Method for providing user adaptive interface and voice control device for implementing same

Abstract

The present invention relates to a method for providing a user adaptive interface and a voice control device for implementing same. The method for providing a user adaptive interface according to an embodiment of the present invention comprises a step in which a voice control device outputs a voice comment suitable for a user's tendency, and the voice control device or a home appliance displays the progress of the output of the voice comment.

Description

Method for providing a user-adaptive interface and a voice control device implementing the same

[0001] The present invention relates to a method for providing a user adaptive interface and a voice control device implementing the same.

[0002] Control methods for home appliances can be divided into direct control and voice control. Direct control involves the user manipulating the remote control, buttons, or dial on the appliance to control its operation. Voice control involves the user uttering voice commands to the appliance, which are then recognized and operated.

[0003] Additionally, voice control devices can provide users with audible outputs of control results for home appliances or answers to user inquiries. Since these voice control devices engage in direct conversation with users, they must operate in a manner appropriate for the user.

[0004] Accordingly, this specification aims to describe a voice control device that operates in a user-adaptive manner.

[0005] This specification is intended to solve the aforementioned problems and to implement a method and device that allows a user to visually check the output time of a voice comment during the process of responding to a voice command of a home appliance.

[0006] Additionally, this specification allows for the generation of voice guidance messages suitable for the user's tendencies by collecting the user's tendencies in various ways.

[0007] In addition, this specification aims to increase user convenience by outputting voice guidance messages tailored to the user's preferences.

[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 and device for providing a user adaptive interface according to one embodiment of the present invention includes a step and embodiment in which a voice control device outputs a voice comment suitable for a user's preference and the voice control device or a home appliance displays the output progress of the voice comment.

[0010] A method for providing a user adaptive interface according to one embodiment of the present invention includes a step in which a control unit of a voice control device divides a first voice comment into two or more parts, a part output step in which a voice output unit of the voice control device outputs a part to be output in order among the two or more parts, a display step in which the control unit displays the progress of outputting the first voice comment on an interface unit of the voice control device simultaneously with or after the output of the part to be output, and a step in which the control unit controls the voice output unit and the interface unit to repeat the part output step and the display step for each part among the remaining parts in order of each part after the output of the part to be output.

[0011] A method for providing a user adaptive interface according to another embodiment of the present invention includes a step in which a server control unit of a server divides a first voice comment into two or more parts, a step in which a server communication unit of the server transmits the divided two or more parts to a voice control device, a part output step in which a voice output unit of the voice control device outputs a part to be output in order among the two or more parts, a display step in which the control unit of the voice control device displays the output progress of the first voice comment on an interface unit of the voice control device simultaneously with the output of the part to be output or at a time point before or after the output of the part to be output, and a step in which the control unit controls the voice output unit and the interface unit to repeat the part output step and the display step for each part among the remaining parts in order of each part after the output of the part to be output.

[0012] A voice control device providing a user adaptive interface according to one embodiment of the present invention provides voice recognition and voice comments, and a control unit of the voice control device divides a first voice comment into two or more parts, and then a voice output unit of the voice control device performs a part output process in which an output target part is output in order among the two or more parts, and the control unit performs a display process in which an output progress of the first voice comment is displayed on an interface unit of the voice control device simultaneously with the output of the output target part or at a time point prior to or after the output of the output target part, and the control unit controls the voice output unit and the interface unit to repeat the part output process and the display process for each part among the remaining parts in order of each part after the output of the output target part.

[0013] When the present invention is applied, a method and device can be implemented that allows a user to visually check the output time of a voice comment through a home appliance or voice control device.

[0014] When the present invention is applied, the user's preferences can be collected in various ways to generate voice guidance messages suitable for the user's preferences, thereby increasing user convenience.

[0015] When the present invention is applied, user convenience can be improved by outputting voice guidance messages tailored to the user's preferences.

[0016] 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.

[0017] FIG. 1 is a drawing showing the mutual operation and arrangement of a home appliance and a voice control device according to one embodiment of the present invention.

[0018] FIG. 2 is a drawing showing the configuration of a voice control device and server according to one embodiment of the present invention.

[0019] FIG. 3 is a drawing showing a control process of an interface unit for generating and outputting a voice comment by a voice control device according to one embodiment of the present invention.

[0020] FIG. 4 is a drawing showing an interface part of a voice control device according to one embodiment of the present invention.

[0021] FIG. 5 is a diagram showing a process of adjusting the output speed of a voice comment using user preference information according to one embodiment of the present invention.

[0022] FIG. 6 is a diagram showing a process of selecting a chatbot according to a user's preference according to one embodiment of the present invention.

[0023] FIG. 7 is a drawing showing a process in which a home appliance adjacent to a user outputs a voice comment of a voice control device or displays the output progress of a voice comment according to one embodiment of the present invention.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] In addition, the voice control device (or voice controller) described in this specification is placed in a home, office, etc. where home appliances are placed, and is portable, and provides functions necessary to control home appliances placed nearby by voice or to answer a user's questions.

[0030] The operating space described in this specification refers to a space (e.g., a home, an office, or a specific room or section) in which a voice control device and an appliance are placed.

[0031] FIG. 1 is a drawing showing the mutual operation and arrangement of a home appliance and a voice control device according to one embodiment of the present invention.

[0032] A voice control device (100) is a device placed in an operating space such as a home or office, and receives a voice command from a user (1) (S1). When a voice command is input, the voice control device (100) processes the voice to perform voice recognition or preprocessing such as noise removal (S2), and then transmits a preprocessed message to a server (500) (S3).

[0033] Here, the preprocessed message includes various embodiments. First, the preprocessed message is, in one embodiment, a voice file recorded from the voice spoken by the user (1). Next, the preprocessed message is, in another embodiment, a voice file from which ambient noise has been removed from the voice spoken by the user (1). Furthermore, the preprocessed message is, in another embodiment, a text file converted from the voice spoken by the user (1). For this purpose, the voice control device (100) may include an STT (Speech-To-Text) function.

