CN111930970A - News storage and search method based on video and voice recognition - Google Patents
News storage and search method based on video and voice recognition Download PDFInfo
- Publication number
- CN111930970A CN111930970A CN202010782002.6A CN202010782002A CN111930970A CN 111930970 A CN111930970 A CN 111930970A CN 202010782002 A CN202010782002 A CN 202010782002A CN 111930970 A CN111930970 A CN 111930970A
- Authority
- CN
- China
- Prior art keywords
- news
- video
- content
- voice
- storage
- 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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/41—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/432—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/45—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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Abstract
The invention discloses a news storage and search method based on video and voice recognition; the method comprises the following steps: s1, intercepting video and voice fragments; s2, storing the news content; s3, storing and returning; s4, searching the stored news; s5, returning the search content; according to the invention, news contents are respectively stored, so that files, videos, voices and the like are independently stored, storage disorder is avoided, and a one-to-many mapping mode is realized through addresses of news brief introduction, so that the searching speed is accelerated; the news content can be rapidly searched through various searching modes, videos and voice segments can be directly searched through the videos and the voice content when the news content is stored, the searching modes are various, the searching can be rapidly realized, and the mapping relation can prevent the news from being confused during searching.
Description
Technical Field
The invention belongs to the technical field of news storage and search, and particularly relates to a news storage and search method based on video and voice recognition.
Background
News, also called messages, is a term for information that is broadcast through media paths such as newspapers, radio stations, radio, television stations, and the like. It is a cultural relic for recording society, transmitting information and reflecting the era. The concept of news is broadly and narrowly defined, and in the broad sense, except for the comments and the texts published in newspapers, broadcasts, the internet, televisions, etc., the common texts belong to news columns including messages, communications, features, shorthand (some shorthand are included in the list of features), etc., the narrow news specifically refers to messages, and the messages are summarized and narrated to quickly and timely report the valuable facts newly occurring at home and abroad and to let others understand the facts. Each news item generally includes five parts, a title, a subject, a background, and a final. The first three are the main parts and the second two are the auxiliary parts. The description is mainly related to the writing, and sometimes includes discussion, description, and comment. The news is a news service platform containing mass information and truly reflects the important events at every moment. The latest progress of news events, hot topics, character dynamics, product information and the like can be quickly known by looking at the news events, the hot topics, the character dynamics, the product information and the like, and in the existing internet era, news needs to be stored and searched, however, various news storage numbers and search modes on the market still have various problems.
Although the method and the device for searching news videos disclosed by the authorized bulletin number CN101944111B effectively solve the problems of automatic, accurate and timely searching and integration of internet news videos, can quickly and accurately identify news video websites, and can automatically and timely find and integrate news videos, the method and the device do not solve the problems that the existing storage method is troublesome, a large number of files, videos, voices and the like are stored in the same place, huge burden is caused to searching, searching is too slow, storage is easy to be disordered, the existing searching method is too complicated, news contents need to be traversed, searching is slow, and the like.
Disclosure of Invention
The present invention is directed to a news storage and search method based on video and voice recognition to solve the problems set forth in the background art described above.
In order to achieve the purpose, the invention provides the following technical scheme: the news storage and search method based on video and voice recognition comprises the following steps:
s1, intercepting video and voice fragments: the method comprises the steps of carrying out fragment interception on video and voice in news and using the video and voice in the news as URL (uniform resource locator) for news storage;
s2, storing the news content: storing the news into a database by taking the intercepted video and voice segments in the S1 as a type of URL, and classifying and storing the news;
s3, storage return: after the storage of S2, the front page skips to display that the storage is successful, and automatically calls out the stored content for display;
s4, searching the stored news: inputting retrieval contents in a search box, and retrieving the storage contents in the database by a retrieval engine;
s5, returning search content: and displaying the detected tag content on a front-end page, clicking a tag of the retrieved news after the determined retrieved content is correct, sequentially and respectively extracting news text content, video content, voice content and picture content through a URL (uniform resource locator) corresponding to the news tag content, and displaying complete news content on the front-end page.
Preferably, the URL in S2 further includes a news brief, a news tag, a news title, and a news time, wherein the news brief is an introduction of news in a simple language by a news editor, and the news tag is a simple summary of news contents by the news editor.
Preferably, the classification in S2 includes positive news, neutral news, and negative news articles, which include super news, big news, and general news, respectively.
Preferably, the database in S2 includes a local database and a cloud database, and the cloud database realizes transmission connection through a data interface during storage and search.
Preferably, the search box in S4 includes a video file input box, a voice file input box, a news tag input box, a news name input box, a news time input box, and a news keyword input box in sequence.
Preferably, the steps of processing the video and the voice transmitted in the video file input box and the voice file input box are as follows:
s41: decomposing a video into pictures according to each frame, then carrying out gray processing on the pictures, carrying out edge processing on the pictures, and then carrying out feature extraction on the pictures;
s42: processing a voice file, converting the voice into characters, and analyzing the semantic meaning and the sound domain of the voice;
s43: news selected according to the news label, the news name, the news time and the news keyword is extracted and stored in a cache memory, then the news is respectively compared with files stored in a database through a video file and a voice file, news content is determined after comparison, and then the news content is displayed on a front-end page.
Preferably, the search mode of the search engine in S4 is one of an enumeration algorithm, a depth-first search, a breadth-first search, an a algorithm, a backtracking algorithm, a monte carlo tree search, a hash function, and the like.
Preferably, the URLs in S5 are addresses of news profiles, respectively, and the URLs correspond to news text content, video content, voice content, and picture content, respectively, through a one-to-many mapping relationship.
Preferably, the news text content, the video content, the voice content and the picture content are stored through a one-to-many mapping relation respectively, so that storage disorder and slow retrieval are avoided.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the invention, news contents are respectively stored, so that files, videos, voices and the like are independently stored, storage disorder is avoided, and a one-to-many mapping mode is realized through addresses of news brief introduction, so that the searching speed is accelerated;
(2) the invention realizes the rapid search of news contents through various search modes, intercepts the video and voice fragments during storage, and can directly search the news through the video and voice contents, so that the search modes are various, the search can be rapidly realized, the mapping relation can be used, and the news can be prevented from being disordered during the search.
Drawings
FIG. 1 is a schematic view of the step structure of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
Referring to fig. 1, the present invention provides a technical solution:
the first embodiment is as follows:
the news storage and search method based on video and voice recognition comprises the following steps:
s1, intercepting video and voice fragments: the method comprises the steps of carrying out fragment interception on video and voice in news and using the video and voice in the news as URL (uniform resource locator) for news storage;
s2, storing the news content: storing the news into a database by taking the intercepted video and voice segments in the S1 as a type of URL, and classifying and storing the news;
s3, storage return: after the storage of S2, the front page skips to display that the storage is successful, and automatically calls out the stored content for display;
s4, searching the stored news: inputting retrieval contents in a search box, and retrieving the storage contents in the database by a retrieval engine;
s5, returning search content: and displaying the detected tag content on a front-end page, clicking a tag of the retrieved news after the determined retrieved content is correct, sequentially and respectively extracting news text content, video content, voice content and picture content through a URL (uniform resource locator) corresponding to the news tag content, and displaying complete news content on the front-end page.
In order to implement the multiple ways of storing news for the subsequent search, in this embodiment, it is preferable that the URL in S2 further includes a news brief, a news tag, a news title, and a news time, the news brief is a news editor introducing news in a simple language, and the news tag is a news editor simply summarizing news contents.
In order to prevent the news from being confused during storage and cause the searching process to be too slow, in this embodiment, it is preferable that the classification in S2 includes positive news, neutral news, and negative news articles, which include super news, big news, and general news, respectively.
In order to implement storage and facilitate searching, in this embodiment, it is preferable that the database in S2 includes a local database and a cloud database, and the cloud database implements transmission connection through a data interface during storage and searching.
In order to perform rapid and simple various searches on news through multiple channels, in this embodiment, it is preferable that the search box in S4 sequentially include a video file input box, a voice file input box, a news tag input box, a news name input box, a news time input box, and a news keyword input box.
In order to implement processing of video and voice and further implement comparison and search of video and voice in news, in this embodiment, preferably, the steps of processing the video and voice transmitted in the video file input box and the voice file input box are as follows:
s41: decomposing a video into pictures according to each frame, then carrying out gray processing on the pictures, carrying out edge processing on the pictures, and then carrying out feature extraction on the pictures;
s42: processing a voice file, converting the voice into characters, and analyzing the semantic meaning and the sound domain of the voice;
s43: news selected according to the news label, the news name, the news time and the news keyword is extracted and stored in a cache memory, then the news is respectively compared with files stored in a database through a video file and a voice file, news content is determined after comparison, and then the news content is displayed on a front-end page.
In order to retrieve news content, in this embodiment, preferably, the search mode of the search engine in S4 is one of an enumeration algorithm, a depth-first search, a breadth-first search, an a algorithm, a backtracking algorithm, a monte carlo tree search, a hash function, and the like.
In order to realize fast detection, the addresses of the news content and the news brief are combined into a one-to-many mapping relationship, and the news content is classified and stored, in this embodiment, it is preferable that the URLs in S5 are the addresses of the news brief, respectively, and the URLs correspond to the news text content, the video content, the voice content, and the picture content through the one-to-many mapping relationship, respectively, and the storage of the news text content, the video content, the voice content, and the picture content through the one-to-many mapping relationship does not generate storage confusion and retrieval slowness.
Example two:
the news storage and search method based on video and voice recognition comprises the following steps:
s1, intercepting video and voice fragments: the method comprises the steps of carrying out fragment interception on video and voice in news and using the video and voice in the news as URL (uniform resource locator) for news storage;
s2, storing the news content: storing the news into a database by taking the intercepted video and voice segments in the S1 as a type of URL, and classifying and storing the news;
s3, storage return: after the storage of S2, the front page skips to display that the storage is successful, and automatically calls out the stored content for display;
s4, searching the stored news: inputting retrieval contents in a search box, and retrieving the storage contents in the database by a retrieval engine;
s5, returning search content: and displaying the detected tag content on a front-end page, clicking a tag of the retrieved news after the determined retrieved content is correct, sequentially and respectively extracting news text content, video content, voice content and picture content through a URL (uniform resource locator) corresponding to the news tag content, and displaying complete news content on the front-end page.
In order to implement the multiple ways of storing news for the subsequent search, in this embodiment, it is preferable that the URL in S2 further includes a news brief, a news tag, a news title, and a news time, the news brief is a news editor introducing news in a simple language, and the news tag is a news editor simply summarizing news contents.
In order to perform rapid and simple various searches on news through multiple channels, in this embodiment, it is preferable that the search box in S4 sequentially include a video file input box, a voice file input box, a news tag input box, a news name input box, a news time input box, and a news keyword input box.
In order to implement processing of video and voice and further implement comparison and search of video and voice in news, in this embodiment, preferably, the steps of processing the video and voice transmitted in the video file input box and the voice file input box are as follows:
s41: decomposing a video into pictures according to each frame, then carrying out gray processing on the pictures, carrying out edge processing on the pictures, and then carrying out feature extraction on the pictures;
s42: processing a voice file, converting the voice into characters, and analyzing the semantic meaning and the sound domain of the voice;
s43: news selected according to the news label, the news name, the news time and the news keyword is extracted and stored in a cache memory, then the news is respectively compared with files stored in a database through a video file and a voice file, news content is determined after comparison, and then the news content is displayed on a front-end page.
In order to retrieve news content, in this embodiment, preferably, the search mode of the search engine in S4 is one of an enumeration algorithm, a depth-first search, a breadth-first search, an a algorithm, a backtracking algorithm, a monte carlo tree search, a hash function, and the like.
In order to realize fast detection, the addresses of the news content and the news brief are combined into a one-to-many mapping relationship, and the news content is classified and stored, in this embodiment, it is preferable that the URLs in S5 are the addresses of the news brief, respectively, and the URLs correspond to the news text content, the video content, the voice content, and the picture content through the one-to-many mapping relationship, respectively, and the storage of the news text content, the video content, the voice content, and the picture content through the one-to-many mapping relationship does not generate storage confusion and retrieval slowness.
The working principle and the using process of the invention are as follows:
the first step, intercepting video and voice segments: the method comprises the steps of carrying out fragment interception on video and voice in news and using the video and voice in the news as URL (uniform resource locator) for news storage;
secondly, storing news contents: storing the news into a database by taking the intercepted video and voice segments in the S1 as a type of URL, and classifying and storing the news;
and step three, storage and return: after the storage of S2, the front page skips to display that the storage is successful, and automatically calls out the stored content for display;
fourthly, searching the stored news: inputting retrieval contents in a search box, and retrieving the storage contents in the database by a retrieval engine;
and step five, returning retrieval contents: and displaying the detected tag content on a front-end page, clicking a tag of the retrieved news after the determined retrieved content is correct, sequentially and respectively extracting news text content, video content, voice content and picture content through a URL (uniform resource locator) corresponding to the news tag content, and displaying complete news content on the front-end page.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The news storage and search method based on video and voice recognition is characterized in that: the method comprises the following steps:
s1, intercepting video and voice fragments: the method comprises the steps of carrying out fragment interception on video and voice in news and using the video and voice in the news as URL (uniform resource locator) for news storage;
s2, storing the news content: storing the news into a database by taking the intercepted video and voice segments in the S1 as a type of URL, and classifying and storing the news;
s3, storage return: after the storage in S2, the front page jumps to display that the storage is successful, and automatically retrieves the storage content for display.
S4, searching the stored news: inputting retrieval contents in a search box, and retrieving the storage contents in the database by a retrieval engine;
s5, returning search content: and displaying the detected tag content on a front-end page, clicking a tag of the retrieved news after the determined retrieved content is correct, sequentially and respectively extracting news text content, video content, voice content and picture content through a URL (uniform resource locator) corresponding to the news tag content, and displaying complete news content on the front-end page.
2. The video and speech recognition-based news storage and search method of claim 1, wherein: the URL in S2 further includes a news brief that the news editor introduces to the news in a simple language, a news tag that the news editor simply summarizes the news content, a news title, and a news time.
3. The video and speech recognition-based news storage and search method of claim 1, wherein: the classification in S2 includes positive news, neutral news, and negative news articles, which include super news, big news, and general news, respectively.
4. The video and speech recognition-based news storage and search method of claim 1, wherein: the database in S2 includes a local database and a cloud database, and the cloud database realizes transmission connection through a data interface during storage and search.
5. The video and speech recognition-based news storage and search method of claim 1, wherein: the search box in S4 includes a video file input box, a voice file input box, a news tag input box, a news name input box, a news time input box, and a news keyword input box in sequence.
6. The video and speech recognition-based news storage and search method of claim 5, wherein: the video and voice processing steps transmitted in the video file input box and the voice file input box are as follows:
s41: decomposing a video into pictures according to each frame, then carrying out gray processing on the pictures, carrying out edge processing on the pictures, and then carrying out feature extraction on the pictures;
s42: processing a voice file, converting the voice into characters, and analyzing the semantic meaning and the sound domain of the voice;
s43: news selected according to the news label, the news name, the news time and the news keyword is extracted and stored in a cache memory, then the news is respectively compared with files stored in a database through a video file and a voice file, news content is determined after comparison, and then the news content is displayed on a front-end page.
7. The video and speech recognition-based news storage and search method of claim 1, wherein: the search mode of the search engine in S4 is one of an enumeration algorithm, a depth-first search, a breadth-first search, an a algorithm, a backtracking algorithm, a monte carlo tree search, a hash function, and the like.
8. The video and speech recognition-based news storage and search method of claim 1, wherein: the URLs in S5 are addresses of news profiles, respectively, and correspond to news text contents, video contents, voice contents, and picture contents, respectively, through a one-to-many mapping relationship.
9. The video and speech recognition-based news storage and search method of claim 8, wherein: the news text content, the video content, the voice content and the picture content are stored through the one-to-many mapping relation respectively, so that storage disorder and slow retrieval are avoided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010782002.6A CN111930970A (en) | 2020-08-06 | 2020-08-06 | News storage and search method based on video and voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010782002.6A CN111930970A (en) | 2020-08-06 | 2020-08-06 | News storage and search method based on video and voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111930970A true CN111930970A (en) | 2020-11-13 |
Family
ID=73307927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010782002.6A Pending CN111930970A (en) | 2020-08-06 | 2020-08-06 | News storage and search method based on video and voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111930970A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021855A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video searching system based on content |
| US20080086476A1 (en) * | 2006-10-04 | 2008-04-10 | Theodore Jack London Shrader | Method for providing news syndication discovery and competitive awareness |
| US20110202844A1 (en) * | 2010-02-16 | 2011-08-18 | Msnbc Interactive News, L.L.C. | Identification of video segments |
| US9342599B2 (en) * | 2011-05-25 | 2016-05-17 | Thomas Stetson Elliott | Methods and systems for centralized audio and video news product collection, optimization, storage, and distribution |
-
2020
- 2020-08-06 CN CN202010782002.6A patent/CN111930970A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080086476A1 (en) * | 2006-10-04 | 2008-04-10 | Theodore Jack London Shrader | Method for providing news syndication discovery and competitive awareness |
| CN101021855A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video searching system based on content |
| US20110202844A1 (en) * | 2010-02-16 | 2011-08-18 | Msnbc Interactive News, L.L.C. | Identification of video segments |
| CN102163212A (en) * | 2010-02-16 | 2011-08-24 | 微软公司 | Identification of video segments |
| US9342599B2 (en) * | 2011-05-25 | 2016-05-17 | Thomas Stetson Elliott | Methods and systems for centralized audio and video news product collection, optimization, storage, and distribution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8656264B2 (en) | Dynamic aggregation and display of contextually relevant content | |
| US11580181B1 (en) | Query modification based on non-textual resource context | |
| US8200649B2 (en) | Image search engine using context screening parameters | |
| US8713002B1 (en) | Identifying media content in queries | |
| WO2016150083A1 (en) | Information input method and apparatus | |
| CN106682147A (en) | Mass data based query method and device | |
| US20090144240A1 (en) | Method and systems for using community bookmark data to supplement internet search results | |
| US20040199495A1 (en) | Name browsing systems and methods | |
| US20030055810A1 (en) | Front-end weight factor search criteria | |
| US10839013B1 (en) | Generating a graphical representation of relationships among a set of articles and information associated with the set of articles | |
| US8965916B2 (en) | Method and apparatus for providing media content | |
| WO2010106642A1 (en) | Search processing method and apparatus | |
| US8086953B1 (en) | Identifying transient portions of web pages | |
| CN104025077A (en) | Real-Time Natural Language Processing Of Datastreams | |
| CN110888990A (en) | Text recommendation method, device, equipment and medium | |
| JP2011529600A (en) | Method and apparatus for relating datasets by using semantic vector and keyword analysis | |
| JP2015525929A (en) | Weight-based stemming to improve search quality | |
| US20150206101A1 (en) | System for determining infringement of copyright based on the text reference point and method thereof | |
| CN113297457B (en) | High-precision intelligent information resource pushing system and pushing method | |
| WO2014000130A1 (en) | Method or system for automated extraction of hyper-local events from one or more web pages | |
| CN109783599A (en) | Knowledge mapping search method and system based on multi storage | |
| US20090313558A1 (en) | Semantic Image Collection Visualization | |
| US20230090601A1 (en) | System and method for polarity analysis | |
| CN111930970A (en) | News storage and search method based on video and voice recognition | |
| Waitelonis et al. | Use what you have: Yovisto video search engine takes a semantic turn |
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 |