Summary of the invention
Because existing for image, prior art adopt the OCR identification caption to need further to proofread and correct the identification caption result, carry out again the problem of caption translating, a kind of caption translating system and method thereof when providing image to play is provided, wherein:
Caption translating system when providing image to play provided by the present invention comprises in the first embodiment: receiver module, image playing module, search module, control module, time acquisition module, enquiry module, translation module and storage module.
Wherein, receiver module is in order to receive words; The image playing module is in order to playing video, and replay image according to playback signal from time out, wherein, image is combined by image file and captions archives, image file comprises time shaft, the captions archives comprise a plurality of captions data, and each captions data comprises temporal information and caption content; When image was play, whether the caption content of the captions data that the time shaft of search module search image is corresponding had words; Control module is suspended the broadcast of image when search module searches caption content when having words; When the time acquisition module suspends broadcast in order to pick-up image, the time of time shaft is time out; Enquiry module inquires the temporal information with time out from the captions archives, and inquires the caption content corresponding with temporal information; Translation module is the translation words with Word translation; Storage module is newly-increased translation words and storing subtitling archives again after the words of caption content, and trigger playback signal.
Caption translating method when providing image to play provided by the present invention comprises the following step in the first embodiment:
At first, receive words; Then, playing video, wherein, image is combined by image file and captions archives, and image file comprises time shaft, and the captions archives comprise a plurality of captions data, and each captions data comprises temporal information and caption content; Then, when image was play, whether the caption content of the captions data that the time shaft of search image is corresponding had words; Then, when searching caption content and have words, suspend the broadcast of image; When then, pick-up image suspends broadcast, the time of time shaft is time out; Then, inquire the temporal information with time out from the captions archives, and inquire the caption content corresponding with temporal information; Then, Word translation is the translation words; Then, newly-increased translation words and storing subtitling archives again after the words of caption content, and trigger playback signal; At last, replay image according to playback signal from time out.
Caption translating system when providing image to play provided by the present invention, comprise in a second embodiment: module, receiver module, translation module and display module chosen in image playing module, words.
Wherein, the image playing module is in order to playing video, and wherein, image is combined by image file and captions archives, and image file comprises time shaft, and the captions archives comprise a plurality of captions data, and each captions data comprises temporal information and caption content; Words is chosen module when image is play, and according to the time shaft position of the image file of user's the instruction current broadcast in location, and provides caption content in captions data corresponding to time shaft position for the mode that the user chooses; Receiver module is in order to receive selected words in the caption content of user from captions data corresponding to time shaft position; Translation module is inquired about chosen translation words corresponding to words from translation word stocks or network lexicon; Display module is used for showing the translation words.
Caption translating method when providing image to play provided by the present invention comprises the following step in a second embodiment:
At first, playing video, wherein, image is combined by image file and captions archives, and image file comprises time shaft, and the captions archives comprise a plurality of captions data, and each captions data comprises temporal information and caption content; Then, when image is play, according to the time shaft position of the image file of user's the instruction current broadcast in location, and provide caption content in captions data corresponding to time shaft position for the mode that the user chooses; Then, receive selected words in the caption content of user from captions data corresponding to time shaft position; Then, chosen translation words corresponding to words of inquiry from translation word stocks or network lexicon; At last, show the translation words.
System and method for provided by the present invention as above, and the difference between prior art is that the present invention is when image is play, whether the caption content of the captions data that the time shaft of search image is corresponding has the words that the user inputs, when searching caption content and have words, suspend the broadcast of image, and the time out when suspending according to image inquires temporal information and the caption content with time out from the captions archives, and Word translation is the translation words, can increase translation words and storing subtitling archives again newly after the words of caption content, replay image according to playback signal from time out at last.
By above-mentioned technological means, the present invention can reach the technique effect that can directly translate image caption when image is play.
Description of drawings
Caption translating system block diagram when Fig. 1 provides image to play for first embodiment of the invention.
Caption translating method flow chart when Fig. 2 provides image to play for first embodiment of the invention.
The user interface schematic diagram of the caption translating when Fig. 3 provides image to play for first embodiment of the invention.
