CN108924658B - Bullet screen association input method and device and computer readable storage medium - Google Patents

Bullet screen association input method and device and computer readable storage medium Download PDF

Info

Publication number
CN108924658B
CN108924658B CN201810567284.0A CN201810567284A CN108924658B CN 108924658 B CN108924658 B CN 108924658B CN 201810567284 A CN201810567284 A CN 201810567284A CN 108924658 B CN108924658 B CN 108924658B
Authority
CN
China
Prior art keywords
bullet screen
video
information
association
input
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
Application number
CN201810567284.0A
Other languages
Chinese (zh)
Other versions
CN108924658A (en
Inventor
汪宇星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Bilibili Technology Co Ltd
Original Assignee
Shanghai Bilibili Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Bilibili Technology Co Ltd filed Critical Shanghai Bilibili Technology Co Ltd
Priority to CN201810567284.0A priority Critical patent/CN108924658B/en
Publication of CN108924658A publication Critical patent/CN108924658A/en
Application granted granted Critical
Publication of CN108924658B publication Critical patent/CN108924658B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/488Data services, e.g. news ticker
    • H04N21/4884Data services, e.g. news ticker for displaying subtitles
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/475End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4756End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie

Abstract

The invention relates to a bullet screen association input method, a bullet screen association input device and a computer readable storage medium, wherein the bullet screen association input method acquires current input content by monitoring a bullet screen input window; and generating an alternative item for the user to select according to the content and the video information of the played video, and then generating the bullet screen, thereby forming a bullet screen association input mode based on the video content, wherein the association content is closely associated with the video content and is more likely to be close to the bullet screen content which the user wants to input, thereby facilitating the user to quickly input the bullet screen and further improving the user experience. The bullet screen association input method is simple and convenient to implement, and the application range of the bullet screen association input device is quite wide.

Description

Bullet screen association input method and device and computer readable storage medium
Technical Field
The invention relates to the technical field of internet video application, in particular to the technical field of video barrage, and specifically relates to a barrage association input method and device and a computer-readable storage medium.
Background
The bullet screen refers to a phenomenon that a large amount of comments presented in a subtitle form are on the same picture as a video when the video is watched. A large number of comments which fly above the video are similar to dense shells, so that the name bullet screen is obtained. The barrage can be presented on the video in real time along with the playing of the video, so that the viewer can see other viewers and the barrage sent by the viewer when watching the video.
Because the content of most barrage is mainly the comment that the audience sent to the video content in the short time quantum, therefore barrage has certain temporal requirement, and barrage content and video content mutually correspond can produce better watching and interactive effect. Therefore, the provision of a convenient barrage sending method becomes a key for improving the experience of the video barrage user.
The existing input method can provide a certain association function, but the association content is preset, is irrelevant to the application scene of the video barrage and has no relation with the video watched by the audience, so the accuracy of the association is low, and the barrage input efficiency cannot be improved.
Therefore, how to provide a bullet screen input mode with higher input efficiency to improve the user experience of video bullet screen application becomes a problem to be solved in the field.
Disclosure of Invention
The present invention is directed to overcome the above-mentioned disadvantages in the prior art, and provides associated content more related to video content based on content already input by a user and in combination with video information and other information, so that the user can input a bullet screen quickly, and further the user experience of the user is improved.
In order to achieve the above object, the bullet screen association input method of the present invention comprises the steps of:
(1) starting a video bullet screen player, playing a video and providing a bullet screen input window;
(2) monitoring the bullet screen input window to obtain the current input content;
(3) generating an alternative item according to the current input content and the video information of the played video;
(4) displaying the alternative options;
(5) and generating the bullet screen according to the selection of the alternative options.
In the bullet screen association input method, the step (3) specifically comprises the following steps:
(31) operating a word bank, wherein the word bank comprises the video information;
(32) and searching the word stock by taking the current input content as a keyword to obtain the alternative.
In the bullet screen association input method, the video information comprises image identification information, audio identification information, an existing bullet screen, video label information, channel information and video owner information.
In the bullet screen association input method, the video information is arranged from high to low according to the association degree: image identification information, audio identification information, an existing barrage, video tag information, channel information, and video owner information, wherein the step (32) specifically comprises:
and searching the word stock by taking the current input content as a keyword to obtain a plurality of matching items, and taking a plurality of matching items with high association degrees as the alternative items.
In the bullet screen association input method, the image identification information is subtitle information obtained by identifying subtitles in the video through an image identification technology; the audio identification information is voice information obtained by identifying voice in the video through a voice transcription technology.
In the bullet screen association input method, the subtitle information and the voice information both comprise a time attribute corresponding to a played video time axis, and the closer the time attribute is to the bullet screen input time point, the higher the association degree of the subtitle information and the voice information is.
In the bullet screen association input method, the more the times of the same bullet screen in the existing bullet screen appear, the higher the association degree is.
In the bullet screen association input method, the word stock further comprises preset phrases, and the preset phrases comprise default alternative phrases and video information of other videos.
In the bullet screen association input method, the association degrees in the word stock are arranged from high to low as follows: default alternative phrases, video information for the played video, video information for other videos.
In the bullet screen association input method, the word stock is searched by taking the current input content as a keyword, and the method specifically comprises the following steps:
and searching the word bank by taking the current input content and the synonym and the similar synonym of the current input content as key words.
In the bullet screen association input method, the step (5) specifically comprises the following steps:
(51) monitoring the selection of the alternative item, and filling the selection into the bullet screen input window;
(52) and monitoring the operation of sending the bullet screen, and generating the bullet screen according to the content in the bullet screen input window.
In the bullet screen association input method, the following steps are further specifically included between the step (51) and the step (52):
(51-1) monitoring the deselection operation, and then the bullet screen input window is restored to the state before the step (51) and displaying the alternative items.
In the bullet screen association input method, the step (51-1) is specifically as follows:
and (5) monitoring the deselection operation, restoring the bullet screen input window to the state before the step (51), deleting the cancelled options, updating and displaying the alternative options.
The invention also provides a bullet screen association input device and a computer readable storage medium, the device comprises a processor and a memory, the memory is a computer readable storage medium, a computer program is stored on the memory, and when the computer program is executed by the processor, the bullet screen association input method is realized.
By adopting the bullet screen association input method, the bullet screen association input device and the computer readable storage medium, the current input content is obtained by monitoring the bullet screen input window; and generating an alternative item for the user to select according to the content and the video information of the played video, and then generating the bullet screen, thereby forming a bullet screen association input mode based on the video content, wherein the association content is closer to the possible bullet screen input content of the user, thereby being capable of rapidly inputting the bullet screen and further improving the user experience. The bullet screen association input method is simple and convenient to implement, and the application range of the bullet screen association input device is quite wide.
Drawings
Fig. 1 is a flowchart illustrating the steps of the bullet screen association input method according to the present invention.
Fig. 2 is a schematic interface diagram of a user editing a bullet screen in the bullet screen association input method of the present invention.
Fig. 3 is a schematic diagram of an alternative display interface associated in the bullet screen association input method of the present invention.
Fig. 4 is a schematic interface diagram illustrating a user selecting an association option according to the bullet screen association input method of the present invention.
Fig. 5 is a schematic interface diagram of an input box automatically inputting corresponding bullet screen contents according to user selection in the bullet screen association input method of the present invention.
Detailed Description
In order to clearly understand the technical contents of the present invention, the following examples are given in detail.
Fig. 1 is a flowchart illustrating the steps of the bullet screen association input method according to the present invention.
In one embodiment, the bullet screen association input method comprises the following steps:
(1) starting a video bullet screen player, playing a video and providing a bullet screen input window;
(2) monitoring the bullet screen input window to obtain the current input content;
(3) generating an alternative item according to the current input content and the video information of the played video;
(4) displaying the alternative options;
(5) and generating the bullet screen according to the selection of the alternative options.
In a more preferred embodiment, the step (3) specifically comprises the following steps:
(31) operating a word bank, wherein the word bank comprises the video information;
(32) and searching the word stock by taking the current input content as a keyword to obtain the alternative.
In a further preferred embodiment, the video information includes a correlation degree from high to low: image identification information, audio identification information, an existing barrage, video tag information, channel information, and video owner information, wherein the step (32) specifically comprises:
and searching the word stock by taking the current input content as a keyword to obtain a plurality of matching items, and taking a plurality of matching items with high association degrees as the alternative items.
In a further preferred embodiment, the image recognition information is subtitle information obtained by recognizing subtitles in the video through an image recognition technology; the audio identification information is voice information obtained by identifying voice in the video through a voice transcription technology. And the caption information and the voice information both comprise time attributes corresponding to the time axis of the played video, and the closer the time attributes are to the bullet screen input time point, the higher the association degree of the caption information and the voice information is.
In another further preferred embodiment, the more times the same bullet screen appears in the existing bullet screen, the higher the correlation.
In another further preferred embodiment, said thesaurus further comprises preset phrases comprising default alternative phrases and video information of other videos. In the thesaurus of this embodiment, the association degrees are arranged from high to low as: default alternative phrases, video information for the played video, video information for other videos.
In another further preferred embodiment, the searching the word stock by using the current input content as the keyword specifically comprises:
and searching the word bank by taking the current input content and the synonym and the similar synonym of the current input content as key words.
In another preferred embodiment, the step (5) specifically comprises the following steps:
(51) monitoring the selection of the alternative item, and filling the selection into the bullet screen input window;
(52) and monitoring the operation of sending the bullet screen, and generating the bullet screen according to the content in the bullet screen input window.
In a further preferred embodiment, the following steps are further specifically included between the step (51) and the step (52):
(51-1) monitoring the deselection operation, and then the bullet screen input window is restored to the state before the step (51) and displaying the alternative items.
In a further preferred embodiment, the step (51-1) is specifically:
and (5) monitoring the deselection operation, restoring the bullet screen input window to the state before the step (51), deleting the cancelled options, updating and displaying the alternative options.
The present invention also provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements each bullet screen association input method described in the above embodiments.
The invention also provides a bullet screen association input device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and when the computer program is executed by the processor, the bullet screen association input device realizes the bullet screen association input method of the embodiment.
In practical application, the basic interaction mode of the bullet screen association input method is as follows:
1. a user enters a video and starts a video bullet screen player;
2. monitoring the barrage content input by the user in real time and submitting the barrage content to the back end together with video information;
3. the back end obtains an alternative bullet screen content list through keyword query and search, and returns the list to the user;
4. and the user can automatically complement the bullet screen content by selecting a certain bullet screen content in the list.
The specific interaction flow is illustrated by the following example:
example 1
The user starts the video barrage player to play the video and simultaneously starts the barrage function. In the case where the video already includes an existing barrage (history barrage), the barrage is displayed synchronously. At this time, the player also provides a bullet screen input window for the user to input the bullet screen. At this time, the user may perform barrage editing, for example, as shown in fig. 2, input "dry cup", at this time, the system searches "dry cup" and its synonyms, synonyms or "dry cups" in other languages, including (chers, dry cup, etc.) in the word library run at the back end, the content of the word library includes image identification information, audio identification information, existing barrage, video tag information, channel information and video owner information, and the relevance is arranged from high to low. For example, OCR image recognition results in a video caption with "We come from the cup bar! ", the system will" We come to dry cup Bar! "return to the front end for the user to select, corresponding search is also performed on the rest contents in the lexicon, and after the rest contents are arranged from high to low according to the association degree, 5 to 10 entries with the top association degree are selected as the alternative items, and the alternative item display interface is shown in fig. 3. As shown in fig. 4, after the user selects and clicks one of the association options, as shown in fig. 5, the input box automatically inputs the corresponding bullet screen content, the input cursor moves to the end position, and at this time, the user clicks the send button, and then the sending of the bullet screen is completed. Therefore, the barrage can be edited and sent quickly, the connection between the barrage and the video content is more tight, the video interaction effect is better, meanwhile, the barrage editing time of a user is saved, and the user cannot miss too many video contents.
Example 2
The difference from embodiment 1 is that the image identification information and the audio identification information included in the thesaurus have respective time attributes. Also taking the example that the user inputs "cup dry", if the caption "we come to cup bar 10 minutes ago in the image recognition video! ", the STT speech transcription acquired speech 7 minutes ago" dried the cup. ", 2 minutes ago STT speech transcription got speech" how to dry up? "the information closer to the input time point is more highly correlated, thereby" how dry? "," dry the cup. "," We come to the cup drying bar! "as an alternative for the user to select.
Example 3
The difference from the embodiments 1 and 2 is that the existing barrage included in the thesaurus determines the degree of association according to the number of times of appearance of the same content, and similarly, taking the example that the user inputs "dry cup", if "our dry cup" appears 50 times and "dry cup together" appears 40 times in the existing barrage, the user is provided with the alternative option of the arrangement sequence of "our dry cup" and "dry cup together".
Example 4
The difference from the above embodiment is that the thesaurus also includes preset phrases, i.e. content that is not related to the video being played. The preset phrases include default alternative phrases and video information for other videos. The video information of the default alternative phrase and other videos can be preset manually or can be continuously updated by the user through self-learning and other functions in the using process. In the word stock with preset phrases, the association degree is arranged from high to low as: default alternative phrases, video information for the played video, video information for other videos. Also taking the example of the user inputting "dry cup", if "coin" つロ dry cup "is included in the default candidate phrase and" constant river water is dried "is included in the video information of other videos, OCR image recognition obtains" we come in a dry cup bar | "in the video subtitles! "how did the STT speech transcription get speech" do you dry? ", the priority order of the alternative items is" coin (degree) つロ dry cup "," our dry cup bar! "how to dry the cup? "," dried the bowl of constant river water ".
Example 5
The difference from the above embodiment is that after the user selects an alternative and automatically inputs the content into the barrage edit box, the system monitors not only the sending operation that the user clicks the sending button, but also the cancellation operation (e.g., Ctrl/Command + Z) of the user, and if the cancellation is monitored, the content in the barrage edit box will be returned to the place before the association, and the associated alternative will be expanded again for the user to select. On the basis of embodiment 4, if the revocation is selected after the user selects "no- つロ dry cup", the editing frame is restored to the state where "dry cup" is input.
Example 6
The difference from the above embodiment 5 is that when the user's undo operation is detected, not only the content in the bullet screen editing frame will be returned to the pre-association state, but also the "coin" - つロ dry cup "option that is removed is deleted from the alternative, and after the update," the dry cup bar we come | "is displayed in turn! "how to dry the cup? "," dried the bowl of constant river water ", and other options with a higher priority, etc.
Besides the contents described in the above embodiments, the bullet screen association input method can also set phrases that can be hit, keywords that must exist during search, phrase contents, and the position of the input cursor after selection.
By adopting the bullet screen association input method, the bullet screen association input device and the computer readable storage medium, the current input content is obtained by monitoring the bullet screen input window; and generating an alternative item for the user to select according to the content and the video information of the played video, and then generating the bullet screen, thereby forming a bullet screen association input mode based on the video content, wherein the association content is closer to the possible bullet screen input content of the user, thereby being capable of rapidly inputting the bullet screen and further improving the user experience. The bullet screen association input method is simple and convenient to implement, and the application range of the bullet screen association input device is quite wide.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims (13)