[0034] The server (500) can perform a predetermined task on the preprocessed message and then transmit it to the corresponding home appliance (10a, 10b, 10c, 10d) (S5a, S5b, S5c, S5d). That is, the server (500) that receives the preprocessed message transmitted by the voice control device (100) performs a voice recognition task or processes a text file, and then transmits a control command that instructs the operation of the corresponding home appliance (10a, 10b, 10c, 10d) to the home appliance (S5a, S5b, S5c, S5d). Then, the server (500) transmits a result message (Result Message) for the control command to the voice control device (100) (S6), and the voice control device (100) outputs the result message as a voice (S7) so that the user (1) can listen to it.

[0035] In the embodiment of Fig. 1, if the voice command input by the user (1) is unrelated to the control of the home appliance, only the processes of S1 / S2 / S3 / S6 / S7 can be performed.

[0036] Additionally, if the voice control device (100) can directly process the voice command input by the user (1), only the processes of S1 / S2 / S7 can be performed.

[0037] Additionally, the voice control device (100) can directly transmit control commands to home appliances (10a, 10b, 10c, 10d) independently of the server (500). In this case, the voice control device (100) can transmit control commands to home appliances (10a, 10b, 10c, 10d) according to a protocol agreed upon and receive a result message accordingly.

[0038] A voice control device (100) according to an embodiment of the present invention is placed within a home and enables voice recognition-based operations of home appliances placed within the operating space, thereby connecting the operating space. This allows users to continuously experience new services by expanding the experience space of a smart home. The voice control device (100) according to an embodiment of the present invention can monitor or control the operation of home appliances located in a multipurpose room, bedroom (dressing room), kitchen, living room / bedroom, etc.

[0039] In addition, the voice control device (100) according to the embodiment of the present invention can transmit voice data to the server (500) in real time when a voice recognition command is uttered.

[0040] Additionally, the voice control device (100) according to an embodiment of the present invention can utilize generative AI to provide voice recognition guidance messages tailored to the user's preferences. In this process, an interface that allows the user to visually check the progress of the voice recognition guidance messages can be provided.

[0041] In addition, the voice control device (100) according to the embodiment of the present invention can also provide long sentence information to users who prefer detailed guidance, unlike the current short information provision.

[0042] For example, when providing information such as laundry tips or recipes through voice, long information tailored to the user's preferences can be provided through voice according to hyper-personalization, and information about the expected total duration of voice guidance can be provided to the user so that the user can anticipate the end point of the voice guidance.

[0043]

[0044] FIG. 2 is a diagram illustrating the configuration of a voice control device and server according to one embodiment of the present invention. The voice control device (100) includes an interface unit (110), a control unit (150), a voice input unit (160), a voice output unit (170), and a communication unit (190). These are logical components, and some of these components may be configured as a single physical component.

[0045] The server (500) includes a server communication unit (590), a voice comment generation unit (510), and a server control unit (550). These are logical components, and some of these components may be configured as a single physical component. When the server (500) generates a voice comment, the voice comment generation unit (510) may perform a process of converting a specific response text into a voice comment.

[0046] In an embodiment of the present invention, some functions performed by the voice control device (100) may be performed by the server (500).

[0047] FIG. 3 is a drawing showing a control process of an interface unit for generating and outputting a voice comment by a voice control device according to one embodiment of the present invention.

[0048] In one embodiment, the first voice comment to be output by the voice control device (100) is a voice comment received from a server. Alternatively, the voice control device (100) may generate the first voice comment on its own. In one embodiment, generating the first voice comment on its own means converting a specific string into the first voice comment, and in one embodiment, the specific string is received from an external source or is a string previously stored by the voice control device (100). Alternatively, the voice control device (100) may also generate a string.

[0049] First, the control unit (150) of the voice control device (100) divides the first voice comment into two or more parts (S11). Since the voice comment has a certain length, the parts can be divided according to the length or based on the pause (non-pronounced part) in the middle.

[0050] A part is an output unit of a voice comment, and a user can perceive that the voice comment is output continuously without distinguishing between such parts. In other words, a part indicates a logical division for the control unit (150) and the voice output unit (160) to output a voice comment.

[0051] And the voice output unit (160) of the voice control device (100) performs a part output process of outputting the output target part in order among two or more parts (S13).

[0052] And the control unit (150) performs a display process of displaying the output progress of the first voice comment on the interface unit (110) of the voice control device (100) simultaneously with the output of the output target part or at a point in time before or after the output of the output target part (S14).

[0053] Thereafter, the control unit (150) controls the voice output unit (160) and the interface unit (110) to repeat the part output process (S13) and the display process (S14) for each part among the remaining parts according to the order of each part after the output of the output target part (S15).

[0054] When applying the embodiment of FIG. 3, the voice control device (100) can display the output progress of the voice comment through the interface unit (110) while outputting the voice comment, so that a user listening to the voice comment can visually recognize how much time is required for all of the voice comments to be output. The interface unit (110) can display the output completion time of the voice comment through an LED display or a number (e.g., 7-segment).

[0055] The interface unit (110) of the voice control device (100) can be implemented in various shapes, such as circular, square, bar-shaped, etc., and the embodiments of the present invention are not limited to a specific shape. The user can estimate the time until the voice message is fully output based on the degree to which the visual light on the interface unit (110) increases or decreases or the degree of blinking changes.

[0056] In S11, it is suggested that the first voice comment can be received from a server (500) or directly generated by the control unit of the voice control device (100).

[0057] If the first voice comment is received from the server (500), the server control unit (550) of the server (500) can generate the first voice comment to be transmitted to the voice control device (100). In addition, the process of the server communication unit (590) transmitting the first voice comment to the voice control device (100) and the communication unit (190) of the voice control device (100) receiving the first voice comment can be performed before S12.

[0058] In addition, when the first voice comment is generated and transmitted from the server, the output time information required to output the first voice comment can also be calculated by the server (500) and transmitted to the voice control device (100).

[0059] As a result, the display step of S14 may further include a process in which the control unit (150) controls the interface unit (110) using the output time information so that the interface unit (110) displays the output progress status.

