Theme recommendation method, computer equipment, and program

Abstract

This provides a theme recommendation method, computer equipment, and computer program based on user intent. [Solution] The intent-based theme recommendation method includes the step of providing a navigation bar consisting of multiple theme keywords on the screen of a video service provided as one of the functions of a messenger platform, in order to view theme-based recommendation content, and the step of providing the navigation bar includes the step of arranging the theme keywords in a personalization order based on user intent.

Description

Technical Field

[0007]

[0001] The following description relates to technologies for providing recommended content.

Background Art

[0002] Social media such as Social Network Service (SNS) and messenger services generally refer to services that support human relationships, form relationships between users, and assist in interactions through posts.

[0003] Social media provides users with information based on various contexts. For example, social media provides update information regarding a user's connections, post update information, content recommendations, and other various information items.

[0004] <00​​​​​​​​​​​​​​​​​​​​​​​​​​​​

[0008] By recommending themes based on user intent analysis, content can be consumed on a theme-by-theme basis.

[0009] By applying category-based recommendation logic to themes, it is possible to provide personalized content tailored to each theme.

[0010] By using categories based on metadata, themes can be subdivided, and content tailored to each subdivided theme can be provided. [Means for solving the problem]

[0011] An intent-based theme recommendation method, executed by a computer device including at least one processor, is provided, which includes the step of providing a navigation bar consisting of multiple theme keywords for theme-based recommendation content viewing on the screen of a video service provided as one of the functions of a messenger platform, wherein the step of providing the navigation bar includes the step of arranging the theme keywords in a personalization order based on user intent.

[0012] According to one embodiment, the step of listing theme keywords may include the step of determining the ranking of theme keywords using intent content based on user history.

[0013] In other embodiments, multiple representative content pieces are defined for each theme keyword, and the step of arranging the theme keywords may include the step of determining the ranking of the theme keywords based on the similarity between the intent content and the representative content, based on user history.

[0014] In another embodiment, the step of providing a navigation bar may include the step of defining theme keywords using metadata extracted from intent content based on user history.

[0015] In other embodiments, the intent-based theme recommendation method may further include the step of providing, by at least one processor, recommended content related to a specific theme keyword through a video service screen when a specific theme keyword is selected from the navigation bar.

[0016] In another embodiment, for each theme keyword, at least one piece of information is specified from one or more hashtags and one or more pieces of account information, and the step of providing recommended content is obtained by providing recommended content using such at least one piece of information.

[0017] In another embodiment, for each theme keyword, one or more categories are specified along with at least one piece of information, which includes one or more hashtags and one or more account information items, and the step of providing recommended content may utilize such at least one piece of information and categories to provide recommended content.

[0018] In another embodiment, one or more meta tags are specified for each theme keyword, and the step of providing recommended content may utilize such meta tags to provide recommended content.

[0019] In another embodiment, the meta tags may be categories based on metadata extracted from content corresponding to theme keywords.

[0020] According to another embodiment, the step of providing recommended content may include the step of mixing a first content pool based on user history and a second content pool based on popularity to form a candidate content pool for recommending content.

[0021] According to another embodiment, the step of forming the candidate content pool may include the step of forming the second content pool in consideration of user types, and the user types may be divided into users whose favorite categories are predictable and users whose favorite categories are not predictable.

[0022] According to still another embodiment, the step of forming the candidate content pool may include the step of predicting the user's favorite category from the content consumed by the user and forming the second content pool with the content belonging to the favorite category.

[0023] To cause a computer device to execute a theme recommendation method based on intent, a program recorded on a computer-readable recording medium is provided.

[0024] A computer device is provided, including at least one processor configured to execute instructions readable by the computer device. The at least one processor provides a navigation bar consisting of a plurality of theme keywords for viewing recommended content by theme unit on a screen of a video service provided as one of the functions of a messenger platform, and arranges the theme keywords in a personalized order based on user intent.

Brief Description of the Drawings

[0025] [Figure 1] It is a diagram showing an example of a network environment in an embodiment of the present invention. [Figure 2] It is a block diagram showing an example of a computer device according to an embodiment of the present invention. [Figure 3]This flowchart shows an example of a method that a computer device according to one embodiment of the present invention can perform. [Figure 4] This diagram illustrates an example of a video service migration process in one embodiment of the present invention. [Figure 5] This diagram illustrates an example of a video service migration process in one embodiment of the present invention. [Figure 6] This diagram illustrates an example of a theme keyword definition in one embodiment of the present invention. [Figure 7] This figure illustrates another example of thematic keyword definitions in embodiments of the present invention. [Figure 8] This figure illustrates another example of thematic keyword definitions in embodiments of the present invention. [Figure 9] This figure shows an example of the theme keyword ranking process in one embodiment of the present invention. [Figure 10] This figure shows an example of the user-specific theme keyword order in an embodiment of the present invention. [Figure 11] This figure shows an example of providing theme keywords in embodiments of the present invention. [Figure 12] This figure shows an example of theme-based content viewing in one embodiment of the present invention. [Figure 13] This diagram illustrates an example of content recommendation logic in one embodiment of the present invention. [Figure 14] This diagram illustrates an example of content recommendation logic in one embodiment of the present invention. [Modes for carrying out the invention]

[0026] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0027] Embodiments of the present invention relate to a technology for providing recommended content.

[0028] Embodiments including those specifically disclosed herein can provide thematic exploration areas for recommended content, in which themes and content can be personalized based on user intent.

[0029] An intent-based theme recommendation device according to an embodiment of the present invention may be implemented by at least one computer device, and an intent-based theme recommendation method according to an embodiment of the present invention may be executed by at least one computer device included in the intent-based theme recommendation device. In this case, a computer program according to one embodiment of the present invention may be installed and executed in the computer device, and the computer device may execute the intent-based theme recommendation method according to an embodiment of the present invention in accordance with the control of the computer program being executed. The above-described computer program may be combined with the computer device and recorded on a computer-readable recording medium in order to cause the computer to execute the intent-based theme recommendation method.

[0030] Figure 1 shows an example of a network environment in one embodiment of the present invention. The network environment in Figure 1 shows an example that includes a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Figure 1 is merely an example for the purpose of explaining the invention, and the number of electronic devices and servers is not limited to that shown in Figure 1. Furthermore, the network environment in Figure 1 is merely an example illustrating an environment applicable to this embodiment, and the environment applicable to this embodiment is not limited to the network environment in Figure 1.

[0031] The multiple electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented by computer devices. Examples of the multiple electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, personal computers (PCs), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), and tablets. As an example, Figure 1 shows a smartphone as an example of electronic device 110, but in embodiments of the present invention, electronic device 110 may mean one of a variety of physical computer devices that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 using substantially wireless or wired communication methods.

[0032] The communication method is not limited, and may include not only communication methods that utilize communication networks that can be included in network 170 (for example, mobile communication networks, wired internet, wireless internet, broadcasting networks), but also short-range wireless communication between devices. For example, network 170 may include one or more arbitrary networks such as PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Furthermore, network 170 may include, but is not limited to, one or more network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks.

[0033] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via a network 170 to provide commands, code, files, content, services, etc. For example, server 150 may be a system that provides services (for example, a content recommendation service) to multiple electronic devices 110, 120, 130, and 140 connected via a network 170.

[0034] Figure 2 is a block diagram showing an example of a computer device according to one embodiment of the present invention. Each of the above-mentioned electronic devices 110, 120, 130, and 140, as well as each of the servers 150 and 160, may be implemented by the computer device 200 shown in Figure 2.

[0035] Such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240, as shown in Figure 2. The memory 210 is a computer-readable recording medium and may include RAM (random access memory), ROM (read-only memory), and a permanent mass storage device such as a disk drive. Here, the permanent mass storage device such as ROM or a disk drive may be included in the computer device 200 as a separate permanent storage device distinct from the memory 210. The memory 210 may also contain an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such a separate computer-readable recording medium may include a floppy disk drive, disk, tape, DVD / CD-ROM drive, memory card, and other computer-readable recording media. In other embodiments, the software components may be loaded into the memory 210 through a communication interface 230 which is not a computer-readable recording medium. For example, software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

[0036] The processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor 220 by memory 210 or a communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code stored in a recording device such as memory 210.

[0037] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the recording device described above) via the network 170. For example, requests, instructions, data, files, etc., generated by the processor 220 of the computer device 200 according to program code recorded in a recording device such as memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc., from other devices may be received by the computer device 200 via the network 170 through the communication interface 230 of the computer device 200. Signals, instructions, data, etc., received via the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc., may be recorded on a recording medium (the persistent recording device described above) that the computer device 200 may further include.

[0038] The input / output interface 240 may be a means for interface with the input / output device 250. For example, the input device may include a microphone, keyboard, or mouse, and the output device may include a display or speaker. In another example, the input / output interface 240 may be a means for interface with a device that integrates input and output functions into one, such as a touchscreen. The input / output device 250 may consist of the computer device 200 and one other device.

[0039] In other embodiments, the computer device 200 may include fewer or more components than those shown in Figure 2. However, it is not necessary to explicitly show most of the conventional components in the figure. For example, the computer device 200 may be implemented to include at least some of the input / output devices 250 described above, and may further include other components such as transceivers and databases.

[0040] The following describes specific embodiments of a theme recommendation method and apparatus based on user intent.

[0041] In this embodiment, a video service may be included as one of the functions provided through the messenger platform.

[0042] In recent years, as the features offered through messenger platforms have become increasingly diverse, video platforms have emerged that allow users to distribute and share not only short-form content (videos under one minute in length) but also longer-form content.

[0043] While video content was given as a typical example, the present invention is not limited to this; it can be applied to all types of content that can be shared through a platform, such as images, text, and audio. Hereafter, content to which the present invention can be applied will be referred to as "post."

[0044] The computer device 200 according to this embodiment may provide content recommendation services to a client through a dedicated application installed on the client or by connecting to a web / mobile site associated with the computer device 200. The computer device 200 may be configured with an intent-based theme recommendation system implemented by the computer. For example, the intent-based theme recommendation system may be implemented as an independently operating program, or it may be configured as an in-app application for a specific application so that it can operate on the specific application.

[0045] The processor 220 of the computer device 200 may be implemented by components for performing a theme recommendation method based on the following intent. Depending on the embodiment, the components of the processor 220 may be selectively included in or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or merged to represent the functions of the processor 220.

[0046] Such a processor 220 and its components may control the computer device 200 to perform steps included in the following intent-based theme recommendation method. For example, the processor 220 and its components may be implemented to execute instructions from operating system code and at least one program code contained in memory 210.

[0047] Here, the components of the processor 220 may be representations of different functions that are executed by the processor 220 in accordance with instructions provided by the program code recorded in the computer device 200.

[0048] The processor 220 may read necessary instructions from the memory 210, which is loaded with instructions related to the control of the computer device 200. In this case, the instructions read may include instructions for controlling the processor 220 to perform the steps described below.

[0049] The steps included in the intent-based theme recommendation method described below may be performed in a different order than shown in the diagram, and some steps may be omitted or additional processes may be included.

[0050] The steps included in the intent-based theme recommendation method may be performed on server 150, and in some embodiments, some of the steps may be performed on the client.

[0051] Figure 3 is a flowchart showing an example of a method that a computer device according to one embodiment of the present invention can perform.

[0052] Referring to Figure 3, in step 310, the processor 220 may define multiple theme keywords to constitute a theme bar. In this embodiment, a video service may be included as one of the functions provided through the messenger platform. The messenger platform may include an interface for moving to the video service screen, i.e., a video service navigation button. When a user presses the video service navigation button on the messenger platform, they may be moved to the video service screen. The video service screen will display a theme bar, which is a navigation bar composed of multiple theme keywords, and when the user moves to the video service screen, the theme bar may be displayed in a predetermined area of ​​the component area of ​​the video service screen (for example, the top of the screen). In this embodiment, the theme bar can be said to be a function that provides a collection of posts using a classification system called "theme". The theme keywords that constitute the theme bar may be set in advance through a CMS (content management system). As an example, theme keywords may be defined using hashtags, which are tags that group related posts together, and popular hashtags used on the platform may be used as theme keywords. As another example, processor 220 may analyze posts consumed by the user and define theme keywords using categories based on metadata extracted from those posts. It is also possible to personalize theme keywords using the titles of posts that the user frequently consumes, i.e., metadata that frequently appears in posts consumed by the user.

[0053] In step 320, the processor 220 may determine the ranking of theme keywords based on user intent. Multiple representative posts are predefined for each theme keyword, and the ranking of theme keywords may be determined based on the similarity between the representative posts and the user's interest posts based on their history. Posts that have hashtags that match the theme keyword or hashtags that contain the theme keyword, provided by the quality assurance account, may be selected as representative posts. The processor 220 may select user intent posts based on user logs for posts, such as posts that users have clicked, posts that users have reacted to with comments or "likes", posts that users have viewed for a certain period of time (e.g., 3 seconds) or more, and posts that users have shared, and may assign a higher ranking to theme keywords that contain many representative posts that are similar to user intent posts to a certain level or higher. Thus, the processor 220 can personalize the ranking of theme keywords based on user intent.

[0054] In step 330, the processor 220 may provide a theme bar on the video service screen that displays multiple theme keywords in user personalization order. The processor 220 may assign a personalization ranking to the multiple theme keywords based on user intent and then arrange them on the theme bar on the video service screen. In this embodiment, when providing a theme bar composed of multiple theme keywords on the video service screen, user intent analysis can be used to display and recommend themes corresponding to intent at the top.

[0055] When a specific theme keyword is selected from the theme bar on the video service screen, recommended posts related to the selected theme keyword may be provided through the video service screen. Each theme keyword constituting the theme bar may have a pre-configured post pool with hashtags corresponding to that keyword, and the processor 220 may provide viewing of recommended posts using the post pool of the theme keyword selected from the theme bar. Therefore, the processor 220 can provide recommended posts by utilizing a theme-based content collection through the theme bar. In this embodiment, as a video service screen accessed from the messenger platform, a theme-specific search area is provided within the recommendation feed tab where recommended posts are displayed, and posts with the same title are provided by selecting a title using the theme bar, thereby consuming posts on a theme-by-theme basis.

[0056] Figures 4-5 illustrate an example of the video service transfer process in one embodiment of the present invention.

[0057] Referring to Figure 4, the messenger screen 400 may include a GNB (global navigation bar) area 410 consisting of top-level menu items. The GNB area 410 may include a video service button 401 for navigating to a video service, which is one of the functions of the messenger platform.

[0058] When the user enters the video service button 401 in the GNB area 410 of the messenger screen 400, the processor 220 may move to the video service screen 500, as shown in Figure 5. At this time, the processor 220 may provide a recommendation feed tab (for example, a "For you" tab) for viewing the recommendation post pool as one of the pages that make up the video service screen 500.

[0059] The processor 220 may display a theme bar 510 consisting of multiple theme keywords when the user moves to the video service screen 500. The processor 220 may display the theme bar 510 at the top of the recommendation feed tab, which is the video service screen 500. In this case, the theme bar 510 may be displayed with a certain level of transparency so as not to hide the post the user is currently consuming.

[0060] Theme Bar 510 may support left and right swiping (or scrolling), allowing users to browse themes by swiping left and right. Theme Bar 510 may include an "All" tab for consuming posts from all themes without specifying a particular theme. The All tab may be fixed to the far left and not scrollable within Theme Bar 510.

[0061] Figure 6 illustrates an example of theme keyword definition in one embodiment of the present invention.

[0062] The theme keyword list in theme bar 510 may be managed through a CMS. Theme keywords may be defined by a combination of keywords and hashtags that apply to the theme. A theme may be applied to a hashtag and at least one of the following: a hashtag and a Quality Assurance Account MID (a MID that has high-quality content for a particular theme). Referring to Figure 6, a single theme keyword may be specified with one or more hashtags and at least one of the following: one or more Quality Assurance Account MID values.

[0063] Theme keywords and hashtags (or MIDs) may be mapped in a 1:N relationship. For example, up to five hashtags may be mapped to a single theme. In this case, the theme keyword may be set to be different from the name of the hashtag it is mapped to. For example, the theme keyword may be set to "cute dogs," and the hashtag it is mapped to may be set to "dogs." It is also possible to display different theme keywords for each user in the theme bar 510. For example, for the hashtag "dogs," the theme keyword displayed to user A may be set to "cute puppies," while the theme keyword displayed to user B may be set to "Shiba Inu collection."

[0064] Figures 7 and 8 illustrate an example of other theme keyword definitions in one embodiment of the present invention.

[0065] Referring to Figure 7, a single theme keyword may be specified with at least one of one or more hashtags and at least one of one or more quality assurance account MID values, in which case one or more categories may be additionally defined. A certain number of categories may be predefined as major classification criteria for classifying posts, and a single theme keyword may be specified with at least one category information from the predefined categories.

[0066] As another example, instead of hashtags, which are subjective information created by the user who posted the post, metadata (hereinafter referred to as "meta tags"), which are objective information directly obtainable from the post, may be applied as a theme. Referring to Figure 8, one theme keyword may be specified with one or more meta tags and at least one of one or more quality assurance account MID values. The hashtags of existing theme keywords are changed to meta tags, in which case the meta tags may mean metadata directly extracted from the content through content analysis. Theme keywords and meta tags (or MIDs) may be mapped in a 1:N relationship; for example, up to five meta tags may be mapped to one theme.

[0067] By defining theme keywords using meta tags extracted from user intent posts (for example, posts that users clicked, posts that users commented on or liked, posts that users viewed for a certain amount of time (e.g., 3 seconds) or more, and posts that users shared), it is possible to construct title-centric theme keywords that are personalized to the user.

[0068] Figure 9 shows an example of the theme keyword ranking process in one embodiment of the present invention.

[0069] Referring to Figure 9, the processor 220 may have multiple representative posts predefined for each theme keyword, and may determine the ranking of theme keywords by using the similarity between user intent posts and representative posts. In this case, the similarity may include tag (hashtag or meta tag) similarity between posts, content similarity, MID similarity, category similarity, etc.

[0070] For example, posts that users have clicked, posts that users have commented on or liked, posts that users have viewed for more than 3 seconds, and posts that users have shared may be selected as user intent posts, and the similarity between user intent posts and representative posts may be calculated. The processor 220 may then sum up the similarities between user intent posts and representative posts for each theme keyword and determine the ranking of theme keywords based on the summation of similarities between posts.

[0071] Figure 10 shows an example of the ranking of theme keywords by user in one embodiment of the present invention.

[0072] The processor 220 may personalize the ranking of theme keywords displayed in the theme bar 510 based on user intent analysis for each user, in order of increasing interest. As shown in Figure 10, the video service screen 500 for user A may be provided with a theme bar 510 arranged in the order of keyword3, keyword1, keyword7, ..., while the video service screen 500 for user B may be provided with a theme bar 510 arranged in the order of keyword2, keyword8, keyword4, ...

[0073] Therefore, based on user intent analysis, the processor 220 can personalize and display theme keywords included in the theme bar 510 according to each user's preferred theme ranking.

[0074] Figure 11 shows an example of theme keyword provision in one embodiment of the present invention.

[0075] In addition to the theme bar 510 displayed on the video service screen 500, the processor 220 may also provide a theme keyword list 1110 on the collection page 1100 related to the video service screen 500, as shown in Figure 11. In this case, the processor 220 may also provide the theme keywords displayed in the theme keyword list 1110 in order of decreasing interest, based on user intent analysis.

[0076] Figure 12 shows an example of theme-based content viewing in one embodiment of the present invention.

[0077] Referring to Figure 12, when the theme bar 510 is displayed on the recommendation feed tab of the video service screen 500, the theme bar 510 may be selected by default to provide viewing of recommended content. Through the "All" tab of the theme bar 510, users can consume content from all themes without specifying a particular theme.

[0078] If a user selects a specific theme keyword from the theme bar 510 in the recommendation feed tab, the system may provide a view of recommended content using the post pool corresponding to the information mapped to the selected theme keyword (hashtags, meta tags, categories, MID).

[0079] Figures 13 and 14 illustrate an example of content recommendation logic in one embodiment of the present invention.

[0080] Referring to Figure 13, the processor 220 may configure a personalization post pool 1310 through personalization-based recommendation logic, and may configure a popularity post pool 1320 through popularity-based recommendation logic.

[0081] In this case, the processor 220 may use recommendation logic based on personalization that automatically predicts user intent, such as CF (Collaborative Filtering) or graph-based recommendation systems (e.g., Pixie), to select posts similar to user intent posts, such as posts that the user has clicked, posts that the user has reacted to with comments or "likes", posts that the user has viewed for a certain period of time (e.g., 3 seconds) or more, and posts that the user has shared, and configure a personalization post pool 1310.

[0082] In this embodiment, by utilizing the category information assigned to each post, the personalization post pool 1310 can be configured by selecting posts that are similar to user intent posts and belong to a category corresponding to the user intent (i.e., preferred category).

[0083] Furthermore, when the processor 220 constructs the popularity post pool 1320 through a recommendation logic based on popularity, it may construct the popularity post pool 1320 while considering the user type. Referring to Figure 14, the processor 220 may divide user types into first users whose preferred categories can be predicted and second users whose preferred categories cannot be predicted. For example, in the case of a user who has consumed more than the minimum number of posts necessary to predict their preferred categories, the processor 220 may predict the user's preferred categories using the hashtags (or meta tags), MID, category information, etc., of the posts the user has consumed. In addition to the posts consumed by the user, the processor 220 can also predict categories that are commonly preferred by each profile by using profile information such as the user's age and gender. In the case of first users whose preferred categories can be predicted, the processor 220 may construct the popularity post pool 1320 by selecting posts with high popularity rankings over the entire period and posts with high popularity rankings over the most recent period in the entire category from among the posts within the predicted preferred categories. For example, for the first user, a popularity pool of 1320 posts may be constructed by selecting long-term popular posts and recent trending popular posts within the predicted preference category in a 90:10 ratio. On the other hand, for the second user, for whom predicting preferred categories is difficult due to the consumption of fewer than the minimum number of posts, a popularity pool of 1320 may be constructed by selecting posts with high popularity rankings across the entire period from among all posts in the category.

[0084] Referring again to Figure 13, the processor 220 may combine the personalization post pool 1310 and the popularity post pool 1320 to form a candidate post pool 1300 for content recommendation. For example, the processor 220 may combine the personalization post pool 1310 and the popularity post pool 1320 in a predetermined fixed ratio (e.g., 70:30) to form the candidate post pool 1300. As another example, the processor 220 may adjust the mixing ratio of the personalization post pool 1310 and the popularity post pool 1320 based on the volume of user history in the video service, for example, click log data. For example, a minimum of 5% of the candidate post pool 1300 for content recommendation may be guaranteed to be the popularity post pool 1320, and up to 95% may be the personalization post pool 1310. If there is insufficient clicklog data to configure the personalization post pool 1310, the proportion of the popularity post pool 1320 may be increased.

[0085] The processor 220 may determine the recommendation order of posts included in the candidate post pool 1300 based on user history. The candidate post pool 1300, which is configured based on popularity and personalization, may be displayed in an order tailored to each user based on their user history in the video service.

[0086] In this case, if the user selects a specific theme keyword from the theme bar 510 of the recommendation feed tab, the processor 220 may recommend posts corresponding to hashtags (or meta tags) of the selected theme keyword, or posts posted by MID accounts of the selected theme keyword, in a personalized order based on the user's history within the candidate post pool 1300.

[0087] As another example, if category information is defined for posts and theme keywords, the processor 220 may, within the candidate post pool 1300, preferentially select posts corresponding to hashtags (or meta tags) of the selected theme keyword or posts posted by MID accounts of the selected theme keyword, and then recommend the selected posts that belong to the category of the selected theme keyword in a personalized order based on the user's history.

[0088] Thus, according to embodiments of the present invention, by providing theme-based exploration areas for recommended content, users can consume content of the same title on a theme-by-theme basis. Furthermore, according to embodiments of the present invention, by providing personalized themes and content through user intent analysis, a content exploration experience optimized for the user can be provided.

[0089] The above-described apparatus may be implemented by hardware components, software components, and / or combinations of hardware and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as processors, controllers, ALUs (arithmetic logic units), digital signal processors, microcomputers, FPGAs (field programmable gate arrays), PLUs (programmable logic units), microprocessors, or various devices capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications running on the OS. The processing unit may also respond to software execution, access data, record, manipulate, process, and generate data. For convenience of understanding, it may be described as if a single processing unit is used, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Other processing configurations, such as a parallel processor, are also possible.

[0090] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired, or to instruct the processing unit independently or collectively. Software and / or data may be embodied in any kind of machine, component, physical device, computer recording medium, or device in order to be interpreted based on the processing unit or to provide instructions or data to the processing unit. Software may be distributed across a networked computer system, and may be recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

[0091] The method according to the embodiment may be implemented in the form of program instructions executable by various computer means and recorded on a computer-readable medium. In this case, the medium may continuously record computer-executable programs or may temporarily record them for execution or download. Furthermore, the medium may be various recording or storage means in the form of a combination of one or more hardware components, and may be a medium directly connected to a computer system or distributed on a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and media configured to record program instructions such as ROM, RAM, and flash memory. Other examples of media include recording media and storage media managed by app stores that distribute applications, and sites and servers that supply and distribute various other software.

[0092] As described above, embodiments have been explained based on limited embodiments and drawings, but those skilled in the art will be able to make various modifications and variations from the above description. For example, the described technique may be performed in a different order than described, and / or the components of the described system, structure, apparatus, circuit, etc. may be combined or assembled in a different manner than described, or opposed or replaced by other components or equivalents, and still achieve suitable results.

[0093] Therefore, even if the embodiment is different, it falls within the scope of the attached claims if it is equivalent to the claims.

[0094] This application claims priority based on Patent Application No. 10-2024-0161114, filed with the Korean Intellectual Property Office on 13 November 2024, and the entire contents of said Patent Application No. 10-2024-0161114 are incorporated into this application by reference. [Explanation of symbols]

[0095] 200: Computer equipment 210: Memory 220: Processor 230: Input / Output Interface 250: Input / Output Devices 170: Network

Claims

1. An intent-based theme recommendation method, which is executed by a computer device including at least one processor, The step of providing a navigation bar consisting of multiple theme keywords for theme-based recommended content viewing on the screen of a video service provided as one of the functions of the messenger platform using at least one of the aforementioned processors. Includes, The step of providing the aforementioned navigation bar is: A theme recommendation method, comprising the step of arranging the aforementioned theme keywords in a personalization order based on user intent.

2. The step of listing the aforementioned theme keywords is, The theme recommendation method according to claim 1, further comprising the step of determining the ranking of the theme keywords using intent content based on user history.

3. Multiple representative content pieces are defined for each theme keyword. The step of listing the aforementioned theme keywords is, The theme recommendation method according to claim 1, further comprising the step of determining the ranking of theme keywords based on the similarity between intent content and representative content based on user history.

4. The step of providing the aforementioned navigation bar is: The theme recommendation method according to claim 1, comprising the step of defining theme keywords using metadata extracted from intent content based on user history.

5. The theme recommendation method according to claim 1, further comprising the step of providing, through the screen of the video service, recommended content related to the specific theme keyword when a specific theme keyword is selected from the navigation bar by the at least one processor.

6. For each theme keyword, at least one of the following information items is specified: one or more hashtags and one or more account information items. The step of providing the aforementioned recommended content is: The theme recommendation method according to claim 5, characterized in that it provides the recommended content using the aforementioned at least one piece of information.

7. For each theme keyword, one or more categories are specified, along with at least one of the following: one or more hashtags and one or more account information. The step of providing the aforementioned recommended content is: The theme recommendation method according to claim 5, characterized in that it provides the recommended content using the at least one piece of information and the category.

8. One or more meta tags are specified for each theme keyword. The step of providing the aforementioned recommended content is: The theme recommendation method according to claim 5, characterized in that it provides the recommended content using the meta tags.

9. The theme recommendation method according to claim 8, characterized in that the meta tag is a category based on metadata extracted from content corresponding to the theme keyword.

10. The step of providing the aforementioned recommended content is: The theme recommendation method according to claim 5, comprising the step of combining a first content pool based on user history and a second content pool based on popularity to constitute a candidate content pool for recommending content.

11. The step of configuring the candidate content pool is: The step includes configuring the second content pool with respect to the user type, The theme recommendation method according to claim 10, characterized in that the user types are divided into users whose preferred categories are predictable and users whose preferred categories are not predictable.

12. The step of configuring the candidate content pool is: The theme recommendation method according to claim 10, comprising the steps of predicting the user's preferred categories from the content consumed by the user, and constituting the second content pool with content belonging to the preferred categories.

13. A program for causing the computer device to execute the theme recommendation method described in any one of claims 1 to 12.

14. A computer device comprising at least one processor configured to execute instructions readable by the computer device, The aforementioned at least one processor is As one of the features of the messenger platform, the video service screen provides a navigation bar consisting of multiple theme keywords to allow users to view theme-based recommended content. A computer device characterized by arranging the aforementioned theme keywords in a personalization order based on user intent.

15. The aforementioned at least one processor is The computer device according to claim 14, characterized in that it determines the ranking of the theme keywords using intent content based on user history.

16. Multiple representative content pieces are defined for each theme keyword. The aforementioned at least one processor is The computer device according to claim 14, characterized in that it determines the ranking of theme keywords based on the similarity between intent content and representative content based on user history.

17. The aforementioned at least one processor is The computer device according to claim 14, characterized in that it defines the theme keywords using metadata extracted from intent content based on user history.

18. The aforementioned at least one processor is The computer device according to claim 14, characterized in that when a specific theme keyword is selected from the navigation bar, recommended content related to the specific theme keyword is provided through the video service screen.

19. For each theme keyword, one or more categories are specified, along with at least one of the following: one or more hashtags and one or more account information. The aforementioned at least one processor is The computer device according to claim 18, characterized in that it provides the recommended content using the at least one piece of information and the category.

20. For each theme keyword, at least one of the following information items is specified: one or more meta tags and one or more account information items. The aforementioned at least one processor is Using at least one of the aforementioned pieces of information, the recommended content is provided. The computer device according to claim 18, characterized in that the meta tag is a category based on metadata extracted from content corresponding to the theme keyword.

Images