Image file and the captions archives schematic diagram of the caption translating when Fig. 4 A provides image to play for first embodiment of the invention.
The captions archive content schematic diagram of the caption translating when Fig. 4 B provides image to play for first embodiment of the invention.
Again the storing subtitling archive content schematic diagram of the caption translating when Fig. 5 provides image to play for first embodiment of the invention.
The image of the caption translating when Fig. 6 provides image to play for first embodiment of the invention replays schematic diagram.
The captions of the caption translating when Fig. 7 provides image to play for first embodiment of the invention record the archive content schematic diagram.
The captions archives full text translation content schematic diagram of the caption translating when Fig. 8 A provides image to play for first embodiment of the invention.
The image of the caption translating when Fig. 8 B provides image to play for first embodiment of the invention is play result schematic diagram.
Caption translating system block diagram when Fig. 9 provides image to play for second embodiment of the invention.
Caption translating method flow chart when Figure 10 provides image to play for second embodiment of the invention.
The user interface schematic diagram of the caption translating when Figure 11 provides image to play for second embodiment of the invention.
The translation of the caption translating when Figure 12 A provides image to play for second embodiment of the invention explains that the first presentation mode shows schematic diagram.
The translation of the caption translating when Figure 12 B provides image to play for second embodiment of the invention explains that the second presentation mode shows schematic diagram.
[critical piece description of reference numerals]
11 receiver modules
12 image playing modules
13 search module
14 control modules
15 time acquisition modules
16 enquiry modules
17 translation modules
18 storage modules
19 pretreatment module
20 user interfaces
21 input areas
22 image play area
23 chosen area
31 image files
32 captions archives
321 first captions data
322 second captions data
323 the 3rd captions data
33 captions record archives
41 image playing modules
Module chosen in 42 words
43 receiver modules
44 translation modules
45 display modules
Step 110 receives words
Step 120 playing video
When step 130 was play at image, whether the caption content of the captions data that the time shaft of search image is corresponding had words
Step 140 is suspended the broadcast of image when searching caption content and have words
The time that step 150 pick-up image suspends time shaft when playing is time out
Step 160 inquires the temporal information with time out from the captions archives, and inquires the caption content corresponding with temporal information
Step 170 is the translation words with Word translation
Step 180 is newly-increased translation words and storing subtitling archives again after the words of caption content, and trigger playback signal
Step 190 replays image according to playback signal from time out
Step 210 will the caption content corresponding with temporal information saves as captions and records archives
Step 220 is carried out full text translation with the caption content of each captions data of captions archives in advance before image is play
Step 230 is the storing subtitling archives again
Step 310 playing video
When step 320 is play at image, according to the time shaft position of the image file of user's the instruction current broadcast in location, and provide caption content in captions data corresponding to time shaft position for the mode that the user chooses
Step 330 receives selected words in the caption content of user from captions data corresponding to time shaft position
Step 340 is inquired about chosen translation words corresponding to words from translation word stocks or network lexicon
Step 350 shows the translation words
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, thus to the present invention how the application technology means implementation procedure that solves technical problem and reach technique effect can fully understand and implement according to this.
At first the first embodiment of the caption translating system when providing image to play provided by the present invention below to be described, and please refer to shown in Figure 1ly, Figure 1 shows that the caption translating system block diagram when first embodiment of the invention provides image to play.
Caption translating system when the first embodiment provided by the present invention provides image to play, it comprises: receiver module 11, image playing module 12, search module 13, control module 14, time acquisition module 15, enquiry module 16, translation module 17 and storage module 18.
Before passing through image playing module 12 playing videos, the user can be when the invention provides image and play the user interface that provides of caption translating system in the words that will inquire about of input, and receiver module 11 namely can receive the words that the user inputs in the user interface, then, namely can be by image playing module 12 playing videos.
it should be noted that, the image of being play by image playing module 12 is combined by image file 31 and captions archives 32, image file 31 can include presentation content, the source of sound content (includes: music, audio, sound etc.) and time shaft, namely when image is play, can be according to time playing video content and the source of sound content of time shaft, and captions archives 32 comprise a plurality of captions data, each captions data comprises temporal information and caption content, temporal information includes zero-time and termination time, that is expression is according to time of time shaft during playing video, be zero-time and can show caption content between the termination time in the time of time shaft.
