CN113468377A - Video and literature association and integration method - Google Patents
Video and literature association and integration method Download PDFInfo
- Publication number
- CN113468377A CN113468377A CN202110745929.7A CN202110745929A CN113468377A CN 113468377 A CN113468377 A CN 113468377A CN 202110745929 A CN202110745929 A CN 202110745929A CN 113468377 A CN113468377 A CN 113468377A
- Authority
- CN
- China
- Prior art keywords
- video
- technology
- indexing
- association
- document
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明公开了一种视频与文献关联整合方法，包括利用自动标引技术、版面分析技术、机器学习技术将视频内容和文献内容进行标引；利用自然语言处理技术、数据挖掘技术、关联规则分析技术将视频与文献进行深度融合关联。本发明在用户观看视频时，当视频数据播放到标引位置时，触发标引规则，读取标引数据，更新推送与视频本节点内容密切相关的知识点和有价值的信息。
The invention discloses a video and document association integration method, which includes using automatic indexing technology, layout analysis technology and machine learning technology to index video content and document content; using natural language processing technology, data mining technology and association rule analysis The technology deeply integrates and associates videos with literature. The invention triggers the indexing rule when the video data is played to the indexing position when the user watches the video, reads the indexing data, and updates and pushes knowledge points and valuable information closely related to the content of the video node.
Description
Technical Field
The invention relates to the technical field of resource association integration and data mining, in particular to a method for deeply associating and integrating video data and literature resources.
Background
At present, the demands of various industries on video data and document resources are higher and higher, a plurality of video websites and document platforms exist in the market, but the video websites and the document platforms only stay in single retrieval of the video data and the document resources, a user can only view videos or documents singly, the indexing degree of the videos is lower, and the technical application of video data and document resource correlation analysis is relatively insufficient; meanwhile, the data mining technology is limited, and under the influence of the computer technology, the mining technology and the like, even if the data mining technology is correctly applied, an expected effect cannot be obtained, and the maximization of the video data and the document resource value cannot be realized.
Disclosure of Invention
To solve the above technical problems, an object of the present invention is to provide a method for performing deep associative integration of video data and literature resources.
The purpose of the invention is realized by the following technical scheme:
a video and literature association and integration method comprises the following steps:
step A, utilizing an automatic indexing technology, a layout analysis technology and a machine learning technology to index video contents and document contents;
and step B, performing deep fusion association on the video and the literature by utilizing a natural language processing technology, a data mining technology and an association rule analysis technology.
One or more embodiments of the present invention may have the following advantages over the prior art:
the video data is subjected to deep processing indexing and recording, on the basis, the deep association fusion of the video data and literature resources is realized, relevant literatures are pushed in association when the video data is opened, or the relevant literatures are pushed in real time when the content of each section of the video is watched or a certain time point is watched, and the literature knowledge points and valuable information associated with the video data are displayed efficiently.
Drawings
FIG. 1 is a flow chart of video data and document resource indexing;
fig. 2 is a diagram of a method of associating video data with a document asset.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings.
As shown in fig. 1, the process for indexing video data and document resources includes: the method comprises the steps of automatically indexing video document resources, establishing a standard library of the resources before processing resource data, indexing the video and document resources according to massive data information of a knowledge network and scientific classification standards by means of an automatic indexing technology, a layout understanding technology, a machine learning technology and the like, automatically splitting chapters and sections of the document resources, identifying pictures, indexing text contents and basic elements, selecting corresponding subject terms from a standardized subject word list according to content characteristics of the document resources, and giving the knowledge resources as subject identifiers; video data is indexed with external incidental information of the video, such as the information of the title, the accountant, the time and the like;
the video literature resource indexing method comprises the following steps of performing human-computer interaction indexing on video literature resources, and completing indexing and editing work on each metadata item of the literature resources through a human-computer interaction interface; the indexing of the internal information of the video data comprises the steps of firstly, analyzing the image, video and audio contents in the video data based on the information acquisition of the video data contents, extracting characteristics and semantics and writing and indexing the video data; and secondly, determining the video data indexing position, namely determining the video indexing time point, adding indexing content according to the indexing rule, and storing the indexing result. And after the indexing is finished, performing indexing correction, generating standard video data and document resources after the indexing, and storing the standard video data and the document resources into a database.
As shown in fig. 2, the method for establishing association between video data and document resources comprises: before resource association is carried out, a concept relation dictionary and an association rule analysis model are built, a learning strategy is set according to the model, association relation analysis of various data is carried out, the established association relation is matched with the model rule, the association relation is identified according to the model rule, and the association relation matching is completed. Association relation among a large amount of data is effectively discovered through association rule analysis, association recommendation between video data and literature resources is achieved, and association analysis in the following aspects is mainly completed: the method comprises the following steps of performing literature correlation analysis, namely establishing correlation between contents described in a video and research results, policy documents, encyclopedic knowledge, historical materials and the like; performing author association analysis, and mining and analyzing the association relationship between the main speaker of the video course and expert information; performing association analysis on organization units, namely mining association relation between author unit information of a main speaker and resume of organization research results; performing keyword association analysis, namely mining the co-occurrence relationship and weight of the analyzed keywords and mining the relation among the keywords; analyzing the video bibliography and the literature theme, mining and analyzing to establish the association relationship between each bibliography of the video and the literature resource, and updating the literature when the video is watched to the node; and (4) title association analysis, namely mining and establishing the relation between the video data title and the literature resource title through the relation and the weight of various resource titles. Through the data association mode, when a video is watched and a data indexing segment or a time point is played, the indexing associated data can be read according to the indexing rule, and the document display content is updated.
Although the embodiments of the present invention have been described above, the above descriptions are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. A method for associating and integrating videos and documents, which is characterized by comprising the following steps:
step A, utilizing an automatic indexing technology, a layout analysis technology and a machine learning technology to index video contents and document contents;
and step B, performing deep fusion association on the video and the literature by utilizing a natural language processing technology, a data mining technology and an association rule analysis technology.
2. The method according to claim 1, wherein the video content and the literature content are indexed by metadata, subject term, and keyword; wherein the indexing position of the video data is a video time point or a segment.
3. The method according to claim 1, wherein in step a, the information in the video data is analyzed by using an automatic indexing technology, big data and machine learning technology, and features and semantics are extracted as the basis for recording and indexing the video data; and automatically splitting chapters and sections according to the directory structure of the document by using a layout analysis technology, identifying pictures, and indexing the content and basic elements of document resources.
4. The video and document association and integration method of claim 3, wherein the information in the video data includes a time point, an image, video content, and metadata.
5. The method as claimed in claim 1, wherein in step B, the association relationship between the video and the document data is analyzed by the association rule using the natural language processing technique and the data mining technique, and the association relationship between the knowledge points, the metadata, etc. is mined to realize the deep association between the video data, the document resources, and the expert information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110745929.7A CN113468377A (en) | 2021-07-01 | 2021-07-01 | Video and literature association and integration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110745929.7A CN113468377A (en) | 2021-07-01 | 2021-07-01 | Video and literature association and integration method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113468377A true CN113468377A (en) | 2021-10-01 |
Family
ID=77877433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110745929.7A Pending CN113468377A (en) | 2021-07-01 | 2021-07-01 | Video and literature association and integration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468377A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539875A (en) * | 2023-10-31 | 2024-02-09 | 广东北区教育科技有限公司 | Exercise question bank periodic updating on-line management method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917258A (en) * | 2012-10-12 | 2013-02-06 | 深圳Tcl新技术有限公司 | Video playing method, terminal and system based on video contents |
| CN105005556A (en) * | 2015-07-29 | 2015-10-28 | 成都理工大学 | Index keyword extraction method and system based on big geological data |
| CN105550940A (en) * | 2015-11-25 | 2016-05-04 | 中国南方电网有限责任公司电网技术研究中心 | Mining and extracting method for standard index data of power grid equipment |
| CN110309265A (en) * | 2019-06-30 | 2019-10-08 | 韶关市启之信息技术有限公司 | A method of determining whether video pushes Relevant Legal Knowledge |
-
2021
- 2021-07-01 CN CN202110745929.7A patent/CN113468377A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917258A (en) * | 2012-10-12 | 2013-02-06 | 深圳Tcl新技术有限公司 | Video playing method, terminal and system based on video contents |
| CN105005556A (en) * | 2015-07-29 | 2015-10-28 | 成都理工大学 | Index keyword extraction method and system based on big geological data |
| CN105550940A (en) * | 2015-11-25 | 2016-05-04 | 中国南方电网有限责任公司电网技术研究中心 | Mining and extracting method for standard index data of power grid equipment |
| CN110309265A (en) * | 2019-06-30 | 2019-10-08 | 韶关市启之信息技术有限公司 | A method of determining whether video pushes Relevant Legal Knowledge |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539875A (en) * | 2023-10-31 | 2024-02-09 | 广东北区教育科技有限公司 | Exercise question bank periodic updating on-line management method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rossetto et al. | V3C–a research video collection | |
| CN106354861B (en) | Automatic indexing method and automatic indexing system for movie labels | |
| US8145648B2 (en) | Semantic metadata creation for videos | |
| CN102053991B (en) | Method and system for multi-language document retrieval | |
| US20130305149A1 (en) | Document reader and system for extraction of structural and semantic information from documents | |
| CN107968959B (en) | Knowledge point segmentation method for teaching video | |
| US10572528B2 (en) | System and method for automatic detection and clustering of articles using multimedia information | |
| Seenivasan | ETL in a World of Unstructured Data: Advanced Techniques for Data Integration | |
| Neudecker et al. | Large-scale refinement of digital historic newspapers with named entity recognition | |
| JP7395377B2 (en) | Content search methods, devices, equipment, and storage media | |
| CN113065018A (en) | Audio and video index library creating and retrieving method and device and electronic equipment | |
| KR20040017824A (en) | Information search system which it follows in the Pattern-Forecast-Analysis to use the pattern of the web document and list | |
| CN116975363A (en) | Video tag generation method and device, electronic equipment and storage medium | |
| Choi et al. | Chrological big data curation: a study on the enhanced information retrieval system | |
| CN119336854A (en) | An intelligent arrangement method for audio-visual archives based on event knowledge graph | |
| CN113468377A (en) | Video and literature association and integration method | |
| CN113656641A (en) | Efficient video retrieval system supporting fuzzy comment mining | |
| Poornima et al. | Text preprocessing on extracted text from audio/video using R | |
| CN111159984A (en) | An assisted reading system with intelligent study notes function | |
| Tan et al. | Placing videos on a semantic hierarchy for search result navigation | |
| CN114328895A (en) | News abstract generation method and device and computer equipment | |
| KR20220079042A (en) | Program recorded medium for providing service | |
| Hast et al. | Making large collections of handwritten material easily accessible and searchable | |
| CN110717091B (en) | Entry data expansion method and device based on face recognition | |
| CN119848359B (en) | A news content extraction and display 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 100084 Beijing city Haidian District Tsinghua University Tsinghua Yuan 36 zone B1410, Huaye building 1412, room 1414 Applicant after: TONGFANG KNOWLEDGE NETWORK (BEIJING) TECHNOLOGY Co.,Ltd. Applicant after: Tongfangzhiwang Digital Technology Co.,Ltd. Address before: 100084 Beijing city Haidian District Tsinghua University Tsinghua Yuan 36 zone B1410, Huaye building 1412, room 1414 Applicant before: TONGFANG KNOWLEDGE NETWORK (BEIJING) TECHNOLOGY Co.,Ltd. Country or region before: China Applicant before: TONGFANG KNOWLEDGE NETWORK DIGITAL PUBLISHING TECHNOLOGY CO.,LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211001 |