Method for providng lecture content using virtual human

Abstract

The present invention relates to a method for providing lecture content using a virtual human, comprising: receiving a lecture script from a terminal of a specific instructor; generating basic lecture content in which a virtual human simulating the specific instructor conducts a lecture based on the lecture script and modeling data stored in a database; generating final lecture content by combining a background image for the lecture with the basic lecture content; and providing the final lecture content to a student's terminal.

Description

Technology Field

[0001] The present invention relates to a method for providing lecture content, and more specifically, to a method for providing lecture content that innovates the lecture production process and improves productivity by utilizing a virtual human. Background Technology

[0002] A virtual human is realized through digital technology that digitizes and analyzes human physical structure and movements to reproduce those movements in a virtual space as if they were a real person. Virtual humans are also referred to as digital humans or cyber humans, and technologies such as artificial intelligence (AI) and Text-to-Video (TTV) are being utilized to produce video content featuring these virtual humans.

[0003] Recently, virtual humans are being commercially utilized as advertising and promotional models, but they are not yet being used in educational fields such as lectures. The problem to be solved

[0004] The objective of the present invention, devised to solve the aforementioned problems, is to provide a method for providing lecture content utilizing a virtual human that can resolve the physical, spatial, and temporal constraints caused by existing lecture content production methods by producing lecture content utilizing a virtual human.

[0005] In addition, another objective of the present invention is to provide a method for providing lecture content using a virtual human, which innovates the lecture production process and dramatically improves productivity, thereby enabling the flexible production of lectures of various topics and contents and, consequently, greatly increasing the diversity of lectures. means of solving the problem

[0006] A method for providing lecture content using a virtual human according to an embodiment of the present invention may include the steps of: receiving a lecture script from a terminal of a specific instructor; generating basic lecture content in which a virtual human simulating the specific instructor conducts a lecture based on the lecture script and modeling data stored in a database; generating final lecture content by combining a background image for the lecture with the basic lecture content; and providing the final lecture content to a student's terminal.

[0007] In addition, the method for providing lecture content utilizing the virtual human further includes a step of setting a student title included in the lecture script, and the step of setting a student title included in the lecture script may provide a first mode for setting a student title by combining 'nim' with the student's name or ID, a second mode for setting a student title by combining 'a' or 'ya' with the student's name or ID, a third mode for automatically setting a student title by comparing the student's age with the age of the specific instructor, and a fourth mode for setting a student title using a name entered from the student's terminal.

[0008] In addition, in the fourth mode, if the name entered from the student's terminal includes a pre-set forbidden word, the student's terminal may be required to re-enter the name.

[0009] Additionally, the method may further include the steps of receiving a question from the terminal of a student who has viewed the final lecture content and transmitting the question to the terminal of the specific instructor, receiving an answer script for the question from the terminal of the specific instructor, generating answer content in which the virtual human performs an answer based on the answer script and the modeling data, and providing the answer content to the student's terminal.

[0010] In addition, a step of setting the student title included in the above answer script to be the same as the student title included in the above lecture script may be further included.

[0011] In addition, when multiple specific points regarding the final lecture content are selected from the student's terminal, the method may further include the step of providing an interface to the student's terminal that allows questions to be entered for each of the multiple specific points.

[0012] Additionally, when a plurality of specific points in time regarding the final lecture content are selected from the terminal of the student, the method may further include the steps of extracting a plurality of unit lecture contents, each containing a plurality of specific points in time, from the final lecture content, combining the extracted plurality of unit lecture contents to generate a replay lecture content, and providing the replay lecture content to the terminal of the student.

[0013] In addition, it may further include a step of searching for non-standard words included in the above lecture script and modifying the searched non-standard words into pre-set standard words.

[0014] In addition, the method may further include a step of modifying the endings related to relative honorifics included in the lecture script to have multiple ending forms selected from among the pre-set ending forms of relative honorifics, including '하십시오체', '하오체', '하게체', '해라체', '해요체', and '해체'.

[0015] In addition, the application ratio of the selected multiple ending forms can be set to a ratio input from the specific instructor's terminal. Effects of the invention

[0016] According to the present invention as described above, by producing lecture content utilizing a virtual human, a method for providing lecture content utilizing a virtual human can be provided that can resolve the physical, spatial, and temporal constraints caused by existing lecture content production methods.

