Questionnaire method and system using a chatbot to which graphicons are applied

Abstract

To provide a questionnaire method and system employing chatbots with graphicons.SOLUTION: A method includes the steps of: setting a chatbot so as to use graphicons that imitate preset human paralinguistic element and nonverbal element; providing a question according to a preset questionnaire to a user terminal connected to communicate with a chatbot server and receiving an answer to the question employing the chatbot; and analyzing the answer and transmitting the graphicon corresponding to the answer among the graphicons to the user terminal.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to a questionnaire method and system using a chatbot to which Graphicon is applied. More specifically, the present invention relates to a method and system for conducting a questionnaire using a chatbot to which Graphicon is applied, which mimics human paralanguage elements and non-verbal elements.

Background Art

[0002] In using the web or applications, the utilization rate of chatbots is high. Chatbots are mainly used for the purpose of replacing CS (Customer Service) operations such as necessary Q&A (Questions & Answers) and FAQ (Frequently Asked Questions) when a user makes an inquiry to a service provider.

[0003] According to a report by the Korea Trade-Investment Promotion Agency, the domestic chatbot market size as of 2021 is understood to be growing at an average annual rate of 51%.

[0004] Conventional chatbots are provided mainly in text, so there are limitations in the use of paralanguage or non-verbal language that is difficult to convey as text, making it difficult to fully mimic human communication. At that time, paralanguage or non-verbal language means a communication method in addition to the linguistic content including facial expression, tone of voice, speaking speed, and intonation.

[0005] Recently, with the development of chatbot technology, it has also been used in the field of questionnaires. Similar to general chatbots, it conducts text-centered questionnaires. This lacks paralinguistic and non-verbal information, and as a result, it has been difficult to give the effect of conducting a questionnaire with a person. Therefore, when conducting a questionnaire, problems such as a decline in the quality of the data collected and a high level of fatigue and a decrease in satisfaction among users participating in the questionnaire have occurred.

[0006] To solve such conventional problems, paralinguistic or non-verbal is provided using graphicons, which are visual elements including emoticons, emojis, stickers, and GIF-formatted photos used when people communicate online with each other, and the existing questionnaire chatbot is utilized to overcome the shortcoming that it cannot imitate paralinguistic or non-verbal, thereby attempting to generate a questionnaire chatbot that imitates paralinguistic and non-verbal.

Summary of the Invention

Problems to be Solved by the Invention

[0007] The present invention is for solving the problems of the above-mentioned prior art, and relates to a method and a system for conducting a questionnaire using a chatbot to which graphicons imitating human paralinguistic elements and non-verbal elements are applied.

[0008] However, the technical problems to be achieved by this embodiment are not limited to the above-mentioned technical problems, and other technical problems can exist.

Means for Solving the Problems

[0009] As a technical means for achieving the above-described technical problems, an embodiment according to a first aspect of the present disclosure provides a questionnaire method using a chatbot to which graphicons are applied. The method includes setting the chatbot to use graphicons that mimic preset paralinguistic elements and non-linguistic elements of humans, providing a question based on a preset questionnaire to a user terminal communicatively connected to the chatbot server using the chatbot, receiving an answer regarding the question, and analyzing the answer to transmit the graphicons corresponding to the answer among the graphicons to the user terminal.

[0010] In addition, an embodiment according to a second aspect of the present disclosure provides a questionnaire system using a chatbot including a communication module, at least one processor, and a memory electrically connected to the processor and storing at least one code executed by the processor. When executed through the processor, the memory stores code that causes the processor to set the chatbot to use graphicons that mimic preset paralinguistic elements and non-linguistic elements of humans, provide a question based on a preset questionnaire to a user terminal communicatively connected to the chatbot server using the chatbot, receive an answer regarding the question, analyze the answer, and transmit the graphicons corresponding to the answer among the graphicons to the user terminal.

Advantages of the Invention

[0011] The present invention can implement a questionnaire using a chatbot to which graphicons are applied.