Particularly, suppose that captions archives 32 include the first captions data, the second captions data and the 3rd captions data, and the very first time information of the first captions data be " 00:01:32; 800 (zero-times)->00:01:36,500 (termination times) " and the first caption content of the first captions data be " This is acomputer. "; The second temporal information of the second captions data be " 00:01:37,580 (zero-times)->00:01:40,170 (termination times) " and the second caption content of the second captions data be " This is arouter. "; And the 3rd temporal information of the 3rd captions data be " 00:01:48; 200 (zero-times)->00:01:51; 690 (termination times) " and the 3rd caption content of the 3rd captions data be " This is anotebook. ", above-mentioned only for illustrating, do not limit to application category of the present invention with this.
Then, search module 13 can be in image playing module 12 playing videos, to the action that the caption content of captions data corresponding to the time shaft of image is searched, whether the caption content of the captions data that namely time shaft of search module 13 meeting search images is corresponding has the words that receiver module 11 receives.
Give an example according to above-mentioned, suppose that the words that the user inputs at the user interface is " router ", whether the first caption content that search module 13 namely can be searched in time of the time shaft of image the first corresponding captions data between for " 00:01:32 " to " 00:01:36 " has words " router " for " This is a computer. "; Then, meeting is whether second caption content of searching the second corresponding captions data between " 00:01:37 " to " 00:01:40 " has words " router " for " This is a router. " in the time of the time shaft of image; And whether the 3rd caption content that can search in time of the time shaft of image the 3rd corresponding captions data between for " 00:01:48 " to " 00:01:51 " has words " router " for " This is a notebook. ".
Then, when the caption content that searches captions data corresponding to the time shaft of image when search module 13 has the words that receiver module 11 receives, can suspend again the broadcast of image by control module 14, meanwhile, namely can pick-up image to suspend the time of time shaft when playing be time out to time acquisition module 15.
give an example according to above-mentioned, the second caption content that search module 13 is the second captions data of search correspondence between " 00:01:37 " to " 00:01:40 " in the time of the time shaft of image is " This is arouter. ", search module 13 namely can hunt out the second caption content and have words " router " for " This is a router. ", suspend again the broadcast of image by control module 14, meanwhile, the time that time acquisition module 15 namely can pick-up image suspends time shaft when playing is assumed to be " 00:01:38 " and is time out, be that time out is " 00:01:38 ".
Then, enquiry module 16 namely can inquire the temporal information with time out from captions archives 32, and inquire the caption content corresponding with temporal information, then, translation module 17 is the translation words with Word translation, translation module 17 can directly be the translation words to Word translation, or translation module 17 can be the translation words to Word translation by network, and Word translation be please refer to prior art for the translation words, no longer give unnecessary details at this, within existing Word translation mode should be contained in the present invention.
Give an example according to above-mentioned, enquiry module 16 namely can be inquired about the first captions data from captions archives 32 very first time information is that " 00:01:32,800->00:01:36,500 " do not have time out " 00:01:38 "; Then, namely can to inquire about the second temporal information of the second captions data in captions archives 32 be that " 00:01:37,580->00:01:40,170 " have time out " 00:01:38 " to enquiry module 16; And enquiry module 16 namely can be inquired about the 3rd captions data in captions archives 32 the 3rd temporal information is that " 00:01:48,200->00:01:51,690 " do not have time out " 00:01:38 ".And it is " This isa router. " for second caption content corresponding to " 00:01:37; 580->00:01:40; 170 " that enquiry module 16 can inquire with the second temporal information, and translation module 17 namely can be translated as words " router " translation words " router ".
The module of serving as interpreter 17 with Word translation for the translation words after, can be by storage module 18 newly-increased translation words and storing subtitling archives 32 again after the words of the caption content that enquiry module 16 inquires, and trigger simultaneously playback signal, and image playing module 12 namely can replay this image from time out according to playback signal, and the user namely can see the translation result of words in image.
give an example according to above-mentioned, translation module 17 is being translated as words " router " translation words " router " afterwards, storage module 18 namely can with the translation words " router " increase newly in the second caption content for " This is arouter. " " router " afterwards, and storing subtitling archives 32 again, thus, the second caption content namely can be modified to " This is a router[router]. ", and storage module 18 can trigger playback signal, and image playing module 12 namely can replay image from time out for " 00:01:38 " according to playback signal, and the user namely can image time shaft " 00:01:37 " to " 00:01:40 " see captions be " This isa router[router]. ".
in addition, storage module 18 can also save as captions with the enquiry module 16 inquires caption content corresponding with temporal information and record archives, provide thus the user need not carry out again the reading of caption content by the broadcast of image, the user is provided further results of learning, and captions record archives can be extend markup language (extensible Markup Language, XML) File Format, Hypertext Markup Language HTML (hypertext Markup Language, HTML) File Format, the text-only file form and generally document processing File Format commonly used one of them.
Caption translating system when providing image to play of the present invention can also comprise pretreatment module 19, pretreatment module 19 is before image is play, in advance the caption content of each captions data of captions archives 32 is carried out full text translation, and by storage module 18 storing subtitling archives 32 again, at this moment, again the captions archives 32 that store namely can comprise a plurality of captions data, each captions data comprises temporal information, caption content and caption content, by image playing module 12 playing video the time, provide the demonstration of bilingual subtitles thus.
Then, will explain with an embodiment function mode and the flow process of first embodiment of the invention, following examples Figure 2 shows that the caption translating method flow chart when first embodiment of the invention provides image to play in connection with Fig. 1 and shown in Figure 2 describing.
Please refer to shown in Figure 3ly, Figure 3 shows that the user interface schematic diagram of caption translating when first embodiment of the invention provides image to play.
before passing through image playing module 12 playing videos, the words that the user can input area 21 inputs in user provided by the present invention interface 20 will inquire about is " router ", and receiver module 11 namely can receive the words that the user inputs and is " router " (step 110) in input area 21, then, namely can image be played in by image playing module 12 in the image play area 22 at user interface 20 (step 120), input area 21 in user interface 20 only is the signal explanation at this, do not limit to application category of the present invention with this, input area 21 also can be presented with floating frame, and the signal that image is play please refer to shown in Figure 3.
Image file and the captions archives schematic diagram of the caption translating when Fig. 4 A is depicted as first embodiment of the invention and provides image to play then, are provided shown in Fig. 4 A and Fig. 4 B; The captions archive content schematic diagram of the caption translating when Fig. 4 B is depicted as first embodiment of the invention and provides image to play.
The image that image playing module 12 is play is combined by image file 31 and captions archives 32, in an embodiment, captions archives 32 include the first caption data 321, the second captions data 322 and the 3rd captions data 323, and the very first time information of the first caption data 321 be " 00:01:32; 800 (zero-times)->00:01:36,500 (termination times) " and the first caption content of the first caption data 321 be " This is a computer. "; The second temporal information of the second captions data 322 be " 00:01:37,580 (zero-times)->00:01:40,170 (termination times) " and the second caption content of the second captions data 322 be " This is a router. "; And the 3rd temporal information of the 3rd captions data 323 be " 00:01:48,200 (zero-times)->00:01:51,690 (termination times) " and the 3rd caption content of the 3rd captions data 323 be " This is a notebook. ".
Then, because the received words of receiver module 11 is " router ", whether the first caption content that search module 13 namely can be searched in time of the time shaft of image the first corresponding captions data 321 between for " 00:01:32 " to " 00:01:36 " has words " router " (step 130) for " This is a computer. "; Then, meeting is whether second caption content of searching the second corresponding captions data 322 between " 00:01:37 " to " 00:01:40 " has words " router " (step 130) for " This is a router. " in the time of the time shaft of image; And whether the 3rd caption content that can search in time of the time shaft of image the 3rd corresponding captions data 323 between for " 00:01:48 " to " 00:01:51 " has words " router " (step 130) for " This is a notebook. ".
In an embodiment, the second caption content that search module 13 namely can hunt out the second captions data 322 has words " router " for " This is a router. ", suspend again the broadcast (step 140) of image by control module 14, meanwhile, the time " 00:01:38 " that time acquisition module 15 namely can pick-up image suspends time shaft when playing is time out (step 150, and please refer to shown in Figure 3), namely time out is " 00:01:38 ".
Then, enquiry module 16 namely can inquire the second captions data 322 from captions archives 32 the second temporal information has time out " 00:01:38 " for " 00:01:37; 580->00:01:40; 170 ", and it is " This is a router. " (step 160) for second caption content corresponding to " 00:01:37; 580->00:01:40; 170 " that enquiry module 16 can inquire with the second temporal information, and translation module 17 namely can be translated as words " router " translation words " router " (step 170).
Then, please refer to shown in Figure 5ly, Figure 5 shows that the archive content of the storing subtitling again schematic diagram of the caption translating when first embodiment of the invention provides image to play.
at translation module 17, words " router " is translated as translation words " router " afterwards, storage module 18 namely can with the translation words for " router " increase newly in the second caption content for " This is a router. " " router " afterwards, and storing subtitling archives 32 (step 180) again, thus, the second caption content namely can be modified to " This is a router[router]. ", and storage module 18 can trigger playback signal (step 180), and image playing module 12 namely can replay image (step 190) from time out for " 00:01:38 " according to playback signal, the signal that replays image please refer to shown in Figure 6, the image that Figure 6 shows that the caption translating when first embodiment of the invention provides image to play replays schematic diagram, and the user namely can image time shaft " 00:01:37 " to " 00:01:40 " see captions be " This is arouter[router]. ".
Then, please refer to shown in Figure 7ly, Figure 7 shows that the captions of the caption translating when first embodiment of the invention provides image to play record the archive content schematic diagram.
Storage module 18 can also save as captions with second caption content " This is a router. " of enquiry module 16 inquires and the second temporal information " 00:01:37; 580->00:01:40; 170 " correspondence and record archives 33 (step 210), provide thus the user to carry out again the reading of caption content by the broadcast of image, the user is provided further results of learning.
The captions archives full text translation content schematic diagram of the caption translating when Fig. 8 A is depicted as first embodiment of the invention and provides image to play then, is provided shown in Fig. 8 A and Fig. 8 B; The image of the caption translating when Fig. 8 B is depicted as first embodiment of the invention and provides image to play is play result schematic diagram.
the present invention can also comprise pretreatment module 19, pretreatment module 19 is before image playing module 12 playing videos, in advance the caption content of each captions data of captions archives 32 is carried out full text translation (step 220), the full text translation result of captions archives 32 please refer to shown in Fig. 8 A, and by storage module 18 storing subtitling archives 32 (step 230) again, at this moment, again the captions archives 32 that store namely can comprise a plurality of captions data, each captions data comprises temporal information, caption content and caption content, thus by image playing module 12 playing video the time, the demonstration of bilingual subtitles is provided, its image is play the result signal and be please refer to shown in Fig. 8 B.
Then, the second embodiment of the caption translating system when providing image to play provided by the present invention is described, and please refer to shown in Figure 9ly, Figure 9 shows that the caption translating system block diagram when second embodiment of the invention provides image to play.
Caption translating system when the second embodiment provided by the present invention provides image to play, it comprises: module 42, receiver module 43, translation module 44 and display module 45 chosen in image playing module 41, words.
image playing module 41 can be play-overed image, the image of being play by image playing module 41 is to be combined by image file 31 and captions archives 32, image file 31 can include presentation content, the source of sound content (includes: music, audio, sound etc.) and time shaft, namely when image is play, can be according to time playing video content and the source of sound content of time shaft, and captions archives 32 comprise a plurality of captions data, each captions data comprises temporal information and caption content, temporal information includes zero-time and termination time, that is expression is according to time of time shaft during playing video, can be zero-time and show caption content between the termination time in the time of time shaft.
