CN107977359A - A kind of extracting method of video display drama scene information - Google Patents
A kind of extracting method of video display drama scene information Download PDFInfo
- Publication number
- CN107977359A CN107977359A CN201711202819.6A CN201711202819A CN107977359A CN 107977359 A CN107977359 A CN 107977359A CN 201711202819 A CN201711202819 A CN 201711202819A CN 107977359 A CN107977359 A CN 107977359A
- Authority
- CN
- China
- Prior art keywords
- scene
- character string
- information
- character
- video display
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/263—Language identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses a kind of extracting method of video display drama scene information, it is related to technical field of software development, by reading video display drama content line by line, automatically identify the video display drama content row with scene description, recycling is based on the matched mode of dictionary, the essential information such as the accurate play extracted in scene information, place, the description of interior outfield, time, weather, high priest.When can solve the scene analysis that video display drama is assessed using the method for the present invention, manual identified accuracy is not high, the problem of losing time, quick and precisely can identify and extract the essential information in scene, improves the quality and speed of the assessment Scene analysis of video display drama.
Description
Technical field
The present invention relates to technical field of software development, more particularly to a kind of extracting method of video display drama scene information.
Background technology
Analyzed involved in the analysis and evaluation of video display drama to scene information, scene information is dispersed in video display drama
Rong Zhong, is described in a line or three rows.Scene information generally comprises play, place, the description of interior outfield, time, weather, master
Want the essential informations such as personage.
Analysis in the analysis and evaluation of video display drama to scene information is mainly by based on manual identified and analysis, there are following
Difficulty：
A. general TV play often collects 30-50 scene, about 150 scenes of whole movie, by TV play, the type of film,
The Factors Factors such as duration, plot, scene number may be more or less, artificial counting elapsed time during analysis.
B. the essential information sequencing included in scene information is not fixed, and may be paused between essential information by comma
Number, fullstop, colon, TAB tabs etc. separate, without the form of standard.
C. write a play when writing video display drama, may be caused due to modification or other reasons, the play in scene information is not
Continuous or repetition, this brings certain difficulty to the statistical analysis of scene.
The content of the invention
An embodiment of the present invention provides a kind of extracting method of video display drama scene information, can solve to deposit in the prior art
The problem of.
The present invention provides a kind of extracting method of video display drama scene information, this method comprises the following steps：
Step 1, inside and outside, time, the essential information dictionary of weather scene description are established；
Step 2, complete video display drama is read, deletes blank line, the front and rear space character of often row content is removed, based on place
Video display drama content after reason carries out scene content identification and extraction；
Step 3,500 characters before reading video display drama, judge video display drama scene description using single file describing mode also
Three row describing modes, if first Chinese character that continuous three row occurs in video display drama content be scape, when, three Chinese characters of people it
One, and scape, when, in the case that three Chinese characters of people all occur once, the describing mode of scene is three row describing modes, is not three rows
Describing mode is single file describing mode；
Step 4, initialize movie and television play one's own profession and read sequence number N, N=1 is set, an empty list L is initialized, for by successively
Order stores identified scene information；
Step 5, judge whether N exceedes video display drama head office number, if it is perform step 9, otherwise read video display drama
Nth row content, is character string S；
Step 6, judge whether character string S first characters are Chinese and English numerical character, and if it is the row is probably field
Scene describing, performs step 7, otherwise performs step 8；
Step 7, the scene description mode obtained according to step 3, using different scene information identification and extracting method；
Step 8, according to judging result in step 6, step 7, next line is set to read this position of movie and television play；
Step 9, list L is the whole scene informations for identifying and extracting from video display drama, by list L storages to text
In part, database, identification and extraction scene information processing are completed.
The extracting method of a kind of video display drama scene information in the embodiment of the present invention, by reading line by line in video display drama
Hold, automatically identify the video display drama content row with scene description, recycling is based on the matched mode of dictionary, accurately extracts field
The essential informations such as play, place, the description of interior outfield, time, weather, high priest in scape information, and reach following effect：
A. automatic identification video display drama Scene describes.
B. the essential information in scene information is accurately extracted.
C. the video display drama scene analysis time is saved, improves scene analysis efficiency and accuracy.
Embodiment
The technical solution in the embodiment of the present invention will be clearly and completely described below, it is clear that described implementation
Example is only part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this area is common
Technical staff's all other embodiments obtained without making creative work, belong to the model that the present invention protects
Enclose.
An embodiment of the present invention provides a kind of extracting method of video display drama scene information, this method comprises the following steps：
Step 1, inside and outside, time, the essential information dictionary of weather scene description are established.
Step 2, complete video display drama is read, deletes blank line, the front and rear space character of often row content is removed, based on place
Video display drama content after reason carries out scene content identification and extraction.
Step 3,500 characters before reading video display drama, judge video display drama scene description using single file describing mode also
Three row describing modes, if first Chinese character that continuous three row occurs in video display drama content be scape, when, three Chinese characters of people it
One, and scape, when, in the case that three Chinese characters of people all occur once, the describing mode of scene is three row describing modes, is not three rows
Describing mode is single file describing mode.
Step 4, initialize movie and television play one's own profession and read sequence number N, N=1 is set, an empty list L is initialized, for by successively
Order stores identified scene information.
Step 5, judge whether N exceedes video display drama head office number, if it is perform step 9, otherwise read video display drama
Nth row content, is character string S.
Step 6, judge whether character string S first characters are Chinese and English numerical character, and if it is the row is probably field
Scene describing, performs step 7, otherwise performs step 8.
Step 7, the scene description mode obtained according to step 3, using different scene information identification and extracting method：
Extracting method when video display drama is single file scene description mode below use：
A. the comma in character string S, pause mark, fullstop, colon, TAB tabs are replaced with into space character, forms character string
S0。
B. using space as separator, character string S0 contents are split in character string dimension A.
C. array A is traveled through, reads the element in character string dimension A one by one, and record the scene essential information number identified
T is measured, performs following operation：
C1. when the element content in character string dimension A is：X field (X is Chinese and English numeral) or first character are Sino-British
Wen Shi, this element describe the play information of scene, take following extracting method：
Situation 1：Element content is X field, the play information using X as scene.
Situation 2：Element content is numeral, the play information using numeral as scene.
Situation 3：Element content is numeral 1- numerals 2 (numeral 1 is connected among numeral 2 with Chinese and English minus sign), by numeral 2
Play information as scene.
After the play information for identifying scene, T values are increased by 1, and the element is removed into out character string dimension A.
C2. when the inside and outside description dictionary in step 1 of the element in character string dimension A, using element as in scene
External information S1, after the inside and outside scene information for identifying scene, increases by 1, and the element is removed out character string dimension A by T values.
C3. when the time when the element in character string dimension A in step 1 describes dictionary, using element as scene when
Between description information S2, after the time description information for identifying scene, T values are increased by 1, and the element is removed into out character string dimension
A。
C4. when the weather when the element in character string dimension A in step 1 describes dictionary, the day using element as scene
Gas description information S3, after the weather description information for identifying scene, increases by 1, and the element is removed out character string dimension by T values
A。
D. surplus element connects to form character string using space in array A, the place using the character string as scene
Information S4, increases by 1 by T values.
E. when the scene essential information quantity T identified is more than or equal to 2, character string S, will as scene description information row
Character string S1, S2, S3 and S4 content are put into one and include inside and outside scene properties, time attribute, Weather property, site attribute respectively
Object in, which is saved in the list L that step 4 creates；When T is less than 2, character string S is retouched not as scene information
State row.
Extracting method when video display drama is three row scene description mode below use：
A. first Chinese character for judging to occur in character string S whether be scape, when, one in three Chinese characters of people, if not
It is that then current line is not scene description, continues to execute step 8；Otherwise subsequent treatment is continued to execute.
B. judge character string S be expert at be followed by it is no also there are 2 row video display drama contents, if it does not exist, then current line
It is not scene description, continues to execute step 8；Otherwise subsequent treatment is continued to execute.
C. note character string S next lines content is S5, and the second row content is S6 after character string S, judge respectively character string S, S5,
The Chinese character of the appearance of S6 first whether be scape, when, people, and scape, when, each of three Chinese characters of people occur once, if conditions are not met,
Then current line is not scene description, continues to execute step 8；Otherwise subsequent treatment is continued to execute.
D. following extracting method is used in character string S, S5, S6 respectively：
Situation 1：When the Chinese character of the appearance of character string first be " scape ", interception character first Chinese character behind the scape
String is until end of string, the location information P1 of the new character strings of formation as scene information.
Situation 2：When the Chinese character of the appearance of character string first be " people ", interception character first Chinese character behind the people
String is until end of string, the people information P2 of the new character strings of formation as scene information.
Situation 3：The Chinese character of the appearance of character string first for " when " when, since when behind first Chinese character intercept character
String forms new character string, following processing is done for new character strings until end of string：
(1) character in character string in addition to Chinese character is replaced with into space and deletes space before and after character string, form character
String S7.
(2) using space as separator, the content of character string S7 is split in character string dimension B.
(3) array B is traveled through, reads the element in character string dimension B one by one, performs following identification operation：
When in the inside and outside description dictionary that element occurs in step 1, the inside and outside scene information P3 using element as scene.
When describing in dictionary the time that element occurs in step 1, the time description information P4 using element as scene.
E. the content of character string P1, P2, P3, P4 are put into one respectively and include site attribute, character attribute, inside and outside scene
Attribute, time attribute object in, which is saved in the list L that step 4 creates.
Step 8, according to judging result in step 6, step 7, next line is set to read this position of movie and television play：
When it is not scene that step 6, which judges character string S, after N=N+1 is set, jumps to step 5 and continue to execute.
When step 7 judges that character string S describes scene mode for single file, after N=N+1 is set, jumps to step 5 and continue to hold
OK.
When step 7 judges that character string S describes scene mode for three rows, after N=N+3 is set, jumps to step 5 and continue to hold
OK.
When it is not scene that step 7, which judges character string S, after N=N+1 is set, jumps to step 5 and continue to execute.
Step 9, list L is the whole scene informations for identifying and extracting from video display drama, by list L storages to text
Part, in database, identification and extraction scene information processing are completed.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or square frame in journey and/or square frame and flowchart and/or the block diagram.These computer programs can be provided
The processors of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices, which produces, to be used in fact
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided and is used for realization in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a square frame or multiple square frames.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know basic creation
Property concept, then can make these embodiments other change and modification.So appended claims be intended to be construed to include it is excellent
Select embodiment and fall into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and scope.In this way, if these modifications and changes of the present invention belongs to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these modification and variations.
Claims (4)
1. a kind of extracting method of video display drama scene information, it is characterised in that this method comprises the following steps：
Step 1, inside and outside, time, the essential information dictionary of weather scene description are established；
Step 2, complete video display drama is read, deletes blank line, the front and rear space character of often row content is removed, after processing
Video display drama content carry out scene content identification and extraction；
Step 3,500 characters before reading video display drama, judge that video display drama scene description uses single file describing mode or three
Row describing mode, if first Chinese character that continuous three row occurs in video display drama content be scape, when, one of three Chinese characters of people,
And scape, when, in the case that three Chinese characters of people all occur once, the describing mode of scene is three row describing modes, is not that three rows are retouched
The mode of stating is single file describing mode；
Step 4, initialize movie and television play one's own profession and read sequence number N, N=1 is set, an empty list L is initialized, for sequentially
Store identified scene information；
Step 5, judge whether N exceedes video display drama head office number, if it is perform step 9, otherwise read video display drama Nth row
Content, is character string S；
Step 6, judge whether character string S first characters are Chinese and English numerical character, and if it is the row is probably that scene is retouched
State, perform step 7, otherwise perform step 8；
Step 7, the scene description mode obtained according to step 3, using different scene information identification and extracting method；
Step 8, according to judging result in step 6, step 7, next line is set to read this position of movie and television play；
Step 9, list L is whole scene informations for identifying and extract from video display drama, by list L storages to file,
In database, identification and extraction scene information processing are completed.
2. the extracting method of video display drama scene information as claimed in claim 1, it is characterised in that work as movie and television play in step 7
Extracting method when this is single file scene description mode below use：
A. the comma in character string S, pause mark, fullstop, colon, TAB tabs are replaced with into space character, forms character string S0；
B. using space as separator, character string S0 contents are split in character string dimension A；
C. array A is traveled through, reads the element in character string dimension A one by one, and records the scene essential information quantity T identified,
Perform following operation：
C1. when the element content in character string dimension A is：When X field or first character are Chinese and English, this element describes field
The play information of scape, takes following extracting method：
Situation 1：Element content is X field, the play information using X as scene；
Situation 2：Element content is numeral, the play information using numeral as scene；
Situation 3：Element content is numeral 1- numerals 2, the play information using numeral 2 as scene；
After the play information for identifying scene, T values are increased by 1, and the element is removed into out character string dimension A；
C2. when the inside and outside description dictionary in step 1 of the element in character string dimension A, the inside and outside letter using element as scene
S1 is ceased, after the inside and outside scene information for identifying scene, by T values increase by 1, and the element is removed into out character string dimension A；
C3. when the time when the element in character string dimension A in step 1 describes dictionary, retouched element as the time of scene
Information S2 is stated, after the time description information for identifying scene, T values are increased by 1, and the element is removed into out character string dimension A；
C4. when the weather when the element in character string dimension A in step 1 describes dictionary, retouched element as the weather of scene
Information S3 is stated, after the weather description information for identifying scene, T values are increased by 1, and the element is removed into out character string dimension A；
D. surplus element connects to form character string using space in array A, the location information using the character string as scene
S4, increases by 1 by T values；
E. when the scene essential information quantity T identified is more than or equal to 2, character string S is as scene description information row, by character
String S1, S2, S3 and S4 content is put into one and includes inside and outside scene properties, time attribute, Weather property, pair of site attribute respectively
As in, which is saved in the list L that step 4 creates；When T is less than 2, character string S is not as scene information lines of description.
