Method for changing feature of home appliance, and server and device for implementing same

Abstract

The present invention relates to a method for changing a feature of a home appliance, and a server and device for implementing same. According to one embodiment of the present invention, the method for changing a feature of a home appliance comprises: a first step in which a server or home appliance calculates a first feature set and a first accuracy corresponding to a feature command; a second step in which the server or home appliance calculates a second feature set and a second accuracy corresponding to the feature command by using a theme module disposed in the server, the home appliance, or an external server when the first accuracy is not greater than the threshold; a third step in which the server or home appliance calculates a third feature set by using personalized information and the feature command corresponding to appliance information about the home appliance when the second accuracy is not greater than the threshold; and a fourth step for changing any one feature set among the first feature set, the second feature set, or the third feature set to a feature of the home appliance.

Description

Method for changing the features of home appliances and server and device implementing the same

[0001] The present invention relates to a method for changing features of a home appliance and a server and device for implementing the same.

[0002] Control methods for devices like home appliances can be divided into direct control through human intervention and natural language command control. In direct control, the user can control the operation of the appliance by operating the remote control, buttons on the appliance, or dial. In natural language control, the user inputs natural language commands to the appliance, which are then recognized and operated.

[0003] However, natural language commands spoken or entered by users are based on individual differences in natural language, making interpretation and translation into actual commands challenging. In particular, accuracy in interpreting natural language commands is required, depending on each user's past command input habits and the device's usage environment.

[0004] Accordingly, this specification describes a method and device for providing personalized services by adaptively receiving user-input commands and changing specific features of a home appliance.

[0005] The present specification is intended to solve the aforementioned problems and to implement a method and device for processing commands that accurately reflect a user's intention when processing voice commands for changing features of electronic devices including home appliances.

[0006] Additionally, this specification allows for providing personalized services by reflecting the user's preferences when processing the user's commands.

[0007] In addition, this specification provides various recognition methods for user commands to increase accuracy in changing the color, function, or voice message of home appliances.

[0008] The objectives of the present invention are not limited to those mentioned above. Other objectives and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objectives and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0009] A method for changing a feature of a home appliance according to one embodiment of the present invention includes a first step in which a server or a home appliance calculates a first feature set and a first accuracy corresponding to a feature command, a second step in which the server or the home appliance calculates a second feature set and a second accuracy corresponding to the feature command using a theme module arranged on the server, the home appliance, or an external server when the first accuracy is below a reference level, a third step in which the server or the home appliance calculates a third feature set using personalized information and a feature command corresponding to device information of the home appliance when the second accuracy is below a reference level, and a fourth step in which any one of the first feature set, the second feature set, or the third feature set is changed to a feature of the home appliance.

[0010] According to one embodiment of the present invention, a server includes a preprocessing module that receives a feature command input by a home appliance and calculates a first feature set and a first accuracy corresponding to the feature command, a theme module that calculates a second feature set and a second accuracy corresponding to the feature command when the first accuracy is below a reference level, and a personalization module that calculates a third feature set using personalized information and a feature command corresponding to device information of the home appliance when the second accuracy is below the reference level, and the home appliance sets one feature set among the first feature set, the second feature set, or the third feature set as a feature of the home appliance.

[0011] According to another embodiment of the present invention, a server includes a preprocessing module that receives a feature command input by a home appliance and calculates a first feature set and a first accuracy corresponding to the feature command, a counter theme module that transmits the feature command to a theme module of a generative AI external server when the first accuracy is below a reference level and receives a second feature set and a second accuracy from the theme module, and a personalization module that calculates a third feature set using personalized information and a feature command corresponding to device information of the home appliance when the second accuracy is below a reference level, and the home appliance changes one of the feature sets of the first feature set, the second feature set, or the third feature set into a feature of the home appliance.

[0012] A device according to one embodiment of the present invention includes a command input module for receiving a feature command, a preprocessing module for receiving the feature command and calculating a first feature set and a first accuracy corresponding to the feature command, a theme module for calculating a second feature set and a second accuracy corresponding to the feature command when the first accuracy is below a reference level, a personalization module for calculating a third feature set using stored personalization information and the feature command when the second accuracy is below the reference level, and a feature setting module for setting any one of the first feature set, the second feature set, or the third feature set as a feature of the device.

[0013] A method for changing a feature of a home appliance according to another embodiment of the present invention includes one or more processors that process information received from the home appliance and input the information into a theme module, which is a generative AI model, to obtain a result, and the processor includes a step of receiving a feature command instructing a change in a feature of the first home appliance from the first home appliance or the second home appliance, a step of generating a prompt including any one of the feature command and configuration information of the first home appliance corresponding to the feature command, a step of inputting the prompt into the theme module to obtain a result, and a step of converting the result into a first feature set to be set in the first home appliance.

[0014] When the present invention is applied, a method and device can be implemented to process a voice command for changing the features of a home appliance by accurately reflecting the user's intention.

[0015] When the present invention is applied, a personalized service can be provided by reflecting the user's tendencies when processing the user's commands.

[0016] When the present invention is applied, it is possible to provide various recognition methods for user commands, thereby increasing accuracy in changing the color, function, or voice message of a home appliance.

[0017] The effects of the present invention are not limited to the effects described above, and various effects of the present invention can be easily derived from the configuration of the present invention.

[0018] FIG. 1 is a drawing showing a process in which a home appliance changes a feature according to a feature command input according to one embodiment of the present invention.

[0019] FIG. 2 is a diagram showing a process in which, when a feature command is input according to another embodiment of the present invention, a home appliance transmits the feature command to a server and then receives a feature set from the server to change the features of the home appliance.

[0020] FIG. 3 is a diagram showing a process in which a server or home appliance generates a feature set according to one embodiment of the present invention.

[0021] FIG. 4 is a diagram showing a process in which a server processes a feature command according to one embodiment of the present invention.

[0022] FIG. 5 is a diagram showing a process for processing a color command according to one embodiment of the present invention.

[0023] Figure 6 is a drawing showing the configuration of a personalization module according to one embodiment of the present invention.

[0024] FIG. 7 is a diagram showing a process in which a personalization module according to one embodiment of the present invention makes recommendations using personalized information.

[0025] FIG. 8 is a diagram showing a process of producing a feature set based on a theme module (320) according to one embodiment of the present invention.

[0026] FIG. 9 is a diagram showing a processing process when fine adjustment of a feature set occurs according to one embodiment of the present invention.

[0027] FIG. 10 is a drawing showing a configuration including all components in a home appliance according to one embodiment of the present invention.

[0028] FIG. 11 is a diagram showing a server including a preprocessing module, a theme module, a personalization module, and a database according to another embodiment of the present invention.

[0029] FIG. 12 is a diagram showing a server including a preprocessing module, a personalization module, and a database according to another embodiment of the present invention.

[0030] FIG. 13 is a drawing showing the configuration of a home appliance, a home appliance for voice processing, and a server according to one embodiment of the present invention.

[0031] FIG. 14 is a drawing showing an interface for changing colors for a command input by a user according to one embodiment of the present invention.

[0032] FIG. 15 is a drawing showing a process of changing the colors of a plurality of home appliances according to one embodiment of the present invention.

[0033]

[0034]

[0035] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present invention. The present invention may be implemented in various different forms and is not limited to the embodiments described herein.

[0036] In order to clearly explain the present invention, parts that are not related to the description have been omitted, and the same or similar components are designated by the same reference numerals throughout the specification. In addition, some embodiments of the present invention will be described in detail with reference to exemplary drawings. When adding reference numerals to components in each drawing, the same components may have the same numerals as much as possible even if they are shown in different drawings. In addition, when explaining the present invention, if it is determined that a specific description of a related known configuration or function may obscure the gist of the present invention, the detailed description may be omitted.

[0037] When describing components of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by the terms. When it is described that a component is "connected," "coupled," or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but that other components may also be "interposed" between each component, or that each component may be "connected," "coupled," or "connected" through another component.

[0038] In addition, in implementing the present invention, components may be described in detail for convenience of explanation, but these components may be implemented in one device or module, or one component may be implemented by being divided into multiple devices or modules.

[0039] Hereinafter, the home appliances described herein are devices containing electronic products. Home appliances can be placed in homes, offices, and other locations, and can be moved and placed in other locations by people.

[0040] Additionally, the home appliances described herein may include electronic devices such as user terminals, such as smartphones, tablets, and iPads. Furthermore, hubs (e.g., AI speakers) that communicate with and control various electronic devices based on wired / wireless communication may also be considered home appliances.

[0041] Additionally, the devices described in this specification, for example, home appliances, can change some of the appearance of the home appliance or change some elements in its operation by applying a specific feature set.

[0042] Sub-concepts of feature sets include color sets, speech sets related to speech patterns and voices, and function sets related to functions in the operation of home appliances.

[0043] A feature set can contain a bundle of information, such as each feature and its corresponding region or function. For example, a feature set can be structured as follows:

[0044] { {1st feature information, 2nd feature information, ..., nth feature information},

[0045] { 1st application area, 2nd application area, ..., nth application area}}

[0046]

[0047] Alternatively, the feature set can be structured as follows:

[0048] { {First feature information, first application area},

[0049] {Second feature information, second application area}, ...,

[0050] {nth feature information, nth application area}}

[0051] If the application area is predetermined based on the order of feature information, the application area information can be omitted from the feature set. For example, if the generative AI module is embedded within a home appliance, such as OnDevice, the information regarding the home appliance, including the application area of ​​the home appliance equipped with the generative AI, can be omitted.

[0052] First, let's look at the color set.

[0053] The home appliance described herein can change the color of its exterior according to a specific color set. A color set refers to a specific area of ​​the exterior of the home appliance to which one or more color information and the color indicated by the color information are applied.

[0054] In one embodiment, a color set has the following structure of color information to be applied to n areas of a home appliance. Color information and area information can be bundled separately.

[0055] { {1st color information, 1st area}, {2nd color information, 2nd area}, ... {nth color information, nth area}}

[0056] For example, if the color set to be applied to a refrigerator is {{#093337, LEFT}, {#093537, RIGHT}}, the RGB color value "093337" may be applied to the left door of the refrigerator, and the RGB color value "093537" may be applied to the right door of the refrigerator. The color set of the present invention can be applied to various home appliances (air conditioners, stylers, digital picture frames, etc.) in which light source modules such as LEDs are arranged in addition to refrigerators in which light source modules such as LEDs are arranged to enable color differentiation of the refrigerator door panel. In addition, the same or similar color theme can be applied to all home appliances through linkage between home appliances.

