CN105183729A - Method and device for retrieving audio/video content - Google Patents
Method and device for retrieving audio/video content Download PDFInfo
- Publication number
- CN105183729A CN105183729A CN201410238636.XA CN201410238636A CN105183729A CN 105183729 A CN105183729 A CN 105183729A CN 201410238636 A CN201410238636 A CN 201410238636A CN 105183729 A CN105183729 A CN 105183729A
- Authority
- CN
- China
- Prior art keywords
- video
- audio
- markup information
- keyword
- multidimensional
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for retrieving audio/video contents, and relates to the field of information retrieval. Multidimensional annotated information of audio/video contents is searched layer by layer, and audio/video fragments corresponding to keywords can be directly retrieved and positioned. Users do not need to browse a whole audio/video file, and the users can find the required audio/video contents, so retrieval efficiency and accuracy are improved. In addition, audio/video contents associated to the audio/video fragments can also be shown.
Description
Technical field
The present invention relates to information retrieval field, particularly a kind of search method of audio-video frequency content and device.
Background technology
At present two kinds of search methods are mainly contained for audio-video frequency content:
A kind of technology is stored by captions, image and the Classification of Speech corresponding to each frame of audio-video document, according to the dissimilar querying condition of user's input, and the database that inquiry is corresponding, thus find the audio-video document of coupling.
Another kind of technology simply marks the key frame of audio-video document, then includes markup information in metadatabase, and user, by search metadata storehouse, finds the audio-video document of coupling.
What prior art found is all audio-video document, and user needs to browse and check that whole audio-video document just can find the audio-video frequency content of needs, recall precision and accuracy lower.
Summary of the invention
An embodiment of the present invention technical matters to be solved is: solve the recall precision and the lower problem of accuracy that exist in audio frequency and video retrieval.
According to an aspect of the embodiment of the present invention, propose a kind of search method of audio-video frequency content, comprising: the retrieval request receiving user; Word segmentation processing is carried out to retrieval request, generates keyword; According to the multidimensional markup information of audio-video frequency content, successively search the corresponding audio frequency and video fragment of keyword.
In one embodiment, the multidimensional markup information of audio-video frequency content has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.
In one embodiment, the method also comprises: according to the logic relation of inclusion of knowledge point, sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, the method also comprises: the mode adopting artificial mark or automatic marking, sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, according to the multidimensional markup information of audio-video frequency content, successively search keyword corresponding audio frequency and video fragment specifically can comprise: the first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
In one embodiment, the method also comprises: be associated audio frequency and video, and in these association audio frequency and video and multidimensional markup information, any point forms mapping relations.
In one embodiment, the method also comprises: what export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment associates audio frequency and video.
In one embodiment, at the multidimensional markup information according to audio-video frequency content, before successively searching the corresponding audio frequency and video fragment of keyword, also comprise: in metadatabase, search the corresponding audio-video frequency content of keyword.
According to another aspect of the embodiment of the present invention, propose a kind of indexing unit of audio-video frequency content, comprising: request receiving module, for receiving the retrieval request of user; Keyword generation module, for carrying out word segmentation processing to retrieval request, generates keyword; Retrieval module, for the multidimensional markup information according to audio-video frequency content, successively searches the corresponding audio frequency and video fragment of keyword.
In one embodiment, the multidimensional markup information of audio-video frequency content has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.
In one embodiment, this device also comprises: markup information sets up module, for the logic relation of inclusion according to knowledge point, sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, markup information sets up module, also for adopting the mode of artificial mark or automatic marking, sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, retrieval module, specifically for: the first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
In one embodiment, this device also comprises: relating module, and for the audio frequency and video that are associated, in these association audio frequency and video and multidimensional markup information, any point forms mapping relations.
In one embodiment, retrieval module, also associates audio frequency and video for what export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment.
In one embodiment, retrieval module, also at the multidimensional markup information according to audio-video frequency content, before successively searching the corresponding audio frequency and video fragment of keyword, searches the corresponding audio-video frequency content of keyword in metadatabase.
The embodiment of the present invention successively searches the multidimensional markup information of audio-video frequency content, directly can retrieve and navigate to the corresponding audio frequency and video fragment of keyword, user can find the audio-video frequency content of needs without the need to browsing whole audio-video document, improve recall precision and accuracy.In addition, the audio-video frequency content of audio frequency and video fragment association can also be represented simultaneously.
By referring to the detailed description of accompanying drawing to exemplary embodiment of the present invention, further feature of the present invention and advantage thereof will become clear.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of a search method embodiment of audio-video frequency content of the present invention.
Fig. 2 is another embodiment schematic flow sheet of search method of audio-video frequency content of the present invention.
Fig. 3 is the structural representation of an indexing unit embodiment of audio-video frequency content of the present invention.
Fig. 4 is the structural representation of another embodiment of indexing unit of audio-video frequency content of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Illustrative to the description only actually of at least one exemplary embodiment below, never as any restriction to the present invention and application or use.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Unless specifically stated otherwise, otherwise positioned opposite, the numerical expression of the parts of setting forth in these embodiments and step and numerical value do not limit the scope of the invention.
Meanwhile, it should be understood that for convenience of description, the size of the various piece shown in accompanying drawing is not draw according to the proportionate relationship of reality.
May not discuss in detail for the known technology of person of ordinary skill in the relevant, method and apparatus, but in the appropriate case, described technology, method and apparatus should be regarded as a part of authorizing instructions.
In all examples with discussing shown here, any occurrence should be construed as merely exemplary, instead of as restriction.Therefore, other example of exemplary embodiment can have different values.
It should be noted that: represent similar terms in similar label and letter accompanying drawing below, therefore, once be defined in an a certain Xiang Yi accompanying drawing, then do not need to be further discussed it in accompanying drawing subsequently.
In order to the problem that the recall precision and accuracy that solve existence in audio frequency and video retrieval are lower, the key frame that the present invention is directed to audio-video document sets up the multifaceted mark system of various dimensions, combine according to the logic defined between the inner different dimensions of system, system outside and various audio, video data storehouse are (as metadatabase, the content data base etc. of audio frequency and video) set up mapping relations, according to the search condition of user, by mark system and the logical relation of inside and outside, search for step by step, find required audio-video document accurately fast, and navigate to concrete audio frequency and video fragment, improve recall precision and accuracy.
The multidimensional markup information of the audio-video frequency content in the embodiment of the present invention has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.Subset is relation of inclusion in logic, therefore, according to the logic relation of inclusion of knowledge point, can set up the multidimensional markup information of audio-video frequency content.Wherein, concrete number of dimensions is not fixed, and can determine according to actual needs.Illustrate the multidimensional markup information of audio-video frequency content below.
Such as, see table 1, a four-dimensional instructional video resource, one dimension with knowledge point be mark (knowledge point 1, knowledge point 2 ...), then the two-dimentional some secondary knowledge points comprised with inside, a certain knowledge point are for mark (knowledge point 1.1, knowledge point 1.2, knowledge point 2.1, knowledge point 2.2, knowledge point 2.3 ...), three-dimensional then with more concrete three grades of knowledge points for mark (knowledge point 1.1.1, knowledge point 1.1.2, knowledge point 1.2.1, knowledge point 1.2.2 ...); The four-dimension is concrete video segment information, such as, video segment 1 is the experiment video of knowledge point 1.1, and video segment 2 is experiment videos of knowledge point 1.2.1, video segment 3 is experiment videos etc. of knowledge point 1.2.2, and the corresponding relation of other video segments and knowledge point is illustrated no longer one by one.
Table 1
In order to make the solution of the present invention clearly, enumerate the example of an actual multidimensional mark below.See table 2, a four-dimensional instructional video resource, one dimension take knowledge point as mark (solid geometry, trigonometric function, organism, ), then with the inner some secondary knowledge points comprised, a certain knowledge point, for mark, (solid geometry is divided into volume and area to two dimension, trigonometric function is divided into sin and cos, organism is divided into molecular formula and reaction, ), three-dimensional then with more concrete three grades of knowledge points for mark (volume is divided into square and cylindrical volume, area is divided into circular cone, rectangular parallelepiped and leg-of-mutton area, knowledge point sin is divided into definition and evaluation technique, knowledge point cos is divided into definition and evaluation technique, molecular formula is divided into memorize and writes, reaction is divided into principle, equation and experiment, ), the four-dimension is concrete video segment information, such as, video segment 1 is the instructional video fragment of square volume, video segment 2 is instructional video fragments of cylinder volume, video segment 3 is instructional video fragments of circular cone area, video segment 4 is instructional video fragments of rectangular parallelepiped area, video segment 5 is instructional video fragments of triangle area, video segment 6 is instructional video fragments of sin, video segment 7 is instructional video fragments of cos, video segment 8 is instructional video fragments of molecular formula, video segment 9 is the principle of reaction and equational instructional video fragment, video segment 10 is video segments of the experiment of reaction.
Table 2
In one embodiment, the mode of artificial mark or automatic marking can be adopted, set up the multidimensional markup information of audio-video frequency content.Artificial mark is by the logic relation of inclusion of user according to knowledge point, sets up the multidimensional markup information of audio-video frequency content by hand.Automatic marking can extract key frame of video automatically, the content of analysis of key frame and scene, in conjunction with the logic relation of inclusion of the knowledge point preset, automatically sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, the audio frequency and video fragment in multidimensional markup information can in the corresponding key frame marker initial time of audio-video document, and namely playing audio-video fragment starts to play this audio-video document at the key frame being marked with initial time.
In one embodiment, can also be associated audio frequency and video, in these association audio frequency and video and multidimensional markup information, any point forms mapping relations, thus according to the setting of user, what can export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment associates audio frequency and video simultaneously.Such as, see table 2, set up the associated video of " organism-reaction-experiment ": video segment 11, about one section of demonstration video doing to test of organism reaction, then when output video 10 " instructional video of organism reaction ", can also export " the experiment video of organism reaction ".
Fig. 1 is the schematic flow sheet of a search method embodiment of audio-video frequency content of the present invention.As shown in Figure 1, search method comprises the following steps:
Step S101, receives the retrieval request of user.
Step S103, carries out word segmentation processing to retrieval request, and generate keyword, concrete segmenting method can with reference to prior art, and the present invention is not construed as limiting this.
Step S105, according to the multidimensional markup information of audio-video frequency content, successively searches the corresponding audio frequency and video fragment of keyword.
In step S105, according to the multidimensional markup information of audio-video frequency content, successively search keyword corresponding audio frequency and video fragment specifically can comprise: the first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
Fig. 2 is another embodiment schematic flow sheet of search method of audio-video frequency content of the present invention.
As shown in Figure 2, step S204 can also be performed before step S105: in metadatabase, search the corresponding audio-video frequency content of keyword, obtain preliminary search result, reduce query context.
As shown in Figure 2, step S206 can also be performed: judge Query Result whether non-NULL after step S105, if non-NULL, export the audio frequency and video fragment (step S207) that the most high-dimensional non-NULL Query Result is corresponding, if neither one non-NULL Query Result, then can inquire about caption database, analyze captions, mate, draw Query Result (step S208).
In one embodiment, if establish association audio frequency and video, then according to user's needs, while output sound video segment, its association audio frequency and video (step S209) can also be exported, that is, export simultaneously the corresponding audio frequency and video fragment of keyword and with this audio frequency and video fragment there are mapping relations associate audio frequency and video.
In one embodiment, if retrieve multiple audio frequency and video fragment or/and association audio frequency and video, can also according to degree of correlation to the audio frequency and video fragment retrieved or/and association audio frequency and video sort, maximally related audio-video frequency content is presented to user, improve recall precision further.
Fig. 3 is the structural representation of an indexing unit embodiment of audio-video frequency content of the present invention.As shown in Figure 3, indexing unit comprises:
Request receiving module 301, for receiving the retrieval request of user;
Keyword generation module 302, for carrying out word segmentation processing to retrieval request, generates keyword; And,
Retrieval module 303, for the multidimensional markup information according to audio-video frequency content, successively searches the corresponding audio frequency and video fragment of keyword.
In one embodiment, the multidimensional markup information of audio-video frequency content has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.
In one embodiment, retrieval module 303, specifically for: the first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
In one embodiment, retrieval module 303, also at the multidimensional markup information according to audio-video frequency content, before successively searching the corresponding audio frequency and video fragment of keyword, searches the corresponding audio-video frequency content of keyword in metadatabase.
Fig. 4 is another example structure schematic diagram of indexing unit of audio-video frequency content of the present invention.
As shown in Figure 4, indexing unit also comprises: markup information sets up module 404, for the logic relation of inclusion according to knowledge point, sets up the multidimensional markup information of audio-video frequency content.
In one embodiment, markup information sets up module 404, also for adopting the mode of artificial mark or automatic marking, sets up the multidimensional markup information of audio-video frequency content.
As shown in Figure 4, indexing unit also comprises: relating module 405, and for the audio frequency and video that are associated, in these association audio frequency and video and multidimensional markup information, any point forms mapping relations.Accordingly, retrieval module 303, also associates audio frequency and video for what export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment.
The embodiment of the present invention successively searches the multidimensional markup information of audio-video frequency content, directly can retrieve and navigate to the corresponding audio frequency and video fragment of keyword, user can find the audio-video frequency content of needs without the need to browsing whole audio-video document, improve recall precision and accuracy.In addition, the audio-video frequency content of audio frequency and video fragment association can also be represented simultaneously.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (16)
1. a search method for audio-video frequency content, comprising:
Receive the retrieval request of user;
Word segmentation processing is carried out to retrieval request, generates keyword;
According to the multidimensional markup information of audio-video frequency content, successively search the corresponding audio frequency and video fragment of keyword.
2. method according to claim 1, is characterized in that, the multidimensional markup information of described audio-video frequency content has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.
3. method according to claim 1, is characterized in that, also comprises: according to the logic relation of inclusion of knowledge point, sets up the multidimensional markup information of audio-video frequency content.
4. method according to claim 1, is characterized in that, also comprises: the mode adopting artificial mark or automatic marking, sets up the multidimensional markup information of audio-video frequency content.
5. method according to claim 1, is characterized in that, the described multidimensional markup information according to audio-video frequency content, successively searches the corresponding audio frequency and video fragment of keyword and comprises:
The first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
6. method according to claim 1, is characterized in that, also comprises:
Be associated audio frequency and video, and in these association audio frequency and video and multidimensional markup information, any point forms mapping relations.
7. method according to claim 6, is characterized in that, also comprises:
What export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment associates audio frequency and video.
8. method according to claim 1, is characterized in that, at the multidimensional markup information according to audio-video frequency content, before successively searching the corresponding audio frequency and video fragment of keyword, also comprises: in metadatabase, search the corresponding audio-video frequency content of keyword.
9. an indexing unit for audio-video frequency content, comprising:
Request receiving module, for receiving the retrieval request of user;
Keyword generation module, for carrying out word segmentation processing to retrieval request, generates keyword;
Retrieval module, for the multidimensional markup information according to audio-video frequency content, successively searches the corresponding audio frequency and video fragment of keyword.
10. device according to claim 9, is characterized in that, the multidimensional markup information of described audio-video frequency content has two-dimentional markup information at least, and every one dimension markup information is the subset of one dimension markup information on it.
11. devices according to claim 9, is characterized in that, also comprise:
Markup information sets up module, for the logic relation of inclusion according to knowledge point, sets up the multidimensional markup information of audio-video frequency content.
12. devices according to claim 11, is characterized in that,
Markup information sets up module, also for adopting the mode of artificial mark or automatic marking, sets up the multidimensional markup information of audio-video frequency content.
13. devices according to claim 9, is characterized in that, described retrieval module, specifically for:
The first dimension markup information according to audio-video frequency content searches the corresponding audio frequency and video fragment of keyword, if Query Result non-NULL, continue to search the corresponding audio frequency and video fragment of keyword at the lower one dimension markup information that Query Result is corresponding, repeat this search procedure, until Query Result is empty, export the audio frequency and video fragment that the most high-dimensional non-NULL Query Result is corresponding.
14. devices according to claim 9, is characterized in that, also comprise:
Relating module, for the audio frequency and video that are associated, in these association audio frequency and video and multidimensional markup information, any point forms mapping relations.
15. devices according to claim 14, is characterized in that,
Described retrieval module, also associates audio frequency and video for what export the corresponding audio frequency and video fragment of keyword and have mapping relations with this audio frequency and video fragment.
16. devices according to claim 9, it is characterized in that, described retrieval module, also at the multidimensional markup information according to audio-video frequency content, before successively searching the corresponding audio frequency and video fragment of keyword, in metadatabase, search the corresponding audio-video frequency content of keyword.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410238636.XA CN105183729A (en) | 2014-05-30 | 2014-05-30 | Method and device for retrieving audio/video content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410238636.XA CN105183729A (en) | 2014-05-30 | 2014-05-30 | Method and device for retrieving audio/video content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105183729A true CN105183729A (en) | 2015-12-23 |
Family
ID=54905818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410238636.XA Pending CN105183729A (en) | 2014-05-30 | 2014-05-30 | Method and device for retrieving audio/video content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105183729A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228643A (en) * | 2016-12-21 | 2018-06-29 | 北京视联动力国际信息技术有限公司 | A kind of search method and system |
| CN110430466A (en) * | 2019-08-13 | 2019-11-08 | 陈嘉涵 | A kind of audio/video acquisition method and device based on AI identification |
| CN111368139A (en) * | 2020-02-13 | 2020-07-03 | 浙江工业大学之江学院 | Video information searching method and device, computer equipment and storage medium |
| CN111510765A (en) * | 2020-04-30 | 2020-08-07 | 浙江蓝鸽科技有限公司 | Audio label intelligent labeling method and device based on teaching video |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799684A (en) * | 2012-07-27 | 2012-11-28 | 成都索贝数码科技股份有限公司 | Video-audio file catalogue labeling, metadata storage indexing and searching method |
| CN103198067A (en) * | 2012-01-06 | 2013-07-10 | 卓望数码技术（深圳）有限公司 | Business searching method and system |
| CN103559317A (en) * | 2013-11-22 | 2014-02-05 | 合一网络技术(北京)有限公司 | Mixed word segmentation and labeling method and system for general video meta-information |
| CN103593363A (en) * | 2012-08-15 | 2014-02-19 | 中国科学院声学研究所 | Video content indexing structure building method and video searching method and device |
-
2014
- 2014-05-30 CN CN201410238636.XA patent/CN105183729A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198067A (en) * | 2012-01-06 | 2013-07-10 | 卓望数码技术（深圳）有限公司 | Business searching method and system |
| CN102799684A (en) * | 2012-07-27 | 2012-11-28 | 成都索贝数码科技股份有限公司 | Video-audio file catalogue labeling, metadata storage indexing and searching method |
| CN103593363A (en) * | 2012-08-15 | 2014-02-19 | 中国科学院声学研究所 | Video content indexing structure building method and video searching method and device |
| CN103559317A (en) * | 2013-11-22 | 2014-02-05 | 合一网络技术(北京)有限公司 | Mixed word segmentation and labeling method and system for general video meta-information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228643A (en) * | 2016-12-21 | 2018-06-29 | 北京视联动力国际信息技术有限公司 | A kind of search method and system |
| CN110430466A (en) * | 2019-08-13 | 2019-11-08 | 陈嘉涵 | A kind of audio/video acquisition method and device based on AI identification |
| CN110430466B (en) * | 2019-08-13 | 2021-10-29 | 陈嘉涵 | Audio and video acquisition method and device based on AI identification |
| CN111368139A (en) * | 2020-02-13 | 2020-07-03 | 浙江工业大学之江学院 | Video information searching method and device, computer equipment and storage medium |
| CN111510765A (en) * | 2020-04-30 | 2020-08-07 | 浙江蓝鸽科技有限公司 | Audio label intelligent labeling method and device based on teaching video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Scalable mobile image retrieval by exploring contextual saliency | |
| TWI297842B (en) | Method and apparatus for content representation and retrieval in concept model space | |
| US20180349735A1 (en) | Method and Device for Comparing Similarities of High Dimensional Features of Images | |
| US11580181B1 (en) | Query modification based on non-textual resource context | |
| US8577882B2 (en) | Method and system for searching multilingual documents | |
| CN109145110B (en) | Label query method and device | |
| CN109918555B (en) | Method, apparatus, device and medium for providing search suggestions | |
| TW201339863A (en) | Device and method for recognizing and searching image | |
| CN104811742A (en) | Video data storage method and device | |
| US10152540B2 (en) | Linking thumbnail of image to web page | |
| CN101470710B (en) | Method for positioning content of multimedia file | |
| CN106446235A (en) | Video searching method and device | |
| TW201610724A (en) | Method and system for searching applications | |
| WO2015096625A1 (en) | Information fragment translating method and system | |
| CN105183729A (en) | Method and device for retrieving audio/video content | |
| JP2007328311A (en) | Multi-media data management method and device therefor | |
| CN103268345A (en) | Method and device for retrieving film and television data | |
| CN103914455A (en) | Method and device for retrieving interest points | |
| CN106469188A (en) | A kind of entity disambiguation method and device | |
| CN104679764A (en) | Method and device for searching graph data | |
| CN103152633A (en) | Method and device for identifying key word | |
| JP2007164633A (en) | Content retrieval method, system thereof, and program thereof | |
| CN113254665A (en) | Knowledge graph expansion method and device, electronic equipment and storage medium | |
| CN102902701B (en) | Information query system and method | |
| CN105630837B (en) | Media record searching method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151223 |