KR20180046550A - Apparatus and method for conversaion using artificial intelligence - Google Patents

Abstract

The present invention relates to a dialogue device using artificial intelligence and a method thereof. According to an embodiment of the present invention, the dialogue device using artificial intelligence comprises: a storage unit for storing a script signal by signaling a keyword; a reception unit for recognizing voice of a user; a first conversion unit for signaling the voice received from the receiving unit to convert the same into a voice signal; a determination unit for determining user information from the received voice or converted voice signal; a signal extraction unit for extracting the script signal corresponding to the voice signal; a second conversion unit for converting the script signal extracted from the signal extraction unit into a voice; and a sound unit for transmitting the voice converted by the second conversion unit. The signal extraction unit extracts the script signal corresponding to the voice signal by an artificial intelligence module. The artificial intelligence module analyzes the script signal converted by the first conversion unit to analyze the meaning of received voice information, and extracts a script signal pre-stored in the storage unit in accordance with a preset dialogue model. The dialog model includes a dialogue flow tree corresponding to a dialogue meaning and a dialogue order.

Description

[0001] APPARATUS AND METHOD FOR CONVERSION USING ARTIFICIAL INTELLIGENCE [0002]

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to an interactive apparatus and method using artificial intelligence, and more particularly, to an artificial intelligent interactive apparatus and method using speech recognition.

Speech Recognition refers to the ability of a machine to understand the daily voice of humans and perform tasks according to the understood voice.

The technology of speech recognition is leading to the development of devices composed of a system that can easily obtain information from a remote place and operate according to voice due to development of computer and information communication.

Various speech recognition application systems have been developed based on the speech recognition technology, and one of them is a system for guiding desired information according to a user's spoken language. For example, supposing that there is a telephone number guidance system of a certain group, a system in which a telephone number of a corresponding department is displayed on a monitor of a user when the user speaks the name of the department to be searched by voice.

In this way, conventional speech recognition systems have unilaterally accepted a human voice unilaterally, and have remained in a one-way system that processes the request according to human voice. In addition, systems that interact with humans in a bidirectional manner through dialogue with each other are inadequate in technology, although the necessity is increasing day by day.

On the other hand, as the number of single-person households has increased recently, the number of people living alone has increased, and there is not enough people to share and communicate with each other. Therefore, the necessity of a conversation apparatus or a conversation system capable of interactive conversation as a human conversation partner is increasing day by day. However, the conventional system does not fully understand or learn human conversation, so there is a problem that conversation is limited. Especially, in the case of the social marginalized people, although the necessity of conversation partner is greater, there are not enough devices or systems capable of communicating with human beings. In addition, not only marginalized people but also human beings have different personality and tendencies for each individual such as age, sex, personality, and interest, and there is a demand for a system capable of customized conversation according to the personality of each individual.

In addition, the security and security need is strengthened in one-person households, and a variety of security systems are being developed, but nowadays there is no safety or security system that is interlocked with artificial intelligence and voice recognition device .

The present invention is intended to provide a dialogue apparatus and method using artificial intelligence capable of interacting with human beings.

The present invention also provides a communication apparatus and method using artificial intelligence including security and security functions.

The objects of the present invention are not limited thereto, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

The present invention provides a communication device using artificial intelligence.

According to an embodiment of the present invention, there is provided a storage medium for storing a script signal for signaling a keyword; A receiving unit for recognizing the user's voice; A first converting unit for converting a voice received from the receiving unit into a voice signal; A determination unit for determining user information from the received voice or the converted voice signal; A signal extracting unit for extracting a script signal corresponding to the voice signal; A second conversion unit for converting the script signal extracted from the signal extraction unit into speech; And the sound extracting unit extracts a script signal corresponding to the voice signal by the artificial intelligence module, and the artificial intelligence module extracts a script signal corresponding to the voice signal from the first conversion unit Analyzing the converted script signal, analyzing the meaning of the received speech information, extracting a script signal pre-stored in the storage unit according to a predetermined dialogue model, the dialogue model including a dialogue meaning and a dialogue flow corresponding to the dialogue order Tree.

According to one embodiment, the artificial intelligence module accumulates and stores voice information of a user to be received, analyzes data on the user from the stored voice information, and transmits the conversation based on the analyzed user- Change the flow tree.

According to an embodiment, the artificial intelligence module analyzes state information of a user by analyzing the received user voice, extracts a corresponding script signal from the detected state information, The user's state information includes at least one of emotion, age, and gender of the user.

