KR20210156513A - Apparatus for providing user interface based on chatbot using image carousel - Google Patents

Abstract

Presented is a chatbot-based user interface providing device for providing an image carousel operation, which allows a user to quickly check information on all carousels without having to move a carousel left or right. The presented chatbot-based user interface providing device for providing an image carousel operation comprises: a receiving unit for receiving a chatbot-based user input; and an answer interface processing unit for configuring one or more answers to the user input as the carousel, and processing and outputting a chatbot user interface so that one or more thumbnails corresponding to the one or more answers included in the carousel are included. The chatbot user interface includes an image area for outputting one selected from among answer images included in an image carousel, and a thumbnail area including the thumbnails corresponding to the answer images, respectively.

Description

Apparatus for providing user interface based on chatbot using image carousel}

The present invention relates to a chatbot-based user interface providing apparatus that provides image carousel operation, and more particularly, to an apparatus providing an efficient user interface to a user based on the chatbot.

A chatbot is an artificial intelligence (AI)-based communication software that provides answers to questions or various related information through conversations with people.

Chatbots are evaluated as a field with excellent growth potential because they possess the advantages of the Web, such as ease of service improvement and update, and the advantages of apps, such as accessibility and mobility.

With the recent development of artificial intelligence technology and the addition of natural language processing capabilities, application services combined with chatbots are emerging in more diverse fields. For example, chatbots are being used in various fields, such as providing an automatic response service by replacing an agent in a counseling center with a chatbot, or providing a product or content recommendation service based on the chatbot.

Conventionally, when providing a product or content recommendation service based on the above-described chatbot, an answer deemed appropriate as an answer to a user's query is provided in a predetermined form. For example, the answer may be provided to the user terminal as a carousel in the form of a card including an image area and/or a text answer.

However, when there are two or more carousels to be displayed on the user terminal, the first carousel is displayed on the user terminal as illustrated in FIG. 1 . In order to check the information of all carousels, it is necessary to check the card-shaped carousel by moving it sequentially to the left or right.

As such, in order to check all carousels, the carousel has to be moved from one end to the other with a large number of mouse clicks, and the problem is that representative images or titles of various cards cannot be checked at a glance in user experience (UX). There is this.

In other words, if it is assumed that the carousel in the form of ten cards is prepared for the user's query, the time from the first card to the tenth card is quite long, and there is a problem in that desired card information cannot be viewed at once.

Prior Art 1: Republic of Korea Patent Registration No. 10-2051890 (Chatbot-based response method) Prior art 2: Republic of Korea Patent Publication No. 10-2019-0053027 (Chatbot device using automatic question generation and its operation method)

The present invention has been proposed to solve the above conventional problems, and a chatbot-based user interface that provides image carousel operation so that information of all carousels can be easily and quickly checked without the need to move the carousel left or right The purpose is to provide a providing device.

In order to achieve the above object, a chatbot-based user interface providing apparatus for providing image carousel operation according to a preferred embodiment of the present invention includes: a receiving unit for receiving a chatbot-based user input; and an answer interface processing unit configured to form a carousel of one or more answers to the user input, and processing and outputting the chatbot user interface to include one or more thumbnails corresponding to the one or more answers included in the carousel. do.

The chatbot user interface may include an image area for outputting one selected from among answer images included in the image carousel, and a thumbnail area including thumbnails respectively corresponding to the answer images.

The answer interface processing unit may display a representative image of an answer corresponding to the selected thumbnail in the image area when any one of the thumbnails in the thumbnail area is selected.

When any one of the thumbnails in the thumbnail area is selected, the answer interface processing unit may display an answer corresponding to the selected thumbnail in the image area of the current screen without moving the image carousel.

Each thumbnail of the thumbnail area may be a simplified image of each answer to the user input.

According to the present invention having such a configuration, the total number of answers to the user input (ie, the total number of thumbnails) can be known at a glance, and even if the user clicks any one thumbnail in the thumbnail area, an image carousel or a text carousel Since the answer corresponding to the thumbnail is displayed in the image carousel or text carousel of the current screen without moving, all answers to the user input can be checked on the currently displayed screen, increasing user convenience.

