Content service apparatus and method

Abstract

A content service apparatus and method are disclosed. The content service apparatus, according to an aspect of the present invention, comprises a communication circuit and a processor connected to the communication circuit, wherein, when a content generation request signal including first query information is received from a user terminal via the communication circuit, the processor may use a generative AI to generate first response information corresponding to the first query information by using pre-registered content, generate new content on the basis of the first response information, and calculate a usage fee for each piece of content on the basis of a reference ratio in which each piece of content is used in generating the new content.

Description

Content service device and method

[0001] The present invention relates to a content service device and method, and more particularly, to a content service device and method that can generate new content based on a response to a user's query and calculate a usage fee for each reference content based on a reference ratio of each reference content used in generating the new content.

[0002]

[0003] Thanks to advances in information and communication technology, consumers now possess not only desktop computers but also various mobile devices, such as smartphones and tablets, and use them to consume a variety of content, including movies, images, and news articles. This content can be for entertainment or business purposes, but it also includes educational content for general learning purposes.

[0004] However, content like this learning content is often complex to produce, requiring extensive information and a high level of creativity. Therefore, it's typically created and distributed by content producers with specialized skills or knowledge. Consequently, the content market is somewhat distinct between content producers and content consumers. Consequently, it's not always easy for consumers to adapt content to their own needs, and this is especially challenging for those who consume learning content.

[0005] The background technology of the present invention is disclosed in Korean Patent Publication No. 10-2013-0089998 (August 13, 2013), entitled ‘Learning information provision system and method for providing learning information to learners using the same.’

[0006]

[0007] The present invention has been devised to improve the above-mentioned problems, and an object of the present invention is to provide a content service device and method that can generate new content based on a response to a user's query and calculate a usage fee for each reference content based on a reference ratio of each reference content used in generating the new content.

[0008] The problems to be solved by the present invention are not limited to the problem(s) mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0009]

[0010] A content service device according to one aspect of the present invention includes a communication circuit and a processor connected to the communication circuit, wherein the processor, when receiving a content creation request signal including first query information from a user terminal through the communication circuit, uses generative AI to create first response information corresponding to the first query information using previously registered contents, creates new content based on the first response information, and calculates a usage fee for each content based on a reference ratio of each content used in the creation of the new content.

[0011] In the present invention, the processor can analyze the meaning of the first query information using the generative AI, obtain content corresponding to the analyzed meaning from at least one content, and generate the first response information using the at least one content obtained.

[0012] In the present invention, the processor can select a template for generating new content based on the first response information, and apply the first response information to the selected template to generate new content.

[0013] In the present invention, the processor may calculate the similarity between the first response information and the previously registered contents, select the content with the highest similarity as the similar content, and select a template for creating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content.

[0014] In the present invention, the processor may calculate a similarity between the reference contents referred to in generating the first response information and the first response information, select the reference contents with the highest similarity as similar contents, and select a template for generating new contents based on at least one of the complexity, learning type, and learning difficulty of the selected similar contents.

[0015] In the present invention, the processor can generate the new content by checking the configuration items of the selected template, extracting the contents of the corresponding configuration items from the first response information, and applying the extracted contents to the corresponding configuration items.

[0016] In the present invention, the processor can calculate the usage fee for each reference content by multiplying the purchase cost set for each reference content used in the creation of the new content and the corresponding reference ratio.

[0017] In the present invention, the processor can calculate a weight based on at least one of the author information, content type, number of views, and number of citations of each reference content, and additionally apply the weight to the reference ratio to calculate the usage fee of each reference content.

[0018] In the present invention, when payment for the new content is completed, the processor can provide a usage fee to the author of each reference content and provide the new content to the user terminal.

[0019] A content service method according to another aspect of the present invention may include a step in which a processor receives a content creation request signal including first query information from a user terminal, a step in which the processor creates first response information corresponding to the first query information using previously registered contents using generative AI, a step in which the processor creates new content based on the first response information, and a step in which the processor calculates a usage fee for each content based on a reference ratio of each content used in the creation of the new content.

[0020] In the present invention, in the step of generating the first response information using the pre-registered contents, the processor may analyze the meaning of the first query information using the generative AI, obtain content corresponding to the analyzed meaning from at least one content, and generate the first response information using the obtained at least one content.

[0021] In the step of generating the new content of the present invention, the processor can select a template for generating the new content based on the first response information, and apply the first response information to the selected template to generate the new content.

