CN108829765A - A kind of information query method, device, computer equipment and storage medium - Google Patents
A kind of information query method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108829765A CN108829765A CN201810529526.7A CN201810529526A CN108829765A CN 108829765 A CN108829765 A CN 108829765A CN 201810529526 A CN201810529526 A CN 201810529526A CN 108829765 A CN108829765 A CN 108829765A
- Authority
- CN
- China
- Prior art keywords
- file
- information
- multimedia file
- multimedia
- text information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000013518 transcription Methods 0.000 claims abstract description 52
- 230000035897 transcription Effects 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 16
- 230000014509 gene expression Effects 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000003287 optical effect Effects 0.000 claims description 8
- 239000004568 cement Substances 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 235000021167 banquet Nutrition 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of information query method, device, computer equipment and storage medium, the method includes:Obtain multimedia file;Canonical matching is carried out to the file extension of multimedia file, determines the file type of multimedia file;According to the corresponding default analysis mode of file type, multimedia file is parsed, obtains the content text information and the corresponding timestamp information of each content text information of multimedia file;The mapping relations between file identification, content text information and the timestamp information of multimedia file are established, and are recorded as file transcription, are saved in Multimedia Knowledge library;If receiving the inquiry request of user, it is based on Multimedia Knowledge library, key word of the inquiry is matched with content text information, and regard the file transcription of successful match record as query result.Technical solution of the present invention realizes the parsing and inquiry of the multimedia file to different file types, improves the search efficiency of multimedia file.
Description
Technical field
The present invention relates to technical field of the computer network more particularly to a kind of information query method, device, computer equipments
And storage medium.
Background technique
With the fast development of computer hardware technology and software technology, computer networking technology application is also more and more richer
Richness can satisfy the needs of people's diversification.As a kind of new science and technology, it is greatly changed computer networking technology
The development form and developing direction of society, and become a kind of widely applied technology, weight has been played in modern society
The effect wanted.Computer networking technology combines the advantages of computer technology and network technology, can be realized effective biography of information
It passs, it accelerates the speed of information transmission, reduces cost and the time of the transmission of people's information, makes the information exchange between people
More and more frequently, it has gradually changed people's lives mode and business appearance etc., has for the development of society important
It influences.
Currently, the storage mode of information is more diversified, and in daily life, the common information storage means of people is to use
Multimedia file stores general information, and multimedia file includes but is not limited to:Video file, audio file, picture file and
Text file etc., still, most of data bank can do effective retrieval just for the content in text file, for video text
Content in part, audio file and picture file can not be retrieved directly, the low efficiency for causing multimedia file to be inquired.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be improved present multimedia file polling efficiency
Information query method, device, computer equipment and storage medium.
A kind of information query method, including:
Obtain multimedia file;
Using preset regular expression, canonical matching is carried out to the file extension of the multimedia file, determines institute
State the file type of multimedia file;
According to the corresponding default analysis mode of the file type, the multimedia file is parsed, is obtained described
The content text information of multimedia file and the corresponding timestamp information of each content text information;
Establish reflecting between file identification, the content text information and the timestamp information of the multimedia file
Penetrate relationship, and using the file identification, the content text information, the timestamp information and the mapping relations as
The file transcription of the multimedia file records, and is saved in Multimedia Knowledge library;
If receiving the inquiry request comprising key word of the inquiry of user's transmission, it is based on the Multimedia Knowledge library, it will
The key word of the inquiry is matched with the content text information, and the file transcription of successful match is recorded as inquiry knot
Fruit;
Export the query result.
A kind of information query device, including:
Data acquisition module, for obtaining multimedia file;
Type determines model, for using preset regular expression, to the file extension of the multimedia file into
The matching of row canonical, determines the file type of the multimedia file;
Document analysis module is used for according to the corresponding default analysis mode of the file type, to the multimedia file
It is parsed, obtains content text information and each content text information corresponding time of the multimedia file
Stab information;
Preserving module is recorded, for establishing the file identification of the multimedia file, the content text information and described
Mapping relations between timestamp information, and by the file identification, the content text information, the timestamp information, with
And the mapping relations are recorded as the file transcription of the multimedia file, are saved in Multimedia Knowledge library;
Matching inquiry module is based on institute if the inquiry request comprising key word of the inquiry for receiving user's transmission
Multimedia Knowledge library is stated, the key word of the inquiry is matched with the content text information, and by the file of successful match
Transcription record is used as query result;
As a result output module, for exporting the query result.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize the step of above- mentioned information querying method when executing the computer program
Suddenly.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
The step of above- mentioned information querying method is realized when calculation machine program is executed by processor.
Above- mentioned information querying method, device, computer equipment and storage medium, by using preset regular expression,
Canonical matching is carried out to the file extension of the multimedia file got, determines the file type of the multimedia file, and root
According to the corresponding default analysis mode of this document type, multimedia file is parsed, obtains the content text of the multimedia file
This information and the corresponding timestamp information of each content text information, and then establish multimedia file identification, content text letter
Cease the mapping relations between timestamp information, and be deposited into Multimedia Knowledge library, realize pair as file transcription record
After the multimedia file of different file types can be parsed using corresponding analysis mode, formed content text information and
Timestamp information, and be stored in Multimedia Knowledge library in a manner of file transcription record, when the inquiry request for receiving user
When, directly matched by the keyword in inquiry request with the content text information in Multimedia Knowledge library, it can be quick
Multimedia file required for user is inquired, and can timely and accurately obtain keyword according to timestamp information in multimedia text
Specific location in part, to improve the search efficiency of multimedia file.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram of information query method provided in an embodiment of the present invention;
Fig. 2 is the implementation flow chart of information query method provided in an embodiment of the present invention;
Fig. 3 is the implementation flow chart of step S3 in information query method provided in an embodiment of the present invention;
Fig. 4 is another implementation flow chart of step S3 in information query method provided in an embodiment of the present invention;
Fig. 5 is to load in information query method provided in an embodiment of the present invention to the multimedia file in query result
Implementation flow chart;
Fig. 6 is the schematic diagram of information query device provided in an embodiment of the present invention;
Fig. 7 is the schematic 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.
Referring to Fig. 1, Fig. 1 shows the application environment of information query method provided in an embodiment of the present invention.Information inquiry
Method is applied in the inquiry scene for multimedia file.The inquiry scene includes server-side and client, wherein server-side and
It is attached between client by network, user is stored multimedia file to server-side by client, and as needed
It is inquired by multimedia file of the client to server-side, server-side after carrying out respective handling to multimedia file by depositing
Enter in multimedia file library, when receiving client query request, corresponding multimedia text is obtained from multimedia file library
Part, client specifically can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable
Formula wearable device, server-side can specifically be realized with the server cluster that independent server or multiple servers form.
Referring to Fig. 2, being applied in this way Fig. 2 shows a kind of information query method provided in an embodiment of the present invention in Fig. 1
In server-side for be illustrated, details are as follows:
S1:Obtain multimedia file.
Specifically, it when receiving the multimedia file transmission request that user is sent by client, receives in the request
The multimedia file for including.
Wherein, multimedia file refers to that the various coded datas of media are all to store shape in the form of a file in a computer
At file, be the set of binary data.The name of file follows specific rule, generally by important name and extension name two parts
Composition, separates between important name and extension name with " ", extension name for indicating the Format Type of file, multimedia file include but
It is not limited to:Audio file, video file, picture file or document files etc..
Wherein, the multimedia file transmission between client and server-side passes through File Transfer Protocol (File Transfer
Protocol, FTP) carry out file transmission.
It should be noted that server-side after the multimedia file for receiving client transmission, can generate one uniquely
File identification identifies the multimedia file.
S2:Using preset regular expression, canonical matching is carried out to the file extension of multimedia file, determines that this is more
The file type of media file.
Specifically, server-side obtains the filename of the multimedia file after receiving multimedia file, by step S1
The description of multimedia file is logical to using preset canonical table it is found that the filename of multimedia file includes important name and extension name
Up to formula, canonical matching is carried out to the extension name of multimedia file, obtains the multimedia file type.
Wherein, file type refers to the specific coding mode to information that computer uses to store information, is to be used for
Identify the data of internal reservoir.Than if any storage picture, some storage programs, some storage text informations.Each category information,
Can one or more file formats be stored in computer storage in.The tray that extension name can help application program to identify
Formula.
Wherein, the model of preset regular expression is:" ^ S+ extension name ", extension name can be view with file type
The extension name of frequency, including be not limited to:AVI,MPEG/1/2/4,RM,RMVB,WMV,VCD/SVCD,DAT,VOB,MOV,MP4,
MKV, ASF and FLV etc. are also possible to the extension name that file type is audio, including but not limited to:WAVE/WAV,AIFF,AU,
MP3, MIDI, WMA, RealAudio, VQF, OggVorbis, AAC and APE etc. are also possible to the extension that file type is picture
Name, including but not limited to:BMP,JPG,PNG,TIFF,GIF,PCX,TGA,EXIF,FPX,SVG,PSD,CDR,PCD,DXF,
UFO, EPS, AI, RAW, WMF and WEBP etc. are also possible to the extension name that file type is document, including but not limited to:WORD,
PDF, TXT and INI etc..
For example, in a specific embodiment, server-side receives a multimedia file, the multimedia file is got
File it is entitled " the 8th session recording .WMA ", by using preset regular expression carry out canonical matching, get this
The extension of the filename of multimedia file is entitled " WMA ", and file format is audio.
S3:According to the corresponding default analysis mode of file type, multimedia file is parsed, obtains multimedia text
The content text information of part and the corresponding timestamp information of each content text information.
Specifically, according to the file type of the multimedia file got in step S2, it is corresponding to choose this document type
Default analysis mode, parses the multimedia file, and according to actual needs, by one or more numbers in parsing result
According in the text being recorded alone, using the text as the content text information of multimedia file, and for for each content text
This information generates the corresponding timestamp information of the data.
For example, in a specific embodiment, the file identification of the multimedia file got is 20180504, according to just
Then matching knows that file type is that audio parses the multimedia file, obtain three according to the default analysis mode of audio
A content text information is respectively:" present ", " I announces ", " meeting formally starts ", according to these three content text information pair
Time frame information of the audio data answered in the multimedia file obtains the corresponding timestamp letter of these three content text information
Breath is respectively:"00:00","00:02 " and " 00:06".
S4:The mapping relations between file identification, content text information and the timestamp information of multimedia file are established, and
It records, protects using file identification, content text information, timestamp information and mapping relations as the file transcription of the multimedia file
It is stored in Multimedia Knowledge library.
Specifically, it after generating content text information and timestamp information, establishes the file identification of multimedia file, be somebody's turn to do
Mapping relations between content text information and the timestamp information, and by file identification, content text information, timestamp information
File transcription with mapping relations as multimedia file records, and is saved in Multimedia Knowledge library, so as in subsequent query,
It can be recorded according to file transcription and find the corresponding file identification of content text information, to find corresponding multimedia file.
Wherein, Multimedia Knowledge library refers to the knowledge base for being stored with mass multimedia the file information.
For content text information and timestamp information obtained in the step S3, to file identification, content text information
Timestamp information corresponding with the content text information establishes mapping relations, obtains three file transcription records and is respectively
" 20180504, now, 00:00 ", " 20180504, I announces, 00:02 " and " 20180504, meeting formally starts, 00:06 ",
And these three file transcriptions record is respectively stored into Multimedia Knowledge library.
S5:If receiving the inquiry request comprising key word of the inquiry of user's transmission, it is based on Multimedia Knowledge library, by this
Key word of the inquiry is matched with content text information, and regard the file transcription of successful match record as query result.
Specifically, when receiving the inquiry request comprising key word of the inquiry that user is sent by client, based on more
Media knowledge base searches whether that there are corresponding content text information to include the key word of the inquiry in file transcription record, if
In the presence of the file transcription of successful match being then denoted as file destination transcription record, and as query result.
It should be understood that obtained query result can be one, or multiple.
For example, in a specific embodiment, key word of the inquiry is " attending a banquet ", in the content text letter of file transcription record
In breath, inquiring two content text information includes key word of the inquiry " attending a banquet ", this two content text information are that " that attends a banquet is outer
Exhale monitoring " and " promotion, which is attended a banquet, links up skilful service degree ", corresponding file transcription is recorded as:" 20180505, the outgoing call prison attended a banquet
Control, 12:26 " and " 20180503, promotion attends a banquet and links up skilful service degree, 46:11 ", both of these documents transcription is denoted as mesh
File transcription record is marked, and as query result.
S6:Export query result.
Specifically, it sends client for query result obtained in step S5 to show, for user's access.
In the present embodiment, the file extent by using preset regular expression, to the multimedia file got
Name carries out canonical matching, determines the file type of the multimedia file, and according to the corresponding default analysis mode of this document type,
Multimedia file is parsed, content text information and each content text information for obtaining the multimedia file are corresponding
Timestamp information, and then establish the mapping relations between multimedia file identification, content text information and timestamp information, and
It is deposited into Multimedia Knowledge library as file transcription record, the multimedia file of different file types can be adopted by realizing
After being parsed with corresponding analysis mode, content text information and timestamp information, and the side recorded with file transcription are formed
Formula is stored in Multimedia Knowledge library, when receiving the inquiry request of user, directly by keyword in inquiry request with
Content text information in Multimedia Knowledge library is matched, can multimedia file required for quick search to user, and
Specific location of the keyword in multimedia file can be timely and accurately obtained according to timestamp information, to improve multimedia
The search efficiency of file.
In one embodiment, the file type of multimedia file is audio, as shown in figure 3, in step S3, i.e., according to file
The corresponding default analysis mode of type, parses multimedia file, obtains the content text information of the multimedia file, with
And the corresponding timestamp information of each content text information, specifically comprise the following steps:
S311:Obtain the audio format of multimedia file.
Specifically, according to the matched mode of regular expressions in step S2, the audio format of the multimedia file, example are obtained
Such as, multimedia file " meeting prologue accompaniment .MP3 " is MP3 format by the audio format that regular expressions obtain.
S312:If audio format is non-default audio format, reference format conversion is carried out to multimedia file, is obtained
The target audio file of preset audio format.
Specifically, whether the audio format got in detecting step S311 is identical as preset audio format, if obtaining
The audio format arrived is non-default audio format, then formats the multimedia file, be converted to preset audio
The multimedia file of format.
Preferably, the preset audio format of the embodiment of the present invention is WMA (Windows Media Audio, Microsoft's audio lattice
Formula), WMA has been above MP3 (MPEG Audio Layer3) in terms of compression ratio and sound quality, even more outclass RA (Real
Audio, instant Public Address System), preferable sound quality can be generated under lower sample frequency, be conducive to improve it is subsequent into
The accuracy rate of row speech recognition.
S313:Speech enhan-cement and noise reduction process are carried out to target audio file, obtain the frame set comprising basic speech frame.
Specifically, speech enhan-cement and noise reduction process are carried out to target audio file and further increases language to reduce interference
The quality of sound, and by way of mute detection come to voice signal carry out framing, by the voice signal in target audio file
It is divided into the frame set comprising several basic speech frames.
Wherein, to speech enhan-cement and noise reduction process in the present embodiment, using spectrum-subtraction, that is, target audio file is being extracted
After voice signal, with the frequency spectrum of the spectral subtraction de-noised signal of signals with noise in the voice signal.Spectrum-subtraction is based on one simply
Hypothesis:Assuming that the noise in voice only has additive noise, as long as noisy speech spectrum is subtracted noise spectrum, so that it may obtain pure
Voice signal.
After obtaining pure voice signal, by way of mute detection, mute section is found out, and according to mute section, it is right
Clean speech signal carries out cutting, which is cut into the frame set comprising several basic speech frames.
Wherein, the mode of mute detection includes but is not limited to:Speech terminals detection, detection audio muting algorithm and voice are living
Dynamic detection (Voice Activity Detection, VAD) algorithm etc..
Preferably, the embodiment of the present invention carries out mute detection to obtained clean speech signal using voice activity detection.
S314:Speech recognition is carried out to each basic speech frame in frame set, generates content text information.
Specifically, speech recognition is carried out for each basic speech frame, obtains the corresponding content text of basic speech frame
Information.
Wherein, speech recognition is carried out to basic speech frame, speech recognition algorithm can be used, also can be used and know with voice
Third party's tool of other function, specifically with no restriction.Speech recognition algorithm includes but is not limited to:Voice based on channel model is known
Other algorithm, sound template match cognization algorithm and/or speech recognition algorithm of artificial neural network etc..
Preferably, speech recognition algorithm used in the embodiment of the present invention is the speech recognition algorithm based on channel model.
For example, in a specific embodiment, target audio file is " about reinforcing outgoing call monitoring minutes of attending a banquet
.WAV " after the enhancing of step S313 and noise reduction, the frame set comprising 120 basic speech frames is obtained, to each basis
Speech frame carries out speech recognition, obtains 120 content text information.
S315:For each content text information, it is right in frame set that the content text information is generated according to predetermined manner
The timestamp information answered, as the corresponding timestamp information of content text information.
Specifically, the content text information corresponding timestamp information in frame set is generated according to predetermined manner, as
The corresponding timestamp information of content text information refers to after carrying out speech recognition to basic speech frame, obtains the basis language
Sound frame corresponding timestamp information in target voice file, and using the timestamp information as the content obtained after speech recognition
The corresponding timestamp information of text information.
In the present embodiment, by judging the audio format for getting multimedia file, and by non-default sound
The multimedia file of frequency format carries out reference format conversion, the target audio file of preset audio format is obtained, to target audio
File carries out speech enhan-cement and noise reduction process, obtains the frame set comprising basic speech frame, and then to each base in frame set
Plinth speech frame carries out speech recognition, generates content text information, and obtain the corresponding timestamp information of each content text information,
So that the multimedia file that file format is audio is resolved to the file of literal type, enable root when subsequent query
According to the content information quick search in multimedia file to the multimedia file, to be conducive to improve multimedia file inquiry
Efficiency.
In one embodiment, the file type of multimedia file is video, before step S311, the information query method
Further include:
The audio coding of multimedia file is extracted according to preset audio format, and using the audio coding as updated
Multimedia file.
Specifically, it is the multimedia file of video for file type, sound can also be passed through by third party's tool
Frequency extraction algorithm carries out audio coding extraction to multimedia file, and obtained audio coding is converted to preset audio lattice
Formula will convert into the audio coding of preset audio format as updated multimedia file.Wherein, preset in the present embodiment
Audio format is WAV, can also be configured, be not specifically limited according to actual needs herein.
Wherein, according to the difference of coding mode, audio coding is divided into three kinds:Waveform coding, parameter coding and hybrid coding.
In general, the speech quality of waveform coding is high, but code rate is also very high;The code rate of parameter coding is very low, generation
The sound quality for synthesizing voice is not high;Hybrid coding uses parametric coding technique and waveform encoding techniques, code rate and sound quality between
Between them.
Preferably, for the audio coding that the present embodiment uses for waveform coding, the coding mode voice quality is higher, is being conducive to
Improve the accuracy rate of the identification of the subsequent multimedia file to audio format.
Wherein, third party's tool includes but is not limited to:Format factory (Format Factory) and FFMPEG (Fast
Forward Moving Picture Experts Group) etc., audio extraction algorithm includes but is not limited to:Sound based on Hash
Frequency fingerprint extraction algorithm, audio sparse expression (Sparse Representation-based Classifier, SRC) algorithm and
Fast algorithm (Fast Fourier Transformation, FFT) of discrete fourier transform etc., third party's tool or audio mention
It takes algorithm that can be chosen according to the actual situation, is not specifically limited herein.
In the present embodiment, when the file format of multimedia file is video, the audio coding in video is extracted, and will
The audio coding saves as the multimedia file of preset audio format, as updated multimedia file, by file
Format is that the multimedia file of video extracts audio coding, so that it is converted to the multimedia file comprising audio-frequency information to handle,
Information wherein included is being obtained subsequently through speech recognition is carried out to audio, to realize that file type is more matchmakers of video
The information extraction of body file.
In one embodiment, the file type of multimedia file is picture, as shown in figure 4, in step S3, i.e., according to file
The corresponding default analysis mode of type, parses multimedia file, obtains the content text information of the multimedia file, with
And the corresponding timestamp information of each content text information, specifically comprise the following steps:
S331:Picture pretreatment is carried out to multimedia file, obtains Target Photo file.
Specifically, picture is pre-processed, main purpose is to eliminate information unrelated in picture, restores useful true letter
Breath enhances detectability for information about and simplifies data to the maximum extent, to improve feature extraction, picture segmentation, matching
With the reliability of identification.
In embodiments of the present invention, to picture pretreatment refer to picture carry out gray scale (Gray Processing) processing,
(Image Sharpening) processing and binaryzation (Image Binarization) processing etc. are sharpened, is pre-processed by picture,
Background or noise, prominent word segment are removed, and scaling pictures are the size for being suitble to processing.
Wherein, gray proces, which refer to the process of, transforms into gray scale picture for color image, in order to improve image quality,
It is more clear the display effect of picture.Gray proces include but is not limited to:Component method, maximum value process, mean value method and weighting
Method of average etc..
Wherein, Edge contrast refers to the profile of compensation picture, enhances the edge of picture and the part of Gray Level Jump, makes figure
Piece is apparent from, and is divided into spatial processing and frequency domain handles two classes, Edge contrast is to protrude the edge of atural object on picture, wheel
The feature of exterior feature or certain linear goal elements.
Wherein, binary conversion treatment is exactly to set the gray value of the pixel on picture to 0 or 255, that is, will be entire
Picture shows the process of apparent black and white effect, and the binaryzation of picture is greatly reduced data volume in picture, so as to highlight
The profile of target out.
S332:Usage scenario text detection algorithm obtains the character area in Target Photo file.
Specifically, due to the Text region in picture file be natural scene under Text region, thus to picture into
Row pretreatment, after obtaining Target Photo, it is thus necessary to determine that the character area in Target Photo, to carry out Text region.
The determination method of character area includes but is not limited to:Hough ballot (Hough Transform) algorithm is based on hidden horse
Character recognition algorithm, the Region Feature Extraction (Maximally of Er Kefu model (Hidden Markov Model, HMM)
Stable Extremal Regions, MSER) algorithm and scene text detect (Connectionist Text Proposal
Network) algorithm.
Preferably, the embodiment of the present invention determines the literal field in Target Photo file using scene text detection algorithm
Domain, implementation are:By using convolutional neural networks (Convolutional Neural Networks, CNN) model pair
Target Photo file is trained, and obtains the depth characteristic of picture;And then according to depth characteristic and line of text construction algorithm (Side
Refinement it) predicts character edge, and according to the rectangle frame of default size, character edge is in the character with a line and is put
Enter the same rectangle frame;Rectangle frame is conspired to create into sequence, and is input to Recognition with Recurrent Neural Network (Recurrent Neural
Networks, RNN) it is trained in model, training result is returned using full articulamentum finally, obtains correct character side
Edge, and correct character edge is connected into line, to obtain the character area in Target Photo file.
S333:By the way of optical character identification, the word content of character area is extracted, as content text information.
Specifically, in the character area got in step S332, using optical character identification (Optical
Character Recognition, OCR) mode, Text region is carried out to the picture in the character area, and extracts knowledge
The text information being clipped to, as content text information.
Wherein, optical character identification refers to the character checked on picture by optical character recognition, dark by detection,
Bright mode determines its shape, then shape is translated into the process of computword with character identifying method;That is, being directed to picture
On character, using optical mode by the text conversion in picture become black and white lattice picture file, and by identify it is soft
Part by the text conversion in picture at text formatting, the technology further edited and processed for word processor.
S334:Set empty for the corresponding timestamp information of content text information.
Specifically, since the picture file that is mentioned in the embodiment of the present invention is static picture file, subsequent user into
When row multimedia file is inquired, the timestamp information for obtaining picture file is not needed, therefore, when content text information is corresponding
Between stamp be set as empty.
In the present embodiment, by carrying out picture pretreatment to multimedia file, Target Photo file is obtained, and use field
Scape text detection algorithm obtains the character area in Target Photo file, and then by the way of optical character identification, identifies
The word content of character area, as content text information, so that the text information for including on picture is extracted, subsequent
User when being inquired according to key word of the inquiry, can quickly and easily inquire include the key word of the inquiry picture, improve
Search efficiency.
In one embodiment, server-side is instructed according to the load that receives, to the corresponding multimedia file of query result into
Row load, as shown in figure 5, information inquiry further includes following steps after step S6:
S71:If receiving user to instruct the load of query result, determine that file to be loaded turns according to load instruction
Write record.
Specifically, obtaining the corresponding file of the query result when receiving load instruction of the user to query result and turning
Write record records this document transcription record as file transcription to be loaded.
It is worth noting that user can be by clicking or pressing on the side of keyboard shortcut in client using mouse
Formula sends load instruction to server-side.
With two query results obtained in step S5 " 20180505, the outgoing call monitoring attended a banquet, 12:26 " and
" 20180503, promotion, which is attended a banquet, links up skilful service degree, and 46:For 11 ", when user clicks query result using mouse
" 20180505, the outgoing call monitoring attended a banquet, 12:After 26 ", that is, complete the load instruction that the query result is sent to server-side, service
End obtains the file transcription record for including in load instruction, and this document transcription record is remembered as file transcription to be loaded
Record.
S72:According to the file identification in file transcription record to be loaded, obtains this document and identify the corresponding more matchmakers of target
Body file.
Specifically, file transcription record in include file identification, content text information, timestamp information and mapping relations,
According to the file identification in file transcription record to be loaded, it can determine that this document identifies corresponding multimedia file, in turn
The multimedia file is obtained as destination multimedia file.
For the file transcription to be loaded record obtained in the step S71, wrapped in file transcription record to be loaded
The file identification contained is " 20180505 ", and then the corresponding target of file identification " 20180505 " is found in Multimedia Knowledge library
Multimedia file " about the outgoing call monitoring minutes .WAV that attends a banquet is reinforced ".
S73:If the file type of destination multimedia file is picture, the destination multimedia file is shown.
Specifically, after getting destination multimedia file, the matched mode of the canonical provided using step S2 determines mesh
The file type for marking multimedia file directly transmits the picture file when the file type of destination multimedia file is picture
It is shown to client, to go to consult for user.
S74:If the file type of destination multimedia file is audio or video, file transcription record to be loaded is obtained
In the timestamp information object time point that includes, and drive the destination multimedia file from object time point execute.
Specifically, after getting destination multimedia file, the matched mode of the canonical provided using step S2 determines mesh
The file type for marking multimedia file obtains to be loaded when the file type of destination multimedia file is video or audio
The object time point that information stamp information includes in file transcription record, drives the destination multimedia file since object time point
It plays.
Got with step S72 file transcription record to be loaded " 20180505, the outgoing call monitoring attended a banquet, 12:26"
For destination multimedia file " about the outgoing call monitoring minutes .WAV that attends a banquet is reinforced ", the file transcription record to be loaded
Middle timestamp information is " 12:26 ", the object time point for including is the 26th second the 12nd minute, and driving destination multimedia file " closes
In reinforce attend a banquet outgoing call monitoring minutes .WAV " played since the 26th second the 12nd minute.
In the present embodiment, to be added according to load instruction determination when receiving load instruction of the user to query result
The file transcription of load records, and according to the file identification in the file transcription record to be loaded, obtains the corresponding more matchmakers of target
Body file, and file type confirmation is carried out to the destination multimedia file, if file type is picture, it is loaded directly into the target
Multimedia file obtains the timestamp information packet in file transcription record to be loaded if file type is audio or video
The object time point contained, driver application open destination multimedia file from the time point, so that receiving user again to looking into
When asking the load instruction of result, corresponding destination multimedia file can be quickly opened, and to audio or video file, it can be with
The keyword corresponding time point for being directly targeted to user query starts to play, and goes to consult for user, improves multimedia file
The efficiency of inquiry.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of information query device is provided, which looks into information in above-described embodiment
Inquiry method corresponds.As shown in fig. 6, the information query device includes data acquisition module 10, determination type module 20, file
Parsing module 30, record preserving module 40, matching inquiry module 50 and result output module 60.Each functional module is described in detail such as
Under:
Data acquisition module 10, for obtaining multimedia file;
Type determines model 20, for using preset regular expression, carries out to the file extension of multimedia file
Canonical matching, determines the file type of the multimedia file;
Document analysis module 30, for being solved to multimedia file according to the corresponding default analysis mode of file type
Analysis, obtains the content text information and the corresponding timestamp information of each content text information of the multimedia file;
Preserving module 40 is recorded, for establishing file identification, content text information and the timestamp information of multimedia file
Between mapping relations, and using file identification, content text information, timestamp information and mapping relations as the multimedia file
File transcription record, be saved in Multimedia Knowledge library;
Matching inquiry module 50, if the inquiry request comprising key word of the inquiry for receiving user's transmission, is based on
Multimedia Knowledge library matches the key word of the inquiry with content text information, and the file transcription of successful match is recorded
As query result;
As a result output module 60, for exporting query result.
Further, file type is audio, and document analysis module 30 includes:
Format acquisition unit 311, for obtaining the audio format of multimedia file;
Format conversion unit 312 marks multimedia file if being non-default audio format for audio format
Quasiconfiguaration conversion, obtains the target audio file of preset audio format;
Data processing unit 313 is obtained for carrying out speech enhan-cement and noise reduction process to target audio file comprising basis
The frame set of speech frame;
Voice recognition unit 314 generates content text for carrying out speech recognition to each basic speech frame in frame set
This information;
Time identifier unit 315 generates content text letter according to predetermined manner for being directed to each content text information
Breath corresponding timestamp information in frame set, as the corresponding timestamp information of content text information.
Further, file type is video, and document analysis module 30 further includes:
Audio extraction unit 321, for extracting the audio coding of multimedia file according to preset audio format, and should
Audio coding is as updated multimedia file.
Further, file type is picture, and document analysis module 30 further includes:
Picture processing unit 331 obtains Target Photo file for carrying out picture pretreatment to multimedia file;
Area determination unit 332 is used for usage scenario text detection algorithm, obtains the literal field in Target Photo file
Domain;
Word Input unit 333 is made for by the way of optical character identification, extracting the word content of character area
For content text information;
Time setting unit 334, for setting empty for the corresponding timestamp information of content text information.
Further, which further includes:
Determining module 71 is recorded, it is true according to load instruction if being instructed for receiving user to the load of query result
Fixed file transcription record to be loaded;
File acquisition module 72, for obtaining this document mark according to the file identification in file transcription record to be loaded
Know corresponding destination multimedia file;
Picture display module 73 shows the more matchmakers of the target if the file type for destination multimedia file is picture
Body file;
File playing module 74 obtains to be added if the file type for destination multimedia file is audio or video
The timestamp information object time point that includes in the file transcription record of load, and when driving the destination multimedia file from target
Between start to execute at point.
Specific about information query device limits the restriction that may refer to above for information query method, herein not
It repeats again.Modules in above- mentioned information inquiry unit can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store file identification pair in the Multimedia Knowledge library and Multimedia Knowledge library in information query method
The multimedia file answered.The network interface of the computer equipment is used to communicate with external terminal by network connection.The calculating
To realize a kind of information query method when machine program is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize above-described embodiment information issuer when executing computer program
The step of method, such as step S1 shown in Fig. 2 to step S6.Alternatively, processor realizes above-mentioned implementation when executing computer program
The function of each module/unit of example information query device, such as module shown in fig. 6 10 is to module 60.To avoid repeating, here
It repeats no more.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of above-described embodiment information query method when being executed by processor, alternatively, computer program is by processor
The function of each module/unit of above-described embodiment information query device is realized when execution, to avoid repeating, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided by the present invention,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that:It still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of information query method, which is characterized in that the information query method includes:
Obtain multimedia file;
Using preset regular expression, canonical matching is carried out to the file extension of the multimedia file, is determined described more
The file type of media file;
According to the corresponding default analysis mode of the file type, the multimedia file is parsed, obtains more matchmakers
The content text information of body file and the corresponding timestamp information of each content text information;
The mapping established between file identification, the content text information and the timestamp information of the multimedia file is closed
System, and using the file identification, the content text information, the timestamp information and the mapping relations as described in
The file transcription of multimedia file records, and is saved in Multimedia Knowledge library;
If receiving the inquiry request comprising key word of the inquiry of user's transmission, it is based on the Multimedia Knowledge library, it will be described
Key word of the inquiry is matched with the content text information, and regard the file transcription of successful match record as query result;
Export the query result.
2. information query method as described in claim 1, which is characterized in that the file type is audio, described according to institute
The corresponding default analysis mode of file type is stated, the multimedia file is parsed, the interior of the multimedia file is obtained
Hold text information and the corresponding timestamp information of each content text information includes:
Obtain the audio format of the multimedia file;
If the audio format is non-default audio format, reference format conversion is carried out to the multimedia file, is obtained
The target audio file of the preset audio format;
Speech enhan-cement and noise reduction process are carried out to the target audio file, obtain the frame set comprising basic speech frame;
Speech recognition is carried out to each of the frame set basic speech frame, generates the content text information;
For each content text information, it is corresponding in the frame set that the content text information is generated according to predetermined manner
Timestamp information, as the corresponding timestamp information of content text information.
3. information query method as claimed in claim 2, which is characterized in that the file type is video, in the acquisition
Before the audio format of the multimedia file, the information query method further includes:
Extract the audio coding of the multimedia file according to preset audio format, and using the audio coding as updating after
The multimedia file.
4. information query method as described in claim 1, which is characterized in that the file type is picture, described according to institute
The corresponding default analysis mode of file type is stated, the multimedia file is parsed, the interior of the multimedia file is obtained
Hold text information and the corresponding timestamp information of the content text information further includes:
Picture pretreatment is carried out to the multimedia file, obtains Target Photo file;
Usage scenario text detection algorithm obtains the character area in the Target Photo file;
By the way of optical character identification, the word content of the character area is extracted, as the content text information;
Set empty for the corresponding timestamp information of the content text information.
5. such as the described in any item information query methods of Claims 1-4, which is characterized in that in the output inquiry knot
After fruit, the information query method further includes:
If receiving the user to instruct the load of the query result, text to be loaded is determined according to the load instruction
Part transcription record;
According to the file identification in the file transcription record to be loaded, obtains this document and identify corresponding destination multimedia text
Part;
If the file type of the destination multimedia file is picture, the destination multimedia file is shown;
If the file type of the destination multimedia file is audio or video, the file transcription record to be loaded is obtained
In the timestamp information object time point that includes, and drive the destination multimedia file since at the object time point
It executes.
6. a kind of information query device, which is characterized in that the information query device includes:
Data acquisition module, for obtaining multimedia file;
Type determines model, for using preset regular expression, carries out just to the file extension of the multimedia file
It then matches, determines the file type of the multimedia file;
Document analysis module, for being carried out to the multimedia file according to the corresponding default analysis mode of the file type
Parsing obtains the content text information and the corresponding timestamp letter of each content text information of the multimedia file
Breath;
Preserving module is recorded, for establishing file identification, the content text information and the time of the multimedia file
The mapping relations between information are stabbed, and by the file identification, the content text information, the timestamp information, Yi Jisuo
The file transcription that mapping relations are stated as the multimedia file records, and is saved in Multimedia Knowledge library;
Matching inquiry module, if the inquiry request comprising key word of the inquiry for receiving user's transmission, based on described more
Media knowledge base matches the key word of the inquiry with the content text information, and by the file transcription of successful match
Record is used as query result;
As a result output module, for exporting the query result.
7. information query device as claimed in claim 6, which is characterized in that the file type is audio, the file solution
Analysing module includes:
Format acquisition unit, for obtaining the audio format of the multimedia file;
Format conversion unit carries out the multimedia file if being non-default audio format for the audio format
Reference format conversion, obtains the target audio file of the preset audio format;
Data processing unit is obtained for carrying out speech enhan-cement and noise reduction process to the target audio file comprising basic language
The frame set of sound frame;
Voice recognition unit, for carrying out speech recognition to each of the frame set basic speech frame, described in generation
Content text information;
Time identifier unit generates the content text information according to predetermined manner for being directed to each content text information
The corresponding timestamp information in the frame set, as the corresponding timestamp information of content text information.
8. information query device as claimed in claim 6, which is characterized in that the file type is picture, the file solution
Analysing module includes:
Picture processing unit obtains Target Photo file for carrying out picture pretreatment to the multimedia file;
Area determination unit is used for usage scenario text detection algorithm, obtains the character area in the Target Photo file;
Word Input unit, for by the way of optical character identification, extracting the word content of the character area, as institute
State content text information;
Time setting unit, for setting empty for the corresponding timestamp information of the content text information.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 5 information query method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization information query method as described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810529526.7A CN108829765A (en) | 2018-05-29 | 2018-05-29 | A kind of information query method, device, computer equipment and storage medium |
PCT/CN2018/094373 WO2019227582A1 (en) | 2018-05-29 | 2018-07-03 | Information query method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810529526.7A CN108829765A (en) | 2018-05-29 | 2018-05-29 | A kind of information query method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108829765A true CN108829765A (en) | 2018-11-16 |
Family
ID=64146081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810529526.7A Pending CN108829765A (en) | 2018-05-29 | 2018-05-29 | A kind of information query method, device, computer equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108829765A (en) |
WO (1) | WO2019227582A1 (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN109657181A (en) * | 2018-12-13 | 2019-04-19 | 平安科技(深圳)有限公司 | Internet information chain type storage method, device, computer equipment and storage medium |
CN109885491A (en) * | 2019-02-12 | 2019-06-14 | 科华恒盛股份有限公司 | To there are the detection methods and terminal device that data overflow expression formula |
CN109933973A (en) * | 2019-01-24 | 2019-06-25 | 平安科技(深圳)有限公司 | Cryptographic check method, apparatus, computer equipment and storage medium |
CN109976669A (en) * | 2019-03-15 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of edge storage method, device and storage medium |
CN110110099A (en) * | 2019-04-12 | 2019-08-09 | 华勤通讯技术有限公司 | A kind of multimedia document retrieval method and device |
CN110390104A (en) * | 2019-07-23 | 2019-10-29 | 苏州思必驰信息科技有限公司 | Irregular text transcription method and system for voice dialogue platform |
CN110399339A (en) * | 2019-06-18 | 2019-11-01 | 平安科技(深圳)有限公司 | File classifying method, device, equipment and the storage medium of knowledge base management system |
CN111049887A (en) * | 2019-11-29 | 2020-04-21 | 天脉聚源(杭州)传媒科技有限公司 | Download control method, system and storage medium based on dynamic search strategy |
CN111314297A (en) * | 2020-01-16 | 2020-06-19 | 深圳软牛科技有限公司 | Musiccdb media data extraction method, device and computer readable storage medium |
CN111353065A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Voice archive storage method, device, equipment and computer readable storage medium |
CN111506747A (en) * | 2020-04-16 | 2020-08-07 | Oppo(重庆)智能科技有限公司 | File analysis method and device, electronic equipment and storage medium |
CN111863043A (en) * | 2020-07-29 | 2020-10-30 | 安徽听见科技有限公司 | Audio transfer file generation method, related equipment and readable storage medium |
CN112071305A (en) * | 2020-11-16 | 2020-12-11 | 成都启英泰伦科技有限公司 | Local off-line intelligent voice batch recognition module and method |
CN112115282A (en) * | 2020-09-17 | 2020-12-22 | 北京达佳互联信息技术有限公司 | Question answering method, device, equipment and storage medium based on search |
CN112163104A (en) * | 2020-09-29 | 2021-01-01 | 北京字跳网络技术有限公司 | Method, device, electronic equipment and storage medium for searching target content |
CN112347061A (en) * | 2020-11-27 | 2021-02-09 | 中国农业银行股份有限公司 | File uploading method and device |
CN112417113A (en) * | 2020-11-10 | 2021-02-26 | 绿瘦健康产业集团有限公司 | Intelligent question-answering method and system based on voice recognition technology |
CN112559444A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | SQL (structured query language) file migration method and device, storage medium and equipment |
CN112836693A (en) * | 2021-02-04 | 2021-05-25 | 北京秒针人工智能科技有限公司 | Optical character recognition repeated detection method and system |
CN112883235A (en) * | 2021-03-11 | 2021-06-01 | 深圳市一览网络股份有限公司 | Video content searching method and device, computer equipment and storage medium |
CN115883648A (en) * | 2021-08-09 | 2023-03-31 | 中移物联网有限公司 | Data integration method, device, equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996195A (en) * | 2009-08-28 | 2011-03-30 | 中国移动通信集团公司 | Searching method and device of voice information in audio files and equipment |
CN102880713A (en) * | 2012-09-29 | 2013-01-16 | 北京奇虎科技有限公司 | File deleting method and file deleting device |
CN103399865A (en) * | 2013-07-05 | 2013-11-20 | 华为技术有限公司 | Method and device for multi-media file generation |
CN105005578A (en) * | 2015-05-21 | 2015-10-28 | 中国电子科技集团公司第十研究所 | Multimedia target information visual analysis system |
CN106021368A (en) * | 2016-05-10 | 2016-10-12 | 东软集团股份有限公司 | Method and device for playing multimedia file |
CN106446051A (en) * | 2016-08-31 | 2017-02-22 | 北京新奥特云视科技有限公司 | Deep search method of Eagle media assets |
CN106982286A (en) * | 2017-04-26 | 2017-07-25 | 努比亚技术有限公司 | A kind of way of recording, equipment and computer-readable recording medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103793515A (en) * | 2014-02-11 | 2014-05-14 | 安徽科大讯飞信息科技股份有限公司 | Service voice intelligent search and analysis system and method |
CN105095211B (en) * | 2014-04-22 | 2019-03-26 | 北大方正集团有限公司 | The acquisition methods and device of multi-medium data |
US20170228399A1 (en) * | 2016-02-05 | 2017-08-10 | National Taipei University Of Technology | Method of searching for multimedia image |
-
2018
- 2018-05-29 CN CN201810529526.7A patent/CN108829765A/en active Pending
- 2018-07-03 WO PCT/CN2018/094373 patent/WO2019227582A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996195A (en) * | 2009-08-28 | 2011-03-30 | 中国移动通信集团公司 | Searching method and device of voice information in audio files and equipment |
CN102880713A (en) * | 2012-09-29 | 2013-01-16 | 北京奇虎科技有限公司 | File deleting method and file deleting device |
CN103399865A (en) * | 2013-07-05 | 2013-11-20 | 华为技术有限公司 | Method and device for multi-media file generation |
CN105005578A (en) * | 2015-05-21 | 2015-10-28 | 中国电子科技集团公司第十研究所 | Multimedia target information visual analysis system |
CN106021368A (en) * | 2016-05-10 | 2016-10-12 | 东软集团股份有限公司 | Method and device for playing multimedia file |
CN106446051A (en) * | 2016-08-31 | 2017-02-22 | 北京新奥特云视科技有限公司 | Deep search method of Eagle media assets |
CN106982286A (en) * | 2017-04-26 | 2017-07-25 | 努比亚技术有限公司 | A kind of way of recording, equipment and computer-readable recording medium |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN109657181A (en) * | 2018-12-13 | 2019-04-19 | 平安科技(深圳)有限公司 | Internet information chain type storage method, device, computer equipment and storage medium |
CN109657181B (en) * | 2018-12-13 | 2024-05-14 | 平安科技(深圳)有限公司 | Internet information chain storage method, device, computer equipment and storage medium |
CN111353065A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Voice archive storage method, device, equipment and computer readable storage medium |
CN109933973A (en) * | 2019-01-24 | 2019-06-25 | 平安科技(深圳)有限公司 | Cryptographic check method, apparatus, computer equipment and storage medium |
CN109933973B (en) * | 2019-01-24 | 2024-01-19 | 平安科技(深圳)有限公司 | Password verification method, password verification device, computer equipment and storage medium |
CN109885491A (en) * | 2019-02-12 | 2019-06-14 | 科华恒盛股份有限公司 | To there are the detection methods and terminal device that data overflow expression formula |
CN109885491B (en) * | 2019-02-12 | 2022-07-05 | 科华恒盛股份有限公司 | Method for detecting existence of data overflow expression and terminal equipment |
CN109976669B (en) * | 2019-03-15 | 2023-07-28 | 百度在线网络技术(北京)有限公司 | Edge storage method, device and storage medium |
CN109976669A (en) * | 2019-03-15 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of edge storage method, device and storage medium |
CN110110099A (en) * | 2019-04-12 | 2019-08-09 | 华勤通讯技术有限公司 | A kind of multimedia document retrieval method and device |
CN110399339A (en) * | 2019-06-18 | 2019-11-01 | 平安科技(深圳)有限公司 | File classifying method, device, equipment and the storage medium of knowledge base management system |
CN110390104A (en) * | 2019-07-23 | 2019-10-29 | 苏州思必驰信息科技有限公司 | Irregular text transcription method and system for voice dialogue platform |
CN110390104B (en) * | 2019-07-23 | 2023-05-05 | 思必驰科技股份有限公司 | Irregular text transcription method and system for voice dialogue platform |
CN112559444A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | SQL (structured query language) file migration method and device, storage medium and equipment |
CN111049887A (en) * | 2019-11-29 | 2020-04-21 | 天脉聚源(杭州)传媒科技有限公司 | Download control method, system and storage medium based on dynamic search strategy |
CN111314297A (en) * | 2020-01-16 | 2020-06-19 | 深圳软牛科技有限公司 | Musiccdb media data extraction method, device and computer readable storage medium |
CN111314297B (en) * | 2020-01-16 | 2022-03-25 | 深圳软牛科技有限公司 | Musiccdb media data extraction method, device and computer readable storage medium |
CN111506747A (en) * | 2020-04-16 | 2020-08-07 | Oppo(重庆)智能科技有限公司 | File analysis method and device, electronic equipment and storage medium |
CN111506747B (en) * | 2020-04-16 | 2023-09-08 | Oppo(重庆)智能科技有限公司 | File analysis method, device, electronic equipment and storage medium |
CN111863043B (en) * | 2020-07-29 | 2022-09-23 | 安徽听见科技有限公司 | Audio transfer file generation method, related equipment and readable storage medium |
CN111863043A (en) * | 2020-07-29 | 2020-10-30 | 安徽听见科技有限公司 | Audio transfer file generation method, related equipment and readable storage medium |
CN112115282A (en) * | 2020-09-17 | 2020-12-22 | 北京达佳互联信息技术有限公司 | Question answering method, device, equipment and storage medium based on search |
WO2022068496A1 (en) * | 2020-09-29 | 2022-04-07 | 北京字跳网络技术有限公司 | Target content search method and apparatus, electronic device and storage medium |
CN112163104A (en) * | 2020-09-29 | 2021-01-01 | 北京字跳网络技术有限公司 | Method, device, electronic equipment and storage medium for searching target content |
CN112417113A (en) * | 2020-11-10 | 2021-02-26 | 绿瘦健康产业集团有限公司 | Intelligent question-answering method and system based on voice recognition technology |
CN112071305A (en) * | 2020-11-16 | 2020-12-11 | 成都启英泰伦科技有限公司 | Local off-line intelligent voice batch recognition module and method |
CN112347061A (en) * | 2020-11-27 | 2021-02-09 | 中国农业银行股份有限公司 | File uploading method and device |
CN112836693A (en) * | 2021-02-04 | 2021-05-25 | 北京秒针人工智能科技有限公司 | Optical character recognition repeated detection method and system |
CN112836693B (en) * | 2021-02-04 | 2024-05-24 | 北京秒针人工智能科技有限公司 | Repeated detection method and system for optical character recognition |
CN112883235A (en) * | 2021-03-11 | 2021-06-01 | 深圳市一览网络股份有限公司 | Video content searching method and device, computer equipment and storage medium |
CN115883648A (en) * | 2021-08-09 | 2023-03-31 | 中移物联网有限公司 | Data integration method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2019227582A1 (en) | 2019-12-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108829765A (en) | A kind of information query method, device, computer equipment and storage medium | |
US10497378B2 (en) | Systems and methods for recognizing sound and music signals in high noise and distortion | |
US10977299B2 (en) | Systems and methods for consolidating recorded content | |
CN110335612A (en) | Minutes generation method, device and storage medium based on speech recognition | |
CN111182347B (en) | Video clip cutting method, device, computer equipment and storage medium | |
CN108986826A (en) | Automatically generate method, electronic device and the readable storage medium storing program for executing of minutes | |
CN112396182B (en) | Method for training face driving model and generating face mouth shape animation | |
KR100676863B1 (en) | System and method for providing music search service | |
US11238869B2 (en) | System and method for reconstructing metadata from audio outputs | |
CN111444382B (en) | Audio processing method and device, computer equipment and storage medium | |
CN110933225B (en) | Call information acquisition method and device, storage medium and electronic equipment | |
CN110750996B (en) | Method and device for generating multimedia information and readable storage medium | |
CN112053692B (en) | Speech recognition processing method, device and storage medium | |
WO2019114015A1 (en) | Robot performance control method and robot | |
CN110503960A (en) | Uploaded in real time method, apparatus, equipment and the storage medium of speech recognition result | |
KR20170086233A (en) | Method for incremental training of acoustic and language model using life speech and image logs | |
CN110970027B (en) | Voice recognition method, device, computer storage medium and system | |
US20200020335A1 (en) | Method for providing vui particular response and application thereof to intelligent sound box | |
CN113435902A (en) | Intelligent logistics customer service robot based on voice information analysis | |
WO2022041177A1 (en) | Communication message processing method, device, and instant messaging client | |
CN116994597B (en) | Audio processing system, method and storage medium | |
CN112820274B (en) | Voice information recognition correction method and system | |
CN113806586B (en) | Data processing method, computer device and readable storage medium | |
Huang et al. | VPCID—A VoIP phone call identification database | |
WO2023160515A1 (en) | Video processing method and apparatus, device and medium |
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 |