a non-volatile memory.
[0110] Figure 2A and Figure 2B is a diagram illustrating a configuration of a data learning server according to an embodiment of the present disclosure.
[0111] Figure 2A The data learning server DS is a functional block diagram for generating a learning model, and Figure 2B The data learning server DS is a functional block diagram using the generated learning model.
[0112] refer to Figure 2Aand Figure 2B , the data learning server DS may include a communication unit 201 , a storage 202 , and a processor 203 .
[0113] The communication unit 201 may perform communication with an external device.
[0114] The external device may include at least one of an external server (e.g., a bridge server, a smart home service server, etc.) and the air conditioner A.
[0115] The communication unit 201 can perform communication with an external device in a wired or wireless communication mode. Wireless communication may include, for example, cellular communication, near field communication, or global navigation satellite system (GNSS) communication. Cellular communication may include, for example, long term evolution (LTE), advanced LTE (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), wireless broadband (WiBro), global mobile communication system (GSM), etc. Near field communication may include, for example, wireless fidelity (WiFi), WiFi direct connection, light fidelity (LiFi), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (NFC), magnetic security transmission, radio frequency (RF) and body area network (BAN).
[0116] The data learning server DS may include a storage 202. The storage 202 may store a learning model generated by the data learning server DS.
[0117] The storage 202 may include volatile and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) (e.g., DRAM, SRAM, or SDRAM). Non-volatile memory may include, for example, one-time programmable read-only memory (OTPROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), mask ROM, flash ROM, flash memory, hard disk drive, or solid state drive (SSD).
[0118] The processor 203 may include one or more of a central processing unit, an application processor, a graphics processing unit (GPU), a camera image signal processor, and a communication processor (CP). According to an embodiment, the processor 203 may be implemented as a system on a chip (SoC) or a system in package (SiP). The processor 203 may drive, for example, an operating system or an application to control at least one other component (e.g., a hardware or software component) of a data learning server (DS) connected to the processor 203, and may perform various data processing and operations. The processor 203 may load commands or data received from other components (e.g., the communication unit 201) into a volatile memory, process the loaded commands or data, and may store the result data in a non-volatile memory.
[0119] Figure 2A The processor 203 can be described as a functional block diagram for generating a learning model.
[0120] exist Figure 2A In the embodiment, the processor 203 may include a learning data acquisition unit 203a and a model learning unit 203b.
[0121] The learning data acquisition unit 203a can acquire the set temperature set in the air conditioner A and the current temperature of the air conditioner A at the set temperature through the communication unit 201. For example, the learning data acquisition unit 203a can acquire the set temperature and the current temperature from the bridge server BS communicatively connected to the air conditioner A. Alternatively, the learning data acquisition unit 203a can also acquire the set temperature and the current temperature from the air conditioner A or a third device communicatively connected to the air conditioner A.
[0122] In addition, the learning data acquisition unit 203a can also acquire external environment information through the communication unit 201. The external environment information may include at least one of the external temperature and the external humidity. For example, the learning data acquisition unit 203a can acquire the external environment information from the smart home service server SS that is communicatively connected to the external content providing server CP.
[0123] The model learning unit 203b can generate or update the learning model using the acquired set temperature and current temperature. When the learning data acquisition unit 203a further acquires external environment information, the model learning unit 203b can generate or update the learning model using the set temperature, current temperature and external environment information. In addition, when the learning data acquisition unit 203a also acquires time information when setting the temperature of the air conditioner A, the model learning unit 203b can generate or update the learning model using the set temperature, current temperature and time information.
[0124] The storage 202 may store the learned learning model to provide a recommended temperature to be set in the air conditioner A as a generation or update result of the learning model.
[0125] On the other hand, when the model learning unit 203 b generates or updates a plurality of learning models for each operation mode of the air conditioner A, the storage 202 may store the plurality of learning models, respectively.
[0126] Figure 2B The processor 203 can be described as a functional block diagram for using a learning model.
[0127] exist Figure 2B In this case, the storage 202 may store a learned learning model to provide a recommended temperature to be set in the air conditioner A.
[0128] exist Figure 2B In the example, the identification data acquisition unit 203c can acquire the current temperature of air conditioner A.
[0129] The model applier 203d may input the acquired current temperature into the learning model of the storage 202 and acquire a recommended temperature to be set in the air conditioner A.
[0130] When the recognition data acquisition unit 203c further acquires external environment information, the model application 203d can input the current temperature and the external environment information to the learning model to acquire the recommended temperature to be set in the air conditioner A.
[0131] In addition, when the storage 202 stores a plurality of learning models for each operation mode of the air conditioner A, the model application 203 d may set the current temperature to the learning model corresponding to the current operation mode of the air conditioner A to obtain the recommended temperature of the air conditioner A.
[0132] The communication unit 201 may transmit the acquired recommended temperature to an external device. The external device may be, for example, the air conditioner A or a third device communicatively connected to the air conditioner A.
[0133] Figure 3A and Figure 3B is a flow chart of a network system according to an embodiment of the present disclosure.
[0134] The flowchart of the network system shows the data flow procedure between the air conditioner A, the user terminal U and the cloud server C.
[0135] Reference 3A and Figure 3B, the flowchart of the network system may include a data import program 351 for importing learning data, a program 352 for generating a data model based on the learning data, a program 353 for operating artificial intelligence functions, and a program 354 for setting a preferred mode for each function.
[0136] exist Figure 3A In the embodiment, the air conditioner A may include a microcomputer 301 and a near field communication module (eg, a Wi-Fi module) 302. The microcomputer 301 corresponds to Figure 2A and Figure 2B The processor 203, and the near field communication module 302 may correspond to Figure 2A and Figure 2B The air conditioner A can communicate with the user terminal U and the cloud server C via the network using the near field communication module 302. In addition, the air conditioner A can receive a recommended temperature recommended by the cloud server C via an API call related to the near field communication module 302, and set the temperature of the air conditioner A depending on the recommended temperature.
[0137] The user terminal U may include a mobile application (app) 303. The mobile application 303 may set the artificial intelligence function and the operation mode of the air conditioner A, and perform a function of displaying the recommended temperature provided by the cloud server C on the user terminal U.
[0138] The cloud server C may include a bridge server BS, a DB server (304), and a data learning server DS. The DB server 304 may be a part of the bridge server BS or a third server physically separated from the bridge server BS.
[0139] First, in operation 311, the user terminal U may receive a user input to change (or set) a desired temperature via the mobile application 303. The mobile application 303 may be, for example, an application that provides a user interface for controlling an air conditioner.
[0140] In operation 312 , depending on a user's input, the user terminal U may transmit a control command to the microcomputer 301 via the near field communication module 302 to set the air conditioner A to a desired temperature.
[0141] Alternatively, in operation 311', the user may change the desired temperature via the remote control device Ub. In operation 312', the remote control device Ub may transmit a control command for setting the air conditioner A to the desired temperature to the microcomputer 301 according to the user's change input.
[0142] In operation 313, the microcomputer 301 of the air conditioner A may generate an expected temperature change event in response to the user's expected temperature change request, and transmit the generated expected temperature change event to the bridge server BS via the near field communication module 302. At this time, the expected temperature change event may include event data. The event data may include, for example, state information of the air conditioner A. The state information of the air conditioner A may include the expected temperature (or set temperature) and the current temperature when the expected temperature is set.
[0143] In addition, the event data may include, for example, operation mode information and time information of the air conditioner A. The operation mode information may include, for example, information indicating the operation mode of the air conditioner A when receiving the control command of the user, or the operation mode of the air conditioner A when the desired temperature change event is generated. The time information may include, for example, information about the time when the user receives the control command or information about the time when the desired temperature change event is generated.
[0144] In operation 314, the bridge server BS may transmit the event data to the DB server 304. In operation 315, the DB server 304 may store the received event data.
[0145] In operation 316, the DB server 304 may periodically send the stored event data to the data learning server DS. For example, the DB server 304 may send the event data in the form of a daily batch file every day. At this time, the daily batch file may include multiple event data. For example, when the user's desired temperature change request is generated multiple times a day, multiple event data may be generated, and the multiple event data are stored in the DB server 304. The multiple generated event data may be included in the daily batch file and sent to the data learning server DS.
[0146] In operation 317, the data learning server DS may generate a learning model using the received event data as learning data. For example, the data learning server DS may generate a learning model using at least one of the set temperature, current temperature, external environment information, operation mode information, and time information of the air conditioner A.
[0147] In the case where the learning model has been generated, as in operation 318, the user terminal U may receive a user input for turning on the artificial intelligence function of the air conditioner A. The partial screen 318a shows a portion of the screen of the user terminal U, which includes a user interface for turning on the artificial intelligence function. In the partial screen 318a, the user terminal U may receive a user input for selecting the "AI custom operation" execution object 318b to turn on the AI function.
[0148] In operation 319 , depending on the user's input, the user terminal U may transmit an artificial intelligence function activation command to the microcomputer 301 via the near field communication module 302 to turn on the AI function of the air conditioner A.
[0149] Based on the artificial intelligence function activation command, the microcomputer 301 may transmit device status information indicating that the artificial intelligence function of the air conditioner A is activated to the user terminal U via the near field communication module 302 as in operation 320. In this case, the status information of the air conditioner A may be transmitted by being included in the notification event.
[0150] Alternatively, as in operation 321, the user terminal U may transmit a device information request command requesting status information of the air conditioner A to the microcomputer 301 via the near field communication module 302. The device information request command may be transmitted in the following manner, for example, included in a 'GET DEVICE' message.
[0151] Based on the device information request command, the microcomputer 301 may transmit a device information response to the user terminal U via the near field communication module 302, as in operation 322. In this case, the device information response may include artificial intelligence setting information indicating that the artificial intelligence function of the air conditioner A is set to on as the state information of the air conditioner A.
[0152] That is, by considering the case where there are multiple user terminals U for controlling the artificial intelligence function of the air conditioner A, the air conditioner A can notify the user terminal U whether the artificial intelligence function of the air conditioner A is activated regularly or when an event occurs.
[0153] In this way, when the artificial intelligence function of the air conditioner A is activated, the user terminal U can receive user input for setting the operation mode.
[0154] refer to Figure 3B In operation 323 , the user terminal U may receive a user input requesting execution of the smart comfort mode.
[0155] In operation 324 , the user terminal U may transmit an intelligent comfort control command to the microcomputer 301 via the near field communication module 302 to execute the intelligent comfort mode of the air conditioner A, depending on the user's input.
[0156] Based on the intelligent comfort control command, the microcomputer 301 may transmit a recommended temperature (or preferred temperature) request command to the data learning server DS via the near field communication module 302, as in operation 325. At this time, the recommended temperature request command may include, for example, the current temperature of the air conditioner A as the state information of the air conditioner A. Alternatively, the recommended temperature request command may further include at least one of operation mode information indicating the current operation mode and location information of the air conditioner A.
[0157] In operation 326, the data learning server DS may obtain the recommended temperature of the air conditioner A as a result of applying the learning model of the state information of the air conditioner A. That is, the data learning server DS may input the state information of the air conditioner A into the learning model stored in the data learning server DS to obtain the recommended temperature of the air conditioner A.
[0158] In this case, the data learning server DS can apply the state information of the air conditioner A to the learning model corresponding to the operation mode of the air conditioner A based on the operation mode information of the air conditioner A to obtain the recommended temperature of the air conditioner A. In this embodiment, the data learning server DS can obtain the recommended temperature of the air conditioner A by applying the state information of the air conditioner A to the learning model corresponding to the intelligent comfort mode.
[0159] Once the recommended temperature is acquired, the data learning server DS may transmit the acquired recommended temperature to the microcomputer 301 via the near field communication module 302 in operation 327 .
[0160] The microcomputer 301 receiving the recommended temperature may change the recommended temperature to a set temperature in operation 328. Then, the microcomputer 301 may control the air conditioner A depending on the changed set temperature.
[0161] On the other hand, if no response is received from the data learning server DS within a predetermined time (e.g., 30 seconds) 329 after the microcomputer 301 requests the data learning server DS for the recommended temperature, the microcomputer 301 may maintain the existing set temperature in operation 330. The existing set temperature may be, for example, a predetermined temperature before a user input for requesting execution of the smart comfort mode, a predetermined temperature corresponding to the current operation mode (e.g., smart comfort mode), or the like.
[0162] Figure 4 is a table showing an example of generation of a learning model according to an embodiment of the present disclosure.
[0163] refer to Figure 4, the data learning server DS may perform a learning program 404 using different learning data 403 depending on the type 401 of the air conditioner A and the mode 402 of the air conditioner A. For example, the type 401 of the air conditioner A may include a floor air conditioner (FAC) type (or a vertical air conditioner) and a room air conditioner (RAC) type. In this case, the data learning server DS may generate a learning model corresponding to each of the smart comfort mode, the tropical night sleep mode, and the windless tropical night sleep mode as the operation mode of the floor air conditioner. In addition, the data learning server DS may generate a learning model corresponding to each of the 2-step cooling mode, the tropical night sleep mode, and the windless tropical night sleep mode as the operation mode of the room air conditioner.
[0164] If each learning model according to the learning program 404 considering the type 401 of the air conditioner A and the mode 402 of the air conditioner A is generated, the data learning server DS may acquire the recommended temperature using the learning model. In this case, the recommended temperature may be acquired considering the setting range 405 for each operation mode. For example, when the recommended temperature acquired by the data learning server DS exceeds the setting range 405, the temperature closest to the recommended temperature in the setting range 405 may be determined as the final recommended temperature.
[0165] refer to Figure 4 Describing an example of a program for generating a learning model in the intelligent comfort mode 411, the room temperature (or current temperature) and the desired temperature (or set temperature) may be used. In this case, the room temperature may be the room temperature measured when the desired temperature is changed. In addition, as learning data, data imported within a specific time period may be used. The specific time period may be data imported, for example, in a specific year, a specific month, or a specific season. The specific data may be data imported based on the temperature setting history information of the air conditioner of an unspecified user who uses the same or similar product as air conditioner A and the user of air conditioner A. At this time, the unspecified users may be limited to users in the same or similar area or the same or similar environment as air conditioner A, for example.
[0166] In the smart comfort mode 411 , the data learning server DS may use the current temperature (or room temperature), the outside temperature, the outside humidity, and the desired temperature as learning data.
[0167] In addition, the data learning server DS may use external environment information based on the local information of the air conditioner A as learning data. On the other hand, when the data learning server DS may not be able to confirm the local information of the air conditioner A, the data learning server DS may generate, learn, and refresh the learning model using the current temperature and the expected temperature as learning data.
[0168] The data learning server DS may acquire a recommended temperature to be set in the air conditioner A by using the generated, learned, and refreshed learning models.
[0169] In this case, if the acquired recommended temperature exceeds the set range of 22° C. to 26° C., the data learning server DS may determine the final recommended temperature in consideration of the set range.
[0170] For example, if the recommended temperature acquired using the learning model is lower than 22° C., the data learning server DS may determine the recommended temperature to be 22° C. Also, if the recommended temperature acquired using the learning model is higher than or equal to 26° C., the data learning server DS may determine the recommended temperature to be 26° C.
[0171] According to various embodiments, when generating a learning model, the data learning server DS may also assign weights to the most recently imported learning data to generate the learning model.
[0172] Figure 5 is a diagram illustrating an example of giving weights to learning data according to an embodiment of the present disclosure.
[0173] refer to Figure 5 , the data learning server DS can assign different weights to the learning data imported for 1 day, 2 days, and 3 days, respectively, such as Figure 5 Like 501, 502 and 503 in.
[0174] For example, in Figure 5 In 501 of , the data learning server DS may assign a weight of 0.8 to all data of the past year (e.g., data imported from unspecified users), and a weight of 0.2 to the user personal data of air conditioner A imported on the first day (the user's desired temperature and current temperature, etc.). Figure 5 In 502, the data learning server DS may assign a weight of 0.8 to all data of the past year and the user personal data of the air conditioner A imported on the first day, and assign a weight of 0.2 to the user personal data of the air conditioner A imported on the second day. Figure 5 In 503 , the data learning server DS may assign a weight of 0.8 to all data of the past year and the user personal data of the air conditioner A imported on the first and second days, and assign a weight of 0.2 to the user personal data imported on the third day.
[0175] On the other hand, the above weight values are only examples, and the data learning server DS may be preset to different values by the manufacturer, manager, operating system, application provider, etc. of the data learning server DS. Figure 5In , instead of weight 0.8 and weight 0.2, weight 0.9 and weight 0.1 can be used respectively. As another example, in Figure 5 In , instead of weight 0.8 and weight 0.2, weight 0.7 and weight 0.3 can be used respectively.
[0176] On the other hand, the above-mentioned weight may be of a variable type which changes depending on the situation rather than a predetermined fixed type.
[0177] In this case, the weight can be changed manually by an administrator of the data learning server DS, a user of the air conditioner, etc., or can be changed automatically depending on certain conditions. For example, as the total amount of imported learning data increases, the weight of the most recently imported personal data can also be increased accordingly.
[0178] Figure 6 is a diagram illustrating a structure of a cloud server according to an embodiment of the present disclosure.
[0179] The cloud server C may include a batch processor 601, a content provider (CP) data collector 602, a CSV maker 603, a model maker 604, and a learning temperature providing server API 605. The components 601 to 604 of the cloud server C described above use and process the data stored in the storage (or database) of the cloud server C to generate a recommended temperature suitable for the air conditioner A.
[0180] First, the cloud server C may store device state data including state information of the air conditioner A acquired depending on the generation of a state change event of the air conditioner A in the device state storage 651. The device state storage 651 may correspond to, for example, Figure 1A and Figure 1B The cloud server C may acquire the status information stored in the device status storage 651 every predetermined period (eg, every day), and store the raw data generated depending on a specific standard (eg, by date) in the object storage 652 .
[0181] The batch processor 601 of the cloud server C may obtain and filter the row data in the object storage 652, and store the filtered data in a distributed environment data DB (e.g., a non-relational database, Not Only SQL DB, NoSQL DB) 653. The filtered data may be, for example, data including device status data of the air conditioner A or status information extracted from metadata.
[0182] In addition, the CP data collector 602 may store weather data including weather information imported from the external content server CP in the object storage 654 .
[0183] The CSV maker 603 of the cloud server C refines the data acquired from the object distributed environment data DB 653 and the object storage 654 to generate data in a specific format (eg, CSV format) suitable for generation of a learning model, and stores the generated data in the object storage 655 .
[0184] The model maker 604 may obtain data in a specific format from the object storage 655 , generate a learning model using the data, and store the generated learning model in the object storage 656 .
[0185] When the learning model needs to be used, the cloud server C can temporarily store the learning model stored in the object storage 655 in the cache 657, where the cache 657 is a high-speed storage memory.
[0186] In the case where the learning model needs to be used, the recommended temperature providing API 605 of the cloud server C can obtain the recommended temperature of the air conditioner A by using the learning model stored in the cache 657.
[0187] The cloud server C may send the recommended temperature acquired through the acquired recommended temperature providing API 605 to the air conditioner A and the mobile application (app) of the user terminal U.
[0188] At the same time, Figure 6 In the drawings, for ease of explanation, object stores 652, 654, 655, and 656 are represented by different reference numerals, but object stores 652, 654, 655, and 656 may represent the same object store or may mean two or more distributed object stores.
[0189] Fig. 7A and Figure 7B is a diagram illustrating a procedure for generating a learning model according to an embodiment of the present disclosure.
[0190] The learning model can be generated using an artificial intelligence algorithm. For example, a decision tree algorithm, a support vector machine algorithm, a linear discriminant analysis algorithm, a genetic algorithm, or a neural network algorithm simulating neurons in a human neural network can be used to generate a learning model. The neural network algorithm may include multiple network nodes with weights. Multiple network nodes can each establish a connection relationship so that the neuron simulates the synaptic activity of sending and receiving signals through synapses. Moreover, a deep learning algorithm developed in a neural network algorithm can be used to generate a learning model. In a deep learning algorithm, multiple network nodes can be located at different depths (or layers) while depending on the convolutional connection relationship to send and receive data. The learning model may include models such as deep neural networks (deep neural network, DNN), recurrent neural networks (recurrent neuralnetwork, RNN) and models that can provide bidirectional recurrent deep neural networks (bidirectional recurrent deepneural network, BRDNN), but are not limited to the above examples.
[0191] For ease of description, the present disclosure describes a method of providing a recommended temperature using linear regression as an algorithm for generation of a learning model.
[0192] The data learning server DS can derive a learning model such as the following equation 1 according to a linear regression algorithm:
[0193] y=a0+a1x1+a2x2+a3x3...Equation 1
[0194] In the above equation 1, y is a variable related to the set temperature set in the air conditioner A, and a0, a1, a2, and a3 are constant values. In addition, x1 is a variable related to the current temperature, x2 is a variable related to the outdoor temperature, and x3 is a variable related to the outdoor humidity.
[0195] For ease of understanding, a learning model in the case where the number of learning variables (or learning elements) in the above-mentioned Equation 1 is 2 is represented by the following Equation 2.
[0196] y=a0+a1x1...Equation 2
[0197] in this case, Fig. 7A The table shows a set temperature (eg, a user's set temperature) 712 depending on a current temperature (or ambient temperature, room temperature) 711 of the air conditioner.
[0198] Based on the linear regression algorithm, the data learning server DS may derive a learning model, which is a calculation expression representing the relationship in which the set temperature 712 depends on the current temperature 711 .
[0199] This is Figure 7B As shown in the figure shown in .
[0200] refer to Figure 7B , Fig. 7A The current temperature 711 and the set temperature 712 in the graph, when plotted on the x-axis and the y-axis, may correspond to a mark 'X' in the graph.
[0201] In this case, a linear regression line 721 using a linear regression algorithm can be obtained so that the sum of errors of multiple "X" marks is small. That is, in the above equation 2, constant values a0 and a1 having the minimum difference between the set temperature 712 of air conditioner A and the predicted temperature can be calculated.
[0202] An example of a linear regression model reflecting the calculated constant value is shown below.
[0203] y = 29.91840623 + (-0.3717125) x1 ... Equation 3
[0204] Therefore, the data learning model DS may provide the recommended temperature to the air conditioner A according to the recommended temperature request command of the air conditioner A based on the following Equation 3.
[0205] For example, when the current room temperature around the air conditioner A is 26°C, the recommended temperature provided by the learning model using the above Equation 3 may be 19°C.
[0206] According to various embodiments, the learning model may be continuously refreshed (or updated).
[0207] To this end, the data learning server DS may further include a model refresher (not shown). The model refresher may analyze the correlation between the basic learning data used in the learning model that has been previously constructed and the newly input learning data to determine whether to refresh the learning model. At this time, the correlation may be determined based on the region and time when the learning data was generated, the time, the model of the air conditioner that provides the learning data, etc.
[0208] For example, the model refresher may continuously refresh the already constructed learning model by using the user's temperature setting history for setting the temperature of the air conditioner A, the user's change history for recommending the temperature, and the like as learning data.
[0209] According to various embodiments, the learning model may be stored in the memory of the air conditioner A, rather than in a separate server. In this case, the learning model constructed in the data learning server DS may be transmitted to the air conditioner A periodically or when an event is generated.
[0210] When the learning model is provided in the air conditioner A, the air conditioner A can obtain the recommended temperature using the stored learning model. For example, the air conditioner A can obtain the recommended temperature by inputting the sensed current temperature into the learning model. In this case, the air conditioner A can obtain the recommended temperature using the sensed current temperature without user intervention, and the temperature of the air conditioner A can be automatically set depending on the recommended temperature.
[0211] Figure 8 is a block diagram illustrating a configuration of an air conditioner according to an embodiment of the present disclosure.
[0212] refer to Figure 8 , the air conditioner A may include a temperature sensor 810, a blower fan 820, a communication unit 830, a storage 840, and a processor 850. In various embodiments, the air conditioner A may omit at least one of the above components or may additionally include other components.
[0213] The temperature sensor 810 may sense the room temperature around the air conditioner A.
[0214] The blower fan 820 may discharge cooling air to the outside through an opening / closing portion (not shown). Alternatively, in the windless mode, the blower fan 820 may discharge cooling air to the outside through a plurality of micro holes (not shown) at a predetermined flow rate or less. At this time, the predetermined flow rate may be 0.25 m / s or less, preferably 0.15 m / s or less.
[0215] The communication unit 830 may perform communication with an external device. At this time, the external device may include at least one of a cloud server C, a data learning server DS, and a user terminal U. The communication between the communication unit 830 and the external device may include communicating with the external device via a third device, etc. For example, the communication unit 830 may receive a remote control signal for controlling the air conditioner A from the user terminal U.
[0216] The communication unit 830 can communicate with the external device via wired communication or wireless communication. For example, the communication unit 830 can communicate with the control terminal device via cellular communication, near field communication, Internet network, and a port to be connected via a cable, and perform communication according to standards such as universal serial bus (USB) communication, Wi-Fi, Bluetooth, Zigbee, infrared data association (IrDA), RF such as UHF and VHF, and ultra-wideband (UWB) communication.
[0217] The storage 840 stores various software and programs for executing the functions of the air conditioner A. Specifically, the storage 840 may store a temperature control algorithm according to a plurality of operation modes. The temperature control algorithm may include changes in the set temperature, the intensity of the wind speed, the direction of the wind speed, etc. depending on a predetermined period for each operation mode. In addition, according to the present disclosure, the storage 840 may store a learned learning model based on the set temperature and the current temperature.
[0218] The processor 850 may read a program stored in the storage 840, etc. Specifically, in order to perform the function of the air conditioner A, the processor 850 may read a program including a series of readable instructions and perform temperature control according to a set temperature.
[0219] The processor 850 can sense the pressure and / or temperature of the refrigerant in the indoor heat exchanger (not shown) to sense whether the temperature control is performed normally. For example, the processor 850 can sense whether the pipe of the indoor heat exchanger is damaged or covered with frost, and whether the water generated by the condensation of steam in the air is properly removed.
[0220] The processor 850 can control the speed of the blower fan 820. Specifically, the processor 850 can control the current temperature measured by the temperature sensor 810 and the speed at which the blower fan 820 rotates according to the set temperature. Specifically, the processor 850 can control the speed at which the blower fan 820 rotates depending on the difference between the current temperature and the set temperature. For example, if the difference between the current temperature and the set temperature is large, the rotation speed of the blower fan 820 is controlled to quickly reach the set temperature, and if the difference between the room temperature and the set temperature is small or the room temperature reaches the set temperature, the room temperature drops excessively, the rotation speed of the blower fan 820 can be slowed down so that the compressor of the outdoor unit will not be turned off. For example, the processor 850 can control the rotation speed of the blower fan 820 to be between 500RPM and 900RPM.
[0221] The processor 850 may control the communication unit 830 to transmit the current temperature and the set temperature sensed by the temperature sensor 810 to an external device.
[0222] In addition, the processor 850 may control the communication unit 830 to receive the recommended temperature received from the external device, and control the recommended temperature acquired through the communication unit 830 to be set in the air conditioner A as the set temperature.
[0223] In addition, the processor 850 may control the communication unit 830 to transmit the current temperature sensed by the temperature sensor 810 to the external device, and may receive the recommended temperature and set the received recommended temperature in the air conditioner depending on the transmission of the current temperature from the external device. In this case, the recommended temperature may be a result of applying the current temperature sensed by the temperature sensor 810 to the learned learning model using a plurality of set temperatures and a plurality of current temperatures set in the air conditioner A. In this case, the external device may include at least one of the cloud server C, the learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0224] According to various embodiments, there may be a network system including the air conditioner A and a learning model server DS that generates a learning model using learning data acquired from the air conditioner A.
[0225] In this case, the air conditioner A of the network system may include a temperature sensor 810 that senses the current temperature, a blower fan 820 that discharges cooling air to the outside, and a communication unit 830 that can communicate with an external device. The air conditioner A may include a processor 850 that controls the communication unit 830 to transmit the set temperature set in the air conditioner A and the current temperature sensed by the temperature sensor 810 to the external device.
[0226] In this case, the external device may include at least one of a cloud server C, a learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0227] In addition, the learning model server DS of the network system may include a learning data acquisition unit (eg, Figure 2A A learning data acquisition unit 203a), a model learning unit (eg, Figure 2A A model learning unit 203b), and a storage (e.g., Figure 2A Memory 202).
[0228] According to various embodiments, there may be a network system including the air conditioner A and a learning model server DS that uses recognition data acquired from the air conditioner A to provide a recommended temperature.
[0229] In this case, the air conditioner A of the network system includes a temperature sensor 810 for sensing the current temperature, a blower fan 820 for discharging cooling air to the outside, a communication unit 830 capable of communicating with an external device, and a processor 850 that controls the communication unit 830 to send the current temperature sensed by the temperature sensor 810 to the external device.
[0230] In this case, the external device may include at least one of a cloud server C, a learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0231] In addition, the learning model server DS may include a storage (eg, Figure 2B Memory 202), an identification data acquisition unit for acquiring the current temperature of air conditioner A (for example, Figure 2B The recognition data acquisition unit 203c), and the model application unit (for example, Figure 2B The model applicator 203d of FIG. 10 is a model applicator 203d of FIG. 10 and a communication unit (eg, Figure 2B The external device may include an air conditioner A or a third device communicatively connected to the air conditioner A. In addition, the external device may include a user terminal U or a third device communicatively connected to the user terminal U to send the recommended temperature.
[0232] Fig. 9 is a block diagram showing a configuration of a user terminal according to an embodiment of the present disclosure.
[0233] refer to Fig. 9 The user terminal U may include a display 910 , a communication unit 920 , an input 930 , a storage 940 and a processor 950 .
[0234] The display 910 may visually provide information to a user of the user terminal U. For example, the display 910 may display a screen including an artificial intelligence operation UI under the control of the processor 950 .
[0235] The communication unit 920 can establish a wired or wireless communication unit channel between the user terminal U and the external device, and support communication performance through the established communication channel. The external device may include, for example, at least one of a cloud server C, a learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0236] The communication unit 920 can use a wireless communication module (e.g., a cellular communication module, a local area wireless communication module, and a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) communication module or a power line communication module) to communicate with an external device through a near field communication network (e.g., Bluetooth, WiFi direction, or infrared data association (IrDA)), etc.) or a long-distance communication network (e.g., a cellular network, the Internet, or a computer network (e.g., LAN or WAN), etc.). The above-mentioned several communication modules can be implemented as a single chip, or can be implemented as separate chips respectively.
[0237] The input 930 may receive a command or data to be used for a component (e.g., the processor 950) of the user terminal U from the outside (e.g., the user) of the user terminal U. The input 930 may include, for example, a button, a microphone, a touch pad, etc. The input 930 may transmit a user input signal generated depending on a user input for controlling the user terminal U to the processor 950.
[0238] The storage 940 may store various data, such as software (e.g., program) used by at least one component (e.g., processor 950) of the user terminal U, and may store input data or output data for commands associated therewith. The storage 940 may include volatile and / or non-volatile memory.
[0239] The program is software stored in the storage 940 , and may include, for example, an operating system, middleware, or an application.
[0240] The processor 950 may drive software (e.g., a program) stored in the storage 940, for example, to control at least one other component (e.g., a hardware or software component) of the user terminal U connected to the processor 950, and perform various data processing and operations. The processor 950 may load commands or data received from other components (e.g., the communication unit 920) into a volatile memory, process the loaded commands or data, and may store the resulting data in a non-volatile memory. According to an embodiment, the processor 950 may include a main processor (e.g., a central processing unit or an application processor), and a sub-processor (e.g., a graphics processor, an image signal processor, a sensor hub processor, or a communication processor) that operates independently of the main processor and additionally or alternatively uses lower power than the main processor or is dedicated to a specified function. The sub-processor may operate separately from the main processor, or may operate while being embedded.
[0241] According to various embodiments, if a user input signal depending on a user input of selecting an artificial intelligence operation UI included in a screen provided by the display 910 is received via the input 930, the processor 950 may control the communication unit 920 to transmit an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner A. If a recommended temperature set in the air conditioner A depending on the artificial intelligence operation request signal is acquired through the communication unit 920, the processor 950 may control the display 910 to display the acquired recommended temperature. At this time, the recommended temperature may be acquired as a result obtained by allowing the air conditioner A to apply the current temperature of the air conditioner A to the learning model. In this case, the processor 950 may control the display 910 so that the user displays the set temperature set in the air conditioner A in the past and the recommended temperature at the current temperature.
[0242] According to various embodiments, a network system including an air conditioner A and a user terminal U controlling the air conditioner A may exist.
[0243] In this case, if a user input signal depending on a user input selecting an artificial intelligence operation UI included in a screen provided by the display 910 of the user terminal U is received via the input 930, the processor 950 can control the communication unit 920 to send an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner A.
[0244] If the air conditioner A receives an artificial intelligence operation request through the communication unit 830 of the air conditioner A, the processor 850 of the air conditioner A may control the communication unit 830 to send the current temperature of the air conditioner A to the external device. The processor 850 of the air conditioner A may control the communication unit 830 to receive the recommended temperature sent from the external device depending on the current temperature. The processor 850 may set the recommended temperature received through the communication unit 830 in the air conditioner A. In this case, the recommended temperature may be a result obtained by applying the current temperature to the learned learning model based on a plurality of set temperatures and a plurality of current temperatures previously set in the air conditioner A. In this case, the external device may include at least one of the cloud server C, the learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0245] Fig. 10A and Fig. 10B is a diagram illustrating a screen of a user terminal on which a recommended temperature is displayed according to an embodiment of the present disclosure.
[0246] refer to Fig. 10A , the user terminal U can display the air conditioner control screen 1010 by executing an application capable of controlling the air conditioner A.
[0247] The air conditioning control screen 1010 may include a UI 1011 for turning on / off air conditioning A, a UI 1012 for selecting an operating mode of air conditioning A, current temperature information 1013, information 1014 on whether the artificial intelligence mode is operating, a damper setting UI 1015, a wind intensity setting UI 1016, a windless operation UI 1017, a UI 1018 on whether air cleaning operation is performed, an artificial intelligence setting UI 1019, a reservation setting UI 1020, and the like.
[0248] In this case, when the air conditioning control screen 1010 is outside the viewport range of the display of the user terminal UI, the user may display the air conditioning control screen 1110 outside the viewport range in the viewport range through a drag gesture.
[0249] refer to Fig. 10A and Fig. 10B In this case, if a user input for selecting the artificial intelligence setting UI 1019 is received, the user terminal U may display the artificial intelligence control screen 1020 in the operating mode of the air conditioner (e.g., the smart comfort mode), such as Fig. 10B The artificial intelligence control screen 1020 may include an artificial intelligence operation UI 1021 for the artificial intelligence mode operation of the air conditioner A and artificial intelligence operation information 1022 indicating the artificial intelligence mode operation of the air conditioner A.
[0250] In this case, if a user input for selecting the artificial intelligence operation UI 1021 is received, the user terminal U can obtain the recommended temperature set in the air conditioner based on the user input. For example, the user terminal U can obtain the recommended temperature via a third device (e.g., an access point (AP)) communicatively connected to the cloud server C.
[0251] Then, the user terminal U may display the recommended temperature 1023 on the artificial intelligence control screen 1020. At this time, the recommended temperature 1023 may be acquired based on the user input of selecting the artificial intelligence operation UI 1021 as a result obtained by allowing the air conditioner A to apply the current temperature of the air conditioner A to the learning model server DS.
[0252] The user terminal U may display not only the recommended temperature 1023 on the artificial intelligence control screen 1020, but also the set temperature 1024 directly set by the user of the air conditioner A in the past in the air conditioner A. In this case, the recommended temperature 1023 and the set temperature 1034 may be displayed together on a graph for comparison with each other.
[0253] Fig.11 is a flowchart illustrating a method for generating a learning model of a data learning server according to an embodiment of the present disclosure.
[0254] refer to Fig.11 In operation 1101, the data learning server DS may acquire the set temperature set in the air conditioner A and the current temperature of the air conditioner A at the set temperature. In addition, the data learning server DS may also acquire the external environment information of the air conditioner A.
[0255] At this time, the data learning server DS may acquire the set temperature and the current temperature from the bridge server BS communicatively connected to the air conditioner A, and acquire external environment information from the smart home service server SS communicatively connected to the external content providing server (CP).
[0256] In addition, the data learning server DS can also obtain time information when setting the temperature in the air conditioner A.
[0257] In operation 1103 , the data learning server DS may generate or refresh a learning model using the acquired set temperature and current temperature.
[0258] When the data learning server DS further acquires external environment information, the data learning server DS may generate or refresh the learning model using the acquired set temperature, current temperature, and external environment information.
[0259] In addition, when the data learning server DS further acquires time information when setting the temperature, the data learning server DS may generate or refresh the learning model using the acquired set temperature, current temperature, and time information.
[0260] In operation 1105 , the data learning server DS may store the learned learning model to provide a recommended temperature to be set in the air conditioner A as a result of generating and refreshing the learning model.
[0261] Meanwhile, the data learning server DS may generate or refresh a plurality of learning models for each operation mode of the air conditioner A. In this case, the data learning server DS may store a plurality of learning models.
[0262] Fig.12 is a flowchart illustrating a method for learning a learning model of a server using data according to an embodiment of the present disclosure.
[0263] refer to Fig.12 In operation 1201 , the data learning server DS may store a learned learning model to provide a recommended temperature to be set in the air conditioner A.
[0264] In the case where the learned learning model is stored, the data learning server DS may acquire the current temperature of the air conditioner A in operation 1203. In this case, the data learning server DS may also acquire external environment information of the air conditioner A.
[0265] In operation 1205 , the data learning server DS may input the acquired current temperature into the learned learning model to acquire a recommended temperature to be set in the air conditioner A.
[0266] In addition, when the data learning server DS further acquires external environment information, the data learning server DS may input the acquired recommended temperature and the external environment information into the learning model to acquire the recommended temperature to be set in the air conditioner A.
[0267] Meanwhile, the data learning server DS may store a plurality of learning models for each operation mode of the air conditioner A. In this case, the data learning server DS may input the acquired current temperature into the learning model corresponding to the current operation mode of the air conditioner A, and input the acquired current temperature into the learning model corresponding to the current operation mode of the air conditioner A to obtain a recommended temperature to be set in the air conditioner A.
[0268] In operation 1207, the data learning server DS may send the acquired recommended temperature to an external device. The external device may be, for example, the air conditioner A or a third device communicatively connected to the air conditioner A to send the recommended temperature. In addition, the external device may be a user terminal U or a third device communicatively connected to the user terminal U to send the recommended temperature.
[0269] Fig.13 is a flowchart illustrating a method for providing a recommended temperature of an air conditioner A according to an embodiment of the present disclosure.
[0270] refer to Fig.13 , in operation 1301, air conditioner A can sense the current temperature of air conditioner A.
[0271] Next, in operation 1303, the air conditioner A may transmit the sensed current temperature to an external device. For example, the air conditioner A may transmit the sensed current temperature to at least one of the cloud server C, the learning model server DS, and a third device that communicates with the cloud server C or the learning model server DS.
[0272] In operation 1305, the air conditioner A may receive a recommended temperature from an external device depending on the transmission of the current temperature, the recommended temperature being a result of applying the current temperature to the learning model. In this case, the recommended temperature may be a result obtained by applying the current temperature to the learned learning model based on a plurality of set temperatures and a plurality of current temperatures previously set in the air conditioner A.
[0273] In operation 1307 , the air conditioner A may set the received recommended temperature in the air conditioner.
[0274] Fig.14is a flowchart illustrating a method for controlling an air conditioner of a user terminal according to an embodiment of the present disclosure.
[0275] refer to Fig.14 , in operation 1401, the user terminal U may receive a user input signal depending on a user input selecting an artificial intelligence operation UI.
[0276] In operation 1403, the user terminal U may transmit an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner A in response to the user input signal.
[0277] In operation 1405 , the user terminal U may acquire a recommended temperature set in the air conditioner A as a result of applying the current temperature of the air conditioner A to the learning model depending on the artificial intelligence operation request signal.
[0278] In operation 1407, the user terminal U may display the acquired recommended temperature on the screen. In this case, the user terminal U may display the set temperature previously set by the user in the air conditioner A and the recommended temperature at the current temperature.
[0279] Fig.15 is a flow chart of a network system including a user terminal and an air conditioner according to an embodiment of the present disclosure.
[0280] refer to Fig.15 , in operation 1501, the user terminal U may receive a user input signal depending on a user input selecting an artificial intelligence operation UI.
[0281] In operation 1503 , the user terminal U may transmit an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner A.
[0282] In operation 1505 , the air conditioner A may sense the current temperature of the air conditioner A.
[0283] Next, in operation 1507, the air conditioner A may transmit the sensed current temperature to the external device 1500. The external device may include at least one of the cloud server C, the learning model server DS, and a third device communicatively connected to the cloud server C or the learning model server DS.
[0284] In operation 1509, the air conditioner A may receive a recommended temperature from the external device 1500 depending on the transmission of the current temperature, the recommended temperature being the result of applying the current temperature to the learning model. In this case, the learning model may be a learning model learned using a plurality of set temperatures previously set in the air conditioner A and a plurality of current temperatures.
[0285] In operation 1511, the air conditioner A may set the received recommended temperature in the air conditioner.
[0286] The disclosed embodiments may be implemented as a S / W program including instructions stored on a computer-readable storage medium.
[0287] The computer is a device that calls stored instructions from a storage medium and can operate according to the disclosed embodiments depending on the called instructions, and may include a data learning server according to the disclosed embodiments or an external server communicatively connected to the data learning server. Alternatively, according to the disclosed embodiments, the computer may include an air conditioner or an external server communicatively connected to the air conditioner.
[0288] The computer-readable storage medium may be provided in the form of a non-transitory storage medium. "Non-transitory" means that the storage medium does not include signals and currents and is tangible, but "non-transitory" does not distinguish whether data is stored in the storage medium semi-permanently or temporarily. For example, the non-transitory storage medium may be a temporary storage medium such as a register, a cache, and a buffer, and a non-transitory readable recording medium such as a CD, a DVD, a hard disk, a Blu-ray disc, a USB, a memory, a memory card, a ROM, and a RAM.
[0289] Furthermore, the method according to the disclosed embodiments may be provided as a computer program product.
[0290] The computer program product may include an S / W program, a computer-readable storage medium in which the S / W program is stored, or a product traded between a seller and a buyer.
[0291] For example, a computer program product may include a product (e.g., a downloadable application) in the form of a software program electronically distributed via a data learning server, an air conditioner manufacturer, or an electronic market (e.g., Google Play Store, AppStore). For electronic distribution, at least a portion of the software program may be stored on a storage medium or may be temporarily generated. In this case, the storage medium may be a storage medium of a manufacturer or server of an electronic market, or a relay server.
[0292] Although the embodiments of the present disclosure have been illustrated and described, the present disclosure is not limited to the above-mentioned specific embodiments, but various modifications can be made by those skilled in the art to which the present disclosure belongs without departing from the spirit and scope of the present disclosure as claimed in the claims. In addition, it should also be understood that these modifications fall within the scope of the present disclosure.
[0293] While the present disclosure has been shown and described with reference to various embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents.
Claims
1. An air conditioner, include: a blower fan configured to discharge cooling air to the outside, a temperature sensor configured to sense a current temperature around the air conditioner, monitor; as well as At least one processor configured to: obtaining a recommended temperature which is a result obtained by applying a current temperature of the air conditioner when one of a plurality of operation modes of the air conditioner is set to a learning model corresponding to the set operation mode of the air conditioner, The control display shows the recommended temperature to be achieved, and Set the recommended temperature obtained in the air conditioner.
2. The air conditioner according to claim 1, in, The learning model is a learning model that learns to identify a recommended temperature based on a plurality of set temperatures previously set in a set operation mode of the air conditioner and a plurality of current temperatures previously sensed in the set operation mode of the air conditioner.
3. The air conditioner according to claim 1, further comprising: include: A memory is configured to store a plurality of learning models for each operation mode of the air conditioner to provide the air conditioner with a recommended temperature to be set.
4. The air conditioner according to claim 1, in, The at least one processor is further configured to: Obtaining external environment information, and The external environment information is input into the learning model to obtain the recommended temperature to be set in the air conditioner.
5. A computer-implemented method for air conditioning, the method include: obtaining, by at least one processor, a recommended temperature, the recommended temperature being a result obtained by applying a current temperature of the air conditioner when one of a plurality of operation modes of the air conditioner is set to a learning model corresponding to the set operation mode of the air conditioner; The recommended temperature obtained is shown on the display; as well as The obtained recommended temperature is set in the air conditioner by the at least one processor.
6. The method according to claim 5, in, The learning model is a learning model that learns to identify a recommended temperature based on a plurality of set temperatures previously set in a set operation mode of the air conditioner and a plurality of current temperatures previously sensed in the set operation mode of the air conditioner.
7. The method according to claim 5, in, The air conditioner further includes a plurality of learning models for each operating mode of the air conditioner to provide the air conditioner with a recommended temperature to be set; as well as Among them, obtaining the recommended temperature includes: Get the current temperature of the air conditioner through the temperature sensor.
8. The method according to claim 5, in, Getting the recommended temperature includes: Obtaining information about the external environment; and The external environment information is input into the learning model to obtain the recommended temperature to be set in the air conditioner.
9. A user terminal for controlling an air conditioner, the user terminal include: a display configured as a display screen; a communicator configured to communicate with an external device; an input receiver configured to receive user input; as well as At least one processor configured to: controlling the communicator to transmit an artificial intelligence operation request signal corresponding to the artificial intelligence operation UI to the air conditioner in response to a user input signal depending on a user input of selecting the artificial intelligence operation UI included in the screen, received through the input receiver, and In response to a recommended temperature set in the air conditioner, a control display displays the recommended temperature, which is a result obtained by applying the current temperature of the air conditioner when one of the multiple operating modes of the air conditioner is set to a learning model corresponding to the set operating mode of the air conditioner depending on an artificial intelligence operation request signal obtained through the communicator.
10. The user terminal according to claim 9, in, The learning model is a learning model that learns to identify a recommended temperature based on a plurality of set temperatures previously set in a set operation mode of the air conditioner and a plurality of current temperatures previously sensed in the set operation mode of the air conditioner.
11. The user terminal according to claim 9, in, The at least one processor is further configured to control the display to display a previously set temperature in the air conditioner together with the current temperature.