1 is a view for explaining a conventional method of displaying a carousel slide.
2 is a block diagram of a system to which a chatbot-based user interface providing apparatus providing efficient carousel operation according to an embodiment of the present invention is applied.
FIG. 3 is an internal configuration diagram of the chatbot server shown in FIG. 2 .
4 is an example of an answer in the form of a user interface processed by the answer interface processing unit shown in FIG. 3 .
5 is another example of an answer in the form of a user interface processed by the answer interface processing unit shown in FIG. 3 .
6 is a flowchart illustrating a chatbot-based user interface providing method for providing efficient carousel operation according to an embodiment of the present invention.
7 to 11 are examples of screens employed to explain the operation of the chatbot-based user interface providing apparatus providing efficient carousel operation according to an embodiment of the present invention to provide a user interface through a conversation with a user.

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate the overall understanding, the same reference numerals are used for the same components in the drawings, and duplicate descriptions of the same components are omitted.

2 is a block diagram of a system to which a chatbot-based user interface providing apparatus providing efficient carousel operation according to an embodiment of the present invention is applied.

The system of FIG. 2 may include a user terminal 10 , a network 20 , and a chatbot server 30 .

The user terminal 10 is connected to the chatbot server 30 through the network 20 .

The user terminal 10 transmits the chatbot-based user input (eg, voice input by the user's speech, text input, button key input, thumbnail selection, etc.) to the chatbot server 30 through the network 20 . and a response to the user input may be received from the chatbot server 30 and displayed on the screen.

For example, the user terminal 10 may receive a voice according to the user's direct utterance, convert it into a message, and transmit it to the chatbot server 30 .

Also, the user terminal 10 may convert a predetermined text directly input by the user into a message and transmit it to the chatbot server 30 .

In addition, the user terminal 10 may transmit a button click signal corresponding thereto to the chatbot server 30 as the user clicks a predetermined button in the user interface (UI) on the screen.

In addition, the user terminal 10 may transmit a corresponding thumbnail selection signal to the chatbot server 30 as the user selects a predetermined thumbnail in the user interface (UI) on the screen.

The user terminal 10 may be implemented as a portable terminal or a portable computer. Here, the portable terminal is a wireless communication device that guarantees portability and mobility, and includes a Personal Communication System (PCS), a Global System for Mobile communications (GSM), a Personal Digital Cellular (PDC), a Personal Handyphone System (PHS), and a Personal Digital (PDA). Assistant), International Mobile Telecommunication (IMT)-2000, Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet (Wibro) terminals, etc. ) based wireless communication device. Portable computers may include notebook computers, laptops, and the like.

Also, the user terminal 10 may be various smart devices such as a smart phone, a smart note, a tablet PC, and a wearable computer.

The network 20 may be implemented as a wired network such as a local area network (LAN), a wide area network (WAN), or a value added network (VAN).

In addition, the network 20 includes all types such as a mobile radio communication network, a satellite communication network, Bluetooth, Wireless Broadband Internet (Wibro), High Speed Downlink Packet Access (HSDPA), Long Term Evolution (LTE), and the like. It can be implemented as a wireless network of

If necessary, the network 20 may be a network in which wired and wireless are mixed.

The chatbot server 30 can communicate with the user. For example, an artificial intelligence chatbot may be installed in the chatbot server 30 .

Accordingly, the chatbot server 30 searches for an answer corresponding to the user input from the user terminal 10 received through the network 20 , and determines the searched answer as an answer to the user input, so that the user terminal 10 ) can be sent to

In addition, the chatbot server 30 also induces a user's response by transmitting a response-induced question to the user terminal 10 .

3 is an internal configuration diagram of the chatbot server shown in FIG. 2 , FIG. 4 is an example of an answer in the form of a user interface processed by the answer interface processing unit shown in FIG. 3 , and FIG. 5 is the answer shown in FIG. It is another example of an answer in the form of a user interface processed by the interface processing unit.

The chatbot server 30 includes a user input receiving unit 31 , a user input analyzing unit 32 , a database 33 , an artificial intelligence-based answer generating unit 34 , an answer interface processing unit 35 , and a chatbot-based answer providing unit (36) may be included. The chatbot server 30 may be a chatbot-based user interface providing device described in the claims of the present invention.

The user input receiving unit 31 receives a chatbot-based user input from the user terminal 10 through the network 20 . Here, as described above, the user input may include a voice input, text input, button key input, thumbnail selection, etc. by the user's utterance.

The user input analyzer 32 may analyze the user input received by the user input receiver 31 .

For example, when the received user input is a natural language query based on an utterance or text, the user input analyzer 32 may analyze the corresponding natural language query to determine the contents of the received natural language query. Here, even if I do not explain in more detail about the analysis of natural language query words and grasping the contents, I think that those in the same industry will be able to fully understand it with well-known techniques.

Meanwhile, when the received user input is a button click signal, the user input analysis unit 32 may determine which button the button click signal refers to and notify the artificial intelligence-based answer generator 34 .

On the other hand, if the received user input is a thumbnail selection signal, the user input analysis unit 32 may identify which thumbnail the thumbnail selection signal refers to and notify the AI-based answer generation unit 34 .

The database 33 stores information for providing an answer to a user input. That is, it can be seen that the database 33 stores one or more answers that may correspond to a user input.

For example, if the chatbot server 30 is a knowledgebase-based chatbot server, in order to enable AIML (Artificial Intelligence Markup Language)-based pattern matching and ontology search, the database 33 stores knowledge It can be configured in the form of a knowledge graph in DB or memory. Accordingly, the chatbot server 30 may search the knowledge graph configured in the database 33 to find and provide an answer corresponding to the user input.

As another example, when the chatbot server 30 is a machine learning-based chatbot server, the database 33 is an optimal machine learning function model that has learned training data consisting of a large amount of key and value pairs. can be configured. Accordingly, the chatbot server 30 may receive an API query to the database 33 using a user input as an input value, and then receive an answer corresponding to the user input and an answer accuracy (ie, reliability (%)) as an output value. .

In the embodiment of the present invention, it can be seen that the data structure of the database 33 takes into account the case of providing an answer based on the above-described knowledge base, or the case of providing an answer based on machine learning, or both cases. .

In the case of machine learning based, the database 33 may automatically extract answer information corresponding to user input of query information from the machine learning based database, and output the extracted corresponding content.

This database 33 is learned through a machine learning algorithm, but based on the learned information, generates recommended answer information that can correspond to user input, or performs image analysis on an image file input by the user to automatically generate answer information It can also be extracted and generated, and it is possible to automatically extract and generate an answer to the information contained in the URL by parsing the specific URL entered by the user.

Machine learning algorithms include, for example, Ridge Regression, Logistic Regression, Generalized Linear Model, Random Forest, GradientBoosting Model, and Neural Networks. (Neural Network) and the like may be used.

Ridge regression is a basic linear model and provides additional parameters to handle outliers or outliers. Logistic regression analysis is a basic linear model, and it is effective to use it when the target variable, that is, the object to be predicted, shows a binomial distribution. The generalized linear model is a basic linear model, and it is effective to use it when the target variable shows a Poisson distribution. As a random forest ensemble model, it is a model composed of multiple decision trees. Each decision tree is developed individually considering the correlation between input variables and target variables, and has more flexible characteristics compared to the upper linear model. The change boosting model is also called the Generalized Boosting Model (GBM) and is an ensemble model with a similar tendency to a random forest, but there is a difference that each decision tree is developed considering the accuracy of an already created decision tree, so it often has higher accuracy than a random forest. It is also considered a model.

Neural networks are very flexible models that can predict virtually any target, and as parameters are tuned, they can cover both linear and non-linear patterns, so parameter tuning needs to be fine-tuned. In particular, neural networks are statistical learning algorithms inspired by neural networks in biology in machine learning and cognitive science, and deep learning methods can be implemented by complexly configuring these neural networks.

For example, the neural network may include an overall fully connected (FC), a convolutional neural network (CNN) that is optimized with Max Pooling and convolution, and a recurrent neural network (RNN) useful for time-series data.

The artificial intelligence-based answer generator 34 may search for one or more answers corresponding to the result (ie, analyzed user input) from the user input analyzer 32 through the database 33 .

When an answer matching the user input is found, the artificial intelligence-based answer generator 34 extracts the searched answer as an answer to the user input.

The answer interface processing unit 35 configures one or more answers to the user input into a carousel, and processes the chatbot user interface so that one or more thumbnails corresponding to one or more answers included in the carousel are included to provide a chatbot-based answer to (36).

For example, the answer interface processing unit 35 may be processed in the form of a chatbot user interface (UI) as illustrated in FIG. 4 or FIG. 5 .

In other words, as illustrated in FIG. 4 , the answer interface processing unit 35 includes an image area for outputting a selected one of answer images included in an image carousel, and thumbnails corresponding to the answer images, respectively. It can be processed in the form of a chatbot user interface (UI) including a thumbnail area including The chatbot user interface (UI) illustrated in FIG. 4 may include an image area 41 , a main title area 42 , a text answer area 43 , a button area 44 , and a thumbnail area 45 . The image area 41 may display a representative image of an answer corresponding to a user input. The large title area 42 may display a large title corresponding to a keyword in the user input. The text answer area 43 may display a text answer to the user input. Button area 44 may include one or more buttons. The thumbnail area 45 may include one or more thumbnails. That is, each thumbnail of the thumbnail area 45 can be said to be a simplified image of each answer adopted as an answer to a user input. For example, the thumbnail area 45 may display a maximum of about 5 thumbnails in one line from the left for each priority, and may consist of a maximum of two lines. The image displayed in the image area 41 may be a representative image of an answer generated based on a user input. The thumbnail area 45 may be formed below the button area 44 to be spaced apart from the button area 44 . Thumbnails of the thumbnail area 45 may be arranged based on the center point of the image carousel. Here, the image carousel may mean a card form in which the image area 41 , the large title area 42 , the text answer area 43 , and the button area 44 are integrated. If any thumbnail in the thumbnail area 45 is clicked (selected), the answer interface processing unit 35 will display a representative image of the answer corresponding to the clicked thumbnail in the image area 41, and the title area At 42, the title of the answer corresponding to the clicked thumbnail will be displayed, the text answer area 43 will display the text of the answer corresponding to the clicked thumbnail, and the button area 44 will display the clicked thumbnail. It will display one or more buttons attached to the corresponding answer.

In the chatbot user interface (UI) of FIG. 4 , the total number of answers to the user input (that is, the total number of thumbnails) can be known at a glance, and the answer interface processing unit 35 displays any one thumbnail in the thumbnail area 45 . When is selected, the answer corresponding to the selected thumbnail is displayed in the image area of the current screen without moving the image carousel, thereby increasing user convenience.

Although the chatbot user interface (UI) illustrated in FIG. 4 includes the text answer area 43 and the button area 44, if necessary, the text answer area 43 and/or the button area 44 do not exist free

Meanwhile, the answer interface processing unit 35 may process a chatbot user interface (UI) including a text answer area and one or more thumbnails as illustrated in FIG. 5 . The chatbot user interface (UI) illustrated in FIG. 5 may include a text answer area 51 , a button area 52 , and a thumbnail area 53 . The text answer area 51 may display a text answer to the user input. Button area 52 may include one or more buttons. The thumbnail area 53 includes one or more thumbnails. For example, the thumbnail area 53 may display a maximum of about 5 thumbnails in one line from the left for each priority, and may consist of a maximum of two lines. The text displayed in the text answer area 51 may be a text of a corresponding answer generated based on a user input. The thumbnail area 53 may be formed below the button area 52 to be spaced apart from the button area 52 . Thumbnails of the thumbnail area 53 may be arranged based on the center point of the text carousel. Here, the text carousel may mean a card form in which the text answer area 51 and the button area 52 are integrated. If any thumbnail in the thumbnail area 53 is clicked (selected), the answer interface processing unit 35 will display the text of the answer corresponding to the clicked thumbnail in the text answer area 51, and the button area 52 ) will display one or more buttons attached to the answer corresponding to the clicked thumbnail. In addition, when there are a plurality of thumbnails in the thumbnail area 53 as shown in FIG. 5 , the answer interface processing unit 35 may display different numbers for each thumbnail for classification by thumbnail.

Although it is assumed that the button area 52 is included in the chatbot user interface (UI) illustrated in FIG. 5 , the button area 52 may be omitted if necessary.

In the chatbot user interface (UI) of FIG. 5 , the total number of answers to the user input (that is, the total number of thumbnails) can be known at a glance, and the answer interface processing unit 35 displays any one thumbnail in the thumbnail area 53 . When is selected, an answer corresponding to the selected thumbnail is displayed in the text answer area of the current screen without moving the text carousel, thereby enhancing user convenience.

The above-described answer interface processing unit 35 processes the answer in the form of a chatbot user interface (UI) including an image carousel or text carousel, and a thumbnail and delivers it to the chatbot-based answer providing unit 36, so the chatbot user It may be called an interface (UI) processing unit.

The reason why the answer interface processing unit 35 processes the answer corresponding to the user input in the form of the chatbot user interface (UI) illustrated in FIG. 4 or 5 is that the user can more conveniently respond to his or her user input. in order to be able to confirm it. That is, in the past, in order to check all answers to user input, there was an inconvenience of moving the carousel from one end to the other with a large number of mouse clicks. However, according to an embodiment of the present invention, by selecting a thumbnail in the thumbnail area, all answers to the user input can be checked on the currently displayed screen without the need to move the carousel from one end to the other with a mouse click.

The chatbot-based answer providing unit 36 receives the answer transmitted from the answer interface processing unit 35 and transmits it to the user terminal 10 through the network 20 .

In FIG. 3 described above, the answer interface processing unit 35 and the chatbot-based answer providing unit 36 are configured respectively, but if necessary, they may be integrated into one module. That is, the chatbot-based answer providing unit 36 may be included in the answer interface processing unit 35 , or the answer interface processing unit 35 may be included in the chatbot-based answer providing unit 36 .

Although not shown in FIG. 3 described above, the chatbot server 30 may additionally include a dialogue unit for conversation with the user. A response-guided question may be sent to the user terminal 10 through the chat unit and a response from the user terminal 10 may be received. After all, since the response from the user terminal 10 is an example of a user input, the user input receiving unit 31 may be replaced with a chatting unit if necessary. In this case, it can be seen that the conversation unit performs both the functions of the user input receiving unit 31 as well as the functions of transmitting a response-induced question and receiving a response from the user terminal 10 .

Otherwise, the user input receiving unit 31 sends a response-induced question to the user terminal 10 as well as the above-described function (that is, the function of receiving the user input from the user terminal 10 through the network 20 ). All functions of sending and receiving a response from the user terminal 10 may be performed.

6 is a flowchart illustrating a chatbot-based user interface providing method for providing efficient carousel operation according to an embodiment of the present invention.

First, the user input receiving unit 31 receives a user input from the user terminal 10 through the network 20 (S10). Here, the user input may include a voice input by a user's utterance, a text input, a button key input, a thumbnail selection, and the like.

Thereafter, the user input analyzing unit 32 analyzes the user input received by the user input receiving unit 31 (S12). For example, when the user input is a natural language query based on an utterance or text, the user input analyzer 32 may analyze the corresponding natural language query to determine the contents of the received natural language query. On the other hand, when the user input is a button click signal, the user input analysis unit 32 may determine which button the button click signal refers to and notify the artificial intelligence-based answer generator 34 . Meanwhile, if the user input is a thumbnail selection signal, the user input analysis unit 32 may determine which thumbnail the thumbnail selection signal refers to and notify the AI-based answer generation unit 34 .

Next, the artificial intelligence-based answer generating unit 34 searches for one or more answers corresponding to the analysis result (ie, user input) of the user input analyzing unit 32 through the database 33 . And, when an answer matching the user input is found, the artificial intelligence-based answer generating unit 34 extracts (generates) the searched answer as an answer to the user input (S14).

Thereafter, the answer interface processing unit 35 processes at least one answer received from the artificial intelligence-based answer generation unit 34 in the form of a chatbot user interface (UI) including an image carousel or text carousel, and a thumbnail. and transmits it to the chatbot-based answer providing unit 36 (S16).

Accordingly, the chatbot-based answer providing unit 36 provides the answer from the answer interface processing unit 35 to the user terminal 10 through the network 20 (S18).

That is, the chatbot-based answer providing unit 36 transmits the answer processed by the answer interface processing unit 35, that is, the chatbot user interface (UI) illustrated in FIG. 4 or 5 through the network 20 to the user terminal 10 can be provided to 4 shows an example of a chatbot user interface (UI) provided when the user makes a speech related to image 1, and FIG. 5 is a chatbot user provided when the user makes a speech related to the text answer (1) It can be said that an example of an interface (UI) is shown.

Meanwhile, the chatbot-based user interface providing apparatus providing efficient carousel operation according to an embodiment of the present invention may provide an appropriate answer to the user through a conversation with the user. This will be described with reference to FIGS. 7 to 11 .

For example, for a user to receive cosmetic recommendations, the chatbot-based user interface providing apparatus according to an embodiment of the present invention recommends cosmetics suitable for the user through sequential conversations with the user as shown in FIGS. 7 and 8 . can do it In this case, the recommendation details (ie, answers) may be displayed in the form of a chatbot user interface (UI) including an image carousel and a plurality of thumbnails as shown in FIG. 8 .

As another example, as shown in FIGS. 9 to 11, a user who visits a certain shopping mall can inquire about the purpose of the visit (eg, product delivery, exchange & refund, order cancellation, other inquiries, etc.) and provide an answer corresponding to the purpose of the visit. can First, as shown in FIG. 9 , a chatbot user interface (UI) including an image carousel and a plurality of thumbnails is transmitted to the user terminal 10 . At this time, the user can select any one from among a plurality of thumbnails (image 1 to image 5) illustrated in FIG. 9 and select a desired category (eg, one of product delivery, exchange & refund, order cancellation, and other inquiries). . If the user selects a thumbnail (image 2) from among a plurality of thumbnails (image 1 to image 5), the chatbot-based user interface providing apparatus according to an embodiment of the present invention provides a display of the thumbnail (image 2) as shown in FIG. A representative image is displayed in the image area. After that, if the user sets the category to Exchange & Refund and selects an exchange & refund inquiry, the chatbot-based user interface providing apparatus according to an embodiment of the present invention provides a chatbot user interface (UI) as shown in FIG. 11 to the user terminal 10 can be sent to

In addition, the chatbot-based user interface providing method for providing efficient carousel operation of the present invention described above can be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. In addition, the computer-readable recording medium is distributed in a computer system connected through a network, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the method can be easily inferred by programmers in the art to which the present invention pertains.

As described above, the best embodiment has been disclosed in the drawings and the specification. Although specific terms have been used herein, they are only used for the purpose of describing the present invention and are not used to limit the meaning or scope of the present invention described in the claims. Therefore, it will be understood by those skilled in the art that various modifications and equivalent other embodiments are possible therefrom. Accordingly, the true technical protection scope of the present invention should be defined by the technical spirit of the appended claims.

10: user terminal 20: network
30: chatbot server 31: user input receiving unit
32: user input analysis unit 33: database
34: artificial intelligence-based answer generating unit 35: answer interface processing unit
36: Chatbot-based answer provider

Claims (4)

a receiver for receiving a chatbot-based user input; and
Constructing one or more answers to the user input into a carousel, and an answer interface processing unit for processing and outputting the chatbot user interface so that one or more thumbnails corresponding to the one or more answers included in the carousel are included; ,
The chatbot user interface is
An image area for outputting any one selected from among the answer images included in the image carousel, and a thumbnail area including thumbnails corresponding to each of the answer images,
A chatbot-based user interface providing device. The method of claim 1,
The answer interface processing unit,
When any one of the thumbnails in the thumbnail area is selected, displaying a representative image of the answer corresponding to the selected thumbnail in the image area,
A chatbot-based user interface providing device. The method of claim 1,
The answer interface processing unit,
When any one of the thumbnails in the thumbnail area is selected, the answer corresponding to the selected thumbnail is displayed in the image area of the current screen without moving the image carousel,
A chatbot-based user interface providing device. The method of claim 1,
each thumbnail in the thumbnail area is a simplified image of each answer to the user input;
A chatbot-based user interface providing device.

Images