[0017] In addition, according to the present invention, by innovating the lecture production process and dramatically increasing productivity, lectures of various topics and contents can be flexibly produced, and accordingly, a method for providing lecture content using a virtual human can be provided that can greatly increase the diversity of lectures. Brief explanation of the drawing

[0018] FIG. 1 is a diagram showing a lecture content provision system utilizing a virtual human according to an embodiment of the present invention. Figure 2 is a diagram showing the configuration of a lecture content provision system according to an embodiment of the present invention. FIG. 3 is a diagram showing a content creation module according to an embodiment of the present invention in more detail. FIG. 4 is a diagram illustrating a method for providing lecture content using a virtual human according to an embodiment of the present invention. Figure 5 is a diagram showing a lecture script according to an embodiment of the present invention. FIG. 6 is a diagram illustrating a method for providing answer content using a virtual human according to an embodiment of the present invention. FIG. 7 is a diagram showing a question input interface according to an embodiment of the present invention. FIG. 8 is a diagram illustrating the step of generating replay lecture content according to an embodiment of the present invention. FIG. 9 is a diagram showing the ending of a relative honorific form according to an embodiment of the present invention. Specific details for implementing the invention

[0019] In the following, embodiments related to the present invention are illustrated in the drawings and described in detail through the detailed description. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention.

[0020] In describing the components of the present invention, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the component from other components, and the essence, order, or sequence of the component is not limited by such terms. Furthermore, where it is stated in this specification that a component is "connected," "coupled," or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but that another component may also be "connected," "coupled," or "connected" between each component. In the case of "connection," "coupled," or "connected," it may be understood not only as being physically "connected," "coupled," or "connected," but also, if necessary, electrically "connected," "coupled," or "connected."

[0021] Terms such as "~part (unit)," "~device," "~part," and "~module" as used in this specification refer to a unit that processes at least one function or operation, and may be implemented in hardware, software, or a combination of hardware and software. Furthermore, terms such as "include," "compose," or "have" as used in this specification, unless specifically stated otherwise, mean that the relevant component may be inherent; therefore, they should be interpreted as allowing for the inclusion of additional components rather than excluding other components.

[0022] Furthermore, it is intended to clarify that the classification of components in this specification is merely based on the primary function each component is responsible for. That is, two or more components described below may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Additionally, each component described below may additionally perform some or all of the functions of other components in addition to its primary function, and it is obvious that some of the primary functions of each component may be exclusively performed by other components.

[0023] Hereinafter, with reference to the drawings related to the embodiments of the present invention, a system and method for providing lecture content utilizing a virtual human according to an embodiment of the present invention will be described.

[0024] FIG. 1 is a diagram showing a lecture content provision system utilizing a virtual human according to an embodiment of the present invention.

[0025] Referring to FIG. 1, a lecture content provision system utilizing a virtual human (1, hereinafter referred to as the lecture content provision system) according to an embodiment of the present invention is network-connected to an instructor terminal (2) and a student terminal (3), and can generate lecture content utilizing a virtual human based on script information received from the instructor terminal (2), and provide the content to the student terminal (3).

[0026] First, the network may be a high-speed backbone network of a large telecommunications network capable of data transmission and reception services, and may be a next-generation wireless network including Wi-Fi, WiGig, Wibro (Wireless Broadband Internet), WiMAX (World Interoperability for Microwave Access), etc., for providing the Internet or high-speed multimedia services.

[0027] The above Internet may refer to a global open computer network structure that provides the TCP / IP protocol and various services existing in the upper layer, such as HTTP (Hyper Text Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service), NIS (Network Information Service), etc., and may provide an environment that enables instructor terminals (2) and student terminals (3), etc., to connect to the system.

[0028] Meanwhile, the above-mentioned internet may be a wired or wireless internet, and may also be a core network integrated with a wired public network, a wireless mobile communication network, or a mobile internet. If the network is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. As an example of an embodiment of the above-mentioned asynchronous mobile communication network, a WCDMA (Wideband Code Division Multiple Access) network may be cited. In this case, although not shown in the drawings, the above-mentioned mobile communication network may include, for example, an RNC (Radio Network Controller). Meanwhile, although the above-mentioned WCDMA network was given as an example, it may be a next-generation communication network such as a 3G network, 4G network, or 5G network, or other IP-based IP networks. However, the network is not limited to those described above, and any modern data communication network may be applied.

[0029] Next, the terminal (2, 3) may be defined as a digital device that includes a function to communicate after connecting to the lecture content provision system (1) and a display function to output images or text. For example, the terminal (2, 3) may include a desktop computer, a laptop computer, a tablet PC (personal computer), a wireless phone, a mobile phone, a smartphone, etc., but is not limited thereto, and any digital device equipped with memory means and equipped with a processor to have computational capabilities may be adopted as the terminal (2, 3) according to the present invention.

[0030] Accordingly, a student who wishes to take the lecture content provided by the lecture content provision system (1) can access the lecture content provision system (1) through a terminal (3) to view the lecture content they want, and can transmit and receive data and information necessary to use the service through a network.

[0031] In addition, an instructor who wishes to produce lecture content through the lecture content provision system (1) can access the lecture content provision system (1) through a terminal (2) to create a virtual human in the form of a clone resembling himself, and create lecture content in which the virtual human conducts the lecture, and can transmit and receive data and information such as scripts through a network to use the service.

[0032] The instructor terminal (2) and student terminal (3) described above may include a browser-related program or application that enables receiving a user interface (UI) from the lecture content provision system (1).

[0034] Figure 2 is a diagram showing the configuration of a lecture content provision system according to an embodiment of the present invention.

[0035] Referring to FIG. 2, a lecture content provision system (1) according to an embodiment of the present invention may include a database (10), a script processing module (20), a content creation module (30), and an interface provision module (40).

[0036] The database (10) can store script-related data (e.g., lecture script, answer script, etc.), student information (e.g., name, gender, age, ID, etc.), instructor information (e.g., name, gender, age, ID, etc.), virtual human-related modeling data, etc. Additionally, the database (10) can store data and information necessary for the operation and function implementation of the lecture content provision system (1), such as information on prohibited words related to student titles and information on non-standard words for each instructor.

[0037] The database (10) can be implemented as one or more as needed.

[0038] The script processing module (20) can receive lecture scripts and answer scripts transmitted from the instructor terminal (2) and can perform preprocessing operations on the received scripts. For example, the script processing module (20) can set the student titles included in the lecture scripts and answer scripts, or search for non-standard words included in the scripts and modify them into pre-set standard words. In addition, the script processing module (20) can modify the endings related to relative honorifics included in the lecture scripts and answer scripts to suit the instructor's characteristics.

[0039] The script processing module (20) can transmit the script reflecting the above-described preprocessing operation to the content creation module (30).

[0040] The content creation module (30) can create basic lecture content in which a virtual human resembling a specific instructor conducts a lecture based on the lecture script transmitted from the script processing module (20) and the modeling data stored in the database (10). That is, in the basic lecture content, a virtual human resembling the appearance of the instructor who wrote the lecture script appears and conducts the lecture according to the lecture script. Subsequently, the content creation module (30) can create final lecture content by combining a background image for the lecture with the basic lecture content.

[0041] Additionally, the content creation module (30) can generate answer content in which a virtual human resembling a specific instructor answers a student's question based on the answer script transmitted from the script processing module (20) and the modeling data stored in the database (10). That is, in the answer content, a virtual human resembling the appearance of the instructor who wrote the answer script appears and answers the question according to the answer script.

[0042] The interface providing module (40) can provide a user interface to the terminals (2, 3) of instructors and students who wish to use the lecture content providing system (1).

[0043] For example, the interface providing module (40) can provide a user interface that allows inputting scripts, background images for lectures, etc., into the instructor terminal (2) and viewing content generated through the content creation module (30). Additionally, the interface providing module (40) can provide a user interface that allows searching and viewing various content generated through the content creation module (30) into the student terminal (3), and the student can input questions, etc., regarding specific lecture content through the user interface.

[0045] FIG. 3 is a diagram showing a content creation module according to an embodiment of the present invention in more detail.

[0046] Referring to FIG. 3, a content generation module (30) according to an embodiment of the present invention may include a voice conversion unit (31), an image generation unit (32), and a synthesis unit (33).

[0047] The voice conversion unit (31) can convert a lecture script transmitted from the script processing module (20) into a lecture voice part (S). To perform this voice conversion operation, the voice conversion unit (31) may include a Text-to-Speech (TTS) module composed of an encoder, a decoder, and a vocoder, and the TTS module may reflect the voice characteristics of the instructor through machine learning.

[0048] The video generation unit (32) can generate basic lecture content (C1) in which a virtual human (VH) conducts a lecture based on modeling data stored in the database (10). At this time, the virtual human (VH) can be modeled in a form that mimics the appearance of an actual instructor, and the modeling data for this can be classified into a library form for each instructor and stored in the database (10).

[0049] Additionally, the video generation unit (32) can generate basic lecture content (C1) by combining a lecture voice part (S) generated by the voice conversion unit (31) with a modeled virtual human (VH). At this time, the video generation unit (32) can change the mouth shape of the virtual human (VH) in synchronization with the lecture voice part (S), thereby generating a more natural virtual human (VH).

[0050] The synthesis unit (33) can generate a final lecture content (C2) by combining a lecture background image (BI) with the basic lecture content (C1) generated by the video generation unit (32). The lecture background image (BI) can be transmitted from the instructor terminal (2) and stored in the database (10), and can be synthesized at specific intervals of the basic lecture content (C1) to form the background image of the final lecture content (C2).

[0051] Meanwhile, the content creation module (30) can create answer content in which a virtual human (VH) answers a student's question in the same way.

[0052] For example, the voice conversion unit (31) can convert the answer script transmitted from the script processing module (20) into an answer voice part. Subsequently, the video generation unit (32) can generate answer content by combining the answer voice part generated by the voice conversion unit (31) with the modeled virtual human (VH).

[0053] Additionally, if necessary, a process of combining a background image with the answer content can be carried out through the synthesis unit (33).

[0055] FIG. 4 is a diagram illustrating a method for providing lecture content using a virtual human according to an embodiment of the present invention.

[0056] Hereinafter, a method for providing lecture content using a virtual human according to an embodiment of the present invention (hereinafter, a method for providing lecture content) will be described by referring together with the embodiments and drawings related to the lecture content provision system (1) described above. In addition, descriptions of content that overlap with the embodiments related to the lecture content provision system described above will be omitted.

[0057] Referring to FIG. 4, a method for providing lecture content according to an embodiment of the present invention may include a lecture script input step (S11), a basic lecture content creation step (S12), a final lecture content creation step (S13), and a lecture content provision step (S14).

[0058] In the lecture script input step (S11), a lecture script can be received from a specific instructor's terminal (2). This step (S11) can be performed by a script processing module (20), and for this purpose, an interface providing module (40) can receive the lecture script through a user interface and input it to the script processing module (20).

[0059] In the basic lecture content generation step (S12), basic lecture content (C1) can be generated in which a virtual human (VH) simulating the specific instructor conducts a lecture based on the lecture script entered in the lecture script input step (S11) and the modeling data stored in the database (10). This step (S12) can be performed by the content generation module (30).

[0060] In the final lecture content creation step (S13), the final lecture content (C2) can be created by combining the basic lecture content (C1) created in the basic lecture content creation step (S12) with a lecture background image (BI). This step (13) can be performed by the content creation module (30).

[0061] In the lecture content provision step (S14), the final lecture content (C2) generated in the final lecture content creation step (S13) can be provided to the student's terminal (3). This step (S14) can be performed by the interface provision module (40).

[0062] By performing each of the steps described above (S11, S12, S13, S14), lecture content can be generated in which a virtual human (VH) conducts the lecture. Accordingly, not only can the physical, spatial, and temporal constraints caused by existing lecture content production methods be resolved, but educational effects similar to those of an instructor actually conducting a lecture can also be achieved.

[0063] In addition, according to the aforementioned method of providing lecture content, the production process of lecture content is innovated and productivity is dramatically improved, thereby allowing for the flexible production of lectures on various topics and content, and consequently, the diversity of lectures can be greatly increased.

[0065] Figure 5 is a diagram showing a lecture script according to an embodiment of the present invention.

[0066] Referring to FIG. 5, the method for providing lecture content according to an embodiment of the present invention may further include the step of setting a student title included in the lecture script.

[0067] This step can be performed by a script processing module (20), and the script processing module (20) can set the student title in each mode by referring to student information and instructor information stored in the database (10).

[0068] Specifically, in this step, a first mode for setting a student title by combining 'nim' with the student's name or ID, and a second mode for setting a student title by combining 'a' or 'ya' with the student's name or ID may be provided.

[0069] For example, if the student's name is 'Cheolsu', the student title included in the lecture script can be set to 'Mr. Cheolsu' in the first mode, and the student title included in the lecture script can be set to 'Cheolsu-ya' in the second mode.

