CN109948409A - For generating the method, apparatus, equipment and computer readable storage medium of article - Google Patents
For generating the method, apparatus, equipment and computer readable storage medium of article Download PDFInfo
- Publication number
- CN109948409A CN109948409A CN201811458107.5A CN201811458107A CN109948409A CN 109948409 A CN109948409 A CN 109948409A CN 201811458107 A CN201811458107 A CN 201811458107A CN 109948409 A CN109948409 A CN 109948409A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- video
- frame
- title
- article
- 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
Abstract
This disclosure relates to method, apparatus, equipment and computer readable storage medium for generating article.This method comprises: determining the set of frame associated with object from source video；Set based on the frame generates target video, using the text as the article；And knowledge base associated with the source video is based at least partially on to generate the title of the article.In this way it is possible to generate the article with appropriate title and text.
Description
Technical field
Embodiment of the disclosure is generally related to information fusion, and more particularly relate to generate article method,
Device, equipment and computer readable storage medium.
Background technique
In current information stream, short video content accounting is continuously improved, and value also becomes increasing.Video content is raw
At more good information resources can not only be provided for user, and the article class that current automatic article generates can be enriched
Type.However, current automatic article generation technique is primarily directed to the article based on content of text, and the text in relation to video content
The generation technique of chapter requires study.
Summary of the invention
In accordance with an embodiment of the present disclosure, it provides a kind of for generating the scheme of article.
In the disclosure in a first aspect, providing a kind of method for article.This method comprises: being determined from source video
The set of frame associated with object；Set based on the frame generates target video, using the text as the article；And
Knowledge base associated with the source video is based at least partially on to generate the title of the article.
In the second aspect of the disclosure, provide a kind of for generating the device of article.The device includes: the first determining mould
Block is configured as determining the set of frame associated with object from source video；First generation module is configured as based on described
The set of frame generates target video, using the text as the article；And second generation module, it is configured as at least partly
The title of the article is generated based on knowledge base associated with the source video.
In the third aspect of the disclosure, a kind of electronic equipment is provided.The electronic equipment includes: one or more processing
Device；And memory, for storing one or more programs, when one or more of programs are by one or more of processing
Device executes, so that the method that electronic equipment realizes the first aspect according to the disclosure.
In the fourth aspect of the disclosure, a kind of computer-readable medium is provided, computer program is stored thereon with, the journey
The method of the first aspect according to the disclosure is realized when sequence is executed by processor.
It should be appreciated that content described in Summary be not intended to limit embodiment of the disclosure key or
Important feature, it is also non-for limiting the scope of the present disclosure.The other feature of the disclosure will become easy reason by description below
Solution.
Detailed description of the invention
It refers to the following detailed description in conjunction with the accompanying drawings, the above and other feature, advantage and aspect of each embodiment of the disclosure
It will be apparent.In the accompanying drawings, the same or similar appended drawing reference indicates the same or similar element, in which:
Fig. 1 is shown can be in the schematic diagram for the exemplary environments for wherein realizing embodiment of the disclosure；
Fig. 2 shows the flow charts according to the methods for generating article of some embodiments of the present disclosure；
Fig. 3 shows the block diagram of the device for generating article according to some embodiments of the present disclosure；And
Fig. 4 shows the block diagram that can implement the electronic equipment of some embodiments of the present disclosure.
Specific embodiment
Embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the certain of the disclosure in attached drawing
Embodiment, it should be understood that, the disclosure can be realized by various forms, and should not be construed as being limited to this
In the embodiment that illustrates, providing these embodiments on the contrary is in order to more thorough and be fully understood by the disclosure.It should be understood that
It is that being given for example only property of the accompanying drawings and embodiments effect of the disclosure is not intended to limit the protection scope of the disclosure.
As mentioned above, automatic article generation technique still lacks video content mainly for content of text at present
Auto.Embodiment of the disclosure provide it is a kind of for generating the scheme of article, to provide it is more abundant more
Good video feeds.Embodiment of the disclosure is specifically described below in conjunction with Fig. 1-Fig. 3.
Fig. 1 is shown can be in the schematic diagram for the exemplary environments 100 for wherein realizing embodiment of the disclosure.Such as Fig. 1 institute
Show, source video 102 can be various types of video resources, for example, film, TV play, cartoon, short-sighted frequency etc..Source video
It may include one or more objects in 102, for example, performer, role etc..The reality of the disclosure is described below with reference to " performer "
Apply example, it being understood, however, that embodiment of the disclosure also can be applied to other objects.Calculating equipment 110 can receive source view
Frequently 102 as input, and the article 104 for describing one or more objects in source video 102 is generated based on source video 102,
To convey information associated with the object.
As shown in Figure 1, article 104 includes title 106 and target video 108, wherein target video 108 is used as article 104
Text.Title 106 is the brief description to article 104, may include a phrase, a sentence or one section of word etc..Mesh
Marking video 108 may include frame associated with one or more objects in source video 102, and be formed with certain forms tissue.
Fig. 2 shows the flow charts according to the methods 200 for generating article of some embodiments of the present disclosure.Method
200 for example can at least partly be executed by the calculating equipment 110 in Fig. 1.It should be appreciated that method 200 can also be any by other
It is suitable to calculate equipment or cloud server to execute.
202, the set of frame associated with one or more objects is determined from source video 102.It can be by various
Approach obtains source video 102.Source video or video resource can store in distributed file system, and can be real
When, periodically or be periodically updated.The information of description video resource can be stored in the form of video resource information table, and
And query interface to video resource can be provided.For example, can timing or periodically scan for video resource information table to obtain
Accessible video resource is taken, for example, the video resource of recent renewal.In this way it is possible to be directed to nearest video resource
Article is generated, to have timeliness.
In some embodiments, the object in source video 102 can be identified by video content analysis (VCA), and
The text informations such as subtitle in source video 102 can also be identified, for example, by means of optical character identification (OCR) technology.
In this way it is possible to the recognition of face information and text information of each frame of source video 102 be obtained, for further locating
Reason.In some embodiments, in order to improve the efficiency of video content analysis, source video 102 can be divided into multiple segments, and
And video content analysis is executed to each segment respectively.
For example, video content analysis can be realized beyond the clouds, for example, the video clip after segmentation can be uploaded to cloud
End, carries out video content analysis by cloud.Alternatively, the segmentation of video can also be executed by cloud and to the video of each segment
Content analysis.Furthermore it is possible to timing scan database, to obtain the resource parsed, for example, obtaining in the video of each segment
Hold analysis information, for example, recognition of face information and/or text information.In some embodiments, it can only obtain untreated
The video content analysis information of segment, and it is handled.
In some embodiments, frame associated with one or more performers can be extracted based on recognition of face information.
For example, if the face information identified in a frame and the similarity of some performer are greater than predetermined threshold, then it is assumed that this frame
It is associated with the performer.In this way it is possible to range or the period of all frames where the performer be determined, so that it is determined that going out
The set of frame associated with the performer.The set of frame associated with multiple performers can be extracted in a similar manner.
204, the set based on frame generates target video 108, using the text as article 104.For example, frame can be based on
Set in time sequencing of each frame in video 102 generate target video 108.It alternatively, can also be by these frames
Sequence sorted with predefined rule, to generate target video 108.Target video 108 generated may be used as article just
Text.
By identifying the objects such as the star in video resource, and using star as dimension effectively organizing video content,
The organisational issues of video content can at least be partially solved, have made video content that there is certain reasonability.
206, knowledge base associated with source video is based at least partially on to generate the title of article.For example, can be with
Clear and coherent, interesting mark is generated from the proper knowledge of selection in knowledge base (for example, video comments library) (for example, comment)
Topic.As another example, multiple comments be can choose, and these comments are combined to generate title.Knowledge base (for example,
Video comments library) it can be a part of knowledge mapping.
In some embodiments, can from knowledge base, object-based mark (for example, name of performer) come obtain with
The associated comment of object.For example, comment relevant to the name of the performer can be inquired from video comments library.Then, base
It is commented in these to generate title.In some embodiments, title can be generated by predefined template.It can will be from commenting
The information obtained in is filled into the respective field of template, to generate title.
In some embodiments, source video 102 can be video display video, for example, film, TV etc..In these embodiments
In, message of film and TV associated with object can be obtained from video display library, for example, director, role name etc..Video display library is also possible to
A part of knowledge mapping, and the message of film and TV such as performer and video display title etc. are associated.It is then possible to object-based mark
(for example, name of performer) and message of film and TV are known to obtain comment associated with object.For example, can be from video comments library
Selection with the associated comment such as the name of performer and the performer institute role name, with acquisition it is most related to video clipping
Comment, to generate the title being more adapted to video clipping.
In addition, text information associated with object is extracted from the set of frame, for example, the text information in subtitle.It can
Title is generated to be based further on the text information of extraction.For example, these text informations can be embodied directly in title,
It can also search and selection comment in knowledge base (for example, video comments library) based on these text informations.
In some embodiments, it can be selected by information filtering model in knowledge base (for example, video comments library)
A part comment, and title is generated according to this part comment of selection.Information filtering model can be based on being currently known
Or the various methods of exploitation are realized in the future, such as may include closing scale, smoothness model and/or interest model.It closes
Scale can be the information for filtering some regulations for not meeting laws and regulations or the code of ethic.It can for example, closing scale
To include yellow inverse model, yellow inverse model can filter out some yellow informations, reaction information etc. by modes such as keywords, with true
It protects the title generated and meets regulation.Smoothness model is determined for the score of the clear and coherent degree of the title generated, to ensure to give birth to
At the title of enough smoothnesses.Interest model can be used for assessing the entertaining degree of the title of generation, have higher interest to obtain
The title of taste.It should be appreciated that yellow inverse model, smoothness model and interest model can pass through any of or future
The model of exploitation realizes that the disclosure is unrestricted herein.Alternatively or additionally, video can also be commented using other models
It is screened by the comment in library.
In some embodiments, other than title 106 and target video 108, article 104 can also include other texts
Information, these text informations can be by manually being edited.
In accordance with an embodiment of the present disclosure, can be generated with the matched title of target video, in order to understand video content, and
And the title generated in this way has readable, interesting property, can attract more click volumes.
Fig. 3 shows according to an embodiment of the present disclosure for generating the schematic diagram of the device 300 of article.Device 300 wraps
The first determining module 302 is included, is configured as determining the set of frame associated with object from source video.
In some embodiments, the first determining module 302 includes: segmentation module, is configured as dividing the source video
For multiple segments；And second determining module, it is associated with the object to be configured to the determination in the multiple segment
Frame, for determining the set of the frame.
Device 300 further includes the first generation module 304, is configured as the set based on the frame and generates target video, with
Text as the article.
In some embodiments, the first generation module 304 includes: the 6th generation module, is configured as based on the frame
Time sequencing of each frame in the source video in set generates the target video.
Device 300 further includes the second generation module 306, is configured as being based at least partially on associated with the source video
Knowledge base generate the title of the article.
In some embodiments, the second generation module 306 includes: the first acquisition module, is configured as from the knowledge base
In, knowledge associated with the object is obtained based on the mark of the object；And third generation module, it is configured as base
The title is generated in the knowledge.
In some embodiments, the source video is video display video, and the first acquisition module includes: the second acquisition mould
Block is configured as obtaining message of film and TV associated with the object from video display library；And third obtains module, is configured as
Knowledge associated with the object is obtained based on the mark of the object and the message of film and TV.
In some embodiments, the second generation module 306 includes: selecting module, is configured as through information filtering model
The knowledge in the knowledge base is filtered, to select a part of the knowledge in the knowledge base；And the 4th generation module, quilt
A part of the knowledge of selection is configured to generate the title.
In some embodiments, device 300 further includes extraction module, is configured as extraction and institute from the set of the frame
State the associated text information of object.And the second generation module 306 includes: the 5th generation module, is configured as based on described
Text information and the knowledge base generate the title.
Fig. 4 shows the schematic block diagram that can be used to implement the equipment 400 of embodiment of the disclosure.Such as Fig. 1 institute
The calculating equipment 110 shown can be realized by equipment 400.As shown in figure 4, equipment 400 includes central processing unit (CPU) 401,
It can according to the computer program instructions being stored in read-only memory (ROM) 402 or from storage unit 408 be loaded into
Machine accesses the computer program instructions in memory (RAM) 403, to execute various movements appropriate and processing.In RAM 403
In, it can also store equipment 400 and operate required various programs and data.CPU 401, ROM 402 and RAM 403 pass through bus
404 are connected with each other.Input/output (I/O) interface 405 is also connected to bus 404.
Multiple components in equipment 400 are connected to I/O interface 405, comprising: input unit 406, such as keyboard, mouse etc.；
Output unit 407, such as various types of displays, loudspeaker etc.；Storage unit 408, such as disk, CD etc.；And it is logical
Believe unit 409, such as network interface card, modem, wireless communication transceiver etc..Communication unit 409 allows equipment 400 by such as
The computer network of internet and/or various telecommunication networks exchange information/data with other equipment.
