CN107977359B - Method for extracting scene information of movie and television scenario - Google Patents
Method for extracting scene information of movie and television scenario Download PDFInfo
- Publication number
- CN107977359B CN107977359B CN201711202819.6A CN201711202819A CN107977359B CN 107977359 B CN107977359 B CN 107977359B CN 201711202819 A CN201711202819 A CN 201711202819A CN 107977359 B CN107977359 B CN 107977359B
- Authority
- CN
- China
- Prior art keywords
- scene
- character string
- information
- line
- description
- 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.)
- Active
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 method for extracting scene information of a movie and television scenario, which relates to the technical field of software development. The method can solve the problems of low accuracy of manual identification and time waste in scene analysis of movie and television scenario evaluation, can quickly and accurately identify and extract basic information in the scene, and improves the quality and speed of scene analysis in the movie and television scenario evaluation.
Description
Technical Field
The invention relates to the technical field of software development, in particular to a method for extracting scene information of a movie and television scenario.
Background
The analysis and evaluation of the movie and television scenario involves analyzing scene information, and the scene information is dispersed in the content of the movie and television scenario and is described in one line or three lines. The scene information generally includes basic information such as the times, places, descriptions of the inside and outside fields, time, weather, main characters, and the like.
The analysis of scene information in the analysis and evaluation of movie and television scenarios is mainly based on manual identification and analysis, and the following difficulties exist:
a. generally, each episode of a television play has 30-50 scenes, the whole movie has about 150 scenes, the number of scenes may be more or less by the factors of the television play, the type of the movie, the duration, the plot and the like, and the time consumed by manual counting during analysis.
b. The sequence of the basic information contained in the scene information is not fixed, and the basic information can be separated by commas, pause signs, periods, colons, TAB characters and the like without standard format.
c. When editing a movie script, the scenes in the scene information may be discontinuous or repeated due to modification or other reasons, which brings certain difficulties to the statistical analysis of the scenes.
Disclosure of Invention
The embodiment of the invention provides a method for extracting scene information of a movie and television scenario, which can solve the problems in the prior art.
The invention provides a method for extracting scene information of a movie and television script, which comprises the following steps:
step 1, establishing a basic information dictionary for describing internal and external scenes, time scenes and weather scenes;
step 2, reading a complete movie and television script, deleting blank lines, removing space characters before and after each line of content, and identifying and extracting scene content based on the processed movie and television script content;
step 3, reading 500 characters in front of the movie script, and judging whether the scene description of the movie script adopts a single-line description mode or a three-line description mode, wherein if the first Chinese character appearing in three consecutive lines in the content of the movie script is one of three Chinese characters of scene, time and person, and the three Chinese characters of scene, time and person all appear once, the description mode of the scene is a three-line description mode, and if not, the three-line description mode is a single-line description mode;
step 4, initializing a movie and television script line to read the serial number N, setting N to be 1, and initializing an empty list L for storing the identified scene information in sequence;
step 5, judging whether N exceeds the total line number of the movie scenario, if so, executing step 9, otherwise, reading the content of the Nth line of the movie scenario, namely a character string S;
step 6, judging whether the first character of the character string S is a Chinese-English digital character, if so, the line is possibly a scene description, executing step 7, otherwise, executing step 8;
step 7, adopting different scene information identification and extraction methods according to the scene description mode obtained in the step 3;
step 8, setting the position of the next line of the reading film and television play book according to the judgment results in the step 6 and the step 7;
and 9, storing the list L, namely all the scene information identified and extracted from the movie and television script, in a file and a database, and completing the processing of identifying and extracting the scene information.
The method for extracting the scene information of the movie and television scenario in the embodiment of the invention automatically identifies the content line of the movie and television scenario with the scene description by reading the content of the movie and television scenario line by line, and accurately extracts the basic information of the scene, the place, the description of the inside and outside fields, the time, the weather, the main people and the like in the scene information by using a dictionary matching mode, and achieves the following effects:
a. scene descriptions in movie scenarios are automatically identified.
b. And accurately extracting basic information in the scene information.
c. The method saves the scene analysis time of the movie and television scenario, and improves the scene analysis efficiency and accuracy.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method for extracting scene information of a movie and television script, which comprises the following steps:
step 1, establishing a basic information dictionary for describing internal and external scenes, time scenes and weather scenes.
And 2, reading the complete movie and television script, deleting blank lines, removing space characters before and after each line of content, and identifying and extracting scene content based on the processed movie and television script content.
And 3, reading 500 characters in front of the movie script, and judging whether the scene description of the movie script adopts a single-line description mode or a three-line description mode, wherein if the first Chinese character appearing in three consecutive lines in the content of the movie script is one of three Chinese characters of scene, time and person, and the three Chinese characters of scene, time and person all appear once, the description mode of the scene is a three-line description mode, and if not, the three-line description mode is a single-line description mode.
And 4, initializing a movie and television script line to read the serial number N, setting N to be 1, and initializing an empty list L for storing the identified scene information according to the sequence.
And 5, judging whether N exceeds the total line number of the movie scenario, if so, executing the step 9, otherwise, reading the content of the Nth line of the movie scenario, namely the character string S.
And 6, judging whether the first character of the character string S is a Chinese-English-numeral character, if so, the line is possibly a scene description, executing the step 7, otherwise, executing the step 8.
And 7, adopting different scene information identification and extraction methods according to the scene description mode obtained in the step 3:
when the movie scenario is in a single-line scene description mode, the following extraction method is used:
a. the comma, pause, period, colon, and TAB characters in the character string S are replaced with space characters to form a character string S0.
b. The character string S0 content is split into character string array A with spaces as separators.
c. Traversing the array A, reading the elements in the character string array A one by one, recording the number T of the identified scene basic information, and executing the following operations:
c1. when the element content in the character string array A is: when the X field (X is Chinese and English numbers) or the first character is Chinese and English, the element describes the field information of the scene, and the following extraction method is adopted:
case 1: the element content is the Xth field, and X is used as the field information of the scene.
Case 2: the element content is a number, and the number is used as the scene information of the scene.
Case 3: the element content is number 1-number 2 (the number 1 and the number 2 are connected by a Chinese and English minus sign), and the number 2 is used as the scene information.
After the field information of the scene is identified, the value of T is increased by 1, and the element is removed to form a character string array A.
c2. When the element in the character string array a describes the dictionary in the inside and outside in step 1, the element is taken as the inside and outside scene information of the scene S1, and after the inside and outside scene information of the scene is recognized, the value T is increased by 1, and the element is removed out of the character string array a.
c3. When the element in the character string array a describes the dictionary in time in step 1, the element is taken as the time description information S2 of the scene, and after the time description information of the scene is recognized, the value of T is increased by 1, and the element is removed out of the character string array a.
c4. When the element in the character string array a is in the weather description dictionary in step 1, the element is taken as the weather description information S3 of the scene, and after the weather description information of the scene is recognized, the value of T is increased by 1, and the element is removed out of the character string array a.
d. The remaining elements in the array a are connected by spaces to form a character string, and the character string is used as the scene location information S4, and the value T is increased by 1.
e. When the number T of the identified scene basic information is greater than or equal to 2, the character string S is used as a scene description information line, the contents of the character strings S1, S2, S3 and S4 are respectively put into an object containing the inside and outside scene attribute, the time attribute, the weather attribute and the place attribute, and the object is stored into the list L created in the step 4; when T is less than 2, the character string S does not serve as a scene information description line.
The following extraction method is used when the movie scenario is in a three-line scene description mode:
a. judging whether the first Chinese character appearing in the character string S is one of three Chinese characters of scene, hour and person, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, the subsequent processing is continuously executed.
b. Judging whether 2 lines of movie script contents exist behind the line of the character string S, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, the subsequent processing is continuously executed.
c. Recording the content of the next line of the character string S as S5, recording the content of the second line behind the character string S as S6, respectively judging whether the first Chinese character appearing in the character strings S, S5 and S6 is scene, time and person, wherein the three Chinese characters of scene, time and person appear once respectively, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, the subsequent processing is continuously executed.
d. The following extraction methods are adopted in the character strings S, S5, S6, respectively:
case 1: when the first Chinese character appearing in the character string is "scene", the character string is cut from the first Chinese character behind the scene until the character string is finished, and the formed new character string is used as the site information P1 of the scene information.
Case 2: when the first Chinese character appearing in the character string is "person", the character string is cut from the first Chinese character behind the person until the character string is ended, and the formed new character string is used as the character information P2 of the scene information.
Case 3: when the first Chinese character of the character string appears is 'time', intercepting the character string from the first Chinese character after the time until the character string is finished to form a new character string, and performing the following processing aiming at the new character string:
(1) the character string S7 is formed by replacing characters in the character string other than the chinese character with spaces and deleting spaces before and after the character string.
(2) The content of the character string S7 is divided into a character string array B with spaces as separators.
(3) Traversing the array B, reading the elements in the character string array B one by one, and executing the following identification operations:
when an element appears in the inside and outside description dictionary in step 1, the element is taken as inside and outside scene information P3 of the scene.
When an element appears in the time description dictionary in step 1, the element is taken as the time description information P4 of the scene.
e. The contents of the character strings P1, P2, P3, and P4 are put into an object containing a place attribute, a person attribute, an inside and outside scene attribute, and a time attribute, respectively, and the object is saved in the list L created in step 4.
And 8, setting the position of the next line of the read film and television play book according to the judgment results in the steps 6 and 7:
when step 6 judges that the character string S is not a scene, after N +1 is set, step 5 is skipped to continue execution.
And when the character string S is judged to be in the single-line scene description mode in the step 7, after N is set to be N +1, jumping to the step 5 to continue execution.
And when the character string S is judged to be in the three-line description scene mode in step 7, after N is set to be N +3, the execution is continued in step 5.
When step 7 judges that the character string S is not a scene, after N +1 is set, the process jumps to step 5 to continue execution.
And 9, storing the list L, namely all the scene information identified and extracted from the movie and television script, in a file and a database, and completing the processing of identifying and extracting the scene information.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. A method for extracting scene information of a movie and television scenario is characterized by comprising the following steps:
step 1, establishing a basic information dictionary for describing internal and external scenes, time scenes and weather scenes;
step 2, reading a complete movie and television script, deleting blank lines, removing space characters before and after each line of content, and identifying and extracting scene content based on the processed movie and television script content;
step 3, reading 500 characters in front of the movie script, and judging whether the scene description of the movie script adopts a single-line description mode or a three-line description mode, wherein if the first Chinese character appearing in three consecutive lines in the content of the movie script is one of three Chinese characters of scene, time and person, and the three Chinese characters of scene, time and person all appear once, the description mode of the scene is a three-line description mode, and if not, the three-line description mode is a single-line description mode;
step 4, initializing a movie and television script line to read the serial number N, setting N =1, and initializing an empty list L for storing the identified scene information according to the sequence;
step 5, judging whether N exceeds the total line number of the movie scenario, if so, executing step 9, otherwise, reading the content of the Nth line of the movie scenario, namely a character string S;
step 6, judging whether the first character of the character string S is a Chinese-English digital character, if so, the line is possibly a scene description, executing step 7, otherwise, executing step 8;
step 7, adopting different scene information identification and extraction methods according to the scene description mode obtained in the step 3;
step 8, setting the position of the next line of the reading film and television play book according to the judgment results in the step 6 and the step 7;
step 9, the list L is all scene information identified and extracted from the movie and television script, the list L is stored in a file and a database, and the identification and extraction of the scene information are completed;
in step 7, when the movie scenario is in a single-line scene description mode, the following extraction method is used:
a. replacing commas, pause signs, periods, colon signs and TAB TABs in the character string S with space signs to form a character string S0;
b. taking a space as a separator, and splitting the content of the character string S0 into a character string array A;
c. traversing the array A, reading the elements in the character string array A one by one, recording the number T of the identified scene basic information, and executing the following operations:
c1. when the element content in the character string array A is: when the X field or the first character is Chinese and English, the element describes the field information of the scene, and the following extraction method is adopted:
case 1: the element content is an Xth field, and X is used as field information of a scene;
case 2: the element content is a number, and the number is used as the field information of the scene;
case 3: the element content is number 1-number 2, and the number 2 is used as the scene information of the scene;
after the field information of the scene is identified, increasing the value T by 1, and removing the element to obtain a character string array A;
c2. when the elements in the character string array A are in the internal and external description dictionary in the step 1, taking the elements as the internal and external scene information S1 of the scene, increasing the value T by 1 after recognizing the internal and external scene information of the scene, and removing the elements to obtain the character string array A;
c3. when the element in the character string array A is in the time description dictionary in the step 1, the element is taken as the time description information S2 of the scene, after the time description information of the scene is identified, the value T is increased by 1, and the element is removed out of the character string array A;
c4. when the element in the character string array A is in the weather description dictionary in the step 1, taking the element as the weather description information S3 of the scene, increasing the value T by 1 after identifying the weather description information of the scene, and removing the element to form the character string array A;
d. connecting the rest elements in the array A by using a blank space to form a character string, using the character string as scene place information S4, and increasing the value T by 1;
e. when the number T of the identified scene basic information is greater than or equal to 2, the character string S is used as a scene description information line, the contents of the character strings S1, S2, S3 and S4 are respectively put into an object containing the inside and outside scene attribute, the time attribute, the weather attribute and the place attribute, and the object is stored into the list L created in the step 4; when T is less than 2, the character string S does not serve as a scene information description line.
2. The method for extracting scene information of a movie scenario as claimed in claim 1, wherein the following extraction method is used in step 7 when the movie scenario is in three-line scene description mode:
a. judging whether the first Chinese character appearing in the character string S is one of three Chinese characters of scene, hour and person, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, continuing to execute subsequent processing;
b. judging whether 2 lines of movie script contents exist behind the line of the character string S, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, continuing to execute subsequent processing;
c. recording the content of the next line of the character string S as S5, recording the content of the second line behind the character string S as S6, respectively judging whether the first Chinese character appearing in the character strings S, S5 and S6 is scene, time and person, wherein the three Chinese characters of scene, time and person appear once respectively, if not, the current line is not the scene description, and continuing to execute the step 8; otherwise, continuing to execute subsequent processing;
d. the following extraction methods are adopted in the character strings S, S5, S6, respectively:
case 1: when the first Chinese character of the character string appears as 'scene', intercepting the character string from the first Chinese character behind the scene until the character string is finished, and taking the formed new character string as the site information P1 of the scene information;
case 2: when the first Chinese character appearing in the character string is a 'person', intercepting the character string from the first Chinese character behind the person until the character string is ended, and taking the formed new character string as character information P2 of the scene information;
case 3: when the first Chinese character of the character string appears is 'time', intercepting the character string from the first Chinese character after the time until the character string is finished to form a new character string, and performing the following processing aiming at the new character string:
(1) replacing the characters except the Chinese characters in the character string with spaces and deleting spaces before and after the character string to form a character string S7;
(2) taking a space as a separator, and splitting the content of the character string S7 into a character string array B;
(3) traversing the array B, reading the elements in the character string array B one by one, and executing the following identification operations:
when the element appears in the inside-outside description dictionary in step 1, the element is taken as inside-outside scene information P3 of the scene;
when an element appears in the time description dictionary in step 1, the element is taken as time description information P4 of the scene;
e. the contents of the character strings P1, P2, P3, and P4 are put into an object containing a place attribute, a person attribute, an inside and outside scene attribute, and a time attribute, respectively, and the object is saved in the list L created in step 4.
3. The method for extracting scenario information of a movie and television scenario as claimed in claim 1, wherein step 8 specifically comprises:
when the character string S is judged not to be the scene in the step 6, after setting N = N +1, skipping to the step 5 to continue execution;
when the character string S is judged to be in a single-line scene description mode in the step 7, after N = N +1 is set, skipping to the step 5 to continue execution;
when the character string S is judged to be in a three-line description scene mode in the step 7, after N = N +3 is set, jumping to the step 5 to continue execution;
when step 7 judges that the character string S is not a scene, after N = N +1 is set, the process jumps to step 5 to continue execution.
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 CN107977359A (en) | 2018-05-01 |
| CN107977359B true 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) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191010B (en) * | 2019-12-31 | 2023-08-08 | 天津外国语大学 | Movie script multi-element information extraction method |
| 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 |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101604250B1 (en) * | 2014-12-18 | 2016-03-25 | 민코넷주식회사 | Method of Providing Service for Recommending Game Video |
-
2017
- 2017-11-27 CN CN201711202819.6A patent/CN107977359B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| Python基于共现提取《釜山行》人物关系;oxuzhenyi;《https://blog.csdn.net/oxuzhenyi/article/details/55511138/?utm_medium=distribute.wap_relevant.none-task-blog-baidulandingword-2》;20170217;第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107977359A (en) | 2018-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977359B (en) | Method for extracting scene information of movie and television scenario | |
| CN107644085B (en) | Method and device for generating sports event news | |
| CN110544477A (en) | Voice recognition method, device, equipment and medium | |
| CN110287949B (en) | Video clip extraction method, device, equipment and storage medium | |
| CN112738640B (en) | Method and device for determining subtitles of video stream and readable storage medium | |
| CN111339250B (en) | Mining method for new category labels, electronic equipment and computer readable medium | |
| CN109766883B (en) | Method for rapidly extracting network video subtitles based on deep neural network | |
| CN111091811B (en) | Method and device for processing voice training data and storage medium | |
| CN109147769B (en) | Language identification method, language identification device, translation machine, medium and equipment | |
| CN111159497B (en) | Regular expression generating method and regular expression-based data extraction method | |
| CN111741331B (en) | Video clip processing method, device, storage medium and equipment | |
| Zhang et al. | Bing++: A fast high quality object proposal generator at 100fps | |
| CN111488847A (en) | System, method and terminal for acquiring sports game video goal segment | |
| CN111738042A (en) | Identification method, device and storage medium | |
| CN113010785A (en) | User recommendation method and device | |
| CN111881734A (en) | Method and device for automatically intercepting target video | |
| US20160142456A1 (en) | Method and Device for Acquiring Media File | |
| CN110717323A (en) | Document seal dividing method and device, terminal and computer readable storage medium | |
| CN112541505B (en) | Text recognition method, text recognition device and computer-readable storage medium | |
| CN115049963A (en) | Video classification method and device, processor and electronic equipment | |
| CN114866788A (en) | Video processing method and device | |
| CN113609315A (en) | Method and device for judging similarity of media assets, electronic equipment and storage medium | |
| CN111798542A (en) | Model training method, data processing device, model training apparatus, and storage medium | |
| CN113810782B (en) | Video processing method and device, server and electronic device | |
| CN114222193B (en) | Video subtitle time alignment model training method and system |
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 |