[0060] In the embodiment of FIG. 3, the server (500) may also separate voice comments. For example, the server (500) may separate the first voice comment to be output by the voice control device (100) into a plurality of output target parts, and transmit each of these output target parts to the voice control device (100). In this case, the voice control device (100) may sequentially output the received plurality of output target parts.

[0061] For example, after the server control unit (550) of the server (500) separates the first voice message into two or more parts, the server communication unit (590) can transmit the two or more separated parts to the voice control device (100). That is, the server (500) performs steps S11 and S12. Thereafter, the voice control device (100) can perform steps S13 to S15.

[0062] FIG. 4 is a drawing showing an interface part of a voice control device according to one embodiment of the present invention.

[0063] 110a is a configuration in which LEDs arranged in a circle light up according to the output progress. In 110aa, each LED is off, and while outputting a voice message, the LEDs can light up for the amount of time that has elapsed, such as in 110ab and 110ac, under the control of the control unit (150), so that the user can visually check the remaining time. As the voice message is output, the proportion of LEDs that light up increases.

[0064] 110b displays the output progress of the voice message in the form of a progress bar. While the voice message is output in a state like 110ba, you can check the output progress of the voice message in 110bb and 110bc.

[0065] 110c is an example of displaying the output progress of a voice comment in a pie shape across the entire circle. While the voice comment is output in a state similar to 110ca, the output progress of the voice comment can be checked in the same way as 110cb and 110cc.

[0066] Referring to FIG. 3 above, a voice comment can be divided into multiple parts depending on the length of the voice file, the number of texts to be spoken, etc. The control unit (150) can display the length of the remaining time required to output the remaining parts of the voice comment after the output target part on the interface unit (110) of the voice control device. The remaining time can be calculated based on various criteria, such as the number of remaining characters and the size of the remaining file.

[0067] Meanwhile, the output speed of a voice comment or part can be increased or decreased using the user's preference information. For example, if the user's preference information prefers a fast voice comment, the voice control device (100) outputs the voice comment or part in a short time. For example, assuming that the time for an actual voice comment or part to be output is t_out, the voice control device (100) outputs the voice comment in a short time, such as t_out * 0.8, for a user who prefers a fast voice comment. This can be implemented through a function for outputting quickly (1.2x speed, 1.5x speed, etc.) when outputting voice.

[0068] Alternatively, the voice control device (100) or server (500) may generate a sound file that composes a voice comment based on the user's preference information. For example, if the user's preference information indicates a preference for quick voice comments, the voice control device (100) may generate a sound file that allows the user to pronounce the same voice comment quickly and output the same.

[0069] Alternatively, the type of voice prompt to be output may vary depending on the user's preference information. For example, if the user's preference information indicates a preference for short answers, the voice control device (100) may output a voice prompt consisting of short answers. Conversely, if the user's preference information indicates a preference for detailed answers, the voice control device (100) may output a voice prompt consisting of long answers.

[0070] In order to display the output progress of a voice comment or part on the interface unit (110), the control unit (150) can calculate output time information of the voice comment or part. To this end, the voice control device (100) can receive output time information from the server (500).

[0071] In summary of the above-described embodiment, the server (500) or the voice control device (100) can calculate the output time of a voice guidance message (Text-To-Speech) generated according to the user's preference or independently of the user's preference, and control the interface unit (110) according to the voice guidance message time.

[0072] As in 110a above, the voice control device (100) can control whether each LED of the circular LED blinks or the blinking speed, or can control the progress speed of the progress bar as in 110b, or can control the size of the pie to be displayed in the circle as in 110c.

[0073] For example, if the internal calculation result of the voice guidance message time is 6 seconds or 1 to 2 seconds have elapsed, the voice control device (100) can slow down the blinking speed of the entire circular LED and adjust the blinking speed to be faster as time elapses.

[0074] That is, when the interface unit (110) of the voice control device (100) is composed of LEDs, etc., the voice control device (100) can visualize the voice guidance time and change the number / area / speed, etc., of LEDs turned on.

[0075] The internal calculation of the voice guidance message time can be performed by the server (500) or the voice control device (100) based on the text length or the size of the voice guidance sound source file to calculate the output time. If the server (500) calculates the output time, the server (500) can transmit the calculated output time information to the voice control device (100).

[0076] The server (500) or the voice control device (100) can calculate the output time based on the length of the text to be output as a voice comment. For example, the length of the text (the number of characters) can be x, and the output time of the voice comment can be calculated as the y value by applying the linear function y = ax + b. For example, a is 0.1953 and b is 0.2578. Here, spaces within the text can be included in the length, but the present invention is not limited thereto.

[0077] For example, referring to Table 1, you can check the output time for each voice comment file.

[0078] No. File name of voice message (Text.pcm) Text length (including spaces) Output time (seconds) y=0.1953 x+0.25781 Drying cycle start. pcm8 1.92 Cold wave warning in effect. pcm9 2.13 Standard washing cycle start. pcm10 2.34 High fine dust concentration. pcm14 3.15 Proceed with the steam cycle for laundry. pcm16 3.46 Please select fabric softener in the rinse cycle. pcm25 5.1

[0079] Meanwhile, the server (500) or voice control device (100) can calculate the output time based on the voice guidance sound source size. For example, the output time of the voice comment can be calculated as the y value by applying a linear function y = cx to the voice guidance sound source size (KB, x value). For example, c is 0.0256. See Table 2.

[0080] No. File name of voice message (Text.pcm) Sound source size Output time (seconds) y=0.0256 x1 Drying course start. pcm83.51.92 Cold wave warning in effect. pcm882.13 Standard washing course start. pcm93.72.34 Fine dust concentration is high. pcm1093.15 Proceed with the steam course for laundry. pcm1253.46 Please select fabric softener in the rinse course. pcm198.55.1

[0081]

[0082] When applying the embodiment of FIG. 4, the voice control device (100) or server (500) calculates and utilizes the expected output time of the voice guidance message, allowing the user to visually check the progress of the voice guidance message output. The progress can be implemented through changes in the illuminated area or speed of the LED, but the present invention is not limited thereto.