1. A bullet screen association input method is characterized by comprising the following steps:
(1) starting a video bullet screen player, playing a video and providing a bullet screen input window;
(2) monitoring the bullet screen input window to obtain the current input content;
(3) generating an alternative item according to the current input content and the video information of the played video; the method specifically comprises the following steps:
(31) operating a word bank, wherein the word bank comprises the video information, and the video information comprises image identification information, audio identification information, an existing barrage, video label information, channel information and video owner information;
(32) searching the word stock by taking the current input content as a keyword to obtain the alternative item;
(4) displaying the alternative options;
(5) and generating the bullet screen according to the selection of the alternative options.
2. The bullet screen association input method according to claim 1, wherein the video information is arranged from high to low according to the association degree: image identification information, audio identification information, an existing barrage, video tag information, channel information, and video owner information, wherein the step (32) specifically comprises:
and searching the word stock by taking the current input content as a keyword to obtain a plurality of matching items, and taking a plurality of matching items with high association degrees as the alternative items.
3. The bullet screen associated input method according to claim 2, wherein the image recognition information is subtitle information obtained by recognizing subtitles in the video through an image recognition technique; the audio identification information is voice information obtained by identifying voice in the video through a voice transcription technology.
4. The bullet screen associated input method according to claim 3, wherein said caption information and said voice information each include a time attribute corresponding to a time axis of the video to be played, and the closer the time attribute is to the time point of the bullet screen input, the higher the association between the caption information and the voice information is.
5. The bullet screen association input method according to claim 2, wherein the more times the same bullet screen appears in the existing bullet screen, the higher the association degree.
6. The bullet screen association input method of claim 1 wherein said thesaurus further comprises preset phrases, said preset phrases comprising default alternative phrases and video information of other videos.
7. The barrage association input method as claimed in claim 6, wherein the association degree in the thesaurus is arranged from high to low as: default alternative phrases, video information for the played video, video information for other videos.
8. The barrage association input method according to claim 1, wherein the word stock is searched by using the current input content as a keyword, and specifically comprises:
and searching the word bank by taking the current input content and the synonym and the similar synonym of the current input content as key words.
9. The bullet screen association input method according to claim 1, wherein the step (5) specifically comprises the following steps:
(51) monitoring the selection of the alternative item, and filling the selection into the bullet screen input window;
(52) and monitoring the operation of sending the bullet screen, and generating the bullet screen according to the content in the bullet screen input window.
10. The bullet screen association input method according to claim 9, further comprising the following steps between the step (51) and the step (52):
(51-1) monitoring the deselection operation, and then the bullet screen input window is restored to the state before the step (51) and displaying the alternative items.
11. The bullet screen association input method according to claim 10, wherein the step (51-1) is specifically:
and (5) monitoring the deselection operation, restoring the bullet screen input window to the state before the step (51), deleting the cancelled options, updating and displaying the alternative options.
12. A computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the bullet screen associative input method according to any one of claims 1 to 11.
13. A bullet screen association input device comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the bullet screen association input device implements the bullet screen association input method according to any one of claims 1 to 11.
CN201810567284.0A 2018-06-05 2018-06-05 Bullet screen association input method and device and computer readable storage medium Active CN108924658B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810567284.0A CN108924658B (en) 2018-06-05 2018-06-05 Bullet screen association input method and device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810567284.0A CN108924658B (en) 2018-06-05 2018-06-05 Bullet screen association input method and device and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN108924658A CN108924658A (en) 2018-11-30
CN108924658B true CN108924658B (en) 2020-10-27

Family

ID=64418310

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810567284.0A Active CN108924658B (en) 2018-06-05 2018-06-05 Bullet screen association input method and device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN108924658B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110166847B (en) * 2019-06-27 2021-07-23 北京奇艺世纪科技有限公司 Bullet screen processing method and device
CN110519617B (en) * 2019-07-18 2023-04-07 平安科技(深圳)有限公司 Video comment processing method and device, computer equipment and storage medium
CN110430448B (en) * 2019-07-31 2021-09-03 北京奇艺世纪科技有限公司 Bullet screen processing method and device and electronic equipment
CN110740387B (en) * 2019-10-30 2021-11-23 深圳Tcl数字技术有限公司 Barrage editing method, intelligent terminal and storage medium
CN111050223A (en) * 2019-12-27 2020-04-21 维沃移动通信有限公司 Bullet screen information processing method and electronic equipment
CN111669657A (en) * 2020-06-08 2020-09-15 咪咕文化科技有限公司 Video comment method and device, electronic equipment and storage medium
CN112272328B (en) * 2020-10-27 2022-11-18 万翼科技有限公司 Bullet screen recommendation method and related device
CN113242453B (en) * 2021-05-06 2023-04-07 深圳小湃科技有限公司 Barrage playing method, server and computer readable storage medium
CN113343984A (en) * 2021-06-28 2021-09-03 北京奇艺世纪科技有限公司 Bullet screen prompting method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104375663A (en) * 2014-11-11 2015-02-25 广东欧珀移动通信有限公司 Associating input method and device
CN104731554A (en) * 2015-03-30 2015-06-24 北京奇艺世纪科技有限公司 Comment information issuing method and device
JP2015211290A (en) * 2014-04-24 2015-11-24 株式会社ドワンゴ Candidate extraction apparatus, comment distribution system, candidate extraction method, and program
CN105578222A (en) * 2016-02-01 2016-05-11 百度在线网络技术(北京)有限公司 Information push method and device
CN106028161A (en) * 2016-04-29 2016-10-12 乐视控股(北京)有限公司 Bullet screen generation method and apparatus, bullet screen presentation method and apparatus, server and client
CN107040824A (en) * 2017-04-18 2017-08-11 深圳市金立通信设备有限公司 A kind of method and terminal for sending barrage

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015211290A (en) * 2014-04-24 2015-11-24 株式会社ドワンゴ Candidate extraction apparatus, comment distribution system, candidate extraction method, and program
CN104375663A (en) * 2014-11-11 2015-02-25 广东欧珀移动通信有限公司 Associating input method and device
CN104731554A (en) * 2015-03-30 2015-06-24 北京奇艺世纪科技有限公司 Comment information issuing method and device
CN105578222A (en) * 2016-02-01 2016-05-11 百度在线网络技术(北京)有限公司 Information push method and device
CN106028161A (en) * 2016-04-29 2016-10-12 乐视控股(北京)有限公司 Bullet screen generation method and apparatus, bullet screen presentation method and apparatus, server and client
CN107040824A (en) * 2017-04-18 2017-08-11 深圳市金立通信设备有限公司 A kind of method and terminal for sending barrage

Also Published As

Publication number Publication date
CN108924658A (en) 2018-11-30

Similar Documents

Publication Publication Date Title
CN108924658B (en) Bullet screen association input method and device and computer readable storage medium
US20230197069A1 (en) Generating topic-specific language models
US10366169B2 (en) Real-time natural language processing of datastreams
CN110430476B (en) Live broadcast room searching method, system, computer equipment and storage medium
US9098533B2 (en) Voice directed context sensitive visual search
JP5894149B2 (en) Enhancement of meaning using TOP-K processing
CN110753269B (en) Video abstract generation method, intelligent terminal and storage medium
US11570527B2 (en) Method and apparatus for retrieving teleplay content
CN109558513A (en) A kind of content recommendation method, device, terminal and storage medium
CN111294660A (en) Video clip positioning method, server, client and electronic equipment
CN113824972A (en) Live video processing method, device and equipment and computer readable storage medium
EP4150523A1 (en) Systems and methods for retreiving videos using natural language description
CN110309324B (en) Searching method and related device
JP5335500B2 (en) Content search apparatus and computer program
US10657176B1 (en) Associating object related keywords with video metadata
WO2023116785A1 (en) Information display method and apparatus, computer device, and storage medium
CN111223014B (en) Method and system for online generation of subdivision scene teaching courses from a large number of subdivision teaching contents
CN116644246A (en) Search result display method and device, computer equipment and storage medium
CN113127686B (en) Video searching method, device, equipment and storage medium
JP5415550B2 (en) Similar content search apparatus and program

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