Then, can choose module 42 when 41 pairs of images of image playing module are play by words, according to the time shaft position of the image file of user's the instruction current broadcast in location, and provide caption content in captions data corresponding to time shaft position for the mode that the user chooses.
Then, choose words in the user is being provided caption content in captions data corresponding to time shaft position after, can receive selected words in the caption content of users from captions data corresponding to time shaft position by receiver module 43.
Then, can inquire about chosen translation words corresponding to words by translation module 44 from translation word stocks or network lexicon again, and after translation module 44 inquires translation words corresponding to chosen words, can be translated the demonstration of words by display module 45, provide thus the translation that the user understands chosen words to explain.
Then, to explain with an embodiment function mode and the flow process of second embodiment of the invention, following examples Figure 10 shows that the caption translating method flow chart when second embodiment of the invention provides image to play in connection with Fig. 9 and shown in Figure 10 describing.
Please refer to shown in Figure 11ly, Figure 11 shows that the user interface schematic diagram of caption translating when second embodiment of the invention provides image to play.
By image playing module 41, image is played in the image play area 22 at user interface 20 (step 310), the signal that image is play please refer to shown in Figure 11.
then, when the user suspends image broadcast (being user's instruction), words was chosen 42 of modules and can be " 00:01:38 " according to the time shaft position of the image file of user's the instruction current broadcast in location this moment, and the caption content in the captions data that time shaft position " 00:01:38 " is corresponding is shown in chosen area 23 for " This is a router. " (please refer to shown in Fig. 4 B), the mode of choosing for the user provides the caption content in captions data corresponding to time shaft position " 00:01:38 " to be " This is arouter. " (step 320), and the user (in Figure 11 is in bottom line mode as the presentation mode that be selected words for choosing words in " This is a router. " for " router " in caption content, at this only for illustrating, the present invention is not as restriction, the presentation mode that is selected words also can be change of background, the modes such as font variation).
Then, when the user be provided the time shaft position choose in for " This is a router. " for the caption content in captions data corresponding to " 00:01:38 " words for " router " after, can receive users by receiver module 43 be that caption content captions data corresponding to " 00:01:38 " is " router " (step 330) for the words of selecting in " Thisis a router. " from the time shaft position.
then, can (only illustrate as an example with translation word stocks in the present embodiment from translation word stocks by translation module 44 again, but the present invention is not as restriction) in the chosen words of inquiry be that translation words of " router " correspondence is " router " (step 340), and translation module 44 inquire translation words corresponding to chosen words " router " for " router " afterwards, can translate the demonstration (step 350) that is interpreted as " router " by display module 45, the demonstration that is interpreted as " router " for translation please refer to shown in Figure 12 A and Figure 12 B, the translation of the caption translating when Figure 12 A is depicted as second embodiment of the invention and provides image to play explains that the first presentation mode shows schematic diagram, the translation of the caption translating when Figure 12 B is depicted as second embodiment of the invention and provides image to play explains that the second presentation mode shows schematic diagram, and the presentation mode that is interpreted as " router " for translation in Figure 12 A and Figure 12 B is only for illustrating, the present invention is as restriction, provides thus the user to understand chosen words and is interpreted as " router " for the translation of " router ".
in sum, difference between the present invention and prior art is that the present invention is when image is play as can be known, whether the caption content of the captions data that the time shaft of search image is corresponding has the words that the user inputs, when searching caption content and have words, suspend the broadcast of image, and the time out when suspending according to image inquires temporal information and the caption content with time out from the captions archives, and Word translation is the translation words, can increase translation words and storing subtitling archives again newly after the words of caption content, replay image according to playback signal from time out at last.
Can solve prior art by this technological means existing for the further identification caption result of proofreading and correct of image employing OCR identification caption needs, carry out again the problem of caption translating, and then reach the technique effect that directly to translate image caption when image is play.
Although execution mode provided by the present invention as above, described content is not in order to direct restriction scope of patent protection of the present invention.Any those skilled in the art can do a little change what implement in form and on details under the prerequisite that does not break away from the disclosed spirit and scope of the present invention.Scope of patent protection of the present invention, still must with appending claims the person of being defined be as the criterion.