[0083] To calculate the output time, the server (500) or voice control device (100) can use a linear function to calculate the expected time based on the text length of the voice comment or the sound source size of the voice comment.

[0084]

[0085] Figure 5 is a diagram illustrating a process for adjusting the output speed of a voice message using user preference information according to one embodiment of the present invention. Figure 5 also illustrates a process for checking preference information for a new user.

[0086] The user's tendency information is calculated based on information collected about the user's personality, tastes, etc., and can be calculated by the server (500) or the voice control device (100). In addition, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can select one voice comment suitable for the user's tendency information from among a plurality of voice comments using the user's tendency information.

[0087] The server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) checks whether the user is a new user or an existing user in order to collect data corresponding to the user's tendency information. If the user is a new user, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) sets the value of User1_Speed ​​to 0 in order to check the user's tendency information (S1). Then, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) checks the answer to the checklist for checking the tendency (S22). In one embodiment, this answer is a value entered by the user when he or she first logs into the service.

[0088] Thereafter, if the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) determines that the user wants a detailed answer based on the items checked by the user in the confirmed answer, the value of User1_Speed ​​is decreased by 1 (User1_Speed--;). Conversely, if the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) determines that the user wants a simple answer based on the items checked by the user in the confirmed answer, the value of User1_Speed ​​is increased by 1 (User1_Speed++;) (S23).

[0089] Next, based on the answer selected by the user as the preferred chatbot character, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) increases or decreases the value of User1_Speed ​​according to the speech tone of the chatbot character. For example, if the user's preferred chatbot character has a slow speech tone, the value of User1_Speed ​​is decreased by 1 (User1_Speed--;). Conversely, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) increases the value of User1_Speed ​​by 1 (User1_Speed++;) (S24) if the user's preferred chatbot character has a fast speech tone based on the items checked by the user in the confirmed answer.

[0090] Additionally, in addition to the items checked by the user, the user's usage habits for home appliances or the user's voice commands can be analyzed to derive user preference information.

[0091] For example, if the user's preferred air conditioner temperature is higher than the reference temperature, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) decreases the value of User1_Speed ​​by 1 (User1_Speed--;) because the user may have a strong tolerance for heat. Conversely, if the user's preferred air conditioner temperature is lower than the reference temperature, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) increases the value of User1_Speed ​​by 1 (User1_Speed++;) (S25).

[0092] In addition, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) decreases the value of User1_Speed ​​by 1 if the speed of the input user's voice command is slow (User1_Speed--;). Conversely, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) increases the value of User1_Speed ​​by 1 if the speed of the input user's voice command is fast (User1_Speed++;) (S26).

[0093] Items S23 to S26 are exemplary, and various judgment criteria may be added. Furthermore, user preference information may be set based on any one of the judgment criteria S23 to S26.

[0094] The server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) sets user preference information (S27) based on the value of User1_Speed ​​accumulated up to S26. For example, if the value of User1_Speed ​​is 2 or higher, it can be determined that the user wants a quick response.

[0095] The embodiment of Fig. 5 illustrates the factors and logic that must be implemented from a hyper-personalization perspective, in addition to the factors for calculating the expected voice guidance time for the user during the voice message output process. That is, the output speed of the voice message determined under the above conditions may change depending on the user's personal preferences, and thus the expected voice message time may also change.

[0096] If the same voice guidance function were provided to all users regardless of their personal characteristics or current emotional state, users might not focus on the voice prompts because they might not be suited to their preferences. Therefore, each of the criteria in Figure 5 can be applied to suit the user's preferences.

[0097] Each user may have different settings for their preferred AI chatbot. For example, depending on whether the user has checked the level of voice guidance explanation they desire, such as S22, as "short answer explanation without detailed explanation" or "detailed explanation," the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) may set the length of the voice message to be output to the user, the output speed, or the type of response differently.

[0098] Accordingly, by automatically reflecting the user's individual personality, tastes, etc., the voice control device (100) can provide a voice guidance function optimized for the individual's personality.

[0099] In addition, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can automatically classify the user's personality by utilizing the user's voice commands and the usage history of the home appliance, and set the chatbot personality that best matches the user's personality.

[0100] As a result, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) provides control of home appliances and personalized voice guidance functions based on the individual personality and chatbot personality.

[0101] The server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can provide the type, length, speed, tone, size, etc. of voice comments (voice guidance comments) in a personalized manner based on user preference information.

[0102] For example, as exemplified in S25, for an impatient individual who sets the air conditioner temperature to 18 degrees, the electric range heat power to 10, etc., the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) provides fast voice guidance.

[0103] In addition, the user's personality can be recognized by utilizing the user's voice command usage history, etc. In the case where the number of settings for low-temperature air conditioners, high-heat cooking appliances, etc. increases in the menu selection of the home appliance, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can provide voice guidance at a high speed.

[0104] Users can manually input commands or questions as text in the app (ThinQ app) installed on user terminals (e.g. smartphones, tablets, etc.) that are linked to home appliances, and in this process, users can select items related to their tendencies.

[0105] For example, users can select an MBTI type or a famous character (a celebrity A known for being impatient or a celebrity B known for being easygoing) through their user terminal, or select their own personality type (e.g., Diplomat / Administrator / Analyzer / Explorer).

[0106] In addition, by linking with an SNS app (e.g., Facebook, Instagram) installed on a user terminal, the user can input his / her personality or tendencies, and this value can be transmitted to a server (500) or voice control device (100) and used as tendencies information.

[0107] In this regard, when implementing PoC (Proof of Concept), the server (500) or voice control device (100) may be implemented in an embodiment that automatically recognizes the personality of the individual user as follows. Assume that the user's name is "Younghee."

[0108] "User Younghee is a friendly and humorous 25-year-old college student. She's very patient and enjoys chatting. She frequently uses her air conditioner and may ask for help with related issues. She also enjoys having casual conversations for fun."

[0109] A sentence like this can also be produced based on the embodiment of Fig. 5. Furthermore, the sentence above can be an example of an output produced by inputting the values ​​input in the embodiment of Fig. 5 into a chatbot or generative artificial intelligence model.

[0110] When applying the process of FIG. 5 described above, the server (500) or voice control device (100) can set a chatbot personality that matches and suits the user's personality or inclination. That is, when there are multiple chatbots, the server (500) or voice control device (100) can set a specific chatbot similar to the user's personality or inclination to process the user's voice commands.

[0111] Additionally, the user can manually input the preferred chatbot personality into an app (e.g., ThinQ) on the user terminal or select one of multiple chatbots. The chatbot personality can be described as, for example, encyclopedic, sociable, scientific, or idea-oriented, or as "detailed explanation" or "short answer explanation," and can be directly selected by the user. As a result, the server (500) or voice control device (100) can generate a sentence describing a chatbot suitable for the user "Younghee" in response to the sentence described for the user above, and output it as a voice message or text.

[0112] "My name is Lgenie, a 33-year-old customer service assistant and a personalized chatbot for user Younghee. Known for her friendly and talkative nature, Lgenie has a unique ability to explain complex concepts in an easy-to-understand way. Whenever a user says "Hi LG," Lgenie interprets this as a signal to start a new conversation or change the current topic of discussion. If asked a question she doesn't know, Lgenie will honestly say she doesn't know."

[0113] When applying such an embodiment, a voice guidance function optimized for individual personality is provided, and through user-customization, the user can use the voice recognition function more conveniently.

[0114] The embodiment of FIG. 5 can also be applied to existing users. However, since the User1_Speed ​​for an existing user already has a calculated value (e.g., 1 or -2), the process of S22 to S27 can be performed starting from the calculated value. Of course, if the user chooses to reset the preference information, the process can proceed according to the flow of FIG. 5.

[0115] Meanwhile, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can change the user preference information according to the user's behavior during the process of outputting the voice comment even after determining the speed of the voice comment by setting the user preference information as in S27.

[0116] For example, if User1_Speed ​​is set to -3 and a voice comment is output at a slow speed, but the user's behavior is detected by a home appliance, such as leaving the seat while listening to the voice comment, or the user shouts "stop" while outputting a long voice comment, and the user's behavior is in conflict with the behavior set by the user preference information, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can reset the user preference information of the user or modify the User1_Speed ​​value.

[0117] When user preference information is set as in FIG. 5, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can increase or decrease the output speed of the output target part or the first voice comment using the user preference information in the part output step of FIG. 3.

[0118] In addition, before the separation step of S12, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can select the first voice comment from among the first voice comment and the second voice comment using the user's tendency information.

[0119] For example, if the user's preference information is such that a short answer is desired at a fast speed, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) may select the first voice comment for the short or summarized answer among the first voice comment for the short or summarized answer and the second voice comment for the long answer.

[0120] Alternatively, a chatbot can be selected based on the user's preferences. Among short-answer chatbots and detailed-answer chatbots, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) can select a chatbot based on the user's preferences, receive a response, and provide the response as a voice message.

[0121] For example, the server control unit (550) of the server (500) or the control unit (150) of the voice control device (100) may select either a first voice comment consisting of short letters or a second voice comment consisting of long letters from among two or more answers, depending on the number of letters to be output. That is, the first voice comment and the second voice comment differ in the number of letters to be output, and a voice comment with a short number of letters or a voice comment with a long number of letters may be selected depending on the user's preference.

[0122]

[0123] FIG. 6 is a diagram showing a process of selecting a chatbot according to a user's preference according to one embodiment of the present invention.

[0124] For example, before the step of separating S12 in FIG. 3, the voice input unit (160) of the voice control device (100) may receive a user's voice input, and the control unit (150) may convert it into a question text (S31). Then, the control unit (150) may select a chatbot (e.g., a first chatbot) that will provide an answer to the question text using the user's tendency information (S32).

[0125] The communication unit (190) of the voice control device (100) transmits a question text to the selected chatbot (first chatbot) and then receives a response message (S33). The control unit then converts the response message into a first voice comment and outputs the first voice comment (S34). Thereafter, the control unit (150) can generate a follow-up response or reselect a second chatbot different from the first chatbot based on the user's subsequent response (S35). In one embodiment, if the user asks an additional question or inputs the voice command "Explain in detail" as a follow-up response, the second chatbot that provides a detailed response is selected.

[0126] Additionally, another embodiment is provided where a second chatbot is selected to provide a brief response if the user leaves the room while listening to the response or inputs the voice command "stop."

[0127] The embodiment of FIG. 6 can be applied to the server control unit (550) of the server (500). In the case of an embodiment in which the server control unit (550) selects a specific chatbot, the server control unit (550) selects a specific chatbot using the user's preference information and transmits a question text corresponding to a voice command to the chatbot to receive a response message.

[0128] The server control unit (550) of the server (500) can directly convert the response message into a voice comment or transmit the response message to the voice control device (100) so that the voice control device (100) can directly generate the voice comment. The S35 process can be performed in response to information about the user's subsequent response (such as seat movement or additional voice command) transmitted by the home appliance or the voice control device (100).

[0129] In steps S31 to S33, there is a process for converting an input voice command (a voice file asking a question) into a question text. If the chatbot can receive a voice question, the process of converting it into a question text can be omitted, and the server (500) or voice control device (100) can transmit the input voice command to the chatbot as is.

[0130] Additionally, when a chatbot generates a voice response, the server (500) or voice control device (100) can output the voice response received from the chatbot as a voice response without converting the response message into a voice comment.

[0131] When applying the embodiment of FIG. 6, the server (500) or voice control device (100) can generate a voice recognition guidance message (Text-To-Speech) tailored to the user's preferences.

[0132] Steps S31 to S33 of FIG. 6 may be performed in a server (500) or a voice control device (100). For example, the voice input unit (160) of the voice control device (100) may receive a user's voice input, and the control unit (150) of the voice control device (100) may convert it into a question text (S31). Then, the voice control device (100) may transmit the converted question text to the server (500).

[0133] The server control unit (550) selects a chatbot that will provide an answer to the question text using the user's preference information (S32), and the server communication unit (590) can transmit the question text to the selected chatbot and then receive a response message (S33). In addition, the server control unit (550) can convert the response message into the first voice comment.

[0134] Next, we will look at an example in which another home appliance outputs the output progress of a voice comment output by the interface unit (110) of the voice control device (100).

[0135] FIG. 7 is a drawing showing a process in which a home appliance adjacent to a user outputs a voice comment of a voice control device or displays the output progress of a voice comment according to one embodiment of the present invention.

[0136] Fig. 7 illustrates an embodiment in which the progress of voice recognition or voice comment output can be displayed via a large LED mounted on a home appliance in the same space where the user is located. The interface (interface unit such as an LED) of the home appliance simultaneously displays the progress of voice comment output in the same manner as the voice control device (100), so that the user can anticipate the point in time when the voice comment output is complete.

[0137] User location can be determined by utilizing sensors related to the presence of the user, or the volume of sound input into the microphone of a home appliance or voice control device (100). Let's take a closer look.

[0138] The communication unit (190) of the voice control device (100) receives a user detection message from a first home appliance that has detected a user (S41). The first home appliance may be, in one embodiment, various home appliances capable of detecting the presence of a person nearby, such as an air conditioner, a light, a water purifier, a TV, etc. Alternatively, each of the presence-related sensors (motion sensor, opening detection sensor, light sensor) may correspond to the first home appliance, and home appliances equipped with the aforementioned sensors may also correspond to the first home appliance.

[0139] And, the communication unit (190) transmits an output progress message to the first home appliance or the second home appliance so that the interface unit of the first home appliance or the second home appliance placed adjacent to the first home appliance displays the output progress of the voice comment (S42).

[0140] At this time, the second home appliances include home appliances that can visually convey information to the user, such as air conditioners, lights, TVs, and microwave ovens.

[0141] Afterwards, the interface section of the first home appliance or the interface section of the second home appliance displays the progress of the voice comment output (S43).

[0142] If there is a home appliance including a speaker among the first home appliance, the second home appliance, or the third home appliance adjacent to the first home appliance, such home appliance may output voice messages.

[0143] An embodiment of the present invention can be implemented as follows. For example, among a plurality of home appliances including LEDs, a home appliance capable of providing information based on a user's location can detect the user's location.

[0144] For example, presence-related sensors (motion sensors, open detection sensors, light sensors, etc.) linked to an app installed on a user terminal (e.g., ThinQ app) can detect the user's location. In this case, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) can select home appliances in a space where the presence-related sensors that detected the user's location are installed. To this end, the app installed on the user terminal (e.g., ThinQ app) can store location information of home appliances including LEDs and transmit this information to the voice control device (100) or the server (500).

[0145] That is, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) can check information that the presence-related sensors have detected a user, select home appliances placed at the detected location, and control the home appliances so that the selected home appliances output a voice comment or display the output progress according to the output of the voice comment.

[0146] For example, if a user is detected by a motion sensor (lighting) or an opening detection sensor (refrigerator) in the kitchen, home appliances that include LEDs registered as being placed in the kitchen can display the output progress according to the output of a voice message to the user. The display method can be applied according to the embodiment of Fig. 4 depending on the characteristics of the interface unit installed in the home appliance.

[0147] When home appliances include LEDs and have built-in microphones, if the sound volume input to the microphone exceeds a certain value, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) determines that a user is located near the home appliance. As a result, the home appliance with the microphone volume exceeding the certain value can display the output progress according to the output of the voice comment. Alternatively, when only the microphone is built-in and there is no LED, another adjacent home appliance with an LED can display the output progress according to the output of the voice comment.

[0148] For example, when the sound level input to the built-in microphone of the tower air conditioner is 60 dB or higher, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) determines that the user is near the tower air conditioner, selects the tower air conditioner as an appliance for displaying the output progress according to voice recognition and voice comment output, and utilizes the built-in LED.

[0149] When applying the embodiment of Fig. 7, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) can simultaneously display the voice recognition progress status, identical to the voice control device (100), through a large LED mounted on the home appliance in the same space, by the home appliance that recognizes the space in which the user is present.

[0150] In an extension of the embodiment of Fig. 7, the voice control device (100) can control the home appliance so that it identifies another adjacent home appliance and displays the output progress status of the identified home appliance according to the voice comment output.

[0151] In addition, when a number of home appliances are placed in a space where a user is present, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) can preferentially select a home appliance with a large LED among these home appliances to enhance the visual effect when displaying the voice recognition progress status.

[0152] Alternatively, when a number of home appliances are placed in a space where a user is present, the control unit (150) of the voice control device (100) or the server control unit (550) of the server (500) can preferentially select home appliances with LEDs of various colors among these home appliances to enhance the visual effect when displaying the voice recognition progress status.

[0153] When applying an embodiment of the present invention, a user can check the accurate voice recognition status and voice comment output status when using a voice control device (100), thereby increasing the user experience (UX, User eXperience).

[0154] In addition, when responding to a user's response through generative AI, the voice guidance message may become longer, and the user can visually check the output progress of the voice message output by the voice control device (100) or home appliances, thereby increasing user convenience.

[0155] In particular, when applying an embodiment of the present invention, the voice control device (100) can provide a detailed or brief description depending on the user's preferences. Furthermore, the voice control device (100) can increase or decrease the voice output speed depending on the user's preferences, thereby providing personalized services to the user.

[0156] That is, even if the voice control device (100) outputs the same voice message quickly or slowly depending on the user's preference. Furthermore, even for the same question, the voice control device (100) can provide a detailed explanation or a short / summary answer depending on the user's preference. Furthermore, the voice control device (100) can provide the user with a voice message in a customized tone of voice by utilizing information about the user's preferred voice or favorite celebrities.

