KR20240056214A - Intelligent video content curation service platform system and method - Google Patents

Abstract

The present invention is an intelligent video content curation service platform system and method that can recommend quality content to open OTT users that is objectively verified and based on systematic table of contents and expertise verification, and is highly relevant to the video content topic being watched. It has the advantage of being able to diversify profit models by automatically linking customized reports and products.

Description

Intelligent video content curation service platform system and method {Intelligent video content curation service platform system and method}

The present invention relates to an intelligent video content curation service platform system and method, and more specifically, to an intelligent video content curation service platform system and method that recommends appropriate quality content to users using an open OTT or video platform.

Recently, people have been using spare time in their daily lives to acquire knowledge and information on topics of interest (learning, hobbies, knowledge, technology, etc.) and access open OTT (Over The Top) or video platforms (YouTube, Naver) for niche learning. The number of students and general adult learners/viewers who regularly use TV (TV, Kakao TV, etc.) is increasing. The trend of acquiring information/knowledge on topics of interest using video platforms is expected to continue to spread, and the trend of self-directed niche learning based on video content is referred to as microlearning.

Meanwhile, due to the nature of open OTT, there has been an increase in cases where information limited to popular creators (video producers) who are mostly commercially active on topics of interest is biased due to content overload, and in the past, as many types of products or products as possible were available. It was thought that having information was the best, but recently, in the flood of indiscriminately produced information, people have fallen into what is called 'decision disorder', and it has become difficult to easily determine what information they want and need. In the case of OTT video platforms, the advertisements provided are not related to the content topic, so most users often skip the advertisements, which reduces the effectiveness of the advertisements. The need for a new curation service that recommends quality content through systematic courseware and expertise verification is increasing.

In addition, due to these problems, AI technology is used to diversify profit models by automatically linking customized advertisements and products that are highly relevant to the topic of the video content being watched (learning materials, learning tools, online shopping linked to academies, advertisements, etc.) ) or advertising-linked revenue paid directly from the video platform due to an increase in viewers/subscribers, as well as diversified linked revenue from the curation platform, the need to increase motivation to create quality content is increasing.

In addition, in order to accurately deliver desired information to users, the demand for mobile device-based learning through microlearning is increasing, and a lot of attention has recently been paid to microlearning, which allows learning flexible and immediately applicable knowledge/information. A literature survey found that 47% of companies around the world use mobile learning and 64% of learners access educational content through mobile devices. Therefore, it is necessary to provide optimized learning and competency development solutions to digitally savvy learners. There is also a need for change in the way of taking standardized e-learning learning programs where one-way lectures are taken, and as the demand for non-face-to-face learning and online learning are rapidly increasing due to pandemics such as COVID-19, Content curation services are needed to meet the demand.

Domestic Published Patent No. 10-2017-0133596 (2017.10.13.)

According to one aspect of the present invention, an intelligent video content curation service platform system is applied to provide a method for curating videos on the most appropriate topic for open OTT content users.

According to one aspect of the present invention, an intelligent video content curation service platform system and method are provided.

According to the present invention described above, it is possible to recommend quality content to open OTT users that is objectively verified and based on systematic table of contents and expertise verification.

In addition, you can diversify your profit model by automatically linking customized content and products that are highly related to the topic of the video content you are watching.

Additionally, you can receive diversified linked profits from the curation platform, which can increase your motivation to create quality content.

Figure 1 is a diagram illustrating the overall configuration of an intelligent video content curation service platform system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating the configuration of the intelligent video content curation service platform system shown in FIG. 1.
Figure 3 is a diagram schematically illustrating the curation process in the intelligent video content curation service platform system according to an embodiment of the present invention.
Figure 4 is an example screen of an APP that can use the intelligent video content curation service platform service shown in Figure 3.
Figure 5 is a diagram illustrating a dynamic plate modeling calculation formula according to an embodiment of the present invention.
Figure 6 is a flowchart showing a method of curation in an intelligent video content curation service platform system according to an embodiment of the present invention.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented in one embodiment without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

FIG. 1 is a diagram illustrating the configuration of an intelligent video content curation service platform system according to an embodiment of the present invention, and FIG. 2 is a diagram illustrating the configuration of the intelligent video content curation service platform system shown in FIG. 1. am.

Referring to Figures 1 and 2, the intelligent video content curation service platform system according to this embodiment is a video content information crawling / analysis / video content information service that curates Youtube videos scattered on the Internet according to the topic, turns them into new content, and provides services. A curation function module 100, a related product recommendation module 200 for marketing revenue that generates revenue through a related product recommendation function when watching video content, and a management system for managing members who have signed up for the system of the present invention and the recommendation algorithm. Includes membership, curation management and content management function module 300.

The video content information crawling/analysis/curation function module 100 includes a video content search and extraction unit 110, a video content recommendation unit 120, a user log-based dynamic reputation modeling unit 130, and a customized courseware service unit ( 140).

The video content information crawling/analysis/curation function module 100 automatically crawls content reputation-related data from various open video platform (OTT) sites and then inputs it into the reputation decision algorithm (Reputation Rating System) through a preprocessing process. Recommended results can be derived by organizing the learning table of contents or structure and video list or content by topic of interest.

The video content search and extraction unit 110 crawls and automatically classifies videos by topic, and curates them in the video content recommendation unit 120 so that users can systematically learn about desired topics, providing a customized courseware service. Unit 140 may recommend video content courseware. Microlearning video content that is systematically classified and created can be freely searched and watched by users in a variety of ways. Through the analysis of events by topic of users' interest in viewed microlearning video content, metadata can be built to systematize this by content classification. By collecting the built metadata and reputation for viewing video content, this can be used to create dynamic user log-based data. The reputation modeling unit 130 may use dynamic domain reputation modeling (Dynamic Domain Reputation Modeling), which assigns weight to content based on a dynamic reputation modeling calculation formula and re-recommends the corresponding content. When creating microlearning video content, searching for related videos is based on Youtube OpenAPI and video meta search and data crawling technology, so video content information can be collected by classification.

Big data-based Clustering, Classification, Text Mining, Hybrid CF, and Reputation Mining techniques can be combined to extract video content related to the user's interests. Among text mining techniques, TF/IDF techniques can be selectively applied to extract content. It can be applied by analyzing topic relevance, and it can also be applied by modifying the feature extraction model and data classification model.

In addition, a table of contents can be automatically created through courseware and content for it can be automatically created so that service users can conveniently study the videos of the OTT service platform through a curriculum suitable for microlearning, and these contents are tailored to the user's conditions and You can learn by recommending content that matches your search or preference.

This video content information crawling/analysis/curation function module 100 focuses on recommending not only the content itself but also the content curriculum courseware composition system to support niche learning and microlearning, and supports niche learning/microlearning. By providing a curation service optimized for , it recommends a content list tailored to tastes through existing user logs and is differentiated from platforms that focus on cultural content such as movies and music.

The related product recommendation module 200 for marketing profit includes a related video recommendation unit 210, a related advertisement/product automatic connection unit 220 by interest, and a creator mileage/reputation management unit 230.

The related video recommendation unit 210 can recommend video content to the user by applying dynamic reputation modeling to the video content, and the automatic linkage unit 220 with related advertisements/products by interest is based on the correlation between the content and the user. By recommending content with similar preferences or viewing patterns, you can generate revenue by recommending products linked to it. The content-based filtering (CBF) function, which recommends similar content corresponding to the same category by analyzing the user's behavior records for microlearning content, that is, the number of views and records, can be applied to the service. When learning content users watch similar content, the Hybrid Collaborative Filtering (Hybrid CF) function, which enables other similar content recommendations based on this, can be applied to the service platform.

The membership, curation management, and content management function module 300 includes a personal information/security management unit 310, a content management function/statistics and log management unit 320, and a content data analysis and report management unit 330.

The personal information/security management unit 310 protects and manages personal information entered to use the service for users who have signed up for the intelligent video content curation service, and the content management function/statistics and log management unit. (320) allows users to manage problematic content among the video curation content that they watch, and the content data analysis and report management unit (330) checks statistics and logs on the number of views of video content and records them. Additional analysis and reporting functions that can be used for service prediction functions can be included.

Figure 3 is a diagram schematically illustrating the curation process in the intelligent video content curation service platform system according to an embodiment of the present invention, and Figure 4 is a diagram showing a system that can use the intelligent video content curation service platform service shown in Figure 3. This is an example screen of the APP.

The intelligent video content curation service platform system according to an embodiment of the present invention can recommend a recommended video table of contents to the user, and the recommended table of contents allows the user to re-select the video he or she wants according to the user's preference. In addition, through microlearning learning management, when users study on their mobile devices, it is possible to provide effective self-learning niche learning support for each topic of interest that the user wants to know. Based on the AI algorithm, a systematic learning table of contents is constructed and organized into contents. A list of video content with a high reputation can be dynamically configured and recommended. In addition, by linking customized profit models related to learning topics (textbooks, tools and materials, shopping malls, advertisements, academy-linked profit sharing, etc.), the contents of existing open OTT video platform services are reprocessed to provide differentiated learning support effects and profit models at the same time. Various routes can be provided to users, including a new concept of intelligent meta-service type web/app solution for the desired video content curation service. Referring to Figure 4, video users can receive recommendations for video content they want, and when learning by modifying it to suit their preferences, they can adjust ongoing learning to suit their skills and areas of interest. Additionally, you can determine the reputation of the content and creators you want, and receive re-recommendations of high-quality content among the determined content.

Figure 5 is a diagram illustrating a dynamic plate modeling calculation formula according to an embodiment of the present invention.

As explained previously, metadata that organizes the content by content category can be constructed through event analysis by topic of user interest in the viewed microlearning video content, and reputation for viewing the constructed metadata and video content can be collected. Through this, the user log-based dynamic reputation modeling unit 130 gives weight to the content based on the dynamic reputation modeling calculation formula, and when using dynamic reputation modeling (Dynamic Domain Reputation Modeling) to re-recommend the content, the calculation formula is shown in Figure 5. It's the same.

Figure 6 is a flowchart showing a method of curation in an intelligent video content curation service platform system according to an embodiment of the present invention.

According to Figure 6, the intelligent video content curation service platform system and method includes a video content search and extraction step (S110), a video content recommendation step (S120), a user log-based dynamic reputation modeling step (S130), and a customized courseware service step. Includes (S140).

The video content search and extraction step (S110) can systematically extract the learning table of contents and video list for each topic of interest to the user through a reputation decision algorithm, and recommend video content suitable for the user based on the extracted table of contents or list. (S120) Users can watch or learn from recommended content and videos and develop a reputation for them. In the user log-based dynamic reputation modeling step (S130), the user's reputation is weighted to provide a customized courseware service. You can proceed to step S140.

The intelligent video content curation service method using an algorithm to execute the intelligent video content curation service platform system of the present invention is implemented in the form of program instructions that can be executed through various computer components and is a computer-readable record. Can be recorded on media. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination.

The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and usable by those skilled in the computer software field.

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, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc.

Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

Although various embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and may be used in the technical field to which the invention pertains without departing from the gist of the invention as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

100: Video content information crawling/analysis/curation function module
110: Video content search and extraction unit
120: Video content recommendation unit
130: User log-based dynamic reputation modeling unit
140: Custom courseware service department
200: Related product recommendation module for marketing profits
210: Related video recommendation section
220: Automatic linking of related advertisements/products by interest
230: Creator Mileage/Reputation Management Department
300: Membership, curation and content management functional modules
310: Personal Information/Security Management Department
320: Content management function/statistics and log management department
330: Content data analysis and report management department

Claims (1)

Intelligent video content curation service platform system and method