[0057] Color information is, for example, RGB values ​​(hexadecimal), but the present invention is not limited thereto. For example, color information of three hexadecimal digits can indicate 16 levels for each of R, G, and B. Alternatively, specific color names can correspond to color information. For example, color information such as "RED1", "RED2", ..., "ORANGE1", ..., "BLUE1", etc. can also constitute a color set.

[0058] Next, let's look at the speech set.

[0059] The home appliance described in this specification can change the tone, intonation, gender, and pitch of the voice guidance according to a specific speech set. A speech set refers to information indicating the features of the voice guidance message.

[0060] As an example, the speech set can set the tone, intonation, gender, etc. of the voice message provided by the home appliance according to the message output by the home appliance as follows.

[0061] { {First speech information, first voice comment},

[0062] {Second speech information, second voice comment}, ...

[0063] {Gen. n speech information, Gen. n voice comment}

[0064] For example, a speech set to be applied to an air conditioner can be set as follows, where the first voice comment is the comment indicating the on / off of the air conditioner (on-off comment) and the second voice comment is the comment indicating the temperature or wind direction of the air conditioner (operation comment).

[0065] { {Iron Man, on-off comment}, {Elsa, on-off comment}}

[0066] In this case, when turning the air conditioner on or off, it will be guided by Iron Man's voice, and when the air conditioner is in operation, the operating instructions for notifying the temperature or changing the wind speed will be guided by Elsa's voice.

[0067] Next, let's look at the feature set.

[0068] The home appliance described in this specification can control the operation of the home appliance according to a specific function set. A function set is information that allows a user to specifically define one or more components of the home appliance.

[0069] { {First function information, First function},

[0070] {Second function information, second function}, ...

[0071] {nth function information, nth function}}

[0072]

[0073] For example, to set the input source of a TV, you can define a feature set as follows:

[0074] { {YouTube, YouTube link},

[0075] {Netflix, Netflix connection},

[0076] {Cinebeam, Project Connection},

[0077] {Move to the feel-good channel, pet channel}}

[0078]

[0079] When a user speaks or enters specific function information through text or selects function information displayed on the TV, the appliance can provide that function.

[0080] In the configuration of various feature sets described above, the user must input voice or text information into the home appliance to set a specific feature set, but such information may be outside the range of standardized information predefined in the home appliance.

[0081] That is, it is necessary to configure the feature set so that the user's intention is reflected even when the user inputs voice / text with various contents.

[0082] Therefore, we will look at the process of combining the output of generative AI with the user's personal information to perform analysis on the user's input voice and provide an appropriate feature set.

[0083] The feature commands described in this specification are commands that specify or change features via voice or text. However, for convenience, the explanation focuses on voice commands.

[0084] In this specification, processing of feature commands can be performed by both home appliances and server devices. Examples of feature commands include color commands, speech commands, and function commands. Home appliances or server devices (servers) or a system comprised of one or more devices can store hardware or software for processing feature commands. In addition, home appliances or server devices (servers) or a system comprised of one or more devices can receive and execute software for processing feature commands from a remote third party device. Processing of feature commands using hardware embedded in the device, software stored in the device, or software that can be received and executed can be performed by a processor within each device. Alternatively, these hardware or software themselves can operate as processors.

[0085] The language model described in this specification is, as an example, a Large Language Model (LLM). The language model can be embedded within a home appliance or a server device. Alternatively, the language model can be embedded in an external device, in which case the home appliance or server device can obtain the language model results through the external device.

[0086] The personalized information described herein includes information generated during the use of a home appliance. Furthermore, the personalized information according to one embodiment of the present invention includes information generated during the use of other home appliances used by the user of the home appliance. The personalized information according to another embodiment of the present invention includes information generated during the use of other home appliances located in the same space as the home appliance.

[0087] For example, personalized information applied in the process of changing the color of a refrigerator may include information generated during the use of an air conditioner in the space where the refrigerator is placed. Similarly, personalized information applied in the process of changing the color of an air conditioner may include information generated during the use of a refrigerator used by a user of the air conditioner or an air conditioner used by the user in the past.

[0088] Additionally, the personalized information applied when changing a refrigerator's voice guidance includes information generated during the use of the air conditioner in the space where the refrigerator is located. Similarly, the personalized information applied when changing an air conditioner's voice guidance includes information generated during the use of the refrigerator used by the user of the air conditioner or air conditioners previously used by the user.

[0089] Similarly, if there are two air conditioners in a home, the personalized information applied when changing the function of the first air conditioner includes information generated during the use of the second air conditioner in the space where the first air conditioner is installed. Similarly, the personalized information applied when changing the function of the second air conditioner includes information generated during the use of the refrigerator or the first air conditioner by the user of the first air conditioner.

[0090] Additionally, the first home appliance instructed to change a feature in the first or second home appliance may directly receive a voice or text command and process or transmit the same to a server. Alternatively, a second home appliance separate from the first home appliance instructed to change a feature may directly receive a voice or text command and process or transmit the same to a server.

[0091]

[0092] FIG. 1 is a drawing showing a process in which a home appliance changes a feature according to a feature command input according to one embodiment of the present invention.

[0093] A user (1) inputs a predetermined command (voice or text) into a home appliance (100) (S3). Alternatively, the user may input the predetermined command through a hub that is connected to and controls multiple electronic devices, such as a mobile terminal or an AI speaker, in addition to the home appliance. The command may be input by voice (VOICE) or text. The home appliance (device) (100) determines a feature set corresponding to the command based on the result of preprocessing by performing text conversion on the input feature command (S5). To determine the feature set, the home appliance (100) may perform a feature set calculation process of up to three steps. Once the feature set is determined through the feature set calculation process, the home appliance (100) sets the determined feature set to the home appliance (100) (S7).

[0094]

[0095] FIG. 2 is a diagram showing a process in which, when a feature command is input according to another embodiment of the present invention, a home appliance transmits the feature command to a server, and then receives a feature set from the server to change the features of the home appliance.

[0096] For a description related to S3, refer to the contents described above in FIG. 1. The home appliance (100) transmits the input feature command to the server (500) (S11). At this time, if the input command is a voice command, the home appliance (100) can convert the voice command into text and also transmit the feature command, which is the result of performing preprocessing on the text, to the server (500).

[0097] In this case, the server (500) can determine a feature set corresponding to the received feature command (S15). The preprocessing process may also be performed on the server (500). In this case, the home appliance (100) can transmit the input command as is to the server (500).

[0098] To determine a feature set, the server (500) can perform a feature set calculation process of up to three steps. Once a feature set is determined through the feature set calculation process, the server (500) transmits information about the determined feature set to the home appliance (100) (S16), and the home appliance (100) sets the received feature set in the home appliance (100) (S17).

[0099]

[0100] As seen in FIGS. 1 and 2, the server (500) or the home appliance (100) can generate a suitable feature set for the preprocessed feature command. Hereinafter, the feature set generation process performed by the server (500) or the home appliance (100) will be examined.

[0101]

[0102] FIG. 3 is a diagram illustrating a process for generating a feature set by a server or home appliance according to one embodiment of the present invention. The process of FIG. 3 can be performed by either a server (500) or home appliance (100).

[0103] The server (500) or the home appliance (100) calculates a first feature set and a first accuracy corresponding to a feature command (S21). The first feature set corresponding to a feature command refers to a feature set in which a feature command corresponds to the name of a specific feature set or corresponds to the name of a feature.

[0104] That is, a feature set includes one or more feature information and information about the area or function of the device to which the feature information is to be set. If the feature set is a color set, the feature set may be composed of color information and the area / function to which the color is to be applied. If the feature set is a speech set, the feature set may be composed of speech information and the area / function to which the speech is to be applied. If the feature set is a function set, the feature set may be composed of function information and the situation to which the function is to be applied.

[0105] For example, if a color set is an example of a feature set, refer to Table 1.

[0106] Name Color Set Orange {Color1, Color2, Color3}, {Region1, Region2, Region3} Sky Blue {Color11, Color12, Color13}, {Region1, Region2, Region3} Green {Color21, Color22, Color23}, {Region1, Region2, Region3}

[0107] In Table 1, if the color command uttered by the user includes the color names of the colors constituting the first color set, this means that the user has accurately uttered a specific feature set (color set), and thus the server (500) or the home appliance (100) can extract a color set corresponding to the color command. As a result, the server (500) or the home appliance (100) determines in step S31 that the result corresponding to the color command and the accuracy of the result (e.g., the first accuracy) meet the standard.

[0108] For example, when the contents of Table 1 are stored in the server (500) or the home appliance (100) and the user inputs a color command that is somewhat modified, such as "tangerine", "green", or "turquoise", the server (500) or the home appliance (100) can compare the similarity between the color command and the name in Table 1 and calculate an accuracy of 90 or higher. Assuming that the first accuracy judgment standard is 85, the server (500) or the home appliance (100) can extract a color set corresponding to the color command from the stored color set in Table 1.

[0109]

[0110] As another example, if the feature set is a speech set, refer to Table 2.

[0111] Name Color Set Female Adult Voice {Female_Tone1, Female_Tone2}, {Air Conditioner_On / Off, Air Conditioner_Temperature Control} Boy Voice {Boy_Tone1, Boy_Tone2}, {Air Conditioner_On / Off, Air Conditioner_Temperature Control}

[0112]

[0113] For another example, if the feature set is a feature set, refer to Table 3.

[0114] Name Color Set Summer_Heat_Temperature {Temperature 1, Air Volume 1}, {Air Conditioner_Temperature, Air Conditioner_Air Volume} Early Summer_Temperature {Temperature 2, Air Volume 2}, {Air Conditioner_Temperature, Air Conditioner_Air Volume}

[0115] In Table 1, Color1, 2, ..., etc. represent specific color shades, for example, RGB values ​​as an example. Region1, 2, ..., etc. are information about the region to which Color1, Color2, etc. are applied. For example, a color set of { {Color1, Color2, Color3, Color4}, {Region1, Region2, Region3, Region4}} is information indicating that Color1 is applied to Region1, Color2 to Region2, Color3 to Region3, and Color4 to Region4. If the order of the color information constituting the color set is applied to the order of the region, the information about the region may be omitted. In step S21, the first accuracy can be calculated depending on the degree of correspondence between the feature command and the feature set / feature information.

[0116] For example, in the case of a color set, the first accuracy can be calculated based on the degree of correspondence between the color command and the color set / color information. If the color command is "Set the refrigerator color to orange" (Case 1) and "Set the refrigerator color to tangerine" (Case 2), the server (500) or the home appliance (100) can calculate a color set that is an orange-based theme color for both color commands.

[0117] However, in Case 1, the color command and name are the same, but in Case 2, the color command "citrus" is not completely identical to the name in Table 1. Therefore, the server (500) or the home appliance (100) may produce the first color set as the result value for the two color commands, but the accuracy may be different. For example, in Case 1, it may be produced as 100, and in Case 2, it may be produced as 80.

[0118] Similarly, for a speech set, the first accuracy can be calculated based on the degree of correspondence between the speech command and the speech set / speech information. If the speech command is "Change the air conditioner voice to an adult female voice" (Case 1) and "Change the air conditioner voice to a child girl voice" (Case 2), the server (500) or the home appliance (100) can produce different speech sets for the two speech commands.

[0119] That is, in Case 1, the speech command and speech information have the same name, but in Case 2, since it is "girl," two cases can be produced: "female adult" and "boy," resulting in a decrease in accuracy. For example, Case 1 could be produced as 100, while Case 2 could be produced as 80.

[0120] For feature sets, as with color sets / speech sets, accuracy is calculated differently depending on whether the user makes a vocal utterance that accurately matches the name or not.

[0121] Accordingly, if the first accuracy is below the standard, the server (500) or the home appliance (100) uses a theme module (e.g., a language model) to calculate a second feature set and a second accuracy corresponding to the feature command (S31). The theme module may be placed within the server (500) or the home appliance (100) or an external language model server. See FIG. 4.

[0122] When the first accuracy is below the standard, it means that a specific feature set cannot be derived from the predefined name-feature set as shown in Tables 1, 2, and 3.

[0123] For example, in Table 1 and the color command example, a user may input the command "Change the color of the refrigerator to Iron Man." In order to construct a feature set for this, information about the color represented by the character "Iron Man" is required. However, the server (500) or the home appliance (100) cannot produce a result corresponding to the color command using the information in Table 1.

[0124] Therefore, in this case, the first accuracy is calculated as 0 or a very low value, and in S31, the server (500) or the home appliance (100) inputs a feature command (e.g., a color command) into a language model, for example, a large language model (LLM), and calculates a corresponding second feature set (e.g., a second color set) and a second accuracy (S31).

[0125] Additionally, in Table 2 and the example of the speech command, a user may input the command "Change the voice of the air conditioner to that of an old professor." To construct a feature set for this, information about the voice of the "old professor" character is required. However, the server (500) or the home appliance (100) cannot produce a result corresponding to the speech command using the information in Table 2.

[0126] Accordingly, in this case, the first accuracy is calculated as 0 or a very low value, and in S31, the server (500) or the home appliance (100) inputs a feature command (e.g., a speech command) into a language model, for example, a large language model (LLM), and calculates a corresponding second feature set (e.g., a second speech set) and a second accuracy (S31).

[0127] In the case of feature sets, as with color sets / speech sets, if the user does not make a voice utterance that corresponds exactly to the name, the accuracy is calculated to be below the standard.

[0128] Here, the second accuracy is an example of the accuracy information produced by LLM.

[0129] The language model used in the present invention includes a language model such as ChatGPT, an example of LLM. Furthermore, the language model used in the present invention may be a language model specialized for generating feature sets. The language model may be embedded and executed within the server device (500) or home appliance (100). Alternatively, the language model may be deployed to be executed externally to the server device (500) or home appliance (100) and produce results through prompt input.

[0130] When a command is simply applied to a generative AI such as LLM without the above prompt, the desired output value may not be produced depending on the number of home appliance panels, type of home appliance, etc. Therefore, an embodiment of the present invention inputs prompting to a generative AI such as LLM, and also allows the prompting to include various information.

[0131]

[0132] If the second accuracy is below the standard in step S31, the server (500) or the home appliance (100) uses personalized information and feature commands corresponding to the device information of the home appliance to generate a third feature set (S41). The device information may include at least one of identification information of the home appliance for which a feature is to be changed and the type of the appliance (refrigerator, air conditioner, etc.). Furthermore, the personalized information may, in one embodiment, be information related to a feature set set for the home appliance. Alternatively, information generated while the user is using other home appliances may also be included in the personalized information.

[0133] Next, the server (500) or the home appliance (100) changes one of the feature sets, either the first feature set, the second feature set, or the third feature set, into a feature of the home appliance (S51). As a result, for example, the exterior color of the home appliance can be changed according to the user's intention.

[0134] In one embodiment, the server (500) or the home appliance (100) can determine whether to use the first feature set or the second feature set using the first accuracy and the second accuracy. If both the first and second accuracies are low, the third feature set can be used.

[0135] In another embodiment, the server (500) or the home appliance (100) may select a feature set similar to a feature set used by the user in the past from among the three feature sets generated after performing S21, S31, and S41.

[0136] When applying an embodiment related to the color set of the present invention, in a home appliance that can change its appearance with various colors, the server (500) or the home appliance (100) first searches for a color of a basic theme in response to a voice or text command input by a user (S21), and if there is no color that exactly matches here, a color set (color information) can be secured through a language model, for example, a generative AI (Artificial Intelligence) (S31).

[0137] However, since the language model and generative AI do not have the user's past color results, if the language model (generative AI) cannot provide a color value in response to the user's voice / text command, the server (500) or the home appliance (100) can determine the AI ​​color through a recommended AI server that reflects the user's past color usage pattern data (S41). The recommended AI server may be embedded in the home appliance to perform data processing, or data may be calculated or performed in various environments such as a cloud server-based system, an Ondevice system, or a distributed server system (multiple servers).

[0138] When applying the embodiment of Fig. 3, when a voice / text command to change the color theme is recognized in a home appliance that can change the color of the exterior, such as an LED panel (e.g., a mood-up refrigerator, a mood-up air conditioner, etc.), even if the color theme included in the input command is not predefined, a generative AI including a large language model such as ChatGPT can be used to generate a color theme that matches the user's intention and change the color of the refrigerator.

[0139] In addition, when utilizing generative AI, data (e.g., prompts) input to the generative AI can be generated or input to the generative AI to perform a feature set that matches the user's intent, thereby accurately outputting a feature set suitable for each situation in a short time or with a small number of processes.

[0140] In one embodiment, a home appliance or server device can input information related to the home appliance as additional input data to a generative AI in addition to a user-entered command, thereby quickly and with minimal computational effort, producing results appropriate to the user's intent. To this end, information related to the home appliance that can be included in the additional input data includes information related to the feature command. Additional input data may include the layout of the display panel related to the home appliance's appearance, the range of colors that the panel can produce, or the type of home appliance. The information that can be added may vary depending on the type of feature indicated in the feature command. The home appliance or server device can store additional input data or categories of additional input data corresponding to each feature type and update them to reflect the results of the generative AI.

[0141] In addition to the existing natural language processing (NLP) server for voice recognition, a generative AI server or a recommendation AI server is combined, so it can handle areas that were impossible to handle with the existing natural language processing (NLP) server alone, such as understanding the user's intent and creating color themes.

[0142]

[0143]

[0144] In other words, since it is possible to respond to even non-predefined color themes or user utterances, it is possible to satisfy various user utterances and requirements related to changing the color of home appliances such as refrigerators and air conditioners. For example, when a user inputs a command such as "I'm feeling depressed right now, change the color" or "Recommend a color that suits me," the server (500) or home appliance (100) can generate an optimal color for the user's command and apply the color to the home appliance such as the refrigerator or air conditioner.

[0145] The process of Figure 3 can also be applied to speech sets or feature sets, as with color sets.

[0146] When applying an embodiment related to a speech set of the present invention, in a home appliance capable of changing a voice guidance message using various voice utterance characters, the server (500) or the home appliance (100) first searches for a speech of a basic theme for a voice or text command input by a user (S21), and if there is no speech that exactly matches here, a speech set (speech information) can be secured through a language model, for example, a generative AI (Artificial Intelligence) (S31).

[0147] However, since the language model and generative AI do not have the user's past preferred speech results, if the language model (generative AI) cannot provide specific speech information in response to the user's voice / text command, the server (500) or home appliance (100) can determine AI speech information through a recommendation AI that reflects the user's past speech selection pattern (S41).

[0148] When applying the embodiment of FIG. 3, when a voice / text command to change a speech theme is recognized in a home appliance that can change the speech characteristics of a voice message of the home appliance, such as when an LED panel is installed, even if the speech theme included in the input command is not predefined, a speech theme that matches the user's intention can be generated using generative AI and the tone or intonation of the voice guidance message of the home appliance can be changed.

[0149] In addition to the existing natural language processing (NLP) server for voice recognition, we have combined a generative AI server and a recommendation AI server, so we can handle areas that were impossible to handle with the existing natural language processing (NLP) server alone, such as understanding the user's intent and generating speech themes.

[0150] That is, since it is possible to respond even to speech themes or user utterances that are not predefined, it is possible to satisfy various user utterances and requirements related to changing the guidance messages of home appliances such as refrigerators and air conditioners. For example, when a user inputs a command such as "I'm feeling depressed right now, change the voice message to a cheerful one" or "Recommend a voice message that matches the current music," the server (500) or home appliance (100) can generate optimal speech information for the user's command and apply it to the guidance messages of home appliances such as refrigerators and air conditioners.

[0151] In the case of a refrigerator as an example, when a function command such as “There are a lot of new foods in the refrigerator, so refrigerate them well” is input, the server (500) or the home appliance (100) can create a function set containing optimal function information for the user’s command and apply it to the function settings of the home appliance such as the refrigerator or air conditioner.

[0152]

[0153] Figure 4 is a diagram illustrating a process by which a server processes a feature command according to one embodiment of the present invention. A single server can perform the functions described below. Alternatively, multiple server groups can perform the functions described below. The embodiment of Figure 4 can be applied to all color commands, speech commands, and function commands included in feature commands.

[0154] Accordingly, according to one embodiment of the present invention, a single server may include each of the modules. According to another embodiment of the present invention, each of the modules described below may be a server, and these servers may be included in a single server group.

[0155] According to another embodiment of the present invention, two or more modules can constitute one server.

[0156] The server's preprocessing module (310) receives a voice / text command (S21a). Then, it preprocesses the input command, converts it into a feature command, and calculates a first feature set and a first accuracy corresponding to the command (S21b).

[0157] The preprocessing module (310) is an example of a legacy NLP (Natural Language Processing) module, and performs a first intent analysis on a voice or text command input by a user. If successful, feature control of the home appliance can be performed in the conventional manner.