According to an embodiment, the sound unit transmits a danger signal when an unregistered user's voice is received by the receiving unit continuously for a predetermined time.

According to one embodiment, there is provided a portable terminal comprising: a housing constituting a main body; An illumination unit for emitting light to the outside; A jetting portion for jetting liquid to the outside; A display unit for displaying predetermined information; Wherein the illumination unit is provided in a mood or the like, and the injection unit includes a sprayer for spraying water and a diffuser for spraying perfume, wherein the control unit controls the sprayer unit And a controller for controlling the power of the illuminating unit and the jetting unit to be turned on and off when a preset keyword among the received voice is included, wherein the sound unit is capable of supporting multi-lingual voice, And transmits the sound corresponding to the signal, and the predetermined information displayed on the display unit is information of a user that emits a sound to the receiving unit or information received by a communication network.

The present invention provides a dialogue method using artificial intelligence.

According to an embodiment of the present invention, there is provided a method of generating a script, the method comprising: storing a keyword as a script signal; A receiving step of receiving a user's voice; A first conversion step of converting the received voice signal into a voice signal; A discriminating step of discriminating the user's information from the voice received in the receiving step or the voice signal converted in the first converting step; A signal extracting step of extracting a script signal corresponding to the voice signal; A second conversion step of converting the extracted script signal into speech; And analyzing the meaning of the received voice information by analyzing the script signal converted in the first conversion step by the artificial intelligence, Extracting a script signal stored in the storing step according to a dialogue model, wherein the dialogue model comprises a dialogue flow tree corresponding to a dialogue meaning and a dialogue order, and the determining step analyzes the user's speech In the sound transmission step, a voice having a preset frequency and size is transmitted according to the status information of the user. In the signal extracting step, the voice information of the user to be received is accumulated and stored, , And the interactive flow tree is changed by artificial intelligence based on the analyzed data The.

According to one embodiment, in the signal extracting step, the script signal is extracted by artificial intelligence according to a user of a predetermined layer, and the specific layer includes at least one of sex, age, and occupation.

According to an embodiment of the present invention, bi-directional communication with a human is possible using artificial intelligence.

In addition, according to an embodiment of the present invention, security and security of a user can be secured through artificial intelligence and speech recognition.

The effects of the present invention are not limited to the above-mentioned effects, and the effects not mentioned can be clearly understood by those skilled in the art from the present specification and attached drawings.

1 is a block diagram briefly showing a configuration of an interactive apparatus using artificial intelligence according to the present invention.
2 is a block diagram showing the configuration of the communication unit.
3 is a block diagram briefly showing the operation principle of the signal extracting unit.
4 is a block diagram showing the configuration of the functional unit.
FIG. 5 is a perspective view showing an interactive apparatus using artificial intelligence according to the present invention.
FIG. 6 is a flowchart sequentially illustrating an artificial intelligence dialogue method according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The embodiments of the present invention can be modified in various forms, and the scope of the present invention should not be construed as being limited to the following embodiments. This embodiment is provided to more fully describe the present invention to those skilled in the art. The shape of the elements in the figures is therefore exaggerated to emphasize a clearer description.

Hereinafter, an example of the present invention will be described in detail with reference to FIGS. 1 to 6. FIG.

1 is a block diagram briefly showing a configuration of an interactive apparatus using artificial intelligence according to the present invention. FIG. 2 is a block diagram showing the configuration of the communication unit, FIG. 3 is a block diagram briefly showing the operation principle of the signal extraction unit 160, FIG. 4 is a block diagram showing the configuration of the functional unit 200, 5 is a perspective view showing a talking apparatus using artificial intelligence according to the present invention.

Referring to FIGS. 1 to 5, an artificial intelligence interactive apparatus 1 according to the present invention includes a communication unit 100 and a functional unit 200.

The communication unit 100 recognizes the voice of the user, that is, the user, and sends out an appropriate answer to the user's voice through the AI. That is, the communication unit 100 enables communication with the human being.

The communication unit 100 includes a storage unit 110, a reception unit 120, a first conversion unit 130, a determination unit 140, a data recording unit 150, a signal extraction unit 160, a second conversion unit 170 And an acoustic portion 180, as shown in FIG.

The storage unit 110 stores a keyword as a script signal. The keyword refers to a word transmitted through the acoustic unit 180 described later. Keywords may be provided in multiple languages. The keywords of the languages of various countries are signaled and stored.

The receiving unit 120 receives and recognizes the human, that is, the voice of the user. When the user speaks, they accept it.

The first conversion unit 130 converts the voice received from the receiving unit 120 into a voice signal.

The determining unit 140 can determine the user's information from the voice received from the receiving unit 120 or the voice signal converted by the first converting unit 130. [ For example, the determination unit 140 may determine the status information of the user. The status information means information that can indicate the current status of the user. The user's current emotional state, age, sex, and the like. Emotional state means emotional state that human can have such as joy, sadness, depression, and guidance. In order to determine the emotional state, the size of the voice and the frequency of the voice signal can be considered. For example, if the reference range is set to the size of the voice and the range is larger than the size of the reference value based on the range, it can be recognized as an excited state such as joy, sadness or angryness. Alternatively, if it is lower than the size of the preset value, it can be recognized as a state of difference, depression, and the like.

Further, if the frequency of the voice signal is higher than the preset value, it means a high sound, so that it can be recognized as an excited state such as joy or angry. If the frequency of the voice signal is lower than the preset value, it means low sound, so it can be recognized as a state of difference, depression, and the like.

In addition, a setting criterion regarding the difference of voice by sex and the difference of voice by age can be input, and the sex and age of the user can be determined based on the setting criterion. For example, the maximum and minimum frequencies of the voice signal converted by the first conversion unit 130 may be determined, and it may be determined whether the voice signal is within a preset frequency range to determine the sex of the user. For example, it is possible to set a criterion relating to a voice signal frequency of a male user and a voice signal frequency of a female user, determine whether the frequency of the voice signal received by the user is within the range, have. In addition, considering the fact that the user is older and the sound is generally slow, the user can grasp the age of the user by grasping the period of the voice signal of the user.

The determination unit 140 may determine whether the user is a previously registered user or an unregistered user. The user's voice information is input, and the inputted voice information is compared with the received voice information to compare the pattern, frequency, and period of the voice to check whether they are within the error range, It is possible to determine whether or not the user is an unregistered user.

The data recording unit 150 can record and store a conversation with a user. The user may be a registered user. The data recording unit 150 accumulates the information about the user by storing the conversation with the user, and the AI module 162 can change the conversation flow tree based on the accumulated conversation record to proceed with the subsequent conversation .

3 is a block diagram briefly showing the operation principle of the signal extracting unit 160. As shown in FIG.

The signal extracting unit 160 extracts a script signal corresponding to the voice signal and transmits the extracted script signal to the second converting unit 170, which will be described later. The signal extracting unit 160 is provided in a configuration that plays an essential role in enabling conversation to proceed between a person and the conversation apparatus 1 using the artificial intelligence according to the present invention.

Referring to FIG. 3, the signal extraction unit 160 is operated by the artificial intelligence module 162. The AI module 162 analyzes the received voice and the voice signal converted by the first conversion unit 130, and selects an appropriate keyword to answer to the user. It is not limited to keywords, but selects and selects a voice to be answered so that it is a completed sentence. As an example, an appropriate answer to a user's question or command is searched, and a script signal corresponding to the answer is selected and extracted. Or, for the user's speech, find the answer that can be naturally followed, and select and extract the script signal corresponding to this answer.

Specifically, the AI module 162 analyzes the script signal converted by the first conversion unit 130, analyzes the meaning of the received voice information, and stores it in the storage unit 110 according to a predetermined dialogue model 164, And extracts the pre-stored script signal. The dialogue model 164 comprises a dialogue flow tree corresponding to dialogue semantics and dialogue order. Conversational meaning refers to the meaning that voice information is intended to convey, and conversation order refers to a conversation flow that can be naturally connected. The dialogue flow tree is a synthesis of dialog meaning and dialogue order. It is to understand the meaning of dialogue between the user and the dialogue device 1 using the artificial intelligence according to the present invention, Quot;

The AI module 162 may change the conversation flow tree. In one example, the AI module 162 can analyze the user's data by accumulating and analyzing data about the user, and change the conversation flow tree to suit each user's preference. For example, if there is a long-term user such as a registered user, the voice information repeatedly received from the long-term user is accumulated and stored, and the user-related data is analyzed from the stored voice information. In addition, based on the analyzed user data, the user can change the conversation flow tree so that the age, sex, inclinations, personality, and the like of the user are established and the conversation proceeds accordingly.

Alternatively, the artificial intelligence module 162 may selectively extract a script signal from the storage unit 110 in accordance with a user of a predetermined layer. For example, a particular class may be gender, age, occupation, and the like.

For example, a particular class may be a youth or an elderly person who occupies a large majority of single-person households. For example, it can be set up as a young person in their 20s or as an elderly person in their 60s or older. In this case, the user of the specified hierarchy often feels lonely. Therefore, the conversation flow tree may be changed for the conversation flow to compensate for such feelings, or the keyword may be supplemented with loneliness The script signal can be selectively extracted and the subsequent conversation can be continued.

If the voice received by the receiving unit 120 is voice of a registered user, the artificial intelligence module 162 generates a script (not shown) according to the dialog model 164 previously set using the conversation history stored in the data recording unit 150, The signal can be extracted. Specifically, when the user is determined to be a user registered by the determination unit 140, the personality, sex, and age of the registered user are analyzed and patterned, and the dialogue model 164 can continue the conversation . For example, since the personal information such as the personal information of the registered user is inputted, the script signal can be extracted by the dialogue model 164 that is set up so that the conversation can be continued based on the personal information.

The AI module 162 may be able to continue the conversation about the user's primary interests. For example, the number of keywords included in the received voice of the registered user can be analyzed and recorded. At this time, the keyword is related to the main interest of the registered user and is recorded as a keyword of interest. The artificial intelligence module 162 transmits the keywords previously registered as the keyword of interest to the artificial intelligence module 162 through the sound unit 180 when the power of the conversation apparatus 1 using the artificial intelligence according to the present invention is turned on from the off state can do. That is, by extracting a script signal corresponding to a keyword of interest and transmitting a voice containing a keyword of interest, conversation on a main interest can be naturally continued. Through this, the user can feel comfortable and friendly, and can continue the follow-up conversation.

The second conversion unit 170 converts the script signal extracted from the signal extraction unit 160 into speech. The second conversion unit 170 may support multi-language voice.

The acoustic unit 180 transmits the converted voice from the second conversion unit 170 to the outside. The user will listen to the voice transmitted from the sound unit 180 and respond accordingly, and the voice of the user is received again by the receiving unit 120 and the above processes are repeated. Thus, the conversation can be continued continuously in relation with the user.

The acoustic unit 180 can send a danger signal. In one example, the acoustic unit 180 may generate an alarm sound. Specifically, when the voice of the unregistered user is received by the receiving unit 120 continuously for a predetermined time, the acoustics unit 180 generates an alarm sound. When the voice of an unregistered user is continuously received for a predetermined time without receiving a voice of a previously registered user, it is considered that a situation such as a house invasion of another person has occurred, and a danger signal is transmitted to inform the outside of the dangerous situation . Hazardous signals can be communicated to agencies such as police or security companies. Alternatively, the acoustic unit 180 itself can generate an alarm sound so that the user can recognize the dangerous situation directly from the outside.

The acoustic unit 180 may be wirelessly connected to an external device. For example, the acoustic unit 180 may be connected to an external device through a short-range wireless technology. The acoustic unit 180 may be connected to an external device by a Bluetooth method. The acoustic unit 180 may receive a signal transmitted from an external device and transmit sound corresponding to the signal.

The acoustic unit 180 can transmit voice of a gender different from that of the user. For example, when the determination unit 140 determines that the user's sex is male, the acoustic unit 180 can transmit sound with the female voice.

Fig. 4 is a block diagram showing the configuration of the functional unit 200, and Fig. 5 is a perspective view showing the interactive apparatus 1 using artificial intelligence. The functional unit 200 will be described below with reference to Figs. 4 and 5. Fig.

The functional unit 200 performs functions so that the user can perceive a predetermined effect visually, audibly, and smell. For example, the present invention affects the indoor environment in which the conversation apparatus 1 using the artificial intelligence according to the present invention is located, thereby enabling the user to feel more comfortable. The functional unit 200 may include a housing 210, a power source 220, an illumination unit 230, a jetting unit 240, a display unit 250, and a control unit 260.

The housing 210 constitutes the body of the interactive apparatus 1 using artificial intelligence. The housing 210 forms an outer appearance. The communication unit 100 may be installed inside the housing 210.

The power supply unit 220 turns on / off the power of the interactive apparatus 1 using the artificial intelligence according to the present invention.

The illumination unit 230 can emit light to the outside. The illumination unit 230 may be installed inside the housing 210. The illumination unit 230 may be provided as a mood or the like.

The jetting section 240 can emit liquid to the outside. The liquid may be at least one of water or perfume. The jetting section 240 may include a sprayer and a diffuser. Sprays can scatter water in spray form. The diffuser can disperse perfume in spray form. Therefore, the humidification effect can be obtained in the room by spraying. By the diffuser, the odor can be removed or the direction effect can be obtained in the room.

The display unit 250 can display predetermined information. The predetermined information may be information of a user who emits a voice to the receiving unit 120, room information, or information received by a communication network. The network may be a wireless network, such as the Internet. The information received by the network may be external information such as weather. The user's information may include whether or not the user is a registered user. The indoor information may include room temperature, indoor humidity, and the like.

The control unit 260 may control the illumination unit 230, the jetting unit 240, and the power supply unit 220. The control unit 260 can turn on and off the operation of the illumination unit 230 and the jetting unit 240 according to the user's voice. Specifically, when the predetermined keyword is included in the voice received from the user, the illuminating unit 230 or the jetting unit 240 can be turned on / off accordingly. For example, if the user speaks a keyword meaning 'to turn off the light,' the power of the illumination unit 230 can be turned off by recognizing the keyword.

FIG. 6 is a flowchart sequentially illustrating an artificial intelligence dialogue method according to the present invention. Hereinafter, referring to Fig. 6, a dialogue method using artificial intelligence will be described using the above-described dialog device 1 using artificial intelligence.

The dialogue method using the artificial intelligence according to the present invention may include a storing step S110, a receiving step S120, a first converting step S130, a determining step S140, a data recording step S150, a signal extracting step S160, , A second conversion step (S170), and an audio transmission step (S180).

In the storing step (S110), a plurality of keywords are signaled and stored as a script signal in the storage unit (110). These keywords may be transmitted through the acoustic unit 180 in the sound transmitting step S180.

In the receiving step (S120), the user's voice is received through the receiving unit (120). Here, the meaning of the received voice of the user is analyzed and grasped, and a proper answer is transmitted in an audio transmission step (S180), and conversation with the user is performed.

In the first conversion step S130, the first conversion unit 130 converts the received voice into a voice signal.

In the discriminating step S140, the information of the user is discriminated. For example, the determination unit 140 may determine the status information of the user. The emotion state of the user can be determined. Or whether the user is a registered user. Or the user's personal information. For example, the age, sex, etc. of the user can be determined.

In the data recording step (S150), the voice of the user can be recorded and stored. Or record conversation records with the user. The recorded and stored conversation data is utilized in the subsequent conversation by the AI module 162 to allow natural conversation with the user to follow.

In the signal extraction step (S160), a script signal corresponding to the voice signal is extracted. In the signal extraction step (S160), a script signal is extracted by the artificial intelligence module (162) of the signal extraction unit (160). Extracts a script signal that can be an appropriate answer so that the conversation about the user's voice can be maintained by the artificial intelligence module 162 based on the dialog model 164. The dialogue model 164 may comprise a dialogue flow tree corresponding to dialogue meaning and dialogue order.

In the second conversion step (S170), the extracted script signal is converted into speech in the second conversion unit (170). The voice to be converted can be provided to enable multi-language support. It can also be provided to support both male and female voices and voices of various ages. These voices can be provided according to the characteristics of the user. And may be provided as a user-preferred voice according to the hierarchy or group to which the user belongs.

In the sound transmission step S180, the sound converted in the second conversion step S170 is transmitted from the sound unit 180 to the outside. The sound emitted can be human voice. Various types of voices can be sent out without limitation in multiple languages, gender, and age. In addition to human voice, when connected to an external device, various sounds can be transmitted by a signal transmitted by an external device.

In the above-described embodiment, the conversation method using speech recognition is performed in a storing step S110, a receiving step S120, a first converting step S130, a discriminating step S140, a data recording step S150, a signal extracting step S160 ), A second conversion step (S170), and an audio transmission step (S180). However, the present invention is not limited thereto. Some steps may be omitted, or the order of each step may be changed.

In the above-described embodiment, the information of the user determined by the determining unit 140 is exemplarily described as an emotion state, an age, a sex, a job, and the like. However, the present invention is not limited thereto. Can be determined. Such user information may be displayed on the display unit 250. [

The foregoing detailed description is illustrative of the present invention. In addition, the foregoing is intended to illustrate and explain the preferred embodiments of the present invention, and the present invention may be used in various other combinations, modifications, and environments. That is, it is possible to make changes or modifications within the scope of the concept of the invention disclosed in this specification, within the scope of the disclosure, and / or within the skill and knowledge of the art. The embodiments described herein are intended to illustrate the best mode for implementing the technical idea of the present invention and various modifications required for specific applications and uses of the present invention are also possible. Accordingly, the detailed description of the invention is not intended to limit the invention to the disclosed embodiments. It is also to be understood that the appended claims are intended to cover such other embodiments.

1: Communication device 100 using artificial intelligence: Communication unit
110: storage unit 120: receiving unit
140: discrimination unit 160: signal extraction unit
200: function unit 230: illumination unit
240: jetting section 260:

Claims (7)

A storage unit for storing a keyword as a script signal;
A receiving unit for recognizing the user's voice;
A first converting unit for converting a voice received from the receiving unit into a voice signal;
A determination unit for determining user information from the received voice or the converted voice signal;
A signal extracting unit for extracting a script signal corresponding to the voice signal;
A second conversion unit for converting the script signal extracted from the signal extraction unit into speech; And
And an acoustic unit for transmitting the voice converted by the second conversion unit,
Wherein the signal extracting unit extracts a script signal corresponding to the speech signal by an artificial intelligence module,
The artificial intelligence module includes:
Analyzing the meaning of the received voice information by analyzing the converted script signal in the first conversion unit, extracting a previously stored script signal in the storage unit according to a predetermined dialogue model,
The conversation model includes:
A dialogue device using artificial intelligence composed of dialogue meaning and dialogue flow tree corresponding to dialogue order.
The method according to claim 1,
The artificial intelligence module includes:
Accumulates and stores voice information of the received user, analyzes data related to the user from the stored voice information,
And changing the conversation flow tree based on the analyzed user-related data.
3. The method of claim 2,
The artificial intelligence module includes:
Analyzing the received user voice to grasp the status information of the user, extracting a corresponding script signal from the detected status information,
Wherein the sound unit transmits a voice of a predetermined frequency and size according to the status information of the user,
The status information of the user includes:
And at least one of emotion, age, and sex of the user. The method of claim 3,
The acoustic unit includes:
And a danger signal is transmitted when an unregistered user's voice is received by the receiving unit continuously for a predetermined time.
5. The method of claim 4,
A housing constituting a main body;
An illumination unit for emitting light to the outside;
A jetting portion for jetting liquid to the outside;
A display unit for displaying predetermined information; And
Further comprising a control unit for controlling the illumination unit and the injection unit,
The illumination unit is provided in a mood or the like,
The injection unit
A spray for spraying water,
A diffuser for spraying perfume,
Wherein,
Wherein when the predetermined keyword is included in the sound received by the receiving unit, the controller turns on / off the power of the illumination unit and the injection unit,
The acoustic unit is capable of supporting multi-lingual voice, wirelessly connecting with an external device, receiving a signal transmitted from the external device, and transmitting sound corresponding to the signal,
Wherein the predetermined information displayed on the display unit is information received from the user via the communication network or information of a user who emits a voice to the receiving unit.
A storing step of storing a keyword as a script signal;
A receiving step of receiving a user's voice;
A first conversion step of converting the received voice signal into a voice signal;
A discriminating step of discriminating the user's information from the voice received in the receiving step or the voice signal converted in the first converting step;
A signal extracting step of extracting a script signal corresponding to the voice signal;
A second conversion step of converting the extracted script signal into speech; And
And an audio transmitting step of transmitting the converted voice,
In the signal extracting step,
Analyzing the meaning of the received voice information by analyzing the script signal converted in the first conversion step by artificial intelligence, extracting the script signal stored in the storing step according to a predetermined dialogue model,
Wherein the dialogue model comprises a dialogue flow tree corresponding to a dialogue meaning and a dialogue order,
Wherein,
Analyzes the voice of the user to grasp the status information of the user,
In the sound transmitting step, a voice having a predetermined frequency and size is transmitted according to the status information of the user,
In the signal extracting step,
A dialogue method using artificial intelligence that accumulates and stores voice information of a received user, analyzes data about a user, and changes the conversation flow tree by artificial intelligence based on the analyzed data.
The method according to claim 6,
In the signal extracting step,
Extracting the script signal by artificial intelligence according to a user of a predetermined layer,
Wherein the specific layer includes at least one of sex, age, and occupation.

Images