Each process as described above and processing, such as method 200 can be executed by processing unit 401.For example, one
In a little embodiments, method 200 can be implemented as computer software programs, be tangibly embodied in machine readable media, such as
Storage unit 408.In some embodiments, some or all of of computer program can be via ROM 402 and/or communication unit
Member 409 and be loaded into and/or be installed in equipment 400.When computer program is loaded into RAM 403 and is executed by CPU 401
When, the one or more steps of method as described above 200 can be executed.Alternatively, in other embodiments, CPU 401 can
By by other it is any it is appropriate in a manner of (for example, by means of firmware) be configured as execution method 200.
The disclosure can be method, equipment, system and/or computer program product.Computer program product may include
Computer readable storage medium, containing the computer-readable program instructions for executing various aspects of the disclosure.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure
Face.
Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/
Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processing unit of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable numbers
When being executed according to the processing unit of processing unit, produces and provided in one or more boxes in implementation flow chart and/or block diagram
Function action device.These computer-readable program instructions can also be stored in a computer-readable storage medium, this
A little instructions so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, be stored with finger
The computer-readable medium of order then includes a manufacture comprising the one or more side in implementation flow chart and/or block diagram
The instruction of the various aspects of function action specified in frame.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and
It is not limited to the disclosed embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or improvement to the technology in market for best explaining each embodiment, or make the art
Other those of ordinary skill can understand various embodiments disclosed herein.
Claims (16)
1. a kind of method for generating article, comprising:
The set of frame associated with object is determined from source video；
Set based on the frame generates target video, using the text as the article；And
Knowledge base associated with the source video is based at least partially on to generate the title of the article.
2. according to the method described in claim 1, wherein generating the title and including:
From the knowledge base, knowledge associated with the object is obtained based on the mark of the object；And
The title is generated based on the knowledge.
3. according to the method described in claim 2, wherein the source video is video display video, and obtaining the knowledge and including:
Message of film and TV associated with the object is obtained from video display library；And
Knowledge associated with the object is obtained based on the mark of the object and the message of film and TV.
4. according to the method described in claim 1, wherein generating the title and including:
The knowledge in the knowledge base is filtered, by information filtering model to select one of the knowledge in the knowledge base
Point；And
The title is generated based on a part of the knowledge of selection.
5. according to the method described in claim 1, further including extracting text associated with the object from the set of the frame
Word information；And
It is based in part on the knowledge base wherein at least to generate the title and include:
The title is generated based on the text information and the knowledge base.
6. according to the method described in claim 1, wherein determining that the set of the frame includes:
The source video is divided into multiple segments；And
Frame associated with the object is determined in the multiple segment respectively, for determining the set of the frame.
7. according to the method described in claim 1, wherein generating the target video and including:
The target video is generated based on time sequencing of each frame in the source video in the set of the frame.
8. a kind of for generating the device of article, comprising:
First determining module is configured as determining the set of frame associated with object from source video；
First generation module is configured as the set based on the frame and generates target video, using the text as the article；With
And
Second generation module is configured as being based at least partially on knowledge base associated with the source video to generate the text
The title of chapter.
9. device according to claim 8, wherein second generation module includes:
First obtains module, is configured as from the knowledge base, is obtained based on the mark of the object and the object phase
Associated knowledge；And
Third generation module is configured as generating the title based on the knowledge.
10. device according to claim 9, wherein the source video is video display video, and described first obtains module
Include:
Second obtains module, is configured as obtaining message of film and TV associated with the object from video display library；And
Third obtains module, is configured as obtaining based on the mark of the object and the message of film and TV related to the object
The knowledge of connection.
11. device according to claim 8, wherein second generation module includes:
Selecting module is configured as filtering the knowledge in the knowledge base by information filtering model, to select the knowledge
A part of knowledge in library；And
4th generation module is configured as generating the title based on a part of the knowledge of selection.
12. device according to claim 8, further includes:
Extraction module is configured as extracting text information associated with the object from the set of the frame；And
Wherein second generation module includes:
5th generation module is configured as generating the title based on the text information and the knowledge base.
13. device according to claim 8, wherein first determining module includes:
Divide module, is configured as the source video being divided into multiple segments；And
Second determining module is configured to determine frame associated with the object in the multiple segment, to be used for
Determine the set of the frame.
14. device according to claim 8, wherein first generation module includes:
6th generation module, be configured as time sequencing of each frame in the source video in the set based on the frame come
Generate the target video.
15. a kind of electronic equipment, the electronic equipment include:
One or more processors；And
Memory, for storing one or more programs, when one or more of programs are by one or more of processors
When execution, so that the electronic equipment realizes method according to any one of claims 1-7.
16. a kind of computer readable storage medium is stored thereon with computer program, realization when described program is executed by processor
Method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811458107.5A CN109948409A (en) | 2018-11-30 | 2018-11-30 | For generating the method, apparatus, equipment and computer readable storage medium of article |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811458107.5A CN109948409A (en) | 2018-11-30 | 2018-11-30 | For generating the method, apparatus, equipment and computer readable storage medium of article |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109948409A true CN109948409A (en) | 2019-06-28 |
Family
ID=67006430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811458107.5A Pending CN109948409A (en) | 2018-11-30 | 2018-11-30 | For generating the method, apparatus, equipment and computer readable storage medium of article |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948409A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114363714A (en) * | 2021-12-31 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Title generation method, title generation device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719167A (en) * | 2010-01-15 | 2010-06-02 | 北京暴风网际科技有限公司 | Interactive movie searching method |
| CN102799637A (en) * | 2012-06-27 | 2012-11-28 | 北京邮电大学 | Method for automatically generating main character abstract in television program |
| CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
| CN106845390A (en) * | 2017-01-18 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Video title generation method and device |
| CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating article |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
| CN108829881A (en) * | 2018-06-27 | 2018-11-16 | 深圳市腾讯网络信息技术有限公司 | video title generation method and device |
| CN108882057A (en) * | 2017-05-09 | 2018-11-23 | 北京小度互娱科技有限公司 | Video abstraction generating method and device |
-
2018
- 2018-11-30 CN CN201811458107.5A patent/CN109948409A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719167A (en) * | 2010-01-15 | 2010-06-02 | 北京暴风网际科技有限公司 | Interactive movie searching method |
| CN102799637A (en) * | 2012-06-27 | 2012-11-28 | 北京邮电大学 | Method for automatically generating main character abstract in television program |
| CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
| CN106845390A (en) * | 2017-01-18 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Video title generation method and device |
| CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating article |
| CN108882057A (en) * | 2017-05-09 | 2018-11-23 | 北京小度互娱科技有限公司 | Video abstraction generating method and device |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
| CN108829881A (en) * | 2018-06-27 | 2018-11-16 | 深圳市腾讯网络信息技术有限公司 | video title generation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114363714A (en) * | 2021-12-31 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Title generation method, title generation device and storage medium |
| CN114363714B (en) * | 2021-12-31 | 2024-01-05 | 阿里巴巴（中国）有限公司 | Title generation method, title generation device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052577B (en) | Universal text content mining method, device, server and storage medium | |
| JP7123122B2 (en) | Navigating Video Scenes Using Cognitive Insights | |
| CN111582241B (en) | Video subtitle recognition method, device, equipment and storage medium | |
| CN108959256B (en) | Short text generation method and device, storage medium and terminal equipment | |
| CN101639943B (en) | Method and apparatus for producing animation | |
| US20180307667A1 (en) | Travel guide generating method and system | |
| CN110121116A (en) | Video generation method and device | |
| US20190087780A1 (en) | System and method to extract and enrich slide presentations from multimodal content through cognitive computing | |
| JP2019511036A (en) | System and method for linguistic feature generation across multiple layer word representations | |
| US20200090246A1 (en) | Media enhancement with customized add-on content | |
| US10180939B2 (en) | Emotional and personality analysis of characters and their interrelationships | |
| CN107767871A (en) | Text display method, terminal and server | |
| US20150248409A1 (en) | Sorting and displaying documents according to sentiment level in an online community | |
| CN102436483A (en) | Video advertisement detecting method based on explicit type sharing subspace | |
| CN112836487B (en) | Automatic comment method and device, computer equipment and storage medium | |
| CN112511854A (en) | Live video highlight generation method, device, medium and equipment | |
| CN109754783A (en) | Method and apparatus for determining the boundary of audio sentence | |
| CN110414004A (en) | A kind of method and system that core information extracts | |
| US20220301579A1 (en) | Automatic video tagging | |
| CN111738016A (en) | Multi-intention recognition method and related equipment | |
| CN109255035A (en) | Method and apparatus for constructing knowledge mapping | |
| CN109948409A (en) | For generating the method, apparatus, equipment and computer readable storage medium of article | |
| US11010562B2 (en) | Visual storyline generation from text story | |
| CN104504104A (en) | Picture material processing method and device for search engine, and search engine | |
| CN115273856A (en) | Voice recognition method and device, electronic equipment and 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 |