[0070] In addition, this stage may provide a third mode that automatically sets the student's title by comparing the student's age with the age of a specific instructor.

[0071] For example, if the age of a student and the age of a specific instructor are the same or the age difference is less than or equal to a preset age gap, they are recognized as friends or peers, and the student title according to the second mode above may be applied. Additionally, if the age difference between a student and a specific instructor exceeds a preset value and the student's age is younger than the specific instructor's age, the student title according to the second mode above may be applied; and if the age difference between a student and a specific instructor exceeds a preset value and the student's age is older than the specific instructor's age, the student title according to the first mode above may be applied.

[0072] In Mode 3, it is possible to set student titles by additionally reflecting information regarding the student's gender and the specific instructor's gender. For example, if the age difference between a student and a specific instructor exceeds a preset value and the student is older than the instructor, student titles can be set by combining words such as 'hyung', 'nuna', 'oppa', or 'unni' with the student's name or ID.

[0073] In addition, at this stage, a fourth mode may be provided to set the student's title using a name entered from the student's terminal (3). For example, if there are many students, a group name (e.g., 'Children of 5th Grade Class 3') may be set as the student's title.

[0074] However, in this case, since problematic student titles must be filtered, the script processing module (20) can determine whether the name entered from the student's terminal (3) contains a prohibited word by referring to the prohibited word information stored in the database (10). If the name contains a prohibited word, the student's terminal (3) may be required to re-enter the name.

[0075] When taking the lecture content, the student can select and use the mode they want among the modes described above, and in response, the script processing module (20) can set the student's title included in the lecture script to a name corresponding to the mode. Accordingly, in the final lecture content (C2), the virtual human (VH) can refer to the student by the pre-set title, thereby enhancing the student's immersion in the lecture.

[0076] Meanwhile, the part of the lecture script where the student's title is to be inserted can be indicated by symbols, characters, spaces, other identifiers, etc., and the script processing module (20) can search for the corresponding part and automatically insert a pre-set student's title. At this time, the particle associated with the student's title can also be automatically changed together to conform to the grammar.

[0078] FIG. 6 is a diagram illustrating a method for providing answer content using a virtual human according to an embodiment of the present invention.

[0079] Referring to FIG. 6, a method for providing lecture content according to an embodiment of the present invention may include a question input step (S21), an answer script input step (S22), an answer content generation step (S23), and an answer content provision step (S24).

[0080] In the question input step (S21), questions are received from the terminal (3) of the student who watched the final lecture content (C2), and the questions can be transmitted to the terminal (2) of a specific instructor. This step (S21) can be performed by an interface providing module (40).

[0081] In the answer script input step (S22), an answer script for a question can be received from a specific instructor's terminal (2). This step (S22) can be performed by a script processing module (20), and to this end, an interface providing module (40) can receive the answer script through a user interface and input it to the script processing module (20).

[0082] In the answer content generation step (S23), answer content can be generated in which a virtual human (VH) simulating a specific instructor delivers an answer based on the answer script entered in the answer script input step (S22) and the modeling data stored in the database (10). This step (S23) can be performed by a content generation module (30) and can be carried out in the same manner as the basic lecture content generation step (S12) described above.

[0083] Additionally, in this step (S23), if necessary, a process of combining a background image with the answer content may be additionally performed, in the same way as the final lecture content creation step (S13).

[0084] In the answer content provision step (S24), the answer content generated in the answer content creation step (S23) can be provided to the student's terminal (3). This step (S14) can be performed by the interface provision module (40).

[0085] In this regard, an embodiment of the present invention may additionally include a step of setting a student title included in the answer script.

[0086] This step can be performed by a script processing module (20) and can be performed in the same way as the step of setting the student title included in the lecture script described above.

[0087] Previously, Q&A services were provided in a format where students posted questions via text on an online bulletin board, and instructors responded with text. However, by performing the aforementioned steps (S21, S22, S23, S24), a Virtual Human (VH) can answer the questions. Consequently, students can experience the situation as if an actual instructor were responding to their inquiries. In particular, since the instructor, represented as a Virtual Human (VH), can address the student by name or ID while answering, student satisfaction can be significantly enhanced.

[0089] FIG. 7 is a diagram showing a question input interface according to an embodiment of the present invention.

[0090] Referring to FIG. 7, the method for providing lecture content according to an embodiment of the present invention may further include the step of providing an interface to a student's terminal (3) that can input questions. This step (S21) may be performed by an interface providing module (40).

[0091] For example, the student may select multiple specific points (Ta, Tb, Tc) that are difficult to understand while watching the final lecture content (C2) through the terminal (3). To this end, the interface providing module (40) may provide a user interface that allows the user to check specific points regarding the final lecture content (C2).

[0092] Additionally, when the selection of multiple specific points (Ta, Tb, Tc) from the student terminal (3) is completed, the interface providing module (40) can provide an interface (UI) to the student terminal (3) that allows questions to be entered for each specific point in time in response.

[0093] Accordingly, students can use the interface (UI) to easily input questions regarding lecture content that requires additional explanation from the instructor.

[0094] When the input of questions through the student terminal (3) is completed, the interface providing module (40) can transmit the questions to the instructor terminal (2) along with information about specific times (Ta, Tb, Tc).

[0095] Additionally, the interface providing module (40) can provide an interface to the instructor terminal (2) that allows input of an answer script for the question, and when an answer script for the question is input from the instructor terminal (2), the answer script can be transmitted to the script processing module (20). Subsequently, answer content for the question can be generated through the answer content generation step (S23) described above.

[0097] FIG. 8 is a diagram illustrating the step of generating replay lecture content according to an embodiment of the present invention.

[0098] Referring to FIG. 8, a method for providing lecture content according to an embodiment of the present invention may further include the step of generating replay lecture content and the step of providing replay lecture content.

[0099] In the step of generating replay lecture content, when multiple specific points in time (Ta, Tb, Tc) regarding the final lecture content (C2) are selected from the student terminal (3), multiple unit lecture contents (Ea, Eb, Ec) each containing the multiple specific points in time (Ta, Tb, Tc) are extracted from the final lecture content (C2), and the extracted multiple unit lecture contents (Ea, Eb, Ec) can be combined to generate replay lecture content (C3). This step can be performed by a content generation module (30), and for this purpose, the content generation module (30) may include a separate video editing unit (not shown).

[0100] For example, the final lecture content (C2) can be divided into multiple unit lecture contents in advance, and the playback time of the unit lecture contents can be set differently.

[0101] Additionally, the unit lecture content can be set as a video segment that has the same lecture background image (BI), and in this case, the video editing unit can recognize the lecture background image (BI) of the final lecture content (C2) and extract the unit lecture content from the final lecture content (C2).

[0102] In the step of providing replay lecture content, the generated replay lecture content (C3) can be provided to the student terminal (3). This step can be performed through the interface providing module (40).

[0103] In existing online lectures, if a student has a part they do not understand, there is the inconvenience of having to search for and watch that part again within the lecture video. However, when using the aforementioned replay lecture content (C3), the student does not need to search for the part they do not understand separately, and can freely use the replay lecture content (C3) in which the parts they do not understand are organized, such as an incorrect answer note, thereby improving user convenience and academic performance.

[0105] FIG. 9 is a diagram showing the ending of a relative honorific form according to an embodiment of the present invention.

[0106] Referring to FIG. 9, the method for providing lecture content according to an embodiment of the present invention may further include a step of modifying a terminal ending related to relative honorifics included in a lecture script. This step may be performed by a script processing module (20).

[0107] The endings of the relative honorifics can be classified into the forms of '하십시오체', '하오체', '하게체', '해라체', '해요체', and '해체', and in this stage, the endings related to the relative honorifics included in the lecture script can be modified to have multiple ending forms selected from the pre-set ending forms of the relative honorifics.

[0108] At this time, the ratio of the selected multiple ending forms can be set to the ratio input from the instructor terminal (2).

[0109] In other words, if the sentence endings in each sentence included in the lecture script are used uniformly, despite the fact that the speaking style and tone of each actual instructor differ, the students' immersion may decrease. Accordingly, by modifying the sentence endings included in the lecture script according to the ratio entered by the instructor to suit the characteristics of each instructor, it is possible to increase the similarity between the virtual human (VH) and the real instructor while simultaneously improving the students' immersion.

[0110] In addition, in the case of response scripts, sentence endings related to relative honorifics can be modified in the same way.

[0111] Meanwhile, some instructors may use non-standard language (e.g., slang) during lectures. Accordingly, if there is a request from a student, the method for providing lecture content according to an embodiment of the present invention may additionally perform a step of modifying non-standard language included in the lecture script into a preset standard language. This step may be performed by a script processing module (20).

[0112] In addition, since the non-standard words frequently used by each instructor differ, non-standard word information can be separated by instructor and stored in a database (10) for each. For example, the non-standard word information can be in the form of a table where non-standard words and standard words are matched.

[0113] Accordingly, the script processing module (20) can search for non-standard words included in the lecture script by referring to non-standard word information stored in the database (10), and can replace the searched non-standard words with standard words matched thereto.

[0114] In addition, in the case of this step, whether to perform it may be determined by referring to the age of the student. That is, since young students may be reluctant to use non-standard language, if the student's age is below a preset standard age, the script processing module (20) can automatically perform this step.

[0115] The method for providing lecture content described above 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., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiments, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0116] In addition, the lecture content provision system (1) described above may include a control unit, a memory unit, a communication unit, and a user input / output unit as hardware configurations for implementing a database (10), a script processing module (20), a content creation module (30), an interface provision module (40), etc.

[0117] The control unit may be configured to include at least one CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), AP (Application Processor), or any type of processor well known in the art of the present invention. The control unit may perform operations for at least one application or program for executing the method according to the embodiments of the present invention.

[0118] The memory section can store various digital data, such as video, audio, photos, videos, and applications. The memory section represents various digital data storage spaces, including flash memory, HDD (Hard Disk Drive), and SSD (Solid State Drive).

[0119] The communication unit can perform communication and transmit / receive data using at least one wired / wireless communication protocol. The communication unit can connect to an external network via wired or wireless means to transmit / receive digital data.

[0120] The user input / output unit may include input devices such as a pointing device (mouse or trackpad, etc.), a keyboard, a touch input device (touchpad or touchscreen, etc.), a voice or sound input device, various types of sensor devices and / or shooting devices, and / or output devices such as a display device, a printer, a speaker and / or a network card.

[0121] A person skilled in the art to which the present invention pertains will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included within the scope of the present invention. Explanation of the symbols

[0122] 1: Lecture content delivery system utilizing virtual humans 2: Instructor Terminal 3: Student terminal 10: Database 20: Script processing module 30: Content creation module 40: Interface providing module

Claims

Claim 1 A method for providing lecture content in a lecture content providing system comprising at least one processor and a database, comprising: receiving a lecture script from a terminal of a specific instructor; generating basic lecture content in which a virtual human simulating the specific instructor conducts a lecture based on the lecture script and modeling data stored in the database; generating final lecture content by combining a lecture background image stored in the database with the basic lecture content; and providing the final lecture content to a student's terminal. The method includes the step of generating the final lecture content, wherein the step of generating the final lecture content comprises: generating the final lecture content by synthesizing different lecture background images for each specific section of the basic lecture content; setting the student title included in the lecture script to the group name to which the student belongs; selecting at least two endings related to relative honorifics included in the lecture script from among pre-set forms of endings of relative honorifics, including 'hasipsipche', 'haoche', 'hageche', 'haerache', 'haeyoche', and 'haeche'; modifying the lecture script to have the selected multiple forms of endings; when multiple specific points regarding the final lecture content are selected from the student's terminal, extracting multiple unit lecture contents including each of the multiple specific points from the final lecture content, and combining the extracted multiple unit lecture contents to generate a replay lecture content; providing the replay lecture content to the student's terminal; and determining the age of the student by comparing it with a pre-set standard age. and if the age of the student is less than or equal to the aforementioned preset standard age, a step of searching for non-standard words included in the lecture script and modifying the searched non-standard words into preset standard words;A method for providing lecture content utilizing a virtual human, further comprising: a step of inserting the group name into the symbol in the step of modifying the lecture script; a step of providing an interface to the terminal of the student who has viewed the final lecture content, wherein, when the selection of multiple specific points in time of the final lecture content is completed from the terminal of the student who has viewed the final lecture content, the interface for inputting questions for each of the multiple specific points in time is provided to the student's terminal; a step of receiving the student's questions through the interface and transmitting information regarding the specific points in time and the questions to the terminal of the specific instructor; a step of receiving an answer script for the questions from the terminal of the specific instructor; a step of generating answer content in which the virtual human performs an answer based on the answer script and the modeling data; and a step of providing the answer content to the terminal of the student. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A method for providing lecture content using a virtual human, further comprising the step of, in claim 1, setting the student title included in the answer script to be the same as the student title included in the lecture script. Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 delete

Images