CN110427499A - Processing method, device and the storage medium and electronic device of multimedia resource - Google Patents
Processing method, device and the storage medium and electronic device of multimedia resource Download PDFInfo
- Publication number
- CN110427499A CN110427499A CN201810387697.0A CN201810387697A CN110427499A CN 110427499 A CN110427499 A CN 110427499A CN 201810387697 A CN201810387697 A CN 201810387697A CN 110427499 A CN110427499 A CN 110427499A
- Authority
- CN
- China
- Prior art keywords
- target
- resource
- target object
- multimedia resource
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a kind of processing method of multimedia resource, device and storage medium and electronic devices.Wherein, this method comprises: identifying the target object in multimedia resource；Obtain target resource relevant to target object；According to the position that target object occurs in the playback progress of multimedia resource, target position is determined；Target resource and target position are associated, so that target resource can be shown in the case where multimedia resource is played to target position.The present invention solves multimedia resource in the related technology and shows the more single technical problem of content way.
Description
Technical field
The present invention relates to computer fields, in particular to a kind of processing method of multimedia resource, device and storage
Medium and electronic device.
Background technique
Existing multimedia resource, for example, documentary film, science popularization video, PPT (Power Point, PowerPoint) etc., base
It originally is that video, audio (such as aside), picture, text (such as subtitle) mode show content.It is interior after multimedia resource is made
Appearance is just fixed up, all ages and classes, knowledge hierarchy people receive identical information from the same resource content, do not account for
Watch the knowledge ability to accept and range of user.
For above-mentioned problem, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the present invention provides processing method, device and the storage medium and electronic device of a kind of multimedia resource, with
The multimedia resource at least solved in the related technology shows the more single technical problem of content way.
According to an aspect of an embodiment of the present invention, a kind of processing method of multimedia resource is provided, comprising: identification is more
Target object in media resource；Obtain target resource relevant to target object；According to target object in multimedia resource
The position occurred in playback progress, determines target position；Target resource and target position are associated, so that target resource energy
It is enough to be shown in the case where multimedia resource is played to target position.
According to another aspect of an embodiment of the present invention, a kind of processing unit of multimedia resource is additionally provided, comprising: identification
Unit, for identification target object in multimedia resource；First acquisition unit, for obtaining target relevant to target object
Resource；First determination unit, the position for being occurred in the playback progress of multimedia resource according to target object, determines target
Position；Associative cell, for target resource and target position to be associated, so that target resource can be in multimedia resource quilt
It is shown in the case where being played to target position.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, and meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the above method when operation.
Another aspect according to an embodiment of the present invention, additionally provides a kind of electronic device, including memory, processor and deposits
Store up the computer program that can be run on a memory and on a processor, wherein above-mentioned processor passes through computer program and executes
Above-mentioned method.
In embodiments of the present invention, by identifying the target object in multimedia resource, will acquire with target pair
As target position of the relevant resource associations in multimedia resource playback progress, and then multimedia resource can be made to be broadcast
Target resource is shown when being put into target position, and then the multimedia resource solved in the related technology shows that content way is more single
The technical issues of.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of schematic diagram of the application environment of the processing method of multimedia resource according to an embodiment of the present invention；
Fig. 2 is a kind of flow diagram of the processing method of optional multimedia resource according to an embodiment of the present invention；
Fig. 3 is a kind of flow diagram of the processing method of optional multimedia resource according to an embodiment of the present invention
Fig. 4 is a kind of schematic diagram of the processing unit of optional multimedia resource according to an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of optional electronic device according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
According to an aspect of an embodiment of the present invention, a kind of processing method of multimedia resource is provided.Optionally, above-mentioned
The processing method of multimedia resource can be, but not limited to be applied in application environment as shown in Figure 1, as shown in Figure 1, one kind can
The processing method of the multimedia resource of choosing may include: that multimedia resource is stored in terminal 102, and terminal 102 can be by answering
Processing request is sent to server 106 with via network 104, identification model is fed back to terminal via network 104 by server 106
102, terminal 102 is after receiving identification model, according to the target pair in the identification model identification multimedia resource received
As, and then terminal 102 can be sent to server 106 by network 104 and search for asking for target resource relevant to target object
It asks, it, can be according to target object in multimedia resource after the target resource that terminal 102 receives the feedback of server 106
The position occurred in playback progress, determines target position；Target resource and target position are associated, so that target resource energy
It is enough to be shown in the case where multimedia resource is played to target position.
In embodiments of the present invention, by identifying the target object in multimedia resource, will acquire with target pair
As target position of the relevant resource associations in multimedia resource playback progress, and then multimedia resource can be made to be broadcast
Target resource is shown when being put into target position, and then the multimedia resource solved in the related technology shows that content way is more single
The technical issues of.
Optionally, in the present embodiment, above-mentioned terminal can include but is not limited at least one of: mobile phone, plate electricity
Brain etc..Above-mentioned network can include but is not limited to wireless network, wherein the wireless network includes: bluetooth, WIFI and other realizations
The network of wireless communication.Above-mentioned server can include but is not limited at least one of: PC machine and other for calculate service
Equipment.Above-mentioned only a kind of example, the present embodiment do not do any restriction to this.
Embodiment 2
As an alternative embodiment, as shown in Fig. 2, the processing method of above-mentioned multimedia resource may include:
S202 identifies the target object in multimedia resource；
S204 obtains target resource relevant to target object；
S206 determines target position according to the position that target object occurs in the playback progress of multimedia resource；
Target resource and target position are associated by S208, so that target resource can be played in multimedia resource
To being shown in the case where target position.
Multimedia resource is the resource for carrying the combination of media form, and media form includes following at least two
Kind: audio, image, text, video (picture frame continuously played) etc..For example, multimedia resource can be documentary film, section
General video, PPT etc..
Multimedia resource can carry the information of target object, example with arbitrary media format (picture, audio, text etc.)
Such as, target object can be certain animal, plant, famous painting, famous person, melody, scenic spot or certain landmark building etc., more matchmakers
It may include the picture of target object or the picture for describing target object, the part of target object itself or complete in body resource
Portion's (a part of selections of such as melody), introduces aside audio of target object, etc..
By identifying at least one forms such as picture, audio, text in multimedia resource, identifying in multimedia resource is
It is no that there are target objects.Optionally, step S202 can be by first pass through in advance the machine learning obtained identification model of training into
Row identification, each identification model whether there is target object in multimedia resource for identification, and in turn, step S202 identifies more matchmakers
The step of target object in body resource may include: the identification mould for obtaining the target object in multimedia resource for identification
Type identifies the target object in multimedia resource by identification model.
It should be noted that identification model can be the use such as audio identification model, image recognition model, Text region model
In the identification model for identifying any media format, for being identified to the correspondence media format in multimedia resource.It is optional
Ground determines multimedia by the target object in the picture frame of identification video in the case where multimedia resource includes video
It whether there is target object in resource, that is, the target object in picture frame is identified by image recognition model.
In identifying multimedia resource in the case where target object, target resource relevant to target object, example are obtained
Such as, the resource of the knowledge contents such as text, image, audio for introducing target object.Target resource, which can be, to be stored in advance in
The resource for having mapping relations with target object in resources bank, resources bank can be through human-edited's generation, alternatively, obtaining
Target resource relevant to target object is also possible to the resource searched on network, searched on resources bank or network with
After the resource of target object, can be most related with selected part or choose to specify the resource of media format carrying as target
Resource.
After getting target resource relevant to target object, target resource is associated with to the broadcasting of multimedia resource
In progress, specifically, can determine target position according to the position that target object occurs in the playback progress of multimedia resource
It sets, and target resource and target position is associated, so that target resource can be played to target position in multimedia resource
It is shown in the case where setting.
Optionally, as an alternative embodiment, the identification mould of the target object in multimedia resource for identification
The acquisition modes of type may include steps of:
S1 determines the target group of multimedia resource；
S2 determines the target object for needing to identify in multimedia resource according to the target group of multimedia resource；
S3 chooses the identification model of target object for identification in identification model library.
For different target group, the target object for needing to identify may be different.For example, for towards youngster
The animal documentary film of virgin popular science category, it may be necessary to identify almost all of animal, and for towards high school student or adult
The documentary film of people then may not be needed to identify all animals since target group have had certain knowledge background, or
Person needs to the more specific of the variety ecotype of animal.
For example, if the target group of animal documentary film (multimedia resource) are children, in documentary film by identification cat,
The image recognition model of dog etc. identifies, if the target group of animal documentary film are adults, using using in documentary film
It is identified in the image recognition model of the identification specific kind of cat, the specific kind of dog.
After the target object for determining to need to identify in multimedia resource, target is chosen in identification model library
The corresponding identification model of object.Identification model library includes one or more identification models, each model corresponding mesh for identification
Mark object.Each identification model in identification model library is pre-generated, is used for specifically, choosing in identification model library
Before the identification model for identifying target object, this method can also include the following steps:
S1 establishes media training set corresponding with target object, wherein media training set includes at least one media sample
Right, each media sample is to including media sample and the training information for whether occurring target object in media sample being used to indicate；
S2 carries out machine learning training using media training set, obtains the identification model of target object for identification；
The identification model of target object for identification is added in identification model library S3.
For example, establishing training set of images corresponding with cat, image instruction to generate the image recognition model of cat for identification
Practice and concentrate including many image patterns pair, each image pattern centering includes whether having cat in an image and the image
Indicate information.Neural network model is trained using the training set of images, obtains the image recognition model of cat for identification,
And it is added into identification model library.
Optionally, as an alternative embodiment, step S204 acquisition target resource relevant to target object can
To include the following steps:
S1 searches for media resource relevant to target object using the name of target object as keyword；
S2 obtains target resource in search result.
Optionally, if necessary to play multimedia resource, the content of displaying can also be filtered, the foundation of filtering is
The description file (user's portrait) and/or selection operation of user, user can correspond to play multimedia resource terminal or
Play the account that the client of multimedia resource is currently logged in.The step of filtering, can be when broadcasting, that is, side plays
While needing the displaying content in the multimedia resource played to be filtered to subsequent, alternatively, the step of filtering is also possible to broadcasting
Before or after putting.
As an alternative embodiment, after target resource and target position are associated by step S208, it can
To execute following steps:
S1, receives the playing request of user, and playing request is used to indicate broadcasting multimedia resource；
S2, obtains the description file and/or selection operation of user, and description file can be user's portrait etc. and use for describing
The file of family personal characteristics, selection operation can be the selection operation that user is inputted by interactive device；
S3 determines filtering rule according to description file and/or selection operation, wherein filtering rule is used for target resource
And/or target position is filtered；
S4 plays multimedia resource, wherein during playing multimedia resource, after being filtered by filtering rule
Target location show pass through the filtered target resource of filtering rule.
Optionally, during playing multimedia resource, text, picture can be shown very on the upper layer of multimedia resource
To the target resource of video class further target resource can also be shown by exhibition methods such as knowledge chains.
Optionally, as an alternative embodiment, step S208 be associated target resource and target position can
To include executing following steps:
S1 marks target position in the playback progress of multimedia resource, obtains the time shaft of target object；
The time shaft of target resource and target object is associated by S2, that is, target resource is associated with corresponding mesh
At the time of mark object occurs in time shaft, the time shaft of target resource is generated.
In embodiments of the present invention, by identifying the target object in multimedia resource, will acquire with target pair
As target position of the relevant resource associations in multimedia resource playback progress, and then multimedia resource can be made to be broadcast
Target resource is shown when being put into target position, and then the multimedia resource solved in the related technology shows that content way is more single
The technical issues of.
A kind of optional embodiment of the above-described embodiment under concrete application scene is as shown in figure 3, to the optional embodiment party
Formula is described as follows.
" Object identifying " is the object identification data (i.e. above-mentioned identification model library) established by machine learning system, such as
For children's popular science category animal video, it is only necessary to can recognize that animal species (for example, dog), and more professional animal is regarded
Frequently, then the information (for example, shepherd dog) for needing can recognize that class, kind, category of animal etc. is more professional, more refining.Object identifying number
According to being the set for carrying out the identification model that machine learning training obtains using a large amount of study material (image training sample to).
Video pictures are analyzed by identification model, identify the target object in original video.Optionally, identification model can be with
It is to be chosen in the object identification data that pre-establishes and (can regularly update) according to the target group of original video, with target
The corresponding identification model of group.
After identifying the target object in video, according to include target object video image frame video playing into
Position in degree generates keyword time axis (object time shaft) corresponding with video progress, and appearance is marked in object time shaft
The period of target object.
In turn, according to these keywords, the corresponding enhancement information of search key (target resource) carries out " object information
Enhancing " generates " enhancement information time shaft ", In that is, the relevant enhancement information of target object is associated on object time shaft
In the case that video is played, in the enhancement information corresponding period occurred, in the upper layer exhibiting pictures of video, character introduction etc.
Enhancement information.
Optionally, as shown in figure 3, when playing video, (the description of user configuration (selection operation)/portrait can also be passed through
File) " enhancement information time shaft " is filtered, filtered " user's enhancement information time shaft " is obtained, is broadcast in original video
It when putting, plays " user's enhancement information time shaft ", is shown with the filtered period on the upper layer of video and pass through filtered figure
The enhancement informations such as piece, character introduction.
The optional embodiment is based on the technologies such as machine learning, and object is identified from video before broadcasting or when playing
(animal, plant, landscape or landmark building) can be schemed when being played to identification point on picture by introductory text
Piece perhaps knowledge point link mode to user show more contents by dissipate knowledge point allow user obtain more information or
Related information.User can establish filtering rule according to oneself hobby, ability to accept etc. simultaneously, only show that oneself is wished
The enhancing of acquisition shows content.
The optional embodiment by establishing the object identification datas of different levels and range, meet product side generate it is different
The enhancing content requirements of depth and range, and suitable machine learning can be selected according to video content, the conditions such as target group
System generates targets improvement content, greatly improves the information content of video, is drawn a portrait filtering enhancing based on user's selection and user
The technical solution of the information content provides more convenient, individual character knowledge channel for user, improves the knowledge body of ornamental video
It tests.
The technical solution of the optional embodiment combines increasingly mature machine learning techniques, by target in video
The identification of object acquires the self information and extension information of target object using existing search product and technology, finally to
Family exports original video and these additional enhancement informations, achievees the effect that extend knowledge.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server or network equipment etc.) method that executes each embodiment of the present invention.
Embodiment 3
Other side according to an embodiment of the present invention additionally provides a kind of for implementing the processing of above-mentioned multimedia resource
Device, as shown in figure 4, the device includes: recognition unit 402, first acquisition unit 404, the first determination unit 406 and association table
Member 408, wherein recognition unit, for identification target object in multimedia resource；First acquisition unit, for acquisition and mesh
Mark the relevant target resource of object；First determination unit, for being gone out in the playback progress of multimedia resource according to target object
Existing position, determines target position；Associative cell, for target resource and target position to be associated, so that target resource
It can be shown in the case where multimedia resource is played to target position.
In embodiments of the present invention, by identifying the target object in multimedia resource, will acquire with target pair
As target position of the relevant resource associations in multimedia resource playback progress, and then multimedia resource can be made to be broadcast
Target resource is shown when being put into target position, and then the multimedia resource solved in the related technology shows that content way is more single
The technical issues of.
Optionally, in the present embodiment, recognition unit includes: the first acquisition module, for obtaining multimedia for identification
The identification model of target object in resource, wherein identification model is the model for first passing through machine learning training in advance and obtaining；Identification
Module, for identifying the target object in multimedia resource by identification model.
Optionally, in the present embodiment, the first acquisition module includes: the first determining module, for determining multimedia resource
Target group；Second determining module needs to know in multimedia resource for being determined according to the target group of multimedia resource
Not Chu target object；Third determining module chooses the identification model of target object for identification in identification model library.
Optionally, in the present embodiment, device further include: establish unit, be used for for being chosen in identification model library
Before the identification model for identifying target object, corresponding with target object media training set is established, wherein media training set includes
At least one media sample pair, each media sample is to including media sample and being used to indicate in media sample whether target occur
The training information of object；Training unit obtains target pair for identification for carrying out machine learning training using media training set
The identification model of elephant；Adding unit, for the identification model of target object for identification to be added in identification model library.
Optionally, in the present embodiment, first acquisition unit includes: search module, for being with the name of target object
Keyword searches for media resource relevant to target object；Second obtains module, for obtaining target money in search result
Source.
Optionally, in the present embodiment, the device further include: receiving unit, for by target resource and target position
After being associated, the playing request of user is received；Second acquisition unit, for obtaining description file and/or the selection of user
Operation；Second determination unit, for determining filtering rule according to description file and/or selection operation, wherein filtering rule is used
It is filtered in target resource and/or target position；Broadcast unit, for playing multimedia resource, wherein playing more matchmakers
During body resource, show by the filtered target location of filtering rule through the filtered target money of filtering rule
Source.
Optionally, in the present embodiment, associative cell includes: mark module, for the playback progress in multimedia resource
Middle label target position, obtains the time shaft of target object；Relating module, for by the time shaft of target resource and target object
It is associated, generates the time shaft of target resource.
Optionally, in the present embodiment, multimedia resource includes video, and recognition unit is for identification in the picture frame of video
Target object.
Embodiment 4
The another aspect of embodiment according to the present invention, additionally provides a kind of storage medium, is stored in the storage medium
Computer program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program:
S1 identifies the target object in multimedia resource；
S2 obtains target resource relevant to target object；
S3 determines target position according to the position that target object occurs in the playback progress of multimedia resource；
Target resource and target position are associated by S4, so that target resource can be played in multimedia resource
It is shown in the case where target position.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: the target object in identification multimedia resource includes: the target object obtained in multimedia resource for identification
Identification model, wherein identification model is the model for first passing through machine learning training in advance and obtaining；Multimedia is identified by identification model
Target object in resource.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: the identification model for obtaining the target object in multimedia resource for identification comprises determining that the mesh of multimedia resource
Mark group；The target object for needing to identify in multimedia resource is determined according to the target group of multimedia resource；It is identifying
The identification model of target object for identification is chosen in model library.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: before choosing the identification model of target object for identification in identification model library, this method further include: establish with
The corresponding media training set of target object, wherein media training set includes at least one media sample pair, each media sample pair
Including media sample and it is used to indicate the training information for whether occurring target object in media sample；It is carried out using media training set
Machine learning training, obtains the identification model of target object for identification；The identification model of target object for identification is added
In identification model library.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: obtaining target resource relevant to target object includes: search and target using the name of target object as keyword
The relevant media resource of object；Target resource is obtained in search result.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: after target resource and target position are associated, this method further include: receive the playing request of user；
Obtain the description file and/or selection operation of user；According to description file and/or selection operation, filtering rule is determined, wherein
Filtering rule is for being filtered target resource and/or target position；Play multimedia resource, wherein playing multimedia
During resource, show by the filtered target location of filtering rule through the filtered target money of filtering rule
Source.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: it includes: the label target position in the playback progress of multimedia resource that target resource and target position, which are associated,
It sets, obtains the time shaft of target object；The time shaft of target resource and target object is associated, generate target resource when
Between axis.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program: multimedia resource includes video, identifies that the target object in multimedia resource includes: in the picture frame for identify video
Target object.
Optionally, in the present embodiment, those of ordinary skill in the art will appreciate that in the various methods of above-described embodiment
All or part of the steps be that the relevant hardware of terminal device can be instructed to complete by program, the program can store in
In one computer readable storage medium, storage medium may include: flash disk, read-only memory (Read-Only Memory,
ROM), random access device (Random Access Memory, RAM), disk or CD etc..
Embodiment 5
Another aspect according to an embodiment of the present invention additionally provides a kind of for implementing the processing of above-mentioned multimedia resource
The electronic device of method, as shown in figure 5, the electronic device includes: processor 802, memory 804, display 806, Yong Hujie
Mouth 808, transmitting device 810, sensor 812 etc..It is stored with computer program in the memory, which is arranged to pass through
Computer program executes the step in any of the above-described embodiment of the method.
Optionally, in the present embodiment, above-mentioned electronic device can be located in multiple network equipments of computer network
At least one network equipment.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S1 identifies the target object in multimedia resource；
S2 obtains target resource relevant to target object；
S3 determines target position according to the position that target object occurs in the playback progress of multimedia resource；
Target resource and target position are associated by S4, so that target resource can be played in multimedia resource
It is shown in the case where target position.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
Target object in identification multimedia resource includes: the identification model for obtaining the target object in multimedia resource for identification,
Wherein, identification model is the model for first passing through machine learning training in advance and obtaining；It is identified in multimedia resource by identification model
Target object.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
The identification model for obtaining the target object in multimedia resource for identification comprises determining that the target group of multimedia resource；Root
The target object for needing to identify in multimedia resource is determined according to the target group of multimedia resource；It is selected in identification model library
Take the identification model of target object for identification.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
Before choosing the identification model of target object for identification in identification model library, this method further include: foundation and target object
Corresponding media training set, wherein media training set includes at least one media sample pair, and each media sample is to including media
Sample and the training information for whether occurring target object in media sample be used to indicate；Machine learning is carried out using media training set
Training obtains the identification model of target object for identification；Identification model is added in the identification model of target object for identification
In library.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
Obtaining target resource relevant to target object includes: to search for related to target object using the name of target object as keyword
Media resource；Target resource is obtained in search result.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
After target resource and target position are associated, this method further include: receive the playing request of user；Obtain user's
File and/or selection operation are described；According to description file and/or selection operation, filtering rule is determined, wherein filtering rule is used
It is filtered in target resource and/or target position；Play multimedia resource, wherein in the process for playing multimedia resource
In, pass through the filtered target resource of filtering rule showing by the filtered target location of filtering rule.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
It includes: that target position is marked in the playback progress of multimedia resource that target resource and target position, which are associated, obtains mesh
Mark the time shaft of object；The time shaft of target resource and target object is associated, the time shaft of target resource is generated.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
Multimedia resource includes video, identifies that the target object in multimedia resource includes: the target pair in the picture frame for identify video
As.
Optionally, in the present embodiment, those of ordinary skill in the art will appreciate that in the various methods of above-described embodiment
All or part of the steps be that the relevant hardware of terminal device can be instructed to complete by program, the program can store in
In one computer readable storage medium, storage medium may include: flash disk, read-only memory (Read-Only Memory,
ROM), random access device (Random Access Memory, RAM), disk or CD etc..
Optionally, it will appreciated by the skilled person that structure shown in fig. 5 is only to illustrate, electronic device can also
To be smart phone (such as Android phone, iOS mobile phone), tablet computer, palm PC and mobile internet device
The terminal devices such as (Mobile Internet Devices, MID), PAD.Fig. 5 it does not cause to the structure of above-mentioned electronic device
It limits.For example, electronic device may also include more perhaps less component (such as network interface) or tool than shown in Fig. 5
There is the configuration different from shown in Fig. 5.
Wherein, memory 804 can be used for storing software program and module, such as the multimedia resource in the embodiment of the present invention
The corresponding program instruction/module for the treatment of method and apparatus, processor 802 passes through the software that is stored in memory 804 of operation
Program and module realize the processing method of above-mentioned multimedia resource thereby executing various function application and data processing.
Memory 804 may include high speed random access memory, can also include nonvolatile memory, such as one or more magnetic storage
Device, flash memory or other non-volatile solid state memories.In some instances, memory 804 can further comprise relative to
The remotely located memory of processor 802, these remote memories can pass through network connection to terminal.The example of above-mentioned network
Including but not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Above-mentioned transmitting device 810 is used to that data to be received or sent via a network.Above-mentioned network specific example
It may include cable network and wireless network.In an example, transmitting device 810 includes a network adapter (Network
Interface Controller, NIC), can be connected by cable with other network equipments with router so as to interconnection
Net or local area network are communicated.In an example, transmitting device 810 is radio frequency (Radio Frequency, RF) module,
For wirelessly being communicated with internet.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
If the integrated unit in above-described embodiment is realized in the form of SFU software functional unit and as independent product
When selling or using, it can store in above-mentioned computer-readable storage medium.Based on this understanding, skill of the invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be with soft in other words for art scheme
The form of part product embodies, which is stored in a storage medium, including some instructions are used so that one
Platform or multiple stage computers equipment (can be personal computer, server or network equipment etc.) execute each embodiment institute of the present invention
State all or part of the steps of method.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed client, it can be by others side
Formula is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, and only one
Kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed it is mutual it
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (18)
1. a kind of processing method of multimedia resource characterized by comprising
Identify the target object in multimedia resource；
Obtain target resource relevant to the target object；
According to the position that the target object occurs in the playback progress of the multimedia resource, target position is determined；
The target resource and the target position are associated, so that the target resource can be in the multimedia resource
It is shown in the case where being played to the target position.
2. the method according to claim 1, wherein the target object in identification multimedia resource includes:
Obtain the identification model of the target object for identification in the multimedia resource, wherein the identification model is
The model that machine learning training obtains is first passed through in advance；
The target object in the multimedia resource is identified by the identification model.
3. according to the method described in claim 2, it is characterized in that, obtaining the mesh in the multimedia resource for identification
Mark object identification model include:
Determine the target group of the multimedia resource；
The target pair for needing to identify in the multimedia resource is determined according to the target group of the multimedia resource
As；
The identification model of the target object for identification is chosen in identification model library.
4. according to the method described in claim 3, it is characterized in that, choosing the target pair for identification in identification model library
Before the identification model of elephant, the method also includes:
Establish media training set corresponding with the target object, wherein the media training set includes at least one media sample
This is right, and each media sample is to including media sample and being used to indicate in the media sample target pair whether occur
The training information of elephant；
Machine learning training is carried out using the media training set, obtains the identification model of the target object for identification；
The identification model of the target object for identification is added in the identification model library.
5. the method according to claim 1, wherein obtaining target resource packet relevant to the target object
It includes:
Using the name of the target object as keyword, media resource relevant to the target object is searched for；
The target resource is obtained in search result.
6. the method according to claim 1, wherein being closed by the target resource and the target position
After connection, the method also includes:
Receive the playing request of user；
Obtain the description file and/or selection operation of the user；
According to the description file and/or the selection operation, filtering rule is determined, wherein the filtering rule is used for institute
It states target resource and/or the target position is filtered；
Play the multimedia resource, wherein during playing the multimedia resource, passing through the filtering rule mistake
The target location after filter, which is shown, passes through the filtered target resource of the filtering rule.
7. the method according to claim 1, wherein the target resource and the target position are associated
Include:
The target position is marked in the playback progress of the multimedia resource, obtains the time shaft of the target object；
The time shaft of the target resource and the target object is associated, the time shaft of the target resource is generated.
8. method according to any one of claim 1 to 7, which is characterized in that the multimedia resource includes video, is known
Target object in other multimedia resource includes:
Identify the target object in the picture frame of the video.
9. a kind of processing unit of multimedia resource characterized by comprising
Recognition unit, for identification target object in multimedia resource；
First acquisition unit, for obtaining target resource relevant to the target object；
First determination unit, the position for being occurred in the playback progress of the multimedia resource according to the target object,
Determine target position；
Associative cell, for the target resource and the target position to be associated, so that the target resource can be
The multimedia resource is shown in the case where being played to the target position.
10. device according to claim 9, which is characterized in that the recognition unit includes:
First obtains module, for obtaining the identification model of the target object in the multimedia resource for identification,
In, the identification model is the model for first passing through machine learning training in advance and obtaining；
Identification module, for identifying the target object in the multimedia resource by the identification model.
11. device according to claim 10, which is characterized in that described first, which obtains module, includes:
First determining module, for determining the target group of the multimedia resource；
Second determining module needs to know in the multimedia resource for being determined according to the target group of the multimedia resource
Not Chu the target object；
Third determining module chooses the identification model of the target object for identification in identification model library.
12. device according to claim 11, which is characterized in that described device further include:
Unit is established, for building before choosing the identification model of the target object for identification in identification model library
Found media training set corresponding with the target object, wherein the media training set includes at least one media sample pair, often
A media sample is to including media sample and the instruction for whether occurring the target object in the media sample being used to indicate
Practice information；
Training unit obtains the target object for identification for carrying out machine learning training using the media training set
Identification model；
Adding unit, for the identification model of the target object for identification to be added in the identification model library.
13. device according to claim 9, which is characterized in that the first acquisition unit includes:
Search module, for using the name of the target object as keyword, searching for media money relevant to the target object
Source；
Second obtains module, for obtaining the target resource in search result.
14. device according to claim 9, which is characterized in that described device further include:
Receiving unit, for after being associated the target resource and the target position, the broadcasting for receiving user to be asked
It asks；
Second acquisition unit, for obtaining the description file and/or selection operation of the user；
Second determination unit, for determining filtering rule, wherein described according to the description file and/or the selection operation
Filtering rule is for being filtered the target resource and/or the target position；
Broadcast unit, for playing the multimedia resource, wherein during playing the multimedia resource, passing through
The filtered target location of filtering rule, which is shown, passes through the filtered target resource of the filtering rule.
15. device according to claim 9, which is characterized in that the associative cell includes:
Mark module obtains the target pair for marking the target position in the playback progress of the multimedia resource
The time shaft of elephant；
Relating module generates the target money for the time shaft of the target resource and the target object to be associated
The time shaft in source.
16. device according to any one of claims 9 to 15, which is characterized in that the multimedia resource includes video,
The recognition unit target object in the picture frame of the video for identification.
17. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute method described in any one of claim 1 to 8 when operation.
18. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to execute side described in any one of claim 1 to 8 by the computer program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810387697.0A CN110427499B (en) | 2018-04-26 | 2018-04-26 | Method and device for processing multimedia resources, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810387697.0A CN110427499B (en) | 2018-04-26 | 2018-04-26 | Method and device for processing multimedia resources, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110427499A true CN110427499A (en) | 2019-11-08 |
| CN110427499B CN110427499B (en) | 2023-08-29 |
Family
ID=68408250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810387697.0A Active CN110427499B (en) | 2018-04-26 | 2018-04-26 | Method and device for processing multimedia resources, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110427499B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046198A (en) * | 2019-11-29 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Information processing method, device, equipment and storage medium |
| CN111078078A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | Video playing control method, device, terminal and computer readable storage medium |
| CN111078070A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | PPT video barrage play control method, device, terminal and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070027844A1 (en) * | 2005-07-28 | 2007-02-01 | Microsoft Corporation | Navigating recorded multimedia content using keywords or phrases |
| CN1981281A (en) * | 2004-04-12 | 2007-06-13 | 克里尔普雷有限公司 | Apparatus, system, and method for filtering objectionable portions of a multimedia presentation |
| CN101828224A (en) * | 2007-04-06 | 2010-09-08 | 纳珀企业有限责任公司 | System and method for selectively identifying media items for play based on a recommender playlist |
| CN105760420A (en) * | 2016-01-13 | 2016-07-13 | 王凯 | Method and device for achieving interaction with content of multimedia file |
| CN107257982A (en) * | 2015-02-22 | 2017-10-17 | 谷歌公司 | The content being adapted to children is recognized in the case of without manual intervention on algorithm |
-
2018
- 2018-04-26 CN CN201810387697.0A patent/CN110427499B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1981281A (en) * | 2004-04-12 | 2007-06-13 | 克里尔普雷有限公司 | Apparatus, system, and method for filtering objectionable portions of a multimedia presentation |
| US20070027844A1 (en) * | 2005-07-28 | 2007-02-01 | Microsoft Corporation | Navigating recorded multimedia content using keywords or phrases |
| CN101828224A (en) * | 2007-04-06 | 2010-09-08 | 纳珀企业有限责任公司 | System and method for selectively identifying media items for play based on a recommender playlist |
| CN107257982A (en) * | 2015-02-22 | 2017-10-17 | 谷歌公司 | The content being adapted to children is recognized in the case of without manual intervention on algorithm |
| CN105760420A (en) * | 2016-01-13 | 2016-07-13 | 王凯 | Method and device for achieving interaction with content of multimedia file |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046198A (en) * | 2019-11-29 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Information processing method, device, equipment and storage medium |
| CN111078078A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | Video playing control method, device, terminal and computer readable storage medium |
| CN111078070A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | PPT video barrage play control method, device, terminal and medium |
| CN111046198B (en) * | 2019-11-29 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Information processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110427499B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108769823B (en) | Direct broadcasting room display methods, device, equipment | |
| CN108536672A (en) | Intelligent robot Training Methodology, device, computer equipment and storage medium | |
| CN109637207A (en) | A kind of preschool education interactive teaching device and teaching method | |
| CN110427499A (en) | Processing method, device and the storage medium and electronic device of multimedia resource | |
| CN106126524A (en) | Information-pushing method and device | |
| CN114339285B (en) | Knowledge point processing method, video processing method, device and electronic equipment | |
| CN103377568A (en) | Multifunctional child somatic sensation educating system | |
| CN106600492A (en) | Customized curriculum generation system | |
| CN108236784A (en) | The training method and device of model, storage medium, electronic device | |
| CN108460122B (en) | Video searching method, storage medium, device and system based on deep learning | |
| CN109859770A (en) | Music separation method, device and computer readable storage medium | |
| CN110290211A (en) | The online communication means of more people, electronic equipment and readable storage medium storing program for executing | |
| CN109640112A (en) | Method for processing video frequency, device, equipment and storage medium | |
| CN107515857A (en) | Semantic understanding method and system based on customization technical ability | |
| CN110851622A (en) | Text generation method and device | |
| CN109460503A (en) | Answer input method, device, storage medium and electronic equipment | |
| CN110414001A (en) | Sentence generation method and device, storage medium and electronic device | |
| CN107210001A (en) | Use the autonomous learning systems of video segment | |
| CN110109937A (en) | A kind of assessment of popular science knowledge and learning method, system and equipment | |
| CN105956963A (en) | Habit formation method and device | |
| CN106293085A (en) | It is applied to examination question searching method and the device of electric terminal | |
| CN105389333B (en) | A kind of searching system construction method and server architecture | |
| CN107551546A (en) | The generation method and device of a kind of game video | |
| CN106954323A (en) | A kind of information sharing system and method based on desk lamp | |
| CN108022462A (en) | Game type learning method, apparatus and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |