CN109582823A - Video information chain type storage method, device, computer equipment and storage medium - Google Patents
Video information chain type storage method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109582823A CN109582823A CN201811389154.9A CN201811389154A CN109582823A CN 109582823 A CN109582823 A CN 109582823A CN 201811389154 A CN201811389154 A CN 201811389154A CN 109582823 A CN109582823 A CN 109582823A
- Authority
- CN
- China
- Prior art keywords
- information
- video
- teller
- processed
- video file
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002123 temporal effect Effects 0.000 claims description 33
- 238000005520 cutting process Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000006835 compression Effects 0.000 abstract description 2
- 238000007906 compression Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000000151 deposition Methods 0.000 description 5
- 210000004027 cell Anatomy 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 210000000352 storage cell Anatomy 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
- G10L2015/025—Phonemes, fenemes or fenones being the recognition units
Abstract
The invention discloses video information chain type storage method, device, computer equipment and storage mediums.Method includes: to obtain video file to be processed, is cut to video file to be processed by video Slicing Model for Foreign to obtain multiple video-frequency bands to be stored；Obtained multiple voice messagings wait store in video-frequency band are identified to obtain text information corresponding with teller according to preset speech recognition modeling；View information corresponding with text information is intercepted in video-frequency band from wait store；Obtained text information and view information are stored into presetting database chained list corresponding with the teller according to the corresponding teller of text information.The present invention is based on compression storing data technologies, lightweight storage is carried out to video file to be processed to realize, memory space needed for greatly reducing video file in the case where not losing important information in video file achieves very good effect in actual application.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of video information chain type storage methods, device, computer
Equipment and storage medium.
Background technique
Need to ensure that the important information in video file is not missed when saving to video file, thus need to occupy compared with
Big memory headroom, traditional processing method are the format of video file to be converted or reduced the resolution ratio of video file
To carry out compression processing, to reduce the byte number of video file, however due to after processing obtained video file still need compared with
Big memory headroom can store, and the problem of video file need to occupy a large amount of memory headrooms can not still be solved perfectly.Thus, it is existing
Method for processing video frequency there are problems that video file lightweight can not being stored.
Summary of the invention
The embodiment of the invention provides a kind of video information chain type storage method, device, computer equipment and storage medium,
Aim to solve the problem that in the presence of the prior art the problem of video file lightweight can not be stored.
In a first aspect, the embodiment of the invention provides a kind of video information chain type storage methods comprising:
Video file to be processed is obtained, video file to be processed is cut by video Slicing Model for Foreign multiple to obtain
Video-frequency band to be stored；
Obtained multiple voice messagings wait store in video-frequency band are identified according to preset speech recognition modeling
To obtain text information corresponding with teller；
View information corresponding with text information is intercepted in video-frequency band from wait store；
Obtained text information and view information are stored to presetting database according to the corresponding teller of text information
In chained list corresponding with the teller.
Second aspect, the embodiment of the invention provides a kind of video information chain type storage devices comprising:
Video file cutter unit, for obtaining video file to be processed, by video Slicing Model for Foreign to video to be processed
File is cut to obtain multiple video-frequency bands to be stored；
Voice messaging recognition unit, for according to preset speech recognition modeling to obtained multiple video-frequency bands to be stored
In voice messaging identified to obtain text information corresponding with teller；
View information acquiring unit, for intercepting view information corresponding with text information in video-frequency band from wait store；
Information memory cell, for according to the corresponding teller of text information by obtained text information and view information
It stores into presetting database chained list corresponding with the teller.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
Video information chain type storage method described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
Video information chain type storage method described in first aspect.
The embodiment of the invention provides a kind of video information chain type storage method, device, computer equipment and storage mediums.
By being cut to video file to be processed, and obtain wait store text information and corresponding view information in video-frequency band,
Text information and view information are saved into chained list, lightweight storage is carried out to video file to be processed to realize, is not being lost
Memory space needed for greatly reducing video file in the case where important information in video file is lost, in actual application
Achieve very good effect.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of video information chain type storage method provided in an embodiment of the present invention；
Fig. 2 is the sub-process schematic diagram of video information chain type storage method provided in an embodiment of the present invention；
Fig. 3 is another sub-process schematic diagram of video information chain type storage method provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of video information chain type storage method provided in an embodiment of the present invention；
Fig. 5 is another flow diagram of video information chain type storage method provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of video information chain type storage device provided in an embodiment of the present invention；
Fig. 7 is the subelement schematic block diagram of video information chain type storage device provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of video information chain type storage device provided in an embodiment of the present invention；
Fig. 9 is another subelement schematic block diagram of video information chain type storage device provided in an embodiment of the present invention；
Figure 10 is another schematic block diagram of video information chain type storage device provided in an embodiment of the present invention；
Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is the flow diagram of video information chain type storage method provided in an embodiment of the present invention.It should
Video information chain type storage method is applied in the terminal device with information storage function, such as desktop computer, notebook electricity
Brain, tablet computer or mobile phone etc..
As shown in Figure 1, the method comprising the steps of S110~S140.
S110, video file to be processed is obtained, video file to be processed is cut to obtain by video Slicing Model for Foreign
To multiple video-frequency bands to be stored.
Video file to be processed is obtained, video file to be processed is cut by video Slicing Model for Foreign multiple to obtain
Video-frequency band to be stored.One video file to be processed is inputted user terminal by user, by video Slicing Model for Foreign to view to be processed
Frequency file is identified and is cut, and multiple video-frequency bands to be stored are obtained.Wherein, video file to be processed is what user was inputted
The video file of lightweight storage need to be carried out, video file to be processed includes number information, video time stamp and teller's information.
Specifically, number information is the number identified for video file to be processed, the ID of video file to be processed that is to say,
Each video file to be processed correspondence possesses a number information, the number information of video file to be handled do not repeat；
Video time stamp is the information being marked for the time to video file to be processed, be can determine by video time stamp
The specific creation time of video file to be processed；Teller's information is the letter for the teller that video file to be processed is included
It ceases, may include one or more tellers in a video file to be processed.
For example, only including in corresponding teller's information if video file to be processed is the video file of a class journey
One teller；If video file to be processed is that one section of aspectant talk show is recorded a video, in corresponding teller's information
Include multiple tellers.
Such as the information that some video file to be processed is included is as shown in table 1.
| Number information | Video time stamp | Teller's information |
| S10021 | 2018.04.11 | AA、BB、CCC |
Table 1
In one embodiment, as shown in Fig. 2, step S110 includes sub-step S111 and S112.
S111, teller's switching is obtained by teller's acquisition of information in video Slicing Model for Foreign and video file to be processed
Time point.
Teller's switching time is obtained by teller's acquisition of information in video Slicing Model for Foreign and video file to be processed
Point.Specifically, if in teller's information only including a teller, without teller's switching time in the video file to be processed
Point does not carry out cutting process to the video file to be processed；If in teller's information including multiple tellers, the video to be processed
Comprising one or more teller's switching time points in file, then need to be obtained in video file to be processed according to video Slicing Model for Foreign
Teller's switching time point.The teller in video file to be processed is identified by video Slicing Model for Foreign, can be obtained
The switching time point for switching to another teller in video file to be processed from a teller is taken, is wrapped in video Slicing Model for Foreign
Face recognition containing all tellers is as a result, carry out face to the teller in video file to be processed by video Slicing Model for Foreign
Identification, can match to obtain the teller of current picture, as picture teller previous in video file to be processed and latter picture
Teller's switching then occurs when teller is not identical, obtain that teller in two pictures of video file to be processed switches when
Between teller's switching time point as the resulting.
S112, video file to be processed is cut to obtain according to teller's switching time point in video file to be processed
Take the corresponding video-frequency band to be stored of each teller.
Video file to be processed is cut according to teller's switching time point in video file to be processed every to obtain
The corresponding video-frequency band to be stored of one teller.It can be by video file to be processed according to obtained teller's switching time point
Multiple video-frequency bands to be stored are cut into, specifically, each video-frequency band to be stored is corresponding with a teller, each waits depositing
Storing up video-frequency band includes its corresponding temporal information in video file to be processed.
S120, according to preset speech recognition modeling to it is obtained it is multiple wait store the voice messaging in video-frequency band carry out
Identification is to obtain text information corresponding with teller.
Obtained multiple voice messagings wait store in video-frequency band are identified according to preset speech recognition modeling,
To obtain text information corresponding with teller.By speech recognition modeling can treat storage video-frequency band in voice messaging into
Row identification, to obtain corresponding text information, each section of text information is corresponding with a teller.Speech recognition modeling is
Concrete model for identifying the voice messaging in video file.Speech recognition modeling includes acoustic model, voice spy
Levy dictionary and semantic analytic modell analytical model.
In one embodiment, as shown in figure 3, step S120 includes sub-step S121, S122 and S123.
S121, cutting is carried out to the voice messaging to obtain voice messaging according to the acoustic model in speech recognition modeling
Included in multiple phonemes.
Cutting is carried out to the voice messaging according to the acoustic model in speech recognition modeling, the voice messaging can be obtained
Included in multiple phonemes.Voice messaging that is to say user by a word described in sounding, specifically, user terminal is connect
The voice messaging received is made of the phoneme of multiple character sounds, the phoneme of a character include the character sound frequency and
Tone color.Include the phoneme of all character sounds in acoustic model, by by phoneme all in voice messaging and acoustic model into
Row matching can carry out cutting to the phoneme of character single in voice messaging, finally obtain institute in the voice messaging by cutting
The multiple phonemes for including.
S122, obtained phoneme is matched according to the phonetic feature dictionary in speech recognition modeling, will be owned
Phoneme conversion is Pinyin information.
Obtained phoneme is matched according to the phonetic feature dictionary in speech recognition modeling, it can be by all phonemes
Be converted to Pinyin information.It include the corresponding phoneme information of all character phonetics in phonetic feature dictionary, by by obtained sound
Corresponding with the character phonetic phoneme information of element is matched, can be by the phoneme conversion of single character in phonetic feature dictionary and
The character phonetic that the phoneme matches, to realize all phoneme conversions included in voice messaging as Pinyin information.
S123, according to the semantic analytic modell analytical model in speech recognition modeling to obtained Pinyin information carry out semantic parsing with
Pinyin information is converted into text information.
Semantic parsing is carried out to obtained Pinyin information according to the semantic analytic modell analytical model in speech recognition modeling, to realize
Pinyin information is converted into text information.Include mapping corresponding between Pinyin information and text information in semantic analytic modell analytical model
Relationship, by mapping relations included in semantic analytic modell analytical model obtained Pinyin information can be carried out semantic parsing with incite somebody to action
Pinyin information is converted to text information.
For example, phonetic " h é, p í ng " text information corresponding in semantic analytic modell analytical model is " peace ".
S130, view information corresponding with text information is intercepted in video-frequency band from wait store.
View information corresponding with text information is intercepted in video-frequency band at random from wait store.From wait store in video-frequency band at random
Cut-away view information, view information as corresponding with the video-frequency band to be stored, since each video-frequency band to be stored is with one
A teller is corresponding, and the view information intercepted is corresponding with teller.Specifically, view information can be one section of video or one
Picture is used as the corresponding view information of video-frequency band to be stored by one section of video or a picture, can treat storage video
The view information of teller is intercepted and is saved in section.For example, can intercept if view information is one section of video wait store view
The video of one section of 5 seconds or 10 seconds is used as the corresponding view information of video-frequency band to be stored in frequency range；If view information is a picture,
It then can be from wait store the picture for intercepting a teller in video-frequency band at random as the corresponding view information of video-frequency band to be stored.
S140, obtained text information and view information are stored to present count according to the corresponding teller of text information
According in the chained list corresponding with the teller of library.
Text information included in video file to be processed and view information are stored into chained list, to view to be processed
Information included in frequency file carries out lightweight storage.Since the voice messaging in video file to be processed is converted into text
Information has intercepted the view information of each teller from video file to be processed, therefore, is wrapped in video file to be processed
The information contained is saved.Presetting database is the database for being stored to data information, includes more in database
A chained list, chained list are to be stored according to time shaft to text information included in video file to be processed and view information
Data storage cell, each teller is corresponding with a chained list in database.Wherein, the data stored in chained list
The logical order of information is realized by the pointer link orders in chained list, in the present embodiment with text information to be processed
Logical order of the corresponding temporal information as chained list in video file, that is to say will for pointer link orders by temporal information
Text information and view information are stored into chained list in video file to be processed.It is suitable by the logic using time sequencing as chained list
Ordered pair text information and view information are stored, and user can get teller using temporal information as the letter of sequence by chained list
List is ceased, the information that wherein chained list is stored has the characteristic that can not be deleted.
In one embodiment, as shown in figure 4, step S140 includes sub-step S141, S142 and S143.
S141, text information corresponding temporal information in video file to be processed is obtained.
Obtain text information corresponding temporal information in video file to be processed.Since each video-frequency band to be stored is equal
Comprising it in video file to be processed corresponding temporal information, and in text information and video file to be processed wait store view
Frequency range corresponds, therefore, by obtain corresponding with text information band storage video-frequency band in video file to be processed when
Between information, text information corresponding temporal information in video file to be processed can be obtained.
For example, temporal information of a certain video-frequency band to be stored in video file to be processed is " 1 point 20 seconds to 3 point 10
Second ", then will " 1 point 10 seconds 20 seconds to 3 points " as text information corresponding with the video-frequency band to be stored in video file to be processed
Corresponding temporal information.
S142, according to the temporal information and corresponding teller of text information with by text information store to teller couple
In the chained list answered.
Text information is stored into chained list according to the temporal information of text information and corresponding teller.Every passage
Information is corresponding with a teller, can obtain chained list corresponding with the teller from presetting database by teller, with
The temporal information of text information stores text information into the chained list as the logical order of chained list, and will be with text information pair
The teller answered is added in stored text information.
S143, view information corresponding with text information is inserted into the text information of storage in the chained list to view
Information is saved.
View information corresponding with text information is inserted into the text information of storage in the chained list to view information
It is saved.Since text information is from accordingly having intercepted view information corresponding in text information wait store in video-frequency band, because
This can will have been stored by the corresponding relationship of text information and view information in the corresponding view information insertion chained list of text information
Text information in.
In one embodiment, as shown in figure 5, further including step S150 after step S140.
S150, index corresponding with text information is generated according to number information, the video time stamp of video file to be processed
Information is simultaneously stored into the database.
Index information corresponding with text information is generated simultaneously according to the number information of video file to be processed, video time stamp
It stores into the database.For convenience of searching the text information and view information that are stored in chained list, can according to
Handle the number information of video file, video time stamp generates index information corresponding with text information, a video to be processed
File can correspond to one or more text informations, then the one or more index informations of corresponding generation are needed, by depositing index information
Storage can significantly facilitate user and quickly be searched the data stored in chained list into database, improve to data in chained list
The efficiency searched.
For example, third section text of a certain text information for video file to be processed in table 1, and text information is to be processed
Corresponding temporal information is " 1 point and 20 seconds to 3 points and 10 seconds " in video file, then the corresponding index information generated be " S10021-3,
2018.04.11-1 divide 20 seconds to 3 points and 10 seconds ".
By being cut to video file to be processed, and obtain wait store text information and corresponding view in video-frequency band
Figure information, text information and view information are saved into chained list, carry out lightweight storage to video file to be processed to realize,
Memory space needed for greatly reducing video file in the case where not losing important information in video file, in practical application
Very good effect is achieved in the process.
The embodiment of the present invention also provides a kind of video information chain type storage device, which is used for
Execute any embodiment of aforementioned video information chain type storage method.Specifically, referring to Fig. 6, Fig. 6 is that the embodiment of the present invention mentions
The schematic block diagram of the video information chain type storage device of confession.The video information chain type storage device can be configured at desktop
In the terminal devices such as brain, laptop, tablet computer or mobile phone.
As shown in fig. 6, video information chain type storage device 100 includes video file cutter unit 110, voice messaging identification
Unit 120, view information acquiring unit 130, information memory cell 140.
Video file cutter unit 110, for obtaining video file to be processed, by video Slicing Model for Foreign to view to be processed
Frequency file is cut to obtain multiple video-frequency bands to be stored.
Video file to be processed is obtained, video file to be processed is cut by video Slicing Model for Foreign multiple to obtain
Video-frequency band to be stored.One video file to be processed is inputted user terminal by user, by video Slicing Model for Foreign to view to be processed
Frequency file is identified and is cut, and multiple video-frequency bands to be stored are obtained.Wherein, video file to be processed is what user was inputted
The video file of lightweight storage need to be carried out, video file to be processed includes number information, video time stamp and teller's information.
Specifically, number information is the number identified for video file to be processed, the ID of video file to be processed that is to say,
Each video file to be processed correspondence possesses a number information, the number information of video file to be handled do not repeat；
Video time stamp is the information being marked for the time to video file to be processed, be can determine by video time stamp
The specific creation time of video file to be processed；Teller's information is the letter for the teller that video file to be processed is included
It ceases, may include one or more tellers in a video file to be processed.
In other inventive embodiments, as shown in fig. 7, the video file cutter unit 110 includes subelement: switching time
Point acquiring unit 111 and cutting process unit 112.
Switching time point acquiring unit 111, for passing through the teller in video Slicing Model for Foreign and video file to be processed
Acquisition of information obtains teller's switching time point.
Teller's switching time is obtained by teller's acquisition of information in video Slicing Model for Foreign and video file to be processed
Point.Specifically, if in teller's information only including a teller, without teller's switching time in the video file to be processed
Point does not carry out cutting process to the video file to be processed；If in teller's information including multiple tellers, the video to be processed
Comprising one or more teller's switching time points in file, then need to be obtained in video file to be processed according to video Slicing Model for Foreign
Teller's switching time point.The teller in video file to be processed is identified by video Slicing Model for Foreign, can be obtained
The switching time point for switching to another teller in video file to be processed from a teller is taken, is wrapped in video Slicing Model for Foreign
Face recognition containing all tellers is as a result, carry out face to the teller in video file to be processed by video Slicing Model for Foreign
Identification, can match to obtain the teller of current picture, as picture teller previous in video file to be processed and latter picture
Teller's switching then occurs when teller is not identical, obtain that teller in two pictures of video file to be processed switches when
Between teller's switching time point as the resulting.
Cutting process unit 112 is used for according to teller's switching time point in video file to be processed to video to be processed
File is cut to obtain the corresponding video-frequency band to be stored of each teller.
Video file to be processed is cut according to teller's switching time point in video file to be processed every to obtain
The corresponding video-frequency band to be stored of one teller.It can be by video file to be processed according to obtained teller's switching time point
Multiple video-frequency bands to be stored are cut into, specifically, each video-frequency band to be stored is corresponding with a teller, each waits depositing
Storing up video-frequency band includes its corresponding temporal information in video file to be processed.
Voice messaging recognition unit 120, for according to preset speech recognition modeling to it is obtained it is multiple wait store view
Voice messaging in frequency range is identified to obtain text information corresponding with teller.
Obtained multiple voice messagings wait store in video-frequency band are identified according to preset speech recognition modeling,
To obtain text information corresponding with teller.By speech recognition modeling can treat storage video-frequency band in voice messaging into
Row identification, to obtain corresponding text information, each section of text information is corresponding with a teller.Speech recognition modeling is
Concrete model for identifying the voice messaging in video file.Speech recognition modeling includes acoustic model, voice spy
Levy dictionary and semantic analytic modell analytical model.
In other inventive embodiments, as shown in figure 8, the voice messaging recognition unit 120 includes subelement: phone segmentation
Unit 121, Pinyin information acquiring unit 122 and text information acquiring unit 123.
Phone segmentation unit 121, for being cut according to the acoustic model in speech recognition modeling to the voice messaging
Divide to obtain multiple phonemes included in voice messaging.
Cutting is carried out to the voice messaging according to the acoustic model in speech recognition modeling, the voice messaging can be obtained
Included in multiple phonemes.Voice messaging that is to say user by a word described in sounding, specifically, user terminal is connect
The voice messaging received is made of the phoneme of multiple character sounds, the phoneme of a character include the character sound frequency and
Tone color.Include the phoneme of all character sounds in acoustic model, by by phoneme all in voice messaging and acoustic model into
Row matching can carry out cutting to the phoneme of character single in voice messaging, finally obtain institute in the voice messaging by cutting
The multiple phonemes for including.
Pinyin information acquiring unit 122, for according to the phonetic feature dictionary in speech recognition modeling to obtained sound
Element is matched, using by all phoneme conversions as Pinyin information.
Obtained phoneme is matched according to the phonetic feature dictionary in speech recognition modeling, it can be by all phonemes
Be converted to Pinyin information.It include the corresponding phoneme information of all character phonetics in phonetic feature dictionary, by by obtained sound
Corresponding with the character phonetic phoneme information of element is matched, can be by the phoneme conversion of single character in phonetic feature dictionary and
The character phonetic that the phoneme matches, to realize all phoneme conversions included in voice messaging as Pinyin information.
Text information acquiring unit 123, for according to the semantic analytic modell analytical model in speech recognition modeling to obtained spelling
Message breath carries out semantic parsing so that Pinyin information is converted to text information.
Semantic parsing is carried out to obtained Pinyin information according to the semantic analytic modell analytical model in speech recognition modeling, to realize
Pinyin information is converted into text information.Include mapping corresponding between Pinyin information and text information in semantic analytic modell analytical model
Relationship, by mapping relations included in semantic analytic modell analytical model obtained Pinyin information can be carried out semantic parsing with incite somebody to action
Pinyin information is converted to text information.
View information acquiring unit 130, for intercepting view information corresponding with text information in video-frequency band from wait store.
View information corresponding with text information is intercepted in video-frequency band at random from wait store.From wait store in video-frequency band at random
Cut-away view information, view information as corresponding with the video-frequency band to be stored, since each video-frequency band to be stored is with one
A teller is corresponding, and the view information intercepted is corresponding with teller.Specifically, view information can be one section of video or one
Picture is used as the corresponding view information of video-frequency band to be stored by one section of video or a picture, can treat storage video
The view information of teller is intercepted and is saved in section.For example, can intercept if view information is one section of video wait store view
The video of one section of 5 seconds or 10 seconds is used as the corresponding view information of video-frequency band to be stored in frequency range；If view information is a picture,
It then can be from wait store the picture for intercepting a teller in video-frequency band at random as the corresponding view information of video-frequency band to be stored.
Information memory cell 140, for according to the corresponding teller of text information by obtained text information and view
Information is stored into presetting database chained list corresponding with the teller.
Text information included in video file to be processed and view information are stored into chained list, to view to be processed
Information included in frequency file carries out lightweight storage.Since the voice messaging in video file to be processed is converted into text
Information has intercepted the view information of each teller from video file to be processed, therefore, is wrapped in video file to be processed
The information contained is saved.Presetting database is the database for being stored to data information, includes more in database
A chained list, chained list are to be stored according to time shaft to text information included in video file to be processed and view information
Data storage cell, each teller is corresponding with a chained list in database.Wherein, the data stored in chained list
The logical order of information is realized by the pointer link orders in chained list, in the present embodiment with text information to be processed
Logical order of the corresponding temporal information as chained list in video file, that is to say will for pointer link orders by temporal information
Text information and view information are stored into chained list in video file to be processed.It is suitable by the logic using time sequencing as chained list
Ordered pair text information and view information are stored, and user can get teller using temporal information as the letter of sequence by chained list
List is ceased, the information that wherein chained list is stored has the characteristic that can not be deleted.
In other inventive embodiments, as shown in figure 9, the information memory cell 140 includes subelement: temporal information is obtained
Unit 141, text information storage unit 142 and view information storage unit 143.
Temporal information acquiring unit 141, for obtaining text information corresponding temporal information in video file to be processed.
Obtain text information corresponding temporal information in video file to be processed.Since each video-frequency band to be stored is equal
Comprising it in video file to be processed corresponding temporal information, and in text information and video file to be processed wait store view
Frequency range corresponds, therefore, by obtain corresponding with text information band storage video-frequency band in video file to be processed when
Between information, text information corresponding temporal information in video file to be processed can be obtained.
Text information storage unit 142, for according to the temporal information and corresponding teller of text information with by text
Information is stored into chained list corresponding with teller.
Text information is stored into chained list according to the temporal information of text information and corresponding teller.Every passage
Information is corresponding with a teller, can obtain chained list corresponding with the teller from presetting database by teller, with
The temporal information of text information stores text information into the chained list as the logical order of chained list, and will be with text information pair
The teller answered is added in stored text information.
View information storage unit 143, for view information corresponding with text information to be inserted into the chained list
Text information is stored to save to view information.
View information corresponding with text information is inserted into the text information of storage in the chained list to view information
It is saved.Since text information is from accordingly having intercepted view information corresponding in text information wait store in video-frequency band, because
This can will have been stored by the corresponding relationship of text information and view information in the corresponding view information insertion chained list of text information
Text information in.
In other inventive embodiments, as shown in Figure 10, the video information chain type storage device 100 further includes subelement:
Index information storage unit 150.
Index information storage unit 150, for according to the number information of video file to be processed, video time stamp generate with
The corresponding index information of text information is simultaneously stored into the database.
Index information corresponding with text information is generated simultaneously according to the number information of video file to be processed, video time stamp
It stores into the database.For convenience of searching the text information and view information that are stored in chained list, can according to
Handle the number information of video file, video time stamp generates index information corresponding with text information, a video to be processed
File can correspond to one or more text informations, then the one or more index informations of corresponding generation are needed, by depositing index information
Storage can significantly facilitate user and quickly be searched the data stored in chained list into database, improve to data in chained list
The efficiency searched.
By being cut to video file to be processed, and obtain wait store text information and corresponding view in video-frequency band
Figure information, text information and view information are saved into chained list, carry out lightweight storage to video file to be processed to realize,
Memory space needed for greatly reducing video file in the case where not losing important information in video file, in practical application
Very good effect is achieved in the process.
Above-mentioned video information chain type storage device can be implemented as the form of computer program, which can be
It is run in computer equipment as shown in figure 11.
Figure 11 is please referred to, Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Refering to fig. 11, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute video information chain type storage method.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute video information chain type storage method.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Figure 11, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: video file to be processed is obtained, video file to be processed is cut by video Slicing Model for Foreign multiple wait deposit to obtain
Store up video-frequency band；Obtained multiple voice messagings wait store in video-frequency band are identified according to preset speech recognition modeling
To obtain text information corresponding with teller；View information corresponding with text information is intercepted in video-frequency band from wait store；Root
Obtained text information and view information are stored to presetting database and the teller according to the corresponding teller of text information
In corresponding chained list.
In one embodiment, processor 502 is executing acquisition video file to be processed, treats place by video Slicing Model for Foreign
When reason video file is cut to obtain multiple steps wait store video-frequency band, perform the following operations: by video blanking punch
Teller's acquisition of information in type and video file to be processed obtains teller's switching time point；According in video file to be processed
Teller's switching time point cuts video file to be processed to obtain the corresponding video-frequency band to be stored of each teller.
In one embodiment, processor 502 is being executed according to preset speech recognition modeling to obtained multiple wait deposit
When voice messaging in storage video-frequency band is identified to obtain the step of text information corresponding with teller, following behaviour is executed
Make: cutting is carried out to the voice messaging to obtain included in voice messaging according to the acoustic model in speech recognition modeling
Multiple phonemes；Obtained phoneme is matched according to the phonetic feature dictionary in speech recognition modeling, by all phonemes
Be converted to Pinyin information；Semantic parsing is carried out to obtained Pinyin information according to the semantic analytic modell analytical model in speech recognition modeling
Pinyin information is converted to text information.
In one embodiment, processor 502 believes obtained text according to the corresponding teller of text information in execution
It when breath and view information store the step into presetting database chained list corresponding with the teller, performs the following operations: obtaining
Text information corresponding temporal information in video file to be processed；According to the temporal information of text information and corresponding teller
Storing text information into chained list corresponding with teller；View information corresponding with text information is inserted into the chained list
In the text information of storage to be saved to view information.
In one embodiment, processor 502 believes obtained text according to the corresponding teller of text information in execution
After breath and view information store the step into presetting database chained list corresponding with the teller, also perform the following operations:
Index information corresponding with text information is generated according to the number information of video file to be processed, video time stamp and is stored to institute
It states in database.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Figure 11 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 11,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
Machine program performs the steps of when being executed by processor obtains video file to be processed, by video Slicing Model for Foreign to be processed
Video file is cut to obtain multiple video-frequency bands to be stored；According to preset speech recognition modeling to it is obtained it is multiple to
Voice messaging in storage video-frequency band is identified to obtain text information corresponding with teller；It is cut from wait store in video-frequency band
Take view information corresponding with text information；Obtained text information and view are believed according to the corresponding teller of text information
Breath is stored into presetting database chained list corresponding with the teller.
In one embodiment, described to obtain video file to be processed, by video Slicing Model for Foreign to video file to be processed
It is cut to obtain multiple video-frequency bands to be stored, comprising: pass through the speech in video Slicing Model for Foreign and video file to be processed
People's acquisition of information obtains teller's switching time point；According to teller's switching time point in video file to be processed to view to be processed
Frequency file is cut to obtain the corresponding video-frequency band to be stored of each teller.
In one embodiment, it is described according to preset speech recognition modeling to obtained multiple wait store in video-frequency band
Voice messaging is identified the step of to obtain text information corresponding with teller, comprising: according in speech recognition modeling
Acoustic model carries out cutting to the voice messaging to obtain multiple phonemes included in voice messaging；According to speech recognition mould
Phonetic feature dictionary in type matches obtained phoneme, using by all phoneme conversions as Pinyin information；According to voice
Semantic analytic modell analytical model in identification model carries out semantic parsing to obtained Pinyin information Pinyin information is converted to text
Information.
In one embodiment, it is described according to the corresponding teller of text information by obtained text information and view information
Store the step into presetting database chained list corresponding with the teller, comprising: obtain text information in video text to be processed
Corresponding temporal information in part；According to the temporal information of text information and corresponding teller with by text information store to say
It talks about in the corresponding chained list of people；View information corresponding with text information is inserted into the text information of storage in the chained list with right
View information is saved.
In one embodiment, it is described according to the corresponding teller of text information by obtained text information and view information
After storing the step into presetting database chained list corresponding with the teller, further includes: according to video file to be processed
Number information, video time stamp generate index information corresponding with text information and store into the database.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a computer readable storage medium, including some instructions are used so that one
Platform computer equipment (can be personal computer, server or the network equipment etc.) executes described in each embodiment of the present invention
The all or part of the steps of method.And computer readable storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
The various media that can store program code such as (ROM, Read-OnlyMemory), magnetic or disk.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of video information chain type storage method characterized by comprising
Video file to be processed is obtained, video file to be processed is cut by video Slicing Model for Foreign multiple wait deposit to obtain
Store up video-frequency band；
Obtained multiple voice messagings wait store in video-frequency band are identified to obtain according to preset speech recognition modeling
To text information corresponding with teller；
View information corresponding with text information is intercepted in video-frequency band from wait store；
Obtained text information and view information stored according to the teller corresponding with the teller to presetting database
Chained list in.
2. video information chain type storage method according to claim 1, which is characterized in that described to pass through video Slicing Model for Foreign
Video file to be processed is cut to obtain multiple video-frequency bands to be stored, comprising:
Teller's switching time point is obtained by teller's acquisition of information in video Slicing Model for Foreign and video file to be processed；
Video file to be processed is cut to obtain each according to teller's switching time point in video file to be processed
The corresponding video-frequency band to be stored of teller.
3. video information chain type storage method according to claim 1, which is characterized in that described to be known according to preset voice
Other model identifies to obtain text corresponding with teller obtained multiple voice messagings wait store in video-frequency band
Information, comprising:
Cutting is carried out to obtain included in voice messaging to the voice messaging according to the acoustic model in speech recognition modeling
Multiple phonemes；
Obtained phoneme is matched according to the phonetic feature dictionary in speech recognition modeling, is by all phoneme conversions
Pinyin information；
Semantic parsing is carried out believing phonetic to obtained Pinyin information according to the semantic analytic modell analytical model in speech recognition modeling
Breath is converted to text information.
4. video information chain type storage method according to claim 1, which is characterized in that described corresponding according to text information
Teller obtained text information and view information are stored into presetting database chained list corresponding with the teller, wrap
It includes:
Obtain text information corresponding temporal information in video file to be processed；
According to the temporal information of text information and corresponding teller storing text information to chained list corresponding with teller
In；
By the text information of storage that view information corresponding with text information is inserted into the chained list to be carried out to view information
It saves.
5. video information chain type storage method according to claim 1, which is characterized in that described corresponding according to text information
Teller obtained text information and view information are stored into presetting database chained list corresponding with the teller it
Afterwards, further includes:
Index information corresponding with text information is generated according to the number information of video file to be processed, video time stamp and is stored
To in the database.
6. a kind of video information chain type storage device characterized by comprising
Video file cutter unit, for obtaining video file to be processed, by video Slicing Model for Foreign to video file to be processed
It is cut to obtain multiple video-frequency bands to be stored；
Voice messaging recognition unit, for according to preset speech recognition modeling to obtained multiple wait store in video-frequency band
Voice messaging is identified to obtain text information corresponding with teller；
View information acquiring unit, for intercepting view information corresponding with text information in video-frequency band from wait store；
Information memory cell, for being stored obtained text information and view information according to the corresponding teller of text information
Into presetting database chained list corresponding with the teller.
7. video information chain type storage device according to claim 6, which is characterized in that the video file cutting is single
Member, comprising:
Switching time point acquiring unit, for passing through teller's acquisition of information in video Slicing Model for Foreign and video file to be processed
Obtain teller's switching time point；
Cutting process unit, for being carried out according to teller's switching time point in video file to be processed to video file to be processed
Cutting is to obtain the corresponding video-frequency band to be stored of each teller.
8. video information chain type storage device according to claim 6, which is characterized in that the voice messaging identification is single
Member, comprising:
Phone segmentation unit, for carrying out cutting to the voice messaging according to the acoustic model in speech recognition modeling to obtain
Multiple phonemes included in voice messaging；
Pinyin information acquiring unit, for according to the phonetic feature dictionary in speech recognition modeling to obtained phoneme carry out
Match, using by all phoneme conversions as Pinyin information；
Text information acquiring unit, for according to the semantic analytic modell analytical model in speech recognition modeling to obtained Pinyin information into
The semantic parsing of row is to be converted to text information for Pinyin information.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in video information chain type storage method.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make the processor execute such as view described in any one of claim 1 to 5 when being executed by a processor
Frequency information chain type storage method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811389154.9A CN109582823A (en) | 2018-11-21 | 2018-11-21 | Video information chain type storage method, device, computer equipment and storage medium |
| PCT/CN2019/092636 WO2020103447A1 (en) | 2018-11-21 | 2019-06-25 | Link-type storage method and apparatus for video information, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811389154.9A CN109582823A (en) | 2018-11-21 | 2018-11-21 | Video information chain type storage method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109582823A true CN109582823A (en) | 2019-04-05 |
Family
ID=65923631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811389154.9A Pending CN109582823A (en) | 2018-11-21 | 2018-11-21 | Video information chain type storage method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109582823A (en) |
| WO (1) | WO2020103447A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414352A (en) * | 2019-06-26 | 2019-11-05 | 深圳市容会科技有限公司 | The method and relevant device of PPT the file information are extracted from video file |
| WO2020103447A1 (en) * | 2018-11-21 | 2020-05-28 | 平安科技（深圳）有限公司 | Link-type storage method and apparatus for video information, computer device and storage medium |
| CN115129198A (en) * | 2022-06-13 | 2022-09-30 | 中移互联网有限公司 | Data acquisition method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104301649A (en) * | 2014-10-29 | 2015-01-21 | 上海斐讯数据通信技术有限公司 | Video recording storage method, video playing method and video recording storage and playing system |
| CN105512348A (en) * | 2016-01-28 | 2016-04-20 | 北京旷视科技有限公司 | Method and device for processing videos and related audios and retrieving method and device |
| CN105912615A (en) * | 2016-04-05 | 2016-08-31 | 重庆大学 | Human voice content index based audio and video file management method |
| CN107273423A (en) * | 2017-05-15 | 2017-10-20 | 中国移动通信集团湖北有限公司 | Multimedia message data processing method, device and system |
| CN108829765A (en) * | 2018-05-29 | 2018-11-16 | 平安科技（深圳）有限公司 | A kind of information query method, device, computer equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102170552A (en) * | 2010-02-25 | 2011-08-31 | 株式会社理光 | Video conference system and processing method used therein |
| CN106162222B (en) * | 2015-04-22 | 2019-05-24 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
| CN105957531B (en) * | 2016-04-25 | 2019-12-31 | 上海交通大学 | Speech content extraction method and device based on cloud platform |
| CN107241616B (en) * | 2017-06-09 | 2018-10-26 | 腾讯科技（深圳）有限公司 | video lines extracting method, device and storage medium |
| CN109582823A (en) * | 2018-11-21 | 2019-04-05 | 平安科技（深圳）有限公司 | Video information chain type storage method, device, computer equipment and storage medium |
-
2018
- 2018-11-21 CN CN201811389154.9A patent/CN109582823A/en active Pending
-
2019
- 2019-06-25 WO PCT/CN2019/092636 patent/WO2020103447A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104301649A (en) * | 2014-10-29 | 2015-01-21 | 上海斐讯数据通信技术有限公司 | Video recording storage method, video playing method and video recording storage and playing system |
| CN105512348A (en) * | 2016-01-28 | 2016-04-20 | 北京旷视科技有限公司 | Method and device for processing videos and related audios and retrieving method and device |
| CN105912615A (en) * | 2016-04-05 | 2016-08-31 | 重庆大学 | Human voice content index based audio and video file management method |
| CN107273423A (en) * | 2017-05-15 | 2017-10-20 | 中国移动通信集团湖北有限公司 | Multimedia message data processing method, device and system |
| CN108829765A (en) * | 2018-05-29 | 2018-11-16 | 平安科技（深圳）有限公司 | A kind of information query method, device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020103447A1 (en) * | 2018-11-21 | 2020-05-28 | 平安科技（深圳）有限公司 | Link-type storage method and apparatus for video information, computer device and storage medium |
| CN110414352A (en) * | 2019-06-26 | 2019-11-05 | 深圳市容会科技有限公司 | The method and relevant device of PPT the file information are extracted from video file |
| CN110414352B (en) * | 2019-06-26 | 2022-11-29 | 深圳职业技术学院 | Method for extracting PPT (Power Point) file information from video file and related equipment |
| CN115129198A (en) * | 2022-06-13 | 2022-09-30 | 中移互联网有限公司 | Data acquisition method and device, electronic equipment and storage medium |
| CN115129198B (en) * | 2022-06-13 | 2023-10-27 | 中移互联网有限公司 | Data acquisition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020103447A1 (en) | 2020-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9514741B2 (en) | Data shredding for speech recognition acoustic model training under data retention restrictions | |
| CN107211027B (en) | Post-meeting playback system with perceived quality higher than that originally heard in meeting | |
| CN109408818A (en) | New word identification method, device, computer equipment and storage medium | |
| CN109408526A (en) | SQL statement generation method, device, computer equipment and storage medium | |
| CN109582823A (en) | Video information chain type storage method, device, computer equipment and storage medium | |
| CN107211061A (en) | The optimization virtual scene layout played back for space meeting | |
| CN107210045A (en) | The playback of search session and search result | |
| US9514740B2 (en) | Data shredding for speech recognition language model training under data retention restrictions | |
| US20170372702A1 (en) | Method and device for recognizing time information from voice information | |
| CN110334110A (en) | Natural language classification method, device, computer equipment and storage medium | |
| WO2021219554A1 (en) | Speaker identity and content de-identification | |
| CN109801630A (en) | Digital conversion method, device, computer equipment and the storage medium of speech recognition | |
| CN108388597A (en) | Conference summary generation method and device | |
| CN109376273A (en) | Company information map construction method, apparatus, computer equipment and storage medium | |
| CN111310440A (en) | Text error correction method, device and system | |
| EP2869219A1 (en) | Text processing apparatus, text processing method, and computer program product | |
| CN109299471B (en) | Text matching method, device and terminal | |
| CN108595412B (en) | Error correction processing method and device, computer equipment and readable medium | |
| CN110532107B (en) | Interface calling method, device, computer equipment and storage medium | |
| WO2022022049A1 (en) | Long difficult text sentence compression method and apparatus, computer device, and storage medium | |
| CN107886940B (en) | Voice translation processing method and device | |
| CN109582775A (en) | Information input method, device, computer equipment and storage medium | |
| CN109960807A (en) | A kind of intelligent semantic matching process based on context relation | |
| CN108108350B (en) | Noun recognition method and device | |
| CN113434663A (en) | Conference summary generation method based on edge calculation and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |