Granted Patent B2

US 12,744,945 · App. 18/715,725 · Granted Sep 22, 2026

Inventor: Yuanyuan Sun (Shanghai, CN)

Assignee: SHANGHAI BILIBILI TECHNOLOGY CO., LTD.

H04N21/2187A61B5/024H04N21/44204H04N21/4788

Abstract

Claims (79)

1 . A method for determining click-farming in a live room, comprising:

receiving, at a server of a livestreaming platform, periodic heartbeat signals reported by client computing devices associated with users currently viewing a target live room, wherein the heartbeat signals reported by the client computing devices comprise IP addresses of the client computing devices;

determining user distribution information associated with a target live room of the livestreaming platform by determining location information of the users based on the IP addresses of the client computing devices associated with the users, and determining a user distribution ratio based on the user distribution information;

obtaining population density distribution information, and determining a population density distribution ratio based on the population density distribution information;

determining whether click-farming exists in the target live room based on the user distribution ratio and the population density distribution ratio by determining, for each region, a distribution variation and determining that click-farming exists when at least one distribution variation for a region is greater than or equal to a preset threshold; and

automatically initiating a punishment action with respect to the target live room in which click-farming exists.

2 . The method according to claim 1 , wherein the determining user distribution information associated with a target live room comprises:

determining a set of users corresponding to the target live room; and

generating the user distribution information based on the location information of each user, wherein the location information comprises at least one of province information or city information of each user.

3 . The method according to claim 2 , wherein the determining a user distribution ratio based on the user distribution information comprises:

determining a quantity of users from the set of users associated with a same piece of location information; and

determining the user distribution ratio based on quantities of users associated with different pieces of location information.

4 . The method according to claim 1 , wherein the obtaining population density distribution information comprises:

sending a request for obtaining the population density distribution information to a statistics server; and

receiving the population density distribution information returned by the statistics server, wherein the population density distribution information comprises real-life population density distribution information.

5 . The method according to claim 1 , wherein the determining whether click-farming exists in the target live room based on the user distribution ratio and the population density distribution ratio comprises:

computing a distribution variation associated with each piece of location information based on the user distribution ratio and the population density distribution ratio; and

determining that click-farming does not exist in the target live room in response to determining that the distribution variation is less than the preset threshold; and

determining that click-farming exists in the target live room in response to determining that the distribution variation is greater than or equal to the preset threshold.

6 . The method according to claim 5 , wherein the computing a distribution variation associated with each piece of location information based on the user distribution ratio and the population density distribution ratio comprises:

determining a target user distribution ratio associated with a particular piece of location information based on the user distribution ratio;

determining a target population density distribution ratio based on the population density distribution ratio and the particular piece of location information; and

computing a target distribution variation based on a difference of the target user distribution ratio relative to the target population density distribution ratio.

7 . The method according to claim 6 ,

wherein the determining that click-farming does not exist in the target live room in response to determining that the distribution variation is less than a preset threshold comprises determining that click-farming does not exist in the target live room in response to determining that the target distribution variation is less than the preset threshold; and

wherein the determining that click-farming exists in the target live room in response to determining that the distribution variation is greater than or equal to the preset threshold comprises determining that click-farming exists in the target live room in response to determining that the target distribution variation is greater than or equal to the preset threshold.

8 . The method according to claim 1 , further comprising:

obtaining information associated with livestreaming content of the target live room; and

determining whether click-farming exists in the target live room based on the information associated with the livestreaming content and the user distribution ratio in response to determining that click-farming does not exist in the target live room based on the user distribution ratio and the population density distribution ratio.

9 . The method according to claim 8 , wherein the information associated with the livestreaming content comprises a livestreaming language of a livestream in the target live room; and wherein the determining whether click-farming exists in the target live room based on the information associated with the livestreaming content and the user distribution ratio comprises:

determining a target user language based on the user distribution ratio;

determining that click-farming does not exist in the target live room in response to determining that the target user language matches the livestreaming language; and

determining that click-farming exists in the target live room in response to determining that the target user language fails to match the livestreaming language.

10 . The method according to claim 8 , wherein the information associated with the livestreaming content comprises at least one of an introduction of a livestream in the target live room or bullet-screen comments on the livestream; and wherein the determining whether click-farming exists in the target live room based on the livestreaming content and the user distribution ratio comprises:

determining a target keyword based on the at least one of the introduction of the livestream or the bullet-screen comments on the livestream;

determining a target region based on the user distribution ratio, wherein the target region corresponds to a piece of location information with a highest value in the user distribution ratio;

calculating a degree of association between the target keyword and the target region;

determining that click-farming does not exist in the target live room in response to determining that the degree of association is greater than a preset association threshold; and

determining that click-farming exists in the target live room in response to determining that the degree of association is less than or equal to the preset association threshold.

11 . The method according to claim 1 , further comprising:

obtaining a set of scheduling information associated with the target live room;

querying a quantity of reuse times for entering the target live room by reusing each piece of scheduling information in the set of the scheduling request information, wherein each piece of scheduling information comprises a playing address associated with the target live room;

determining that click-farming exists in the target live room in response to determining that a piece of scheduling information with reuse times being greater than a preset threshold exists in the set of the scheduling information; and

determining that click-farming does not exist in the target live room in response to determining that no piece of scheduling information with reuse times being greater than the preset threshold exists in the set of the scheduling information.

12 . The method according to claim 1 , further comprising:

determining an initial live room on the livestreaming platform, and obtaining a quantity of users in the initial live room; and

determining the initial live room as the target live room in response to determining that the quantity of users exceeds a preset user quantity threshold.

13 . A computing device, comprising a memory, a processor, and computer instructions stored in the memory and executable by the processor, wherein the computer instructions upon execution by the processor cause the processor to implement operations comprising:

receiving, at a server of a livestreaming platform, periodic heartbeat signals reported by client computing devices associated with users currently viewing a target live room, wherein the heartbeat signals reported by the client computing devices comprise IP addresses of the client computing devices;

determining user distribution information associated with a target live room of the livestreaming platform by determining location information of the users based on the IP addresses of the client computing devices associated with the users, and determining a user distribution ratio based on the user distribution information;

obtaining population density distribution information, and determining a population density distribution ratio based on the population density distribution information;

determining whether click-farming exists in the target live room based on the user distribution ratio and the population density distribution ratio by determining, for each region, a distribution variation and determining that click-farming exists when at least one distribution variation for a region is greater than or equal to a preset threshold; and

automatically initiating a punishment action with respect to the target live room in which click-farming exists.

14 . The computing device according to claim 13 , wherein the determining user distribution information associated with a target live room comprises:

determining a set of users corresponding to the target live room; and

generating the user distribution information based on the location information of each user, wherein the location information comprises at least one of province information or city information of each user.

15 . The computing device according to claim 14 , wherein the determining a user distribution ratio based on the user distribution information comprises:

determining a quantity of users from the set of users associated with a same piece of location information; and

determining the user distribution ratio based on quantities of users associated with different pieces of location information.

16 . The computing device according to claim 13 , wherein the determining whether click-farming exists in the target live room based on the user distribution ratio and the population density distribution ratio comprises:

computing a distribution variation associated with each piece of location information based on the user distribution ratio and the population density distribution ratio, wherein the computing a distribution variation associated with each piece of location information based on the user distribution ratio and the population density distribution ratio comprises:

determining a target user distribution ratio associated with a particular piece of location information based on the user distribution ratio,

determining a target population density distribution ratio based on the population density distribution ratio and the particular piece of location information, and

computing a target distribution variation based on a difference of the target user distribution ratio relative to the target population density distribution ratio;

determining that click-farming does not exist in the target live room in response to determining that the target distribution variation is less than a preset threshold; and

determining that click-farming exists in the target live room in response to determining that the target distribution variation is greater than or equal to the preset threshold.

17 . The computing device according to claim 13 , the operations further comprising:

obtaining information associated with livestreaming content of the target live room; and

determining whether click-farming exists in the target live room based on the information associated with the livestreaming content and the user distribution ratio.

18 . The computing device according to claim 17 , wherein the information associated with the livestreaming content comprises a livestreaming language of a livestream in the target live room, and wherein the determining whether click-farming exists in the target live room based on the information associated with the livestreaming content and the user distribution ratio comprises:

determining a target user language based on the user distribution ratio;

determining that click-farming does not exist in the target live room in response to determining that the target user language matches the livestreaming language; and

determining that click-farming exists in the target live room in response to determining that the target user language fails to match the livestreaming language.

19 . A non-transitory computer-readable storage medium, storing computer instructions, wherein the computer instructions upon execution by a processor cause the processor to implement operations comprising:

receiving, at a server of a livestreaming platform, periodic heartbeat signals reported by client computing devices associated with users currently viewing a target live room, wherein the heartbeat signals reported by the client computing devices comprise IP addresses of the client computing devices;

determining user distribution information associated with a target live room of the livestreaming platform by determining location information of the users based on the IP addresses of the client computing devices associated with the users, and determining a user distribution ratio based on the user distribution information;

obtaining population density distribution information, and determining a population density distribution ratio based on the population density distribution information;

determining whether click-farming exists in the target live room based on the user distribution ratio and the population density distribution ratio by determining, for each region, a distribution variation and determining that click-farming exists when at least one distribution variation for a region is greater than or equal to a preset threshold; and

automatically initiating a punishment action with respect to the target live room in which click-farming exists.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (19)