KR102315020B1 - Apparatus and method for providing customized voice interaction based on user life pattern - Google Patents

Abstract

The present invention relates to a device and method for providing a customized voice conversation based on a user life pattern, wherein the device for providing the customized voice conversations based on the user life pattern comprises: a user life pattern processing part that generates the user life pattern based on an object contact behavior; a user situation determination part that recognizes a current user situation based on an environment context; an utterance message determining part that utters through a speaker by determining an utterance message of a conversation content for the user behavior recommendation according to the user situation based on the user life pattern; and a feedback processing part that feedbacks a user reaction for the utterance message to the utterance message determining part to provide a contextual voice conversation. Therefore, the present invention is capable of allowing the behavior of the user to be facilitated through a user customized voice conversation appropriate to the situation.

Description

Apparatus and method for providing customized voice conversation based on user's life pattern

The present invention relates to a technology for providing customized voice conversation based on a user's life pattern, and more particularly, to a customized voice conversation based on a user's life pattern that can promote a user's behavior through a user-customized voice conversation suitable for a situation based on the user's life pattern It relates to an apparatus and method for providing voice conversation.

Recently, as interest in user interfaces increases and voice processing technology develops, IT devices having a built-in voice recognition function are increasing. For example, smartphones, smart watches, smart TVs, smart refrigerators, etc. that can perform an operation requested by a user by recognizing a user's voice are widely used.

In addition, artificial intelligence (AI) speakers capable of simple conversations are being developed. Such an artificial intelligence speaker refers to a speaker device that recognizes a user's voice, understands the user's command, and responds according to the corresponding command.

Artificial intelligence (AI) speakers are applied to various living areas to improve the quality of life, and in particular, the elderly care service function is being installed to increase the usability.

However, until now, the artificial intelligence (AI) speaker is activated only when the user calls a predetermined trigger word, that is, a name assigned to each speaker before starting a voice input. Users can deliver their requests or start conversations only after the artificial intelligence speaker is activated, and since only conversations in the form of responding to the user's questions are possible without recognizing the user's situation, it is necessary to perform the elderly care service function. there is a limit

Korean Patent No. 10-2053534 (2019.12.02) relates to a method of providing elderly care using an artificial intelligence speaker, which diagnoses and prevents diseases such as depression through the artificial intelligence speaker, and informs facility information based on location, A technology for providing information to a user before the user asks a question according to a predetermined time based on the collected information is disclosed.

Korean Patent Registration No. 10-2053534 (2019.12.02)

An embodiment of the present invention is to provide an apparatus and method for providing a customized voice conversation based on a user's life pattern, which can promote a user's behavior through a user-customized voice conversation suitable for a situation based on the user's life pattern.

An embodiment of the present invention recognizes the user's time-series situation based on the user's life pattern and automatically utters a voice message suitable for the situation, so that the user's life pattern-based customized voice conversation can be exchanged in a contextual conversation with the user. It is intended to provide a providing apparatus and method.

An embodiment of the present invention attaches a tag to a user's object, creates a user's life pattern through an object contact action, recommends an appropriate action according to the pattern, and provides direct value to the user. An object of the present invention is to provide an apparatus and method for providing voice conversation.

In embodiments, the apparatus for providing a customized voice conversation based on a user's life pattern includes a user life pattern processing unit generating a user life pattern based on an object contact behavior, a user situation determining unit recognizing a current user's situation based on an environment context, and the An utterance message determiner uttering through a speaker by determining an utterance message of the conversation content for the user action recommendation according to the user situation based on a user life pattern, and feedbacks a user reaction to the uttered message to the utterance message determiner and a feedback processing unit for providing a contextual voice conversation.

The user life pattern processing unit receives the object identification information provided by itself from the object or from the object tag attached to the object in the process of contacting the object, and receives the user's meal pattern, medication pattern, viewing pattern, exercise pattern, and posture pattern. , a life pattern including at least one of an outing pattern, a bowel movement, and a bedtime activity pattern may be generated.

The user context determiner may determine the user's context based on an environment context including at least one of location, time, season, temperature, weather, and illuminance.

The utterance message determining unit may determine whether to automatically utter a message according to a message operation schedule, and dynamically determine a message type according to a current user situation during automatic utterance.

The utterance message determining unit determines at least one of name, weather, number of steps, wake-up time, bedtime, sleep time, event time, contact object type, contact action type, posture, location, meal and daily life behavior of the utterance message dynamically. It can be included as a variable.

The utterance message determiner may build a user behavior recommendation model for improving the user's pattern situation through learning based on the user's life pattern and situation, and may update the user behavior recommendation model through user response feedback.

The feedback processing unit may analyze whether a recommended action is accepted and a mood based on the user's response voice after the spoken message is uttered, and feedback the user response to the uttered message determining unit.

Among the embodiments, the method for providing a customized voice conversation based on a user life pattern includes generating a user life pattern based on an object contact action, recognizing the current user's situation based on an environment context, and based on the user life pattern and determining an utterance message of the conversation content for the user action recommendation according to the user situation and uttering it through a speaker, and feeding back a user reaction to the utterance message.

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be construed as being limited thereby.

The apparatus and method for providing a customized voice conversation based on a user's life pattern according to an embodiment of the present invention can promote a user's action through a user's customized voice conversation suitable for a situation based on the user's life pattern.

An apparatus and method for providing a customized voice conversation based on a user's life pattern according to an embodiment of the present invention recognizes the user's time-series situation based on the user's life pattern and automatically utters a voice message suitable for the situation in context with the user. can have a conversation.

An apparatus and method for providing a customized voice conversation based on a user's life pattern according to an embodiment of the present invention attaches a tag to a user's object, creates a user's life pattern through an object contact action, and recommends an appropriate action according to the pattern. can provide direct value to

Therefore, the present invention recognizes situations according to each user's individual life pattern, can automatically utter at the optimal timing, and can recommend and suggest actions suitable for the user, thereby improving the user's life, which can be viewed from the elderly's point of view. available for care services, etc.

1 is a view for explaining a system for providing a customized voice conversation based on a user's life pattern according to the present invention.
FIG. 2 is a block diagram illustrating a physical configuration of the apparatus for providing a customized voice conversation of FIG. 1 .
FIG. 3 is a block diagram illustrating a functional configuration of the apparatus for providing a customized voice conversation of FIG. 1 .
FIG. 4 is a flowchart illustrating a process of providing a customized voice conversation based on a user's life pattern performed by the apparatus for providing a customized voice conversation of FIG. 1 .
5 is an exemplary diagram illustrating a message operation schedule according to an embodiment.
6 is an exemplary diagram illustrating the provision of a customized voice conversation according to an embodiment.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected” to another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, “between” and “immediately between” or “neighboring to” and “directly adjacent to”, etc., should be interpreted similarly.

The singular expression is to be understood to include the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

Identifiers (eg, a, b, c, etc.) in each step are used for convenience of description, and the identification code does not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer-readable codes on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in a network-connected computer system, and the computer-readable code may be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms defined in general used in the dictionary should be interpreted as being consistent with the meaning in the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining a system for providing a customized voice conversation based on a user's life pattern according to the present invention.

Referring to FIG. 1 , a system 100 for providing a customized voice conversation based on a user's life pattern may include a plurality of objects 110 to be touched, a customized voice conversation providing device 130 , and a database 150 .

Tags 110a, ..., 110b may be attached to each of the plurality of objects 110 . Each of the object tags 110a, ... 110b may store additional information together with a unique number for identifying the corresponding object. Here, the additional information may mean a service profile including at least one service content for each available condition that the thing can provide to the user. Accordingly, it is possible to provide meaningful service content to the user at the moment of contact with the corresponding object. Here, the object tags 110a, ..., 110b in the object 110 may include a human body communication module or a short-range communication module. Short-range communication may be based on radio frequency identification (RFID) or near frequency communication (NFC). The object tags 110a, ... 110b may be implemented in a form that can be attached to an object, and may be implemented in the same form as a conventional RFID or NFC sticker label.

The object tags 110a, ... 110b can be attached to various objects such as refrigerators, microwave ovens, water purifiers, faucets, medicine bottles, TV remote controls, toilet bowls, washbasins, etc. can be transmitted via In an embodiment, the object tags 110a, ..., 110b may be connected to the customized voice conversation providing apparatus 130 through human body communication. In one embodiment, the object tags 110a, ... 110b can wake up through the user's object contact and are connected to the customized voice conversation providing device 130 through human body communication or a wireless communication network such as RFID, NFC, Bluetooth, WiFi, etc. data can be exchanged.

In an embodiment, the object 110 may store its own identification information and transmit identification information when a user's contact is detected.

The customized voice conversation providing device 130 may correspond to a computing device capable of facilitating a user's actions through a user's customized voice conversation suitable for a situation based on a user's life pattern, and may be implemented with a smartphone, a laptop computer, or a computer. In addition, the present invention is not necessarily limited thereto and may be implemented in various devices. In one embodiment, the customized voice conversation providing apparatus 130 may be implemented as a wearable device in the form of a smart watch that can be connected to at least one object tag 110a, ... 110b through human body communication, but is not necessarily limited thereto. It may be implemented in various forms that can be worn or attached to the user's body. In an embodiment, the customized voice conversation providing apparatus 130 may be an electronic device equipped with a speaker function that can be connected to at least one object tag 110a, ..., 110b through wireless communication. Here, the customized voice conversation providing apparatus 130 may be implemented in various forms according to a network connection method with the object tags 110a, ..., 110b.

The customized voice conversation providing apparatus 130 may include a reader module that enables data transmission/reception through human body communication with the object tags 110a, ..., 110b. In an embodiment, the customized voice conversation providing apparatus 130 may recognize the user's time-series situation based on the user's life pattern and automatically utter a voice message suitable for the situation to exchange a contextual conversation with the user. Here, the customized voice conversation providing apparatus 130 may be connected to the object tags 110a, ..., 110b through human body communication, and may exchange data with the object tags 110a, ..., 110b through a network. The customized voice conversation providing apparatus 130 is not limited to receiving the identification information of the corresponding object from the object tags 110a, ..., 110b, and when the identification information is stored in the object 110 itself, the user's contact object 110 Identification information may be received.

In an embodiment, the apparatus 130 for providing a customized voice conversation may store data necessary for providing a customized voice conversation in conjunction with the database 150 . Meanwhile, the customized voice conversation providing apparatus 130 may be implemented by including the database 150 therein, unlike FIG. 1 .

The database 150 may correspond to a storage device for storing various types of information required in a process of providing a customized voice conversation according to a user's life pattern. The database 150 may store information about a message operation schedule, and may store information about a situation for each message type, but is not limited thereto, and the customized voice conversation providing apparatus 130 provides a customized voice according to a user's life pattern. In the process of providing a conversation, information collected or processed in various forms may be stored.

FIG. 2 is a block diagram illustrating a physical configuration of the apparatus for providing a customized voice conversation of FIG. 1 .

Referring to FIG. 2 , the customized voice conversation providing apparatus 130 may be implemented including a processor 210 , a memory 230 , a user input/output unit 250 , and a network input/output unit 270 .

The processor 210 may execute a procedure for processing each step in the process in which the customized voice conversation providing apparatus 130 operates, and manage the memory 230 that is read or written throughout the process, the memory A synchronization time between the volatile memory and the non-volatile memory in 230 may be scheduled. The processor 210 may control the overall operation of the customized voice conversation providing apparatus 130 , and is electrically connected to the memory 230 , the user input/output unit 250 , and the network input/output unit 270 to control the flow of data therebetween. can be controlled The processor 210 may be implemented as a central processing unit (CPU) of the apparatus 130 for providing a customized voice conversation.

The memory 230 is implemented as a non-volatile memory, such as a solid state drive (SSD) or a hard disk drive (HDD), and may include an auxiliary storage device used to store overall data required for the customized voice conversation providing device 130 . and may include a main memory implemented as a volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving a user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 includes an input device including an adapter such as a button, a touch pad, a touch screen, an on-screen keyboard, a microphone, or a pointing device, and an output device including an adapter such as a monitor or a touch screen and a speaker. may include In an embodiment, the user input/output unit 250 may correspond to a computing device accessed through a remote connection, and in such a case, the customized voice conversation providing device 130 may be performed as a server.

The network input/output unit 270 includes an environment for connecting with an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN (Wide Area Network) (VAN). It may include an adapter for communication such as Value Added Network).

FIG. 3 is a block diagram illustrating a functional configuration of the apparatus for providing a customized voice conversation of FIG. 1 .

Referring to FIG. 3 , the customized voice conversation providing apparatus 130 includes a user life pattern processing unit 310 , a user situation determining unit 330 , an utterance message determining unit 350 , a feedback processing unit 370 , and a control unit 390 . may include

The user life pattern processing unit 310 conducts information including identification data for the object from the object 110 that the user has contacted using human body communication or from the object tags 110a, ..., 110b attached to the object 110 . can receive In one embodiment, the user life pattern processing unit 310 may generate the user's life pattern according to the user's contact action of the object 110 from the received object identification data for each time zone. Here, the user's life pattern processing unit 310 may know from the object identification data in which space the user was and what purpose he or she intends to perform. For example, the user's life pattern processing unit 310 may generate the user's cooking order pattern from the contact action of the object 110 such as a refrigerator, a microwave oven, a gas stove, a cooking table, and a sink placed in the user's kitchen. The user life pattern processing unit 310 collects object identification data from the object 110 or the object tags 110a, ..., 110b attached to the object 110 whenever the user touches the object 110, and the user life patterns can be created. A user's life pattern may include a meal pattern, medication pattern, viewing pattern, exercise pattern, posture pattern, outing pattern, daily change, activity pattern, etc. A variety of patterns may be included.

In an embodiment, the user life pattern processing unit 310 may generate a meal pattern including a meal time, a duration time, a meal interval, and whether or not to eat breakfast during the day through reception of identification data of an object placed in the kitchen. The user life pattern processing unit 310 may generate a medication pattern including the number and time of medication from the medication action information of the user who contacts the medication bottle and cup. The user life pattern processing unit 310 may generate a viewing pattern including the number of TV viewings and night viewing, etc. from the behavior information of the user contacting the remote control. The user's life pattern processing unit 310 performs an exercise pattern including the number of steps, stride length, walking speed, exercise intensity, etc., posture patterns such as lying down and sitting, the number of times of going out, interval, and duration through behavior information according to the user's contact with objects. It is possible to create an outing pattern including the like, and an activity pattern including waking up, going to bed, and spatial mobility.

The user context determiner 330 may collect an environment context by itself or through wireless communication, and determine the user's context based on the collected environment context. Here, the environment context may include at least one of location, time, season, temperature, weather, and illuminance. In one embodiment, when the user is in a specific service area based on the current user's location and time, the user context determining unit 330 may include physical activity, outing activity, eating activity, medication activity, and bowel activity based on the environment context. It is possible to estimate the user's behavioral situation such as sleep activity and sleeping activity and its purpose.

The spoken message determining unit 350 may include a speaker to determine an uttered message suitable for the current user's situation based on the user's life pattern, and to utter the determined uttered message through the speaker. Here, the speaker may be provided in the customized voice conversation providing device 130 or as a separate device wirelessly connected to the customized voice conversation providing device 130 . In an embodiment, the speech message determining unit 350 may determine whether the speaker is automatically uttered according to a message operation schedule, and may dynamically determine the message type according to the current user's situation when the speaker is automatically uttered. Here, the uttered message determining unit 350 may automatically ignite the speaker according to a message operation schedule in which message types are set for each time zone from the first contact with an object after waking up.

The spoken message determining unit 350 may dynamically determine the type of the spoken message according to the current user's situation when automatically uttering according to the message operation schedule. Here, the dynamic variables of the speech message include name, weather, number of steps, wake up time, bedtime, sleep time, event time (eg, meal, medication, toilet, homecoming, etc.), contact object type, contact action type, These may include posture, position, diet, and activities of daily living. As shown in Table 1 below, the spoken message determining unit 350 may define a situation for each message type.

Kinds Target hour situation T type full, gender slot Settings by tag Type A Target selection
(total, gender, individual) time zone designation after waking up
Exercise promotion, nanny quiz, etc.
action
alarm
Target selection
(total, gender, individual)
time zone designation homecoming
Meals (breakfast, lunch and dinner)
Toilet (regular, early morning)
watching TV
Alarm by condition
Target selection
(individual)
time zone designation Exercise promotion by condition
Sleep promotion by condition
Food promotion by condition
Medication promotion by condition

In an embodiment, the spoken message determining unit 350 may determine the content of a conversation for facilitating the user's action, and may determine the vocabulary and tone for forming a voice corresponding to the conversation, respectively. Here, the spoken message determiner 350 may build a user behavior recommendation model through learning based on the user's life pattern and current situation, and may update the user behavior recommendation model through user reaction feedback. The determination unit 350 may automatically utter the conversation content suitable for the context according to the user's life pattern and current situation, thereby facilitating the user's action without giving the user objection. The spoken message determining unit 350 may receive a user response to the spoken message as feedback through the feedback processing unit 370 to conduct a contextual conversation.

In an embodiment, the utterance message determiner 350 determines the uttered message based on the user's life pattern and context information, but the present invention is not limited thereto, and the uttered message may also be determined in consideration of user information in addition thereto. To this end, user information including data on at least one of a user's name, gender, age, health-related numerical value, and disease history may be collected to dynamically determine a message to be uttered. Here, the spoken message is outputted by voice through the speaker, but is not limited thereto and may be displayed on the screen.

The feedback processing unit 370 may determine the user's mood through the user's voice analysis during the voice conversation with the user, and may determine whether the user is accepted according to the user's behavior recommendation. The feedback processing unit 370 may include a microphone for inputting a user's voice. The feedback processing unit 370 feeds back the user's mood and behavior acceptance to the speech message determination unit 350 so that it can be reflected in the conversation content. In an embodiment, the feedback processing unit 370 may classify acceptance, non-acceptance, and do not know based on the user's response voice after the user action recommendation, and feedback whether acceptance or not to the spoken message determination unit 350 . The feedback processing unit 370 may also analyze the user's response voice to identify three types of moods of positive, negative, and unknown, and feed it back to the utterance message determination unit 350 .

The control unit 390 controls the overall operation of the customized voice conversation providing apparatus 130 , and is performed between the user life pattern processing unit 310 , the user situation determination unit 330 , the spoken message determination unit 350 , and the feedback processing unit 370 . Control flow and data flow can be managed.

FIG. 4 is a flowchart illustrating a process of providing a customized voice conversation based on a user's life pattern performed by the apparatus for providing a customized voice conversation of FIG. 1 .

Referring to FIG. 4 , the customized voice conversation providing apparatus 130 receives behavior information including identification information for the object from the object the user has contacted through the user's life pattern processing unit 310 and receives the user's life. A pattern may be generated (step S410). The customized voice conversation providing apparatus 130 may recognize the current user's situation based on the environment context through the user situation determining unit 330 (step S430).

Also, the customized voice conversation providing apparatus 130 may determine an uttered message according to the current user situation based on the user's life pattern through the uttered message determiner 350 and utter it through the speaker (step S450).

In an embodiment, the utterance message determiner 350 may determine whether or not to automatically utter the speaker based on the user's life pattern and the current user's situation. The utterance message determiner 350 may determine automatic utterance of the speaker based on the user's object contact and message operation schedule. When the automatic speech of the speaker is determined, the speech message determining unit 350 determines a speech message with content appropriate to the current user's situation based on the user's life pattern and user situation, and processes the determined speech message to be uttered through the speaker. . The uttered message determiner 350 may determine the uttered message to improve the user's life for each situation. For example, by sending an utterance message to the situation that needs improvement in the user's life pattern, such as few steps, late watching TV, skipping breakfast, eating convenience food, irregular meal times, accumulating dishes, late eating, early morning toilet, etc. can lead to behavioral improvement.

In addition, the customized voice conversation providing apparatus 130 may provide a contextual voice conversation by feeding back the user's reaction after sending the spoken message through the feedback processing unit 370 and reflecting it in the conversation content of the message (step S470).

5 is an exemplary diagram illustrating a message operation schedule according to an embodiment.

In FIG. 5 , the customized voice conversation providing apparatus 130 may provide a customized voice conversation suitable for a situation to the user by setting an uttered message corresponding to a situation for each time zone as a message operation schedule. The customized voice conversation providing apparatus 130 may designate a time zone and set up a message to be sent in relation to contact with the object 110 or to promote an action according to a situation.

6 is an exemplary diagram illustrating the provision of a customized voice conversation according to an embodiment.

In FIG. 6 , the customized voice conversation providing apparatus 130 may determine the conversation content in consideration of the current user's situation along with the user's life pattern and automatically utter it through a speaker to provide the voice conversation. The user's life pattern may be generated based on the user's object contact behavior. The user context may be recognized based on the environment context. For example, if the user performs the 'first touch after waking up' action, on a day when the amount of exercise is insufficient and the weather is cool, “You are not getting enough exercise these days! The weather is cool, how about taking a walk?” message may be uttered. The customized voice conversation providing apparatus 130 may provide an immediate feedback on the user's reaction after the message is uttered. The customized voice conversation providing apparatus 130 may provide feedback by identifying acceptance and mood through the user's voice analysis. For example, if a user asks, “Would you like to go out and come back?” If you answered, “After all, Grandpa likes cool days!” A feedback message may be uttered.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: A system for providing customized voice conversations based on user life patterns
110: object 110a, . . . ,110b: Thing tag
130: customized voice conversation providing device 150: database
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: user life pattern processing unit 330: user situation determination unit
350: speech message determination unit 370: feedback processing unit
390: control unit

Claims (8)

In the process of contacting an object, the user's meal pattern, medication pattern, viewing pattern, exercise pattern, posture pattern, outing pattern, and daily change by receiving object identification information provided by the object itself or from an object tag attached to the object , a user life pattern processing unit that generates a user life pattern including at least one personalized pattern of defecation and bedtime activity patterns for each time period;
a user context determiner configured to determine a current user's situation based on an environment context including at least one of a current user's location and time, season, temperature, weather, and illuminance;
Based on the user life pattern, an utterance message of the conversation content for facilitating user behavior according to the user situation is determined based on the user's life pattern, and the vocabulary and tone for forming a voice corresponding to the conversation content are determined respectively, and the conversation content is uttered through the speaker. an utterance message determining unit for inducing behavioral improvement; and
A feedback processing unit for providing a contextual voice conversation by feeding back whether or not the user's action with respect to the spoken message is accepted to the spoken message determining unit,
The spoken message determining unit
After waking up, it determines whether to automatically ignite according to the message operation schedule in which the message type is set for each time zone, starting from the first contact after waking up, and dynamically determines the message type according to the current user situation when auto-igniting,
Including at least one of name, weather, number of steps, wake up time, bedtime, sleep time, event time, contact object type, contact action type, posture, location, meal and daily life behavior as a dynamic variable of the utterance message,
Custom voice based on user life pattern, characterized in that building a user behavior recommendation model for improving the pattern situation of the user through learning based on the user life pattern and situation, and updating the user behavior recommendation model through user reaction feedback Conversational device.
delete delete delete delete delete The method of claim 1, wherein the feedback processing unit
After uttering the utterance message, the user's life pattern-based customized voice conversation providing apparatus, characterized in that the user's response feedback is fed back to the uttered message determining unit by analyzing whether the recommended action is accepted and the mood based on the user's response voice.
delete

Images