IP Library Granted Patent US 12,445,661
Granted Patent B2
US 12,445,661 · App. 18/685,209 · Granted Oct 14, 2025

Virtual object interaction method, apparatus, storage medium and computer program product

Inventor: Qimin Tan (Hangzhou, CN)
Assignee: Hangzhou AliCloud Feitian Information Technology Co., Ltd.
H04N21/2187G06T13/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,445,661
App. No.
18/685,209
Granted
Oct 14, 2025
Kind
B2
Abstract

Embodiments of the present application provide a virtual object interaction method, an apparatus, a storage medium and a computer program product, and the virtual object interaction method includes: performing a live stream by using a first virtual streamer in a first live stream room of a live stream platform; making a virtual interactive object appear in the first live stream room for a preset time period during the live stream of the first live stream room, and the preset time period is shorter than a time period of the live stream in the first live stream room; where the first virtual streamer performs a live stream task set by the using party of the first live stream room, and the virtual interactive object performs an interactive task set by a manager of the live stream platform.

Claims (61)

1. A method of virtual object interaction, applied to a live stream platform configured to provide one or more live stream rooms for a using party to conduct a live stream activity, the method comprising:

performing a live stream by using a first virtual streamer in a first live stream room of the live stream platform;

making a virtual interactive object appear in the first live stream room for a preset time period during the live stream of the first live stream room, the preset time period being shorter than a time period of the live stream of the first live stream room;

obtaining an appearing time point when the virtual interactive object appears in the first live stream room, the appearing time point being randomly set; and

making the virtual interactive object appear in the first live stream room when current time reaches the appearing time point,

wherein the first virtual streamer performs a live stream task set by the using party of the first live stream room, and the virtual interactive object performs an interactive task set by a manager of the live stream platform.

2. The method according to claim 1 , wherein the method further comprises:

generating interactive information based on the virtual interactive object, wherein the interactive information is related to the interactive task to be performed by the virtual interactive object.

3. The method according to claim 2 , wherein the generating interactive information based on the virtual interactive object comprises:

displaying an interactive prompt related to the virtual interactive object, wherein the interactive prompt is used to prompt a user to perform an interactive input; and

receiving the interactive input of the user to the virtual interactive object, and generating the interactive information according to the interactive input.

4. The method according to claim 3 , wherein the generating the interactive information according to the interactive input comprises:

determining an interactive behavior corresponding to the virtual interactive object according to the interactive input, and generating the interactive information based on the interactive behavior, wherein the interactive behavior includes an action and a posture of the virtual interactive object interacting with the user.

5. The method according to claim 2 , wherein the generating interactive information based on the virtual interactive object comprises:

obtaining key information of a live stream target included in a live stream content according to the live stream content of the first virtual streamer, and generating the interactive information based on the key information.

6. The method according to claim 5 , wherein the obtaining key information of the live stream target included in a live stream content according to the live stream content of the first virtual streamer comprises:

obtaining text information of the live stream content of the first virtual streamer; and

performing a semantic recognition on the text information, determining the live stream target included in the live stream content according to a result of the semantic recognition, and obtaining the key information of the live stream target.

7. The method according to claim 1 , wherein the method further comprises:

providing guidance information corresponding to a second live stream room when the virtual interactive object appears in the first live stream room of the live stream platform, wherein the guidance information is used for guiding a user to follow the virtual interactive object into the second live stream room, and the second live stream room performs a live stream using a second virtual streamer; and

displaying the guidance information on the live interface of the first live stream room.

8. The method according to claim 7 , wherein the method further comprises:

making the virtual interactive object appear in the second live stream room;

wherein a way in which the virtual interactive object appears in the second live stream room is the same or different from a way in which the virtual interactive object appears in the first live stream room, and time at which the virtual interactive object appears in the second live stream room is the same or different from time at which the virtual interactive object appears in the first live stream room.

9. The method according to claim 7 , wherein the method further comprises:

receiving an input of the user to follow the virtual interactive object, so that a viewing picture of the user switches from the first live stream room to the second live stream room.

10. The method according to claim 1 , wherein the method further comprises:

displaying at least one of visual effect or sound effect of the virtual interactive object appearing in the first live stream room on a display interface of the first live stream room when the virtual interactive object appears in the first live stream room; and

displaying at least one of visual effect or sound effect of the virtual interactive object leaving the first live stream room on the display interface of the first live stream room when the virtual interactive object leaves the first live stream room.

11. A virtual object interactive apparatus, applied to a live stream platform which provides one or more live stream rooms for a using party to conduct a live stream activity, the virtual object interactive apparatus comprising:

at least one memory that stores computer executable instructions; and

at least one processor configured to execute the computer executable instructions stored in the memory to:

establish a first live stream room on the live stream platform to perform a live stream by using a first virtual streamer;

make a virtual interactive object appear in the first live stream room for a preset time period during the live stream of the first live stream room, the preset time period being shorter than a time period of the live stream in the first live stream room;

obtain an appearing time point when the virtual interactive object appears in the first live stream room, the appearing time point being randomly set; and

make the virtual interactive object appear in the first live stream room when current time reaches the appearing time point,

wherein the first virtual streamer performs a live stream task set by the using party of the first live stream room, and the virtual interactive object performs an interactive task set by a manager of the live stream platform.

12. The virtual object interactive apparatus according to claim 11 , wherein the at least one processor executes the computer executable instructions to further execute the following operation:

generating interactive information based on the virtual interactive object, wherein the interactive information is related to the interactive task to be performed by the virtual interactive object.

13. The virtual object interactive apparatus according to claim 12 , wherein the at least one processor executes the computer executable instructions to further execute the following operations:

displaying an interactive prompt related to the virtual interactive object, wherein the interactive prompt is used to prompt a user to perform an interactive input; and

receiving the interactive input of the user to the virtual interactive object, and generating the interactive information according to the interactive input.

14. The virtual object interactive apparatus according to claim 13 , wherein the at least one processor executes the computer executable instructions to further execute the following operations:

determining an interactive behavior corresponding to the virtual interactive object according to the interactive input, and generating the interactive information based on the interactive behavior, wherein the interactive behavior includes an action and a posture of the virtual interactive object interacting with the user.

15. The virtual object interactive apparatus according to claim 12 , wherein the at least one processor executes the computer executable instructions to further execute the following operations:

obtaining key information of a live stream target included in a live stream content according to the live stream content of the first virtual streamer, and generating the interactive information based on the key information.

16. The virtual object interactive apparatus according to claim 15 , wherein the at least one processor executes the computer executable instructions to further execute the following operations:

obtaining text information of the live stream content of the first virtual streamer; and

performing a semantic recognition on the text information, determining the live stream target included in the live stream content according to a result of the semantic recognition, and obtaining the key information of the live stream target.

17. The virtual object interactive apparatus according to claim 11 , wherein the at least one processor executes the computer executable instructions to further execute the following operations:

providing guidance information corresponding to a second live stream room when the virtual interactive object appears in the first live stream room of the live stream platform, wherein the guidance information is used for guiding a user to follow the virtual interactive object into the second live stream room, and the second live stream room performs a live stream using a second virtual streamer; and

displaying the guidance information on the live interface of the first live stream room.

18. The virtual object interactive apparatus according to claim 17 , wherein the at least one processor executes the computer executable instructions to further execute the following operation:

making the virtual interactive object appear in the second live stream room;

wherein a way in which the virtual interactive object appears in the second live stream room is the same or different from a way in which the virtual interactive object appears in the first live stream room, and time at which the virtual interactive object appears in the second live stream room is the same or different from time at which the virtual interactive object appears in the first live stream room.

19. A non-transitory storage medium, on which a computer program is stored, which, when executed by a processor, causes the processor to execute the following operations:

performing a live stream by using a first virtual streamer in a first live stream room of a live stream platform;

making a virtual interactive object appear in the first live stream room for a preset time period during the live stream of the first live stream room, the preset time period being shorter than a time period of the live stream of the first live stream room;

obtaining an appearing time point when the virtual interactive object appears in the first live stream room, the appearing time point being randomly set; and

making the virtual interactive object appear in the first live stream room when current time reaches the appearing time point,

wherein the first virtual streamer performs a live stream task set by a using party of the first live stream room, and the virtual interactive object performs an interactive task set by a manager of the live stream platform.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 22, 2026
From: HANGZHOU ALICLOUD FEITIAN INFORMATION TECHNOLOGY CO., LTD.
To: CLOUD INTELLIGENCE ASSETS HOLDING (SINGAPORE) PRIVATE LIMITED
Reel/Frame 075437/0941 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 22, 2024
From: TAN, QIMIN
To: HANGZHOU ALICLOUD FEITIAN INFORMATION TECHNOLOGY CO., LTD.
Reel/Frame 066534/0942 →
Priority Claims (1)
CN 202111245048.5 · Oct 26, 2021 · national
Continuity (1)
Related Publication 20250142137A1 · May 1, 2025
References Cited (53)
US 5682469A · Linnett · 1997 [cited by examiner]
US 5727174A · Aparicio, IV · 1998 [cited by examiner]
US 6021403A · Horvitz · 2000 [cited by examiner]
US 6369821B2 · Merrill · 2002 [cited by examiner]
US 6657643B1 · Horvitz · 2003 [cited by examiner]
US 6931656B1 · Eshelman · 2005 [cited by examiner]
US 10521188B1 · Christie · 2019 [cited by examiner]
US 12088887B2 · Yang · 2024 [cited by examiner]
US 20020187833A1 · Nishiyama · 2002 [cited by examiner]
US 20040199057A1 · Hasegawa · 2004 [cited by examiner]
US 20080081694A1 · Hong · 2008 [cited by examiner]
US 20090019541A1 · Fontijn · 2009 [cited by examiner]
US 20090204909A1 · Hornbaker · 2009 [cited by examiner]
US 20150161521A1 · Shah · 2015 [cited by examiner]
US 20150382047A1 · Van Os · 2015 [cited by examiner]
US 20170084189A1 · Rubalcaba · 2017 [cited by examiner]
US 20170374426A1 · Wang · 2017 [cited by examiner]
US 20180098030A1 · Morabia · 2018 [cited by examiner]
US 20180183844A1 · Danker · 2018 [cited by examiner]
US 20180373547A1 · Dawes · 2018 [cited by examiner]
US 20190318318A1 · Sergott · 2019 [cited by examiner]
US 20190373303A1 · Ashraf · 2019 [cited by examiner]
US 20210029339A1 · Liu et al. · 2021 [cited by applicant]
US 20210099761A1 · Zhang · 2021 [cited by examiner]
US 20210104100A1 · Whitney · 2021 [cited by examiner]
US 20220239988A1 · Yang · 2022 [cited by examiner]
CN 1770746A · 2006 [cited by examiner]
CN 104469444A · 2015 [cited by examiner]
CN 106028166A · 2016 [cited by applicant]
CN 106993195A · 2017 [cited by examiner]
CN 107277599A · 2017 [cited by examiner]
CN 107423809A · 2017 [cited by applicant]
CN 109120985A · 2019 [cited by examiner]
CN 109688477A · 2019 [cited by applicant]
CN 110850983A · 2020 [cited by applicant]
CN 111083570A · 2020 [cited by examiner]
CN 111343473A · 2020 [cited by applicant]
CN 111652678A · 2020 [cited by applicant]
CN 112188297A · 2021 [cited by applicant]
CN 112291576A · 2021 [cited by applicant]
CN 112929678A · 2021 [cited by applicant]
CN 113329234A · 2021 [cited by applicant]
CN 113382270A · 2021 [cited by applicant]
CN 113691829A · 2021 [cited by applicant]
CN 115314729A · 2022 [cited by examiner]
FR 3023020A1 · 2016 [cited by examiner]
TW 202123128A · 2021 [cited by applicant]
Tyler Fisbee, “Clippy”, https://www.youtube.com/watch?v=3G_uCbKoG5A, retrieved on Oct. 15, 2024. [cited by applicant]
International Search Report and Written Opinion, as issued in connection with European Patent Application No. 22885794.2, dated Oct. 28, 2024. [cited by applicant]
Office Action mailed Nov. 30, 2021, in Chinese Application No. 202111245048.5. [cited by applicant]
Office Action mailed Dec. 22, 2021, in Chinese Application No. 202111245048.5. [cited by applicant]
International Search Report mailed Dec. 6, 2022, in PCT Application No. PCT/CN2022/126523. [cited by applicant]
Notification to Grant Patent Right for Invention mailed Jan. 13, 2022, in Chinese Application No. 202111245048.5. [cited by applicant]