CN113766296A - Live broadcast picture display method and device - Google Patents

Live broadcast picture display method and device Download PDF

Info

Publication number
CN113766296A
CN113766296A CN202110507350.7A CN202110507350A CN113766296A CN 113766296 A CN113766296 A CN 113766296A CN 202110507350 A CN202110507350 A CN 202110507350A CN 113766296 A CN113766296 A CN 113766296A
Authority
CN
China
Prior art keywords
live broadcast
target
picture
scene
page
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110507350.7A
Other languages
Chinese (zh)
Other versions
CN113766296B (en
Inventor
陈春勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202110507350.7A priority Critical patent/CN113766296B/en
Publication of CN113766296A publication Critical patent/CN113766296A/en
Application granted granted Critical
Publication of CN113766296B publication Critical patent/CN113766296B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/488—Data services, e.g. news ticker
    • H04N21/4884—Data services, e.g. news ticker for displaying subtitles

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The application discloses a display method and a display device for live pictures, and relates to the field of artificial intelligence; the method includes the steps that an initial live broadcast page is displayed, and the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room; when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.

Description

Live broadcast picture display method and device
Technical Field
The application relates to the technical field of computers, in particular to a live broadcast picture display method and device.
Background
With the development of computer technology and network technology, the live broadcast method of real-time sharing data by using internet and streaming media technology gradually becomes the next popular interactive communication method. Live webcasting is used as a network interaction mode, attracts more users in a novel form, and is increasingly widely applied to shopping, entertainment, learning and the like. In practical application, the anchor user can create a live broadcast room through the anchor client, and perform online live broadcast through the live broadcast room, and the audience user can enter the live broadcast room through the audience client to watch the live broadcast content of the anchor user.
For live broadcasting, a material diagram of atmosphere propaganda is generally required to be prepared in advance so as to be used in the live broadcasting process, for example, related pictures of products can be prepared in live broadcasting of product propaganda, and the related pictures of the products are used for rendering according to live broadcasting contents in live broadcasting so as to enhance the atmosphere effect of the product propaganda. However, this method is inefficient, not convenient enough, and cannot perform real-time scene atmosphere rendering according to live content.
Disclosure of Invention
The embodiment of the application provides a live broadcast picture display method and device, live broadcast content can be subjected to real-time scene atmosphere rendering based on scene recognition, and the efficiency and convenience of live broadcast scene atmosphere rendering can be improved.
The embodiment of the application provides a display method of a live broadcast picture, which comprises the following steps:
displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene.
The embodiment of the application provides another live broadcast picture display method, which comprises the following steps:
receiving a page detection request aiming at an initial live broadcast page sent by a terminal, and carrying out content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
Correspondingly, the embodiment of the present application provides a display device for live broadcast pictures, including:
the first display unit is used for displaying an initial live broadcast page, and the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
and the second display unit is used for switching and displaying a target live broadcast page under a target picture scene when detecting that the content change of the current live broadcast picture meets a preset condition, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed and a target material, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene.
Correspondingly, an embodiment of the present application provides another display apparatus for a live view, including:
the system comprises a receiving unit, a content detecting unit and a processing unit, wherein the receiving unit is used for receiving a page detection request aiming at an initial live broadcast page sent by a terminal and detecting the content of the initial live broadcast page according to the page detection request, and the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
the identification unit is used for carrying out scene identification on the current live broadcast picture when detecting that the content change of the current live broadcast picture meets a preset condition so as to obtain a target picture scene corresponding to the current live broadcast picture;
the fusion unit is used for fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and the sending unit is used for sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
Optionally, in some embodiments of the present application, the second presentation unit may include a first presentation subunit, a determination subunit, a picture fusion subunit, and a second presentation subunit, as follows:
the first display subunit is configured to display a switching preview page, where the switching preview page includes a scene switching control and a preview live view, the preview live view is a preview view obtained by fusing the current live view and an initial material, and the initial material is a material associated with the target view scene;
the determining subunit is configured to determine, in response to a scene switching operation on the scene switching control, an initial material corresponding to a preview live view currently displayed on the switching preview page as the target material;
the picture fusion subunit is configured to fuse a next frame of live broadcast picture to be displayed based on the target material to obtain the target live broadcast picture;
and the second display subunit is used for switching and displaying the target live broadcast page in the target picture scene.
Optionally, in some embodiments of the present application, the switching preview page further includes a material replacement control; the second presentation unit may further comprise an acquisition subunit and a third presentation subunit, as follows:
the obtaining subunit is configured to, in response to an operation on the material replacement control, obtain a new material associated with the target picture scene as an updated target material;
and the third display subunit is configured to display the updated preview live broadcast picture in the switching preview page, where the updated preview live broadcast picture is a preview picture in which the updated target material and the current live broadcast picture are merged.
Optionally, in some embodiments of the present application, the second presentation unit may include a fourth presentation subunit, an identification subunit, a fifth presentation subunit, and a return subunit, as follows:
the fourth display subunit is used for switching and displaying a target live broadcast page in a target picture scene;
the identification subunit is used for carrying out scene identification on the target live broadcast picture when detecting that the content change of the target live broadcast picture meets a preset condition, and taking a scene corresponding to the target live broadcast picture as a new target picture scene;
a fifth display subunit, configured to switch to display a new target live broadcast page in the new target picture scene, where the new target live broadcast page includes a new target live broadcast picture, the new target live broadcast picture is a picture obtained by fusing a next live broadcast picture to be displayed with a new target material, and the new target material is a material associated with the new target picture scene;
and the return subunit is used for returning and executing the scene recognition and the subsequent steps of the target live broadcast picture when the content change of the target live broadcast picture is detected to meet the preset condition.
Optionally, in some embodiments of the present application, the apparatus for displaying a live view may further include a generating unit, where the generating unit may be configured to generate a target live view;
the generating unit may include a scene recognition subunit, a calculation subunit, a selection subunit, and a fusion subunit, as follows:
the scene identification subunit is configured to perform scene identification on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
the calculating subunit is used for calculating the association degree between the candidate material in the preset material library and the target picture scene;
the selecting subunit is used for selecting a target material from the candidate materials according to the relevance;
and the fusion subunit is used for fusing the target material and the next frame of live broadcast picture to be displayed so as to generate a target live broadcast picture.
Optionally, in some embodiments of the present application, the target material includes a target foreground atmosphere material and a target background atmosphere material; the fusion subunit is specifically configured to, when the display mode of the target live broadcast room is a first mode, fuse the target foreground atmosphere material with a next live broadcast picture to be displayed to generate a target live broadcast picture; and when the display mode of the target live broadcast room is a second mode, fusing the target foreground atmosphere material, the target background atmosphere material and the next live broadcast picture to be displayed to generate a target live broadcast picture.
Optionally, in some embodiments of the present application, the first presentation unit may include a preview acquisition subunit, an initial fusion subunit, and an initial presentation subunit, as follows:
the forecast acquisition subunit is used for acquiring live broadcast forecast information and selecting an initial target material from candidate materials based on the association degree between the live broadcast forecast information and the candidate materials in a preset material library;
the initial fusion subunit is used for fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture;
and the initial display subunit is used for displaying an initial live broadcast page, and the initial live broadcast page comprises the initial live broadcast picture.
The electronic device provided by the embodiment of the application comprises a processor and a memory, wherein a plurality of instructions are stored in the memory, and the instructions are loaded by the processor so as to execute the steps in the method for displaying the live broadcast picture provided by the embodiment of the application.
In addition, a storage medium is further provided, where a computer program is stored on the storage medium, where the computer program, when executed by a processor, implements the steps in the method for displaying a live view provided in the embodiments of the present application.
The embodiment of the application provides a method and a device for displaying a live broadcast picture, which can display an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room; when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1a is a scene schematic diagram of a method for displaying a live view provided in an embodiment of the present application;
fig. 1b is a flowchart of a method for displaying a live view provided in an embodiment of the present application;
fig. 1c is a schematic page diagram of a method for displaying a live view provided in an embodiment of the present application;
fig. 1d is a schematic view of another page of a display method of a live view provided in an embodiment of the present application;
fig. 1e is a schematic view of another page of a display method of a live view provided in an embodiment of the present application;
fig. 1f is a schematic view of another page of a display method of a live view provided in an embodiment of the present application;
fig. 2a is another flowchart of a method for displaying a live view provided in an embodiment of the present application;
fig. 2b is another flowchart of a method for displaying a live view provided in an embodiment of the present application;
fig. 3a is a schematic structural diagram of a display apparatus for a live view provided in an embodiment of the present application;
fig. 3b is another schematic structural diagram of a display apparatus for displaying a live view according to an embodiment of the present application;
fig. 3c is another schematic structural diagram of a display apparatus for displaying a live view according to an embodiment of the present application;
fig. 3d is another schematic structural diagram of a display apparatus for displaying a live view according to an embodiment of the present application;
fig. 3e is another schematic structural diagram of a display apparatus for displaying a live view according to an embodiment of the present application;
fig. 3f is another schematic structural diagram of a display apparatus for displaying a live view according to an embodiment of the present application;
fig. 3g is another schematic structural diagram of a display apparatus for a live view provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a method and a device for displaying a live broadcast picture. The display device of the live broadcast picture can be specifically integrated in an electronic device, and the electronic device can be a terminal or a server and other devices.
It can be understood that the method for displaying the live view in this embodiment may be executed on the terminal, may also be executed on the server, and may also be executed by both the terminal and the server. The above examples should not be construed as limiting the present application.
As shown in fig. 1a, a method for displaying a live view performed by a terminal and a server together is taken as an example. The display system of the live broadcast picture provided by the embodiment of the application comprises a terminal 10, a server 11 and the like; the terminal 10 and the server 11 are connected via a network, for example, a wired or wireless network connection, wherein the display device of the live view can be integrated in the terminal.
Wherein, the terminal 10 may be configured to: displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room; when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene. The terminal 10 may include a mobile phone, a smart television, a tablet Computer, a notebook Computer, a Personal Computer (PC), or the like. A client, which may be an application client or a browser client or the like, may also be provided on the terminal 10.
The server 11 may be configured to receive a page detection request for an initial live broadcast page sent by the terminal 10, and perform content detection on the initial live broadcast page according to the page detection request, where the initial live broadcast page includes a current live broadcast picture in a target live broadcast room; when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture; fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene; and sending the target live broadcast picture to the terminal 10 so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture. The server 11 may be a single server, or may be a server cluster or a cloud server composed of a plurality of servers. In the method or the apparatus for displaying a live view disclosed in the present application, a plurality of servers can be grouped into a blockchain, and the servers are nodes on the blockchain.
The step of generating the target live view by the server 11 may be executed by the terminal 10.
The embodiment of the application provides a live broadcast picture display method, which relates to a computer vision technology in the field of artificial intelligence. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
Computer Vision technology (CV) is a science for researching how to make a machine "see", and more specifically, it refers to that a camera and a Computer are used to replace human eyes to perform machine Vision such as identification, tracking and measurement on a target, and further perform graphic processing, so that the Computer processing becomes an image more suitable for human eyes to observe or transmitted to an instrument to detect. As a scientific discipline, computer vision research-related theories and techniques attempt to build artificial intelligence systems that can capture information from images or multidimensional data. Computer vision technologies generally include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technologies, virtual reality, augmented reality, synchronous positioning, map construction, and other technologies, and also include common biometric technologies such as face recognition and fingerprint recognition.
The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.
The embodiment will be described from the perspective of a display device of a live view, where the display device of the live view may be specifically integrated in an electronic device, and the electronic device may be a server or a terminal.
The method for displaying the live broadcast picture can be applied to various live broadcast scenes. For example, by the live broadcast picture display method provided by the embodiment, scenes in the live broadcast process of a certain product brand can be quickly identified, a target material matching the current live broadcast atmosphere is obtained, and a target live broadcast picture is generated based on the target material and the current live broadcast picture, so that the efficiency and convenience in rendering the live broadcast scene atmosphere are improved.
As shown in fig. 1b, a specific flow of the live view display method may be as follows:
101. and displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of the target live broadcast room.
The initial live broadcast page is an initial live broadcast page of a certain live broadcast client, and the live broadcast client can be specifically an audience client or a main broadcast client. The live client can be a browser client or an application client. The type of live broadcast is not limited in this embodiment. The target live broadcast room is a live broadcast room where the live broadcast client is located.
In some embodiments, the anchor can release live advance notice before live broadcast, under the scene of live advance notice, the server can acquire the live advance notice information corresponding to the live advance notice, and the live advance notice information is identified by linkage big data so as to extract the characteristic information corresponding to the live advance notice information, and according to the characteristic information, the materials matched with the live advance notice information are acquired, and the materials are used in live broadcast, thereby being beneficial to enhancing the propaganda strength of related products in a target live broadcast room.
The live preview information may include live time, live subject, anchor avatar, anchor nickname, anchor identification information (id), live summary, live goods, etc. The type of the live preview information may be various, and may include, for example, video, image, audio, and text, which is not limited in this embodiment.
The Big data (Big data) refers to a data set which cannot be captured, managed and processed by a conventional software tool within a certain time range, and is a massive, high-growth-rate and diversified information asset which can have stronger decision-making power, insight discovery power and flow optimization capability only by a new processing mode. With the advent of the cloud era, big data has attracted more and more attention, and the big data needs special technology to effectively process a large amount of data within a tolerance elapsed time. The method is suitable for the technology of big data, and comprises a large-scale parallel processing database, data mining, a distributed file system, a distributed database, a cloud computing platform, the Internet and an extensible storage system.
Optionally, in this embodiment, before the step "displaying the initial live page", the method may further include:
acquiring live broadcast forecast information, and selecting an initial target material from candidate materials based on the correlation degree between the live broadcast forecast information and the candidate materials in a preset material library;
the step of showing the initial live page may include:
fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture;
and displaying an initial live broadcast page, wherein the initial live broadcast page comprises the initial live broadcast picture.
The candidate materials may include various scene atmosphere images, brand approval image elements, and the like. According to the embodiment, the materials matched with the live broadcast can be selected from the candidate materials according to the live broadcast preview information.
The initial target materials can comprise initial foreground atmosphere materials and initial background atmosphere materials; the step of fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture may specifically include:
when the display mode of the target live broadcast room is a first mode, fusing the initial foreground atmosphere material and the current live broadcast picture to obtain an initial live broadcast picture;
and when the display mode of the target live broadcast room is a second mode, fusing the initial foreground atmosphere material, the initial background atmosphere material and the current live broadcast picture to obtain an initial live broadcast picture.
In some embodiments, the first mode may specifically be a vertical screen mode, and the display effect of the current live broadcast picture in the vertical screen mode is as follows: the length of the current live broadcast picture is less than the width; the second mode may be a horizontal screen mode, and the display effect of the current live broadcast picture in the horizontal screen mode is as follows: the length of the current live picture is greater than the width.
The initial foreground atmosphere material can comprise a brand praise image element, a top atmosphere image element and the like; the initial background ambience material may comprise a scene ambience image or the like.
In some embodiments, the initial target material may include initial foreground ambient material and initial background ambient material; the step of fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture may specifically include:
fusing the initial background atmosphere material and the current live broadcast picture to obtain a fused initial basic live broadcast picture;
and fusing the initial foreground atmosphere material and the fused initial basic live broadcast picture to obtain an initial live broadcast picture.
In some embodiments, the initial target material may include initial foreground ambient material and initial background ambient material; the step of fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture may specifically include:
performing element identification on the current live broadcast picture to determine foreground picture elements and background picture elements in the current live broadcast picture;
fusing the initial foreground atmosphere material and the foreground picture elements to obtain a fused initial foreground picture;
fusing the initial background atmosphere material and the background picture elements to obtain a fused initial background picture;
and acquiring an initial live broadcast picture according to the fused initial foreground picture and the fused initial background picture.
Specifically, the foreground picture elements may include operation area image elements and the like (the operation area may be specifically used for pop-up publishing, sharing, collecting and the like), the background picture elements may include live broadcast pictures and the like, the initial foreground atmosphere material may include a titling image element, a top atmosphere image element and the like, and the initial background atmosphere material may include a scene atmosphere image and the like. The embodiment can fuse the fused initial foreground picture and the fused initial background picture to obtain the initial live broadcast picture.
The step of selecting an initial target material from the candidate materials based on the association between the live preview information and the candidate materials in the preset material library may include:
extracting the characteristics of the live broadcast preview information to obtain characteristic information corresponding to the live broadcast preview information;
performing feature extraction on candidate materials in a preset material library to obtain feature information corresponding to the candidate materials;
determining the association degree between the live broadcast forecast information and the candidate material according to the live broadcast forecast information and the characteristic information corresponding to the candidate material;
and selecting initial target materials from the candidate materials according to the relevance.
The vector distance between the characteristic information of the live broadcast preview information and the characteristic information of the candidate material can be calculated; and determining the association degree between the live broadcast forecast information and the candidate material according to the vector distance. The smaller the vector distance, the greater the degree of association; conversely, the larger the vector distance, the smaller the degree of association. Optionally, the candidate material with the association degree greater than the preset association degree can be used as an initial target material; the candidate materials can also be ranked from large to small according to the degree of association to obtain ranked candidate materials, the top N candidate materials in the ranked candidate materials are used as initial target materials, and N is a positive integer.
Optionally, after the initial target material is acquired, whether the initial target material is used in the target live broadcast room or not may be determined based on a scene setting instruction of the anchor, that is, whether an initial live broadcast picture obtained by fusing the initial target material and a current live broadcast picture is displayed during live broadcast.
Specifically, as shown in page 1 in fig. 1c, the live preview information includes live time, live subject, main screen name, live introduction, live goods, live preview cover page, and the like. In some embodiments, the live preview information may be analyzed, for example, it may be analyzed that the live preview is related to a camera category by an anchor nickname "photograph xxx" and a live theme "teach how you play a cool shadow", and at this time, the server may filter the associated material from the big data based on the brand keyword (e.g., photograph) under the category, for example, brand-related praise image elements and background decoration elements (i.e., associated initial target materials) may be generated, for example, the photograph-related praise image elements are: cameras, love, etc.; the background decoration element may be a photographic-related background atmosphere image generated based on a live broadcast theme, at this time, a live broadcast brand customization element (including a praise image element and a background decoration element) generated by the server is transmitted back to the live broadcast client, and when the anchor starts live broadcast, the audience can see a customized live broadcast room scene, that is, an initial live broadcast picture obtained by fusing an initial target material and a current live broadcast picture, as shown in page 2 of fig. 1 c.
102. When the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene.
After the anchor broadcast is played, the live broadcast picture can be detected, whether the content change of the live broadcast picture meets a preset condition or not is determined, if the content change meets the preset condition, scene recognition can be performed on the current live broadcast picture, and a target picture scene corresponding to the current live broadcast picture is determined. The preset condition may be set according to an actual situation, which is not limited in this embodiment, for example, the preset condition may be set according to a requirement for scene atmosphere rendering. The time interval for detecting the live broadcast picture can be set according to actual conditions, for example, the time interval can be set to detect the live broadcast picture once in one minute.
The live view is obtained by converting information such as light or sound into electrical information (i.e., information that can be recognized by a device) by a sensor.
Optionally, in this embodiment, before the step "switching the target live broadcast page in the target picture scene to be displayed", the method may further include:
carrying out scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
calculating the association degree between the candidate materials in a preset material library and the target picture scene;
selecting target materials from the candidate materials according to the relevance;
and fusing the target material and the next frame of live broadcast picture to be displayed to generate a target live broadcast picture.
The scene recognition model may specifically be a Convolutional Neural Network (CNN), a Visual Geometry Group Network (VGGNet), a Residual Network (Residual Network), a Dense connection Convolutional Network (densneet), and the like, but it should be understood that the scene recognition model of the present embodiment is not limited to the above listed types.
The method comprises the steps of extracting material characteristic information of candidate materials and scene characteristic information of a target picture scene, and calculating a vector distance between the material characteristic information of the candidate materials and the scene characteristic information of the target picture scene; and determining the association degree between the candidate material and the target picture scene according to the vector distance. The smaller the vector distance, the greater the degree of association; conversely, the larger the vector distance, the smaller the degree of association. The vector distance may include a euclidean distance, a cosine distance, etc., which is not limited by the embodiment.
In some embodiments, candidate materials with the association degree greater than a preset association degree can be selected as target materials, and the preset association degree can be set according to actual conditions; the candidate materials can also be sorted from large to small according to the degree of association, the first N candidate materials in the sorted candidate materials are selected as target materials, and N is a positive integer.
Optionally, in this embodiment, the step of "performing scene recognition on the current live view to obtain a target view scene corresponding to the current live view" may include:
extracting the characteristics of the current live broadcast picture to obtain the characteristic information of the current live broadcast picture;
and based on the characteristic information, carrying out scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture.
Before feature extraction, the current live broadcast picture can be preprocessed, the preprocessing process can include operations of denoising, smoothing, transformation and the like in image processing, and important features of images in the current live broadcast picture can be enhanced through preprocessing.
Optionally, in this embodiment, the step of "performing feature extraction on the current live view to obtain feature information of the current live view" may include:
performing convolution processing on the current live broadcast picture to obtain convolution information of the current live broadcast picture;
and performing downsampling processing on the convolution information to obtain the characteristic information of the current live broadcast picture.
In particular, the scene recognition model may include a convolutional layer and a convergence layer. The convolutional layer may scatter the current live picture into one small pixel block (e.g., 3 × 3/5 × 5 pixel blocks) by a convolution kernel, each pixel block may be regarded as a tile, the tiles are arranged in a set, and the content of each tile in the set is represented by axes, which may include height, width, and color, thus obtaining a three-dimensional numerical representation of each tile. The convergence layer combines the spatial dimension of the image group with the sampling function, and outputs a joint array only containing relatively important parts in the image, wherein the joint array is the characteristic information of the current live broadcast picture.
In this embodiment, scene recognition may be performed on the current live broadcast picture based on the feature information by using a classifier, so as to obtain a target picture scene corresponding to the current live broadcast picture. The classifier may be a Support Vector Machine (SVM), a recurrent neural network, a full-connection Deep Neural Network (DNN), or the like, which is not limited in this embodiment. The classifier is designed to obtain a recognition rule through training, and a feature classification can be obtained through the recognition rule, so that related labels and categories are formed, and further, the scene category of the live broadcast picture is classified, decided and recognized.
The scene recognition process utilizes the principle of strong relevance and strong similarity of adjacent pixels in the same image; i.e. two adjacent pixels in an image, have more relevance than two separate pixels in the image. Therefore, the current live picture can be dispersed into pixel blocks, and the pixels in each pixel block have strong relevance and can be considered as containing the same or similar features.
Optionally, in this embodiment, when it is detected that the content change of the current live broadcast picture meets the preset condition, a reminding message may be generated, and the reminding message is sent to the anchor, where the reminding message is used to remind the anchor that the scene of the target live broadcast room changes, and the anchor may determine whether to perform a scene switching operation on the current live broadcast picture based on the reminding message.
Optionally, in this embodiment, the step "switching to show a target live broadcast page in a target picture scene" may include:
displaying a switching preview page, wherein the switching preview page comprises a scene switching control and a previewing live broadcast picture, the previewing live broadcast picture is a previewing picture formed by fusing the current live broadcast picture and initial materials, and the initial materials are materials related to the target picture scene;
responding to the scene switching operation of the scene switching control, and determining an initial material corresponding to a preview live broadcast picture currently displayed on the switching preview page as the target material;
fusing a next frame of live broadcast picture to be displayed based on the target material to obtain the target live broadcast picture;
and switching and displaying the target live broadcast page in the target picture scene.
The switching preview page may specifically be a switching preview page of the anchor client.
The initial material may be selected from candidate materials in a preset material library according to the degree of association between the candidate materials and the target picture scene. In some embodiments, after an initial material associated with a target picture scene is selected, an initial material corresponding to a preview live broadcast picture currently displayed on a switched preview page is determined as a target material only in response to a scene switching operation of a main broadcast on a scene switching control; in other embodiments, the initial material may be directly regarded as the target material.
The scene switching operation may specifically be a click operation, a sliding operation, and the like on the scene switching control, and may specifically be set according to an actual situation, which is not limited in this embodiment.
By previewing the live broadcast picture, the anchor can preview the effect of the target live broadcast page in the target picture scene in advance so as to determine whether to perform scene switching operation.
Optionally, in this embodiment, the switching preview page further includes a material replacement control; the display method of the live broadcast picture can further comprise the following steps:
responding to the operation of the material replacing control, and acquiring a new material associated with the target picture scene as an updated target material;
displaying an updated preview live broadcast picture in the switching preview page, wherein the updated preview live broadcast picture is a preview picture formed by fusing the updated target material and the current live broadcast picture.
The operation on the material replacement control may specifically be a click operation or a slide operation on the material replacement control, and the like, which is not limited in this embodiment.
In some embodiments, before the step "displaying the switching preview page", a target material may be selected from candidate materials based on a degree of association between the candidate materials and the target screen scene; and fusing the target material and the next frame of live broadcast picture to be displayed to generate a target live broadcast picture.
In some embodiments, a target material is selected from the candidate materials based on the degree of association between the candidate materials and the target picture scene, and specifically, the candidate materials may be sorted from large to small based on the degree of association between the candidate materials and the target picture scene to obtain sorted candidate materials; and selecting the first sorted material from the sorted candidate materials as a target material. When the operation of the material replacement control is detected, a new material can be selected as an updated target material based on the sequence of the sorted candidate materials, for example, a second sorted material in the sorted candidate materials can be used as the updated target material; when the operation on the material replacing control is detected again, the material arranged at the third position in the sorted candidate materials can be selected as the updated target material, and so on.
In other embodiments, the association degree between the candidate material and the target picture scene may also be calculated, and the candidate material whose association degree is greater than the preset association degree is added to the target material set, where the target material set includes at least one target material. When the operation of the material replacing control is detected, new target materials can be selected from the target materials in a centralized manner to serve as updated target materials.
In a specific scenario, as shown in fig. 1d, a page a is a live broadcast room screen when the live broadcast is directly played in the anchor landscape mode, and a system default live broadcast room is shown, in which the praise image elements are conventional icons such as "love heart", "praise gesture", and the like. After the main broadcast is played, the system obtains a target picture scene corresponding to the current live broadcast picture based on scene recognition, and obtains a preview live broadcast picture fused by the current live broadcast picture and materials associated with the target picture scene, namely, a brand-customized live broadcast room is generated, and the system is customized according to the target picture scene obtained by scene recognition, wherein the target picture scene corresponding to the live broadcast room is a scene related to a certain automobile brand. The preview live view can be displayed in a switching preview page of a live view client of the anchor user, as shown in page b, a preview sub-window is popped up from the live view client, the preview sub-window includes a preview live view, a scene switching control, a material changing control and a canceling control, and a control corresponding to the "use determined" icon in page b is the scene switching control in the above embodiment. The anchor can preview the effect of the live broadcast room after using the brand customization through previewing the live broadcast picture, and can click to change a corresponding control (namely a material change control) if the current effect is not satisfactory; if the anchor does not want to switch scenes, the cancel control can be clicked. After the anchor clicks the icon of "use confirmation", the system directly replaces the target live broadcast picture after the brand customization in the live broadcast client, for example, it can be seen from the page c that the image elements of praise have been replaced by the icons of "gasoline", "steering wheel", "tires" and the like associated with the automobile, the background in the target live broadcast picture also contains the scene atmosphere image of the automobile, the top of the target live broadcast picture includes the brand of the automobile brand and the like, and the brand atmosphere can be improved.
As shown in fig. 1e, the page d is a live broadcast room frame when the live broadcast is directly played in the anchor vertical screen mode, and shows a system default live broadcast room, in which the praise image elements are conventional icons such as "love heart", "praise gesture", and the like. After the main broadcast is started, the system obtains a target picture scene corresponding to the current live broadcast picture based on scene recognition, and obtains a preview live broadcast picture obtained by fusing the current live broadcast picture and a material associated with the target picture scene, namely, a brand-customized live broadcast room is generated. The preview live view can be displayed in a switching preview page of a live view client of the anchor user, as shown in page e, a preview sub-window is popped up from the live view client, the preview sub-window includes a preview live view, a scene switching control, a material changing control and a canceling control, and a control corresponding to the "use determined" icon in page e is the scene switching control in the above embodiment. The anchor can preview the effect of the live broadcast room after using the brand customization through previewing the live broadcast picture, and if the current effect is not satisfactory, a corresponding control (namely a material replacing control) can be clicked; if the anchor does not want to switch scenes, the cancel control can be clicked. After the anchor clicks the icon of "determine use", the system directly replaces the target live broadcast picture after the brand customization in the live broadcast client, for example, it can be seen from the page f that the praise image element has been replaced with the icon corresponding to the avatar of the mall, "wealth bringing cat", the top of the target live broadcast picture also includes the avatar of the mall, and the like, so that the brand atmosphere of the mall can be improved.
Optionally, in this embodiment, the step "switching to show a target live broadcast page in a target picture scene" may include:
switching a target live broadcast page in a target picture scene;
when detecting that the content change of the target live broadcast picture meets a preset condition, performing scene recognition on the target live broadcast picture, and taking a scene corresponding to the target live broadcast picture as a new target picture scene;
switching and displaying a new target live broadcast page under the new target picture scene, wherein the new target live broadcast page comprises a new target live broadcast picture, the new target live broadcast picture is a picture obtained by fusing a live broadcast picture to be displayed in the next frame with new target materials, and the new target materials are materials related to the new target picture scene;
and returning to execute the steps of performing scene recognition and the subsequent steps on the target live broadcast picture when the content change of the target live broadcast picture is detected to meet the preset condition.
In the process of live broadcast by the anchor, the content of the live broadcast picture can be detected in real time to determine whether the picture scene corresponding to the live broadcast picture changes, specifically, the time interval for detecting the content of the live broadcast picture can be set according to actual conditions, and this embodiment does not limit this, for example, the time interval can be set to be once detection for the content of the live broadcast picture every one minute.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to generate the target live broadcast picture may include:
when the display mode of the target live broadcast room is a first mode, fusing the target foreground atmosphere material with a next frame of live broadcast picture to be displayed to generate a target live broadcast picture;
and when the display mode of the target live broadcast room is a second mode, fusing the target foreground atmosphere material, the target background atmosphere material and the next live broadcast picture to be displayed to generate a target live broadcast picture.
In some embodiments, the first mode may be a vertical screen mode, and the display effect of the live broadcast picture in the vertical screen mode is as follows: the length of the live broadcast picture is less than the width; the second mode may be a horizontal screen mode, and the display effect of the live broadcast picture in the horizontal screen mode is as follows: the length of the live frame is greater than the width.
The target foreground atmosphere material can comprise a brand praise image element, a top atmosphere image element and the like; the target background atmosphere material may comprise a scene atmosphere image or the like.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to generate the target live broadcast picture may include:
performing element identification on the next frame of live broadcast picture to be displayed so as to determine foreground picture elements and background picture elements in the next frame of live broadcast picture to be displayed;
fusing the target foreground atmosphere material and the foreground picture elements to obtain a fused foreground picture;
fusing the target background atmosphere material and the background picture element to obtain a fused background picture;
and acquiring a target live broadcast picture according to the fused foreground picture and the fused background picture.
In some embodiments, the live picture may be resolvable, that is, the live picture is obtained by combining a plurality of image layers. The method comprises the steps of carrying out element identification on a live broadcast picture, specifically carrying out layer decomposition on the live broadcast picture, and obtaining foreground picture elements and background picture elements of the live broadcast picture.
For example, foreground picture elements of a live broadcast picture may be icons, bullet screen areas, and the like corresponding to like controls in the live broadcast picture; the background picture elements of the live broadcast picture may include a picture obtained by live broadcast shooting, and the like.
Specifically, the placement position of the layer material may be determined first, and the layer material is covered on the picture element based on the placement position.
The step of acquiring the target live broadcast picture according to the fused foreground picture and the fused background picture may include:
and fusing the fused foreground picture and the fused background picture to obtain a target live broadcast picture.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to generate the target live broadcast picture may include:
fusing the target background atmosphere material and the next live broadcast picture to be displayed to obtain a fused basic live broadcast picture;
and fusing the target foreground atmosphere material and the fused basic live broadcast picture to obtain a target live broadcast picture.
Optionally, the live view may specifically be non-resolvable, and specifically, the view data corresponding to the live view only has one view layer.
As shown in fig. 1f, the target material may be divided into a target foreground ambient material and a target background ambient material. The target foreground atmosphere material, namely the brand customization layer, can highlight brand head portraits and the like, can comprise live broadcast title decorations, like image elements like a praise under a target picture scene, and like the praise image elements under a scene related to the automobile brand can comprise gasoline, a steering wheel, tires and the like. The target background atmosphere material is also a brand atmosphere layer, can highlight brand atmosphere, and can comprise a brand atmosphere background image. The target material can be fused with a basic control layer of live broadcast to highlight a live broadcast theme, and the basic control layer can comprise a live broadcast picture, a public screen message area, operation controls (namely operation area image elements, such as operation controls for bullet screen publishing, sharing and collecting) and the like.
In particular, conventional like image elements may be red packets, love hearts, like gestures, and the like. If the target picture scene is a propaganda live broadcast room of a certain automobile brand, the generated praise image elements can be a steering wheel, gasoline, tires, automobile brand trademarks and the like; if the target picture scene is a live broadcast room related to a certain mall, the generated praise image element can be an avatar of the mall, such as a cat bringing in wealth.
Optionally, in this embodiment, the step of fusing the target foreground atmosphere material and the fused basic live broadcast picture to obtain a target live broadcast picture may include:
and covering the target foreground atmosphere material on the preset position of the fused basic live broadcast picture based on the transparent channel parameter of the target foreground atmosphere material to obtain a target live broadcast picture.
In some embodiments, a fusion region (i.e., a region corresponding to a preset position) in the post-fusion basic live broadcast picture may be determined first, the fusion region is extracted from the post-fusion basic live broadcast picture, a target foreground atmosphere material and the fusion region are fused to obtain a mixed image region, and the mixed image region and the extracted post-fusion basic live broadcast picture are synthesized to obtain a target live broadcast picture.
The transparency Channel is an Alpha Channel (Alpha Channel) which refers to transparency and translucency of a picture, and an Alpha Channel value can be used to set the transparency of the picture. In the process of processing video images, various special effects are often required to be made by utilizing an alpha channel. The alpha channel data can be expressed by eight-digit binary digits, and additional information representing the transparency of each pixel point in the image file is stored. The transparent characteristic of the alpha channel can create abundant image effects, and the method has great application not only in multimedia works, but also in the aspects of movies, televisions, animations and the like. For example, the alpha transparency channel may be used to complete the overlay and composition of a special picture, so that a certain portion of the image is transparent according to different principles, and the selected color or brightness is removed from the image, so that the color-removed portion of the image is exposed to the background, and the color-not-removed portion remains the original image.
In some embodiments, if the target foreground atmosphere material does not have a transparent channel, the transparent channel of the target foreground atmosphere material may be established first, and the transparent channel parameters of each pixel may be determined. For each pixel, the transparency of the pixel can be changed by adjusting its transparency channel parameter. The larger the transparent channel parameter is, the smaller the transparency is, and conversely, the smaller the transparent channel parameter is, the higher the transparency is.
The pixel color of the target foreground atmosphere material can be regarded as foreground color, and the pixel color of the fused basic live broadcast picture can be regarded as background color. For the red, green and blue color channel with 256-level brightness, when the transparent channel parameter of the pixel of the target foreground atmosphere material is 255, the channel is opaque, namely the channel is all foreground color; and when the transparent channel parameter of the pixel of the target foreground atmosphere material is 0, the target foreground atmosphere material is completely transparent, namely the target foreground atmosphere material is completely background color. For the pixels of the target foreground atmosphere material to be presented, the transparent channel parameters can be set to be larger; for pixels of the target foreground atmosphere material which do not need to be presented, the transparent channel parameter of the pixels can be set to be smaller.
It can be understood that the fusion of other pictures may also be based on the transparent channel parameter, which is not described in detail herein, and reference may be made to the fusion process in the foregoing embodiment specifically.
The existing live broadcast platform is not beneficial to brand main exposure because merchants of different brands lack brand customization and atmosphere sense in live broadcast in a live broadcast room. If the merchant needs to perform deep brand atmosphere customization on the live broadcast room in combination with the official business, the merchant needs to prepare material diagrams of atmosphere propaganda in advance, and the process is not convenient enough.
The method and the device can intelligently identify the brand merchant owner which is currently played in real time before and in live broadcast based on scene identification and big data, intelligently generate target materials matched with the target picture scene of the current live broadcast according to the characteristics of the brand merchant owner, and then fuse the target materials and the live broadcast picture to obtain the target live broadcast picture. This scheme not only can improve the brand owner and expose and strengthen the brand atmosphere sense in the live room, can also improve the counter that the platform beckoned the cooperation to make the platform influence.
In a specific embodiment, when a live broadcast room scene is identified as a scene in a library, a background atmosphere map (one type of target material) matched with the scene, such as a school background map, a library background map, etc., is acquired; the pixel of the image corresponding to the scene may be a book, a pen, etc. Through scene recognition and big data combination, the immersive live broadcast room atmosphere decoration with brand feeling can be generated on the basis of the broadcast content and the scene of the anchor broadcast in real time. And displaying the target live broadcast picture in the target picture scene.
Optionally, in this embodiment, the server performs score sorting on candidate materials generated based on the big data, and selects a material with the highest score sorting as a target material by default. When the anchor is not satisfied with the generated target materials, the material replacing control of the preview page can be operated, and the server can transmit the corresponding materials back to the live broadcast client according to the sorting level of the candidate materials until the anchor is satisfied. If the anchor does not want to use the scene customization scheme, the scene customization can be cancelled at any time, and the server does not perform real-time scene detection on the live broadcast room subsequently.
As can be seen from the above, the present embodiment may display an initial live broadcast page, where the initial live broadcast page includes a current live broadcast picture of a target live broadcast room; when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
According to the method described in the foregoing embodiment, the following will be described in further detail by way of example in which the display device of the live view is specifically integrated in the server.
An embodiment of the present application provides a method for displaying a live view, and as shown in fig. 2a, a specific process of the method for displaying a live view may be as follows:
201. the method comprises the steps of receiving a page detection request aiming at an initial live broadcast page sent by a terminal, and carrying out content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room.
The page detection request is specifically to detect content change of a current live broadcast picture in an initial live broadcast page so as to determine whether a scene corresponding to the current live broadcast picture changes.
In some embodiments, the anchor broadcasts a live preview before live broadcasting, in a scene with the live preview, the server can acquire live preview information corresponding to the live preview information, and the live preview information is identified by linkage with big data to extract characteristic information corresponding to the live preview information, according to the characteristic information, materials matched with the live preview information are acquired and used in live broadcasting, specifically, initial target materials matched with the live preview information are acquired, when the live broadcasting starts, a current live broadcast picture and the initial target materials are fused, an initial live broadcast picture can be acquired, and the terminal is triggered to display the initial live broadcast picture through an initial live broadcast page, so that the promotion strength of related products in a target live broadcast room is enhanced.
The live preview information may include live time, live subject, anchor avatar, anchor nickname, anchor identification information (id), live summary, live goods, etc. The type of the live preview information may be various, and may include, for example, video, image, audio, and text, which is not limited in this embodiment.
Optionally, in this embodiment, the method for displaying the live view may further include:
acquiring live broadcast forecast information, and selecting an initial target material from candidate materials based on the correlation degree between the live broadcast forecast information and the candidate materials in a preset material library;
fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture;
and sending the initial live broadcast picture to the terminal so as to display the initial live broadcast picture through an initial live broadcast page of the terminal.
202. And when detecting that the content change of the current live broadcast picture meets a preset condition, carrying out scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture.
After the anchor broadcast is played, the server can detect the live broadcast picture, determine whether the content change of the live broadcast picture meets a preset condition, and if the content change meets the preset condition, perform scene recognition on the current live broadcast picture and determine a target picture scene corresponding to the current live broadcast picture. The preset condition may be set according to an actual situation, which is not limited in this embodiment, for example, the preset condition may be set according to a requirement for scene atmosphere rendering. The time interval for detecting the live broadcast picture can be set according to actual conditions, for example, the time interval can be set to detect the live broadcast picture once in one minute.
The scene recognition model may specifically be a Convolutional Neural Network (CNN), a Visual Geometry Group Network (VGGNet), a Residual Network (Residual Network), a Dense connection Convolutional Network (densneet), and the like, but it should be understood that the scene recognition model of the present embodiment is not limited to the above listed types.
Optionally, in this embodiment, the step "performing scene recognition on the current live view to obtain a target view scene corresponding to the current live view" may include:
extracting the characteristics of the current live broadcast picture to obtain the characteristic information of the current live broadcast picture;
and based on the characteristic information, carrying out scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture.
Before feature extraction, the current live broadcast picture can be preprocessed, the preprocessing process can include operations of denoising, smoothing, transformation and the like in image processing, and important features of images in the current live broadcast picture can be enhanced through preprocessing.
Optionally, in this embodiment, the step of "performing feature extraction on the current live view to obtain feature information of the current live view" may include:
performing convolution processing on the current live broadcast picture to obtain convolution information of the current live broadcast picture;
and performing downsampling processing on the convolution information to obtain the characteristic information of the current live broadcast picture.
203. And fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material associated with the target picture scene.
Optionally, in this embodiment, before the step "fusing the target material with the next frame of live view to be displayed to obtain the target live view", the method may further include:
calculating the association degree between the candidate materials in a preset material library and the target picture scene;
and selecting target materials from the candidate materials according to the relevance.
The method comprises the steps of extracting material characteristic information of candidate materials and scene characteristic information of a target picture scene, and calculating a vector distance between the material characteristic information of the candidate materials and the scene characteristic information of the target picture scene; and determining the association degree between the candidate material and the target picture scene according to the vector distance. The smaller the vector distance, the greater the degree of association; conversely, the larger the vector distance, the smaller the degree of association. The vector distance may include a euclidean distance, a cosine distance, etc., which is not limited by the embodiment.
In some embodiments, candidate materials with the association degree greater than a preset association degree can be selected as target materials, and the preset association degree can be set according to actual conditions; the candidate materials can also be sorted from large to small according to the degree of association, the first N candidate materials in the sorted candidate materials are selected as target materials, and N is a positive integer.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to obtain the target live broadcast picture may include:
when the display mode of the target live broadcast room is a first mode, fusing the target foreground atmosphere material with a next frame of live broadcast picture to be displayed to generate a target live broadcast picture;
and when the display mode of the target live broadcast room is a second mode, fusing the target foreground atmosphere material, the target background atmosphere material and the next live broadcast picture to be displayed to generate a target live broadcast picture.
In some embodiments, the first mode may be a vertical screen mode, and the display effect of the live broadcast picture in the vertical screen mode is as follows: the length of the live broadcast picture is less than the width; the second mode may be a horizontal screen mode, and the display effect of the live broadcast picture in the horizontal screen mode is as follows: the length of the live frame is greater than the width.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to obtain the target live broadcast picture may include:
performing element identification on the next frame of live broadcast picture to be displayed so as to determine foreground picture elements and background picture elements in the next frame of live broadcast picture to be displayed;
fusing the target foreground atmosphere material and the foreground picture elements to obtain a fused foreground picture;
fusing the target background atmosphere material and the background picture element to obtain a fused background picture;
and acquiring a target live broadcast picture according to the fused foreground picture and the fused background picture.
Optionally, in this embodiment, the target material includes a target foreground atmosphere material and a target background atmosphere material; the step of fusing the target material with the next live broadcast picture to be displayed to obtain the target live broadcast picture may include:
fusing the target background atmosphere material and the next live broadcast picture to be displayed to obtain a fused basic live broadcast picture;
and fusing the target foreground atmosphere material and the fused basic live broadcast picture to obtain a target live broadcast picture.
204. And sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
In a specific embodiment, the anchor issues the live preview, the server can acquire the live preview information, if the server can record the head portrait of the anchor, the identification information of the anchor, the content of the live preview and the like, the linkage big data identifies the live preview information, the content characteristic information of the live preview information is obtained, according to the content characteristic information, the live atmosphere material (namely the initial target material in the embodiment) corresponding to the brand in the live preview information is selected from the candidate material, the live atmosphere material is sent to the live client, and the anchor can select to use the live atmosphere material in the live process through the live client. During live broadcasting, a material picture customized by brand live broadcasting can be displayed in a live broadcasting client (the material picture is obtained by fusing a live broadcasting atmosphere material and a current live broadcasting picture); in addition, in the live broadcast process, the server can also detect the live broadcast picture in real time, when the content in the live broadcast picture is detected to change, the scene recognition can be carried out on the live broadcast picture by linkage big data, thereby based on a new target picture scene obtained by recognition, a new target material matched with the new target picture scene is obtained (namely, a new live broadcast atmosphere material corresponding to the new target picture scene is generated), the new live broadcast atmosphere material is returned to the live broadcast client, the new live broadcast atmosphere material is selected and used through main broadcast, and the live broadcast picture fused with the new live broadcast atmosphere material is displayed in the live broadcast client.
The specific process of rendering the live content in real time in the scene atmosphere is as follows, with reference to fig. 2 b:
2001. the anchor issues a live broadcast preview;
2002. the server records live broadcast preview information which can comprise a main broadcast head portrait, identification information, main broadcast preview content and the like;
2003. the server is linked with the big data to identify the live broadcast preview information and determine a target brand corresponding to the live broadcast preview information;
2004. generating a live broadcast atmosphere material corresponding to a target brand based on the big data content;
2005. the server transmits the live broadcast atmosphere materials back to the live broadcast client;
2006. the anchor selects and uses the live broadcast atmosphere material;
2007. the live broadcast client displays a material picture customized by brand live broadcast, wherein the material picture is obtained by fusing a live broadcast atmosphere material and a live broadcast picture;
2008. the server detects that the anchor live content changes based on scene recognition;
2009. the server is linked with the big data to identify scene content, determine a picture scene of a live broadcast picture, further determine a new target brand corresponding to the picture scene, and return to step 2004 to execute the steps of 'generating live broadcast atmosphere materials corresponding to the target brand based on the big data content' and the subsequent steps.
As can be seen from the above, in this embodiment, a server may receive a page detection request for an initial live broadcast page sent by a terminal, and perform content detection on the initial live broadcast page according to the page detection request, where the initial live broadcast page includes a current live broadcast picture in a target live broadcast room; when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture; fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene; and sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
In order to better implement the method, the embodiment of the application further provides a display system of the live broadcast picture. The display system of the live broadcast picture comprises a display device 31 of a first live broadcast picture and a display device 32 of a second live broadcast picture. As shown in fig. 3a, the presentation apparatus 31 of the first direct view may include a first presentation unit 3101 and a second presentation unit 3102; as shown in fig. 3b, the presentation apparatus 32 of the second live view may include a receiving unit 3201, a recognition unit 3202, a fusion unit 3203, and a transmitting unit 3204, as follows:
(1) the first display unit 3101;
the first displaying unit 3101 is configured to display an initial live broadcast page, where the initial live broadcast page includes a current live broadcast picture of the target live broadcast room.
Optionally, in some embodiments of the present application, the first display unit 3101 may include a preview acquisition subunit 31011, an initial fusion subunit 31012 and an initial display subunit 31013, see fig. 3c, as follows:
the forecast acquisition subunit 31011 is configured to acquire live forecast information, and select an initial target material from the candidate materials based on a degree of association between the live forecast information and candidate materials in a preset material library;
an initial fusion subunit 31012, configured to fuse the current live broadcast picture and the initial target material to obtain an initial live broadcast picture;
an initial display subunit 31013 is configured to display an initial live page, where the initial live page includes the initial live frame.
(2) A second display unit 3102;
the second display unit 3102 is configured to, when it is detected that the content change of the current live broadcast picture meets a preset condition, switch and display a target live broadcast page in a target picture scene, where the target live broadcast page includes a target live broadcast picture, the target live broadcast picture is a picture obtained by fusing a next live broadcast picture to be displayed and a target material, the target picture scene is determined by performing scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene.
Optionally, in some embodiments of the present application, the second display unit 3102 may include a first display subunit 31021, a determination subunit 31022, a picture fusion subunit 31023 and a second display subunit 31024, see fig. 3d, as follows:
the first display subunit 31021 is configured to display a switching preview page, where the switching preview page includes a scene switching control and a preview live view, the preview live view is a preview view obtained by fusing the current live view and an initial material, and the initial material is a material associated with the target view scene;
a determining subunit 31022, configured to, in response to a scene switching operation on the scene switching control, determine an initial material corresponding to a preview live view currently displayed on the switched preview page as the target material;
a picture fusion subunit 31023, configured to fuse, based on the target material, a next live broadcast picture to be displayed, so as to obtain the target live broadcast picture;
a second display subunit 31024, configured to switch to display the target live broadcast page in the target picture scene.
Optionally, in some embodiments of the present application, the switching preview page further includes a material replacement control; the second display unit 3102 may also include an acquisition subunit 31025 and a third display subunit 31026, see fig. 3e, as follows:
the acquiring subunit 31025, configured to acquire, in response to an operation on the material replacement control, a new material associated with the target screen scene as an updated target material;
and a third displaying subunit 31026, configured to display an updated preview live view in the switching preview page, where the updated preview live view is a preview view obtained by fusing the updated target material and the current live view.
Optionally, in some embodiments of the present application, the second presentation unit 3102 may include a fourth presentation subunit 31027, an identification subunit 31028, a fifth presentation subunit 31029, and a return subunit 310210, see fig. 3f, as follows:
the fourth display subunit 31027 is configured to switch to display a target live broadcast page in a target picture scene;
an identifying subunit 31028, configured to, when it is detected that the content change of the target live broadcast picture meets a preset condition, perform scene identification on the target live broadcast picture, and use a scene corresponding to the target live broadcast picture as a new target picture scene;
a fifth display subunit 31029, configured to switch to display a new target live broadcast page in the new target picture scene, where the new target live broadcast page includes a new target live broadcast picture, the new target live broadcast picture is a picture obtained by fusing a next live broadcast picture to be displayed with a new target material, and the new target material is a material associated with the new target picture scene;
and the returning subunit 310210 is configured to return to execute the scene recognition and subsequent steps on the target live view when it is detected that the content change of the target live view meets a preset condition.
Optionally, in some embodiments of the present application, the presentation apparatus 31 of the first live view may further include a generating unit 3103, where the generating unit 3103 may be configured to generate a target live view;
the generating unit 3103 may comprise a scene recognition subunit 31031, a computation subunit 31032, a selection subunit 31033 and a fusion subunit 31034, see fig. 3g, as follows:
the scene recognition subunit 31031 is configured to perform scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
a calculating subunit 31032, configured to calculate a degree of association between the candidate material in the preset material library and the target picture scene;
a selecting subunit 31033, configured to select a target material from the candidate materials according to the association degree;
and a fusion subunit 31034, configured to fuse the target material with a next live view to be displayed, so as to generate a target live view.
Optionally, in some embodiments of the present application, the target material includes a target foreground atmosphere material and a target background atmosphere material; the fusion subunit 31034 may be specifically configured to, when the display mode of the target live broadcast room is the first mode, fuse the target foreground atmosphere material with a next live broadcast picture to be displayed, so as to generate a target live broadcast picture; and when the display mode of the target live broadcast room is a second mode, fusing the target foreground atmosphere material, the target background atmosphere material and the next live broadcast picture to be displayed to generate a target live broadcast picture.
(3) A receiving unit 3201;
the receiving unit 3201 is configured to receive a page detection request for an initial live broadcast page sent by a terminal, and perform content detection on the initial live broadcast page according to the page detection request, where the initial live broadcast page includes a current live broadcast picture in a target live broadcast room.
(4) An identification unit 3202;
the identifying unit 3202 is configured to perform scene identification on the current live broadcast picture when it is detected that the content change of the current live broadcast picture meets a preset condition, so as to obtain a target picture scene corresponding to the current live broadcast picture.
(5) A fusion unit 3203;
the fusing unit 3203 is configured to fuse a target material with a next live broadcast picture to be displayed to obtain a target live broadcast picture, where the target material is a material associated with the target picture scene.
(6) A transmission unit 3204;
a sending unit 3204, configured to send the target live broadcast picture to the terminal, so as to display a target live broadcast page through the terminal, where the target live broadcast page includes the target live broadcast picture.
As can be seen from the above, in this embodiment, the first displaying unit 3101 may display an initial live broadcast page, where the initial live broadcast page includes a current live broadcast picture of the target live broadcast room; when detecting that the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene through a second display unit 3102, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture obtained by fusing a next live broadcast picture to be displayed and a target material, the target picture scene is determined by performing scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene;
alternatively, the first and second electrodes may be,
a receiving unit 3201 receives a page detection request for an initial live broadcast page sent by a terminal, and performs content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room; when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture through a recognition unit 3202 to obtain a target picture scene corresponding to the current live broadcast picture; a fusion unit 3203 fuses a target material with a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene; and sending the target live broadcast picture to the terminal through a sending unit 3204 so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
An electronic device according to an embodiment of the present application is further provided, as shown in fig. 4, which shows a schematic structural diagram of the electronic device according to the embodiment of the present application, where the electronic device may be a terminal or a server, and specifically:
the electronic device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 4 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 401 is a control center of the electronic device, connects various parts of the whole electronic device by various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.
The electronic device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 through a power management system, so that functions of managing charging, discharging, and power consumption are realized through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The electronic device may further include an input unit 404, and the input unit 404 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application program stored in the memory 402, thereby implementing various functions as follows:
displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a next live broadcast picture to be displayed and a target material, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene;
alternatively, the first and second electrodes may be,
receiving a page detection request aiming at an initial live broadcast page sent by a terminal, and carrying out content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
As can be seen from the above, the present embodiment may display an initial live broadcast page, where the initial live broadcast page includes a current live broadcast picture of a target live broadcast room; when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene. The method and the device for rendering the live broadcast scene atmosphere can perform real-time scene atmosphere rendering on the live broadcast content based on scene recognition, and are beneficial to improving the efficiency and convenience of the live broadcast scene atmosphere rendering.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present application provides a storage medium, where a plurality of instructions are stored, where the instructions can be loaded by a processor to execute steps in any method for displaying a live view provided in an embodiment of the present application. For example, the instructions may perform the steps of:
displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a next live broadcast picture to be displayed and a target material, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene;
alternatively, the first and second electrodes may be,
receiving a page detection request aiming at an initial live broadcast page sent by a terminal, and carrying out content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the storage medium can execute the steps in any live-broadcast-picture displaying method provided in the embodiment of the present application, beneficial effects that can be achieved by any live-broadcast-picture displaying method provided in the embodiment of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations of the aspect of presentation of live frames.
The method and the device for displaying the live broadcast picture provided by the embodiment of the application are described in detail, a specific example is applied in the description to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A method for displaying a live broadcast picture is characterized by comprising the following steps:
displaying an initial live broadcast page, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when the content change of the current live broadcast picture meets a preset condition, switching and displaying a target live broadcast page in a target picture scene, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed in the next frame and target materials, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target materials are materials related to the target picture scene.
2. The method of claim 1, wherein the switching to show the target live page in the target picture scene comprises:
displaying a switching preview page, wherein the switching preview page comprises a scene switching control and a previewing live broadcast picture, the previewing live broadcast picture is a previewing picture formed by fusing the current live broadcast picture and initial materials, and the initial materials are materials related to the target picture scene;
responding to the scene switching operation of the scene switching control, and determining an initial material corresponding to a preview live broadcast picture currently displayed on the switching preview page as the target material;
fusing a next frame of live broadcast picture to be displayed based on the target material to obtain the target live broadcast picture;
and switching and displaying the target live broadcast page in the target picture scene.
3. The method of claim 2, wherein the toggle preview page further comprises a material change control; the method further comprises the following steps:
responding to the operation of the material replacing control, and acquiring a new material associated with the target picture scene as an updated target material;
displaying an updated preview live broadcast picture in the switching preview page, wherein the updated preview live broadcast picture is a preview picture formed by fusing the updated target material and the current live broadcast picture.
4. The method of claim 1, wherein the switching to show the target live page in the target picture scene comprises:
switching a target live broadcast page in a target picture scene;
when detecting that the content change of the target live broadcast picture meets a preset condition, performing scene recognition on the target live broadcast picture, and taking a scene corresponding to the target live broadcast picture as a new target picture scene;
switching and displaying a new target live broadcast page under the new target picture scene, wherein the new target live broadcast page comprises a new target live broadcast picture, the new target live broadcast picture is a picture obtained by fusing a live broadcast picture to be displayed in the next frame with new target materials, and the new target materials are materials related to the new target picture scene;
and returning to execute the steps of performing scene recognition and the subsequent steps on the target live broadcast picture when the content change of the target live broadcast picture is detected to meet the preset condition.
5. The method of claim 1, wherein before switching to the target live page in the target picture scene, the method further comprises:
carrying out scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
calculating the association degree between the candidate materials in a preset material library and the target picture scene;
selecting target materials from the candidate materials according to the relevance;
and fusing the target material and the next frame of live broadcast picture to be displayed to generate a target live broadcast picture.
6. The method of claim 5, wherein the target material comprises target foreground ambient material and target background ambient material; the fusing the target material with the next frame of live broadcast picture to be displayed to generate a target live broadcast picture, comprising:
when the display mode of the target live broadcast room is a first mode, fusing the target foreground atmosphere material with a next frame of live broadcast picture to be displayed to generate a target live broadcast picture;
and when the display mode of the target live broadcast room is a second mode, fusing the target foreground atmosphere material, the target background atmosphere material and the next live broadcast picture to be displayed to generate a target live broadcast picture.
7. The method of claim 1, wherein before presenting the initial live page, further comprising:
acquiring live broadcast forecast information, and selecting an initial target material from candidate materials based on the correlation degree between the live broadcast forecast information and the candidate materials in a preset material library;
the displaying of the initial live broadcast page comprises:
fusing the current live broadcast picture and the initial target material to obtain an initial live broadcast picture;
and displaying an initial live broadcast page, wherein the initial live broadcast page comprises the initial live broadcast picture.
8. A method for displaying a live broadcast picture is characterized by comprising the following steps:
receiving a page detection request aiming at an initial live broadcast page sent by a terminal, and carrying out content detection on the initial live broadcast page according to the page detection request, wherein the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
when detecting that the content change of the current live broadcast picture meets a preset condition, performing scene recognition on the current live broadcast picture to obtain a target picture scene corresponding to the current live broadcast picture;
fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
9. A display device for live pictures, comprising:
the first display unit is used for displaying an initial live broadcast page, and the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
and the second display unit is used for switching and displaying a target live broadcast page under a target picture scene when detecting that the content change of the current live broadcast picture meets a preset condition, wherein the target live broadcast page comprises a target live broadcast picture, the target live broadcast picture is a picture formed by fusing a live broadcast picture to be displayed and a target material, the target picture scene is determined by carrying out scene recognition on the current live broadcast picture, and the target material is a material associated with the target picture scene.
10. A display device for live pictures, comprising:
the system comprises a receiving unit, a content detecting unit and a processing unit, wherein the receiving unit is used for receiving a page detection request aiming at an initial live broadcast page sent by a terminal and detecting the content of the initial live broadcast page according to the page detection request, and the initial live broadcast page comprises a current live broadcast picture of a target live broadcast room;
the identification unit is used for carrying out scene identification on the current live broadcast picture when detecting that the content change of the current live broadcast picture meets a preset condition so as to obtain a target picture scene corresponding to the current live broadcast picture;
the fusion unit is used for fusing a target material and a next frame of live broadcast picture to be displayed to obtain a target live broadcast picture, wherein the target material is a material related to a target picture scene;
and the sending unit is used for sending the target live broadcast picture to the terminal so as to display a target live broadcast page through the terminal, wherein the target live broadcast page comprises the target live broadcast picture.
CN202110507350.7A 2021-05-10 2021-05-10 Live broadcast picture display method and device Active CN113766296B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110507350.7A CN113766296B (en) 2021-05-10 2021-05-10 Live broadcast picture display method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110507350.7A CN113766296B (en) 2021-05-10 2021-05-10 Live broadcast picture display method and device

Publications (2)

Publication Number Publication Date
CN113766296A true CN113766296A (en) 2021-12-07
CN113766296B CN113766296B (en) 2023-10-13

Family

ID=78787097

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110507350.7A Active CN113766296B (en) 2021-05-10 2021-05-10 Live broadcast picture display method and device

Country Status (1)

Country Link
CN (1) CN113766296B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114125569A (en) * 2022-01-27 2022-03-01 阿里巴巴（中国）有限公司 Live broadcast processing method and device
CN114449252A (en) * 2022-02-12 2022-05-06 北京蜂巢世纪科技有限公司 Method, device, equipment, system and medium for dynamically adjusting live video based on explication audio
CN114547436A (en) * 2021-12-31 2022-05-27 北京达佳互联信息技术有限公司 Page display method and device, electronic equipment and storage medium
CN115002555A (en) * 2022-06-01 2022-09-02 无限魔方(深圳)科技有限公司 Theme making method, device and equipment applied to live broadcast room
CN115065876A (en) * 2022-08-18 2022-09-16 广州市千钧网络科技有限公司 Method and device for changing live title and cover and related product
WO2024099425A1 (en) * 2022-11-10 2024-05-16 北京字跳网络技术有限公司 Live streaming reservation method and apparatus, device, and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106203990A (en) * 2016-07-05 2016-12-07 深圳市星尚天空科技有限公司 A kind of method and system utilizing virtual decorative article to beautify net cast interface
CN108650523A (en) * 2018-05-22 2018-10-12 广州虎牙信息科技有限公司 The display of direct broadcasting room and virtual objects choosing method, server, terminal and medium
CN109525853A (en) * 2018-11-29 2019-03-26 北京字节跳动网络技术有限公司 Direct broadcasting room cover methods of exhibiting, device, terminal, server and readable medium
CN109660853A (en) * 2017-10-10 2019-04-19 腾讯科技（北京）有限公司 Interactive approach, apparatus and system in net cast
CN111263227A (en) * 2020-02-10 2020-06-09 腾讯科技（深圳）有限公司 Multimedia playing method, device and storage medium
CN111800661A (en) * 2020-07-08 2020-10-20 网易（杭州）网络有限公司 Live broadcast room display control method, electronic device and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106203990A (en) * 2016-07-05 2016-12-07 深圳市星尚天空科技有限公司 A kind of method and system utilizing virtual decorative article to beautify net cast interface
CN109660853A (en) * 2017-10-10 2019-04-19 腾讯科技（北京）有限公司 Interactive approach, apparatus and system in net cast
CN108650523A (en) * 2018-05-22 2018-10-12 广州虎牙信息科技有限公司 The display of direct broadcasting room and virtual objects choosing method, server, terminal and medium
CN109525853A (en) * 2018-11-29 2019-03-26 北京字节跳动网络技术有限公司 Direct broadcasting room cover methods of exhibiting, device, terminal, server and readable medium
CN111263227A (en) * 2020-02-10 2020-06-09 腾讯科技（深圳）有限公司 Multimedia playing method, device and storage medium
CN111800661A (en) * 2020-07-08 2020-10-20 网易（杭州）网络有限公司 Live broadcast room display control method, electronic device and storage medium

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114547436A (en) * 2021-12-31 2022-05-27 北京达佳互联信息技术有限公司 Page display method and device, electronic equipment and storage medium
CN114125569A (en) * 2022-01-27 2022-03-01 阿里巴巴（中国）有限公司 Live broadcast processing method and device
CN114449252A (en) * 2022-02-12 2022-05-06 北京蜂巢世纪科技有限公司 Method, device, equipment, system and medium for dynamically adjusting live video based on explication audio
CN115002555A (en) * 2022-06-01 2022-09-02 无限魔方(深圳)科技有限公司 Theme making method, device and equipment applied to live broadcast room
CN115002555B (en) * 2022-06-01 2024-01-05 无限魔方(深圳)科技有限公司 Theme making method, device and equipment applied to live broadcasting room
CN115065876A (en) * 2022-08-18 2022-09-16 广州市千钧网络科技有限公司 Method and device for changing live title and cover and related product
WO2024099425A1 (en) * 2022-11-10 2024-05-16 北京字跳网络技术有限公司 Live streaming reservation method and apparatus, device, and storage medium

Also Published As

Publication number Publication date
CN113766296B (en) 2023-10-13

Similar Documents

Publication Publication Date Title
CN113766296B (en) Live broadcast picture display method and device
US11741681B2 (en) Interaction analysis systems and methods
CN107633441A (en) Commodity in track identification video image and the method and apparatus for showing merchandise news
CN106203286B (en) Augmented reality content acquisition method and device and mobile terminal
US11706485B2 (en) Display device and content recommendation method
TWI617930B (en) Method and system for sorting a search result with space objects, and a computer-readable storage device
CN111491187B (en) Video recommendation method, device, equipment and storage medium
CN103686344A (en) Enhanced video system and method
WO2024077909A1 (en) Video-based interaction method and apparatus, computer device, and storage medium
CN112287848A (en) Live broadcast-based image processing method and device, electronic equipment and storage medium
CN111142967B (en) Augmented reality display method and device, electronic equipment and storage medium
US20170013309A1 (en) System and method for product placement
CN113596574A (en) Video processing method, video processing apparatus, electronic device, and readable storage medium
CN113610953A (en) Information processing method and device and computer readable storage medium
CN112684893A (en) Information display method and device, electronic equipment and storage medium
WO2023241154A1 (en) Interaction method and apparatus based on news feed advertisement, and device and medium
CN112449249A (en) Video stream processing method and device, electronic equipment and storage medium
CN114500833B (en) Shooting method and device and electronic equipment
CN114245174B (en) Video preview method and related equipment
CN113873080B (en) Multimedia file acquisition method and device
US20230326161A1 (en) Data processing method and apparatus, electronic device, computer-readable storage medium, and computer program product
WO2022111005A1 (en) Virtual reality (vr) device and vr scenario image recognition method
CN117857894A (en) Live cover processing method and device, electronic equipment and computer storage medium
CN115981755A (en) Face payment method and related equipment
CN117036150A (en) Image acquisition method, device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant