CN112269899A - Video retrieval method based on deep learning - Google Patents
Video retrieval method based on deep learning Download PDFInfo
- Publication number
- CN112269899A CN112269899A CN202011127370.3A CN202011127370A CN112269899A CN 112269899 A CN112269899 A CN 112269899A CN 202011127370 A CN202011127370 A CN 202011127370A CN 112269899 A CN112269899 A CN 112269899A
- Authority
- CN
- China
- Prior art keywords
- video
- search
- learning
- searching
- method based
- 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
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- 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
- G06F16/73—Querying
-
- 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
Abstract
The invention discloses a video retrieval method based on deep learning, which comprises the steps of establishing a retrieval frame, wherein the retrieval frame is used for video distinguishing, the retrieval frame mainly comprises title bar searching, type searching, character searching and uploading time searching, the title bar searching, the type searching, the character searching and the uploading time searching can be simultaneously searched, and symbols are used for carrying out intervals among the title bar searching, the type searching, the character searching and the uploading time searching. The video retrieval method based on deep learning solves the problems that the conventional retrieval technology searches through characters and searches videos according to the names of the characters, but the search is performed only through the characters in a title bar, so that a large number of videos with the searched characters appear, time is brought to screening, and some videos irrelevant to learning appear, so that the screening is inaccurate.
Description
Technical Field
The invention relates to the technical field of video retrieval, in particular to a video retrieval method based on deep learning.
Background
The internet, also known as an international network, refers to a huge network formed by connecting networks in series, and these networks are connected by a set of general protocols to form a logically single huge international network. Generally, the Internet refers generally to the Internet, and the Internet refers specifically to the Internet. This method of interconnecting computer networks may be referred to as "internetworking", and on this basis, a worldwide internetworking network, referred to as the internet, has been developed to cover the world, i.e., a network structure of interconnected networks. The Internet is not the same as the world wide web, which is a global system formed by interlinking based on hypertext and is one of the services provided by the Internet, and the Internet means the Internet, also called Internet (Internet) and the Internet, which are huge networks formed by connecting networks in series according to transliteration. These networks are connected by a set of common protocols to form a logically single and huge global network, in which there are network devices such as switches, routers, etc., various connection links, a wide variety of servers and countless computers, terminals. In recent years, along with the rapid development of the internet, the network becomes a main approach for people to entertain and acquire information, in the process, a large amount of video data is accumulated on the internet, the existing rather mature text retrieval technology can help people to acquire information, and the video retrieval technology can help people to search other videos related to a certain video, so that the video retrieval technology has great attraction to both academic circles and industrial circles.
The current retrieval technology commonly searches through characters and searches videos according to the names of the characters, but the search only through the characters in a title bar can cause a large number of videos with the searched characters to appear, so that not only can time be brought to screening, but also some videos irrelevant to learning can appear, and the screening is inaccurate.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a video retrieval method based on deep learning, which solves the problems that the conventional retrieval technology commonly searches for texts and searches videos according to the names of the texts, but the search is carried out only by the texts in a title bar, so that a large number of videos with the searched texts appear, not only can time be brought to screening, but also some videos irrelevant to learning appear, and the screening is inaccurate.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: a video retrieval method based on deep learning, a video retrieval method based on deep learning, including the following steps;
step 1, establishing a learning video inventory, namely firstly establishing a database, wherein the title of the database is a learning class, and storing all videos needing to be titled as learning in the database;
step 3, establishing a display block chain, and presenting the video searched by the retrieval frame;
step 4, matrix video sequencing, namely sequencing the displayed video screens on a matrix interface;
and 6, in a downloading mode, downloading the required learning video, storing the video into a database, and watching the video offline through a background.
Preferably, the database in step 1 includes the following parts,
first, title bar;
second, type;
thirdly, a character;
and fourthly, uploading time.
Preferably, the title bar is a general name of the learning video, the types of the learning video are all course classifications in learning, the characters are names and nicknames of teachers, and the uploading time is the year, month, day and time of the uploading network.
Preferably, the search box of step 2 mainly includes the following functions,
firstly, title bar searching;
secondly, searching for types;
thirdly, searching people;
and fourthly, searching for uploading time.
Preferably, the title bar search, the type search, the person search and the uploading time search can be performed simultaneously, and the title bar search, the type search, the person search and the uploading time search are performed at intervals by using symbols, for example;
the symbol is '/',
the search mode is title bar search/type search/person search/upload time search.
Preferably, in the step 3, the display block chain performs next selection in a scrolling manner during the display process, wherein the number of the interface videos can be selected, and the change of the number correspondingly changes the size of the videos in the interface.
Preferably, the size of the video can be automatically set in a setting mode, and the scaling of the video scaling is changed according to the requirement of the video.
Preferably, the online mode and the download mode in the steps 5 and 6 are viewed online and offline by means of network traffic and a wireless network.
(III) advantageous effects
The invention provides a video retrieval method based on deep learning. Compared with the prior art, the method has the following beneficial effects:
(1) the video retrieval method based on deep learning comprises the steps of establishing a retrieval frame, wherein the retrieval frame is used for video distinguishing and mainly comprises the following functions of searching a first title bar; secondly, searching for types; thirdly, searching people; and fourthly, uploading time search, wherein simultaneous search can be realized among the title bar search, the type search, the character search and the uploading time search, and symbols are used for carrying out intervals among the title bar search, the type search, the character search and the uploading time search, so that the problems that the search is carried out through characters and the video search is carried out according to the names of the characters in the conventional search technology, but the search is carried out only through the characters in the title bar, a large number of videos with the searched characters can appear, time can be brought to screening, and some videos irrelevant to learning can appear, so that the screening is inaccurate are solved.
(2) According to the video retrieval method based on deep learning, the next face is selected in a rolling mode in the display process through the display block chain, the number of interface videos can be selected, the size of the videos in the interface is correspondingly changed by changing the number, the size of the videos can be automatically set in a setting mode, and the scaling of the videos is changed according to the self needs, so that the experience feeling of different people in retrieval is met.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of a comparative example of the practice of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described, 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.
Referring to fig. 2 of the drawings, a schematic diagram of a display device,
example 1
The embodiment of the invention provides a technical scheme that: a video retrieval method based on deep learning, a video retrieval method based on deep learning, including the following steps;
step 1, establishing a learning video inventory, namely firstly establishing a database, wherein the title of the database is a learning class, and storing all videos needing to be titled as learning in the database;
step 3, establishing a display block chain, and presenting the video searched by the retrieval frame;
step 4, matrix video sequencing, namely sequencing the displayed video screens on a matrix interface;
and 6, in a downloading mode, downloading the required learning video, storing the video into a database, and watching the video offline through a background.
Preferably, the database in step 1 comprises four major parts,
first, title bar;
and the second, type.
Preferably, the title bar is a general name of the learning video, and the type is all course classes in the learning.
Preferably, the search box of step 2 mainly includes the following functions,
firstly, title bar searching;
second, type search.
Preferably, the title bar search and the genre search are both spaced apart using symbols, e.g.;
the symbol is '/',
the search mode is title bar search/type search.
Preferably, in step 3, the display block chain performs next selection in a scrolling manner during the display process, wherein the number of the interface videos can be selected, and the change of the number correspondingly changes the size of the videos in the interface.
Preferably, the size of the video can be automatically set in a setting mode, and the scaling of the video scaling can be changed according to the needs of the user.
Preferably, the online mode and the download mode in step 5 and step 6 are viewed online and offline by means of a wireless network.
Example 2
The embodiment of the invention provides a technical scheme that: a video retrieval method based on deep learning, a video retrieval method based on deep learning, including the following steps;
step 1, establishing a learning video inventory, namely firstly establishing a database, wherein the title of the database is a learning class, and storing all videos needing to be titled as learning in the database;
step 3, establishing a display block chain, and presenting the video searched by the retrieval frame;
step 4, matrix video sequencing, namely sequencing the displayed video screens on a matrix interface;
and 6, in a downloading mode, downloading the required learning video, storing the video into a database, and watching the video offline through a background.
Preferably, the database in step 1 comprises four major parts,
first, title bar;
second, type;
thirdly, a person.
Preferably, the title bar is a general name of the learning video, the type is all course categories in the learning, and the character is a name and a nickname of the teacher.
Preferably, the search box of step 2 mainly includes the following functions,
firstly, title bar searching;
secondly, searching for types;
thirdly, searching for people.
Preferably, simultaneous searches can be implemented between the title bar search, the genre search and the people search, and the title bar search, the genre search and the people search are all spaced by using symbols, for example;
the symbol is '/',
the search mode is title bar search/type search/person search.
Preferably, in step 3, the display block chain performs next selection in a scrolling manner during the display process, wherein the number of the interface videos can be selected, and the change of the number correspondingly changes the size of the videos in the interface.
Preferably, the size of the video can be automatically set in a setting mode, and the scaling of the video scaling can be changed according to the needs of the user.
Preferably, the online mode and the download mode in step 5 and step 6 are viewed online and offline by means of network traffic and wireless network.
Example 3
The embodiment of the invention provides a technical scheme that: a video retrieval method based on deep learning, a video retrieval method based on deep learning, including the following steps;
step 1, establishing a learning video inventory, namely firstly establishing a database, wherein the title of the database is a learning class, and storing all videos needing to be titled as learning in the database;
step 3, establishing a display block chain, and presenting the video searched by the retrieval frame;
step 4, matrix video sequencing, namely sequencing the displayed video screens on a matrix interface;
and 6, in a downloading mode, downloading the required learning video, storing the video into a database, and watching the video offline through a background.
Preferably, the database in step 1 comprises four major parts,
first, title bar;
second, type;
thirdly, a character;
and fourthly, uploading time.
Preferably, the title bar is a general name of the learning video, the types are all course classifications in the learning, the character is a name and a nickname of a teacher, and the uploading time is the year, month, day and time of the uploading network.
Preferably, the search box of step 2 mainly includes the following functions,
firstly, title bar searching;
secondly, searching for types;
thirdly, searching people;
and fourthly, searching for uploading time.
Preferably, simultaneous searches can be performed between the title bar search, the genre search, the person search, and the upload time search, and the title bar search, the genre search, the person search, and the upload time search are spaced using symbols, for example;
the symbol is '/',
the search mode is title bar search/type search/person search/upload time search.
Preferably, in step 3, the display block chain performs next selection in a scrolling manner during the display process, wherein the number of the interface videos can be selected, and the change of the number correspondingly changes the size of the videos in the interface.
Preferably, the size of the video can be automatically set in a setting mode, and the scaling of the video scaling can be changed according to the needs of the user.
Preferably, the online mode and the download mode in step 5 and step 6 are viewed online and offline by means of network traffic and wireless network.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
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 (8)
1. A video retrieval method based on deep learning is characterized by comprising the following steps;
step 1, establishing a learning video inventory, namely firstly establishing a database, wherein the title of the database is a learning class, and storing all videos needing to be titled as learning in the database;
step 2, establishing a retrieval frame, wherein the retrieval frame is used for video distinguishing;
step 3, establishing a display block chain, and presenting the video searched by the retrieval frame;
step 4, matrix video sequencing, namely sequencing the displayed video screens on a matrix interface;
step 5, in an online mode, directly watching and learning;
and 6, in a downloading mode, downloading the required learning video, storing the video into a database, and watching the video offline through a background.
2. The video retrieval method based on deep learning of claim 1, wherein: the database in said step 1 comprises the following parts,
first, title bar;
second, type;
thirdly, a character;
and fourthly, uploading time.
3. The video retrieval method based on deep learning of claim 2, wherein: the title column is a general name of the learning video, the types of the learning video are all course classifications in learning, the characters are names and nicknames of teachers, and the uploading time is the year, month, day and time of the uploading network.
4. The video retrieval method based on deep learning of claim 1, wherein: the search box of step 2 mainly comprises the following functions,
firstly, title bar searching;
secondly, searching for types;
thirdly, searching people;
and fourthly, searching for uploading time.
5. The video retrieval method based on deep learning of claim 1, wherein: the title bar search, the type search, the character search and the uploading time search can be simultaneously searched, and the title bar search, the type search, the character search and the uploading time search are all separated by using symbols, for example;
the symbol is '/',
the search mode is title bar search/type search/person search/upload time search.
6. The video retrieval method based on deep learning of claim 1, wherein: and 3, selecting the next surface of the display block chain in a rolling mode in the display process in the step 3, wherein the quantity of the interface videos can be selected, and the change of the quantity correspondingly changes the size of the videos in the interface.
7. The video retrieval method based on deep learning of claim 6, wherein: the size of the video can be automatically set in a setting mode, and the scaling of the video can be changed according to the self requirement.
8. The video retrieval method based on deep learning of claim 1, wherein: and the online mode and the downloading mode in the steps 5 and 6 are viewed online and offline in a network flow and wireless network mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127370.3A CN112269899A (en) | 2020-10-20 | 2020-10-20 | Video retrieval method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127370.3A CN112269899A (en) | 2020-10-20 | 2020-10-20 | Video retrieval method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112269899A true CN112269899A (en) | 2021-01-26 |
Family
ID=74341191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011127370.3A Pending CN112269899A (en) | 2020-10-20 | 2020-10-20 | Video retrieval method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112269899A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836350A (en) * | 2021-09-23 | 2021-12-24 | 深圳绿米联创科技有限公司 | Video retrieval method, system, device, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831213A (en) * | 2012-08-16 | 2012-12-19 | 广东小天才科技有限公司 | Method and device for searching learning content and electronic product |
| CN106157203A (en) * | 2016-06-16 | 2016-11-23 | 北京数智源科技股份有限公司 | Micro-teaching platform |
| CN107229737A (en) * | 2017-06-14 | 2017-10-03 | 广东小天才科技有限公司 | The method and electronic equipment of a kind of video search |
| CN109359240A (en) * | 2018-09-07 | 2019-02-19 | 陈包容 | A method of automation search |
| CN110717068A (en) * | 2019-08-27 | 2020-01-21 | 中山大学 | Video retrieval method based on deep learning |
| CN111506771A (en) * | 2020-04-22 | 2020-08-07 | 上海极链网络科技有限公司 | Video retrieval method, device, equipment and storage medium |
-
2020
- 2020-10-20 CN CN202011127370.3A patent/CN112269899A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831213A (en) * | 2012-08-16 | 2012-12-19 | 广东小天才科技有限公司 | Method and device for searching learning content and electronic product |
| CN106157203A (en) * | 2016-06-16 | 2016-11-23 | 北京数智源科技股份有限公司 | Micro-teaching platform |
| CN107229737A (en) * | 2017-06-14 | 2017-10-03 | 广东小天才科技有限公司 | The method and electronic equipment of a kind of video search |
| CN109359240A (en) * | 2018-09-07 | 2019-02-19 | 陈包容 | A method of automation search |
| CN110717068A (en) * | 2019-08-27 | 2020-01-21 | 中山大学 | Video retrieval method based on deep learning |
| CN111506771A (en) * | 2020-04-22 | 2020-08-07 | 上海极链网络科技有限公司 | Video retrieval method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836350A (en) * | 2021-09-23 | 2021-12-24 | 深圳绿米联创科技有限公司 | Video retrieval method, system, device, storage medium and electronic equipment |
| CN113836350B (en) * | 2021-09-23 | 2024-02-27 | 深圳绿米联创科技有限公司 | Video retrieval method, system, device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8943035B2 (en) | Distributing web applications across a pre-existing web | |
| CN106055617A (en) | Data pushing method and device | |
| CN105095480A (en) | Providing link to portion of media object in real time in social networking update | |
| CN105245924B (en) | The video player of the push of video information and display methods and application this method | |
| CN102779136A (en) | Method and device for information search | |
| CN102592298A (en) | Visual treatment for a user interface in a content integration framework | |
| CN102622390A (en) | Application recommending method and application recommending server in mobile terminal | |
| CN108492290A (en) | Image evaluation method and system | |
| CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
| CN108230025A (en) | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement | |
| CN107798147A (en) | A kind of news client and its information push method | |
| CN104679820A (en) | Search result ordering method and search result ordering device | |
| CN110134845A (en) | Project public sentiment monitoring method, device, computer equipment and storage medium | |
| US20020062358A1 (en) | Review data retrieval system | |
| CN112269899A (en) | Video retrieval method based on deep learning | |
| CN103279908A (en) | Data pushing method for educational information system | |
| KR20180096341A (en) | System for implementing educational contents social curator based on ontology supporting mooc and flipped learning on social platform and method thereof | |
| CN108763369A (en) | A kind of video searching method and device | |
| CN110008395A (en) | Comment on rendering method, device, storage medium and the terminal of content | |
| CN101685445A (en) | Method for expressing distance priority of network geographic information subject matters | |
| CN103324720A (en) | Personalized recommendation method and system according to user state | |
| CN110188277A (en) | A kind of recommended method and device of resource | |
| CN115168637A (en) | Method, system and storage medium for adding label to picture | |
| US20070016652A1 (en) | Dynamic image display | |
| CN104881501A (en) | Automatic Internet information obtaining and pushing method |
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 |