3. the extracting method of video display drama scene information as claimed in claim 1, it is characterised in that work as movie and television play in step 7
Extracting method when this is three row scene description mode below use：
A. first Chinese character for judging to occur in character string S whether be scape, when, one in three Chinese characters of people, if it is not, then
Current line is not scene description, continues to execute step 8；Otherwise subsequent treatment is continued to execute；
B. judge character string S be expert at be followed by it is no also there are 2 row video display drama contents, if it does not exist, then current line is not
Scene description, continues to execute step 8；Otherwise subsequent treatment is continued to execute；
C. note character string S next lines content is S5, and the second row content is S6 after character string S, judges character string S, S5, S6 the respectively
The Chinese character of one appearance whether be scape, when, people, and scape, when, each of three Chinese characters of people occur once, if conditions are not met, then when
It is not scene description to move ahead, and continues to execute step 8；Otherwise subsequent treatment is continued to execute；
D. following extracting method is used in character string S, S5, S6 respectively：
Situation 1：When the Chinese character of the appearance of character string first be " scape ", interception character string is straight first Chinese character behind the scape
To end of string, the location information P1 of the new character strings of formation as scene information；
Situation 2：When the Chinese character of the appearance of character string first be " people ", interception character string is straight first Chinese character behind the people
To end of string, the people information P2 of the new character strings of formation as scene information；
Situation 3：The Chinese character of the appearance of character string first for " when " when, since when behind first Chinese character to intercept character string straight
To end of string, new character string is formed, following processing is done for new character strings：
(1) character in character string in addition to Chinese character is replaced with into space and deletes space before and after character string, form character string S7；
(2) using space as separator, the content of character string S7 is split in character string dimension B；
(3) array B is traveled through, reads the element in character string dimension B one by one, performs following identification operation：
When in the inside and outside description dictionary that element occurs in step 1, the inside and outside scene information P3 using element as scene；
When describing in dictionary the time that element occurs in step 1, the time description information P4 using element as scene；
E. the content of character string P1, P2, P3, P4 are put into one respectively and include site attribute, character attribute, inside and outside scene category
Property, time attribute object in, which is saved in the list L that step 4 creates.
4. the extracting method of video display drama scene information as claimed in claim 1, it is characterised in that step 8 specifically includes：
When it is not scene that step 6, which judges character string S, after N=N+1 is set, jumps to step 5 and continue to execute；
When step 7 judges that character string S describes scene mode for single file, after N=N+1 is set, jumps to step 5 and continue to execute；
When step 7 judges that character string S describes scene mode for three rows, after N=N+3 is set, jumps to step 5 and continue to execute；
When it is not scene that step 7, which judges character string S, after N=N+1 is set, jumps to step 5 and continue to execute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711202819.6A CN107977359B (en) | 2017-11-27 | 2017-11-27 | Method for extracting scene information of movie and television scenario |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711202819.6A CN107977359B (en) | 2017-11-27 | 2017-11-27 | Method for extracting scene information of movie and television scenario |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107977359A true CN107977359A (en) | 2018-05-01 |
| CN107977359B CN107977359B (en) | 2021-03-30 |
Family
ID=62011649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711202819.6A Active CN107977359B (en) | 2017-11-27 | 2017-11-27 | Method for extracting scene information of movie and television scenario |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977359B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191010A (en) * | 2019-12-31 | 2020-05-22 | 天津外国语大学 | Movie scenario multivariate information extraction method |
| CN111291535A (en) * | 2020-03-02 | 2020-06-16 | 北京奇艺世纪科技有限公司 | Script processing method and device, electronic equipment and computer readable storage medium |
| CN111507082A (en) * | 2020-04-23 | 2020-08-07 | 北京奇艺世纪科技有限公司 | Text processing method and device, storage medium and electronic device |
| CN112188117A (en) * | 2020-08-29 | 2021-01-05 | 上海量明科技发展有限公司 | Video synthesis method, client and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160182956A1 (en) * | 2014-12-18 | 2016-06-23 | Minkonet Corporation | Method of providing service for recommending game video |
| CN106709968A (en) * | 2016-11-30 | 2017-05-24 | 剧加科技（厦门）有限公司 | Data visualization method and system for play story information |
| CN107368965A (en) * | 2017-07-18 | 2017-11-21 | 杭州火剧科技有限公司 | A kind of script data processing method, device and apply its computer equipment |
-
2017
- 2017-11-27 CN CN201711202819.6A patent/CN107977359B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160182956A1 (en) * | 2014-12-18 | 2016-06-23 | Minkonet Corporation | Method of providing service for recommending game video |
| CN106709968A (en) * | 2016-11-30 | 2017-05-24 | 剧加科技（厦门）有限公司 | Data visualization method and system for play story information |
| CN107368965A (en) * | 2017-07-18 | 2017-11-21 | 杭州火剧科技有限公司 | A kind of script data processing method, device and apply its computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| OXUZHENYI: "Python基于共现提取《釜山行》人物关系", 《HTTPS://BLOG.CSDN.NET/OXUZHENYI/ARTICLE/DETAILS/55511138/?UTM_MEDIUM=DISTRIBUTE.WAP_RELEVANT.NONE-TASK-BLOG-BAIDULANDINGWORD-2》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191010A (en) * | 2019-12-31 | 2020-05-22 | 天津外国语大学 | Movie scenario multivariate information extraction method |
| CN111191010B (en) * | 2019-12-31 | 2023-08-08 | 天津外国语大学 | Movie script multi-element information extraction method |
| CN111291535A (en) * | 2020-03-02 | 2020-06-16 | 北京奇艺世纪科技有限公司 | Script processing method and device, electronic equipment and computer readable storage medium |
| CN111291535B (en) * | 2020-03-02 | 2024-06-11 | 北京奇艺世纪科技有限公司 | Scenario processing method and device, electronic equipment and computer readable storage medium |
| CN111507082A (en) * | 2020-04-23 | 2020-08-07 | 北京奇艺世纪科技有限公司 | Text processing method and device, storage medium and electronic device |
| CN112188117A (en) * | 2020-08-29 | 2021-01-05 | 上海量明科技发展有限公司 | Video synthesis method, client and system |
| CN112188117B (en) * | 2020-08-29 | 2021-11-16 | 上海量明科技发展有限公司 | Video synthesis method, client and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107977359B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582241B (en) | Video subtitle recognition method, device, equipment and storage medium | |
| CN108052577B (en) | Universal text content mining method, device, server and storage medium | |
| CN110020437B (en) | Emotion analysis and visualization method combining video and barrage | |
| CN107977359A (en) | A kind of extracting method of video display drama scene information | |
| US10970334B2 (en) | Navigating video scenes using cognitive insights | |
| US9881215B2 (en) | Apparatus and method for identifying a still image contained in moving image contents | |
| CN104794171B (en) | Mark the method and device of picture geographical location information | |
| CN104883515B (en) | A kind of video labeling processing method and video labeling processing server | |
| CN108307229A (en) | A kind of processing method and equipment of video-audio data | |
| CN108460415A (en) | Pseudo label generates model training method and pseudo label generation method | |
| CN111813998B (en) | Video data processing method, device, equipment and storage medium | |
| CN109766883B (en) | Method for rapidly extracting network video subtitles based on deep neural network | |
| CN112738640B (en) | Method and device for determining subtitles of video stream and readable storage medium | |
| JP2019503541A (en) | An annotation system for extracting attributes from electronic data structures | |
| CN111798543B (en) | Model training method, data processing method, device, equipment and storage medium | |
| CN112182297A (en) | Training information fusion model, and method and device for generating collection video | |
| CN107392883A (en) | The method and system that video display dramatic conflicts degree calculates | |
| CN110119401A (en) | Processing method, device, server and the storage medium of user's portrait | |
| CN108986569A (en) | A kind of desktop AR interactive learning method and device | |
| CN106997350A (en) | A kind of method and device of data processing | |
| KR101389730B1 (en) | Method to create split position accordance with subjects for the video file | |
| CN104504104B (en) | Picture material processing method, device and search engine for search engine | |
| CN112861750A (en) | Video extraction method, device, equipment and medium based on inflection point detection | |
| CN108229285A (en) | Object classification method, the training method of object classification device, device and electronic equipment | |
| CN113411517B (en) | Video template generation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |