The prediction technique and device of multimedia fileTechnical field
The present invention relates to software application technology field more particularly to the prediction techniques and device of a kind of multimedia file.
Background technology
In recent years, deep learning is widely applied in fields such as video image, speech recognition, natural language processings.For example, for video image, content recognition is carried out using image recognition algorithm；For voice data, using speech recognitionAlgorithm carries out content recognition；For text data, is handled using natural-sounding and carry out content recognition.
And in practical applications, it is individually identified using a kind of algorithm, often can not accurately identify content.For example,For typical UGC platforms (User Generated Content, user's original content platform), a large number of users is had dailyVarious videos are uploaded, the video of these records user's life includes the contents such as self-timer, dancing, cuisines.When will from number withWhen filtering out the video of " cuisines study course " in the video of hundred million meters, if only with image classification algorithms, although can identify " beautifulFood " video, but None- identified goes out " study course " video；If using natural language processing algorithm, although can be isolated from text" study course " is to identify " study course " video, but " cuisines " in None- identified image；If this two algorithm simple associations are risenCome, although certain " cuisines study course " video can be filtered out, not all " cuisines study course " video all includes " study course "Printed words, the word that user describes video are likely to the food materials such as " green onion ", " ginger ", " garlic ".To only lean on simple algorithm fusion withoutMethod accurately identifies content.
Invention content
The prediction technique and device of multimedia file provided in an embodiment of the present invention can solve that speech recognition is individually used to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, the poor problem of accuracy.
On the one hand, the embodiment of the invention discloses a kind of prediction techniques of multimedia file, including：
Destination multimedia file set is calculated by speech recognition algorithm, image recognition algorithm and natural language processing respectivelyMethod, identification obtain the first tally set, the second tally set and third tally set；
It, will be in the destination multimedia file set according to first tally set, the second tally set and third tally setEach destination multimedia file is divided in each theme of preset themes collection, and counts each destination multimedia file in each themeIn distribution probability；
It is corresponded to according to target topic in distribution probability of each destination multimedia file in each theme and each themeCondition distribution probability, predict the score of each destination multimedia file；The condition distribution probability passes through to the more matchmakers of trainingBody file set is trained to obtain；
Each destination multimedia file is ranked up according to the score.
On the other hand, the embodiment of the invention also discloses a kind of prediction meanss of multimedia file, including：
Label acquisition module, for passing through speech recognition algorithm, image recognition algorithm respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；
Theme division module is used for according to first tally set, the second tally set and third tally set, by the targetEach destination multimedia file that multimedia file is concentrated is divided in each theme of preset themes collection, and it is more to count each targetDistribution probability of the media file in each theme；
Score prediction module is used for the distribution probability in each theme and each master according to each destination multimedia fileThe corresponding condition distribution probability of target topic in topic predicts the score of each destination multimedia file；The condition distribution is generalRate to training multimedia file collection by being trained to obtain；
Sorting module, for being ranked up to each destination multimedia file according to the score.
In embodiments of the present invention, speech recognition algorithm, image recognition algorithm are passed through respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；According to first labelCollection, the second tally set and third tally set, each destination multimedia file in the destination multimedia file set are divided to pre-If in each theme of theme collection, and counting distribution probability of each destination multimedia file in each theme；According to described eachThe corresponding condition distribution probability of target topic in distribution probability and each theme of the destination multimedia file in each theme, predictionThe score of each destination multimedia file；The condition distribution probability is by being trained training multimedia file collectionIt arrives；Each destination multimedia file is ranked up according to the score.So as to solve individually to use speech recognition to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, and the poor problem of accuracy achieves and improves more matchmakersThe advantageous effect of the accuracy of body file content identification.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,And can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage canIt is clearer and more comprehensible, below the special specific implementation mode for lifting the present invention.
Description of the drawings
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 inventionAttached 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 present inventionExample, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawingsObtain other attached drawings.
Fig. 1 shows a kind of step flow chart of the prediction technique of multimedia file in the embodiment of the present invention one；
Fig. 2 shows a kind of step flow charts of the prediction technique of multimedia file in the embodiment of the present invention two；
Fig. 3 shows a kind of structure diagram of the prediction meanss of multimedia file in the embodiment of the present invention three；
Fig. 4 shows a kind of structure diagram of the prediction meanss of multimedia file in the embodiment of the present invention four.
Specific implementation mode
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, completeSite preparation describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hairEmbodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative effortsExample, shall fall within the protection scope of the present invention.
Below by the prediction for enumerating several specific embodiments and being discussed in detail a kind of multimedia file provided by the inventionMethod and apparatus.
Embodiment one
Referring to Fig.1, it shows a kind of step flow chart of the prediction technique of multimedia file of the embodiment of the present invention one, hasBody may include steps of：
Step 101, speech recognition algorithm, image recognition algorithm and natural language are passed through respectively to destination multimedia file setProcessing Algorithm, identification obtain the first tally set, the second tally set and third tally set.
The embodiment of the present invention is classified for multimedia file.Wherein, multimedia file includes at least video, cardonDeng.
Speech recognition algorithm identifies content by the pretreatment, feature extraction, pattern match of voice signal.Pretreatment packetInclude the processes such as pre-filtering, sampling and quantization, adding window, end-point detection, preemphasis.
Image recognition algorithm is by image procossing, analysis and understanding, to identify picture material.Image recognition is mainly with imageMain feature based on.For example, there is a acute angle etc. at the center that letter A has a point, P to have a circle, Y.
Natural language processing algorithm is parsed by grammer, semanteme etc., identifies content.
The embodiment of the present invention can integrate three kinds of algorithms and destination multimedia file is identified, to more accurately rightDestination multimedia file is classified.
In practical applications, in order to distinguish the label of three kinds of algorithms generation, the label that each algorithm generates is arranged uniqueMark.Specifically, the tag identifier that speech recognition algorithm generates uses prefix A, the tag identifier that image recognition algorithm generates to adoptWith prefix I, the label that natural language processing algorithm generates uses prefix T.For example, for the label 1 of same multimedia file, it is rightThree kinds of algorithms are answered to generate the label for being identified as A-1, I-1, T-1 respectively.For destination multimedia file set, give birth to according to the method described aboveAt the first tally set be A-1, A-2, A-3 ..., A-M, the second tally set be I-1, I-2, I-3 ..., I-N, third tally setFor T-1, T-2, T-3 ..., T-L.
It is appreciated that a destination multimedia file can correspond to multiple labels according to a kind of algorithm.
Step 102, according to first tally set, the second tally set and third tally set, by destination multimedia textEach destination multimedia file that part is concentrated is divided in each theme of preset themes collection, and counts each destination multimedia fileDistribution probability in each theme.
Wherein, preset themes collection can be set according to current task, can be related to the theme of current task.For example, working asPreceding task is to identify " cuisines study course " to multimedia file, then needs setting and the relevant theme of cuisines study course.It is appreciated thatTheme number can be set according to practical application scene, and the embodiment of the present invention does not limit it.
Specifically, destination multimedia file is divided in each theme of preset themes concentration using LDA models.LDA(Latent Dirichlet Allocation, hiding Di Li Crays distribution) is that a kind of document subject matter generates model, also referred to as threeLayer bayesian probability model, including word, theme and document three-decker.It generates model and thinks that each word of an article is logicalIt crosses " with some theme of certain probability selection, and with some word of certain probability selection from this theme ".Wherein, document arrivesTheme obeys multinomial distribution, and theme to word obeys multinomial distribution.
LDA is a kind of non-supervisory machine learning techniques, can be used for identify in extensive document sets or corpus hideEvery document is considered as a word frequency vector by subject information using bag of words method, is easy to model to convert text message toDigital information.But bag of words method does not account for the sequence between word and word, to simplify complexity, while being mould yetThe improvement of type provides opportunity.The probability distribution that some themes of each documents representative are constituted, and each themeThe probability distribution that many words are constituted is represented again.
Step 103, target in the distribution probability according to each destination multimedia file in each theme and each themeThe corresponding condition distribution probability of theme predicts the score of each destination multimedia file；It is right that the condition distribution probability passes throughTraining multimedia file collection is trained to obtain.
Wherein, the corresponding condition distribution probability of target topic corresponds to the multimedia file being divided in the theme in each themeIn, belong to the probability of target topic.
The score of multimedia file represents the probability that multimedia file belongs to target topic.Score is higher, multimedia fileThe probability for belonging to target topic is bigger；Score is lower, and the probability that multimedia file belongs to target topic is smaller.
It is weighted it is appreciated that condition distribution probability is equivalent to how each theme.Condition distribution probability is bigger, shows thisThe weighted value of theme is bigger；Condition distribution probability is smaller, shows that the weighted value of the theme is smaller.It is bigger hence for conditional probabilityTheme, if the distribution probability that multimedia file is divided to the theme is bigger, the score of multimedia file is bigger；For conditionThe smaller theme of probability, if the distribution probability that multimedia file is divided to the theme is smaller, the score of multimedia file is smaller.
Step 104, each destination multimedia file is ranked up according to the score.
Specifically, destination multimedia file is subjected to descending arrangement according to sequence, the multimedia text to sort more forwardThe probability that part belongs to target topic is bigger；The probability that the multimedia file of sequence more rearward belongs to target topic is smaller.
In embodiments of the present invention, speech recognition algorithm, image recognition algorithm are passed through respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；According to first labelCollection, the second tally set and third tally set, each destination multimedia file in the destination multimedia file set are divided to pre-If in each theme of theme collection, and counting distribution probability of each destination multimedia file in each theme；According to described eachThe corresponding condition distribution probability of target topic in distribution probability and each theme of the destination multimedia file in each theme, predictionThe score of each destination multimedia file；The condition distribution probability is by being trained training multimedia file collectionIt arrives；Each destination multimedia file is ranked up according to the score.So as to solve individually to use speech recognition to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, and the poor problem of accuracy achieves and improves more matchmakersThe advantageous effect of the accuracy of body file content identification.
Embodiment two
With reference to Fig. 2, a kind of step flow chart of the prediction technique of multimedia file of the embodiment of the present invention two is shown, haveBody may include steps of：
Step 201, speech recognition algorithm, image recognition algorithm and natural language are passed through respectively to training multimedia file collectionProcessing Algorithm, identification obtain the first training tally set, the second training tally set and third training tally set.
Wherein, each multimedia file that training multimedia file is concentrated is marked.For example, current task is screening " cuisinesThe multimedia file of study course ", marks whether each trained multimedia file is " cuisines study course ".But it is drawn multimedia file will be trainedWhen point being concentrated to preset themes, the markup information is invisible, to not use markup information to be divided.
It is appreciated that since training multimedia file collection is different from the file content of destination multimedia file set, the first instructionPractice tag set, the second training tally set and third training tally set and the first tag set, the second tally set and third labelThe content of collection is also different.
In practical applications, in order to improve the accuracy of training result, the number of training multimedia file is The more the better.
Step 202, tally set, the second training tally set and third is trained to train tally set according to described first, it will be describedEach trained multimedia file that training multimedia file is concentrated is divided in each theme of preset themes collection.
The step is referred to the detailed description of step 102, and details are not described herein.
Step 203, according to the markup information of each trained multimedia file, the training multimedia text in each theme is countedPart belongs to the probability of target topic, obtains the corresponding condition distribution probability of target topic in each theme.
Wherein, it is different and different to correspond to current task for target topic.For example, current task is to determine regarding for " cuisines study course "Frequently, then target topic is cuisines study course.
It is appreciated that condition distribution probability corresponds to theme, show occur the probability of target topic in the theme.For example, rightIn a theme, the video probability for " cuisines study course " in the theme is determined.
Optionally, in another embodiment of the invention, step 203 includes sub-step 2031：
Sub-step 2031 counts according to the markup information of each trained multimedia file and belongs to target master in each themeThe number of the training multimedia file of topic, obtains the first numerical value.
In practical applications, since markup information indicates the theme of multimedia file, to the theme that will mark whether withTarget topic is consistent, judges whether multimedia file is target topic.If consistent, it is determined that multimedia file belongs to target masterTopic；If inconsistent, it is determined that multimedia file is not belonging to target topic.
Sub-step 2032 counts the total number of the training multimedia file in each theme, obtains second value.
Second value corresponds to the sum for the multimedia file for being divided to a theme.
Sub-step 2033 calculates the ratio of first numerical value and second value, obtains target topic in each theme and corresponds toCondition distribution probability.
In practical applications, several can suitably be retained after decimal point.Under normal conditions, retain 2 significant digits.
Step 204, speech recognition algorithm, image recognition algorithm and natural language are passed through respectively to destination multimedia file setProcessing Algorithm, identification obtain the first tally set, the second tally set and third tally set.
The step is referred to the detailed description of step 101, and details are not described herein.
Step 205, for each destination multimedia file in the destination multimedia file set, according to the more matchmakers of the targetIn the second label and third tally set of the body file in the first tally set in corresponding first label, the second tally setThree labels carry out comprehensive descision so that the destination multimedia file to be divided in each theme of preset themes concentration, and countDistribution probability of each destination multimedia file in each theme.
In practical applications, for a multimedia file, the first label, the second label, third are obtained according to three kinds of algorithmsMultimedia file is divided in preset themes by label to carry out comprehensive descision according to three kinds of labels.
Step 206, for each destination multimedia file, distribution of the destination multimedia file in each theme is generalRate condition distribution probability corresponding with target topic in each theme is multiplied respectively, obtains the destination multimedia file in each themeIn destination probability；The condition distribution probability to training multimedia file collection by being trained to obtain.
Wherein, condition distribution probability is the probability that step 201 is obtained to 203.
Specifically, destination probability of i-th of multimedia file in j-th of theme can be calculated by following formula：
Si,j=Di,j·Rj (1)
Wherein, Di,jFor distribution probability of i-th of multimedia file in j-th of theme, RjFor target in j-th of themeThe corresponding condition distribution probability of theme.
Step 207, the destination probability by the destination multimedia file in each theme is added, and obtains the more matchmakers of the targetThe score of body file.
Specifically, i-th of multimedia file belongs to the score of target topic and can be calculated according to following formula：
Wherein, τ is that preset themes concentrate the theme number for including, and can be set according to practical application scene.
Step 208, each destination multimedia file is ranked up according to the score.
The step is referred to the detailed description of step 104, and details are not described herein.
In embodiments of the present invention, speech recognition algorithm, image recognition algorithm are passed through respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；According to first labelCollection, the second tally set and third tally set, each destination multimedia file in the destination multimedia file set are divided to pre-If in each theme of theme collection, and counting distribution probability of each destination multimedia file in each theme；According to described eachThe corresponding condition distribution probability of target topic in distribution probability and each theme of the destination multimedia file in each theme, predictionThe score of each destination multimedia file；The condition distribution probability is by being trained training multimedia file collectionIt arrives；Each destination multimedia file is ranked up according to the score.So as to solve individually to use speech recognition to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, and the poor problem of accuracy achieves and improves more matchmakersThe advantageous effect of the accuracy of body file content identification.Further, it is also possible to determine target master in preset themes by training in advanceInscribe corresponding condition distribution probability, to improve multimedia file forecasting efficiency advantageous effect.
Embodiment three
With reference to Fig. 3, a kind of structure diagram of the prediction meanss of multimedia file of the embodiment of the present invention three is shown, specificallyIncluding following module：
Label acquisition module 301, for being calculated by speech recognition algorithm, image recognition respectively destination multimedia file setMethod and natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set.
Theme division module 302 is used for according to first tally set, the second tally set and third tally set, will be describedEach destination multimedia file in destination multimedia file set is divided in each theme of preset themes collection, and counts each meshMark distribution probability of the multimedia file in each theme.
Score prediction module 303, for according to distribution probability of each destination multimedia file in each theme andThe corresponding condition distribution probability of target topic in each theme predicts the score of each destination multimedia file；The condition pointCloth probability to training multimedia file collection by being trained to obtain.
Sorting module 304, for being ranked up to each destination multimedia file according to the score.
In embodiments of the present invention, speech recognition algorithm, image recognition algorithm are passed through respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；According to first labelCollection, the second tally set and third tally set, each destination multimedia file in the destination multimedia file set are divided to pre-If in each theme of theme collection, and counting distribution probability of each destination multimedia file in each theme；According to described eachThe corresponding condition distribution probability of target topic in distribution probability and each theme of the destination multimedia file in each theme, predictionThe score of each destination multimedia file；The condition distribution probability is by being trained training multimedia file collectionIt arrives；Each destination multimedia file is ranked up according to the score.So as to solve individually to use speech recognition to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, and the poor problem of accuracy achieves and improves more matchmakersThe advantageous effect of the accuracy of body file content identification.
Embodiment three is one corresponding device embodiment of embodiment of the method, and detailed description is referred to embodiment one, hereinIt repeats no more.
Example IV
With reference to Fig. 4, a kind of structure diagram of the prediction meanss of multimedia file of the embodiment of the present invention four is shown, specificallyIncluding following module：
Training label acquisition module 401, for being known respectively by speech recognition algorithm, image to training multimedia file collectionOther algorithm and natural language processing algorithm, identification obtain the first training tally set, the second training tally set and third training labelCollection.
Training theme division module 402, for training tally set, the second training tally set and third to instruct according to described firstPractice tally set, each trained multimedia file that the trained multimedia file is concentrated is divided to each theme of preset themes collectionIn.
Condition distribution probability statistical module 403, for the markup information according to each trained multimedia file, statistics is eachTraining multimedia file in theme belongs to the probability of target topic, and it is general to obtain the corresponding condition distribution of target topic in each themeRate.
Label acquisition module 404, for being calculated by speech recognition algorithm, image recognition respectively destination multimedia file setMethod and natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set.
Theme division module 405 is used for according to first tally set, the second tally set and third tally set, will be describedEach destination multimedia file in destination multimedia file set is divided in each theme of preset themes collection, and counts each meshMark distribution probability of the multimedia file in each theme.Optionally, in embodiments of the present invention, above-mentioned theme division module 405,Including:
Theme divides submodule 4051, is used for for each destination multimedia file in the destination multimedia file set,According to second label of the destination multimedia file in the first tally set in corresponding first label, the second tally set andThird label in third tally set carries out comprehensive descision so that the destination multimedia file is divided to preset themes concentrationIn each theme.
Score prediction module 406, for according to distribution probability of each destination multimedia file in each theme andThe corresponding condition distribution probability of target topic in each theme predicts the score of each destination multimedia file；The condition pointCloth probability to training multimedia file collection by being trained to obtain.Optionally, in embodiments of the present invention, above-mentioned score predictionModule 406, including：
Destination probability statistic submodule 4061 is used for for each destination multimedia file, by destination multimedia textDistribution probability of the part in each theme condition distribution probability corresponding with target topic in each theme is multiplied respectively, obtains the meshMark destination probability of the multimedia file in each theme.
Score predicts submodule 4062, for destination probability of the destination multimedia file in each theme to be added,Obtain the score of the destination multimedia file.
Sorting module 407, for being ranked up to each destination multimedia file according to the score.
Optionally, in another embodiment of the invention, above-mentioned condition distribution probability statistical module 403, including：
First numerical statistic submodule counts each theme for the markup information according to each trained multimedia fileIn belong to target topic training multimedia file number, obtain the first numerical value.
Second value statistic submodule, the total number for counting the training multimedia file in each theme, obtainsSecond value.
Condition distribution probability computational submodule, the ratio for calculating first numerical value and second value, obtains each masterThe corresponding condition distribution probability of target topic in topic.
In embodiments of the present invention, speech recognition algorithm, image recognition algorithm are passed through respectively to destination multimedia file setAnd natural language processing algorithm, identification obtain the first tally set, the second tally set and third tally set；According to first labelCollection, the second tally set and third tally set, each destination multimedia file in the destination multimedia file set are divided to pre-If in each theme of theme collection, and counting distribution probability of each destination multimedia file in each theme；According to described eachThe corresponding condition distribution probability of target topic in distribution probability and each theme of the destination multimedia file in each theme, predictionThe score of each destination multimedia file；The condition distribution probability is by being trained training multimedia file collectionIt arrives；Each destination multimedia file is ranked up according to the score.So as to solve individually to use speech recognition to calculateMethod, image recognition algorithm or natural language processing algorithm carry out content recognition, and the poor problem of accuracy achieves and improves more matchmakersThe advantageous effect of the accuracy of body file content identification.Further, it is also possible to determine target master in preset themes by training in advanceInscribe corresponding condition distribution probability, to improve multimedia file forecasting efficiency advantageous effect.
Example IV is two corresponding device embodiment of embodiment of the method, and detailed description is referred to embodiment two, hereinIt repeats no more.
For device embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of descriptionPlace illustrates referring to the part of embodiment of the method.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are withThe difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.Various general-purpose systems can also be used together with teaching based on this.As described above, it constructs required by this kind of systemStructure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that can utilize variousProgramming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hairBright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present inventionExample can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detailAnd technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimesIn example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：It is i.e. required to protectShield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as followingClaims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itselfAll as a separate embodiment of the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodimentChange and they are arranged in the one or more equipment different from the embodiment.It can be the module or list in embodimentMember or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement orSub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used anyCombination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appointWhere all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint powerProfit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generationIt replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodimentsIn included certain features rather than other feature, but the combination of the feature of different embodiments means in of the inventionWithin the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointedOne of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processorsSoftware module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practiceMicroprocessor or digital signal processor (DSP) come realize in mobile terminal device according to the ... of the embodiment of the present invention some orThe some or all functions of person's whole component.The present invention is also implemented as one for executing method as described hereinDivide either whole equipment or program of device (for example, computer program and computer program product).Such this hair of realizationBright program can may be stored on the computer-readable medium, or can be with the form of one or more signal.It is suchSignal can be downloaded from internet website and be obtained, and either provided on carrier signal or provided in any other forms.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and abilityField technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of notElement or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple suchElement.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer realIt is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branchTo embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fameClaim.
Those of ordinary skill in the art may realize that the embodiment in conjunction with disclosed in the embodiment of the present invention describes eachExemplary unit and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.TheseFunction is implemented in hardware or software actually, depends on the specific application and design constraint of technical solution.ProfessionTechnical staff can use different methods to achieve the described function each specific application, but this realization is not answeredThink beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In embodiment provided herein, it should be understood that disclosed device and method can pass through othersMode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, onlyA kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine orPerson is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutualBetween coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, device or unitIt connects, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unitThe component shown may or may not be physical unit, you can be located at a place, or may be distributed over multipleIn network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can alsoIt is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent productIt is stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially in other wordsThe part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meterCalculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can bePeople's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, ROM, RAM, magnetic disc or CD etc. are various can to store program codeMedium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, anyThose familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all containLid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.