TWI897124B - Method, computer device, and computer program to recommend account - Google Patents

Abstract

The present invention discloses a method, computer device, and computer program for recommending accounts in a timeline service. In the context of providing a timeline service utilizing functionality included in a community based on a social graph of friendships, the method includes the following steps: selecting recommended accounts based on follow-up relevance, which indicates subscription relationships within the timeline service; selecting recommended accounts based on popularity, based on the number of followers within the timeline service; and combining the recommended accounts based on follow-up and popularity to form a recommendation pool.

Description

Account recommendation method, computer device, and computer program

The following description relates to a technique for providing a timeline service in a communicator.

Community services such as social networking services (SNS) or messengers support post-based interactions by building relationships between users.

Community services can provide users with information as different contexts. For example, community services can provide updates about the user's connections, post updates, content recommendations, and various other types of information items.

For example, Korean Patent No. 10-1754373 (grant date: June 29, 2017) discloses technology for managing posts using SNS.

Some social services offer a timeline-style view for browsing posts. This timeline-style post display method has been primarily used for quick content updates and personal communication for consumption.

Technical problems to be solved

A timeline service can be provided as a service in the communicator to change the subscription relationship from friend-based to follow-based.

An account recommendation pool can be formed based on follow-up relevance in the timeline service.

You can use both the follow-based social graph and the friend-based social graph to recommend accounts in the Timeline service.

Means of solving the problem

The present invention provides an account recommendation method executed in a computer device, the computer device including at least one processor, the at least one processor being configured to execute computer-readable commands contained in a memory, providing a timeline service as a function included in a community using a social graph based on friend relationships, the timeline service providing a timeline based on subscription relationships different from the social graph, the account recommendation method including the following steps: The at least one processor selects, by the at least one processor, follow-based recommended accounts based on follow relevance representing a subscription relationship within the timeline service; the at least one processor selects, by the at least one processor, popularity-based recommended accounts based on the number of followers within the timeline service; and the at least one processor combines the follow-based recommended accounts and the popularity-based recommended accounts to form a recommendation pool.

According to one aspect of the present invention, the step of selecting a recommended account based on follow-up may include: selecting at least one of an account followed by an account already followed by the user, an account similar to the account already followed by the user, and an account that has followed the user but is not followed by the user, as the recommended account based on follow-up.

According to another aspect of the present invention, the step of selecting a popularity-based recommended account may include: selecting the popularity-based recommended account using the number of followers from at least one of a general account, an official account, and a promotional account.

According to another aspect of the present invention, the step of selecting a popularity-based recommended account may include: after filtering a predetermined number of accounts in order of the number of followers, randomly selecting the popularity-based recommended account from the filtered accounts.

According to another aspect of the present invention, the step of selecting recommended accounts based on popularity may include: after filtering a predetermined number of accounts in order of the number of followers, selecting accounts with a history of creating posts within a recent predetermined time from the filtered accounts as the recommended accounts based on popularity, or after filtering accounts with a history of creating posts within a recent predetermined time, selecting accounts with a number of followers greater than a predetermined value from the filtered accounts as the recommended accounts based on popularity.

According to another aspect of the present invention, the step of selecting the recommended accounts based on popularity may include selecting the recommended accounts based on popularity using a user response score to posts owned by each account and a follower increase/decrease rate during a recent predetermined period of time.

According to another aspect of the present invention, the step of forming the recommendation pool may include: mixing the recommendation accounts based on attention and the recommendation accounts based on popularity in a predetermined fixed ratio to form the recommendation pool.

According to another aspect of the present invention, the step of forming the recommendation pool may include: mixing the recommendation accounts based on attention and the recommendation accounts based on popularity in a ratio adjusted according to the number of selections to form the recommendation pool.

According to another aspect of the present invention, the account recommendation method may further include the following step: determining, by the at least one processor, an exposure order for the follow-based recommended accounts based on at least one of a friendship relationship with the user and timeline activity.

According to another aspect of the present invention, the account recommendation method may further include the following step: by the at least one processor, giving priority to accounts among the follow-based recommended accounts that have established a friend relationship with the user within a recent predetermined time period, so that they are exposed higher than other accounts.

According to another aspect of the present invention, the account recommendation method may further include the following step: by the at least one processor, giving priority to accounts with a history of creating post resumes within a recent predetermined time period among the follow-up recommended accounts so that they are exposed higher than other accounts.

A computer program is provided. The computer program is stored in a computer-readable recording medium to enable a computer device to execute the account recommendation method.

A computer device is provided, including at least one processor configured to execute computer-readable instructions contained in a memory, and providing a timeline service as a function included in a community utilizing a social graph based on friendship relationships, the timeline service providing a timeline based on follow-based subscription relationships that is different from the social graph. The at least one processor processes the following processes: selecting a follow-based recommended account based on follow relevance representing a subscription relationship within the timeline service; selecting a popularity-based recommended account based on the number of followers within the timeline service; and combining the follow-based recommended accounts and the popularity-based recommended accounts to form a recommendation pool.

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

An embodiment of the present invention relates to a technology for providing a timeline service in a communicator.

In an embodiment disclosed in this specification, a timeline service is provided as a function included in a communicator that utilizes a subscription relationship based on following rather than a subscription relationship based on friends, and in this case, accounts that the user may follow can be recommended in the timeline service.

The timeline service system according to an embodiment of the present invention can be implemented by at least one computer device, and the timeline service method according to an embodiment of the present invention can be executed by at least one computer device included in the timeline service system. In this case, a computer program according to an embodiment of the present invention can be installed on the computer device and driven, and the computer device can execute the timeline service method according to an embodiment of the present invention under the control of the driven computer program. The computer program can be combined with the computer device and stored on a computer-readable recording medium, so that the computer executes the timeline service method.

FIG1 illustrates an example of a network environment according to an embodiment of the present invention. The network environment in FIG1 includes multiple electronic devices 110, 120, 130, and 140, multiple servers 150 and 160, and a network 170. FIG1 is provided as an example for illustrating the present invention; the number of electronic devices or servers is not limited to that shown in FIG1. Furthermore, the network environment in FIG1 illustrates only one example of an environment applicable to this embodiment, and is not limited to the network environment in FIG1.

The plurality of electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented as computer devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 may include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcast terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), tablet PCs, and the like. For example, FIG1 illustrates an image of a smartphone as an example of electronic device 110. However, in embodiments of the present invention, electronic device 110 may actually represent any of a variety of physical computer devices capable of communicating with other electronic devices 120, 130, and 140 and/or servers 150 and 160 via a network 170 using wireless or wired communication methods.

The communication method is not limited to this and may include not only communication using communication networks that may be included in network 170 (e.g., mobile communication networks, wired Internet, wireless Internet, broadcast networks, etc.), but also short-range wireless communication between devices. For example, network 170 may include one or more networks selected from a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. Furthermore, network 170 may include one or more networks selected from network topologies including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree network, or a hierarchical network.

Servers 150 and 160 can each be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via network 170 to provide instructions, code, files, content, and services. For example, server 150 can be a system that provides services (e.g., communication services) to multiple electronic devices 110, 120, 130, and 140 connected via network 170.

2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices 110, 120, 130, and 140 or each of the servers 150 and 160 as described above can be implemented by the computer device 200 shown in FIG.

As shown in FIG2 , such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input/output interface 240. Memory 210, as a computer-readable recording medium, may include non-volatile large-capacity recording devices such as RAM, ROM, and a hard disk drive. Non-volatile large-capacity recording devices such as ROM and a hard disk drive may be included in computer device 200 as independent permanent storage devices separate from memory 210. Memory 210 may also store an operating system and at least one program code. These software components may be loaded into memory 210 from a computer-readable recording medium separate from memory 210. Computer-readable recording media may include floppy disk drives, hard disks, magnetic tapes, DVD/CD-ROM drives, and memory cards. In another embodiment, software components may be loaded into memory 210 via communication interface 230 rather than a computer-readable recording medium. For example, software components may be loaded into memory 210 of computer device 200 based on a computer program installed from a file received via network 170.

Processor 220 may be configured to process computer program instructions by performing basic arithmetic operations, logical operations, and input/output operations. Instructions may be provided to processor 220 via memory 210 or communication interface 230. For example, processor 220 may be configured to execute received instructions based on program code stored in a storage device such as memory 210.

Communication interface 230 can provide functionality for computer device 200 to communicate with another device (e.g., the aforementioned storage device) via network 170. For example, requests, instructions, data, files, etc. generated by processor 220 of computer device 200 based on program code stored in a storage device such as memory 210 can be transmitted to another device via network 170 under the control of communication interface 230. Conversely, signals or instructions, data, files, etc. from other devices can be received by computer device 200 via network 170 through communication interface 230 of computer device 200. Signals, instructions, data, etc. received through the communication interface 230 can be transmitted to the processor 220 or the memory 210, and files, etc. can be stored in a storage medium (the above-mentioned permanent storage device) that may be included in the computer device 200.

The input/output interface 240 may be a unit for connecting to an input/output device 250. For example, input devices may include microphones, keyboards, and mice, while output devices may include displays and speakers. As another example, the input/output interface 240 may be a unit for connecting to a device that integrates input and output functions, such as a touch screen. The input/output device 250 and the computer device 200 may form a single device.

In addition, in another embodiment, the computer device 200 may include fewer or more components than those shown in FIG. However, it is not necessary to clearly illustrate most of the components of the prior art. For example, the computer device 200 may be implemented to include at least a portion of the input/output device 250, or may further include other components such as a transceiver, a database, and the like.

The following describes a specific embodiment of a method and system for recommending accounts in a timeline service.

In this specification, the term "community" may include relationship-based communication spaces on the internet, such as communicators. Communities can provide chat services, timeline services, and call services between users who have established friendships by adding friends using phone numbers or IDs. However, this is not limited to these services; any space that enables communication based on friendships through various communication functions can be broadly applied.

FIG3 is a diagram showing an example of structural elements that a processor of a computer device according to an embodiment of the present invention may include, and FIG4 is a flowchart showing an example of a timeline service method that can be executed by a computer device according to an embodiment of the present invention.

According to this embodiment, the computer device 200 can provide communication services by accessing a dedicated application or a website/mobile site. The computer device 200 can include a timeline service system implemented by the computer. For example, the timeline service system can be implemented as a standalone program or as an in-app application within a specific application.

As shown in FIG3 , the processor 220 of the computer device 200 , as a component for executing the timeline service method described below, may include an account recommendation unit 310 , a subscription relationship setting unit 320 , and a post providing unit 330 . Depending on the embodiment, the components of the processor 220 may be selectively included in or excluded from the processor 220 . Furthermore, depending on the embodiment, the components of the processor 220 may be separated or combined to represent the functionality of the processor 220 .

Such a processor 220 and its components can control the computer device 200 to execute the steps included in the timeline service method described below. For example, the processor 220 and its components can be implemented to execute instructions based on operating system code and at least one program code included in the memory 210.

The components of processor 220 may represent different functions executed by processor 220 according to instructions provided by program code stored in computer device 200. For example, account recommendation unit 310 may represent a function of processor 220. Processor 220 controls computer device 200 according to the instructions to recommend accounts on the communicator.

The processor 220 may read necessary instructions from the memory 210 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 execute the timeline service method described later.

The steps included in the timeline service method described later may be performed in an order different from the order shown in the figure, and some of the steps may be omitted, or additional steps may be further included.

The steps included in the timeline service method may be executed by a client having a communicator installed thereon, and some of the steps may also be executed by the server 150 according to an embodiment.

Referring to Figure 4, in step S410, the account recommendation unit 310 may recommend accounts on the communicator that are related to the user as accounts for timeline subscription. In this embodiment, a timeline service may be provided as a feature included in the communicator. Specifically, a subscription environment for timeline posts may be provided based on following rather than friendship. The account recommendation unit 310 may recommend accounts on the communicator so that the user can set up a following relationship for timeline subscription. As an example, the account recommendation unit 310 may recommend accounts on the communicator with which the user has established a friendship relationship, i.e., communicator friends, as recommended accounts. In this case, recommended accounts can include regular accounts (personal accounts) or official accounts that are associated with the user in the communicator through the "add friends" process using a phone number or ID. As another example, the account recommendation unit 310 can recommend accounts on the communicator that match the user's interests. Promoted accounts, such as influencer accounts with a certain number of followers, can also be recommended. Among the recommended accounts for timeline subscription, the account recommendation unit 310 can distinguish and display followed accounts (with a subscription relationship already established) and unfollowed accounts (without a subscription relationship established).

In step S420, the subscription relationship setting unit 320 may establish subscription relationships based on the user following at least some of the recommended accounts. In other words, the subscription relationship setting unit 320 may set up a subscription relationship based on following, different from the relationship with the communicator friend, for timeline subscriptions. Based on the user's settings, the subscription relationship setting unit 320 may establish subscription relationships with unfollowed accounts among the recommended accounts and may also unsubscribe from currently followed accounts.

In step S430, the post provider 330 may provide posts from the user's followed accounts in a timeline format based on the user's following subscription relationship. In a timeline service, a timeline view of posts uploaded via a Communicator account can be provided. In this case, posts from the user's followed accounts are arranged and provided in chronological order. Therefore, the post provider 330 may provide posts from accounts with which the user has established a following subscription relationship in a timeline format. If the timeline is provided as a Communicator service, it can be changed from a subscription relationship based on Communicator friends to a subscription relationship based on following.

In this specification, when a timeline service is provided in a communicator using a social graph based on friendship, a timeline service using a social graph based on following, which is different from the social graph based on friendship, may be provided.

5 to 8 are exemplary diagrams for illustrating a process of setting an attention-based subscription relationship according to an embodiment of the present invention.

When entering the timeline service in the communicator, a user guidance process can be provided for changing the friend-based subscription relationship applied in the existing subscription list to the follow-based subscription relationship.

As an example, the processor 220 may provide a tutorial-style account recommendation screen for finding new followers and setting up subscription relationships.

5 , when a “Timeline” menu 501 is selected on a service screen 500 provided as another function of the communicator (such as a chat service or a call service) to move to the timeline service, the processor 220 can receive the user's selection through an intro page 50 to maintain a friend-based subscription list or change to a follow-based subscription list.

When the user requests to change to an interest-based subscription list through the introduction page 50, as shown in FIG6 , the processor 220 may provide an interest setting screen 610 for setting the user's interests.

The interest setting screen 610 may include a category directory 611 for categorizing a communicator account or post, etc. Relevant categories may be set during the process of creating a communicator account or registering a post, so that the account or post, etc. may be categorized according to each category.

The user can select one or more categories corresponding to his or her interests in the category list 611 of the interest setting screen 610. When the user's interest setting is completed, the processor 220 can provide the account on the communicator that corresponds to the user's interest as a recommended account.

When the user's interests are set, as shown in FIG7 , the processor 220 may provide an influencer recommendation screen 720. The processor 220 may provide an influencer recommendation directory 721, which is composed of influencer accounts of categories corresponding to the user's interests among influencer accounts with a certain number of followers or more.

For each account included in the influencer recommendation directory 721, at least one post of the corresponding account (e.g., the most recently created post, the post with the most action, etc.) can be displayed, and a "Follow" menu 72 can be provided for setting up a subscription relationship. Among the recommended accounts, the "Follow" menu 72 can be provided for unfollowed accounts that the user has not followed. On the other hand, for followed accounts that the user has followed, the account can be displayed as a followed account and an "Unfollow" menu can be provided for unfollowing the account.

Users can use the 721 influencer recommendation directory to find influencer accounts with common interests and set up subscription relationships by following them.

When the user requests the next recommendation list, the processor 220 may provide a friend recommendation screen 730. The processor 220 may provide a friend recommendation list 731 composed of accounts that have established a relationship with the user through a friend adding process using a phone number or ID, among general accounts on the communicator.

A "Follow" menu 73 for setting a follow as a subscription relationship may be provided for each account included in the friend recommendation directory 731. Among the recommended accounts, a "Follow" menu 73 may be provided for unfollowed accounts that the user has not followed, while an "Unfollow" menu for canceling the follow setting may be provided for followed accounts that the user has already followed.

The processor 220 may also recommend official accounts in addition to general accounts.

When the user requests the next recommendation list, as shown in Figure 8, the processor 220 may provide an official account recommendation screen 840. The processor 220 may provide an official account recommendation list 841 consisting of official accounts on the communicator that have established a relationship with the user through the friend addition process using a phone number or ID.

A "Follow" menu 84 for setting a subscription relationship for each account included in the official account recommendation directory 841 can be provided. Among the recommended accounts, a "Follow" menu 84 can be provided for unfollowed accounts that the user has not followed, while an "Unfollow" menu for canceling the follow setting can be provided for followed accounts that the user has already followed.

The friend recommendation directory 731 and the official account recommendation directory 841 may also be provided as one directory instead of being provided as separate directories.

In the Timeline service, instead of applying subscription relationships to all Communicator friends (regular accounts and official accounts set as friends), selective subscription relationships can be applied based on the following set directly by the user.

When the follow setting using the recommended account is completed, the processor 220 may provide a timeline service screen 800 to which the follow-based subscription relationship is applied.

The processor 220 may perform follow migration on the timeline by changing a friend-based subscription relationship to a follow-based subscription relationship, and may provide a timeline feed based on the follow-based subscription relationship.

8 , the user's subscribed post directory is displayed in a timeline service screen 800 in a timeline type, and posts 80 of accounts that the user has followed can be arranged and displayed in chronological order.

Furthermore, the timeline service screen 800 may include a list of accounts 801 that the user is currently following, and when a specific account is selected in the list of followed accounts 801, a list of posts of the selected account may be provided.

The timeline service screen 800 may also include a menu 802 for adding a followed account, a menu 803 for confirming various notifications related to the timeline service, a menu 804 for confirming the user's attention such as the followed account, follower account, etc.

Therefore, the processor 220 can recommend internet celebrity accounts that the user is interested in, as well as general accounts or official accounts with which the user has established a friend relationship, to search for new followers and set up subscription relationships.

In addition to the paths described with reference to FIG5 and FIG8, accounts for setting up follow-up can be recommended through various paths when using the timeline service.

In this embodiment, in order to encourage new accounts to follow in the timeline service, accounts that users can follow can be recommended in the form of relationship-based recommendations. In this case, the recommendation pool can be constructed by a social graph based on friend relationships and a social graph based on follow relationships.

When recommending accounts, the account recommendation unit 310 may apply one or more of the following common requirements. For example, the account recommendation unit 310 may filter recommended accounts from accounts permitted to be followed to form a recommendation pool. As another example, the account recommendation unit 310 may exclude accounts without profile images in the timeline service, accounts with a history of disciplinary actions due to reports, etc., from the recommendation targets. As another example, the account recommendation unit 310 may filter accounts with a predetermined number (e.g., four) or more of their posts that are fully public, and recommend them. At this time, the number of all public posts used as a criterion for account recommendations may be limited to posts created with specific types of content (e.g., images, videos, audio, etc.) rather than posts created solely with text.

FIG9 is a flowchart illustrating an example of a process of forming an account recommendation pool according to an embodiment of the present invention.

The process of FIG. 9 may be included in step S410, and according to an embodiment, part of the steps may also be executed in the server 150.

Referring to FIG. 9 , in step S901, the account recommendation unit 310 may select at least one recommended account (hereinafter referred to as a "follow-based recommended account") based on follow-up relevance, which indicates a subscription relationship within the timeline service. For example, the account recommendation unit 310 may select the following of accounts followed by a user as follow-up recommended accounts. For example, if user A follows user B and user C, user B follows user D and user E, and user C follows user F, user D, user E, and user F may be recommended to user A. As another example, the account recommendation unit 310 may select accounts similar to the accounts followed by the user as follow-up recommended accounts. For example, if user A follows user B and user C, user B and user D have a high number of co-follows, and user C and user E have a high number of co-follows, user D and user E may be recommended to user A. In another example, the account recommendation unit 310 may select accounts that the user is not following, i.e., accounts that the users are not following each other, as follow-based recommended accounts. For example, if user D follows user A but user A does not follow user D, user D may be recommended to user A.

In step S902, the account recommendation unit 310 may select at least one recommended account (hereinafter referred to as a "popularity-based recommended account") based on the number of followers within the timeline service. The account recommendation unit 310 may select general accounts or official accounts with a large number of followers within the timeline service, as well as influencer accounts, which serve as promotional accounts, as popularity-based recommended accounts. For example, the account recommendation unit 310 may filter a predetermined number of accounts, starting with the highest priority, in order of follower count, and then randomly select a popularity-based recommended account from the filtered accounts without weighting the order. As another example, the account recommendation unit 310 may filter a predetermined number of accounts, starting with the highest priority, in order of the number of followers, and then select accounts with a history of posting within a predetermined period of time (e.g., three days) as recommended accounts based on popularity. In another example, the account recommendation unit 310 may filter accounts with a history of posting within a predetermined period of time, and then select accounts with a predetermined number of followers or more from the filtered accounts as recommended accounts based on popularity.

In addition to the number of followers, the level of user reactions to a user's posts and the rate of follower growth and decline can also be used to enhance the criteria for selecting recommended accounts based on popularity. For example, the account recommendation unit 310 can calculate an author score by summing the follower growth and decline rate relative to the number of impressions of the account's posts within a recent predetermined period and the user reaction score (e.g., number of clicks) for posts generated by the account. In this case, the user reaction score, which represents the level of reaction to a post, can be calculated by assigning a predetermined score to each reaction type. For example, clicking on a comment on a post and reading the post assigns +5 points, sharing a post assigns +5 points, entering a comment or like on a post assigns +3 points, hiding a post assigns -5 points, and reporting a post assigns -30 points. Furthermore, the account recommendation unit 310 can calculate the author rating by determining a reflection ratio for each measurement criterion. For example, the follower increase/decrease rate and the user reaction score can be reflected at a ratio of 50% each, or at different ratios. The account recommendation unit 310 can select accounts with higher author ratings as recommended accounts based on popularity. In other words, the account recommendation unit 310 may select, among accounts active in the timeline service, accounts that have received many positive responses from other users and whose number of followers has recently increased rapidly, as recommended accounts based on popularity.

In step S903, the account recommendation unit 310 may create a recommendation pool that includes recommended accounts based on follow and recommended accounts based on popularity as relationship-based recommendations for users. Referring to Figure 10 , the account recommendation unit 310 may combine recommended accounts based on follow 1010 and recommended accounts based on popularity 1020 to create a recommendation pool 1000 to attract new accounts. For example, the account recommendation unit 310 may combine recommended accounts based on follow 1010 and recommended accounts based on popularity 1020 at a predetermined fixed ratio to create the recommendation pool 1000. For example, the account recommendation unit 310 may maintain a 50:50 ratio between recommended accounts 1010 based on follower counts and recommended accounts 1020 based on popularity. In this case, the ratio of followers, similar accounts, and non-following accounts belonging to the recommended accounts 1010 based on follower counts is approximately 16.6:16.6:16.6, while the ratio of general accounts, official accounts, and influencer accounts belonging to the recommended accounts 1020 based on popularity is 15:15:20. As another example, the account recommendation unit 310 may mix recommended accounts 1010 based on follower counts and recommended accounts 1020 based on popularity at an adjusted ratio to form the recommendation pool 1000. The proportions used to make up the recommendation pool 1000 can be determined based on the proportions of various account types. For example, if the total number of selected accounts is 100, of which 40 are follow-based recommendation accounts 1010 and 60 are popularity-based recommendation accounts 1020, the ratio of follow-based recommendation accounts 1010 to popularity-based recommendation accounts 1020 can be adjusted to 40:60 to form the recommendation pool 1000. Sub-accounts belonging to the follow-based recommendation accounts 1010 and popularity-based recommendation accounts 1020 can also be divided and mixed based on the proportions of each account type.

To continuously attract new accounts within the timeline service, the account recommendation unit 310 creates and provides a pool of recommended accounts, including popular accounts and personalized recommendations based on their relevance to the user's followers. Account recommendation unit 310 can promote accounts in the recommendation pool through various channels, such as providing service screens showing posts from already-followed accounts in a timeline format.

Furthermore, the account recommendation unit 310 may additionally apply the follow relevance obtained through the follow-based social graph and the friend relationship obtained through the friend-based social graph as recommendation conditions, thereby improving the relationship-based recommendation technology.

FIG11 is a flow chart illustrating an example of a process for assigning an exposure order to recommended accounts based on attention according to an embodiment of the present invention.

The process of FIG. 11 may be included in step S901, and according to an embodiment, part of the steps may also be executed in the server 150.

The account recommendation unit 310 may adjust the exposure order so that among the recommended accounts based on follow-up included in the recommendation pool, accounts that meet the highest priority exposure conditions are exposed before other accounts. In this case, the exposure order may be determined based on at least one of friendship and timeline activity.

Referring to Figure 11, in step S1101, the account recommendation unit 310 prioritizes exposure for accounts selected based on follow-relatedness and those that have been added as a user's Communicator friend within a predetermined period (e.g., 60 days). The account recommendation unit 310 may filter out accounts that are not followed by Communicator friends before recommending them, to avoid missing Communicator friends from the recommended list. For accounts that are follow-related and recently added as Communicator friends, the account recommendation unit 310 may adjust their exposure ranking to prioritize them over accounts that are only follow-related.

In step S1102, the account recommendation unit 310 prioritizes exposure for accounts recommended based on follower status that have posted within a predetermined period (e.g., 30 days). The account recommendation unit 310 selects and recommends accounts with recent posting history. For accounts with both follower-related and recent posting history, the account recommendation unit 310 adjusts their exposure ranking to prioritize them over accounts with only follower-related status.

The account recommendation unit 310 may give the highest priority to the account that meets all the following conditions, including the following relevance condition, the condition of being recently added as a friend in the communicator, and the condition of recent activity in the timeline service, among the recommended accounts based on following.

The account recommendation unit 310 may calculate a recommendation score for each recommended account based on follow-up relevance, friendship relationships, and timeline activity, and the higher the recommendation score, the higher the priority for exposure.

The account recommendation unit 310 can prioritize exposure to users and provide relationship-based recommendations using various exposure criteria. For example, the first priority level can be 50% of all recommended accounts based on following, filtering out accounts that meet all criteria for following relevance, friendship, and timeline activity (accounts with following relevance, a history of being recently added as a user's Messenger friend, and a history of recently creating a post). The second priority level can be 25% of all recommended accounts based on following, filtering out accounts that meet two of the following relevance, friendship, and timeline activity criteria (accounts with following relevance and a history of being recently added as a Messenger friend, or accounts with following relevance and a history of recently creating a post). The third priority level may be equal to 25% of all accounts recommended based on following, and may filter for accounts that meet one of the following relevance, friend relationship, and timeline activity criteria (accounts with following relevance, accounts with a profile that has been recently added as a friend in the Messenger, and accounts with a profile that has recently created a post).

12 and 13 are diagrams illustrating example screens for exposing an account recommendation directory according to an embodiment of the present invention.

12 , the processor 220 may expose an account recommendation directory 1251 for following a new account on the timeline service screen 800 , in which posts 80 of accounts followed by the user are arranged and displayed in chronological order.

The account recommendation directory 1251 may include recommended accounts based on attention and recommended accounts based on popularity. The processor 220 may sequentially expose the accounts included in the recommendation pool according to scrolling of the account recommendation directory 1251.

Processor 220 can prioritize and position recommended accounts based on following among the recommended accounts in the recommendation pool in the top slot of account recommendation directory 1251 for exposure. Recommended accounts based on following are expected to have higher click-through rates (CTRs) than other accounts, and thus, their priority placement can be used to attract readers. In this case, if there are no recommended accounts based on following in the recommendation pool, recommended accounts based on popularity can occupy the entire account recommendation directory 1251.

A “Follow” menu 125 for setting a follow as a subscription relationship may be provided for each account included in the account recommendation directory 1251.

Furthermore, a “Remove” menu 1201 may be provided to remove the corresponding account from the recommendation pool for each account included in the account recommendation directory 1251. The account removed from the recommendation pool using the “Remove” menu 1201 may be excluded from the recommendation target for a predetermined period of time (e.g., 7 days).

Regarding the account recommendation directory 1251, a "View More" menu 1202 may be provided. When the "View More" menu 1202 is selected, the user may be directed to the account recommendation directory page 1300 as shown in FIG. 13 .

The processor 220 may provide a list of all account recommendations included in the recommendation pool 1310 via the account recommendation list page 1300. The recommended account list page 1300 may provide a “Follow” menu 125 for setting a subscription relationship for each account included in the list of all account recommendations 1310 and a “Remove” menu 1201 for removing the corresponding account from the recommendation pool.

The processor 220 can recommend accounts that the user can follow through various paths in the timeline service.

Therefore, in this embodiment, in order to guide the attention of new accounts within the timeline service, personalized relationship-based recommendations can be provided by following relevance. In order to further improve relationship-based recommendations, at least one of friend relationships, timeline activity, follower increase and decrease rate, and user response score can be additionally applied as a recommendation condition.

The devices described above can be implemented using hardware components, software components, and/or a combination of hardware and software components. For example, the devices and components described in the embodiments of the present invention can be implemented using one or more general-purpose or special-purpose computers, such as processors, controllers, arithmetic logic units (ALUs), digital signal processors (DSPs), microcomputers, field-programmable gate arrays (FPGAs), programmable logic units (PLUs), microprocessors, or other devices capable of executing and responding to instructions. The processing device can execute an operating system (OS) and one or more software applications running on the OS. Additionally, the processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is described as using only a single processing device, but those skilled in the art will appreciate that the processing device may include multiple processing elements and/or multiple types of processing elements. For example, the processing device may include multiple processors, or a processor and a controller. Alternatively, another processing configuration, such as a parallel processor, may be employed.

Software may include one or more of a computer program, code, instructions, or combinations thereof, and may configure a processing device or, independently or in combination, instruct a processing device to perform desired operations. Software and/or data may be implemented as any type of machine, component, physical device, computer storage medium, or device for interpretation by a processing device or for providing instructions or data to a processing device. Software may be distributed across networked computer systems, allowing the software to be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment can be implemented in the form of program instructions that can be executed by various computer units and recorded on computer-readable media. In this case, the medium can continuously store the program that can be executed by the computer, or temporarily store it for execution or downloading. In addition, the medium can be various recording devices or storage devices in the form of a single or multiple hardware combinations, but is not limited to media directly connected to any computer system and can also be distributed on a network. Examples of media include magnetic media such as hard drives, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; ROM, RAM, flash memory, etc., which can be used to store program instructions. Another example of a medium may be an application store that distributes applications, a website that provides or distributes other software, a recording medium or storage medium managed by a server, etc.

As described above, the embodiments are described by way of limited examples and drawings. However, those skilled in the art may make various modifications and variations based on the above description. For example, even if the described techniques are performed in a different order than the described method, and/or the described systems, structures, devices, circuits, and other structural elements are combined or combined in a different manner than the described method, or are replaced or substituted with other components or equivalents, appropriate results may still be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are within the scope of the claims.

50: Introduction Page 72: Menu 73: Menu 80: Posts 84: Menu 110: Electronic Devices 120: Electronic Devices 125: Menu 130: Electronic Devices 140: Electronic Devices 150: Server 160: Server 170: Network 200: Computer Device 210: Memory 220: Processor 230: Communication Interface 240: Input/Output Interface 250: Input/Output Devices 310: Account Recommendation 320: Subscription Relationship Settings 330: Post Provisioning 500: Service Screen 501: Menu 610: Settings Screen 611: Category Directory 720: Recommendation Screen 721: Recommendation Directory 730: Recommendation Screen 731: Recommendation Directory 800: Service Screen 801: Account Directory 802: Menu 840: Recommendation Screen 841: Recommendation Directory 1000: Recommendation Pool 1010: Recommended Account 1020: Recommended Account 1201: Menu 1202: Menu 1251: Recommendation Directory 1300: Recommendation Directory Page 1310: Account Recommendation Directory S410: Step S420: Step S430: Step S901: Step S902: Step S903: Step S1101: Step S1102: Step

FIG1 is a diagram showing an example of a network environment according to an embodiment of the present invention.

FIG2 is a block diagram showing an example of a computer device according to an embodiment of the present invention.

FIG3 is a diagram showing an example of constituent elements that may be included in a processor of a computer device according to an embodiment of the present invention.

FIG4 is a flowchart illustrating an example of a method that can be performed by a computer device according to an embodiment of the present invention.

5 to 8 are exemplary diagrams for illustrating a process of setting an attention-based subscription relationship according to an embodiment of the present invention.

FIG9 is a flowchart illustrating an example of a process of forming an account recommendation pool according to an embodiment of the present invention.

FIG10 is a diagram showing an example of the configuration of an account recommendation pool according to an embodiment of the present invention.

FIG11 is a flow chart illustrating an example of a process for assigning an exposure order to recommended accounts based on attention according to an embodiment of the present invention.

12 and 13 are diagrams illustrating example screens for exposing an account recommendation directory according to an embodiment of the present invention.

S410: Step

S901~S903: Steps

Claims (18)

An account recommendation method executed in a computer device, characterized in that the computer device includes at least one processor, the at least one processor being configured to execute computer-readable commands included in a memory, and providing a timeline service as a function included in a community using a social graph based on friend relationships, wherein the community is a communication service, and the social graph is based on friend relationships established between multiple users of the communication service; the timeline service provides a timeline based on subscription relationships, wherein the subscription relationships are based on relationships established between multiple users. The at least one processor selects a recommended account based on popularity based on the number of followers in the timeline service; and the at least one processor mixes the recommended account based on popularity with the recommended account based on the follower count to form a recommendation pool. The account recommendation method according to claim 1 is characterized in that the step of selecting a recommended account based on follow-up includes: selecting at least one of an account followed by an account already followed by the user, an account similar to the account already followed by the user, and an account that has followed the user but is not followed by the user, as the recommended account based on follow-up. The account recommendation method of claim 1 is characterized in that the step of selecting a popularity-based recommended account includes: selecting the popularity-based recommended account using the number of followers of at least one of a general account, an official account, and a promotional account. The account recommendation method of claim 1 is characterized in that the step of selecting a popularity-based recommended account includes: filtering a predetermined number of accounts in order of the number of followers, and then randomly selecting the popularity-based recommended account from the filtered accounts. The account recommendation method according to claim 1 is characterized in that the step of selecting a recommended account based on popularity includes: after filtering a predetermined number of accounts in order of the number of followers, selecting an account with a history of creating a post within a recent predetermined time as the recommended account based on popularity, or after filtering accounts with a history of creating a post within a recent predetermined time, selecting an account with a number of followers greater than a predetermined value among the filtered accounts as the recommended account based on popularity. The account recommendation method according to claim 1 is characterized in that the step of selecting the recommended account based on popularity includes: selecting the recommended account based on popularity using a user response score for posts owned by each account and a follower increase or decrease rate during a recent predetermined period of time. The account recommendation method according to claim 1 is characterized in that the step of forming the recommendation pool includes: mixing the recommended accounts based on attention and the recommended accounts based on popularity in a predetermined fixed ratio to form the recommendation pool. The account recommendation method according to claim 1 is characterized in that the step of forming the recommendation pool includes: mixing the recommended accounts based on attention and the recommended accounts based on popularity in a ratio adjusted according to the number of selections to form the recommendation pool. The account recommendation method according to claim 1 is characterized in that the account recommendation method further includes the following step: determining, by the at least one processor, an exposure order for the follow-based recommended account based on at least one of a friendship relationship with the user and timeline activity. The account recommendation method according to claim 1 is characterized in that the account recommendation method further includes the following step: by the at least one processor, giving priority to the accounts with a history of creating post resumes within a recent predetermined time period among the recommended accounts based on attention, so that the accounts are exposed at a higher position than other accounts. A computer program stored in a computer-readable recording medium causes a computer device to execute the account recommendation method described in any one of claims 1 to 10. A computer device, characterized in that it includes at least one processor, the at least one processor being configured to execute computer-readable instructions included in a memory, and providing a timeline service as a function included in a community using a social graph based on friend relationships, wherein the community is a communication service, and the social graph is based on friend relationships established between multiple users of the communication service, and the timeline service provides a timeline based on subscription relationships, wherein the subscription relationships are based on multiple The at least one processor processes the following processes: selecting a recommended account based on attention based on the attention relevance representing the subscription relationship in the timeline service; selecting a recommended account based on popularity based on the number of followers in the timeline service; and mixing the recommended account based on attention and the recommended account based on popularity to form a recommendation pool. The computer device according to claim 12 is characterized in that the at least one processor selects at least one of an account followed by an account already followed by the user, an account similar to the account already followed by the user, and an account that has followed the user but is not followed by the user, as the recommended account based on attention. The computer device according to claim 12 is characterized in that, after filtering a predetermined number of accounts in order of the number of followers, the at least one processor selects an account with a history of creating a post within a recent predetermined time from among the filtered accounts as the recommended account based on popularity, or after filtering accounts with a history of creating a post within a recent predetermined time, selects an account with a number of followers greater than a predetermined value from among the filtered accounts as the recommended account based on popularity. The computer device of claim 12, wherein the at least one processor selects the popularity-based recommended account using a user response score for posts of each account and a follower increase/decrease rate during a recent predetermined period of time. The computer device according to claim 12 is characterized in that the at least one processor mixes the recommendation account based on attention and the recommendation account based on popularity in a predetermined fixed ratio to form the recommendation pool. The computer device according to claim 12 is characterized in that the recommendation pool is constructed by mixing the recommendation account based on attention and the recommendation account based on popularity in a ratio adjusted according to the number of selections. The computer device of claim 12, wherein the at least one processor determines an exposure order for the follow-based recommended accounts based on at least one of a friendship relationship with the user and timeline activity.