[0158] For example, if the input color command is "Change the color to a spring theme," the preprocessing module (310) preprocesses the input command to extract the color command "spring theme." Then, if a color set corresponding to the "spring theme" is pre-stored in the preprocessing module (310), the preprocessing module (310) calculates the corresponding color set and its accuracy.

[0159] If the input command is "Change the color to a spring breeze theme," the preprocessing module (310) preprocesses the input command to extract the color command "spring breeze theme." However, unlike the previous embodiment, there is no color set corresponding to the "spring breeze theme," so the preprocessing module (310) can calculate the color set corresponding to the most similar "spring theme" and an accuracy (e.g., 60).

[0160] For example, if the input speech command is "Change the voice message to a refreshing voice," the preprocessing module (310) preprocesses the input command to extract the speech command "refreshing theme." Then, if a speech set corresponding to the "refreshing theme" is stored in advance in the preprocessing module (310), the preprocessing module (310) calculates the speech set and its accuracy.

[0161] If the input command is "Change the voice message to a refreshing and bright theme," the preprocessing module (310) preprocesses the input command to extract the speech command "refreshing and bright theme." However, unlike the previous embodiment, there is no speech set corresponding to the "refreshing and bright theme," so the preprocessing module (310) can calculate the speech set corresponding to the most similar "refreshing theme" and an accuracy (e.g., 60).

[0162]

[0163] If the accuracy of the feature set produced by the preprocessing module (310) exceeds the standard, it means that the accuracy is successful, and therefore the feature setting module (340) can apply the feature set produced by S21b to the home appliances (100a, 100b, 100c) (S51a, S51b, S51c).

[0164] On the other hand, if the accuracy of the feature set produced by the preprocessing module (310) is below the standard, this means that the accuracy is a failure, and therefore the theme module (320) can produce a feature set and accuracy corresponding to the feature command (S31b).

[0165] That is, if the analysis of the user's feature change intention through the NLP module (or NLP server), which is an embodiment of the preprocessing module (310), fails, the theme module (320), which is an embodiment of the LLM (Large Language Model) server, processes the user's feature command (e.g., color command) to perform secondary intent analysis and extract intent analysis and color theme color hex values.

[0166] At this time, if the theme module (320) is implemented in a device different from the preprocessing module (310) (e.g., a device provided by an external third party), the server (500) can input a prompt to the theme module (320) to obtain information in a manner agreed upon in advance with the theme module (320).

[0167] Additionally, even if the theme module (320) is an external server or an internal server, information necessary for producing various feature sets (e.g., format of a color set, examples of color sets corresponding to color commands, etc.) can be input into the theme module (320).

[0168] For example, in response to the command "The weather is too hot today, change the color to cool", the preprocessing module (310) generates a color command as "The weather is hot, change the color to cool", but if there is no predefined color set corresponding to the cool color, the color command can be input into LLM, which is an embodiment of the theme module (320), to produce a color set (S31b).

[0169] And if the second user's intention to change color is successfully identified based on the accuracy result produced by LLM, the theme module (320), for example, extracts the color theme hex value for applying the color theme produced by the generative AI, and the feature setting module (e.g., color setting module) (340) can change the panel color of a home appliance (100a, 100b, 100c) such as a refrigerator (S51a, S51b, S51c). In one embodiment, the intention identification is the calculation of a color set corresponding to the user's color command. In the present specification, the intention identification for the feature command input by the user includes a process of calculating a feature set corresponding to the feature command.

[0170] In this process, if the theme module (320) is an external server, the LG ThinQ server may include a feature setting module (340) that can set a feature set (e.g., a color set) produced by the theme module (320) to a home appliance.

[0171] Meanwhile, if the accuracy of the feature set (e.g., color set) produced by the theme module (320) is below the standard (S41a), this means that the accuracy is a failure, and therefore the personalization module (330) can produce a feature set corresponding to the feature command (S41b).

[0172] If the theme module (320) fails to analyze the user's feature change intent through, for example, generative AI or LLM (i.e., fails to identify the secondary feature intent), the personalization module (330), for example, a recommendation AI server, can recommend features. In this process, the theme module (320) can determine whether the user intends to recommend a feature, and the theme module (320) can also output an accuracy result regarding whether the user desires a feature recommendation from the recommendation AI server.

[0173] For example, if the input color command is "Recommend a color theme that suits me today," the accuracy of the color set generated by S21b / S31b may be below the standard and thus fail. Alternatively, the LLM may respond that it is unable to generate a color set. In this case, the personalization module (330) may utilize history information regarding the user's previous color settings for the home appliance.

[0174] The personalization module (330) extracts a color theme calculated to be liked by the user based on the user's color usage pattern in the home appliance and transmits the extracted color theme to the color setting module (340) (e.g., LG ThinQ server) to change the color theme of the product.

[0175] The above can also be applied to various feature sets, such as speech sets or feature sets.

[0176] FIG. 5 is a diagram showing a process for processing a color command according to one embodiment of the present invention.

[0177] A user inputs a color command by voice or text (S22). A preprocessing module (310) verifies a color set based on logic (S23). That is, the preprocessing module (310) extracts keywords from the color command (speech command or text command) input by the user. Then, the preprocessing module (310) calculates a color set corresponding to the intent of the color command input by the user based on a logic that compares the extracted keywords with names or keywords of pre-stored color sets. This includes a process in which the preprocessing module (310) determines the intent of the color command and calculates a color set suitable for it.

[0178] If the color set is confirmed in the S23 process (if the user's color intention for color change is identified) (S24-Yes), the feature setting module (340) applies the confirmed color set to the home appliance (S52).

[0179] If the color set is not confirmed in the S23 process (if the user's color intention for color change is not identified) (S24 - No), the color set is generated by the theme module (320) (S32). For example, the server (500) or the home appliance (100) identifies the color intention from the color command input by the user using LLM (GPT), etc. (S32). The server (500) or the home appliance (100) checks whether the accuracy of the generated color set is above a standard (S33). For example, the server (500) or the home appliance (100) determines whether the color set generated in S32 is suitable for the color intention of the color command input by the user. If the determination result shows that the accuracy is above the standard, step S52 is performed.

[0180] Meanwhile, if the accuracy is low in S33, the server (500) or home appliance (100) verifies whether the input color command is a recommendation target based on personalized information (S34). For example, if the input color command is "Make it my favorite color," the color command can be confirmed as requesting a color based on personalized information.

[0181] On the other hand, if the input color command is "Oh, the refrigerator color is strange?", it is difficult to confirm that the color command requested a color change based on personalized information.

[0182] This judgment is made in one embodiment when the theme module (320) determines that the color command is difficult to determine as a color change during the process of calculating a color set for the color command.

[0183] If a recommendation target based on personalized information is identified at S34, the personalization module (330) uses the personalized information to generate a color set (S42). The server (500) or the home appliance (100) then verifies whether the accuracy of the generated color set is above a standard (S43). For example, the server (500) or the home appliance (100) determines whether the color set generated at S42 aligns with the color intent of the color command entered by the user. If the accuracy is above the standard, step S52 is performed.

[0184] If the accuracy does not meet the standard even at S43 (S43-No), the home appliance (100) requests re-input (S45). For example, the home appliance (100) may request re-input by re-voicing a command, such as "Please say again to change the color."

[0185] Figure 6 is a drawing showing the configuration of a personalization module according to one embodiment of the present invention.

[0186] The personalization module (330) may include a user database (DB) (350) that stores information set by the user in relation to colors, and a recommendation AI module (335). The personalization module (330) may extract a specific color set from the user database based on the user's past usage patterns for color commands. If the personalization module (330) is arranged in a server (500), the recommendation AI module (335) may be implemented as a recommendation AI server. Meanwhile, if the personalization module (330) is arranged in a home appliance (100), the recommendation AI module (335) may be configured as a software component or hardware component within the home appliance (100).

[0187] Figure 7 is a diagram illustrating a process in which a personalized module, according to one embodiment of the present invention, makes recommendations using personalized information. Step S42 will be examined in more detail.

[0188] The personalization module (330) checks the home appliance and time information, and the color set currently applied to the home appliance (S61). Furthermore, the personalization module (330) requests n color sets (most frequently applied color sets) from the user database (350) for the home appliance in question or other home appliances used by the user (S62). "n" may be 2 or a greater number.

[0189] If the number of most frequent color sets extracted from the requested result is not greater than m (S63-No), the number of most frequent color sets is insufficient, so the personalization module (330) calculates a color set reflecting the season information of the current date or the current weather information and applies it to the home appliance (S67). For example, m may be 2 in one embodiment.

[0190] If the number of most frequent color sets is m or more (S63 - Yes), the number of most frequent color sets secured by the personalization module (330) is sufficient, so each most frequent color set is compared with the color set currently set in the home appliance. For example, the personalization module (330) checks whether most frequent color set 1 is the same as the color set currently set in the home appliance. If they are the same (S64 - Yes), the personalization module (330) sets one of the m most frequent color sets except most frequent color set 1 in the home appliance (S65). If they are not the same (S64 - No), the personalization module (330) sets most frequent color set 1 in the home appliance (S66).

[0191] In the above-described embodiments, n or m can be set in various ways.

[0192] The embodiment of Fig. 7 can be applied to a process for recommending a feature set based on a user's usage pattern. Fig. 7 illustrates an embodiment in which a personalization module (330) extracts the top two most frequent values ​​from a list of color sets (color theme hex values) that have been applied so far among color sets and then applies them as a theme different from the currently applied color theme.

[0193] If the user database is insufficient to extract the two most frequent values, color themes can be recommended based on the current date, time, weather, etc. and applied to home appliances.

[0194] Next, we will look at the process of generating a feature set using the theme module (320).

[0195]

[0196] When a user uses a predefined name in the product as a feature command to use a specific feature of the device, the preprocessing module (310) included in the server (500) or home appliance (100) can provide a feature set corresponding to the feature.

[0197] Meanwhile, if a user utters a feature command that is commonly used in the society to which the user belongs while uttering the feature command, the theme module (320) can produce a feature set using a language model.

[0198]

[0199] FIG. 8 is a diagram showing a process of producing a feature set based on a theme module (320) according to one embodiment of the present invention.

[0200] The server (500) or the home appliance (100) extracts feature commands and feature sets that can be input into the theme module (320) from its internal storage. These are called sample feature commands and sample feature sets. Then, the server (500) or the home appliance (100) inputs sample feature commands, sample feature sets, and feature commands into the theme module (320) (S71).

[0201] As a result, the theme module (320) calculates a second feature set and a second accuracy (S72). If the second accuracy is higher than the standard (S73), the server (500) or the home appliance (100) can apply the second feature set to the home appliance (100) (S74). On the other hand, if the second accuracy does not satisfy the standard, the server (500) or the home appliance (100) calculates a feature set using the personalization module (330).

[0202]

[0203] Sample feature commands are examples of commands a user might utter. A sample feature set is a feature set that corresponds to these sample feature commands.

[0204] For example, the sample color command and its corresponding sample feature command are as follows.

[0205] Sample Feature Commands Sample Feature Sets Make it Iron Man colored {"#FF0000", "#FF0700" , "#FF8C00", "#C0C0C0"} Make it Autumn colored {"#FF7F50", "#FFA500" , "#FFB700", "#800000"}......Make it Giraffe colored {"FFD700", "#8B4513" , "#060400", "#FFA500"}

[0206] When a sample color command and a sample feature set are input into the theme module (320), and a color command is input, the theme module (320) can apply the relationship between the sample feature command and the sample feature set to produce a color set (second color set) corresponding to the color command.

[0207] In one embodiment, if the theme module (320) is configured based on a language model such as chatGPT, the server (500) or the appliance (100) may input a prompt to the theme module (320). In one embodiment, the server (500) or the appliance (100) may include a sample color command and a sample feature set in a few shots.

[0208]

[0209] The prompt input to the theme module may include instructions and sample feature commands. In one embodiment, the prompt may include instructions to be input to the theme module (320) and messages provided by the server (500) or home appliance (100) to the theme module (340).

[0210] Additionally, the message may include a sample feature command (sample color command) and a corresponding sample feature set (sample color set) as shown in Table 4. Through this, the theme module (320) can produce a color set corresponding to the color command (user_request) uttered by the user.

[0211] In order for the theme module (320) to more accurately produce results, the server (500) or the home appliance (100) may additionally input information about the region or country to which the user who uttered the feature command belongs into the theme module (320). For example, the color of an apple that a Korean person thinks of may be different from the color of an apple that an American person thinks of. Accordingly, the server (500) or the home appliance (100) inputs information about the region or country where the feature command was uttered into the theme module (320), so that a feature set, such as colors, sounds, or functions commonly used by people belonging to a specific region or country, can be accurately produced.

[0212] In one embodiment, when the theme module (320) is GPT, the home appliance (100) or server (50) can instruct the GPT prompt to extract four theme colors as hexadecimal values.

[0213] In addition, if the color command uttered by the user is determined to be a recommendation, the theme module (320) is instructed to return a "True" value (area instructed to return whether or not a recommendation is made). The home appliance (100) or server (50) can also add color therapy content as prompt instructions to create a color theme appropriate for the situation. The home appliance (100) or server (50) can include in the prompt a few examples (sample color commands and sample color sets) in few shots so that a recommendation flag or RGB color hex values ​​that the home appliance (100) can set are output as a result in the form of a list.

[0214] If applied to a 3-door kimchi refrigerator, the home appliance (100) or server (50) can be modified to extract the number of color hex values ​​from 4 to 3.

[0215] Additionally, when applied to other types of home appliances such as air conditioners and ovens, the color hex values ​​output can be modified and set according to the number of panels on the door or side of the appliance.

[0216] Meanwhile, the personalization module can use personalization information to produce a feature set corresponding to a feature command.

[0217] The personalization module (330) included in the server (500) or the home appliance (100) acquires device information of the home appliance into which the feature command has been input. The personalization module (330) then extracts personalization information corresponding to the device information. In one embodiment, the personalization information may be used to derive a third color set by using information on at least one of a color set previously set for the device corresponding to the device information and the setting frequency of these color sets or the maintenance time of the color set.

[0218] To achieve this, the database can store color set identification information, time information, and device-specific identification information. The database can also store information about the most recently applied color set.

[0219] The database stores color sets configured for each device. Therefore, if the theme module (320) determines that a feature command is a pattern-based recommendation for the user, the personalization module (330) can perform calculations to recommend a feature set for each device. As a result, different feature sets can be generated for each home appliance.

[0220] For example, if device_id is 1, you can sort the most frequent values ​​for the color sets applied to device_id and then set the color of the home appliance to the next color that is different from the current setting color.

[0221] [Color 1, Color 2, Color3, Color 4]

[0222] If device_id is 2, you can sort the most frequent values ​​for the color sets applied to device_id and then set the color of the home appliance to the next color that is different from the currently set color.

[0223] [Color 13, Color 14. Color 15, Color 16]

[0224]

[0225] For example, if the device_id is 1 in the information stored in the database, Iron Man has been applied twice and the color set "Republic of Korea" is currently applied. Accordingly, if the user's spoken command requests "recommend," the personalization module (330) provides the color corresponding to Iron Man as the recommended color set.

[0226] Similarly, if device_id is 2, "autumn color" is applied twice, so "autumn color" is also applied in the recommendation.

[0227]

[0228] Meanwhile, the server (500) or home appliance (100) can store the feature set produced by the theme module (320) as personalized information.

[0229] For example, if a device with device_id of 1 repeatedly sets a feature set (e.g., Iron Man color) generated by the theme module (320) to the device or maintains the feature set for a long time after setting, the server (500) or home appliance (100) stores the feature command (Iron Man) and color information ([Color 1, Color 2, Color3, Color 4]) in the database.

[0230] Afterwards, when the user inputs a new command, the server (500) or home appliance (100) loads and applies the information stored in the database.

[0231] For example, when the preprocessing module (310) processes the color command “Make it Iron Man color”, the “Iron Man” color and color information ([Color 1, Color 2, Color3, Color 4]) stored in the database after keyword extraction can be produced as the first color set.

[0232] Alternatively, when the personalization module (330) processes the color command “make it Iron Man color”, the “Iron Man” color and color information ([Color 1, Color 2, Color3, Color 4]) stored in the database after keyword extraction can be produced as a third color set.

[0233] In this process, the server (500) or the home appliance (100) may not input a separate feature command to the theme module (320). That is, it is assumed that the second feature set produced in S31 is applied to the home appliance (100) and maintained for a long time during the process of performing the steps S21-S51 of FIG. 3 once.

[0234] If the user utters the same feature command, the preprocessing module (310) of the home appliance (100) or server (500) can process it, or step S31 can be skipped and the personalization module (330) can load the stored feature set from the database in step S41.

[0235] That is, if the user utters the Iron Man color once and applies it to the home appliance (100) and the time it is maintained or the number of times it is set repeatedly is greater than a standard, the server (500) or the home appliance (100) can increase the processing speed of the user's utterance command by storing the feature command and feature set in the database.

[0236] To summarize, the server (500) or home appliance (100) stores the feature command and the second feature set in the database according to the retention time or application number of the second feature set produced by the theme module (320).

[0237] After the server (500) or the home appliance (100) performs steps S21 to S51 of FIG. 3, the preprocessing module (310) can use the information stored in the database in the process of producing the first feature set or the personalization module (330) can produce the third feature set for the input feature command.

[0238] In more detail, the preprocessing module (310) can acquire information stored in the database to create a feature set. Alternatively, the personalization module (330) can acquire information stored in the database to create a feature set.

[0239]

[0240] Below, a device for implementing embodiments of the present invention will be described.

[0241] Embodiments of the present invention can be implemented in various devices. Devices include servers, home appliances, electronic devices, computing devices, and the like. Furthermore, in addition to physical devices, the devices of the present invention may include hardware or software components that perform embodiments of the present invention. Furthermore, embodiments of the present invention include programs, hardware, chips, and the like, implemented in a form capable of storing or executing certain tasks.

[0242] In the case of programs, software, etc., they may be stored permanently within the device, or they may be temporarily transmitted from an external source, stored in the device, and then executed. In the case of a fixed storage method, the device may include a non-transitory computer-readable medium.

[0243] That is, embodiments of the present invention may be implemented as computer-readable storage media as one or more computer programs, or a combination of one or more of the above.

[0244] The functions of the elements disclosed herein may be implemented using circuits or processing circuits, including general-purpose processors, special-purpose processors, integrated circuits, ASICs ("application-specific integrated circuits"), conventional circuits, and / or combinations thereof. The circuits may be processors configured or programmed to perform the disclosed functions. A processor may be considered a processing circuit or circuits, as it includes transistors and other circuits.

[0245] In this specification, a circuit, unit, or means may be hardware that performs or is programmed to perform the functions mentioned in the detailed description. The hardware may be hardware disclosed herein or other known hardware, and may be hardware programmed or configured to perform the functions mentioned in the detailed description of the specification. If the hardware is a processor that can be considered a type of circuit, the circuit, means, or unit may be a combination of hardware and software used to configure the hardware and / or the processor. In addition, the computer storage medium may be a non-transitory computer readable medium. For example, it may be executable by a cloud server-based system. The computer storage medium may be located within the same device or may be distributed across two or more different devices. Therefore, a logical computer storage medium may physically include two or more computer storage media, and the locations where they are located may also be one or more locations. The computer storage medium includes various storage media such as hard disks, CD / DVD disks, memory cards, and memory chips.

[0246] Furthermore, the data described in this specification can be computed or performed in various environments, including cloud server-based systems, on-device systems, and distributed server systems (multiple servers). Processing can be distributed on cloud servers or executed locally on on-device processors, and the results of processing in each environment can be stored in non-volatile memory.

[0247]

[0248] Electronic devices, such as home appliances and server computing devices, may be connected to one or more storage devices via a network. The storage devices may be a combination of volatile and non-volatile memory, and may or may not be located in the same physical location as the computing device.

[0249] A server computing device may include one or more processors and memory. The memory stores information that can be accessed by the processor and may include data that can be processed, stored, or modified by instructions that can be executed by the processor. The memory may also be comprised of volatile and non-volatile memory. The processor may include a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or a tensor processing unit (TPU).

[0250]

[0251] Instructions can be configured to cause a processor to perform specific actions when performing a directed task, and can be stored in object code or interpretable script format. These instructions can be used to implement a system and can be executed on a local or remote processor. Data can be retrieved, stored, or modified according to the instructions, and can be organized in database, JSON, YAML, or XML formats.

[0252] These commands may contain executable files, source code files, or metadata.

[0253]

[0254] An electronic device, including a home appliance or hub, may be configured similarly to a server computing device. The electronic device, including a home appliance or hub, may include a processor, memory, instructions, data, and user input and output devices. The server computing device may transmit data to the electronic device, and the electronic device may display a portion of the received data through a display. In addition, data transmission and communication between the server computing device and the electronic device is possible through a network such as Bluetooth, Wi-Fi, a wired network, or a wireless network, and various protocols and connection methods are supported. Direct and indirect communication between computing devices is possible, and various protocols and connection methods can be supported.

[0255] Additionally, the functions of the server computing device of the present invention can be performed by a smartphone, tablet, etc.

[0256] The methods or processes in the embodiments of this specification sequentially perform one or more tasks, and each task may be performed through the collaboration of either hardware or software, or both. For example, hardware may perform the first task, and software may perform the second task. Of course, hardware may perform the entire task, or software may perform the entire task.

[0257]

[0258] FIG. 9 is a diagram showing a processing process when fine-tuning occurs for a feature set according to one embodiment of the present invention.

[0259] The server (500) or the home appliance (100) receives a fine-tuning command for one of the first feature set produced by the preprocessing module (310), the second feature set produced by the theme module (320), or the third feature set produced by the personalization module (330) and produces a fourth feature set (S81).

[0260] In this case, the server (500) or the home appliance (100) stores the feature command and the fourth feature set in the database (S82). Then, the server (500) or the home appliance (100) processes the feature command using the fourth feature set stored in the database for the feature command input thereafter (S83).

[0261] For example, after the server (500) or the home appliance (100) performs the processes of S21 to S41 of FIG. 3, the preprocessing module (310) calculates a feature set for the input feature command, or the personalization module (330) loads the fourth feature set stored in the database during the process of calculating a feature set, and sets it as the feature set of the home appliance.

[0262] When applying the above-described embodiments, when a user wants to change the features (e.g., color, voice message, function) of a home appliance such as a refrigerator or air conditioner, one of the feature set (e.g., basic theme) provided by the home appliance by default, the feature set provided by a theme module such as a generative AI, and the feature set provided by a personalized module equipped with a recommendation AI can be applied in response to the user's text or voice command.

[0263] In addition, when the same voice / text commands for features (e.g., color values) produced by a theme module (320) such as a generative AI are accumulated, they can be stored in a database as a personalized feature set to increase efficiency in the process of changing features.

[0264] The personalization module (330) may be implemented within the home appliance or within a server (500), such as a cloud server. The theme module (320), which uses generative AI as an example, may utilize an external generative AI server or may be implemented within the home appliance (100) or its own server (500).

[0265] Each module illustrated in FIG. 4 may be implemented in either the home appliance (100) or the server (500). Additionally, the theme module (320) may be placed in a separate, generative AI external server distinct from the server (500).

[0266] FIG. 10 is a drawing showing a configuration including all components in a home appliance according to one embodiment of the present invention.

[0267] An example of a device, a home appliance (100), includes a preprocessing module (310), a theme module (320), a personalization module (330), and a feature setting module (340). The command input module (110) is a module that receives feature commands such as voice or text. The preprocessing module (310), theme module (320), personalization module (330), feature setting module (340), and database (350) refer to the descriptions given above. The database (350) can store personalization information of the device.

[0268] The feature setting module (340) sets one feature set among the first feature set, the second feature set, or the third feature set produced by each of the preprocessing module (310), the theme module (320), and the personalization module (330) as a feature.

[0269] Figure 11 is a diagram illustrating a server including a preprocessing module, a theme module, a personalization module, and a database according to another embodiment of the present invention. The server (500) and the home appliance (100) may include a communication module (not shown in the drawing) to transmit and receive certain information.

[0270] The server of Fig. 11 provides personalized services using generative AI. Looking at the detailed components of the server (500), the preprocessing module (310) receives feature commands input by a home appliance and calculates a first feature set and a first accuracy corresponding to the feature commands.

[0271] The theme module (320) calculates a second feature set and a second accuracy corresponding to the feature command if the first accuracy is below the standard. The personalization module (330) calculates a third feature set using personalized information corresponding to the device information of the home appliance and the feature command if the second accuracy is below the standard.

[0272] When the server (500) transmits one of the first to third feature sets thus produced to the home appliance (100), the home appliance (100) sets one of these feature sets as a feature of the home appliance. To this end, the feature setting module (340) can set the received feature set to a specific area or function of the home appliance (100).

[0273] If the feature set is a color set, the feature command corresponds to a color command. If the server (500), for example, the preprocessing color command, includes the color names of the colors constituting the first color set, the server (500), for example, the module (310), can determine that the first color set satisfies the first accuracy standard. This is the case when a specific color name, such as orange or blue, is included in the color command.

[0274] In addition, the server (500) inputs a sample feature command and a sample feature set corresponding to the sample feature command into the theme module (320) to obtain a feature set using the theme module (320). Then, the server (500) checks the second feature set and second accuracy produced by the theme module (320) and determines whether to input a feature command into the personalization module (330) accordingly.

[0275] If the user enters a command such as “recommend”, the theme module (320) may set the second accuracy very low.

[0276] As previously discussed, the personalization module (330) of the server (500) can calculate a color set using information on at least one of a color set previously set for a home appliance corresponding to device information and the frequency of the set color set or the maintenance time of the color set.

[0277] Additionally, to increase the accuracy of the results produced by the theme module (320), the server (500) may additionally input information about the region or country to which the user who uttered the feature command belongs into the theme module (320). In addition, the user's age information, gender information, and occupation information may also be additionally input into the theme module (320) to increase the accuracy of the feature set produced in response to the user's feature command.

[0278] The server (500) transmits one of the generated feature sets to the home appliance (100), and the home appliance (100) can apply the transmitted feature set to the home appliance (100).

[0279]

[0280] Figure 12 is a diagram illustrating a server including a preprocessing module, a personalization module, and a database according to another embodiment of the present invention. The server (500) and the home appliance (100) may include a communication module (not shown in the drawing) to transmit and receive certain information.

[0281] Additionally, the theme module (320) is placed in a separate generative AI external server (700) distinct from the server (500). In this case, unlike FIG. 11, the server (500) includes a counter theme module (325). For a description of other components, refer to FIG. 11.

[0282] If the first accuracy calculated by the preprocessing module (310) is below the standard, the counter theme module (325) transmits a feature command to the theme module (320) of the generative AI external server (700) and receives a second feature set and a second accuracy from the theme module (320).

[0283] The counter theme module (325) transmits a sample feature command and a sample feature set corresponding to the sample feature command to the theme module (320) to increase the accuracy of the result of the theme module (320). In addition, the counter theme module (325) receives a second feature set and a second accuracy corresponding to the feature command from the theme module (320).

[0284] The above-described embodiment can be implemented in a remote control for controlling a home appliance (100) for voice recognition and intent identification, or in a device capable of voice recognition (e.g., an AI speaker or hub) in addition to the home appliance (100) itself. For example, a home appliance such as a refrigerator or air conditioner may include only a feature setting module (340), while a home appliance such as an AI speaker or hub may include a command input module (110).

[0285] Additionally, home appliances such as AI speakers or hubs may include a preprocessing module (310), a theme module (320), and a personalization module (330). In this case, home appliances such as AI speakers or hubs may transmit device control signals to related home appliances (or devices to be controlled).

[0286] As in the embodiment of Fig. 12, when a theme module (320), such as LLM (GPT), is deployed on an external AI server (700), the theme module (320) cannot access the customer's user database due to privacy or security issues. Therefore, the embodiment of Fig. 12 can be implemented by separating the generative AI and server (theme module) and the recommendation AI server (personalization module).

[0287] A feature set for feature commands can be generated by a generative AI function (theme module) that reflects the linguistic characteristics of the society to which the user belongs and a recommendation AI function (personalization module) based on personalized information through the theme module (320) and the personalization module (330). In addition, by applying the preprocessing module (310) and the personalization module (330), problems such as increased costs or network delays that occur during the use of the theme module (320) deployed on an external AI server (700) can be resolved.

[0288] FIG. 13 is a drawing showing the configuration of a home appliance, a home appliance for voice processing, and a server according to one embodiment of the present invention.

[0289] An AI speaker or hub, etc., is a home appliance (100b) for voice processing and includes a command input module (110). In this case, the home appliance (100b) for voice processing communicates with a server (500), receives a feature set, and provides it to a home appliance (100a) such as a refrigerator, air conditioner, or oven, thereby controlling the feature settings of the home appliance (100a).

[0290] Alternatively, when combining the embodiments of FIGS. 10 and 13, an AI speaker or hub, etc., may include a home appliance (100b) for voice processing, a preprocessing module (310), a theme module (320), a personalization module (330), and a command input module (110). In addition, home appliances (100a), such as a refrigerator, air conditioner, or oven, may be configured to include a feature setting module (340).

[0291] The present invention is not limited to a specific home appliance and can be applied to all home appliances that include a feature setting module (340) that sets the type and function of color or voice comment as described above.

[0292] In the embodiments of FIGS. 11 and 13, the preprocessing module (310), the theme module (320), and the personalization module (330) can constitute one processor.

[0293] In the embodiment of FIG. 12, the preprocessing module (310), the counter theme module (325), and the personalization module (330) can constitute one processor.

[0294] Based on the embodiments of FIGS. 11 to 13, the server's processor can process information received from a home appliance and input it into a generative AI model, a theme module (320), to obtain a result. The processor can receive a feature command instructing a feature change of the first home appliance from the first home appliance or the second home appliance.

[0295] Additionally, the processor can generate a prompt including at least one of configuration information of the first home appliance, status information of the first home appliance, and the feature command in response to the feature command.

[0296] The processor can input the generated prompt into the theme module (320) to obtain a result and convert the obtained result into a first feature set to be set in the first home appliance.

[0297] Here, the second home appliance may be a user terminal or a home appliance other than the first home appliance. For example, a smart hub or a smart AI speaker may be the second home appliance. In this case, the user's voice / text command for converting the feature set of the first home appliance (e.g., a refrigerator or air conditioner) may be transmitted to the server (500) via the second home appliance.

[0298] The user's command can be entered as voice or text, and the device that receives the command and transmits it to the server can be a first home appliance instructed to change the feature set, or a separate second home appliance (e.g., user terminal, AI speaker, etc.).

[0299] As discussed above, the feature command is, in one embodiment, a command that instructs a change in the color of the first home appliance.

[0300] A feature set contains information about one or more colors to be set in a first home appliance.

[0301] Configuration information is information about the areas of a first appliance to which one or more colors are to be set. For example, information about whether a specific color is set for the refrigerator door is configuration information.

[0302] The status information includes information about the second feature set that is currently set or was set in the past for the first appliance.

[0303] The result obtained from the theme module (320) may include two or more candidate feature sets.

[0304] The processor can apply one or more of configuration information, state information, and feature instructions to transform one of the two or more candidate feature sets into a first feature set.

[0305] Additionally, the processor may transmit the first feature set to the first home appliance or transmit a feature control command to the first home appliance to apply the first feature set to the first home appliance. The processor may also transmit the first feature set to the first home appliance via the second home appliance.

[0306] To this end, the processor may store software or program code capable of performing the aforementioned tasks. Such software or program code may be received from another external device and stored on a storage medium used by the processor, after which the processor may execute the software or program code.

[0307] Additionally, the processor may include hardware components such as programmable chips, and the processor may store data or program codes to be input into the hardware components in a predetermined storage medium and then input them into the hardware components.

[0308] The hardware or software may be the processor itself. Alternatively, the hardware or software may work in conjunction with the processor to implement embodiments of the present invention.

[0309] When applying the embodiments of FIGS. 11 to 13, even existing old home appliances (e.g., 100a) without AI functions can be connected to a service (e.g., ThinQ On) that provides a feature set by a server (500) that processes voice and generates a feature set or a home appliance (100b) for voice processing.

[0310] As a result, generative AI provides a feature set that enables it to understand the context of user commands and operate seamlessly, and home appliances (100a) can be upgraded into AI appliances. As a result, users can combine ThinQ On with IoT devices to create a reasonable AI home with existing appliances, eliminating the need to purchase all new AI appliances.

[0311] For example, let's say a customer connects a non-AI air conditioner and an occupancy sensor to the LG ThinQ On, which provides a feature set. By generating a feature set that responds to feature commands, ThinQ On can identify the user's location in real time and adjust the air conditioner's airflow and direction to provide optimal airflow. Without having to purchase a new, expensive, state-of-the-art AI air conditioner, existing air conditioners can be upgraded into powerful AI air conditioners by combining them with LG ThinQ On.

[0312] The server (500) according to an embodiment of the present invention is a server that provides artificial intelligence services and may include a database (350) that stores past personalized information or routine information of a customer.

[0313] By using a large language model such as ChatGPT and a server that contains user experience data such as the user's electronic device usage patterns, it is possible to provide an optimized spatial solution for each individual based on learning about the user's lifestyle. For example, if a user uses a feature command such as "I studied well last week, so please set it up the same way," the settings stored in the database (350) at the time can be loaded to create a personalized environment.

[0314] In one embodiment of the present invention, the server (500) includes an embodiment of a server group that is a collection of various servers. Accordingly, the configuration of the server (500) can be easily modified by those skilled in the art.

[0315] In one embodiment, the server (500) in the embodiments of FIGS. 11 to 13 may provide the functions of an NLP (Natural Language Processing) server. For example, the preprocessing module (310), the counter theme module (325), the theme module (320), etc. may correspond thereto. In addition, the server (500) may perform a task for inputting a predetermined prompt message to the theme module (320). That is, in order to obtain an accurate answer through an LLM model such as chatGPT, the server (500) may structure the prompt content and embed and store the utterance DB.

[0316] If the theme module (320) is implemented in an external AI server (700) as shown in FIG. 12, the server (500) can efficiently generate prompt tokens to secure maximum performance of the theme module (320) using GPT as an example through low cost and low network latency. The NLP server may be implemented within the server (500) or as a separate cloud server (e.g., AWS's cloud server).

[0317] In the embodiment of FIG. 12, the server (500) may incur costs in the process of inputting a predetermined prompt message to an external AI server (700) and obtaining a result accordingly. Therefore, if the server (500) performs maximum fine-tuning on the feature commands by the preprocessing module (310) and the personalization module (330) to train them and store the results in a database, the number of times the external AI server (700) is used can be reduced.

[0318] For example, in the embodiment of FIG. 12, if the server (500) learns by fine-tuning the speech data instead of using the GPT API, which incurs a cost, it can process feature commands using internal modules (310, 330) without using the GPT API.

[0319] Fine tuning according to one embodiment of the present invention includes developing and applying a dedicated model specialized for a home appliance (e.g., a specific home appliance such as a refrigerator or air conditioner) using a small language model (sLM).

[0320] If the performance of the AI ​​chip installed in the home appliance (100) is guaranteed, the service can also be provided in the onDevice form as shown in Fig. 10.

[0321] Additionally, the theme module (320) according to one embodiment of the present invention can apply LLM. For example, the theme module (320) can interpret the meaning of utterances using NLP and output corresponding intents and slots based on input prompts and sample data.

[0322] LLMs like GPT can provide overwhelming performance in terms of processing speed and data volume, thanks to their high-performance data centers. Therefore, the theme module (320) can be deployed within the server (500) or implemented on an external AI server (700), as shown in FIG. 12.

[0323] In one embodiment, the external AI server (700) is a server (700) implementing chatGPT, MS Azure GPT, GPT-4o mini, etc. provided by Open AI. The task of entering a query, for example, a prompt, into these external AI servers (700) and receiving a result can utilize an API (Application Protocol Interface). For example, the counter theme module (325) of FIG. 12 can obtain a feature set corresponding to a feature command using the API provided by the theme module (320).

[0324]

[0325] When applying an embodiment of the present invention, a theme module (320) equipped with artificial intelligence that performs natural language processing such as GPT can identify the intent of a feature command spoken by a user and provide a result (feature set) indicating whether a recommendation is desired or a specific feature combination is desired.

[0326] In addition, when prompt engineering technology is applied to feature commands to be input to the theme module (320), the performance equivalent to fine tuning can be achieved through prompt engineering alone, without the need to fine tune the entire GPT artificial intelligence model.

[0327] Mood-up home appliances, such as refrigerators and air conditioners, can be combined with generative AI (GPT) to accurately identify various user utterance intentions and set desired features (e.g., various color themes, voice tones (speech tones), and a set of functions).

[0328] The preprocessing module (310) has predefined a feature set corresponding to a specific user utterance and has learned to recognize this, so it can process commands for predefined features (e.g., a specific color theme) in a short time.

[0329] Meanwhile, if a user desires a feature set not defined in the preprocessing module (310), a theme module (320), such as LLM (GPT), can be applied. In this case, prompt engineering can be applied to commands (feature commands) that are not predefined, allowing a large number of feature sets to be set. For example, when a color command is entered, the theme module (320) can recognize natural language related to various color theme changes and extract themes related to the color.

[0330] The theme module (320) may include one or more of the following: Microsoft's GPT, a third-party LLM module, or an LLM developed by LG. Furthermore, the server (500) does not necessarily need to include the theme module (320), and the theme module (320) may be included in a separate LLM server provided by an external service provider or LG.

[0331] By applying an embodiment of the present invention, the server (500) can provide an accurate feature set by identifying the intent from a feature command input by a user through a structure that combines an LLM (GPT) server (theme module) and a recommendation AI server (personalization module) in addition to a natural language processing (NLP) server (preprocessing module).

[0332] In one embodiment, if a user says, "Change to a so cool color," the preprocessing module (310) can change the color set defined as a summer theme color to a summer theme color. Furthermore, if a user says, "The weather is really hot, change it to a very cool color," if the corresponding color set is not defined in the preprocessing module (310), the theme module (320) can recognize the user's intent and generate a color theme.

[0333] That is, when applying an embodiment of the present invention, the preprocessing module (310) and the theme module (320) can be combined to identify the user's intent and produce a feature set reflecting the intent. To this end, through prompt engineering, sample feature commands and sample feature sets can be included in the prompt, allowing the theme module (320) to produce feature values ​​(e.g., color values) reflecting the user's intent.

[0334] Additionally, the theme module (320) can acquire information on feature sets commonly accepted by a given society or country. For example, the theme module (320) can provide a color therapy function, generating a color theme that provides appropriate psychological stability when a user utters, "I'm feeling depressed, change the color."

[0335] Meanwhile, if the preprocessing module (310) and theme module (320) fail to produce a feature set that corresponds to the user's intent, the personalization module (330) can provide a feature set customized for the user based on the feature set set for the user's past or current home appliances using the user's information (e.g., information about the user's device usage, etc.). In this case, the appearance of the home appliance can be changed to the user's favorite or preferred color.

[0336] Since the theme module (320) does not store information related to the user, the personalization module (330) can use information related to the user to provide a feature set customized for the user.

[0337] The personalization module (330) can create a color theme suitable for the user when the user inputs a feature command such as “Change it to a color that suits me.”

[0338] The recommendation AI server, which is an embodiment of the personalization module (330), determines whether the user's speech requires an AI recommendation through the theme module (320), for example, LLM (GPT).

[0339] And if it is determined that a recommendation is desired (for example, if the result of the feature set produced by a theme module such as LLM does not meet the criteria), color theme recommendations based on the user's usual usage patterns can be made through the recommendation AI server.

[0340] For example, if a user wants to receive a recommendation for a refrigerator color theme, a personalization module (330), for example, a recommendation AI server, can generate a color theme, thereby increasing the success rate of responding to the user's color theme change-related command (color command) and increasing satisfaction with the generated color theme.

[0341]

[0342] FIG. 14 is a drawing showing an interface for changing colors for a command input by a user according to one embodiment of the present invention.

[0343] A user inputs a feature command via voice or text into a smartphone, tablet, or refrigerator (100a). The entered feature command (Feature_Command) may be displayed in the "User Request" field. For example, commands such as "I'm angry, so change it to a calming color," "Change it to Iron Man color," or "Recommend a color that suits me today" may be input.

[0344] The preprocessing module (310), theme module (320), or personalization module (330) of the server (500) or the home appliance (100a) processes the input command to produce a color result. In Fig. 14, "C_A1, C_A2, C_A3, C_A4" are examples of color sets. Each color set can be applied to the exterior of the refrigerator (100a) to which the colors are to be applied. The order of application can be determined in advance.

[0345] 91 may be a theme of colors previously used by the user, or the names of colors that the preprocessing module (310) can process.

[0346] The user can input information on whether to maintain or change the applied color using the interface of the home appliance (100a) or a smartphone / tablet, etc. The input information (maintain or change) is stored in the personalization module (330).

[0347]

[0348] FIG. 15 is a drawing showing a process of changing the colors of a plurality of home appliances according to one embodiment of the present invention.

[0349] The user inputs a feature command via voice (S92). For example, the user inputs a voice command such as "It's really hot outside. Change the color to a very cool theme!" using a home appliance (one of the 100a, 100b, or 100c) or a smartphone / tablet (S92).

[0350] The server (500) or the home appliance (one of 100a, 100b, 100c) performs the process described in FIG. 3 and the like to produce a feature set (e.g., a color set) corresponding to the feature command (S93). If the result is "[C_A1, C_A2, C_A3, C_A4]", the color set can be applied to multiple home appliances.

[0351] For example, all four colors are applied to the refrigerator (100a). On the other hand, the kimchi refrigerator (100b) with three color panels applies three colors, such as "[C_A1, C_A3, C_A4]." In the case of the air conditioner (100c), two colors, such as "[C_A1, C_A4]," are applied.

[0352] When a user gives a single voice command, a consistent color theme can be applied to all home appliances (100a, 100b, 100c) in the house connected to the user's account on a server (500), for example, a ThinQ server.

[0353] In summary, in response to a user's feature command, the home appliance (100) or server (500) can apply one of the first feature set produced through the preprocessing module (310), the second feature set produced through the theme module (320), or the third feature set produced through the personalization module (330) to other home appliances connected to the user account of the home appliance (100), thereby applying consistent features to home appliances owned or used by the user.

[0354]

[0355] Although all components constituting the embodiments of the present invention have been described as being combined or operating in combination, the present invention is not necessarily limited to such embodiments, and within the scope of the present invention, all components may be selectively combined and operated one or more times. In addition, although all of the components may be implemented as individual independent hardware, some or all of the components may be selectively combined and implemented as a computer program having program modules that perform some or all of the functions combined in one or more hardware pieces. The codes and code segments constituting the computer program may be easily inferred by those skilled in the art of the present invention. Such a computer program may be stored in a computer-readable storage medium and read and executed by a computer, thereby implementing the embodiments of the present invention. Storage media for computer programs include magnetic recording media, optical recording media, and storage media including semiconductor recording devices. In addition, a computer program implementing an embodiment of the present invention includes a program module that is transmitted in real time through an external device.

[0356] While the above description focuses on specific embodiments of the present invention, various modifications and variations can be made within the scope of those skilled in the art. Therefore, it should be understood that such modifications and variations are within the scope of the present invention, as long as they do not depart from its scope.

[0357]

[0358]

Claims

A first step in which a server or home appliance produces a first feature set and a first accuracy corresponding to a feature command; A second step in which, if the first accuracy is below a standard, the server or the home appliance calculates a second feature set and a second accuracy corresponding to the feature command using a theme module placed on the server, the home appliance, or an external server; A third step in which the server or the home appliance calculates a third feature set using personalized information corresponding to the device information of the home appliance and the feature command when the second accuracy is below a standard; and A method for changing a feature of a home appliance, comprising a fourth step of changing any one of the first feature set, the second feature set, or the third feature set into a feature of the home appliance. In paragraph 1, A method for changing a feature of a home appliance, wherein the feature set includes any one of a color set, a speech set, or a function set. In paragraph 2, If the above feature set is a color set, the above feature command is a color command, A method for changing a feature of a home appliance, wherein if the above color command includes a color name of a color constituting the first color set, the second step includes a step in which the server or the home appliance determines that the first accuracy corresponds to a standard. In paragraph 1, The above second step is A method for changing a feature of a home appliance, comprising the step of inputting a sample feature command and a sample feature set corresponding to the sample feature command into the theme module, and calculating the second feature set corresponding to the feature command and the second accuracy. In paragraph 2, If the above feature set is a color set, the above feature command is a color command, A method for changing a feature of a home appliance, wherein the personalized information corresponding to the above device information includes information regarding one or more of a color set previously set in the home appliance corresponding to the above device information, the frequency of the set color set, or the duration of the color set. In paragraph 1, A method for changing a feature of a home appliance, wherein the server or home appliance further includes a step of inputting information about the region or country to which the user who uttered the feature command belongs in the theme module. In paragraph 1, A method for changing a feature of a home appliance, wherein the feature set includes one or more feature information and information about an area or function of a device to which the feature information is to be set. In paragraph 1, The server or the home appliance further includes a step of storing the feature command and the second feature set in a database according to the maintenance time or application number of the second feature set, A method for changing a feature of a home appliance, wherein the server or the home appliance further includes a step of setting information stored in the database as the first feature set or the third feature set in the process of calculating the first feature set or the third feature set for a feature command input after the fourth step. In paragraph 1, The server or the home appliance receives a fine-tuning command for any one of the first feature set, the second feature set, or the third feature set and produces a fourth feature set; A step of storing the above feature command and the fourth feature set in a database; and A method for changing a feature of a home appliance, wherein the server or the home appliance further includes a step of setting the fourth feature set stored in the database to the home appliance during the process of generating a feature set for a feature command input after the fourth step. In paragraph 1, A method for changing a feature of a home appliance, wherein the server or the home appliance further includes a step of applying one of the first feature set, the second feature set, or the third feature set to another home appliance connected to a user account of the home appliance. A preprocessing module that receives a feature command input by a home appliance and calculates a first feature set and a first accuracy corresponding to the feature command; A theme module that calculates a second feature set and a second accuracy corresponding to the feature command when the first accuracy is below a standard; If the second accuracy is below the standard, it includes a personalization module that calculates a third feature set using personalized information corresponding to the device information of the home appliance and the feature command. A server that sets any one of the first feature set, the second feature set, or the third feature set as a feature of the home appliance. In Article 11, If the above feature set is a color set, the above feature command is a color command, A server, wherein when the color command includes a color name of a color constituting the first color set, the server determines that the first color set meets the first accuracy standard. In Article 11, The server inputs a sample feature command and a sample feature set corresponding to the sample feature command into the theme module to produce the second feature set and the second accuracy corresponding to the feature command. In Article 11, If the above feature set is a color set, the above feature command is a color command, A server wherein personalized information corresponding to the above device information includes information on at least one of a color set previously set for a home appliance corresponding to the above device information, the frequency of the set color set, or the maintenance time of the color set. In Article 11, The above server is a server that additionally inputs information about the region or country to which the user who uttered the above feature command belongs into the above theme module. In Article 11, The server applies one of the first feature set, the second feature set, or the third feature set to another home appliance connected to the user account of the home appliance. A preprocessing module that receives a feature command input by a home appliance and calculates a first feature set and a first accuracy corresponding to the feature command; A counter theme module that transmits the feature command to a theme module of a generative AI external server when the first accuracy is below the standard and receives a second feature set and a second accuracy from the theme module; and If the second accuracy is below the standard, it includes a personalization module that calculates a third feature set using personalized information corresponding to the device information of the home appliance and the feature command. The above home appliance is a server that changes one of the feature sets of the first feature set, the second feature set, or the third feature set into a feature of the home appliance. In Article 17, If the above feature set is a color set, the above feature command is a color command, A server, wherein when the color command includes a color name of a color constituting the first color set, the server determines that the first color set meets the first accuracy standard. In Article 17, The counter theme module is a server that inputs a sample feature command and a sample feature set corresponding to the sample feature command into the theme module to receive the second feature set and the second accuracy corresponding to the feature command. In Article 17, If the above feature set is a color set, the above feature command is a color command, A server wherein personalized information corresponding to the above device information includes information on at least one of a color set previously set for a device corresponding to the above device information and the frequency of the set color set or the maintenance time of the color set. In Article 17, The above server is a server that additionally inputs information about the region or country to which the user who uttered the above feature command belongs into the above theme module. In Article 17, The server applies one of the first feature set, the second feature set, or the third feature set to another home appliance connected to the user account of the home appliance. A command input module that receives feature commands; A preprocessing module that receives the above feature command and calculates a first feature set and a first accuracy corresponding to the feature command; A theme module that calculates a second feature set and a second accuracy corresponding to the feature command when the first accuracy is below a standard; A personalization module that produces a third feature set using the stored personalized information and the feature command when the second accuracy is below the standard; and A device comprising a feature setting module for setting any one of the first feature set, the second feature set, or the third feature set as a feature. In Article 23, If the above feature set is a color set, the above feature command is a color command, A device, wherein when the color command includes a color name of a color constituting the first color set, the device determines that the first color set meets the first accuracy standard. In Article 23, The device inputs a sample feature command and a sample feature set corresponding to the sample feature command into the theme module to produce the second feature set and the second accuracy corresponding to the feature command. In Article 23, If the above feature set is a color set, the above feature command is a color command, A device in which personalized information corresponding to the above device information includes information on at least one of a color set previously set to a home appliance corresponding to the above device information and the frequency of the set color set or the maintenance time of the color set. In Article 23, The above device is a device that additionally inputs information about the region or country to which the user who uttered the feature command belongs into the theme module. In Article 23, A device that applies one of the first feature set, the second feature set, or the third feature set to another home appliance connected to a user account of the home appliance. It includes one or more processors that process information received from home appliances and input it into a theme module, which is a generative AI model, to obtain a result, and The above processor, A step of receiving a feature command from the first home appliance or the second home appliance that instructs a feature change of the first home appliance; A step of generating a prompt including at least one of the above feature command and configuration information of the first appliance corresponding to the above feature command; A step of obtaining a result by inputting the above prompt into the above theme module; and A method for changing features of a home appliance, comprising the step of converting the above result into a first feature set to be set in the first home appliance. In Article 29, The above prompt is a method for changing the features of a home appliance, which further includes status information of the first home appliance. In Article 29, A method for changing the features of a home appliance, characterized in that the second home appliance is a user terminal or a home appliance excluding the first home appliance. In Article 29, The received information above is voice or text, and A method for changing a feature of a home appliance, characterized by voice or text being input through the first home appliance, the second home appliance, or a user terminal. In Article 29, The above feature command is a command that instructs a change in the color of the first appliance, and A method for changing a feature of a home appliance, wherein the first feature set above includes information for one or more colors to be set in the first home appliance. In Article 33, The above configuration information is information regarding the area of ​​the first appliance to which the one or more colors are to be set, and A method for changing the features of a home appliance, wherein the above-mentioned state information includes information about a second feature set that is currently set or was previously set in the first home appliance. In Article 29, The above result includes two or more candidate feature sets, and A method for changing a feature of a home appliance, comprising the step of the processor applying one or more of the configuration information, the state information, and the feature instruction to convert one of the two or more candidate feature sets into the first feature set. In Article 29, A method for changing a feature of a home appliance, comprising the step of the processor transmitting the first feature set to the first home appliance or transmitting a feature control command to the first home appliance for applying the first feature set to the first home appliance.

Images