CN104599692A - Recording method and device and recording content searching method and device - Google Patents
Recording method and device and recording content searching method and device Download PDFInfo
- Publication number
- CN104599692A CN104599692A CN201410774335.9A CN201410774335A CN104599692A CN 104599692 A CN104599692 A CN 104599692A CN 201410774335 A CN201410774335 A CN 201410774335A CN 104599692 A CN104599692 A CN 104599692A
- Authority
- CN
- China
- Prior art keywords
- recording
- image
- audio
- word
- keyword
- 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.)
- Granted
Links
Landscapes
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses a recording method. The recording method comprises step one, performing audio recording through a recording device; step two, performing once or multi-time image shooting through the recording device during audio recording as the recording device comprises an image shooting part, and recording the positions of all image shooting moments on a recorded audio time axis; step three, saving recorded audio, shot images and the positions of the image shooting moments on the recorded audio time axis. The invention further discloses the recording device for implementing the recording method, a searching method for recording contents from the recording method and a recording content searching device. By means of the recording method and device the recording content searching method and device, images related to the recording contents are obtained in a shooting mode during recording, the images or information recorded on the images are or is used as the recording content searching basis, searching of the recording contents is achieved, the step is simple and convenient, usage is facilitated, and the accuracy is high.
Description
Technical field
The present invention relates to a kind of way of recording.The invention still further relates to a kind of recording device.The present invention relates to again a kind of data search method, especially a kind of recording substance searching method.The present invention relates to a kind of data serching device again, especially a kind of recording substance searcher.
Background technology
Along with the development of infotech, people can touch increasing electronic data in life.In order to obtain the data that oneself needs from the electronic data of magnanimity, data searching technology just becomes a kind of vital technology.But due to the standardization of text code, the search for text data is fairly simple comparatively speaking, and the result of retrieval is also more accurate.Such as, but just more difficult for the search of voice data, current existing way identifies audio data content, identifies the language content in audio frequency, and then search in the mode of text search.Like this, user just in a section audio, can search the fragment oneself needed.Instant audio content is very long, and user need not all play, and also can obtain the fragment required for oneself, improves the efficiency of voice data search greatly.Because identified content comes from voice data itself, the voice data current with this identification content has natural relevance, therefore, it is possible to be positioned to the audio content place of user's needs according to the content of this identification.But, can ground unrest be there is when voice data is recorded, sometimes also can along with the change of the factor such as intonation, tone, these all can cause audio content identification to there is a large amount of mistakes, cause searching for audio content accurately.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of way of recording, and realize the recording device that this way of recording adopts, the recording data being convenient to carry out searching for location to recorded audio data content can be produced, the present invention also will provide a kind of recording substance searching method, and realize the recording substance searcher that this recording substance searching method adopts, can search for recording substance easily, help user navigates to the position in the recording data of needs fast.
For solving the problems of the technologies described above, the technical scheme of the way of recording of the present invention comprises the following steps:
Step one, adopts recording device to carry out audio recording;
Step 2, described recording device includes image pickup section, uses described recording device to carry out the image taking of one or many in the process of audio recording, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
The invention discloses a kind of recording device realizing the above-mentioned way of recording and adopt, its technical scheme is, based on computer system, comprising:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
First storage component, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
The invention also discloses a kind of recording searching method, its technical scheme is, the above-mentioned way of recording of described recording is recorded, comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline, described recording substance searching method comprises the following steps:
Step one, selects in described image;
Step 2, according to selected image, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
The invention also discloses a kind of recording substance searcher realizing above-mentioned recording substance searching method and adopt, its technical scheme is, based on computer system, comprising:
Second storage component, stores described recording, described recording comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline;
Image selection unit, is used for selecting in described image;
First search parts, according to the image that described image selection unit is selected, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
The present invention discloses a kind of way of recording again, and its technical scheme comprises the following steps:
Step one, adopts sound pick-up outfit to carry out audio recording;
Step 2, described sound pick-up outfit includes image pickup section, in the process of audio recording, use described sound pick-up outfit to carry out the image taking of one or many, in captured image, include word, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, Text region is carried out in captured image, to identify that each word of obtaining is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place, preserve the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
The present invention discloses a kind of recording device realizing the above-mentioned way of recording and adopt again, and its technical scheme is, based on computer system, comprising:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
3rd Text region parts, carry out Text region to the image of described shooting parts shooting, will identify that each word obtained is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place;
3rd memory unit, preserves the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
The present invention again discloses a kind of recording substance searching method, its technical scheme is, described recording is recorded according to the above-mentioned way of recording, comprise the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word, described recording substance searching method comprises the following steps:
Step one, the word that the word selecting an identification to obtain or the one group of identification corresponding to same position on audio timeline obtain;
Step 2, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
The present invention again discloses a kind of recording substance searcher realizing above-mentioned recording substance searching method and adopt, and its technical scheme is, based on computer system, comprising:
4th memory unit, stores described recording, and described recording comprises the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word,
Word alternative pack, is used for word that selection identification obtains or the word that one group of identification corresponding to same position on audio timeline obtains;
Second search parts, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
The present invention passes through technique scheme, the image relevant to recording substance is obtained by the mode of shooting when recording, and the foundation that the information recorded on this image or this image is searched for as recording substance, achieve the search of recording substance, step is easy, be easy to use, and accuracy rate is high.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the present invention is further detailed explanation:
Fig. 1 is the schematic diagram of the way of recording of the present invention and a recording substance searching method embodiment;
Fig. 2 is the schematic diagram of recording device of the present invention and a recording substance searcher embodiment;
Fig. 3 is the schematic diagram of the way of recording of the present invention and another embodiment of recording substance searching method.
Embodiment
The invention discloses a kind of way of recording, comprise the following steps:
Step one, adopts recording device to carry out audio recording;
Step 2, described recording device includes image pickup section, uses described recording device to carry out the image taking of one or many in the process of audio recording, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
Word is included in described image.
After carrying out image taking, also comprise the step of image being carried out to Text region, and in step 3, preserve record audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline.
The invention also discloses a kind of recording substance searching method, the above-mentioned way of recording of described recording is recorded, comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline, described recording substance searching method comprises the following steps:
Step one, selects in described image;
Step 2, according to selected image, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
Include word in described image, Text region is carried out to described image; Whether input or selection keyword, include described keyword in retrieval Text region result, if comprised, then in described step one, selects the image comprising keyword.
Described recording comprise record to some extent audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline, input or selection keyword, described keyword whether is included in retrieval Text region result, if comprised, then in described step one, select the image comprising keyword.
If described keyword is included in the Text region result of multiple image, then in described step one, select one of them in the plurality of comprising in the image of keyword.
The audio content of the position of described image capture moment on recorded audio timeline refers at least one in following three kinds:
Audio content in the previous time period of the position of described image capture moment on recorded audio timeline;
Audio content after the position of described image capture moment on recorded audio timeline in the time period;
Audio content in the time period of the position of described image capture moment on recorded audio timeline, this audio content contains the position of described image capture moment on recorded audio timeline on described audio timeline.
User adopts the way of recording provided by the present invention to carry out recording audio, carries out the image taking of one or many in the process of recording audio.Because recording audio and shooting image carry out with same place at one time, therefore captured image is inevitable has natural contacting with audio content.Such as, in a meeting, spokesman makes a speech in conjunction with the lantern slide of projection, the speech of user to spokesman is recorded, in the process of recording, user can take the lantern slide of current projection, because the speech content of projection and the spokesman of institute's lantern slide is synchronously carried out, therefore take the moment of often opening lantern slide, necessarily spokesman explains the moment of this lantern slide related content.The audio frequency of recorded spokesman being made a speech, the slide image of shooting and the position of each image capture moment on recorded audio timeline are preserved as recording data together, as shown in Figure 1.In Fig. 1, namely image 1 and image 2 can be captured slide images, and shooting time is respectively 00:30 and 01:40.
When user needs to obtain the fragment of certain in spokesman's speech, namely the image of each lantern slide preserved in recording can be checked, the audio content of the position on the time shaft corresponding to it is learnt from slide image, thus by selecting specific image, be positioned to the recording fragment required for user.
Owing to may comprise word in slide image, user can carry out Text region to each slide image.In recording as shown in Figure 1, image 1 contains the character image of keyword 1, keyword 2 and keyword 3, by carrying out Text region, obtains " keyword 1 ", " keyword 2 " and " keyword 3 " word of the text formatting corresponding with image 1; Image 2 contains the character image of keyword 2, by carrying out Text region, obtains " keyword 2 " word of the text formatting corresponding with image 2.User is when searching for the recording substance needed, can select or input keyword, such as input or selection " keyword 1 ", find through search to include " keyword 1 " in the Text region result of image 1, therefore image 1 is just selected, and be positioned to the recording fragment be engraved in when image 1 is taken on audio timeline, i.e. the recording fragment of 00:30 position.
In addition to the above, user can also making recording in, carry out Text region to image, and by recognition result also with the slide image at its place and corresponding being kept in recording data of the shooting time of this slide image.In recording as shown in Figure 1, when recording by carrying out Text region, obtain " keyword 1 ", " keyword 2 " and " keyword 3 " word of the text formatting corresponding with image 1, and " keyword 2 " word of the text formatting corresponding with image 2, and by these words and the slide image at its place and corresponding being kept in recording data of the shooting time of this slide image.When user carries out recording substance search, also can select or input keyword, such as input or selection " keyword 1 ", find through search to include " keyword 1 " in the Text region result of the image 1 preserved, therefore image 1 is just selected, and is positioned to the recording fragment be engraved in when image 1 is taken on audio timeline.
In the process of above-mentioned keyword search, likely there will be in multiple image and all include same keyword.Such as, if user's input or selection " keyword 2 ", all include " keyword 2 " in the Text region result that search finds image 1 and image 2, now these can be included " keyword 2 " image and be supplied to user, selected in these specific images by user, thus be positioned to the recording substance of user's needs.
In the present invention, the audio content of the position of described image capture moment on recorded audio timeline can be the audio content in the previous time period of the position of described image capture moment on recorded audio timeline, the image such as selected is image 1, then above-mentioned audio content is the audio content in 00:20 to the 00:30 time period.
In the present invention, the audio content of the position of described image capture moment on recorded audio timeline can also be the position of described image capture moment on recorded audio timeline after audio content in a time period, the image such as selected is image 1, then above-mentioned audio content is the audio content in 00:30 to the 00:40 time period.
In the present invention, audio content in the time period of all right position of described image capture moment on recorded audio timeline of audio content of the position of described image capture moment on recorded audio timeline, this audio content contains the position of described image capture moment on recorded audio timeline on described audio timeline, the image such as selected is image 1, then above-mentioned audio content is the audio content in 00:25 to the 00:35 time period.
The invention also discloses a kind of recording device realizing the above-mentioned way of recording and adopt, based on computer system, described computer system can be PC, also can be smart mobile phone, as shown in Figure 2, can also be panel computer, recording device of the present invention also comprises:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
First storage component, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
Described recording device also comprises the first Text region parts, Text region is carried out to the image of described shooting parts shooting, described first storage component preserve record audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline.
The invention also discloses a kind of recording substance searcher realizing above-mentioned recording substance searching method and adopt, based on computer system, described computer system can be PC, also can be smart mobile phone, as shown in Figure 2, can also be panel computer, recording substance searcher of the present invention also comprises:
Second storage component, stores described recording, described recording comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline;
Image selection unit, is used for selecting in described image;
First search parts, according to the image that described image selection unit is selected, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
Described recording substance searcher also comprises:
Second Text region parts, carry out Text region to described image;
First keyword parts, input or selection keyword, retrieve in the Text region result of described second Text region parts whether include described keyword, if comprised, then selects by described image selection unit the image comprising keyword.
In described recording substance searcher, store described recording in described second storage component, described recording comprise record to some extent audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline; Described recording substance searcher also comprises the second keyword parts, and input or selection keyword, retrieve in described each pictograph recognition result whether include described keyword, if comprised, then selects by described image selection unit the image comprising keyword.
The present invention discloses a kind of way of recording again, comprises the following steps:
Step one, adopts sound pick-up outfit to carry out audio recording;
Step 2, described sound pick-up outfit includes image pickup section, in the process of audio recording, use described sound pick-up outfit to carry out the image taking of one or many, in captured image, include word, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, Text region is carried out in captured image, to identify that each word of obtaining is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place, preserve the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
The present invention discloses a kind of recording substance searching method again, the above-mentioned way of recording of described recording is recorded, comprise the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word, described recording substance searching method comprises the following steps:
Step one, the word that the word selecting an identification to obtain or the one group of identification corresponding to same position on audio timeline obtain;
Step 2, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
Also comprise input in the step of described recording substance searching method or select keyword, retrieving in the word that described identification obtains whether include described keyword, if comprised, then in described step one, selecting the word that the described identification comprising keyword obtains.
If described keyword is included in the word that the many groups identification corresponding to diverse location on audio timeline obtains, then, in described step one, in the word that the plurality of many groups identification comprising keyword obtains, select a group wherein.
The audio content of the position on the audio timeline that described word is corresponding refers at least one in following three kinds:
Audio content in the previous time period of the position of described image capture moment on recorded audio timeline;
Audio content after the position of described image capture moment on recorded audio timeline in the time period;
Audio content in the time period of the position of described image capture moment on recorded audio timeline, this audio content contains the position of described image capture moment on recorded audio timeline on described audio timeline.
Similar to previous embodiment, user adopts the way of recording provided by the present invention to carry out recording audio, carries out the image taking of one or many in the process of recording audio, and carries out Text region to captured image, obtains Text region result.Because recording audio and shooting image carry out with same place at one time, therefore captured image is inevitable has natural contacting with audio content, and identifying in image that the word obtained is also inevitable has natural contacting with audio content.Such as, in a meeting, spokesman makes a speech in conjunction with the lantern slide of projection, the speech of user to spokesman is recorded, in the process of recording, user can take the lantern slide of current projection, because the speech content of projection and the spokesman of institute's lantern slide is synchronously carried out, therefore take the moment of often opening lantern slide, necessarily spokesman explains the moment of this lantern slide related content.Text region is carried out by often opening slide image, and identify each word of obtaining be engraved in when being corresponded to the shooting of the image at its place the position on the audio timeline recorded, the audio frequency that recorded spokesman is made a speech, identify corresponding to the word that obtains and each word audio timeline on position preserve as recording data together, as shown in Figure 3.In Fig. 3, user have taken an image at 00:30, and identification obtains " keyword 1 ", " keyword 2 " and keyword 3; User have taken an image at 01:40, and identification obtains " keyword 2 ".
When user needs to obtain the fragment of certain in spokesman's speech, namely the word that the identification of preserving in recording obtains can be checked, the audio content of the position on the time shaft corresponding to it can be learnt from these words, thus by selecting specific word, be positioned to the recording fragment required for user.
User is when searching for the recording substance needed, can select or input keyword, such as input or selection " keyword 1 ", then " keyword 1 " in Fig. 3 is just selected, and the recording fragment be engraved in when being positioned to " keyword 1 " shooting on audio timeline, i.e. the recording fragment of 00:30 position.
In the process of above-mentioned keyword search, likely there will be in multiple image and all include same keyword.Such as, if user's input or selection " keyword 2 ", all include " keyword 2 " in search finds the word that identification corresponding to recording 00:30 position and 00:40 position obtains, the word that many groups identification that now these can be included " keyword 2 " obtains all is supplied to user, selected in these specific group of text by user, thus be positioned to the recording substance of user's needs.
In the present invention, the audio content of the position on the audio timeline that described word is corresponding can be the audio content in the previous time period of position on audio timeline that described word is corresponding, the word such as selected is " keyword 1 ", then above-mentioned audio content is the audio content in 00:20 to the 00:30 time period.
In the present invention, the audio content of the position on the audio timeline that described word is corresponding can be the position on audio timeline that described word is corresponding after audio content in a time period, the word such as selected is " keyword 1 ", then above-mentioned audio content is the audio content in 00:30 to the 00:40 time period.
In the present invention, the audio content of the position on the audio timeline that described word is corresponding can be the audio content in the time period of position on audio timeline that described word is corresponding, this audio content contains the position on audio timeline corresponding to described word on described audio timeline, the word such as selected is " keyword 1 ", then above-mentioned audio content is the audio content in 00:25 to the 00:35 time period.
The present invention again discloses a kind of recording device realizing the above-mentioned way of recording and adopt, and based on computer system, described computer system can be PC, also can be smart mobile phone, as shown in Figure 2, can also be panel computer, recording device of the present invention also comprises:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
3rd Text region parts, carry out Text region to the image of described shooting parts shooting, will identify that each word obtained is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place;
3rd memory unit, preserves the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
The present invention again discloses a kind of recording substance searcher realizing above-mentioned recording substance searching method and adopt, based on computer system, described computer system can be PC, also can be smart mobile phone, as shown in Figure 2, can also be panel computer, recording substance searcher of the present invention also comprises:
4th memory unit, stores described recording, and described recording comprises the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word,
Word alternative pack, is used for word that selection identification obtains or the word that one group of identification corresponding to same position on audio timeline obtains;
Second search parts, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
Described recording substance searcher, also comprise: the 3rd keyword parts, input or select keyword, retrieve in the word that described identification obtains whether include described keyword, if comprised, then the word selecting the described identification comprising keyword to obtain by described word alternative pack.
The present invention passes through technique scheme, the image relevant to recording substance is obtained by the mode of shooting when recording, and the foundation that the information recorded on this image or this image is searched for as recording substance, achieve the search of recording substance, step is easy, be easy to use, and accuracy rate is high.
The foregoing is only preferred embodiment of the present invention, and be not used to limit substantial technological context of the present invention, substantial technological content of the present invention be broad sense be defined in the right of application, any technology entities that other people complete or method, if with application right define identical, also or a kind of change of equivalence, be all covered by being regarded as among this right.
Claims (21)
1. a way of recording, is characterized in that, comprises the following steps:
Step one, adopts recording device to carry out audio recording;
Step 2, described recording device includes image pickup section, uses described recording device to carry out the image taking of one or many in the process of audio recording, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
2. the way of recording according to claim 1, is characterized in that, includes word in described image.
3. the way of recording according to claim 2, it is characterized in that, after carrying out image taking, also comprise the step of image being carried out to Text region, and in step 3, preserve record audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline.
4. realize as the way of recording in claim 1-3 as described in any one the recording device that adopts, it is characterized in that, based on computer system, comprising:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
First storage component, the audio frequency that preservation is recorded, the image of shooting and the position of each image capture moment on recorded audio timeline.
5. recording device according to claim 4, it is characterized in that, also comprise the first Text region parts, Text region is carried out to the image of described shooting parts shooting, described first storage component preserve record audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline.
6. a recording substance searching method, it is characterized in that, described recording is recorded according to the way of recording in claim 1-3 described in any one, comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline, described recording substance searching method comprises the following steps:
Step one, selects in described image;
Step 2, according to selected image, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
7. recording substance searching method according to claim 6, is characterized in that, includes word in described image, carries out Text region to described image; Whether input or selection keyword, include described keyword in retrieval Text region result, if comprised, then in described step one, selects the image comprising keyword.
8. recording substance searching method according to claim 6, it is characterized in that, described recording comprise record to some extent audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline, input or selection keyword, described keyword whether is included in retrieval Text region result, if comprised, then in described step one, select the image comprising keyword.
9. the recording substance searching method according to claim 7 or 8, is characterized in that, if described keyword is included in the Text region result of multiple image, then in described step one, selects one of them in the plurality of comprising in the image of keyword.
10. recording substance searching method according to claim 6, is characterized in that, the audio content of the position of described image capture moment on recorded audio timeline refers at least one in following three kinds:
Audio content in the previous time period of the position of described image capture moment on recorded audio timeline;
Audio content after the position of described image capture moment on recorded audio timeline in the time period;
Audio content in the time period of the position of described image capture moment on recorded audio timeline, this audio content contains the position of described image capture moment on recorded audio timeline on described audio timeline.
11. 1 kinds realize as the recording substance searching method in claim 6-10 as described in any one the recording substance searcher that adopts, it is characterized in that, based on computer system, comprising:
Second storage component, stores described recording, described recording comprise record to some extent audio frequency, image and each position of described image capture moment on recorded audio timeline;
Image selection unit, is used for selecting in described image;
First search parts, according to the image that described image selection unit is selected, is positioned to the audio content of the position of this image capture moment on recorded audio timeline.
12. recording substance searchers according to claim 11, is characterized in that, also comprise:
Second Text region parts, carry out Text region to described image;
First keyword parts, input or selection keyword, retrieve in the Text region result of described second Text region parts whether include described keyword, if comprised, then selects by described image selection unit the image comprising keyword.
13. recording substance searchers according to claim 11, it is characterized in that, store described recording in described second storage component, described recording comprise record to some extent audio frequency, the image of shooting, each pictograph recognition result and the position of each image capture moment on recorded audio timeline; Described recording substance searcher also comprises the second keyword parts, and input or selection keyword, retrieve in described each pictograph recognition result whether include described keyword, if comprised, then selects by described image selection unit the image comprising keyword.
14. 1 kinds of ways of recording, is characterized in that, comprise the following steps:
Step one, adopts sound pick-up outfit to carry out audio recording;
Step 2, described sound pick-up outfit includes image pickup section, in the process of audio recording, use described sound pick-up outfit to carry out the image taking of one or many, in captured image, include word, record each shooting image time be engraved in position on recorded audio timeline;
Step 3, Text region is carried out in captured image, to identify that each word of obtaining is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place, preserve the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
15. 1 kinds of recording devices realizing the way of recording as claimed in claim 14 and adopt, is characterized in that, based on computer system, comprising:
Taping component, is used for carrying out audio recording;
Shooting parts, are used for carrying out image taking in the process of audio recording, and record each shooting image time be engraved in position on recorded audio timeline;
3rd Text region parts, carry out Text region to the image of described shooting parts shooting, will identify that each word obtained is engraved in the position on recorded audio timeline when corresponding to the shooting of the image at its place;
3rd memory unit, preserves the audio frequency recorded, the position identified on the word that obtains and the audio timeline corresponding to each word.
16. 1 kinds of recording substance searching methods, it is characterized in that, the described recording way of recording according to claim 14 is recorded, and comprise the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word, described recording substance searching method comprises the following steps:
Step one, the word that the word selecting an identification to obtain or the one group of identification corresponding to same position on audio timeline obtain;
Step 2, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
17. recording substance searching methods according to claim 16, it is characterized in that input or select keyword retrieves in the word that described identification obtains whether include described keyword, if comprised, then in described step one, select the word that the described identification comprising keyword obtains.
18. recording substance searching methods according to claim 17, it is characterized in that, if described keyword is included in the word that the many groups identification corresponding to diverse location on audio timeline obtains, then in described step one, in the word that the plurality of many groups identification comprising keyword obtains, select a group wherein.
19. recording substance searching methods according to claim 16, is characterized in that, the audio content of the position on the audio timeline that described word is corresponding refers at least one in following three kinds:
Audio content in the previous time period of the position of described image capture moment on recorded audio timeline;
Audio content after the position of described image capture moment on recorded audio timeline in the time period;
Audio content in the time period of the position of described image capture moment on recorded audio timeline, this audio content contains the position of described image capture moment on recorded audio timeline on described audio timeline.
20. 1 kinds realize as the recording substance searching method in claim 16-19 as described in any one the recording substance searcher that adopts, it is characterized in that, based on computer system, comprising:
4th memory unit, stores described recording, and described recording comprises the audio frequency recorded to some extent, the position identified on the word that obtains and the audio timeline corresponding to each word,
Word alternative pack, is used for word that selection identification obtains or the word that one group of identification corresponding to same position on audio timeline obtains;
Second search parts, according to selected word, is positioned to the audio content of the position on audio timeline corresponding to this word.
21. recording substance searchers according to claim 20, is characterized in that, also comprise:
3rd keyword parts, input or select keyword, retrieves in the word that described identification obtains whether include described keyword, if comprised, then the word selecting the described identification comprising keyword to obtain by described word alternative pack.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410774335.9A CN104599692B (en) | 2014-12-16 | 2014-12-16 | The way of recording and device, recording substance searching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410774335.9A CN104599692B (en) | 2014-12-16 | 2014-12-16 | The way of recording and device, recording substance searching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104599692A true CN104599692A (en) | 2015-05-06 |
| CN104599692B CN104599692B (en) | 2017-12-15 |
Family
ID=53125422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410774335.9A Active CN104599692B (en) | 2014-12-16 | 2014-12-16 | The way of recording and device, recording substance searching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104599692B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106128460A (en) * | 2016-08-04 | 2016-11-16 | 周奇 | A kind of record labels method and device |
| CN106357929A (en) * | 2016-11-10 | 2017-01-25 | 努比亚技术有限公司 | Previewing method based on audio file and mobile terminal |
| CN106875968A (en) * | 2017-01-21 | 2017-06-20 | 上海量明科技发展有限公司 | The method of information gathering, client and system |
| CN107124648A (en) * | 2017-04-17 | 2017-09-01 | 浙江德塔森特数据技术有限公司 | The method that advertisement video is originated is recognized by intelligent terminal |
| CN107295284A (en) * | 2017-08-03 | 2017-10-24 | 浙江大学 | A kind of generation of video file being made up of audio and picture and index playing method, device |
| CN107424640A (en) * | 2017-07-27 | 2017-12-01 | 上海与德科技有限公司 | A kind of audio frequency playing method and device |
| CN107885483A (en) * | 2017-11-07 | 2018-04-06 | 广东欧珀移动通信有限公司 | Method of calibration, device, storage medium and the electronic equipment of audio-frequency information |
| CN110099332A (en) * | 2019-05-21 | 2019-08-06 | 科大讯飞股份有限公司 | A kind of audio environment methods of exhibiting and device |
| CN110134817A (en) * | 2019-05-16 | 2019-08-16 | 天津讯飞极智科技有限公司 | A kind of storage method of recording file, searching method and relevant apparatus |
| CN112087653A (en) * | 2020-09-18 | 2020-12-15 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0752703A2 (en) * | 1995-07-04 | 1997-01-08 | Pioneer Electronic Corporation | Information recording apparatus and information reproducing apparatus |
| CN101281534A (en) * | 2008-05-28 | 2008-10-08 | 叶睿智 | Method for searching multimedia resource based on audio content retrieval |
| CN101430915A (en) * | 2003-10-04 | 2009-05-13 | 三星电子株式会社 | Reproducing apparatus |
| JP4489650B2 (en) * | 2005-07-21 | 2010-06-23 | 株式会社第一興商 | Karaoke recording and editing device that performs cut and paste editing based on lyric characters |
| US20100157097A1 (en) * | 2008-12-08 | 2010-06-24 | Samsung Electronics Co., Ltd. | Voice recordable terminal and its image processing method |
| CN102122506A (en) * | 2011-03-08 | 2011-07-13 | 天脉聚源(北京)传媒科技有限公司 | Method for recognizing voice |
| CN102158614A (en) * | 2010-02-12 | 2011-08-17 | 阿瓦雅公司 | Context sensitive, cloud-based telephony |
| JP4866396B2 (en) * | 2008-07-08 | 2012-02-01 | 株式会社デンソーアイティーラボラトリ | Tag information adding device, tag information adding method, and computer program |
| CN103065659A (en) * | 2012-12-06 | 2013-04-24 | 广东欧珀移动通信有限公司 | Multi-media recording method |
| CN103165131A (en) * | 2011-12-17 | 2013-06-19 | 富泰华工业（深圳）有限公司 | Voice processing system and voice processing method |
-
2014
- 2014-12-16 CN CN201410774335.9A patent/CN104599692B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0752703A2 (en) * | 1995-07-04 | 1997-01-08 | Pioneer Electronic Corporation | Information recording apparatus and information reproducing apparatus |
| CN101430915A (en) * | 2003-10-04 | 2009-05-13 | 三星电子株式会社 | Reproducing apparatus |
| JP4489650B2 (en) * | 2005-07-21 | 2010-06-23 | 株式会社第一興商 | Karaoke recording and editing device that performs cut and paste editing based on lyric characters |
| CN101281534A (en) * | 2008-05-28 | 2008-10-08 | 叶睿智 | Method for searching multimedia resource based on audio content retrieval |
| JP4866396B2 (en) * | 2008-07-08 | 2012-02-01 | 株式会社デンソーアイティーラボラトリ | Tag information adding device, tag information adding method, and computer program |
| US20100157097A1 (en) * | 2008-12-08 | 2010-06-24 | Samsung Electronics Co., Ltd. | Voice recordable terminal and its image processing method |
| CN102158614A (en) * | 2010-02-12 | 2011-08-17 | 阿瓦雅公司 | Context sensitive, cloud-based telephony |
| CN102122506A (en) * | 2011-03-08 | 2011-07-13 | 天脉聚源(北京)传媒科技有限公司 | Method for recognizing voice |
| CN103165131A (en) * | 2011-12-17 | 2013-06-19 | 富泰华工业（深圳）有限公司 | Voice processing system and voice processing method |
| CN103065659A (en) * | 2012-12-06 | 2013-04-24 | 广东欧珀移动通信有限公司 | Multi-media recording method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106128460A (en) * | 2016-08-04 | 2016-11-16 | 周奇 | A kind of record labels method and device |
| CN106357929A (en) * | 2016-11-10 | 2017-01-25 | 努比亚技术有限公司 | Previewing method based on audio file and mobile terminal |
| CN106875968A (en) * | 2017-01-21 | 2017-06-20 | 上海量明科技发展有限公司 | The method of information gathering, client and system |
| CN106875968B (en) * | 2017-01-21 | 2024-03-22 | 上海量明科技发展有限公司 | Information acquisition method, client and system |
| CN107124648A (en) * | 2017-04-17 | 2017-09-01 | 浙江德塔森特数据技术有限公司 | The method that advertisement video is originated is recognized by intelligent terminal |
| CN107424640A (en) * | 2017-07-27 | 2017-12-01 | 上海与德科技有限公司 | A kind of audio frequency playing method and device |
| CN107295284A (en) * | 2017-08-03 | 2017-10-24 | 浙江大学 | A kind of generation of video file being made up of audio and picture and index playing method, device |
| CN107885483A (en) * | 2017-11-07 | 2018-04-06 | 广东欧珀移动通信有限公司 | Method of calibration, device, storage medium and the electronic equipment of audio-frequency information |
| CN107885483B (en) * | 2017-11-07 | 2021-03-02 | Oppo广东移动通信有限公司 | Audio information verification method and device, storage medium and electronic equipment |
| CN110134817A (en) * | 2019-05-16 | 2019-08-16 | 天津讯飞极智科技有限公司 | A kind of storage method of recording file, searching method and relevant apparatus |
| CN110099332A (en) * | 2019-05-21 | 2019-08-06 | 科大讯飞股份有限公司 | A kind of audio environment methods of exhibiting and device |
| CN112087653A (en) * | 2020-09-18 | 2020-12-15 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104599692B (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104599692A (en) | Recording method and device and recording content searching method and device | |
| US10750245B1 (en) | User interface for labeling, browsing, and searching semantic labels within video | |
| US9659278B2 (en) | Methods, systems, and computer program products for displaying tag words for selection by users engaged in social tagging of content | |
| JP2019501466A (en) | Method and system for search engine selection and optimization | |
| US9972340B2 (en) | Deep tagging background noises | |
| US10528227B2 (en) | Systems and methods for linking attachments to chat messages | |
| CN109408672B (en) | Article generation method, article generation device, server and storage medium | |
| CN103440243A (en) | Teaching resource recommendation method and device thereof | |
| US20190179848A1 (en) | Method and system for identifying pictures | |
| CN107885483B (en) | Audio information verification method and device, storage medium and electronic equipment | |
| CN104994404A (en) | Method and device for obtaining keywords for video | |
| WO2021115277A1 (en) | Image retrieval method and apparatus, storage medium, and electronic device | |
| US20220415366A1 (en) | Smart summarization, indexing, and post-processing for recorded document presentation | |
| RU2015152415A (en) | MULTIMODAL SEARCH RESPONSE | |
| CN104765767B (en) | For the knowledge store system and its knowledge searching method of intelligence learning | |
| CN112765460A (en) | Conference information query method, device, storage medium, terminal device and server | |
| CN103152633A (en) | Method and device for identifying key word | |
| Truong et al. | Video search based on semantic extraction and locally regional object proposal | |
| CN107885827B (en) | File acquisition method and device, storage medium and electronic equipment | |
| CN110543449A (en) | chat record searching method based on AR equipment | |
| CN110019863B (en) | Object searching method and device, terminal equipment and storage medium | |
| CN103309993A (en) | Keyword extraction method and device | |
| CN109657129B (en) | Method and device for acquiring information | |
| Khan et al. | Ivia: interactive video intelligent agent framework for instructional video information retrieval | |
| CN109710844A (en) | The method and apparatus for quick and precisely positioning file based on search engine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 7, No. 200433, building 335, building 3, National Road, Yangpu District, Shanghai, B Patentee after: Shanghai hehe Information Technology Co., Ltd Address before: 7, No. 200433, building 335, building 3, National Road, Yangpu District, Shanghai, B Patentee before: INTSIG INFORMATION Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: Room 1105-1123, No. 1256, 1258, Wanrong Road, Jing'an District, Shanghai, 200436 Patentee after: Shanghai hehe Information Technology Co., Ltd Address before: 7, No. 200433, building 335, building 3, National Road, Yangpu District, Shanghai, B Patentee before: Shanghai hehe Information Technology Co., Ltd |