[0022] In the step of generating the new content, the processor can generate the new content by checking the configuration items of the selected template, extracting the contents of the corresponding configuration items from the first response information, and applying the extracted contents to the corresponding configuration items.

[0023] In the present invention, in the step of calculating the usage fee for each content, the processor can calculate the usage fee for each reference content by multiplying the purchase cost set for each reference content used in the creation of the new content by the corresponding reference rate.

[0024] In the present invention, in the step of calculating the usage fee for each content, the processor can calculate a weight based on at least one of the author information, content type, number of views, and number of citations of each reference content, and additionally apply the weight to the reference ratio to calculate the usage fee for each reference content.

[0025] The present invention may further include a step of calculating the usage fee for each content, and then, when payment for the new content is completed, the processor provides the usage fee to the author of each reference content and provides the new content to the user terminal.

[0026] In addition, other methods for implementing the present invention, other systems and computer programs for executing the above methods may be further provided.

[0027]

[0028] The content service device and method according to an embodiment of the present invention can generate learning content unique to each user by generating new content based on responses to user inquiries, thereby enabling users to secure learning content appropriate to their individual abilities.

[0029] The content service device and method according to an embodiment of the present invention calculates a usage fee for each reference content based on the reference ratio of each reference content used in creating new content, and pays the usage fee to the author of the reference content, thereby enabling smooth distribution of content, thereby enabling users to produce more diverse content, and enabling authors to obtain profits through the content.

[0030] Meanwhile, the effects of the present invention are not limited to the effects mentioned above, and various effects may be included within a range obvious to those skilled in the art from the contents described below.

[0031]

[0032] FIG. 1 is a drawing for explaining a content service system according to one embodiment of the present invention.

[0033] FIG. 2 is a block diagram schematically illustrating a content service device according to one embodiment of the present invention.

[0034] Figure 3 is a flowchart for explaining a content service method according to one embodiment of the present invention.

[0035]

[0036] Hereinafter, a content service device and method according to one embodiment of the present invention will be described with reference to the attached drawings. In this process, the thickness of lines and the sizes of components depicted in the drawings may be exaggerated for clarity and convenience of explanation.

[0037] Furthermore, the implementations described herein may be implemented as, for example, a method or process, an apparatus, a software program, a data stream, or a signal. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., as an apparatus or a program). The apparatus may be implemented using suitable hardware, software, firmware, and the like. The method may be implemented in an apparatus such as a processor, which generally refers to a processing device including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. A processor also includes a communication device such as a computer, a cell phone, a personal digital assistant ("PDA"), and other devices that facilitate communication of information between end-users.

[0038] In addition, the terminology used in this specification is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

[0039] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. In describing with reference to the attached drawings, identical or corresponding components are assigned the same drawing numbers, and redundant descriptions thereof will be omitted.

[0040]

[0041] Generative AI is currently being used to generate new content, including text, images, audio, and video. Because this new content is not entirely new, but rather builds upon existing content, copyright issues related to the results generated by generative AI have arisen and are likely to continue to arise in the future.

[0042] Accordingly, the present invention proposes a technology that can solve copyright issues by creating new content based on copyrighted content, calculating a usage fee for each reference content based on the reference ratio of each reference content used in creating the new content, and paying the usage fee to the author of each reference content.

[0043]

[0044] FIG. 1 is a drawing for explaining a content service system according to one embodiment of the present invention.

[0045] Referring to FIG. 1, a personalized content service system according to one embodiment of the present invention includes a user terminal (100) and a content service device (200).

[0046] The user terminal (100) can execute and / or display a content creation application or content creation site provided by the content service device (200), and the content service device (200) that receives the user's access identification information (ID) and password through the user terminal (100) can perform user authentication for the content creation application or content creation site.

[0047] A user terminal (100) can request content creation from a content service device (200) through a content creation application or a content creation site, and receive content created from the content service device (200).

[0048] The user terminal (100) may be, but is not limited to, a desktop computer, a smartphone, a laptop, a tablet PC, a smart TV, a mobile phone, a PDA (personal digital assistant), a laptop, a media player, a micro server, a GPS (global positioning system) device, an e-book reader, a digital broadcasting terminal, a navigation device, a kiosk, an MP3 player, a digital camera, a home appliance, or any other mobile or non-mobile computing device operated by a user. In addition, the user terminal (100) may be a wearable terminal such as a watch, glasses, a hair band, or a ring, having a communication function and a data processing function. The user terminal (100) is not limited to the above-described contents, and any terminal capable of web browsing may be borrowed without limitation.

[0049] When a content service device (200) receives a content creation request signal including first query information from a user terminal (100), the content service device (200) uses generative AI to create first response information corresponding to the first query information using previously registered contents, creates new content based on the first response information, and calculates a usage fee for each content based on a reference ratio of each content used in creating the new content. Here, the content may be referred to as learning content, a learning process, etc. Here, the user's query may be in various forms such as voice or text.

[0050] For a detailed description of this content service device (200), refer to FIG. 2.

[0051]

[0052] FIG. 2 is a block diagram schematically illustrating a content service device according to one embodiment of the present invention.

[0053] Referring to FIG. 2, a content service device (200) according to one embodiment of the present invention includes a communication circuit (210), a memory (220), a database (230), and a processor (240).

[0054] The communication circuit (210) may provide a communication interface necessary to provide transmission and reception signals in the form of packet data between the content service device (200) and the user terminal (100) in conjunction with a communication network. Furthermore, the communication circuit (210) may serve to receive a content creation request signal including first query information from the user terminal (100), and may serve to transmit content created by the processor (240) and the usage fee for the content to the user terminal (100). Here, the communication network refers to a medium that serves to connect the content service device (200) and the user terminal (100), and may include a path that provides a connection path so that the user terminal (100) can transmit and receive information after connecting to the content service device (200). In addition, the communication circuit (210) may be a device including hardware and software necessary to transmit and receive signals such as control signals or data signals through a wired or wireless connection with another network device. In addition, the communication circuit (210) can be implemented in various forms such as a short-range communication module, a wireless communication module, a mobile communication module, and a wired communication module.

[0055] The memory (220) is a configuration that stores data related to the operation of the content service device (200). Here, the memory (220) may use a known storage medium, and for example, may use one or more of known storage media such as ROM, PROM, EPROM, E EPROM, RAM, etc. In particular, the memory (220) may store a program (application or applet) that enables content to be generated based on a response to a query using generative AI, a program (application or applet) that enables calculation of the usage fee for each content based on the reference ratio of the content used to generate new content, etc., and the stored information may be selectively selected by the processor (240) as needed.

[0056] The database (230) may include a user database (232), a content database (234), and a template database (236).

[0057] The user database (232) may store user information of each user, first query information of each user, content generated based on the first query information, etc. Here, the user information may include basic information about the user such as the user's name, affiliation, personal information, gender, age, contact information, email, address, occupation, title, job, and competency level, information about authentication (login) such as ID (or email) and password, information related to connection such as the country of connection, connection location, information about the device used for connection, and the connected network environment.

[0058] The content database (234) can store content by category. Each content stored in the content database (234) is configured with information such as content complexity, learning type, learning difficulty, applied template, and purchase cost. Additionally, each content stored in the content database (234) is registered with a summary, keywords, and content.

[0059] The template database (236) can store template information including template identification information, configuration items of each template, application conditions of each template, etc. Here, the configuration items of the template include content introduction, motivational content, content required for learning, quizzes, summaries, demonstration content, missions for practice, simulation content, concept explanation of learning content, problem raising content, hypothesis proposition content, search tool and opinion collection content (configured to provide a search tool so that opinions can be input), presentation of discussion space (url) online / offline, items that allow checking the progress after discussion, content that allows learning by creating a scenario, content that allows creating it, evaluation items, items that allow checking the learning content, etc., and the configuration items of the template can be set differently depending on the type of template.

[0060] The template application conditions include simple, complex, understanding-centered, practice-centered, and learning difficulty levels, and may vary depending on the type of template. For example, the case where there are templates 1 through 8 will be described. In this case, the application conditions of the first template may be understanding-centered and learning difficulty level 1 or 2, and the application conditions of the second template may be simple, understanding-centered, and learning difficulty level 3. In addition, the application conditions of the third template may be simple, practice-centered, and learning difficulty level 1, or complex, practice-centered, and learning difficulty level 1. The application conditions of the fourth template may be simple, practice-centered, and learning difficulty level 2 or 3. The application conditions of the fifth template may be complex, understanding-centered, and learning difficulty level 1, and the application conditions of the sixth template may be complex, understanding-centered, and learning difficulty level 2 or 3. The application conditions of the 7th template may be complex, practice-oriented, and learning difficulty level 2, and the application conditions of the 8th template may be complex, practice-oriented, and learning difficulty level 3.

[0061] Meanwhile, in the embodiment of the present invention, the content database (234) and the template database (236) are described as being included in the content service device (200), but the content database (234) and the template database (236) may be provided in an external device connected to the content service device (200) via a wired or wireless communication network.

[0062] When the processor (240) receives a content creation request signal including first query information from a user terminal (100) through a communication circuit (210), the processor (240) uses generative AI to create first response information corresponding to the first query information using previously registered contents, creates new content based on the first response information, and calculates a usage fee for each content based on a reference ratio of each content used in the creation of the new content.

[0063] Hereinafter, the operation of the processor (240) will be described in detail.

[0064] When a content creation request signal including first query information is received from a user terminal (100) through a communication circuit (210), the processor (240) can analyze the meaning of the first query information using a generative AI.

[0065] Once the meaning of the first query information is analyzed, the processor (240) can obtain content corresponding to the analyzed meaning from the contents registered in the content database (234) using the generative AI. Since the generative AI has learned the content, meaning, etc. of all contents registered in the content database (234), the processor (240) can obtain content corresponding to the meaning of the first query information from at least one content using the generative AI.

[0066] The processor (240) can generate first response information using content corresponding to the meaning of first query information obtained from at least one content.

[0067] In this way, the processor (240) can generate first response information corresponding to the first query information using an artificial intelligence model (generative AI). Generative AI is an artificial intelligence (AI) technology that newly creates similar content by utilizing existing content such as text, audio, and images. It is a technology that goes beyond simply learning the patterns of content and creating new content as an inference result, and a content creator and a discriminator that evaluates the created content constantly compete and confront each other to create new content. A generative AI model is an artificial intelligence model that generates various types of data such as text, images, and voice for a given input. The generative AI model is based on deep learning and natural language processing technology, and may include a language generation model and an image generation model. In addition, the generative AI model may be provided in the device (200) or may communicate with the device (200) via wired or wireless communication as a separate artificial intelligence model. In addition, the generative AI model may be implemented in the same form as a commonly used generative AI model, and the generative AI model may be a model in the same form as the ChatGPT model. Additionally, the processor (240) may generate first response information for first query information using an artificial intelligence question-answering method (To-Be, Question-Answering). The artificial intelligence question-answering method uses natural language-based sentences as input and can provide specific responses, i.e., instant unique responses, as search results. The artificial intelligence question-answering method allows users to naturally search for information as if asking questions to a human.

[0068] When the first response information is generated, the processor (240) can select a template for generating new content from the template database (236) based on the first response information.

[0069] For example, the processor (240) may calculate a similarity between the first response information and the reference contents referenced in generating the first response information, select the reference contents with the highest similarity as similar contents, and select a template for generating new contents based on at least one of the complexity, learning type, and learning difficulty of the selected similar contents. In this case, the processor (240) may calculate a text-based similarity between the reference contents and the first response information.

[0070] The processor (240) may select a reference content having the highest reference ratio among the reference contents referenced in generating the first response information, and may select a template for generating new content based on at least one of the complexity, learning type, and learning difficulty of the selected reference content.

[0071] The processor (240) may calculate the similarity between the first response information and the contents registered in the content database (234), select the content with the highest similarity as the similar content, and select a template for creating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content.

[0072] Specifically, the processor (240) can calculate text-based similarity between each content registered in the content database (234) and the first response information. At this time, the processor (240) can calculate an embedding vector by converting text values ​​in each document of the first response information and the contents into vector values ​​by positioning them in a vector space, calculate an angle between the embedding vectors of the two texts, and calculate the similarity between the first response information and the contents using the angle between the embedding vectors. In addition, the processor (240) can also calculate a distance between the embedding vectors of the two texts, and calculate the similarity between the first response information and the contents using the distance between the embedding vectors. At this time, the processor (240) can vectorize the relationship between keywords used in each of the first response information and the contents. To this end, the processor (240) may calculate the relative frequency of keywords used in each of the first response information and the content, and may represent the relationship between words used in the first response information and the content as a TDM (Term-Document Matrix) structure converted into a vector (numerical information capable of operation). In addition, the processor (240) may extract words (e.g., nouns) from each of the first response information and the content, and may calculate the similarity between the first response information and the content using the ratio of the number of elements of the union of words between the first response information and the content and the number of elements of the intersection. Here, the number of elements of the union may mean the sum of the numbers of words included in the first response information and the content, and the number of elements of the intersection may mean the number of words commonly included in the first response information and the content.

[0073] Since each content stored in the content database (234) has a summary, content, and keywords, the processor (240) can calculate similarity by comparing the first response information with the summary, content, keywords, etc. of each content.

[0074] Once the similarity between the first response information and each content is calculated, the processor (240) can select a template for generating new learning content using different methods depending on whether there is content with a similarity level higher than a preset threshold. Here, the threshold can be set to a preset value, such as 0.5.

[0075] If there are contents with a similarity between the first response information and each content that is greater than or equal to a reference value, the processor (240) can select the content with the highest similarity among the contents with a similarity greater than or equal to the reference value as similar content.

[0076] Thereafter, the processor (240) may select a template for generating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content. That is, the processor (240) may compare at least one of the simple, complex, understanding-centered, practice-centered, and learning difficulty levels set for the similar content with the application conditions of the templates stored in the template database (236) to select one template.

[0077] For example, a case where there are templates 1 through 8 will be described. If the similar content is simple, understanding-centered, and has a learning difficulty level of 1 (or 2), the processor (240) can select the first template. If the similar content is simple, understanding-centered, and has a learning difficulty level of 3, the processor (240) can select the second template. If the similar content is simple, practice-centered, and has a learning difficulty level of 1, the processor (240) can select the third template. If the similar content is simple, practice-centered, and has a learning difficulty level of 2 or 3, the processor (240) can select the fourth template. If the similar content is complex, understanding-centered, and has a learning difficulty level of 1, the processor (240) can select the fifth template. If the similar content is complex, understanding-centered, and has a learning difficulty level of 2 or 3, the processor (240) can select the sixth template. If the similar content is complex, practice-oriented, and has a learning difficulty level of 1, the processor (240) may select the third template. If the similar content is complex, practice-oriented, and has a learning difficulty level of 2, the processor (240) may select the seventh template. If the similar content is complex, practice-oriented, and has a learning difficulty level of 3, the processor (240) may select the eighth template.

[0078] If there is no content with a similarity higher than the reference value, the processor (240) may select a template for creating new content based on at least one of the most frequently used complexity, learning type, and learning difficulty of the content in the field included in the first response information.

[0079] When a template for creating new content is selected, the processor (240) can apply the first response information to the selected template to create new content. At this time, the processor (240) can check the configuration items of the selected template, and for configuration items included in the first response information, the processor (240) can extract the corresponding content from the first response information and input it into the corresponding configuration item. For configuration items not included in the first response information, the processor (240) can generate the corresponding content based on the first response information and input the generated content into the corresponding configuration item.

[0080] That is, in the case of a configuration item whose content exists in the first response information, the processor (240) can extract the content of the configuration item from the first response information and apply the extracted content to the configuration item, thereby generating new content.

[0081] In the case of a configuration item for which the corresponding content does not exist in the first response information, the processor (240) generates second query information including the field, summary, and configuration item content, applies the second query information to a generative AI (artificial intelligence model) to generate second response information for the corresponding configuration item, and applies the second response information to the corresponding configuration item, thereby generating new content.

[0082] For example, if the selected template is a first template including a content introduction, motivational content, content required for learning, and a quiz, a method for generating new content will be described. If the first response information only includes a content introduction, the processor (240) can generate second query information such as "What is the motivational content for learning the first response information (including a field, summary, etc.), what is the content required for learning the first response information, and what if a quiz is generated based on the response to the first response information?" Then, the processor (240) can apply the second query information to a generative AI (artificial intelligence model) to generate motivational content for learning the first response information, content required for learning the first response information, and a quiz. Thereafter, the processor (240) can generate new content by applying the first response information, motivational content, content required for learning, and quiz to the template.

[0083] When new content is created, the processor (240) can calculate the reference ratio of each reference content used to create the new content and calculate the usage fee for each content based on the reference ratio of each reference content.

[0084] That is, since the purchase cost of each content is set in the content database (234), the processor (240) can calculate the usage fee of each reference content by multiplying the purchase cost set for each reference content by the corresponding reference ratio.

[0085] The processor (240) may calculate a weight based on at least one of the author information, content type (video, audio, text, etc.), number of views, and number of citations of each reference content, and may additionally apply the weight to the reference ratio to calculate the usage fee of each reference content.

[0086] The processor (240) can calculate the purchase cost of new content by adding up the usage fees for each reference content.

[0087] The processor (240) can provide a summary of new content and purchase cost to the user terminal (100) through the communication circuit (210).

[0088] Users can review a summary of new content and make payments for their purchases.

[0089] Once payment for new content is completed, the processor (240) may provide royalties to the author of each reference content.

[0090] When payment for new content is completed, the processor (240) can provide the new content to the user terminal (100) through the communication circuit (210).

[0091]

[0092] Figure 3 is a flowchart for explaining a content service method according to one embodiment of the present invention.

[0093] Referring to FIG. 3, when a content creation request signal including first query information is received from a user terminal (100) (S302), the processor (240) uses a generative AI to create first response information corresponding to the first query information using contents registered in the content database (234) (S304). That is, the processor (240) can analyze the meaning of the first query information using the generative AI. When the meaning of the first query information is analyzed, the processor (240) can obtain content corresponding to the analyzed meaning using the generative AI from contents registered in the content database (234). Since the generative AI has learned the contents, meanings, etc. of all contents registered in the content database, the processor (240) can obtain content corresponding to the meaning of the first query information from at least one content using the generative AI. The processor (240) can generate the first response information using content corresponding to the meaning of the first query information obtained from at least one content.

[0094] When step S304 is performed, the processor (240) selects a template for creating new content from the template database (236) based on the first response information (S306).

[0095] For example, the processor (240) may calculate a similarity between the first response information and the reference contents referenced in generating the first response information, select the reference contents with the highest similarity as similar contents, and select a template for generating new contents based on at least one of the complexity, learning type, and learning difficulty of the selected similar contents. In this case, the processor (240) may calculate a text-based similarity between the reference contents and the first response information.

[0096] The processor (240) may select a reference content having the highest reference ratio among the reference contents referenced in generating the first response information, and may select a template for generating new content based on at least one of the complexity, learning type, and learning difficulty of the selected reference content.

[0097] The processor (240) may calculate the similarity between the first response information and the contents registered in the content database (234), select the content with the highest similarity as the similar content, and select a template for creating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content.

[0098] When step S306 is performed, the processor (240) generates new content by applying the selected template based on the first response information (S308). At this time, the processor (240) checks the configuration items of the selected template, and for configuration items included in the first response information, the processor (240) can extract the corresponding content from the first response information and input it into the corresponding configuration item. For configuration items not included in the first response information, the processor (240) can generate the corresponding content based on the first response information and input the generated content into the corresponding configuration item.

[0099] That is, in the case of a configuration item whose content exists in the first response information, the processor (240) can extract the content of the configuration item from the first response information and apply the extracted content to the configuration item, thereby generating new content.

[0100] In the case of a configuration item for which the corresponding content does not exist in the first response information, the processor (240) generates second query information including the field, summary, and configuration item content, applies the second query information to a generative AI (artificial intelligence model) to generate second response information for the corresponding configuration item, and applies the second response information to the corresponding configuration item, thereby generating new content.

[0101] When step S308 is performed, the processor (240) calculates the reference ratio of each reference content used to create new content (S310), and calculates the usage fee of each reference content based on the reference ratio of each reference content (S312).

[0102] That is, since the purchase cost of each content is set in the content database (234), the processor (240) can calculate the usage fee of each reference content by multiplying the purchase cost set for each reference content by the corresponding reference ratio.

[0103] The processor (240) may calculate a weight based on at least one of the author information, content type (video, audio, text, etc.), number of views, and number of citations of each reference content, and may additionally apply the weight to the reference ratio to calculate the usage fee of each reference content.

[0104] The processor (240) can calculate the purchase cost of new content by adding up the usage fees for each reference content.

[0105] When step S312 is performed, the processor (240) provides a summary of the new content and the purchase cost to the user terminal (100) (S314).

[0106] When payment for new content is completed (S316), the processor (240) provides a usage fee to the author of each reference content and provides the new content to the user terminal (100) (S318).

[0107]

[0108] As described above, the content service device and method according to the embodiment of the present invention can create learning content unique to each user by creating new content based on a response to a user's inquiry, thereby enabling each user to obtain learning content appropriate to their individual abilities.

[0109] The content service device and method according to an embodiment of the present invention calculates a usage fee for each reference content based on the reference ratio of each reference content used in creating new content, and pays the usage fee to the author of the reference content, thereby enabling smooth distribution of content, thereby enabling users to produce more diverse content, and enabling authors to obtain profits through the content.

[0110] While the present invention has been described with reference to the embodiments illustrated in the drawings, these are merely exemplary, and those skilled in the art will understand that various modifications and equivalent embodiments are possible. Therefore, the true technical protection scope of the present invention should be defined by the following claims.

Claims

1. Communication circuit; and Including a processor connected to the above communication circuit, The above processor, A content service device characterized in that, when a content creation request signal including first query information is received from a user terminal through the above communication circuit, first response information corresponding to the first query information is created using previously registered contents using generative AI, new content is created based on the first response information, and a usage fee for each content is calculated based on a reference ratio of each content used in the creation of the new content.

2. In paragraph 1, The above processor, A content service device characterized in that it analyzes the meaning of the first query information using the generative AI, obtains content corresponding to the analyzed meaning from at least one content, and generates the first response information using the at least one obtained content.

3. In paragraph 1, The above processor, A content service device characterized in that a template for creating new content is selected based on the first response information, and the new content is created by applying the first response information to the selected template.

4. In paragraph 3, The above processor, A content service device characterized in that it calculates the similarity between the first response information and the previously registered contents, selects the content with the highest similarity as the similar content, and selects a template for creating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content.

5. In paragraph 3, The above processor, A content service device characterized in that it calculates the similarity between the reference contents referred to in generating the first response information and the first response information, selects the reference contents with the highest similarity as similar content, and selects a template for generating new content based on at least one of the complexity, learning type, and learning difficulty of the selected similar content.

6. In paragraph 3, The above processor, A content service device characterized in that it creates the new content by checking the configuration items of the selected template, extracting the contents of the corresponding configuration items from the first response information, and applying the extracted contents to the corresponding configuration items.

7. In paragraph 1, The above processor, A content service device characterized in that the usage fee for each reference content is calculated by multiplying the purchase cost set for each reference content used in the creation of the above new content by the corresponding reference ratio.

8. In paragraph 7, The above processor, A content service device characterized in that a weight is calculated based on at least one of the author information, content type, number of views, and number of citations of each reference content, and the usage fee of each reference content is calculated by additionally applying the weight to the reference ratio.

9. In paragraph 1, The above processor, A content service device characterized in that, when payment for the new content is completed, a usage fee is provided to the author of each reference content and the new content is provided to the user terminal.

10. A step in which the processor receives a content creation request signal including first query information from a user terminal; A step in which the processor generates first response information corresponding to the first query information using generative AI using previously registered contents; The step of the processor generating new content based on the first response information; and A step in which the processor calculates the usage fee for each content based on the reference ratio of each content used to create the new content. A content service method characterized by including:

11. In paragraph 10, In the step of generating the above first response information using the registered contents, A content service method characterized in that the processor analyzes the meaning of the first query information using the generative AI, obtains content corresponding to the analyzed meaning from at least one content, and generates the first response information using the at least one obtained content.

12. In paragraph 10, In the step of creating the above new content, A content service method, characterized in that the processor selects a template for creating new content based on the first response information, and applies the first response information to the selected template to create new content.

13. In paragraph 12, In the step of creating the above new content, A content service method characterized in that the processor verifies the configuration items of the selected template, extracts the contents of the corresponding configuration items from the first response information, and applies the extracted contents to the corresponding configuration items, thereby generating the new content.

14. In paragraph 10, At the stage of calculating the usage fee for each of the above contents, A content service method characterized in that the processor calculates the usage fee for each reference content by multiplying the purchase cost set for each reference content used in the creation of the new content by the corresponding reference ratio.

15. In paragraph 14, At the stage of calculating the usage fee for each of the above contents, A content service method characterized in that the processor calculates a weight based on at least one of the author information, content type, number of views, and number of citations of each reference content, and additionally applies the weight to the reference ratio to calculate the usage fee of each reference content.

16. In paragraph 10, After calculating the usage fee for each of the above contents, A content service method characterized in that, when payment for the new content is completed, the processor further includes a step of providing a usage fee to the author of each reference content and providing the new content to a user terminal.

Images