[0012] By mimicking para-linguistic and non-linguistic elements, which are fundamental components of human communication that cannot be expressed by existing chatbots through graphicons, it is possible to assist users' understanding of communication, provide users with the experience of communicating with humans, provide richer context information for conversations, and improve the quality of user response data collected through questionnaires and the user experience.

[0013] Note that the user experience of communicating with humans obtained from para-linguistic and non-linguistic expressions has the effect of conducting questionnaires in a way such as face-to-face interviews with users, thereby enabling large-scale questionnaires to be conducted and expecting higher response quality compared to existing questionnaires.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Best Mode for Carrying Out the Invention

[0015] Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings. However, the present disclosure can be implemented in various different forms and is not limited to the embodiments described herein. The accompanying drawings are for facilitating understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the accompanying drawings. All terms, including technical and scientific terms used herein, should be interpreted as having the meaning commonly understood by those of ordinary skill in the technical field to which the present disclosure pertains. Terms defined in a dictionary should be interpreted as having an additional meaning consistent with the relevant technical literature and the presently disclosed content, and should not be interpreted in an overly ideal or restrictive sense unless otherwise defined.

[0016] To clearly explain the present invention in the drawings, parts not related to the explanation are omitted, and the sizes, forms, and shapes of the components shown in the drawings can be variously deformed. The same / similar parts throughout the specification are denoted by the same / similar reference numerals.

[0017] Throughout the specification, when a part is said to be "connected (connected, contacted, or coupled)" to another part, this includes not only the case where it is "directly connected (connected, contacted, or coupled)", but also the case where other members are interposed therebetween and it is "indirectly connected (connected, contacted, or coupled)". In addition, when a part is said to "include (comprise or be provided with)" a certain component, this means that, unless otherwise stated to the contrary, it does not exclude other components, and it can further "include (comprise or be provided with)" other components.

[0018] As used herein, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Note that one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. On the other hand, the term "~ unit" is not limited to software or hardware, and the "~ unit" can also be configured to be in an addressable storage medium and can also be configured to cause one or more processors to execute. Therefore, as an example, the "~ unit" includes components such as software components, object-oriented software components, class components, and task components, and processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided in the components and the "~ unit" can not only be combined with a smaller number of components and "~ unit" or further separated into additional components and "~ unit", but also the components and the "~ unit" can be implemented to cause one or more CPUs in a device or a security multimedia card to execute.

[0019] Suffixes such as "module" and "unit" of the components used in the following description are given or mixed only for ease of preparation of the specification, and do not have a meaning or role that distinguishes them from each other as such. Note that when it is determined that a specific description of related known technologies obscures the gist of the embodiments disclosed in this specification in the description of the embodiments disclosed in this specification, the detailed description thereof will be omitted.

[0020] As used herein, terms representing ordinal numbers such as first, second, etc. are used only for the purpose of distinguishing one component from another and do not limit the procedures or relationships of the components. For example, the first component of the present disclosure can be named the second component, and similarly, the second component can also be named the first component. The singular forms used herein should be construed to include plural forms as well, unless clearly indicated to the contrary.

[0021] The "user terminal" mentioned below can be embodied as a computer or a mobile terminal that can be connected to a server or other terminals through a network. Here, the computer can include, for example, a notebook computer equipped with a web browser (WEB Browser), a desktop, a laptop, a VR HMD (such as HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.). Here, VR HMDs include those for PCs (such as HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), those for mobile devices (such as GearVR, DayDream, Baofeng Magic Mirror, Google Cardboard, etc.), and Stand Alone models (such as Deepon, PICO, etc.) that are embodied independently for consoles (PSVR). The mobile terminal can include, for example, as a wireless communication device that guarantees portability and mobility, not only smart phones, tablet PCs, wearable devices, but also various devices equipped with communication modules such as Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, ultrasonic, infrared, Wi-Fi (WiFi), Li-Fi, etc. Note that the "network" means a connection structure that enables information exchange between each node such as a terminal and a server, and includes a local area network (LAN), a wide area communication network (WAN), the Internet (WWW: World Wide Web), a wired / wireless data communication network, a telephone network, a wired / wireless television communication network, etc.Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WiMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC), LiFi, etc.

[0022] FIG. 1 is a diagram for explaining a questionnaire system using a chatbot according to an embodiment of the present invention.

[0023] Referring to FIG. 1, a questionnaire system using a chatbot includes a chatbot server (100) and a user terminal (200), and the chatbot server (100) and the user terminal (200) can be communicatively connected through a communication network. The chatbot server (100) can be formed of a cloud computing server such as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). Note that the chatbot server (100) may be constructed in the form of a private cloud, a public cloud, or a hybrid cloud system, but the scope of the present invention is not limited thereto.

[0024] The chatbot server (100) is set to use graphicons that imitate the pre-set para-linguistic and non-linguistic elements of humans by the chatbot. For example, the para-linguistic elements include at least one of text and images that express tone of voice, intonation, accent, rhythm, and sound field used in communication as detailed elements, and the non-linguistic elements can include images related to eye contact, facial expressions, movements, and body language used in communication as detailed elements.

[0025] The chatbot server (100) provides questions based on a pre-set questionnaire to the user terminal (200) communicatively connected to the chatbot server (100) using the chatbot, and receives answers regarding the questions.

[0026] The chatbot server (100) analyzes the answers and transmits the graphicons corresponding to the answers among the graphicons to the user terminal (200). For example, in the case of a multiple-choice question, the answer can be one selected option from the options included in the multiple-choice question. The chatbot server (100) can provide the graphicons pre-stored by matching the options. Or in the case of a descriptive question, the answer can be a text containing one or more words. The chatbot server (100) can perform sentiment analysis on the text and provide graphicons according to the sentiment analysis result.

[0027] The user terminal (200) can be communicatively connected to the chatbot server (100) through a communication network. The user terminal (200) can mean any type of handheld-based wireless communication device such as a notebook computer equipped with a web browser, a desktop, a laptop, a wireless communication device that guarantees portability and mobility, or a smartphone, a tablet PC, etc.

[0028] Figure 2 is a diagram showing the detailed configuration of the chatbot server shown in Figure 1.

[0029] Referring to Figure 2, the chatbot server (100) can include a communication module (110), a processor (120), and a memory (130).

[0030] The communication module (110) can include devices that include the hardware and software necessary to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

[0031] The communication module (110) can receive answers to the questionnaire questions from the user terminal (200). Note that the communication module (110) can transmit graphic icons corresponding to the questionnaire questions and answers to the user terminal (200).

[0032] The processor (120) can include various types of devices that control and process data. The processor (120) can mean a data processing device incorporated in hardware having a physically structured circuit for executing functions represented by codes or instructions included in a program.

[0033] As an example, the processor (120) can be embodied in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

[0034] The processor (120) executes operations according to the code stored in the memory (130).

[0035] The memory (130) can store at least one or more of the information and data input to the communication module (110), the information and data necessary for the functions executed by the processor (120), and the data generated according to the execution of the processor (120).

[0036] The memory (130) should be interpreted as a general term for a non-volatile memory device that continues to maintain the stored information even when no power is supplied and a volatile memory device that requires power to maintain the stored information. The memory (130) can include a self-memory medium (magnetic storage media) or a flash storage media in addition to the volatile memory device that requires power to maintain the stored information, but the scope of the present invention is not limited thereto.

[0037] The memory (130) is electrically connected to the processor (120) and stores at least one code executed by the processor (120). When executed through the processor (120), the memory (130) stores code that causes the processor (120) to execute functions and procedures as follows.

[0038] The memory (130) stores code that causes it to use graphicons that mimic the pre-set paralinguistic and non-linguistic elements of a human for the chatbot.

[0039] For example, graphicons including emoticons, emojis, stickers, and photos / GIFs in the chatbot server (100) are configured in the form of a table by visual, auditory, and tactile methods, and the graphicons can be classified and stored by visual, auditory, and tactile methods. The stored graphicons can be used by the chatbot server (100) to perform sentiment analysis on the responses of the user terminal (200) described later and provided as chatbot responses corresponding to the sentiment analysis results.

[0040] The memory (130) stores code that causes it to include at least one of text and images that represent pitch, intonation, accent, rhythm, and sound field used in communication as detailed elements of paralinguistic elements, and images related to gaze, expression, movement, and body language used in communication as detailed elements of non-linguistic elements. For example, the graphicons can include images, emoji GIFs, images, and videos corresponding to paralinguistic elements or non-linguistic elements.

[0041] The memory (130) can store code that causes it to provide questions based on a questionnaire preset in a user terminal (200) communicatively connected to a chatbot server (100) using a chatbot and receive answers to the questions.

[0042] The memory (130) can store code that causes it to analyze the answers and transmit corresponding graphicons to the user terminal (200).

[0043] In the case of a multiple-choice question, the answer can be one selected option from among the options included in the multiple-choice question. The chatbot server (100) can store code that causes it to provide a pre-stored graphicon that matches the option.

[0044] In the case of a descriptive question, the answer can be a passage containing one or more words. The chatbot server (100) can store code that causes it to perform sentiment analysis on the passage and provide a graphicon according to the sentiment analysis result.

[0045] In the memory (130), as the result of emotion analysis execution, a valence value regarding whether the polarity of the answer is positive or negative and an arousal value regarding whether the intensity of the answer is high or low are obtained, and code for causing the provision of a graphicon corresponding to the answer by using the valence value and the arousal value can be stored.

[0046] In the memory (130), when the valence value is positive and the arousal value is high, a graphicon corresponding to a preset high affirmation is provided, when the valence value is positive and the arousal value is low, a graphicon corresponding to a preset low affirmation is provided, when the valence value is negative and the arousal value is high, a graphicon corresponding to a preset high negation is provided, and code for causing the provision of a graphicon corresponding to a preset low negation when the valence value is negative and the arousal value is low can be stored.

[0047] FIG. 3 is a diagram for explaining a graphicon applied to a questionnaire system using a chatbot according to an embodiment of the present invention.

[0048] Referring to FIG. 3, the graphicon can be classified into emoticons, emojis, stickers, and photos / GIFs according to the form, and can be classified into visual, auditory, and tactile methods according to the expression method.

[0049] As shown in FIG. 3, the visual emoticon can be represented in the form of a smiling face, the visual emoji can be represented in the form meaning the best, the visual sticker can be represented in a state including people or animals, and the visual photo / GIF can be represented by a photo or a moving picture (GIF) of the meaning to be expressed.

[0050] JPEG0007690156000001.jpg33170

[0051] Thereafter, as shown in FIG. 3, the auditory emoticon can be represented in the form of blowing a whistle, the auditory emoji can be represented in the form of clapping hands, the auditory sticker can be represented in the form of making sounds including smiling people and animals, and the auditory photo / GIF can be represented in the form of an actual model making sounds for expression.

[0052] JPEG0007690156000002.jpg28170

[0053] Next, as shown in FIG. 3, the tactile emoticon can be represented in the form of stroking, the tactile emoji can be represented in the form of clapping, the tactile sticker can be represented in the form of including people and animals in a comforting manner, and the tactile photo / GIF can be represented by a photo of people putting their hands together with each other.

[0054] JPEG0007690156000003.jpg28170

[0055] FIG. 4 is a flowchart showing an inquiry process implemented by a chatbot server (100) according to an embodiment of FIG. 2.

[0056] Referring to FIG. 4, the chatbot server (100) collects user information, provides questions of a selective or descriptive questionnaire, receives the user's answers, and conducts the questionnaire in a procedure of rule-based or natural language processing sentiment analysis and non-verbal and para-verbal expression answers. At that time, the user information includes the user's address, age, gender, occupation, etc., and the criteria for questionnaire results can be set through the collection of user information. For example, questionnaires such as "singers preferred by age", "brands preferred by men (or women) in their 20s", and "annual income surveys by occupation" can be conducted.

[0057] FIG. 5 is a diagram showing a questionnaire screen provided to a user terminal (200) according to an embodiment of the present invention.

[0058] Referring to FIG. 5, the questionnaire screen provided to the user terminal (200) can start the questionnaire together with the text "Start Questionnaire", and the text "Hello! I am the HAS bot who proceeds with the questionnaire. I will ask you some questions to proceed with the questionnaire, so please answer carefully" can be provided together with a visual sticker. As the next question, the text "Has your lover ever persistently asked about the past?" can be provided, and as options for the answer, "1) Very much so, 2) So, 3) Normal, 4) Not so, and 5) Not at all so" can be provided.

[0059] And the user terminal (200) can input an answer using the keyboard. At this time, the answer can be implemented by inputting the applicable number from the options or the text corresponding to the number. The chatbot server (100) can perform sentiment analysis on the received answer and provide an answer corresponding to the sentiment analysis result, which can be like "Really?" in FIG. 5. And the text "It must have been very difficult" sharing the sentiment together with the answer can be provided together with a tactile sticker.

[0060] In the case of the options provided above, the nature of the answer is determined according to whether the nature of the question is affirmative or negative. Therefore, if the answer to an affirmative question is "Very much so", it will be an affirmative answer according to the sentiment analysis, and if the answer is "Not at all so", it may be a negative answer according to the sentiment analysis. Regarding the answer of the chatbot server (100) by such sentiment analysis, it will be described later with reference to FIG. 6.

[0061] Hereinafter, FIG. 6 is an exemplary diagram showing the process of performing sentiment analysis according to an embodiment of the present invention.

[0062] Referring to FIG. 6, the responses of the user terminal (200) regarding the questionnaire can perform sentiment analysis in a valence - arousal type. The valence value is a value that classifies and represents positive or negative in the direction of behavioral activation regarding emotions, and the arousal value is a value that classifies and indicates high or low in the intensity of emotional activation.

[0063] For example, when the polarity of the emotion is negative and the intensity is low, it can be expressed as VN - AL (Valence Negative - Arousal Low), and when the polarity of the emotion is negative and the intensity is high, it can be expressed as VN - AH (Valence Negative - Arousal High). In addition, when the polarity of the emotion is positive and the intensity is low, it can be expressed as VP - AL (Valence Positive - Arousal Low), and when the polarity of the emotion is positive and the intensity is high, it can be expressed as VP - AH (Valence Positive - Arousal High).

[0064] In this way, the graphicons provided when answering corresponding to the values according to the sentiment analysis results can also be classified according to the sentiment analysis results.

[0065] For example, if the sentiment analysis result value is an extreme value such as VN - AL or VP - AH, a red tooltip with text or a graphicon in the form of being flustered or surprised can be provided. Or if the sentiment analysis result value is a value distributed in the middle such as VN - AH or VP - AL, a blue tooltip with text or a graphicon in the form of showing empathy and smiling can be provided. However, for moderate emotions, graphicons cannot be provided.

[0066] Hereinafter, FIG. 7 is a diagram showing the procedure of a questionnaire method using a chatbot according to another embodiment of the present invention.

[0067] FIG. 8 is a diagram showing detailed steps related to a partial step of the questionnaire method using the chatbot shown in FIG. 7.

[0068] The questionnaire method using the chatbot described below can be implemented by the questionnaire system and server using the chatbot described with reference to FIGS. 1 to 6 above. Therefore, the content of the embodiments of the present disclosure described with reference to FIGS. 1 to 6 above can also be similarly applied to the embodiments described below, and the content overlapping with the above description will be omitted below. The steps described below are not necessarily to be executed in the order of the procedures, the procedures of the steps can be set variously, and the steps can be executed almost simultaneously.

[0069] Referring to FIG. 7, the questionnaire method using the chatbot includes a step of setting to use graphicons (S100), a step of providing questions and receiving answers (S200), and a step of transmitting graphicons to the user terminal (200) (S300).

[0070] The step of setting to use graphicons (S100) is a step of setting the chatbot to use graphicons that mimic preset paralinguistic and non-linguistic elements of humans.

[0071] The step of receiving answers (S200) is a step of providing questions based on a preset questionnaire to the user terminal (200) communicatively connected to the chatbot server (100) using the chatbot and receiving answers to the questions.

[0072] The step of transmitting graphicons to the user terminal (200) (S300) is a step of analyzing the answers and transmitting the graphicons corresponding to the answers to the user terminal (200).

[0073] Referring to FIG. 8, the step of receiving an answer (S200) and the step of transmitting a graphicon to the user terminal (200) (S300) can include detailed steps according to whether it is a multiple-choice question or a descriptive question.

[0074] In the case of a multiple-choice question, the answer is one selected option from among the options included in the multiple-choice question, and it is possible to provide a graphicon that is pre-stored by matching the option. At that time, rule-based sentiment analysis can be performed to select a graphicon that is pre-stored by matching the option.

[0075] In the case of a descriptive question, the answer is a sentence including one or more words, and as shown in FIG. 8 below, it can further include a sentiment analysis execution step (S310) and a graphicon providing step (S320) according to the execution result.

[0076] The sentiment analysis execution step (S310) is a step of performing sentiment analysis on the sentence, and the graphicon providing step (S320) according to the execution result is a step of providing a graphicon according to the sentiment analysis execution result. At that time, the sentiment analysis can perform sentiment analysis based on natural language processing.

[0077] An embodiment of the present invention can also be embodied in the form of a recording medium including computer-executable instructions such as a program module executed by a computer. A computer-readable medium is any available medium accessible by a computer, including all volatile and non-volatile media, and all removable and non-removable media. Note that the computer-readable medium can include all of the computer storage media. The computer storage media includes all volatile and non-volatile, removable and non-removable media embodied by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data.

[0078] The method and system of the present invention are described with respect to specific embodiments, but some or all of its components or operations can be implemented using a computer system having a general-purpose hardware architecture.

[0079] Those with ordinary knowledge in the technical field to which this disclosure pertains can understand that, based on the foregoing description, it can be easily deformed into other specific forms without changing the technical idea and essential features of this disclosure. Therefore, it should be understood that the embodiments described above are exemplary in all aspects and not restrictive. The scope of this disclosure is indicated by the claims described below, and all changes or modified forms derived from the meaning and scope of the claims, and concepts such as their equivalents, should be construed as being included within the scope of this disclosure. The scope of this specification is indicated by the claims described below after the foregoing detailed description, and all changes or modified forms derived from the meaning and scope of the claims, and concepts such as their equivalents, should be construed as being included within the scope of this specification.

Description of Reference Numerals

[0080] 100: Chatbot Server 100: Communication Module 120: Processor 130: Memory 200: User Terminal

Claims

1. In a method for generating a questionnaire chatbot performed by a chatbot server, a) setting to use graphicons that imitate human paraverbal and non-verbal elements preset for the chatbot; b) providing, using the chatbot, questions based on a preset questionnaire to a user terminal communicatively connected to the chatbot server and receiving answers to the questions; and c) analyzing the answers and transmitting, to the user terminal, the graphicons corresponding to the answers among the graphicons, wherein the graphicons including emoticons, emojis, stickers, and photos in the chatbot server are configured in a table form by expression methods of visual method, auditory method, and tactile method, and the graphicons are stored in each method, In the step b), the chatbot server collects user information including the user's address, age, gender, and occupation, sets criteria for questionnaire results based on the user information, provides questions of a multiple-choice or descriptive questionnaire to the user terminal, receives answers from the user terminal, performs rule-based sentiment analysis or natural language processing sentiment analysis, and provides answers of expressions including non-verbal elements and expressions including paraverbal elements, The paraverbal elements include at least one of text and image expressing tone, intonation, accent, rhythm, and sound field used in communication in detailed elements, The non-verbal elements include images related to gaze, expression, movement, and body language used in communication in detailed elements, and a questionnaire method using a chatbot characterized by this.

2. In the step b), in the case of a multiple-choice question, the answer is one selected option from among the options included in the multiple-choice question, and the step c) provides a graphicon pre-stored in matching with the option The questionnaire method using a chatbot according to Claim 1, characterized by this.

3. In the step b), in the case of a descriptive question, the answer is a sentence including one or more words, and the step c) includes c-1) performing sentiment analysis on the sentence; and c-2) providing a graphicon according to the sentiment analysis execution result The questionnaire method using the chatbot according to claim 1, characterized in that...

4. The step c-2) is... As the result of the sentiment analysis execution corresponding to the step c-1), obtain a valence value regarding whether the polarity of the answer is positive or negative and an arousal value regarding whether the intensity of the answer is high or low, and provide a graphicon corresponding to the answer using the valence value and the arousal value. The questionnaire method using the chatbot according to claim 3, characterized in that...

5. When the valence value is positive and the arousal value is high, provide the graphicon corresponding to a preset high affirmation. When the valence value is positive and the arousal value is low, provide the graphicon corresponding to a preset low affirmation. When the valence value is negative and the arousal value is high, provide the graphicon corresponding to a preset high negation. When the valence value is negative and the arousal value is low, provide the graphicon corresponding to a preset low negation. The questionnaire method using the chatbot according to claim 4, characterized in that...

6. A communication module; At least one processor; and A memory electrically connected to the processor and storing at least one code executed by the processor, When the memory is executed through the processor, the processor is... Set to use a graphicon that imitates preset paralinguistic and non-linguistic elements of a human, provide a question based on a preset questionnaire to a user terminal communicatively connected to a chatbot server using the chatbot, receive an answer to the question, analyze the answer, and cause the graphicon corresponding to the answer among the graphicons to be transmitted to the user terminal. The memory stores the code for this. The graphic icons including emoticons, emojis, stickers, and photos in the processor are configured in the form of a table by means of visual, auditory, and tactile expression methods, and the graphic icons are stored in each method, When the processor is executed through the processor, collect user information including the user's address, age, gender, and occupation, set criteria for the questionnaire results based on the user information, provide selective or descriptive questionnaire questions to the user terminal, receive answers from the user terminal, perform rule-based sentiment analysis or natural language processing sentiment analysis, and provide answers to expressions including non-verbal elements and expressions including paralinguistic elements, The paralinguistic elements are at least one of text and images that represent tone, intonation, accent, rhythm, and sound field used in communication in the detailed elements, The non-verbal elements are A questionnaire system using a chatbot, characterized in that it includes images related to eye contact, facial expressions, movements, and body language used in communication in the detailed elements.

7. The memory is In the case of a selective question, the answer is one selected option from the options included in the selective question, and when the processor is executed through the processor, the processor causes a pre-stored graphic icon to be provided that matches the option Further store the code The questionnaire system using the chatbot according to claim 6, characterized in that.

8. The memory is In the case of a descriptive question, the answer is a text containing one or more words, and when the processor is executed through the processor, the processor performs sentiment analysis on the text and causes a graphic icon corresponding to the sentiment analysis result to be provided Further store the code The questionnaire system using the chatbot according to claim 6, characterized in that.

9. The memory is When executed through the processor, the processor obtains, as the sentiment analysis execution result, a valence value regarding whether the polarity of the answer is positive or negative and an arousal value regarding whether the intensity of the answer is high or low, and causes to provide a graphicon corresponding to the answer by using the valence value and the arousal value. Further store the code The questionnaire system using the chatbot according to claim 8, characterized in that.

10. When the valence value is positive and the arousal value is high, provide the graphicon corresponding to the preset high affirmation. When the valence value is positive and the arousal value is low, provide the graphicon corresponding to the preset low affirmation. When the valence value is negative and the arousal value is high, provide the graphicon corresponding to the preset high negation. The questionnaire system using the chatbot according to claim 9, characterized in that when the valence value is negative and the arousal value is low, the graphicon corresponding to the preset low negation is provided.

Images