CN110381266A - A kind of video generation method, device and terminal - Google Patents
A kind of video generation method, device and terminal Download PDFInfo
- Publication number
- CN110381266A CN110381266A CN201910700099.9A CN201910700099A CN110381266A CN 110381266 A CN110381266 A CN 110381266A CN 201910700099 A CN201910700099 A CN 201910700099A CN 110381266 A CN110381266 A CN 110381266A
- Authority
- CN
- China
- Prior art keywords
- casting
- video
- virtual portrait
- text
- report
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005266 casting Methods 0.000 claims abstract description 226
- 239000000463 material Substances 0.000 claims abstract description 25
- 230000015654 memory Effects 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 239000011800 void material Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000272525 Anas platyrhynchos Species 0.000 description 1
- 241001085205 Prenanthella exigua Species 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Processing Or Creating Images (AREA)
Abstract
This application discloses a kind of video generation methods, are related to video field.Specific implementation are as follows: obtain video content material and video template, video content material includes the image of virtual portrait, the dynamic element of virtual portrait and casting content;The report clips of virtual portrait are generated according to casting content, the image of virtual portrait, the dynamic element of virtual portrait;The report clips of virtual portrait are added in video template, casting video is obtained.The efficiency that video generation can not only be improved, reduces cost, and enrich video content, meets the diversified demand of spectators.
Description
Technical field
This application involves a kind of field of computer technology more particularly to a kind of video fields.
Background technique
Traditional news report, taking a long time from column preparation, the links such as material preparation, gather and edit, make could be complete
At, while needing a large amount of manpower intervention.So traditional news report is at high cost, whole production efficiency is low.Currently, can be with
Using virtual newscaster's reciting news content, and then the video that virtual newscaster carries out news report is generated, to replace traditional news
Casting.However, the video that virtual newscaster carries out news report only includes two elements of background picture and virtual newscaster.In video
Element it is single, news is not abundant enough, is unable to satisfy spectators to the diversified demand of news report.
Summary of the invention
The application provides a kind of video generation method, device and terminal, to solve one or more in the prior art
Technical problem.
In a first aspect, this application provides a kind of video generation methods, comprising:
It obtains video content material and video template, video content material includes the image of virtual portrait, virtual portrait
Dynamic element and casting content;
The report clips of virtual portrait are generated according to casting content, the image of virtual portrait, the dynamic element of virtual portrait;
The report clips of virtual portrait are added in video template, casting video is obtained.
The efficiency that can be improved video generation, reduces cost, and enrich video content, meets the diversified need of spectators
It asks.
In one embodiment, casting content includes casting text, and the dynamic element of virtual portrait includes virtual portrait
Lip is dynamic, expression and movement, virtual portrait is generated according to casting content, the image of virtual portrait, the dynamic element of virtual portrait
Report clips, comprising:
Casting pronunciation type is obtained according to video template;
Casting voice is generated according to casting text and casting pronunciation type;
Casting voice is input in lip movable model, the lip for exporting virtual portrait corresponding with casting voice is dynamic;
Obtain the expression and movement of virtual portrait corresponding with casting text;
According to the image of virtual portrait, broadcast broadcasting for dynamic voice, the lip of virtual portrait, expression and movement generation virtual portrait
Report tablet section.
The embodiment is by moving the image of virtual portrait, lip, expression and movement are corresponding with casting voice, so that generating
Virtual portrait report clips in, virtual portrait is by expression and acts shown mood and casting voice more meets
Broadcast the logic of text.Meanwhile so that casting video is finer and smoother.
In one embodiment, the report clips of virtual portrait are added in video template, obtain casting video, packet
It includes:
The distributing position of virtual portrait is obtained according to video template;
The report clips of virtual portrait are added in the distributing position of virtual portrait, casting video is obtained.The embodiment party
Formula improves the generating rate of casting video by the way that the report clips of virtual portrait to be added to the distributing position of virtual portrait.
In one embodiment, casting content further includes picture relevant to casting text and/or video, and this method is also
Include:
The first display area of picture relevant to casting text and/or video is obtained according to video template;
The first display area will be added to the relevant picture of casting text and/or video.
The embodiment shows the relevant picture of casting text and/or video by the first display area, enriches casting
The casting content of video.
In one embodiment, casting text includes casting title, casting text, casting date, method further include:
The second display area of casting text is obtained according to video template, the second display area includes broadcast title first
Subregion, the second subregion for broadcasting text and the third subregion for broadcasting the date;
Casting title is added to the first subregion, casting text is added to the second subregion, and the casting date is added to the
Three subregions.
The embodiment shows the relevant picture of casting text and/or video by the first display area, enriches casting
The casting content of video.
In one embodiment, further includes:
At least one of casting scene, head, run-out and clothes of virtual portrait are obtained according to video template.
Second aspect, this application provides a kind of video-generating devices, comprising:
Material and template obtain module, and for obtaining video content material and video template, video content material includes void
The image of anthropomorphic object, the dynamic element of virtual portrait and casting content;
Report clips generation module, for raw according to casting content, the image of virtual portrait, the dynamic element of virtual portrait
At the report clips of virtual portrait;
Video generation module is broadcasted, for the report clips of virtual portrait to be added in video template, obtains casting view
Frequently.
In one embodiment, casting content includes casting text, and the dynamic element of virtual portrait includes virtual portrait
Lip is dynamic, expression and movement, report clips generation module include:
Casting pronunciation type acquiring unit, for obtaining casting pronunciation type according to video template;
Speech production unit is broadcasted, for generating casting voice according to casting text and casting pronunciation type;
Lip moves generation unit, is input in lip movable model for that will broadcast voice, and output is corresponding with casting voice virtual
The lip of personage is dynamic;
Expression and movement acquiring unit, for obtaining the expression and movement of virtual portrait corresponding with text is broadcasted;
Report clips generation unit, for according to the image of virtual portrait, casting voice, the lip of virtual portrait be dynamic, expression
The report clips of virtual portrait are generated with movement.
In one embodiment, casting video generation module includes:
The distribution of the persons position acquisition unit, for obtaining the distributing position of virtual portrait according to video template;
Report clips adding unit, for the report clips of virtual portrait to be added in the distributing position of virtual portrait,
Obtain casting video.
In one embodiment, casting content further includes picture relevant to casting text and/or video, further includes:
First display area obtains module, for obtaining picture relevant to casting text and/or view according to video template
First display area of frequency;
Picture and video adding module, for the first displaying will to be added to the relevant picture of casting text and/or video
Region.
In one embodiment, casting text includes casting title, casting text, casting date, further includes:
Second display area obtain module, for according to video template obtain casting text the second display area, second
Display area includes broadcasting the first subregion of title, broadcast the second subregion of text and broadcasting the third sub-district on date
Domain;
Text adding module is broadcasted, is added to the first subregion for title will to be broadcasted, casting text is added to the second son
Region, casting date are added to third subregion.
In one embodiment, further includes:
Template elements obtain module, for obtaining casting scene, head, run-out and virtual portrait according to video template
At least one of clothes.
The third aspect, this application provides a kind of electronic equipment, the function of electronic equipment can be by hardware realization, can also
To execute corresponding software realization by hardware.Hardware or software include one or more modules corresponding with above-mentioned function.
It include processor and memory in the structure of electronic equipment, memory is for storing in a possible design
Electronic equipment is supported to execute the program of above-mentioned video generation method, processor is configurable for executing the journey stored in memory
Sequence.Electronic equipment can also include communication interface, be used for and other equipment or communication.
Other effects possessed by above-mentioned optional way are illustrated hereinafter in conjunction with specific embodiment.
Detailed description of the invention
Attached drawing does not constitute the restriction to the application for more fully understanding this programme.Wherein:
Fig. 1 is the method flow diagram according to the application first embodiment;
Fig. 2 is the method schematic diagram according to the application first embodiment;
Fig. 3 is the another method flow chart according to the application first embodiment;
The video that the application first embodiment may be implemented in Fig. 4 generates scene figure;
Fig. 5 is the schematic diagram according to the application second embodiment;
Fig. 6 is another schematic diagram according to the application second embodiment;
Fig. 7 is another schematic diagram according to the application second embodiment;
Fig. 8 is another schematic diagram according to the application second embodiment;
Fig. 9 is another schematic diagram according to the application second embodiment;
Figure 10 is the block diagram for the electronic equipment for the method for realizing the video generation of the embodiment of the present application.
Specific embodiment
It explains below in conjunction with exemplary embodiment of the attached drawing to the application, including the various of the embodiment of the present application
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from the scope and spirit of the present application.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
Embodiment one ...
In a kind of specific embodiment, a kind of video generation method is provided, as shown in Figure 1, this method comprises:
Step S10: obtaining video content material and video template, video content material include the image of virtual portrait, void
The dynamic element and casting content of anthropomorphic object.
In a kind of example, as shown in Fig. 2, each video content material can be inputted.The image of virtual portrait may include
Cartoon character, real person's image etc..For example, the host of news channel, Donald duck cartoon host etc..Virtual portrait moves
State element may include when carrying out casting content, and the lip of virtual figure image is dynamic, expression and movement etc..For example, true people
The lip of various lips folding of the object when speaking is dynamic etc..The expression of smile, the expression of indignation, the expression of laugh, sad expression
Deng.Movement may include limb action and headwork.It embraces for example, limb action can be both arms in front, broadcasting content can
To include news content or various programme contents.For example, the program cooked, the program of music introduction, sports cast, children's programs
Deng.Wherein, news content may include preceding string field word, rear string field word, headline, body, news date etc..In casting
Holding can also include various pictures relevant to news content or various programme contents and video etc..
It may include in head, run-out, the distributing position of virtual portrait, various scenes and casting content in video template
Picture or video equal distribution position.Different video templates may include different above-mentioned element.For example, can be according to difference
Virtual figure image select corresponding scene.The image of virtual portrait is to stand or be seated.Virtual portrait shape can also be given
As selecting corresponding clothes, for example, the clothes etc. of black, pink colour, white.Corresponding sound can also be selected to virtual figure image
Color type, for example, male voice or female voice.Corresponding head and run-out also may be selected.For example, the head on daytime, at night
The run-out of different brands showing advertisement etc. may be selected in head, run-out.
Step S20: virtual portrait is generated according to casting content, the image of virtual portrait, the dynamic element of virtual portrait
Report clips.
In a kind of example, as shown in Fig. 2, automatically generating casting view after obtaining video template and video content material
Frequently.The report clips of virtual portrait can completely broadcast one Duan Xinwen or program.Specifically, the shape of virtual portrait
As the lip in the dynamic element with virtual portrait is dynamic, expression and movement etc. are merged, played together with casting content.For example,
Virtual portrait is during carrying out a batch of news casting, the casting voice broadcasted according to news content, with virtual portrait
The lip of image moves, expression and movement are corresponding.The content for enriching news report meets diversification of the spectators to news report
Demand.
Step S30: the report clips of virtual portrait are added in video template, obtain casting video.
In a kind of example, as shown in Fig. 2, since video template provides the distributing position of virtual portrait, various scenes
And wave broadcasts picture or video equal distribution position in content etc., so by the report clips and video template of virtual portrait
It is merged, obtains casting video.After generating casting video, casting video download can be set to hardware such as local, hard disks
It is saved in standby or cloud device.Or be distributed in each media platform, share etc. in Internet application.
Video generation method provided in this embodiment can not only improve the efficiency of video generation, reduce cost, Er Qiefeng
Rich video content, meets spectators to the diversified demand of the videos such as news report.Because using video content material abundant,
The technological means of various template is matched simultaneously, so overcoming the single technical problem of video content, and then reaches and enriches view
Frequency content meets spectators to the technical effect of the diversified demand of the videos such as news report.
In one embodiment, casting content includes casting text, and the dynamic element of virtual portrait includes virtual portrait
Lip is dynamic, expression and movement, according to casting content, as shown in figure 3, step S20 includes:
S201: casting pronunciation type is obtained according to video template;
S202: casting voice is generated according to casting text and casting pronunciation type;
S203: casting voice is input in lip movable model, and the lip for exporting virtual portrait corresponding with casting voice is dynamic;
S204: the expression and movement of virtual portrait corresponding with casting text are obtained;
S205: according to the image of virtual portrait, dynamic voice, the lip of virtual portrait, expression and movement generation visual human are broadcasted
The report clips of object.
It include casting pronunciation type in a kind of example, in video template.Casting pronunciation type may include adult male
Sound, the adult types such as female voice and child's voice.Alternatively, can also include droning sound, loud and sonorous sound, gentle sound, can
The types such as the sound of love.It is, of course, also possible to add a greater variety of casting pronunciation types according to demand in video template.It can be with
It is the casting text progress voice broadcast of preceding string field word, headline, body, rear string field word in sequence.Meanwhile it regarding
Selection casting pronunciation type corresponding with casting text in casting pronunciation type in frequency template.It will casting text and casting pronunciation class
Type synthesis casting voice.
Further, it is also possible to the speech synthesis model that the voice training based on some specific speaker obtains, by casting text
Originally it is input in speech synthesis model, obtains the casting voice of specific speaker.Wherein, the sound of some specific speaker
It can be described as sound library, obtain is sound library model using the training of sound library.The material moved using various lips and material training lip of speaking are dynamic
Model, the lip that obtained lip moves when speaking to true man move similar.Casting voice is input in lip movable model, can export and broadcast
Report the corresponding lip of voice dynamic.According to the expression and movement of casting text adjustment virtual portrait, so that expression and movement and casting text
This correspondence.Happy text is expressed for example, having in casting text, the expression of collocation is the expression smiled, and movement can be double
The movement that arm opens.In addition, the clothes of many selective virtual figure images can also be provided in video template.Finally,
By the image of virtual portrait, broadcast dynamic voice, the lip of virtual portrait, expression and the report clips for acting generation virtual portrait.
In present embodiment, by the image of virtual portrait, lip is dynamic, expression and movement are corresponding with casting voice, so that generation
Virtual portrait report clips in, virtual portrait is by expression and acts shown mood and casting voice more meets
Broadcast the logic of text.Meanwhile so that casting video is finer and smoother.
In one embodiment, as shown in figure 3, step S30, comprising:
Step S301: the distributing position of virtual portrait is obtained according to video template;
Step S302: the report clips of virtual portrait are added in the distributing position of virtual portrait, obtain casting video.
In a kind of example, as shown in figure 4, including the distributing position of at least one virtual portrait in video template.It is trying
In sound template, the distributing position and number of virtual portrait can be adaptively adjusted according to demand, in present embodiment
In protection scope.The report clips of virtual portrait obtained in a upper embodiment are added into the visual human in video template
In the distributing position of object, casting video is obtained.When playing casting video, the head in video template start to play, Zhi Houshi
The report clips of virtual portrait are finally run-outs.
In one embodiment, as shown in figure 5, casting content further includes picture relevant to casting text and/or view
Frequently, this method further include:
Step S40: the first display area of picture relevant to casting text and/or video is obtained according to video template;
Step S50: the first display area will be added to the relevant picture of casting text and/or video.
In a kind of example, as shown in figure 4, in video template include at least one first display area, for show with
Broadcast the relevant picture of text and/or video.For example, casting text is the first news about Tangshan Earthquake, in the first exhibition
Show in region, the picture after Tangshan Earthquake can be played, and the video etc. that camera takes in seismic process.It is regarding
In frequency template, the position of the first display area and number can be adaptively adjusted according to demand, in present embodiment
In protection scope.The setting of first display area, being capable of apparent specific reflection so that the content of casting video is more abundant
Broadcast the content of text.
It in one embodiment, should as shown in figure 5, casting text includes casting title, casting text, broadcasts the date
Method further include:
Step S60: obtaining the second display area of casting text according to video template, and the second display area includes casting mark
First subregion of topic, the second subregion for broadcasting text and the third subregion for broadcasting the date;
Step S70: casting title is added to the first subregion, casting text is added to the second subregion, broadcasts the date
It is added to third subregion.
In a kind of example, as shown in figure 4, when broadcasting content, it will usually carry out casting text in a manner of subtitle
It shows, better understands the content in casting text convenient for spectators, enrich the content of casting video.For example, for showing casting
First subregion of title, for showing that the third subregion on casting date can be showed in the lower right-hand side of screen, left side
The positions such as side, the theme currently broadcasted and date are quickly found convenient for spectators.Casting text can be showed in the bottom position of screen
It sets, forms subtitle, be played simultaneously with casting voice.
In one embodiment, as shown in Figure 5, further includes:
Step S80: it is obtained in the clothes of casting scene, head, run-out and virtual portrait at least according to video template
One.
In a kind of example, the casting scene in video template can be outdoor scene, for example, the scene of tourist festival purpose casting
It can be the Forbidden City in front of the door.Casting scene can also be indoor scene, for example, the casting of house ornamentation program can be a family Nordic Style
House ornamentation indoor scene.Head and run-out are corresponding with casting text, preferably mutually to echo with casting content.Video template is also
Include clothes required for the image of a large amount of virtual portraits, suitable clothes can be selected for different casting themes.
Embodiment two
In another embodiment specific implementation mode, as shown in fig. 6, providing a kind of video-generating device 10, comprising:
Material and template obtain module 101, and for obtaining video content material and video template, video content material includes
The image of virtual portrait, the dynamic element of virtual portrait and casting content;
Report clips generation module 102, for according to casting content, the image of virtual portrait, the dynamic of virtual portrait member
Element generates the report clips of virtual portrait;
Casting video generation module 103 is broadcasted for the report clips of virtual portrait to be added in video template
Video.
In one embodiment, casting content includes casting text, and the dynamic element of virtual portrait includes virtual portrait
Lip is dynamic, expression and movement, as shown in fig. 7, report clips generation module 102 includes:
Casting pronunciation type acquiring unit 1021, for obtaining casting pronunciation type according to institute's video template;
Speech production unit 1022 is broadcasted, for generating casting voice according to casting text and casting pronunciation type;
Lip moves generation unit 1023, is input in lip movable model for that will broadcast voice, and output is corresponding with casting voice
The lip of virtual portrait is dynamic;
Expression and movement acquiring unit 1024, for obtaining the expression and movement of virtual portrait corresponding with text is broadcasted;
Report clips generation unit 1025, moved for the image of virtual portrait, according to the lip of casting voice, virtual portrait,
Expression and movement generate the report clips of virtual portrait.
In one embodiment, as shown in figure 8, casting video generation module 103 includes:
The distribution of the persons position acquisition unit 1031, for obtaining the distributing position of virtual portrait according to video template;
Report clips adding unit 1032, for the report clips of virtual portrait to be added to the distributing position of virtual portrait
In, obtain casting video.
In one embodiment, casting content further includes picture relevant to casting text and/or video, such as Fig. 9 institute
Show, further includes:
First display area obtains module 104, for according to video template obtain with broadcast the relevant picture of text and/or
First display area of video;
Picture and video adding module 105, for the first exhibition will to be added to the relevant picture of casting text and/or video
Show region.
In one embodiment, casting text includes casting title, casting text, casting date, as shown in figure 9, also
Include:
Second display area obtains module 106, for obtaining the second display area of casting text according to video template, the
Two display areas include broadcasting the first subregion of title, broadcast the second subregion of text and broadcasting the third sub-district on date
Domain;
Text adding module 107 is broadcasted, is added to the first subregion for title will to be broadcasted, casting text is added to second
Subregion, casting date are added to third subregion.
In one embodiment, as shown in Figure 9, further includes:
Template elements obtain module 108, for obtaining casting scene, head, run-out and visual human according to video template
At least one of clothes of object.
Embodiment three
According to an embodiment of the present application, present invention also provides a kind of electronic equipment and a kind of readable storage medium storing program for executing.
As shown in Figure 10, it is block diagram according to the electronic equipment of the video generation method of the embodiment of the present application.Electronic equipment
It is intended to indicate that various forms of digital computers, such as, laptop computer, desktop computer, workbench, individual digital help
Reason, server, blade server, mainframe computer and other suitable computer.Electronic equipment also may indicate that various shapes
The mobile device of formula, such as, personal digital assistant, cellular phone, smart phone, wearable device and other similar calculating dresses
It sets.Component, their connection and relationship shown in this article and their function are merely exemplary, and are not intended to limit
The realization of described herein and/or requirement the application.
As shown in Figure 10, which includes: one or more processors 1001, memory 1002, and for connecting
Connect the interface of each component, including high-speed interface and low-speed interface.All parts are interconnected using different bus, and can be with
It is installed on public mainboard or installs in other ways as needed.Processor can be to the finger executed in electronic equipment
Order is handled, including storage in memory or on memory (such as, to be coupled to and connect in external input/output device
Mouthful display equipment) on show graphic user interface (Graphical User Interface, GUI) graphical information finger
It enables.In other embodiments, if desired, by multiple processors and/or multiple bus and multiple memories and multiple can deposit
Reservoir is used together.It is also possible to connect multiple electronic equipments, each equipment provides the necessary operation in part (for example, as clothes
Business device array, one group of blade server or multicomputer system).In Figure 10 by taking a processor 1001 as an example.
Memory 1002 is non-transitory computer-readable storage medium provided herein.Wherein, the memory
It is stored with the instruction that can be executed by least one processor, so that at least one described processor executes view provided herein
Frequency generation method.The non-transitory computer-readable storage medium of the application stores computer instruction, and the computer instruction is for making
Computer executes video generation method provided herein.
Memory 1002 be used as a kind of non-transitory computer-readable storage medium, can be used for storing non-instantaneous software program,
Non-instantaneous computer executable program and module, as the corresponding program instruction of video generation method in the embodiment of the present application/
Module (generates for example, attached material shown in fig. 6 and template obtain module 101, report clips generation module 102 and casting video
Module 103).Non-instantaneous software program, instruction and the module that processor 1001 is stored in memory 1002 by operation, from
And the various function application and data processing of execute server, i.e. video generation method in realization above method embodiment.
Memory 1002 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function;Storage data area can store the use of the electronic equipment generated according to video
The data etc. created.In addition, memory 1002 may include high-speed random access memory, it can also include non-instantaneous storage
Device, for example, at least a disk memory, flush memory device or other non-instantaneous solid-state memories.In some embodiments,
Optional memory 1002 includes the memory remotely located relative to processor 1001, these remote memories can pass through network
It is connected to the electronic equipment of video generation.The example of above-mentioned network include but is not limited to internet, intranet, local area network,
Mobile radio communication and combinations thereof.
The electronic equipment of video generation method can also include: input unit 1003 and output device 1004.Processor
1001, memory 1002, input unit 1003 and output device 1004 can be connected by bus or other modes, Tu10Zhong
For being connected by bus.
Input unit 1003 can receive the number or character information of input, and generate the electronic equipment generated with video
User setting and function control related key signals input, such as touch screen, keypad, mouse, track pad, touch tablet, refer to
Show the input units such as bar, one or more mouse button, trace ball, control stick.Output device 1004 may include that display is set
Standby, auxiliary lighting apparatus (for example, LED) and haptic feedback devices (for example, vibrating motor) etc..The display equipment may include but
It is not limited to, liquid crystal display (Liquid Crystal Display, LCD), light emitting diode (Light Emitting
Diode, LED) display and plasma scope.In some embodiments, display equipment can be touch screen.
The various embodiments of system and technology described herein can be in digital electronic circuitry, integrated circuit system
System, is consolidated specific integrated circuit (Application Specific Integrated Circuits, ASIC), computer hardware
It is realized in part, software, and/or their combination.These various embodiments may include: to implement in one or more calculating
In machine program, which can hold in programmable system containing at least one programmable processor
Row and/or explain, which can be dedicated or general purpose programmable processors, can from storage system, at least
One input unit and at least one output device receive data and instruction, and data and instruction is transmitted to the storage system
System, at least one input unit and at least one output device.
These calculation procedures (also referred to as program, software, software application or code) include the machine of programmable processor
Instruction, and can use programming language, and/or the compilation/machine language of level process and/or object-oriented to implement these
Calculation procedure.As used herein, term " machine readable media " and " computer-readable medium " are referred to for referring to machine
It enables and/or data is supplied to any computer program product, equipment, and/or the device of programmable processor (for example, disk, light
Disk, memory, programmable logic device (programmable logic device, PLD)), including, receiving can as machine
The machine readable media of the machine instruction of read signal.Term " machine-readable signal " is referred to for by machine instruction and/or number
According to any signal for being supplied to programmable processor.
In order to provide the interaction with user, system and technology described herein, the computer can be implemented on computers
Include for user show information display device (for example, CRT (Cathode Ray Tube, cathode-ray tube) or
LCD (liquid crystal display) monitor);And keyboard and indicator device (for example, mouse or trace ball), user can be by this
Keyboard and the indicator device provide input to computer.The device of other types can be also used for providing the friendship with user
Mutually;For example, the feedback for being supplied to user may be any type of sensory feedback (for example, visual feedback, audio feedback or
Touch feedback);And it can be received with any form (including vocal input, voice input or tactile input) from user
Input.
System described herein and technology can be implemented including the computing system of background component (for example, as data
Server) or the computing system (for example, application server) including middleware component or the calculating including front end component
System is (for example, the subscriber computer with graphic user interface or web browser, user can pass through graphical user circle
Face or the web browser to interact with the embodiment of system described herein and technology) or including this backstage portion
In any combination of computing system of part, middleware component or front end component.Any form or the number of medium can be passed through
Digital data communicates (for example, communication network) and is connected with each other the component of system.The example of communication network includes: local area network
(Local Area Network, LAN), wide area network (Wide Area Network, WAN) and internet.
Computer system may include client and server.Client and server is generally off-site from each other and usually logical
Communication network is crossed to interact.By being run on corresponding computer and each other with the meter of client-server relation
Calculation machine program generates the relationship of client and server.
According to the technical solution of the embodiment of the present application, the efficiency of video generation can not only be improved, cost, Er Qiefeng are reduced
Rich video content, meets spectators to the diversified demand of the videos such as news report.Because using video content material abundant,
The technological means of various template is matched simultaneously, so overcoming the single technical problem of video content, and then reaches and enriches view
Frequency content meets spectators to the technical effect of the diversified demand of the videos such as news report.
It should be understood that various forms of processes illustrated above can be used, rearrangement increases or deletes step.Example
Such as, each step recorded in the application of this hair can be performed in parallel or be sequentially performed the order that can also be different and execute,
As long as it is desired as a result, being not limited herein to can be realized technical solution disclosed in the present application.
Above-mentioned specific embodiment does not constitute the limitation to the application protection scope.Those skilled in the art should be bright
White, according to design requirement and other factors, various modifications can be carried out, combination, sub-portfolio and substitution.It is any in the application
Spirit and principle within made modifications, equivalent substitutions and improvements etc., should be included within the application protection scope.
Claims (14)
1. a kind of video generation method characterized by comprising
It obtains video content material and video template, the video content material includes vivid, the described visual human of virtual portrait
The dynamic element and casting content of object;
The visual human is generated according to the dynamic element of the casting content, vivid, the described virtual portrait of the virtual portrait
The report clips of object;
The report clips of the virtual portrait are added in the video template, casting video is obtained.
2. the method according to claim 1, wherein the casting content includes casting text, the visual human
The dynamic element of object includes the lip of the virtual portrait dynamic, expression and movement, according to the casting content, the virtual portrait
The dynamic element of vivid, the described virtual portrait generates the report clips of the virtual portrait, comprising:
Casting pronunciation type is obtained according to the video template;
Casting voice is generated according to the casting text and casting pronunciation type;
The casting voice is input in lip movable model, the lip of the virtual portrait corresponding with the casting voice is exported
It is dynamic;
Obtain the expression and movement of the virtual portrait corresponding with the casting text;
Described according to vivid, described casting voice, the lip of the virtual portrait of the virtual portrait, dynamic, expression and movement are generated
The report clips of virtual portrait.
3. the method according to claim 1, wherein the report clips of the virtual portrait are added to the view
In frequency template, casting video is obtained, comprising:
The distributing position of the virtual portrait is obtained according to the video template;
The report clips of the virtual portrait are added in the distributing position of the virtual portrait, obtain casting video.
4. according to the method described in claim 2, it is characterized in that, the casting content further includes related to the casting text
Picture and/or video, the method also includes:
The first display area of picture relevant to the casting text and/or video is obtained according to the video template;
Picture relevant to the casting text and/or video are added to first display area.
5. according to the method described in claim 2, it is characterized in that, the casting text includes casting title, casting text, broadcasts
The date is reported, the method also includes:
The second display area of the casting text is obtained according to the video template, second display area includes described broadcasts
The second subregion and the third subregion on the casting date of first subregion of bid quotation topic, the casting text;
The casting title is added to first subregion, the casting text is added to second subregion, described
The casting date is added to the third subregion.
6. the method according to claim 1, wherein further include:
At least one of casting scene, head, run-out and clothes of the virtual portrait are obtained according to the video template.
7. a kind of video-generating device characterized by comprising
Material and template obtain module, and for obtaining video content material and video template, the video content material includes void
The dynamic element and casting content of vivid, the described virtual portrait of anthropomorphic object;
Report clips generation module, for according to the dynamic of vivid, the described virtual portrait of the casting content, the virtual portrait
The report clips of virtual portrait described in state Element generation;
Casting video generation module is broadcast for the report clips of the virtual portrait to be added in the video template
Report video.
8. device according to claim 7, which is characterized in that the casting content includes casting text, the visual human
The dynamic element of object includes that the dynamic lip of the virtual portrait, expression and movement, the report clips generation module include:
Casting pronunciation type acquiring unit, for obtaining casting pronunciation type according to the video template;
Speech production unit is broadcasted, for generating casting voice according to the casting text and casting pronunciation type;
Lip moves generation unit, for the casting voice to be input in lip movable model, exports corresponding with the casting voice
The lip of the virtual portrait is dynamic;
Expression and movement acquiring unit, for obtaining the expression and movement of the virtual portrait corresponding with the casting text;
Report clips generation unit, for vivid, the described lip for broadcasting voice, the virtual portrait according to the virtual portrait
Dynamic, expression and movement generate the report clips of the virtual portrait.
9. device according to claim 7, which is characterized in that the casting video generation module includes:
The distribution of the persons position acquisition unit, for obtaining the distributing position of the virtual portrait according to the video template;
Report clips adding unit, for the report clips of the virtual portrait to be added to the distributing position of the virtual portrait
In, obtain casting video.
10. device according to claim 9, which is characterized in that the casting content further includes and the casting text phase
The picture and/or video of pass, further includes:
First display area obtains module, for according to the video template obtain relevant to casting text picture and/
Or the first display area of video;
Picture and video adding module, for picture relevant to the casting text and/or video to be added to described first
Display area.
11. device according to claim 9, which is characterized in that the casting text include casting title, casting text,
Broadcast the date, further includes:
Second display area obtains module, for obtaining the second display area of the casting text according to the video template,
Second display area includes the first subregion of the casting title, casting second subregion of text and described
Broadcast the third subregion on date;
Text adding module is broadcasted, for the casting title to be added to first subregion, the casting text addition
To second subregion, the casting date is added to the third subregion.
12. device according to claim 7, which is characterized in that further include:
Template elements obtain module, for obtaining casting scene, head, run-out and the visual human according to the video template
At least one of clothes of object.
13. a kind of electronic equipment characterized by comprising
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
It manages device to execute, so that at least one described processor is able to carry out method of any of claims 1-6.
14. a kind of non-transitory computer-readable storage medium for being stored with computer instruction, which is characterized in that the computer refers to
It enables for making the computer perform claim require method described in any one of 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910700099.9A CN110381266A (en) | 2019-07-31 | 2019-07-31 | A kind of video generation method, device and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910700099.9A CN110381266A (en) | 2019-07-31 | 2019-07-31 | A kind of video generation method, device and terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110381266A true CN110381266A (en) | 2019-10-25 |
Family
ID=68257212
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910700099.9A Pending CN110381266A (en) | 2019-07-31 | 2019-07-31 | A kind of video generation method, device and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110381266A (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110677598A (en) * | 2019-09-18 | 2020-01-10 | 北京市商汤科技开发有限公司 | Video generation method and device, electronic equipment and computer storage medium |
CN110913259A (en) * | 2019-12-11 | 2020-03-24 | 百度在线网络技术(北京)有限公司 | Video playing method and device, electronic equipment and medium |
CN111698563A (en) * | 2020-05-06 | 2020-09-22 | 广东康云科技有限公司 | Content sending method and device based on AI virtual anchor and storage medium |
CN111696182A (en) * | 2020-05-06 | 2020-09-22 | 广东康云科技有限公司 | Virtual anchor generation system, method and storage medium |
CN112102449A (en) * | 2020-09-14 | 2020-12-18 | 北京百度网讯科技有限公司 | Virtual character generation method, virtual character display device, virtual character equipment and virtual character medium |
CN112233210A (en) * | 2020-09-14 | 2021-01-15 | 北京百度网讯科技有限公司 | Method, device, equipment and computer storage medium for generating virtual character video |
CN112860979A (en) * | 2021-02-09 | 2021-05-28 | 北京达佳互联信息技术有限公司 | Resource searching method, device, equipment and storage medium |
CN112906553A (en) * | 2021-02-09 | 2021-06-04 | 北京字跳网络技术有限公司 | Image processing method, apparatus, device and medium |
CN112995530A (en) * | 2019-12-02 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Video generation method, device and equipment |
CN112988100A (en) * | 2021-04-09 | 2021-06-18 | 上海掌门科技有限公司 | Video playing method and device |
CN113194348A (en) * | 2021-04-22 | 2021-07-30 | 清华珠三角研究院 | Virtual human lecture video generation method, system, device and storage medium |
CN113259778A (en) * | 2021-04-22 | 2021-08-13 | 清华珠三角研究院 | Method, system and storage medium for using virtual character for automatic video production |
CN113923515A (en) * | 2021-09-29 | 2022-01-11 | 马上消费金融股份有限公司 | Video production method and device, electronic equipment and storage medium |
CN114125491A (en) * | 2022-01-20 | 2022-03-01 | 阿里巴巴(中国)有限公司 | Virtual live broadcast control method and device |
CN114157897A (en) * | 2022-01-25 | 2022-03-08 | 阿里巴巴(中国)有限公司 | Virtual live broadcast control method and device |
CN114302153A (en) * | 2021-11-25 | 2022-04-08 | 阿里巴巴达摩院(杭州)科技有限公司 | Video playing method and device |
CN114339069A (en) * | 2021-12-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Video processing method and device, electronic equipment and computer storage medium |
CN114401431A (en) * | 2022-01-19 | 2022-04-26 | 中国平安人寿保险股份有限公司 | Virtual human explanation video generation method and related device |
CN114793300A (en) * | 2021-01-25 | 2022-07-26 | 天津大学 | Virtual video customer service robot synthesis method and system based on generation countermeasure network |
CN115022674A (en) * | 2022-05-26 | 2022-09-06 | 阿里巴巴(中国)有限公司 | Method and system for generating virtual character broadcast video and readable storage medium |
CN115129205A (en) * | 2022-08-05 | 2022-09-30 | 华中师范大学 | Course interaction method, system, server and storage medium based on virtual teacher |
WO2023045716A1 (en) * | 2021-09-24 | 2023-03-30 | 北京搜狗科技发展有限公司 | Video processing method and apparatus, and medium and program product |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102447839A (en) * | 2011-08-26 | 2012-05-09 | 深圳市万兴软件有限公司 | Quartz Composer-based video production method and device |
WO2013017918A1 (en) * | 2011-08-04 | 2013-02-07 | Sony Ericsson Mobile Communications Ab | Contact video generation system |
CN104780439A (en) * | 2014-01-15 | 2015-07-15 | 腾讯科技(深圳)有限公司 | Video processing method and device |
CN109118562A (en) * | 2018-08-31 | 2019-01-01 | 百度在线网络技术(北京)有限公司 | Explanation video creating method, device and the terminal of virtual image |
CN109377797A (en) * | 2018-11-08 | 2019-02-22 | 北京葡萄智学科技有限公司 | Virtual portrait teaching method and device |
CN109496295A (en) * | 2018-05-31 | 2019-03-19 | 优视科技新加坡有限公司 | Multimedia content generation method, device and equipment/terminal/server |
US20190171883A1 (en) * | 2015-10-20 | 2019-06-06 | Gopro, Inc. | System and method of providing recommendations of moments of interest within video clips post capture |
-
2019
- 2019-07-31 CN CN201910700099.9A patent/CN110381266A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013017918A1 (en) * | 2011-08-04 | 2013-02-07 | Sony Ericsson Mobile Communications Ab | Contact video generation system |
CN102447839A (en) * | 2011-08-26 | 2012-05-09 | 深圳市万兴软件有限公司 | Quartz Composer-based video production method and device |
CN104780439A (en) * | 2014-01-15 | 2015-07-15 | 腾讯科技(深圳)有限公司 | Video processing method and device |
US20190171883A1 (en) * | 2015-10-20 | 2019-06-06 | Gopro, Inc. | System and method of providing recommendations of moments of interest within video clips post capture |
CN109496295A (en) * | 2018-05-31 | 2019-03-19 | 优视科技新加坡有限公司 | Multimedia content generation method, device and equipment/terminal/server |
CN109118562A (en) * | 2018-08-31 | 2019-01-01 | 百度在线网络技术(北京)有限公司 | Explanation video creating method, device and the terminal of virtual image |
CN109377797A (en) * | 2018-11-08 | 2019-02-22 | 北京葡萄智学科技有限公司 | Virtual portrait teaching method and device |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110677598B (en) * | 2019-09-18 | 2022-04-12 | 北京市商汤科技开发有限公司 | Video generation method and device, electronic equipment and computer storage medium |
CN110677598A (en) * | 2019-09-18 | 2020-01-10 | 北京市商汤科技开发有限公司 | Video generation method and device, electronic equipment and computer storage medium |
CN112995530A (en) * | 2019-12-02 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Video generation method, device and equipment |
CN110913259A (en) * | 2019-12-11 | 2020-03-24 | 百度在线网络技术(北京)有限公司 | Video playing method and device, electronic equipment and medium |
CN111698563A (en) * | 2020-05-06 | 2020-09-22 | 广东康云科技有限公司 | Content sending method and device based on AI virtual anchor and storage medium |
CN111696182A (en) * | 2020-05-06 | 2020-09-22 | 广东康云科技有限公司 | Virtual anchor generation system, method and storage medium |
CN112102449A (en) * | 2020-09-14 | 2020-12-18 | 北京百度网讯科技有限公司 | Virtual character generation method, virtual character display device, virtual character equipment and virtual character medium |
CN112233210A (en) * | 2020-09-14 | 2021-01-15 | 北京百度网讯科技有限公司 | Method, device, equipment and computer storage medium for generating virtual character video |
CN112102449B (en) * | 2020-09-14 | 2024-05-03 | 北京百度网讯科技有限公司 | Virtual character generation method, virtual character display device, virtual character display equipment and virtual character display medium |
CN112233210B (en) * | 2020-09-14 | 2024-06-07 | 北京百度网讯科技有限公司 | Method, apparatus, device and computer storage medium for generating virtual character video |
CN114793300A (en) * | 2021-01-25 | 2022-07-26 | 天津大学 | Virtual video customer service robot synthesis method and system based on generation countermeasure network |
CN112906553A (en) * | 2021-02-09 | 2021-06-04 | 北京字跳网络技术有限公司 | Image processing method, apparatus, device and medium |
CN112860979A (en) * | 2021-02-09 | 2021-05-28 | 北京达佳互联信息技术有限公司 | Resource searching method, device, equipment and storage medium |
CN112860979B (en) * | 2021-02-09 | 2024-03-26 | 北京达佳互联信息技术有限公司 | Resource searching method, device, equipment and storage medium |
CN112988100A (en) * | 2021-04-09 | 2021-06-18 | 上海掌门科技有限公司 | Video playing method and device |
CN113194348A (en) * | 2021-04-22 | 2021-07-30 | 清华珠三角研究院 | Virtual human lecture video generation method, system, device and storage medium |
CN113259778A (en) * | 2021-04-22 | 2021-08-13 | 清华珠三角研究院 | Method, system and storage medium for using virtual character for automatic video production |
WO2023045716A1 (en) * | 2021-09-24 | 2023-03-30 | 北京搜狗科技发展有限公司 | Video processing method and apparatus, and medium and program product |
CN113923515A (en) * | 2021-09-29 | 2022-01-11 | 马上消费金融股份有限公司 | Video production method and device, electronic equipment and storage medium |
CN114302153A (en) * | 2021-11-25 | 2022-04-08 | 阿里巴巴达摩院(杭州)科技有限公司 | Video playing method and device |
CN114302153B (en) * | 2021-11-25 | 2023-12-08 | 阿里巴巴达摩院(杭州)科技有限公司 | Video playing method and device |
CN114339069A (en) * | 2021-12-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Video processing method and device, electronic equipment and computer storage medium |
CN114339069B (en) * | 2021-12-24 | 2024-02-02 | 北京百度网讯科技有限公司 | Video processing method, video processing device, electronic equipment and computer storage medium |
CN114401431A (en) * | 2022-01-19 | 2022-04-26 | 中国平安人寿保险股份有限公司 | Virtual human explanation video generation method and related device |
CN114401431B (en) * | 2022-01-19 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Virtual person explanation video generation method and related device |
CN114125491A (en) * | 2022-01-20 | 2022-03-01 | 阿里巴巴(中国)有限公司 | Virtual live broadcast control method and device |
CN114157897A (en) * | 2022-01-25 | 2022-03-08 | 阿里巴巴(中国)有限公司 | Virtual live broadcast control method and device |
WO2023143133A1 (en) * | 2022-01-25 | 2023-08-03 | 阿里巴巴(中国)有限公司 | Virtual live broadcast control method and apparatus |
CN115022674A (en) * | 2022-05-26 | 2022-09-06 | 阿里巴巴(中国)有限公司 | Method and system for generating virtual character broadcast video and readable storage medium |
CN115129205A (en) * | 2022-08-05 | 2022-09-30 | 华中师范大学 | Course interaction method, system, server and storage medium based on virtual teacher |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110381266A (en) | A kind of video generation method, device and terminal | |
US11450350B2 (en) | Video recording method and apparatus, video playing method and apparatus, device, and storage medium | |
CN110465097B (en) | Character vertical drawing display method and device in game, electronic equipment and storage medium | |
CN109168026A (en) | Instant video display methods, device, terminal device and storage medium | |
CN110636365B (en) | Video character adding method and device, electronic equipment and storage medium | |
CN111510753A (en) | Display apparatus and content display method | |
JP2023501832A (en) | Realization method, apparatus and related products for lens division | |
WO2022170958A1 (en) | Augmented reality-based display method and device, storage medium, and program product | |
CN113473207B (en) | Live broadcast method and device, storage medium and electronic equipment | |
CN110784753B (en) | Interactive video playing method and device, storage medium and electronic equipment | |
CN110458820A (en) | A kind of multimedia messages method for implantation, device, equipment and storage medium | |
CN113542624A (en) | Method and device for generating commodity object explanation video | |
CN112053370A (en) | Augmented reality-based display method, device and storage medium | |
JP2021006977A (en) | Content control system, content control method, and content control program | |
CN113660528A (en) | Video synthesis method and device, electronic equipment and storage medium | |
CN105263038A (en) | Method and apparatus for dynamic display of virtual auditorium | |
US20220308262A1 (en) | Method and apparatus of generating weather forecast video, electronic device, and storage medium | |
CN110647780A (en) | Data processing method and system | |
CN114302221A (en) | Virtual reality equipment and screen-casting media asset playing method | |
CN112017261B (en) | Label paper generation method, apparatus, electronic device and computer readable storage medium | |
CN106331525A (en) | Realization method for interactive film | |
CN116668733A (en) | Virtual anchor live broadcast system and method and related device | |
CN108271056A (en) | Video interaction method, subscription client, server and storage medium | |
CN116843802A (en) | Virtual image processing method and related product | |
KR20220116440A (en) | Augmented reality-based display method, device, storage medium and program product |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |
|
RJ01 | Rejection of invention patent application after publication |