[0157] The embodiments of the present invention can also be applied to voice recognition. However, in the case of voice recognition, since the end time cannot be confirmed unless the user finishes speaking, the interface unit of the voice control device (100) may indicate that voice recognition is in progress.

[0158] When applying an embodiment of the present invention, a voice control device (100), for example, a voice controller, may generate a voice recognition guidance message (Text-To-Speech) tailored to the user's preferences by utilizing generative AI when responding to or responding to a voice recognition command, and may internally calculate the voice guidance message time. The voice control device (100) may adjust whether or not to blink an LED built into the voice control device (100) and a home appliance in the same space, or the blinking speed, according to the time taken to output the voice guidance message (calculated time), so that the user can check the remaining time for the voice message output.

[0159] The voice control device (100) can control the home appliance so that it can simultaneously display the status of voice recognition and comment output in the same manner as the voice control device (100) through a large LED installed in the home appliance placed in the same space as the voice control device (100) or placed adjacent to the user.

[0160] When a voice control device (100) provides voice guidance, it automatically recognizes the user's personality, preferences, etc., and provides a voice guidance function optimized for the user's personality. By utilizing the characteristics of voice commands and the user's home appliance usage history, parameters for automatically recognizing or estimating the user's personality can be calculated, and a chatbot personality that best matches the user's personality can be set. The voice control device (100) provides home appliance control and personalized voice guidance functions based on the user's personality and chatbot personality.

[0161] Depending on the user's personality, the voice control device (100) may provide a short explanation without detailed explanation or an explanation including detailed explanation.

[0162] For example, for a user set to the "Brief Answer Type" (a type that provides a short explanation without detailed explanation), an example of the voice guidance message for the user's question is as follows:

[0163] User Question: "I got soy sauce on my clothes. Can you give me some washing tips?"

[0164] Voice guidance message: "If soy sauce is present, we recommend washing without pretreatment. If you need further assistance, say <continue> or <more>."

[0165] If the user says "continue" here, the voice control device (100) can provide a detailed answer. Furthermore, if the user subsequently inputs a voice command requesting a detailed answer for another question, the voice control device (100) sets the user's preference to "the type that provides detailed answers."

[0166] Conversely, if the user does not ask any more questions, the voice control device (100) remains in the “type that provides brief answers” ​​according to the user’s tendency.

[0167] If the user is set to the “type that provides detailed answers,” the voice control device (100) can output detailed answers to the above questions, including quick processing methods, detergent usage methods, washing machine course settings, bleach usage methods, and leaving it to a professional.

[0168] In this process, if the user says "stop" or "stop," the voice control device (100) stores a history of the user's voice command input. And, if the number of times the user interrupts the output of detailed voice commands such as "stop / stop" exceeds a certain standard, the voice control device (100) sets the user's type to "the type that provides brief answers" so that the user can hear a brief explanation later.

[0169] When applying an embodiment of the present invention, the voice control device (100) can display the output status of the voice guidance message or the remaining time using an LED or the like while outputting the voice guidance message, thereby allowing the user to estimate the time when the voice guidance message ends, thereby increasing the convenience of use.

[0170] In addition, the voice control device (100) simultaneously displays the output status of the comment or the remaining time through a large LED of a home appliance (e.g., an air conditioner, a TV, a refrigerator, etc.) placed in the same space as the user or the home appliance placed in the same space as the user, so that the user can easily check the voice recognition and comment output progress status of the voice control device (100).

[0171] The voice control device (100) can automatically recognize the user's personality, tastes, etc. or set an answer type suitable for the user. Based on this, the voice control device (100) provides a voice guidance function optimized for the user's personal personality, thereby enabling the user to use the voice recognition function more usefully.

[0172] That is, when applying an embodiment of the present invention, the voice control device (100) or server (500) can automatically recognize an individual's personality by utilizing voice commands and the user's home appliance usage history, and set a chatbot personality that best matches the individual's personality. Accordingly, based on the individual's personality and the chatbot personality, the voice control device (100) or server (500) can provide home appliance control and personalized voice guidance functions.

[0173]

[0174] 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.

[0175] 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.

[0176] -Explanation of the symbol-

[0177] 10a, 10b, 10c, 10d: Home appliances

[0178] 100: Voice Control Device

[0179] 500: Server

[0180]

Claims

1. A step in which the control unit of the voice control device separates the first voice comment into two or more parts; A part output step in which the voice output unit of the voice control device outputs the output target part in order among the two or more parts; A display step in which the control unit displays the output progress of the first voice comment on the interface unit of the voice control device simultaneously with the output of the output target part or at a point in time before or after the output of the output target part; and A method for providing a user adaptive interface, wherein the control unit controls the voice output unit and the interface unit to repeat the part output step and the display step for each part among the remaining parts according to the order of each part after outputting the output target part.

2. In paragraph 1, The above display steps are A method for providing a user adaptive interface, wherein the interface unit further includes a step of displaying the length of the remaining time required to output the remaining part after the output target part among the first voice comments.

3. In paragraph 1, A method for providing a user adaptive interface, wherein the part output step further includes a step in which the control unit increases or decreases the output speed of the output target part or the first voice comment using the user's tendency information.

4. In paragraph 1, Before the above separation step, A method for providing a user adaptive interface, wherein the control unit further includes a step of selecting the first voice comment from among the first voice comment and the second voice comment using the user's preference information.

5. In paragraph 4, A method for providing a user-adaptive interface, wherein the first voice comment and the second voice comment differ in the number of characters to be voiced.

6. In paragraph 1, The communication unit of the voice control device includes a step of receiving a user detection message from a first home appliance that has detected a user, The above display steps are A method for providing a user adaptive interface, further comprising a step of the communication unit transmitting an output progress message to the first home appliance or the second home appliance so that the interface unit of the first home appliance or the second home appliance located adjacent to the first home appliance displays the output progress, and the interface unit of the first home appliance or the second home appliance displays the output progress.

7. In paragraph 1, Before the above separation step A step in which the voice input unit of the voice control device receives the user's voice input and converts it into a question text; The above control unit selects a chatbot that will provide an answer to the question text using the user's tendency information; The communication unit of the voice control device transmits the question text to the selected chatbot and then receives a response message; and A method for providing a user adaptive interface, wherein the control unit further comprises a step of converting the response message into the first voice comment.

8. In paragraph 1, Before the above separation step A step in which the server control unit of the server generates a first voice comment to be transmitted to the voice control device; and A method for providing a user adaptive interface, comprising a step in which a server communication unit of the server transmits the first voice comment to the voice control device and the communication unit of the voice control device receives the first voice comment from the server.

9. In paragraph 8, The step of the above communication unit receiving the first voice message is It further includes a step of receiving output time information required to output the first voice comment, A method for providing a user adaptive interface, wherein the display step further includes a step of controlling the interface unit using the output time information so that the control unit displays the output progress status.

10. A step in which the server control unit of the server separates the first voice comment into two or more parts; A step in which the server communication unit of the above server transmits the two or more separated parts to a voice control device; A part output step in which the voice output unit of the voice control device outputs the output target part in order among the two or more parts; A display step in which the control unit of the voice control device displays the output progress of the first voice comment on the interface unit of the voice control device simultaneously with the output of the output target part or at a point in time before or after the output of the output target part; and A method for providing a user adaptive interface, wherein the control unit controls the voice output unit and the interface unit to repeat the part output step and the display step for each part among the remaining parts according to the order of each part after outputting the output target part.

11. In paragraph 10, The above display steps are A method for providing a user adaptive interface, wherein the interface unit further includes a step of displaying the length of the remaining time required to output the remaining part after the output target part among the first voice comments.

12. In paragraph 10, A method for providing a user adaptive interface, wherein the part output step further includes a step in which the control unit increases or decreases the output speed of the output target part or the first voice comment using the user's tendency information.

13. In paragraph 10, Before the above separation step, A method for providing a user adaptive interface, wherein the server control unit further includes a step of selecting the first voice comment from among the first voice comment and the second voice comment using the user's preference information.

14. In paragraph 13, A method for providing a user-adaptive interface, wherein the first voice comment and the second voice comment differ in the number of characters to be voiced.

15. In paragraph 10, The communication unit of the voice control device includes a step of receiving a user detection message from a first home appliance that has detected a user, The above display steps are A method for providing a user adaptive interface, further comprising a step of the communication unit transmitting an output progress message to the first home appliance or the second home appliance so that the interface unit of the first home appliance or the second home appliance located adjacent to the first home appliance displays the output progress, and the interface unit of the first home appliance or the second home appliance displays the output progress.

16. In paragraph 10, Before the above separation step A step in which the voice input unit of the voice control device receives a user's voice input, converts it into a question text, and transmits the question text to the server; The server control unit selects a chatbot that will provide an answer to the question text using the user's preference information; The above server communication unit transmits the question text to the selected chatbot and then receives a response message; and A method for providing a user adaptive interface, wherein the server control unit further comprises a step of converting the response message into the first voice comment.

17. In paragraph 10, Before the above separation step A step in which the server control unit of the above server generates a first voice comment to be transmitted to the voice control device; and A method for providing a user adaptive interface, comprising a step in which a server communication unit of the server transmits the first voice comment to the voice control device and the communication unit of the voice control device receives the first voice comment from the server.

18. In paragraph 17, The step of the above communication unit receiving the first voice message is It further includes a step of receiving output time information required to output the first voice comment from the server, A method for providing a user adaptive interface, wherein the display step further includes a step of controlling the interface unit using the output time information so that the control unit displays the output progress status.

19. In a voice control device that provides voice recognition and voice comments, After the control unit of the voice control device separates the first voice comment into two or more parts, the voice output unit of the voice control device performs a part output process of outputting the output target part in order among the two or more parts. The control unit performs a display process for displaying the output progress of the first voice comment on the interface unit of the voice control device at the same time as the output of the output target part or at a point in time before or after the output of the output target part. A voice control device providing a user adaptive interface, wherein the control unit controls the voice output unit and the interface unit to repeat the part output process and the display process for each part among the remaining parts according to the order of each part after outputting the output target part.

20. In paragraph 19, In the above display process A voice control device providing a user adaptive interface, wherein the interface unit displays the length of the remaining time required to output the remaining part after the output target part among the first voice comments.

21. In paragraph 19, In the above part output process A voice control device providing a user adaptive interface, wherein the control unit increases or decreases the output speed of the output target part or the first voice comment using the user's preference information.

22. In paragraph 19, A voice control device providing a user adaptive interface, wherein the control unit selects the first voice comment from among the first voice comment and the second voice comment using the user's preference information and then separates the first voice comment into two or more parts.

23. In paragraph 22, A voice control device providing a user-adaptive interface, wherein the first voice comment and the second voice comment are different in the number of characters to be voiced.

24. In paragraph 19, The communication unit of the above voice control device receives a user detection message from the first home appliance that detects the user, In the above display process A voice control device providing a user-adaptive interface, wherein the communication unit transmits an output progress message to the first home appliance or the second home appliance so that the interface unit of the first home appliance or the second home appliance located adjacent to the first home appliance displays the output progress, and the interface unit of the first home appliance or the second home appliance displays the output progress.

25. In paragraph 19, The voice input unit of the voice control device receives the user's voice input and converts it into a question text, and the control unit selects a chatbot that will provide an answer to the question text using the user's tendency information. A voice control device providing a user adaptive interface, wherein the communication unit of the voice control device transmits the question text to the selected chatbot and then receives a response message, and the control unit converts the response message into the first voice comment and then separates the first voice comment into two or more parts.

26. In paragraph 19, A voice control device providing a user adaptive interface, wherein the communication unit of the voice control device receives the first voice comment from the server that generated the first voice comment.

27. In paragraph 26, The above communication unit receives output time information required to output the first voice comment from the server, In the above display process A voice control device providing a user adaptive interface, wherein the control unit controls the interface unit using the output time information so that the interface unit displays the output progress status.

Images