Granted Patent B2

US 12,732,592 · App. 18/579,842 · Granted Sep 8, 2026

Inventors: Yali Wang (Huizhou, CN); Wanfu Zhou (Huizhou, CN)

Assignee: HUIZHOU TCL CLOUD INTERNET CORPORATION TECHNOLOGY CO. LTD

H04N7/157G06T13/80G06T15/00G06V40/172G06V40/20

Abstract

Claims (66)

1 . A virtual image video call method, comprising:

detecting one or more network quality indicators in a process for a video call;

determining whether the one or more network quality indicators for the video call meet one or more predetermined conditions;

controlling a pre-generated virtual image of a call user to be obtained when it is detected that the one or more network quality indicators for the video call meet the one or more predetermined conditions; and

switching an interface for the video call to the virtual image mapped with behavior of the user for display;

wherein the one or more network quality indicators comprise at least one of a network speed, a packet loss rate, and a delay, and detecting the one or more network quality indicators in real time or at a fixed interval;

when at least one of the following conditions is detected: the network speed is lower than a first threshold, the packet loss rate is higher than a second threshold, or the delay is higher than a third threshold, controlling the pre-generated virtual image to be invoked, and after switching to the virtual image, detecting the one or more network quality indicators again in a virtual image call process, and when the indicators are restored to normal values continuously for a preset time period, switching the virtual image back to the interface for the video call;

wherein after detecting that the network quality meets a predetermined switching condition, the invoked virtual image comprises a preset virtual image corresponding to appearance features of the user; and when no corresponding preset virtual image is detected, generating and storing a new virtual image based on appearance information of the user captured by a camera of the terminal for subsequent video calls;

wherein, after switching to the virtual image, user behavior is captured through a camera and/or a sound sensor, and at least one of mouth shape, facial expression, head movement, or limb movement is mapped to the virtual image.

2 . The method of claim 1 , further comprising: before detecting of the one or more network quality indicators,

presetting one or more predetermined conditions for the one or more network quality indicators, and controlling an interface for the video call to be switched to the virtual image for display when it is detected in the process for the video call that a network state for the video call meets the predetermined conditions; and

presetting the virtual image used for the video call when the one or more network quality indicators meet the one or more predetermined conditions.

3 . The method of claim 2 , wherein the determining of whether the one or more network quality indicators for the video call meet the one or more predetermined conditions comprises:

the one or more network quality indicators comprising a network speed, a packet loss rate, and a delay,

detecting at least one of: whether the network speed is lower than a first value, whether the packet loss rate is higher than a second value, or whether the delay is higher than a third value.

4 . The method of claim 3 , wherein the controlling the pre-generated virtual image of the call user to be obtained comprises:

controlling the pre-generated virtual image of the call user to be invoked when at least one of following items is detected: the network speed is lower than the first value, the packet loss rate is higher than the second value, or the delay is higher than the third value.

5 . The method of claim 1 , wherein the switching of the interface for the video call to the virtual image comprises:

switching an interface for the video call to a virtual image for display;

capturing behavior of the user through at least one of a camera or a sound sensor of a mobile terminal; and

mapping the behavior of the user into the virtual image for display.

6 . The method of claim 1 , wherein the detecting of the one or more network quality indicators comprises:

detecting the one or more network quality indicators in the process for the video call in real time or at a fixed interval.

7 . The method of claim 1 , wherein the one or more predetermined conditions are set by the user based on a usage habit and a usage feeling.

8 . The method of claim 1 , further comprising: before the controlling of the pre-generated virtual image of the call user to be obtained,

recognizing a face of each of one or more call users currently performing the video call is recognized to check whether the call user has respective one of preset virtual images; in response to the call user having the preset virtual image, invoking the preset virtual image directly; and in response to the call user not having the preset virtual image, allocating a template virtual image to the call user for the video call.

9 . The method of claim 8 , further comprising:

in response to the call user not having the preset virtual image, generating and storing a virtual image including one or more appearance features of the call user by an algorithm based on to appearance information of the call user captured by a camera of a terminal, to enable the call user to invoke the preset virtual image of the call user when the call user makes the video call again later.

10 . The method of claim 1 , further comprising: after the switching of the interface for the video call to the virtual image,

detecting one or more network quality indicators in a process for a virtual image call, and switching the virtual image to the interface for the video call when the one or more network quality indicators are restored to normal values continuously for a preset time period.

11 . A virtual image video call switching method, comprising:

detecting whether an instruction for making a video call using a virtual image is received when it is monitored that a video call request is received or transmitted;

invoking or generating the virtual image when it is detected that the instruction for making the video call using the virtual image is received, and mapping behavior of the user into the virtual image; and

displaying the virtual image mapped with the behavior of the user in a picture of the video call when it is detected that the video call is successfully established;

wherein the one or more network quality indicators comprise at least one of a network speed, a packet loss rate, and a delay, and detecting the one or more network quality indicators in real time or at a fixed interval;

when at least one of the following conditions is detected: the network speed is lower than a first threshold, the packet loss rate is higher than a second threshold, or the delay is higher than a third threshold, controlling the pre-generated virtual image to be invoked, and after switching to the virtual image, detecting the one or more network quality indicators again in a virtual image call process, and when the indicators are restored to normal values continuously for a preset time period, switching the virtual image back to the interface for the video call;

wherein after detecting that the network quality meets a predetermined switching condition, the invoked virtual image comprises a preset virtual image corresponding to appearance features of the user; and when no corresponding preset virtual image is detected, generating and storing a new virtual image based on appearance information of the user captured by a camera of the terminal for subsequent video calls;

wherein, after switching to the virtual image, user behavior is captured through a camera and/or a sound sensor, and at least one of mouth shape, facial expression, head movement, or limb movement is mapped to the virtual image.

12 . The method of claim 11 , further comprising: before monitoring receiving or transmitting of the video call request,

presetting a virtual image for the video call or presetting an algorithm for automatically generating the virtual image based on one or more appearance features of the user.

13 . The method of claim 11 , wherein the displaying of the virtual image mapped with the behavior of the user comprises:

controlling a sound sensor to capture a sound of the user after it is detected that the video call is successfully established, and recognizing a mouth shape corresponding to the sound and an emotion of the user when speaking by a speech recognition algorithm; and

controlling the recognized mouth shape and emotion to be mapped into a face action of the virtual image for display.

14 . A terminal device, comprising: a memory, a processor, and a virtual image video call program stored on the memory and operable on the processor, wherein the virtual image video call program, when executed by the processor, implements operations comprising:

detecting one or more network quality indicators in a process for a video call;

determining whether the one or more network quality indicators for the video call meet one or more predetermined conditions;

controlling a pre-generated virtual image of a call user to be obtained when it is detected that the one or more network quality indicators for the video call meet the one or more predetermined conditions; and

switching an interface for the video call to the virtual image mapped with behavior of the user for display;

wherein the one or more network quality indicators comprise at least one of a network speed, a packet loss rate, and a delay, and detecting the one or more network quality indicators in real time or at a fixed interval;

when at least one of the following conditions is detected: the network speed is lower than a first threshold, the packet loss rate is higher than a second threshold, or the delay is higher than a third threshold, controlling the pre-generated virtual image to be invoked, and after switching to the virtual image, detecting the one or more network quality indicators again in a virtual image call process, and when the indicators are restored to normal values continuously for a preset time period, switching the virtual image back to the interface for the video call;

wherein after detecting that the network quality meets a predetermined switching condition, the invoked virtual image comprises a preset virtual image corresponding to appearance features of the user; and when no corresponding preset virtual image is detected, generating and storing a new virtual image based on appearance information of the user captured by a camera of the terminal for subsequent video calls;

wherein, after switching to the virtual image, user behavior is captured through a camera and/or a sound sensor, and at least one of mouth shape, facial expression, head movement, or limb movement is mapped to the virtual image.

15 . The terminal device of claim 14 , wherein the processor is further configured to perform the operations comprising:

presetting one or more predetermined conditions for the one or more network quality indicators, and controlling an interface for the video call to be switched to the virtual image for display when it is detected in the process for the video call that a network state for the video call meets the predetermined conditions; and

presetting the virtual image used for the video call when the one or more network quality indicators meet the one or more predetermined conditions.

16 . The terminal device of claim 15 , wherein the processor is further configured to perform the operations comprising:

the one or more network quality indicators comprising a network speed, a packet loss rate, and a delay,

detecting at least one of: whether the network speed is lower than a first value, whether the packet loss rate is higher than a second value, or whether the delay is higher than a third value.

17 . The terminal device of claim 16 , wherein the processor is further configured to perform the operations comprising:

controlling the pre-generated virtual image of the call user to be invoked when at least one of following items is detected: the network speed is lower than the first value, the packet loss rate is higher than the second value, or the delay is higher than the third value.

18 . The terminal device of claim 14 , wherein the processor is further configured to perform the operations comprising:

switching an interface for the video call to a virtual image for display;

capturing behavior of a user through at least one of a camera or a sound sensor of a mobile terminal; and

mapping the behavior of the user into the virtual image for display.

19 . The terminal device of claim 14 , wherein the processor is further configured to perform the operations comprising:

detecting the one or more network quality indicators in the process for the video call in real time or at a fixed interval.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (23)