CN-122002098-A - Live content generation method and device, electronic equipment and storage medium

CN122002098ACN 122002098 ACN122002098 ACN 122002098ACN-122002098-A

Abstract

The method comprises the steps of responding to identification processing operation for preset audio information, displaying a plurality of text information in a text display area of a content generation page, responding to visual lens adding operation for each text information, displaying a visual lens corresponding to the plurality of text information in a lens display area of the content generation page, wherein the visual lens comprises a visual lens segment corresponding to each text information, the visual lens adding operation comprises adding operation of an image of a virtual anchor and a live broadcasting scene element, and responding to a live broadcasting content generation instruction corresponding to the visual lens and the preset audio information, and displaying target live broadcasting content. According to the embodiment of the application, live broadcast pictures of the flow field can be generated through virtual anchor, scene setting and the like, live broadcast content is generated by combining audio information, the interaction sense and immersion sense of live broadcast of a real person are restored, and the investment of manpower cost is reduced while live broadcast resources are effectively utilized.

Inventors

WU CHAO
JIA WEI
XU WENJING
Yue Qizhen
ZHENG LONGLONG
KONG YINPING
YU YUE
HUANG YUJIA

Assignees

北京达佳互联信息技术有限公司

Dates

Publication Date: 20260508
Application Date: 20251224

Claims (15)

1. A live content generation method, comprising: Responding to an identification processing operation aiming at preset audio information, and displaying a plurality of text information in a text display area of a content generation page, wherein each text information in the plurality of text information corresponds to one recommended object; The method comprises the steps of responding to a visual lens adding operation aiming at each text message, displaying visual lenses corresponding to a plurality of text messages in a lens display area of a content generation page, wherein the visual lenses comprise visual lens fragments corresponding to each text message, the visual lens adding operation comprises an adding operation of a virtual anchor image and a live broadcasting set element, and the added live broadcasting set elements are different in the visual lens fragments corresponding to different text messages; And responding to a live broadcast content generation instruction corresponding to the visual lens and the preset audio information, and displaying target live broadcast content, wherein the mouth shape of the virtual host in the target live broadcast content is consistent with the preset audio information.
2. The live content generation method according to claim 1, wherein the displaying a plurality of text information in a text display area of the content generation page in response to the recognition processing operation for the preset audio information, comprises: Displaying the preset audio information on the content generation page; displaying a plurality of text information to be processed in the text display area in response to the recognition segmentation processing for the preset audio information; Displaying the processed text information in the text display area in response to a text processing instruction triggered based on the text processing control, wherein the text processing comprises repeated sentence processing, content deletion processing and content confusion processing; And displaying the modified target audio information in response to an audio modification operation of the preset audio information based on the processed plurality of text information.
3. The live content generation method according to claim 1, wherein the responding to the visual shot adding operation for each text information further comprises, before displaying the visual shots corresponding to the plurality of text information in the shot display area of the content generation page: Displaying a plurality of shot selection controls and shot selection adding controls on the content generation page; The plurality of shot selection controls are in one-to-one correspondence with the plurality of text information; the lens selection adding control is used for adding the lens selection control.
4. The live content generation method according to claim 3, wherein the displaying the visual shots corresponding to the plurality of text information in the shot display area of the content generation page in response to the visual shot adding operation for each text information, comprises: for any one of the plurality of text information, performing: The method comprises the steps of responding to a shot selection instruction triggered based on a target shot selection control, and displaying an element display area on a content generation page, wherein the target shot selection control is a shot selection control corresponding to text information currently being processed, and the element display area comprises a virtual anchor control and a live broadcasting scene control; determining a target virtual anchor in response to a virtual anchor selection instruction triggered based on the virtual anchor control; determining a target scenery element in response to a live-broadcast room scenery instruction triggered based on the live-broadcast room scenery control, wherein the target scenery element comprises a background element and a foreground element; And displaying a visual shot segment corresponding to the text information currently being processed, wherein the visual shot segment corresponding to each text information degree forms a visual shot corresponding to the plurality of text information.
5. The method of claim 4, wherein the element display area includes a material display area and a preview area, wherein the determining a target virtual anchor in response to a virtual anchor selection instruction triggered based on the virtual anchor control includes: Responding to an image material display instruction triggered based on the virtual anchor control, and displaying a plurality of virtual anchors in the material display area; responding to a selection instruction for a target virtual anchor in the plurality of virtual anchors, and displaying the image of the target virtual anchor in the preview area; And responding to the image changing instruction aiming at the target virtual anchor, and displaying the image of the modified target virtual anchor in the preview area.
6. The method of claim 5, wherein the live-room scenery control comprises a background scenery control and a front Jing Bujing control, wherein the determining the target scenery element in response to the live-room scenery instruction triggered based on the live-room scenery control comprises: Responding to a background element display instruction triggered based on the background scene control, and displaying a plurality of background elements in the material display area, wherein the plurality of background elements comprise background pictures or background videos; In response to a selection instruction for a target background element of the plurality of background elements, displaying the target background element in the preview area at a lower layer of the avatar of the target virtual anchor; Responding to a foreground element display instruction triggered based on the front Jing Bujing control, and displaying a plurality of foreground elements in the material display area, wherein the foreground elements comprise a sticker element and a control element; in response to a selection instruction for a target foreground element of the plurality of foreground elements, the target foreground element is displayed in the preview area at an upper layer of the avatar of the target virtual anchor.
7. The method of generating live content of any of claims 5 or 6, wherein the element display area further comprises a track control, the method further comprising: Responding to a track display instruction triggered based on the track control, and displaying a plurality of track materials in the material display area, wherein the plurality of track materials comprise a single track and a plurality of tracks, and the plurality of tracks comprise a main track and a sub track; displaying a plurality of overlay resources in response to a selection instruction for the multi-track; and responding to a selection instruction for a target overlay resource in the plurality of overlay resources, and displaying the overlay resources in the preview area.
8. The method for generating live content according to claim 7, wherein displaying, in the shot display area, a visual shot segment corresponding to the text information currently being processed, the visual shot segment being composed of the avatar of the target virtual anchor and the target scenery element, comprises: and displaying a visual shot segment corresponding to the text information currently being processed, wherein the visual shot segment consists of the image of the target virtual anchor, the target scenery element and the superposition resource in the shot display area.
9. The method for generating live content according to any one of claims 1 to 6, wherein the shot display area includes a pair of visual text Ji Kongjian, and wherein after displaying the visual shots corresponding to the plurality of text messages in the shot display area of the content generation page, the method further includes: Under the condition that target text information and visual lens segments corresponding to the target text information in the plurality of text information are selected, responding to a visual text alignment instruction triggered based on the visual text alignment control, and adjusting the duration of the visual lens segments corresponding to the target text information, wherein the adjusted duration of the visual lens segments is consistent with the audio duration corresponding to the target text information.
10. The method for generating live content according to any one of claims 4 to 6 and 8, wherein after displaying the visual shot segment corresponding to the text information currently being processed in the shot display area, the method further comprises: the interactive configuration display area comprises interactive information of the text information which is currently being processed, wherein the interactive information comprises audience question information, anchor reply information and text reply information; responding to the configuration instruction of the interaction information, and starting the interaction mode of the visual lens segment corresponding to the text information which is currently being processed; The interaction mode is used for adding an interaction segment into a live broadcast segment corresponding to the visual lens segment in the target live broadcast content when comment information matched with the audience question information exists in a live broadcast interaction area in the live broadcast process, the interaction segment comprises an audio segment and a video segment corresponding to the anchor reply information, and the time of the audio segment is consistent with that of the video segment.
11. The method of claim 10, wherein the audio clip is a clip of a virtual anchor corresponding to the visual shot clip dictating the anchor reply message; The video clips are clips for performing picture switching for object display based on user demand information in comment information, and the picture switching comprises wearing switching of the virtual anchor, gesture angle switching of the virtual anchor and shot distance switching of the virtual anchor.
12. A live content generation apparatus, comprising: A first display module configured to perform an identification processing operation in response to preset audio information, display a plurality of text information in a text display area of a content generation page, each text information of the plurality of text information corresponding to a recommended object; The system comprises a first display module, a second display module and a content generation page, wherein the first display module is used for performing a visual shot adding operation for each text message, and displaying visual shots corresponding to a plurality of text messages in a shot display area of the content generation page; And the third display module is configured to execute a live broadcast content generation instruction corresponding to the visual lens and the preset audio information and display target live broadcast content, wherein the mouth shape of the virtual host in the target live broadcast content is consistent with the preset audio information.
13. An electronic device, comprising: A processor; a memory for storing the processor-executable instructions; Wherein the processor is configured to execute the instructions to implement the live content generation method of any of claims 1 to 11.
14. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the live content generation method of any one of claims 1 to 11.
15. A computer program product, characterized in that the computer program product comprises a computer program stored in a readable storage medium, from which at least one processor of a computer device reads and executes the computer program, causing the device to perform the live content generation method according to any of claims 1 to 11.

Description

Live content generation method and device, electronic equipment and storage medium Technical Field The disclosure relates to the technical field of internet, and in particular relates to a live content generation method, a live content generation device, electronic equipment and a storage medium. Background With the rapid development of the current mobile internet, selling products by live broadcasting is already a popular selling way for most brands, however, live selling goods requires either the brands to cultivate their own anchor or to spend a great price to ask for the mature anchor. In either case, the sales cost is too high for the merchant and the human resources are too high. Disclosure of Invention The disclosure provides a live content generation method, a device, an electronic device and a storage medium, and the technical scheme of the disclosure is as follows: According to a first aspect of an embodiment of the present disclosure, there is provided a live content generation method, including: Responding to the identification processing operation aiming at the preset audio information, and displaying a plurality of text information in a text display area of a content generation page; Responding to a visual lens adding operation aiming at each text message, and displaying visual lenses corresponding to a plurality of text messages in a lens display area of a content generation page, wherein the visual lenses comprise visual lens fragments corresponding to each text message; And responding to a live broadcast content generation instruction corresponding to the visual lens and the preset audio information, and displaying target live broadcast content, wherein the mouth shape of the virtual host in the target live broadcast content is consistent with the preset audio information. Optionally, in response to the recognition processing operation for the preset audio information, displaying a plurality of text information in a text display area of the content generation page includes: Displaying preset audio information on a content generation page; In response to the recognition segmentation processing for the preset audio information, displaying a plurality of text information to be processed in a text display area; Displaying the processed plurality of text information in a text display area in response to a text processing instruction triggered based on a text processing control; And displaying the modified target audio information in response to an audio modification operation of the preset audio information based on the processed plurality of text information. Optionally, in response to the visual shot adding operation for each text information, before displaying the visual shots corresponding to the plurality of text information in the shot display area of the content generation page, the method further includes: Displaying a plurality of shot selection controls and shot selection adding controls on a content generation page; The plurality of shot selection controls are in one-to-one correspondence with the plurality of text information, and the shot selection adding control is used for adding the shot selection controls. Optionally, in response to a visual shot adding operation for each text information, displaying visual shots corresponding to a plurality of text information in a shot display area of the content generation page, including: For any one of the plurality of text information, performing: the method comprises the steps of responding to a shot selection instruction triggered based on a target shot selection control, and displaying an element display area on a content generation page, wherein the target shot selection control is a shot selection control corresponding to text information currently being processed; Determining a target virtual anchor in response to a virtual anchor selection instruction triggered based on a virtual anchor control; Determining a target scenery element in response to a live-broadcast-room scenery instruction triggered based on the live-broadcast-room scenery control, wherein the target scenery element comprises a background element and a foreground element; and displaying visual shot segments corresponding to the text information currently being processed, wherein the visual shot segments corresponding to each text information degree form visual shots corresponding to a plurality of text information. Optionally, the element display area comprises a material display area and a preview area, and the determining the target virtual anchor in response to the virtual anchor selection instruction triggered based on the virtual anchor control comprises the following steps: Responding to an image material display instruction triggered based on a virtual anchor control, and displaying a plurality of virtual anchors in a material display area; responding to a selection instruction aiming at a target virtual anchor in a plurality of virtual anchors, and displaying