KR20220168534A - Method and system for training artificial intelligence character's dialogue engine - Google Patents

Abstract

A conversation engine learning method and system for an artificial intelligence character are disclosed. A conversation engine learning method for an artificial intelligence character according to an embodiment of the present invention includes generating an artificial intelligence character based on a creator's input; Collecting question and answer data of each of the artificial intelligence character and followers following the artificial intelligence character with respect to a preset initial question; and reflecting the collected dialogue data to the dialogue engine of the artificial intelligence character to learn the dialogue engine.

Description

AI character dialogue engine learning method and its system {METHOD AND SYSTEM FOR TRAINING ARTIFICIAL INTELLIGENCE CHARACTER'S DIALOGUE ENGINE}

The present invention relates to a conversation engine learning technology of an artificial intelligence character, and more specifically, by collecting question and answer data between followers following an artificial intelligence character and an artificial intelligence character in the direction of conversation desired by the creator who created the artificial intelligence character. The present invention relates to a method and system for learning a conversation engine of an artificial intelligence character that can learn a conversation engine of an artificial intelligence character in a conversation direction desired by a creator by reflecting the conversation engine.

Artificial intelligence is revolutionizing business, organisations, lifestyles and communication methods. Various informatization projects are being carried out to provide optimal services to the fast-changing lifestyle of modern culture and the diverse and constantly changing requirements of customers. Among them, big data and deep learning-related technologies are rapidly changing. Artificial intelligence technology that has been developed and applied to real life in certain fields has been implemented, and it is also applied to intelligent personal services that analyze specific data and provide and utilize information in various fields specialized to individuals. Currently, human interaction with artificial intelligence is limited, but it takes place in everyday natural language, that is, in the form of conversation. Although it is still at a rudimentary stage, control of various home appliances connected to the network is being carried out in a voice-based conversation method, and search for specific information, inquiry, and response are becoming possible through a knowledge base to which deep learning is applied.

Embodiments of the present invention collect question and answer data between followers who follow an artificial intelligence character and an artificial intelligence character in the conversation direction desired by the creator who created the artificial intelligence character and reflect it to the conversation engine, so that the conversation engine of the artificial intelligence character Provides a method and system for learning an artificial intelligence character's conversation engine that can learn in the conversation direction desired by the creator.

A conversation engine learning method for an artificial intelligence character according to an embodiment of the present invention includes generating an artificial intelligence character based on a creator's input; Collecting question and answer data of each of the artificial intelligence character and followers following the artificial intelligence character with respect to a preset initial question; and reflecting the collected dialogue data to the dialogue engine of the artificial intelligence character to learn the dialogue engine.

The collecting step may include a first step of providing a first answer to the first question by a conversation engine of the artificial intelligence character to each of the followers following the artificial intelligence character based on the creator's answer input; Receiving a response to the first answer from each of the followers, and providing a second answer of the artificial intelligence character to the response received from each of the followers to each of the followers based on the creator's answer input second step; and a third step of collecting question-and-answer data for the first question by repeating the artificial intelligence character's answer and each of the followers' responses to the artificial intelligence character's answer a predetermined number of times.

The collecting step is a function for collecting the question-and-answer data when an answer dialog window is provided by the conversation engine of the artificial intelligence character for the initial question, and the answer dialog window is pressed for a predetermined period of time or longer preset by the creator. By performing this, the question and answer data may be collected.

In the second step, when a response to the first answer is received, a notification thereof is provided to the creator, and the second answer to the response received from each of the followers through the notification is converted into an answer desired by the creator. In order to learn, the second answer may be provided to each of the followers by inputting the second answer through the creator's answer input.

In the generating step, the artificial intelligence character may be created by giving at least one hash tag for a specific topic for learning the artificial intelligence character.

A conversation engine learning method for an artificial intelligence character according to another embodiment of the present invention includes generating an artificial intelligence character based on a creator's input; generating an answer of the artificial intelligence character to a preset initial question based on an answer input of the creator; and reflecting the initial question and the creator's answer input to the conversation engine of the artificial intelligence character to learn the conversation engine.

A conversation engine learning method for an artificial intelligence character according to another embodiment of the present invention includes generating an artificial intelligence character based on a creator's input; In a chat window between the artificial intelligence character and a follower following the artificial intelligence character, if the artificial intelligence character's answer is pressed for more than a predetermined period of time preset by the creator, the artificial intelligence character's answer is entered as the creator's answer Modifying based on; and reflecting the contents of the conversation in the chat window and the corrected answer to the conversation engine of the artificial intelligence character to learn the conversation engine.

A conversation engine learning method for an artificial intelligence character according to another embodiment of the present invention includes generating an artificial intelligence character based on a creator's input; Receiving conversation data from the artificial intelligence character or a follower following the artificial intelligence character; generating response data corresponding to the dialogue data using a second artificial intelligence character; and recommending the response data.

In addition, the method for learning a conversation engine of an artificial intelligence character according to another embodiment of the present invention further includes the step of learning the conversation engine by reflecting the response data for the conversation data to the conversation engine of the artificial intelligence character. can do.

In the recommending step, the response data is recommended near an input window for inputting a message, and a copy icon recommending the response data may be positioned near the response data.

When the copy icon is clicked by the creator, the recommended response data may be input to the input window and may be modified.

In the recommending step, the response data may be recommended with a font and color according to the creator's selection input.

An artificial intelligence character conversation engine learning system according to an embodiment of the present invention includes a generator for generating an artificial intelligence character based on a creator's input; A collection unit for collecting question and answer data of each of the artificial intelligence character and followers following the artificial intelligence character with respect to a preset initial question; and a learning unit for learning the conversation engine by reflecting the collected dialogue data to the conversation engine of the artificial intelligence character.

The collecting unit provides a first answer by the conversation engine of the artificial intelligence character to the first question to each of the followers following the artificial intelligence character based on the creator's answer input, and from each of the followers Receiving a response to the first answer of the artificial intelligence character, providing a second answer of the artificial intelligence character to the response received from each of the followers to each of the followers based on the creator's answer input, The question and answer data for the question may be collected by repeating the artificial intelligence character's answer and each follower's response to the artificial intelligence character's answer a predetermined number of times or more.

The collecting unit performs a function for collecting the question-and-answer data when an answer dialog window is provided by the conversation engine of the artificial intelligence character to the initial question, and the answer dialog window is pressed for a predetermined time or longer set by the creator. By doing so, the question and answer data can be collected.

The collecting unit provides a notification to the creator when a response to the first answer is received, and learns the second answer to the response received from each of the followers through the notification as an answer desired by the creator. To this end, the second answer may be provided to each of the followers by inputting the second answer through the creator's answer input.

The generating unit may generate the artificial intelligence character by giving at least one hash tag for a specific subject for learning the artificial intelligence character.

According to embodiments of the present invention, by collecting question and answer data between followers who follow an artificial intelligence character and an artificial intelligence character in the conversation direction desired by the creator who created the artificial intelligence character and reflecting it to the conversation engine, The conversation engine is trained in the direction of conversation desired by the user, and through this, the creator can communicate in the direction desired by the creator when communicating with followers.

According to embodiments of the present invention, by generating an artificial intelligence character's answer to a preset initial question based on a creator's answer input, the artificial intelligence character's answer to the initial question is reflected in the dialog engine so that the creator can create a dialog engine. You can learn in the direction of conversation you want.

According to embodiments of the present invention, in a chat window between an artificial intelligence character and a follower, when an answer of an artificial intelligence character is pressed for a predetermined time or longer set by a creator, the answer of the artificial intelligence character is modified based on the creator's answer input. By doing so, the conversation contents and modified answers in the chat window are reflected in the conversation engine of the artificial intelligence character, and the conversation engine can be trained in the conversation direction desired by the creator.

According to the embodiments of the present invention, by repeatedly learning the conversation engine by collecting question and answer data, the conversation skills of the artificial intelligence character are improved, and thus the follower and the artificial intelligence character can naturally have a conversation.

1 illustrates an exemplary diagram for explaining a network environment according to an embodiment of the present invention.
FIG. 2 is an exemplary view for explaining internal configurations of the electronic device and server shown in FIG. 1 .
3 is a flowchart illustrating an operation of a method for learning a conversation engine of an artificial intelligence character according to an embodiment of the present invention.
4 and 5 show exemplary diagrams for explaining a process of collecting question and answer data of an artificial intelligence character.
6 illustrates exemplary diagrams for explaining a process of recommending response data of an artificial intelligence character.
7 shows the configuration of an artificial intelligence character conversation engine learning system according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various forms different from each other, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention pertains. It is provided to completely inform the person who has the scope of the invention, and the present invention is only defined by the scope of the claims.

Terms used in this specification are for describing the embodiments and are not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" means that a stated component, step, operation, and/or element is present in the presence of one or more other components, steps, operations, and/or elements. or do not rule out additions.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in more detail. The same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

Embodiments of the present invention, by collecting the question and answer data between the artificial intelligence character and the followers who follow the artificial intelligence character in the conversation direction desired by the user who created the artificial intelligence character, that is, the creator, and reflecting it to the conversation engine, the artificial intelligence character The main point is to train the conversation engine in the conversation direction the creator wants.

1 shows an exemplary diagram for explaining a network environment according to an embodiment of the present invention, and the network environment of FIG. 1 includes a plurality of electronic devices 110, 120, 130, and 140, a plurality of servers ( 150, 160) and a network 170 are shown. 1 is an example for explanation of the invention, and the number of electronic devices or servers is not limited as shown in FIG. 1 .

The plurality of electronic devices 110, 120, 130, and 140 may be mobile terminals implemented as computer devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 include smart phones, mobile phones, tablet PCs, navigation devices, computers, laptop computers, digital broadcasting terminals, personal digital assistants (PDAs), and PMPs ( Portable Multimedia Player), user wearable devices (wearable devices), and the like. For example, the first electronic device 110 may communicate with the other electronic devices 120, 130, and 140 and/or the servers 150 and 160 through the network 170 using a wireless or wired communication method.

The communication method is not limited, and short-distance wireless communication between devices as well as a communication method utilizing a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, and a broadcasting network) that the network 170 may include may also be included. For example, the network 170 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , one or more arbitrary networks such as the Internet. In addition, the network 170 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, and the like. Not limited.

Each of the servers 150 and 160 communicates with the plurality of electronic devices 110, 120, 130, and 140 through the network 170 to provide commands, codes, files, contents, services, and the like, or a computer device or a plurality of computers. Can be implemented in devices.

For example, the server 160 may provide a file for installing an application to the first electronic device 110 accessed through the network 170 . In this case, the first electronic device 110 may install an application using a file provided from the server 160 . In addition, the server 150 is connected to the server 150 under the control of an operating system (OS) included in the first electronic device 110 or at least one program (for example, a browser or the installed application), and the server 150 provides services or content may be provided. For example, when the first electronic device 110 transmits a service request message to the server 150 through the network 170 under the control of an application, the server 150 transmits a code corresponding to the service request message to the first It can be transmitted to the electronic device 110, and the first electronic device 110 can provide content to the user by constructing and displaying a screen according to a code under the control of an application.

FIG. 2 shows an exemplary view for explaining the internal configuration of the electronic device and server shown in FIG. 1, and in FIG. 2, a first electronic device 110 as an example of one electronic device that is a terminal possessed by a user , And the internal configuration of the server 150 will be described as an example for one server communicating with the user's terminal. Accordingly, hereinafter, the first electronic device 110 means a user's terminal, and the server 150 means a server communicating with the user's terminal. Other electronic devices 120 , 130 , and 140 or the server 160 may also have the same or similar internal configuration.

The first electronic device 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input/output interfaces 214 and 224. The memories 211 and 221 are computer-readable recording media and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. In addition, the memories 211 and 221 may store an operating system or at least one program code (for example, a code for an application installed and driven in the first electronic device 110). These software components may be loaded from a computer readable recording medium separate from the memories 211 and 221 . The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, software components may be loaded into the memories 211 and 221 through the communication modules 213 and 223 rather than computer-readable recording media. For example, at least one program is a program installed by files provided by developers or a file distribution system (eg, the above-described server 160) that distributes installation files of applications through the network 170 (eg, the above-described server 160). It may be loaded into the memories 211 and 221 based on the above-described application).

The processors 212 and 222 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to processors 212 and 222 by memories 211 and 221 or communication modules 213 and 223 . For example, the processors 212 and 222 may be configured to execute instructions received according to program codes stored in a recording device such as the memories 211 and 221 .

The communication modules 213 and 223 may provide a function for the first electronic device 110 and the server 150 to communicate with each other through the network 170, and other electronic devices (for example, the second electronic device 120). )) or a function for communicating with another server (for example, the server 160). For example, a request generated by the processor 212 of the first electronic device 110 according to a program code stored in a recording device such as the memory 211 (for example, a search request) is transmitted to the network under the control of the communication module 213. It may be transmitted to the server 150 through 170. Conversely, control signals, commands, contents, files, etc. provided under the control of the processor 222 of the server 150 pass through the communication module 223 and the network 170 to the communication module of the first electronic device 110. It can be received by the first electronic device 110 through 213. For example, control signals or commands of the server 150 received through the communication module 213 may be transmitted to the processor 212 or memory 211, and contents or files may be transferred to the first electronic device 110. Can be stored in a storage medium that can further include.

The input/output interface 214 may be a means for interface with the input/output device 215 . For example, the input device may include a device such as a keyboard or mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input/output interface 214 may be a means for interface with a device in which functions for input and output are integrated into one, such as a touch screen. As a more specific example, the processor 212 of the first electronic device 110 uses data provided by the server 150 or the second electronic device 120 in processing the command of the computer program loaded into the memory 211. The service screen or content configured as above may be displayed on the display through the input/output interface 214 . Similarly, the input/output interface 224 may output information configured using data provided by the server 150 when the processor 222 of the server 150 processes the command of the computer program loaded into the memory 221. there is.

Also, in other embodiments, the first electronic device 110 and the server 150 may include more components than those shown in FIG. 2 . However, there is no need to clearly show most of the prior art components. For example, the first electronic device 110 is implemented to include at least some of the above-described input/output devices 215 or other devices such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. It may contain more components. As a more specific example, when the first electronic device 110 is a smartphone, a direction sensor, an acceleration sensor or a gyro sensor, a camera, various physical buttons, buttons using a touch panel, an input/output port, It can be seen that various components such as a vibrator for vibration may be implemented to be further included in the first electronic device 110 .

Hereinafter, specific embodiments of a method and system for learning an artificial intelligence character that is equipped with a conversation engine and communicates with followers following the corresponding artificial intelligence character will be described.

3 is an operation flowchart of a method for learning a conversation engine of an artificial intelligence character according to an embodiment of the present invention, in a system or server that provides a conversation service and can learn an artificial intelligence character in a desired direction by a creator. It shows the operation flow chart.

Referring to FIG. 3 , the conversation engine learning method of an artificial intelligence character according to an embodiment of the present invention generates an artificial intelligence character based on a user's input as a creator (S310).

Here, step S310 can be created through a function for creating an artificial intelligence character provided by a system capable of learning a conversation service and an artificial intelligence character conversation engine by a creator. For example, in step S310, a face image, tone of voice, personality, conversation field of interest (or conversation content of interest), name, gender, character introduction, etc. are set by a user who is a creator, so that a preset basic conversation engine is learned and artificial Intelligent characters can be created. At this time, the artificial intelligence character created in step S310 can exchange conversations with followers, users who follow the artificial intelligence character, with the tone of voice and the content of conversations of interest set by the user who is the creator.

In the method of the present invention, when the artificial intelligence character created in this way communicates with followers using a conversation engine, the creator determines the answer method or content of the answer desired by the creator, such as the answer method or content of the answer that the artificial intelligence character communicates with the followers. It is to learn the conversation engine of the artificial intelligence character so that it can communicate with That is, the method of the present invention gradually develops the conversation engine of the artificial intelligence character that has already been created according to the creator's request, and can be repeatedly performed until the conversation engine of the artificial intelligence character is completed.

In addition, at least one hash tag set by the creator may be given to the artificial intelligence character created in step S310 so that other users can search for the artificial intelligence character created by the creator through keywords such as areas of interest in conversation. .

For example, if the artificial intelligence character's hashtags are set to "#golf" and "#sports" by the creator, the artificial intelligence character can be searched for golf and sports, and conversations about golf and sports can be performed. It can be classified as an artificial intelligence character with

After the artificial intelligence character is created by the creator in step S310, if there are followers who follow the artificial intelligence character, in order to additionally learn the conversation engine of the artificial intelligence character, the dialogue data exchanged between the artificial intelligence character and the followers is Collect (S320).

Followers in the present invention may include creators capable of creating artificial intelligence characters other than artificial intelligence characters or users who conduct conversations with artificial intelligence characters.

Here, in step S320, a function for collecting question and answer data may be performed by a creator's input or action. For example, when a "relay" function is provided as a function for collecting question and answer data of an artificial intelligence character in an application for a user terminal provided by the present invention, the "relay" function for the artificial intelligence character is input by the creator. If selected by , it is possible to collect dialogue data exchanged between the AI character and each follower until the “relay” function is completed. In this case, the answer provided from the artificial intelligence character to each of the followers may be provided as a conversation between the artificial intelligence character and the creator's input.

For example, as shown in FIG. 4 , among artificial intelligence characters 410 created by creators, an artificial intelligence character called "Genji" responds to the question "What color do you like?" "It's red!" If you answer (420), a notification of the answer is provided to each of the followers who follow Genji, and if User 1 among the followers sees the answer and responds with "But I think the red color hurts my eyes", it responds Receipt notification is provided to the creator, and an answer input window 430 for the creator to directly input an answer to the corresponding response is provided. Here, the answer "It's red!" (420) can be directly entered by the creator as the answer of "Genji", and the first question "What color do you like?" is a frequently asked question by followers, the method of the present invention. It may be either a question set in advance or a question directly input by the creator.

In response to the response "But I think red hurts my eyes" in the answer input window 430, the creator directly inputs the answer he wants the artificial intelligence character to give and answers to User 1, thereby collecting question and answer data with User 1. can Here, the initial question “What color do you like?”, the answer “It’s red!” (420), the response “But I think red hurts my eyes”, and the creator’s input into the answer input window 430 The answer is reflected in the conversation engine by step S330, so that the AI character "Genji" later responds to the answer "It's red!" The input answer can be answered by an artificial intelligence character through a conversation engine. FIG. 4 relates to a screen from the point of view of a creator and an artificial intelligence character, and will be further explained through FIG. 5 showing a screen from the point of view of a follower.

As shown in FIG. 5A , when a follower receives a conversation message saying “It's red!” 520 from the artificial intelligence character “elk” among the following artificial intelligence characters 510, the follower inputs an answer thereto. In the case of FIG. 5, "But I think red hurts my eyes" (530) is input as an answer and transmitted, and in response to the answer (530), "Elk" creator directly inputs " If the response "Still strong and memorable" is received, as shown in FIG. 5B, a notification is provided, and the follower directly inputs the answer into the answer input window 550 to send the AI character to the corresponding AI character. can transmit

In FIGS. 4 and 5, the artificial intelligence characters have been described as being different as "Genji" and "elk", respectively, but when the two artificial intelligence characters are the same, it is possible to collect question and answer data between the artificial intelligence character and followers in this way. that showed This process is performed for each of all followers, and the process of collecting question and answer data may be repeated a certain number of times or more. That is, question-and-answer data may be collected by repeating the artificial intelligence character's answer and each follower's response to the artificial intelligence character's answer a certain number of times or more.

In addition, this function of step S320 may be performed by selecting a specific function, but when the answer dialog window automatically input by the conversation engine of the artificial intelligence character to the provided question is pressed for a predetermined period of time preset by the creator, that is, long When pushed, a function of collecting question and answer data for updating a conversation engine of a corresponding artificial intelligence character may be automatically performed. In other words, if the creator long pushes the conversation input window automatically entered by the conversation engine of the AI character for more than a preset time, it is determined that the part of the conversation with the current followers is to be collected as Q&A data, Answers and responses between followers can be collected as Q&A data. This embodiment relates to a case where an answer to an initial question is automatically input by a conversation engine of an artificial intelligence character. Of course, the answer or response of the artificial intelligence character to the response or answer received from the follower may be an answer or response directly input or selected by the creator.

Depending on the situation, this function of step S320 can modify the answer input window when the answer dialog window for the question automatically input by the dialogue engine of the artificial intelligence character with respect to the initial question is long-pushed for a predetermined time or longer set by the creator. The creator can modify the answer dialog and provide it to each follower again, and when the corrected answer is provided to each follower, collects question and answer data to update the conversation engine of the AI character. function may be performed automatically. For example, if the creator does not like the answer "It's red" (420) shown in FIG. It can be modified, and if the creator modifies it to the desired answer, it is determined that the part of the current conversation with the followers is to be collected as question-and-answer data, and the answers and responses between the AI character and the followers can be collected as question-and-answer data. Of course, in this case, the corrected answer may be transmitted to each of the followers.

When Q&A data for a specific question is collected through the above-described process, the collected Q&A data, that is, the Q&A data including each follower's response and the creator's desired answer to it, is reflected in the conversation engine to communicate the AI character's conversation. The engine is learned in a direction desired by the creator (S330).

Therefore, since the Q&A data is reflected in the conversation engine, when the AI character and the followers have a conversation later, when the conversation included in the Q&A data is transmitted from the follower to the AI character, the AI character is directly input by the creator. You can continue the conversation by replying. This learning process can be continuously performed by the creator, and if the learning process is repeated, the artificial intelligence character created by the creator can grow in the direction the creator wants in the corresponding field of conversation.

6 illustrates exemplary diagrams for explaining a process of recommending response data of an artificial intelligence character.

Referring to FIG. 6, the conversation engine learning method of an artificial intelligence character of the present invention creates an artificial intelligence character based on a creator's input, and follows the artificial intelligence character or AI character in a chat room as shown in FIG. Conversation data may be received from followers who do. In this case, the artificial intelligence character or a follower following the artificial intelligence character may be an AI or a real person.

6(a) to 6(c) as an example, when an artificial intelligence character or a follower following an artificial intelligence character inputs conversation data of 'I wish you all a happy day', a second artificial intelligence character ( A recommendation (601) may be made by generating response data corresponding to the conversation data using an anonymous lazy turtle. The recommended response data is characterized in that it is located near the input window 603 for inputting a message in the chat room, and a copy icon 602 recommending response data may be located near the response data.

Accordingly, when the copy icon 602 is clicked by the creator, the recommended response data 601 is input to the input window 603, and the response data input to the input window can be deleted or further modified by the creator. . When the creator clicks 'send' on one side of the input window 603, the corresponding response data may be input 604 to the chat room.

Other graphic effects such as font and color may be applied to the response data 601 recommended in the present invention according to the creator's selection input.

In this way, the conversation engine learning method of an artificial intelligence character according to an embodiment of the present invention collects question and answer data between followers following an artificial intelligence character and an artificial intelligence character in the direction of conversation desired by the creator who created the artificial intelligence character. By reflecting it to the conversation engine, the conversation engine of the artificial intelligence character is trained in the conversation direction the creator wants, and through this, the creator can communicate in the direction the creator wants when talking with followers.

In addition, in the method for learning a conversation engine of an artificial intelligence character according to an embodiment of the present invention, the conversation skill of an artificial intelligence character is improved by repeatedly learning a conversation engine by collecting question and answer data, and thus the follower and the artificial intelligence character have a conversation. can be naturally divided.

3 to 5 show that the creator directly inputs the answer to the initial question, receives the answer from the follower, and then the creator directly inputs the answer and receives the answer from the follower. , Q&A data for the initial question is collected as a conversation between the creator and the follower, and the collected Q&A data is reflected in the conversation engine of the artificial intelligence character for learning, and then the conversation reflected in the conversation engine is conducted with the follower in the direction the creator wants. Although it has been described that conversations can be performed, the method of the present invention is not limited or limited to sequentially collecting conversations between creators and followers and reflecting them to the conversation engine.

In another embodiment, in the method of learning the conversation engine of an artificial intelligence character in the present invention, any one of questions frequently asked by followers, preset questions, or questions directly input by creators is provided to the artificial intelligence character as the first question. If the answer is also directly entered by the creator, the initial question and the creator's answer to it are reflected in the conversation engine of the artificial intelligence character, and the conversation engine can be trained with the creator's directly input answer.

As another embodiment, the conversation engine of the artificial intelligence character may be trained through a chat window in which a conversation has already been made between the artificial intelligence character and the followers. For example, if a creator enters a chat window where a conversation between an AI character and a follower has already taken place, the creator can view the conversation. When a speech bubble, that is, a conversation bubble is long pushed, the contents of the conversation bubble can be directly modified and input as the answer desired by the creator, and the answer entered in this way can be reflected in the conversation engine of the artificial intelligence character to learn the conversation engine. .

As described above, in the method according to the embodiments of the present invention, 1) the creator directly inputs the artificial intelligence character's answer to the first question using the relay function, provides it to the follower, and receives the follower's response. Then, by repeating the process of directly inputting the answer and providing it to the follower, the creator collects question-and-answer data, and reflects the collected question-and-answer data to the conversation engine of the artificial intelligence character to learn the conversation engine. 2) In the home of the application, the creator directly inputs the AI character's answer to the first question and reflects the Q&A data for the first question and answer to the AI character's conversation engine to learn the conversation engine. 3) AI character and It may include a method in which a creator directly corrects and inputs an artificial intelligence character's utterance in a chat window in which a conversation has already occurred between followers, and reflects the utterance input by the creator to the artificial intelligence character's dialogue engine to learn the dialogue engine.

In addition, in each of the above-described methods, all sentences are recorded in vector form and reflected in the conversation edge, so that the conversation engine of the artificial intelligence character can be learned in the direction the creator wants, and when learning the conversation engine of the artificial intelligence character, a specific For intentions, for example, sexual expression and hate speech, the creator's answers are not reflected in the conversation engine, so the conversation engine does not learn specific intentions. Thus, for specific intents, the original sentence of the dialogue engine is uttered by the artificial intelligence character. Here, specific intentions can be confirmed by analyzing the preceding context and the utterance sentence input by the creator.

7 shows the configuration of an artificial intelligence character conversation engine learning system according to an embodiment of the present invention, and shows a conceptual configuration of a server or system that performs a conversation engine learning method of an artificial intelligence character.

Referring to FIG. 7 , an artificial intelligence character conversation engine learning system 700 according to an embodiment of the present invention includes a generator 710, a collection unit 720, and a learning unit 730.

The generating unit 710 generates an artificial intelligence character based on a user's input as a creator.

Here, the generation unit 710 can be created through a function for creating an artificial intelligence character provided by a system capable of learning a conversation service and an artificial intelligence character conversation engine by a creator, and a face image, tone, and personality by the creator. , conversation fields of interest (or conversation contents of interest), name, gender, character introduction contents, etc. are set, so that artificial intelligence characters can be created by learning a preset basic conversation engine.

Furthermore, the generation unit 710 may generate an artificial intelligence character by giving at least one hash tag set by a creator so that other users may search for the artificial intelligence character through keywords such as fields of interest in conversation.

When a specific function for collecting question and answer data for additional learning of the conversation engine of the artificial intelligence character is executed, the collecting unit 720 collects question and answer data exchanged between the artificial intelligence character and the followers.

Here, the collection unit 720 may collect dialogue data exchanged between the artificial intelligence character and followers, as a function for collecting dialogue data is performed by a creator's input or action. For example, the collection unit 720 collects question and answer data exchanged between the artificial intelligence character and each follower until the "relay" function is completed when the "relay" function is selected by the creator's input for the corresponding artificial intelligence character. It is possible to collect question and answer data including answers by the creator's input and responses or answers by each of the followers.

Furthermore, the collection unit 720 converts the part of the conversation with the current followers into question-and-answer data when the answer dialog automatically input by the dialog engine of the artificial intelligence character to the first question provided is long-fushed for more than a predetermined time set by the creator. When it is determined that it is to be collected as , it is possible to collect question and answer data for updating the conversation engine of the corresponding artificial intelligence character.

Furthermore, the collection unit 720 has a function of modifying the corresponding answer input window when the answer dialog automatically input by the conversation engine of the artificial intelligence character to the initial question provided is long-pushed for a predetermined time or longer set by the creator. and, if the creator modifies the answer in the corresponding answer dialog window, it is determined that the part of the conversation with the current followers is to be collected as Q&A data, and Q&A data can be collected to update the conversation engine of the AI character. there is.

The learning unit 730 reflects the question and answer data collected by the collection unit 720 to the conversation engine of the corresponding artificial intelligence character and learns the conversation engine, so that the artificial intelligence capable of carrying out a conversation with the conversation engine reflecting the creator's intention. You can grow as a character.

Although the description is omitted in the system of FIG. 7, each component constituting FIG. 7 may include all of the contents described in FIGS. 1 to 6, which is obvious to those skilled in the art.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. can be embodied in Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (17)

Generating an artificial intelligence character based on a creator's input;
Collecting question and answer data of each of the artificial intelligence character and followers following the artificial intelligence character with respect to a preset initial question; and
Learning the conversation engine by reflecting the collected question and answer data to the conversation engine of the artificial intelligence character
A conversation engine learning method for an artificial intelligence character that includes a. According to claim 1,
The collecting step is
A first step of providing a first answer of the artificial intelligence character to the first question to each of the followers following the artificial intelligence character based on the creator's answer input;
Receiving a response to the first answer from each of the followers, and providing a second answer of the artificial intelligence character to the response received from each of the followers to each of the followers based on the creator's answer input second step; and
A third step of collecting question-and-answer data for the first question by repeating the artificial intelligence character's answer and each of the followers' responses to the artificial intelligence character's answer a certain number of times;
A conversation engine learning method for an artificial intelligence character that includes a. According to claim 1,
The collecting step is
For the first question, an answer dialog window is provided by the conversation engine of the artificial intelligence character, and a function for collecting the question and answer data is performed when the answer dialog window is pressed for a predetermined period of time or longer set by the creator. A method for learning a conversation engine of an artificial intelligence character, characterized in that it collects question and answer data. According to claim 2,
The second step is
In order to provide a notification to the creator when a response to the first answer is received, and to learn the second answer to the response received from each of the followers through the notification as an answer desired by the creator, A conversation engine learning method for an artificial intelligence character, characterized in that by inputting the second answer through the creator's answer input, the second answer is provided to each of the followers. According to claim 1,
The generating step is
A conversation engine learning method for an artificial intelligence character, characterized in that for generating the artificial intelligence character by giving at least one hash tag for a specific topic for learning the artificial intelligence character. Generating an artificial intelligence character based on a creator's input;
generating an answer of the artificial intelligence character to a preset initial question based on an answer input of the creator; and
Learning the conversation engine by reflecting the initial question and the creator's answer input to the conversation engine of the artificial intelligence character
A conversation engine learning method for an artificial intelligence character that includes a. Generating an artificial intelligence character based on a creator's input;
In a chat window between the artificial intelligence character and a follower following the artificial intelligence character, if the artificial intelligence character's answer is pressed for more than a predetermined period of time preset by the creator, the artificial intelligence character's answer is entered as the creator's answer Modifying based on; and
Learning the conversation engine by reflecting the contents of the conversation in the chat window and the modified answer to the conversation engine of the artificial intelligence character
A conversation engine learning method for an artificial intelligence character that includes a. Generating an artificial intelligence character based on a creator's input;
Receiving conversation data from the artificial intelligence character or a follower following the artificial intelligence character;
generating response data corresponding to the dialogue data using a second artificial intelligence character; and
recommending the response data
A conversation engine learning method for an artificial intelligence character that includes a. According to claim 8,
Learning the conversation engine by reflecting the response data for the conversation data to the conversation engine of the artificial intelligence character
A conversation engine learning method of an artificial intelligence character further comprising a. According to claim 8,
The recommended steps are
recommending the response data near an input window for entering a message;
Characterized in that a copy icon recommending the response data is located near the response data, a conversation engine learning method for an artificial intelligence character. According to claim 10,
Characterized in that, when the copy icon is clicked by the creator, the recommended response data is input to the input window and can be modified. According to claim 10,
The recommended steps are
A method for learning a conversation engine of an artificial intelligence character, recommending the response data with a font and color according to the creator's selection input. A generator for generating an artificial intelligence character based on a creator's input;
A collection unit for collecting question and answer data of each of the artificial intelligence character and followers following the artificial intelligence character with respect to a preset initial question; and
A learning unit for learning the conversation engine by reflecting the collected question and answer data to the conversation engine of the artificial intelligence character
A dialogue engine learning system for artificial intelligence characters that includes According to claim 13,
the collection department
A first answer by the conversation engine of the artificial intelligence character to the first question is provided to each of the followers following the artificial intelligence character based on the creator's answer input,
Receiving a response to the first answer from each of the followers, and providing a second answer of the artificial intelligence character to the response received from each of the followers to each of the followers based on the creator's answer input, ,
A conversation engine learning system for an artificial intelligence character, characterized in that for collecting the question-and-answer data for the first question by repeating the answer of the artificial intelligence character and each of the followers' responses to the answer of the artificial intelligence character a certain number of times . According to claim 13,
the collection department
For the first question, an answer dialog window is provided by the conversation engine of the artificial intelligence character, and a function for collecting the question and answer data is performed when the answer dialog window is pressed for a predetermined period of time or longer set by the creator. An artificial intelligence character conversation engine learning system characterized by collecting question and answer data. According to claim 14,
the collection department
In order to provide a notification to the creator when a response to the first answer is received, and to learn the second answer to the response received from each of the followers through the notification as an answer desired by the creator, A dialogue engine learning system for an artificial intelligence character, characterized in that by inputting the second answer through the creator's answer input, the second answer is provided to each of the followers. According to claim 13,
the generator
The artificial intelligence character conversation engine learning system, characterized in that for generating the artificial intelligence character by giving at least one hash tag for a specific topic for learning the artificial intelligence character.

Images