CN110362698A - A kind of pictorial information generation method, device, mobile terminal and storage medium - Google Patents
A kind of pictorial information generation method, device, mobile terminal and storage medium Download PDFInfo
- Publication number
- CN110362698A CN110362698A CN201910612131.8A CN201910612131A CN110362698A CN 110362698 A CN110362698 A CN 110362698A CN 201910612131 A CN201910612131 A CN 201910612131A CN 110362698 A CN110362698 A CN 110362698A
- Authority
- CN
- China
- Prior art keywords
- target photo
- description
- words
- scene
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Abstract
The embodiment of the present disclosure discloses a kind of pictorial information generation method, device, mobile terminal and storage medium.Wherein, method comprises determining that at least one object for including in Target Photo, obtains the first words of description of Target Photo according at least one object, and, it is the probability of default scene according to the scene of Target Photo, determines the second words of description of Target Photo；By the first words of description and the second words of description, it is input to preset natural language model, obtains the picture descriptive statement of Target Photo.The embodiment of the present disclosure can obtain the first words of description of Target Photo according to the object for including in Target Photo, it is the probability of default scene according to the scene of Target Photo, determine the second words of description of Target Photo, and according to the first words of description and the second words of description of Target Photo, obtain the picture descriptive statement of Target Photo, to which picture be described accurately, in detail using picture descriptive statement, picture talk is realized.
Description
Technical field
The embodiment of the present disclosure is related to field of computer technology more particularly to a kind of pictorial information generation method, device, movement
Terminal and storage medium.
Background technique
With popularizing for mobile terminal, user can be shot using mobile terminal whenever and wherever possible.It would generally be to user
The image content of shooting is analyzed, and the description information of picture is obtained, and is then stored in photograph album for picture is corresponding with description information
In.
The prior art generally identifies picture, determines the corresponding label word of picture, for example, sky, ocean, then
It is stored in picture is corresponding with label word in photograph album.
Drawback of the prior art is that label word compares summary, cannot it is more acurrate, describe picture in detail.
Summary of the invention
The disclosure provides a kind of pictorial information generation method, device, mobile terminal and storage medium, to realize to existing
Pictorial information generates scheme and optimizes, and accurately, in detail picture is described.
In a first aspect, the embodiment of the present disclosure provides a kind of pictorial information generation method, comprising:
Determine at least one object for including in Target Photo, obtain Target Photo according at least one object first is retouched
Predicate language, and, it is the probability of default scene according to the scene of Target Photo, determines the second words of description of Target Photo；
By the first words of description and the second words of description, it is input to preset natural language model, obtains Target Photo
Picture descriptive statement.
Second aspect, the embodiment of the present disclosure additionally provide a kind of pictorial information generating means, comprising:
Words of description determining module, for determining at least one object for including in Target Photo, according at least one object
Body obtains the first words of description of Target Photo, and, it is the probability of default scene according to the scene of Target Photo, determines target
Second words of description of picture；
Descriptive statement determining module, for being input to preset nature for the first words of description and the second words of description
Language model obtains the picture descriptive statement of Target Photo.
The third aspect, the embodiment of the present disclosure additionally provide a kind of mobile terminal, comprising:
One or more processing units；
Storage device, for storing one or more programs；
When one or more programs are executed by one or more processing units, so that one or more processing units are realized such as
Pictorial information generation method described in the embodiment of the present disclosure.
Fourth aspect, the embodiment of the present disclosure additionally provide a kind of computer readable storage medium, are stored thereon with computer
Program realizes the pictorial information generation method as described in the embodiment of the present disclosure when computer program is executed by processor.
The embodiment of the present disclosure passes through at least one object for determining and including in Target Photo, is obtained according at least one object
First words of description of Target Photo, and, it is the probability of default scene according to the scene of Target Photo, determines Target Photo
Second words of description is input to preset natural language model, obtains then by the first words of description and the second words of description
The picture descriptive statement of Target Photo, the label word for solving the prior art compare summary, cannot it is more acurrate, describe in detail
The problem of picture, can obtain the first words of description of Target Photo, according to target figure according to the object for including in Target Photo
The scene of piece is the probability of default scene, determines the second words of description of Target Photo, and according to the first of Target Photo the description
Word and the second words of description obtain the picture descriptive statement of Target Photo, thus accurately, in detail using picture descriptive statement
Picture is described, realizes picture talk.
Detailed description of the invention
In conjunction with attached drawing and refer to following specific embodiments, the above and other feature, advantage of each embodiment of the disclosure and
Aspect will be apparent.In attached drawing, the same or similar appended drawing reference indicates the same or similar element.It should manage
Solution attached drawing is schematically that original part and element are not necessarily drawn to scale.
Fig. 1 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides；
Fig. 2 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides；
Fig. 3 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides；
Fig. 4 is a kind of structural schematic diagram for pictorial information generating means that the embodiment of the present disclosure provides；
Fig. 5 is a kind of structural schematic diagram for mobile terminal that the embodiment of the present disclosure provides.
Specific embodiment
Embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the certain of the disclosure in attached drawing
Embodiment, it should be understood that, the disclosure can be realized by various forms, and should not be construed as being limited to this
In the embodiment that illustrates, providing these embodiments on the contrary is in order to more thorough and be fully understood by the disclosure.It should be understood that
It is that being given for example only property of the accompanying drawings and embodiments effect of the disclosure is not intended to limit the protection scope of the disclosure.
It should be appreciated that each step recorded in disclosed method embodiment can execute in a different order,
And/or parallel execution.In addition, method implementation may include additional step and/or omit the step of execution is shown.This public affairs
The range opened is not limited in this respect.
Terms used herein " comprising " and its deformation are that opening includes, i.e., " including but not limited to ".Term "based"
It is " being based at least partially on ".Term " one embodiment " expression " at least one embodiment "；Term " another embodiment " indicates
" at least one other embodiment "；Term " some embodiments " expression " at least some embodiments ".The correlation of other terms is fixed
Justice provides in will be described below.
It is noted that the concepts such as " first " that refers in the disclosure, " second " are only used for different devices, module or list
Member distinguishes, and is not intended to limit the sequence or relation of interdependence of function performed by these devices, module or unit.
It is noted that referred in the disclosure "one", the modification of " multiple " be schematically and not restrictive this field
It will be appreciated by the skilled person that being otherwise construed as " one or more " unless clearly indicate otherwise in context.
The being merely to illustrate property of title of the message or information that are interacted between multiple devices in disclosure embodiment
Purpose, and be not used to limit the range of these message or information.
Fig. 1 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides.The present embodiment is applicable to
The case where generating pictorial information, this method can be executed by pictorial information generating means, the device can using software and/or
The mode of hardware realizes that the device can be configured in mobile terminal.As shown in Figure 1, this method may include steps of:
Step 101 determines at least one object for including in Target Photo, obtains Target Photo according at least one object
The first words of description, and, be the probability of default scene according to the scene of Target Photo, determine the second description of Target Photo
Word.
Wherein, the picture that Target Photo can be shot for user by the camera of mobile terminal.First words of description is
Words of description corresponding with each object included by Target Photo.Second words of description is the scene description word of Target Photo
Language.
In a specific example, determines at least one object for including in Target Photo, obtained according at least one object
To the first words of description of Target Photo, it may include: that Target Photo is input to preset object identification model, obtain target
First words of description of picture.
Preset object identification model Target Photo for receiving input identifies the object for including in Target Photo, and
Export words of description corresponding with each object recognized, i.e. the first words of description of Target Photo.For example, the first descriptor
Language includes: people, desk.
It is the probability of default scene according to the scene of Target Photo in a specific example, determines the of Target Photo
Two words of description may include: that Target Photo is input in preset image classification model, and the scene for exporting Target Photo is
The scene probability of default scene；It is the scene probability of default scene according to the scene of Target Photo, determines the second of Target Photo
Words of description.
Default scene is pre-set a plurality of types of scenes.For example, the scenes such as baby, sandy beach, night scene.Each class
Other scene has a corresponding scene description word.Scene corresponding scene description word in sandy beach is " sandy beach ".Target figure
It include the scene of Target Photo is the probability of all kinds of scenes that the scene of piece, which is the scene probability of default scene,.
Target Photo is input in preset image classification model, scene class of the preset image classification model to picture
It is not analyzed, the scene for exporting picture is the probability of default scene, so that it is determined that the scene of Target Photo is default scene
Probability.Then it is ranked up, obtains maximum according to the probability that scene of the sequence from big to small to Target Photo is default scene
Probability, and the scene description word of scene corresponding with maximum probability is determined as to the second words of description of Target Photo.
Step 102, by the first words of description and the second words of description, be input to preset natural language model, obtain
The picture descriptive statement of Target Photo.
In a specific example, preset natural language model receives the first words of description and the second description of input
Word is ranked up the first words of description and the second words of description, obtains at least two sequence of terms.
For example, the first words of description includes: people, automobile.Second words of description is to drive.Obtain sequence of terms: { people's automobile
Drive, { people's driving }；{ driver's automobile }, { driving people }, { automobile people driving }, { motorist }.
It sorts for each word, an expression is calculated by condition probability formula in preset natural language model
The rational probability of sequence of terms.It sorts to each word and assigns a probability.Legal word sorts to obtain likelihood ratio
It is larger, and illegal sentence obtains that the probability is relatively small.I.e. the bigger word of probability, which sorts, more meets the speech habits of the mankind.
The rational probability of sequence of terms is ranked up according to sequence from big to small, obtains maximum probability, and will be with maximum probability
Corresponding sequence of terms is determined as the picture descriptive statement of Target Photo, exports the picture descriptive statement of Target Photo.
For example, the maximum probability of sequence of terms { people's driving }, is determined as the figure of Target Photo for { people's driving }
Piece descriptive statement exports { people's driving }.
The technical solution of the present embodiment, by determining at least one object for including in Target Photo, according at least one
Object obtains the first words of description of Target Photo, and, it is the probability of default scene according to the scene of Target Photo, determines mesh
The second words of description of piece of marking on a map is input to preset natural language then by the first words of description and the second words of description
Model obtains the picture descriptive statement of Target Photo, and the label word for solving the prior art compares summary, cannot it is more acurrate,
The problem of describing picture in detail can obtain the first words of description of Target Photo according to the object for including in Target Photo,
It is the probability of default scene according to the scene of Target Photo, determines the second words of description of Target Photo, and according to Target Photo
The first words of description and the second words of description, the picture descriptive statement of Target Photo is obtained, to use picture descriptive statement
Accurately, picture is described in detail, realizes picture talk.
Fig. 2 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides.The present embodiment can with it is upper
It states each optinal plan in one or more embodiment to combine, in the present embodiment, determines in Target Photo to include at least
One object obtains the first words of description of the Target Photo according at least one object, may include: that Target Photo is defeated
Enter the first words of description that Target Photo is obtained to preset object identification model.
And be the probability of default scene according to the scene of Target Photo, determine the second words of description of Target Photo, it can
To include: that Target Photo is input in preset image classification model, the scene for exporting Target Photo is the field of default scene
Scape probability；It is the scene probability of default scene according to the scene of Target Photo, determines the second words of description of Target Photo.
As shown in Fig. 2, this method may include steps of:
Target Photo is input to preset object identification model by step 201, obtains the first descriptor of Target Photo
Language.
Wherein, preset object identification model Target Photo for receiving input identifies the object for including in Target Photo
Body, and export words of description corresponding with each object recognized, i.e. the first words of description of Target Photo.For example, first
Words of description includes: people, desk.
Target Photo is input in preset image classification model by step 202, and it is default for exporting the scene of Target Photo
The scene probability of scene.
Optionally, presetting scene is pre-set a plurality of types of scenes.For example, the scenes such as baby, sandy beach, night scene.
The scene of each classification has a corresponding scene description word.Scene corresponding scene description word in sandy beach is
For " sandy beach ".It include the scene of Target Photo is the general of all kinds of scenes that the scene of Target Photo, which is the scene probability of default scene,
Rate.Target Photo is input in preset image classification model, preset image classification model to the scene type of picture into
Row analysis, the scene for exporting picture is the probability of default scene, so that it is determined that the scene of Target Photo is the probability of default scene.
Step 203, be according to the scene of Target Photo default scene scene probability, determine the second description of Target Photo
Word.
Wherein, it is ranked up, obtains according to the probability that scene of the sequence from big to small to Target Photo is default scene
Maximum probability, and the scene description word of scene corresponding with maximum probability is determined as to the second words of description of Target Photo.
Step 204, by the first words of description and the second words of description, be input to preset natural language model, obtain
The picture descriptive statement of Target Photo.
Optionally, preset natural language model is for receiving the first words of description and the second words of description, to first
Words of description and the second words of description are ranked up, and obtain at least two sequence of terms, and export target according to sequence of terms
The picture descriptive statement of picture.
Optionally, the picture descriptive statement that Target Photo is exported according to sequence of terms, may include: preset natural language
The rational probability of expression sequence of terms is calculated by condition probability formula in model；It is right according to sequence from big to small
The rational probability of sequence of terms is ranked up, and obtains maximum probability, and sequence of terms corresponding with maximum probability is determined as
The picture descriptive statement of Target Photo；Export the picture descriptive statement of Target Photo.
The technical solution of the present embodiment obtains target figure by the way that Target Photo is input to preset object identification model
First words of description of piece, and, Target Photo is input in preset image classification model, the scene of Target Photo is exported
For the scene probability for presetting scene；It is the scene probability of default scene according to the scene of Target Photo, determines the of Target Photo
Two words of description can obtain the first words of description of Target Photo by preset object identification model, can be by default
Image classification model determine the second words of description of Target Photo, can be according to the first words of description of Target Photo and second
Words of description obtains the picture descriptive statement of Target Photo.
Fig. 3 is a kind of flow chart for pictorial information generation method that the embodiment of the present disclosure provides.The present embodiment can with it is upper
It states each optinal plan in one or more embodiment to combine, in the present embodiment, in the picture description for obtaining Target Photo
It, can be with after sentence further include: picture descriptive statement is bound with Target Photo；Respectively by picture descriptive statement and target
Picture is saved to corresponding storage location.
As shown in figure 3, this method may include steps of:
Step 301 determines at least one object for including in Target Photo, obtains Target Photo according at least one object
The first words of description, and, be the probability of default scene according to the scene of Target Photo, determine the second description of Target Photo
Word.
Step 302, by the first words of description and the second words of description, be input to preset natural language model, obtain
The picture descriptive statement of Target Photo.
Step 303 binds picture descriptive statement and Target Photo.
Wherein, picture descriptive statement is bound with Target Photo, establishes tying up for picture descriptive statement and Target Photo
Determine relationship.
Step 304 respectively saves picture descriptive statement to corresponding storage location with Target Photo.
Optionally, picture descriptive statement is saved to pictorial information storage location, Target Photo is saved to mobile terminal
Photograph album in.
In a specific example, user, can be according to picture descriptive statement and target when photograph album checks Target Photo
The binding relationship of picture obtains the picture descriptive statement of Target Photo.
In another specific example, user when sharing to Target Photo, can according to picture descriptive statement with
The binding relationship of Target Photo obtains the picture descriptive statement of Target Photo, Target Photo and picture descriptive statement is carried out same
Step is shared.
It optionally, can be with after obtaining the picture descriptive statement of Target Photo further include: raw according to picture descriptive statement
Voice is described at the picture of Target Photo；Voice is described to picture to bind with Target Photo；Voice is described into picture respectively
It saves with Target Photo to corresponding storage location.
By text speech converter, voice is described into the picture that picture descriptive statement is converted to Target Photo.To picture
Description voice is bound with Target Photo, establishes the binding relationship that picture describes voice and Target Photo.Picture is described into language
Sound is saved to pictorial information storage location, and Target Photo is saved into the photograph album of mobile terminal.
In a specific example, user can describe voice and target according to picture when photograph album checks Target Photo
The binding relationship of picture, the picture for obtaining Target Photo describe voice and play out.
In another specific example, user when sharing to Target Photo, can be described according to picture voice with
The binding relationship of Target Photo, the picture for obtaining Target Photo describe voice, and Target Photo and picture are described voice and carried out together
Step is shared.
The technical solution of the present embodiment then respectively will figure by binding to picture descriptive statement with Target Photo
Piece descriptive statement is saved with Target Photo to corresponding storage location, can establish tying up for picture descriptive statement and Target Photo
After determining relationship, picture descriptive statement is saved with Target Photo, consequently facilitating obtaining target in time according to binding relationship
The picture descriptive statement of picture.
Fig. 4 is a kind of structural schematic diagram for pictorial information generating means that the embodiment of the present disclosure provides.The present embodiment can fit
The case where for generating pictorial information.The device can realize that the device can be configured at by the way of software and/or hardware
Mobile terminal.As shown in figure 4, the apparatus may include: words of description determining module 401 and descriptive statement determining module 402.
Wherein, words of description determining module 401, for determining at least one object for including in Target Photo, according to extremely
A few object obtains the first words of description of Target Photo, and, it is the probability of default scene according to the scene of Target Photo,
Determine the second words of description of Target Photo；Descriptive statement determining module 402, for describing the first words of description and second
Word is input to preset natural language model, obtains the picture descriptive statement of Target Photo.
The technical solution of the present embodiment, by determining at least one object for including in Target Photo, according at least one
Object obtains the first words of description of Target Photo, and, it is the probability of default scene according to the scene of Target Photo, determines mesh
The second words of description of piece of marking on a map is input to preset natural language then by the first words of description and the second words of description
Model obtains the picture descriptive statement of Target Photo, and the label word for solving the prior art compares summary, cannot it is more acurrate,
The problem of describing picture in detail can obtain the first words of description of Target Photo according to the object for including in Target Photo,
It is the probability of default scene according to the scene of Target Photo, determines the second words of description of Target Photo, and according to Target Photo
The first words of description and the second words of description, the picture descriptive statement of Target Photo is obtained, to use picture descriptive statement
Accurately, picture is described in detail, realizes picture talk.
Optionally, based on the above technical solution, words of description determining module 401 may include: that the first word is true
Order member, for Target Photo to be input to preset object identification model, obtains the first words of description of Target Photo.
Optionally, based on the above technical solution, words of description determining module 401 may include: probability output list
Member, for Target Photo to be input in preset image classification model, the scene for exporting Target Photo is the field of default scene
Scape probability；Second word determination unit is the scene probability of default scene for the scene according to Target Photo, determines target figure
Second words of description of piece.
Optionally, based on the above technical solution, presetting scene is pre-set a plurality of types of scenes.
Optionally, based on the above technical solution, preset natural language model is for receiving the first words of description
And second words of description, the first words of description and the second words of description are ranked up, at least two sequence of terms are obtained,
And the picture descriptive statement of Target Photo is exported according to sequence of terms.
It optionally, based on the above technical solution, can be with further include: the first binding module, for being described to picture
Sentence is bound with Target Photo；First preserving module, for respectively saving picture descriptive statement and Target Photo to right
The storage location answered.
It optionally, based on the above technical solution, can be with further include: speech production module, for being retouched according to picture
The picture that predicate sentence generates Target Photo describes voice；Second binding module, for picture describe voice and Target Photo into
Row binding；Second preserving module is saved with Target Photo to corresponding storage location for picture to be described voice respectively.
The letter of picture provided by the embodiment of the present disclosure can be performed in pictorial information generating means provided by the embodiment of the present disclosure
Generation method is ceased, has the corresponding functional module of execution method and beneficial effect.
Below with reference to Fig. 5, it illustrates the structural representations for the mobile terminal 500 for being suitable for being used to realize the embodiment of the present disclosure
Figure.Mobile terminal in the embodiment of the present disclosure can include but is not limited to such as mobile phone, laptop, digital broadcasting and connect
Receive device, PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player), car-mounted terminal (such as vehicle
Carry navigation terminal) etc..Mobile terminal shown in Fig. 5 is only an example, function to the embodiment of the present disclosure and should not be made
With range band come any restrictions.
As shown in figure 5, mobile terminal 500 may include processing unit (such as central processing unit, graphics processor etc.)
501, random access can be loaded into according to the program being stored in read-only memory (ROM) 502 or from storage device 506
Program in memory (RAM) 503 and execute various movements appropriate and processing.In RAM 503, it is also stored with mobile terminal
Various programs and data needed for 500 operations.Processing unit 501, ROM 502 and RAM 503 pass through the phase each other of bus 504
Even.Input/output (I/O) interface 505 is also connected to bus 504.
In general, following device can connect to I/O interface 505: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 506 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 507 of dynamic device etc.；Storage device 506 including such as tape, hard disk etc.；And communication device 509.Communication device
509, which can permit mobile terminal 500, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 5 shows tool
There is the mobile terminal 500 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising being carried on non-transient computer can
The computer program on medium is read, which includes the program code for method shown in execution flow chart.At this
In the embodiment of sample, which can be downloaded and installed from network by communication device 509, or be filled from storage
It sets 506 to be mounted, or is mounted from ROM 502.When the computer program is executed by processing unit 501, the disclosure is executed
The above-mentioned function of being limited in the method for embodiment.
It should be noted that the above-mentioned computer-readable medium of the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit
Any computer-readable medium other than storage media, the computer-readable signal media can send, propagate or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. are above-mentioned
Any appropriate combination.
In some embodiments, client, server can use such as HTTP (HyperText Transfer
Protocol, hypertext transfer protocol) etc the network protocols of any currently known or following research and development communicated, and can
To be interconnected with the digital data communications (for example, communication network) of arbitrary form or medium.The example of communication network includes local area network
(" LAN "), wide area network (" WAN "), Internet (for example, internet) and ad-hoc network are (for example, the end-to-end net of ad hoc
Network) and any currently known or following research and development network.
Above-mentioned computer-readable medium can be included in above-mentioned mobile terminal；It is also possible to individualism, and not
It is fitted into the mobile terminal.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the shifting
When dynamic terminal executes, so that the mobile terminal: at least one object for including in Target Photo is determined, according at least one object
The first words of description of Target Photo is obtained, and, it is the probability of default scene according to the scene of Target Photo, determines target figure
Second words of description of piece；By the first words of description and the second words of description, it is input to preset natural language model, is obtained
The picture descriptive statement of Target Photo.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include but is not limited to object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing, illustrate according to the method, apparatus of the various embodiments of the disclosure, mobile terminal and
The architecture, function and operation in the cards of computer program product.In this regard, each side in flowchart or block diagram
Frame can represent a part of a module, program segment or code, and a part of the module, program segment or code includes one
Or multiple executable instructions for implementing the specified logical function.It should also be noted that in some implementations as replacements, side
The function of being marked in frame can also occur in a different order than that indicated in the drawings.For example, two sides succeedingly indicated
Frame can actually be basically executed in parallel, they can also be executed in the opposite order sometimes, this according to related function and
It is fixed.It is also noted that the group of each box in block diagram and or flow chart and the box in block diagram and or flow chart
It closes, can be realized with the dedicated hardware based system for executing defined functions or operations, or specialized hardware can be used
Combination with computer instruction is realized.
Being described in the embodiment of the present disclosure involved module and unit can be realized by way of software, can also be with
It is realized by way of hardware.Wherein, module or the title of unit do not constitute under certain conditions to the module or
The restriction of unit itself, for example, descriptive statement determining module is also described as " describing the first words of description and second
Word is input to preset natural language model, obtains the module of the picture descriptive statement of Target Photo ", the first word determines
Unit is also described as " Target Photo being input to preset object identification model, obtains the first description of Target Photo
The unit of word ".
Function described herein can be executed at least partly by one or more hardware logic components.Example
Such as, without limitation, the hardware logic component for the exemplary type that can be used include: field programmable gate array (FPGA), specially
With integrated circuit (ASIC), Application Specific Standard Product (ASSP), system on chip (SOC), complex programmable logic equipment (CPLD) etc.
Deng.
In the context of the disclosure, machine readable media can be tangible medium, may include or is stored for
The program that instruction execution system, device or equipment are used or is used in combination with instruction execution system, device or equipment.Machine can
Reading medium can be machine-readable signal medium or machine-readable storage medium.Machine readable media can include but is not limited to electricity
Son, magnetic, optical, electromagnetism, infrared or semiconductor system, device or equipment or above content any conjunction
Suitable combination.The more specific example of machine readable storage medium will include the electrical connection of line based on one or more, portable meter
Calculation machine disk, hard disk, random access memory (RAM), read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM
Or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage facilities or
Any appropriate combination of above content.
According to one or more other embodiments of the present disclosure, example one provides a kind of pictorial information generation method, comprising:
It determines at least one object for including in Target Photo, the Target Photo is obtained according at least one described object
The first words of description, and, be the probability of default scene according to the scene of the Target Photo, determine the Target Photo
Second words of description；
By first words of description and second words of description, it is input to preset natural language model, is obtained
The picture descriptive statement of the Target Photo.
According to one or more other embodiments of the present disclosure, example two provides a kind of pictorial information generation method, in example
On the basis of one pictorial information generation method, at least one object for including in the determining Target Photo, according to it is described extremely
A few object obtains the first words of description of the Target Photo, comprising:
The Target Photo is input to preset object identification model, obtains the first descriptor of the Target Photo
Language.
According to one or more other embodiments of the present disclosure, example three provides a kind of pictorial information generation method, in example
On the basis of one pictorial information generation method, the scene according to the Target Photo is the probability of default scene, is determined
Second words of description of the Target Photo, comprising:
The Target Photo is input in preset image classification model, it is default for exporting the scene of the Target Photo
The scene probability of scene；
It is the scene probability of default scene according to the scene of the Target Photo, determines the second description of the Target Photo
Word.
According to one or more other embodiments of the present disclosure, example four provides a kind of pictorial information generation method, in example
On the basis of three pictorial information generation method, the default scene is pre-set a plurality of types of scenes.
According to one or more other embodiments of the present disclosure, example five provides a kind of pictorial information generation method, in example
On the basis of one pictorial information generation method, the preset natural language model for receive first words of description with
And second words of description, first words of description and second words of description are ranked up, obtain at least two
A sequence of terms, and export according to the sequence of terms picture descriptive statement of the Target Photo.
According to one or more other embodiments of the present disclosure, example six provides a kind of pictorial information generation method, in example
On the basis of one pictorial information generation method, after obtaining the picture descriptive statement of the Target Photo, further includes:
The picture descriptive statement is bound with the Target Photo；
The picture descriptive statement is saved with the Target Photo to corresponding storage location respectively.
According to one or more other embodiments of the present disclosure, example seven provides a kind of pictorial information generation method, in example
On the basis of one pictorial information generation method, after obtaining the picture descriptive statement of the Target Photo, further includes:
Voice is described according to the picture that the picture descriptive statement generates the Target Photo；
Voice is described to the picture to bind with the Target Photo；
The picture voice is described respectively to save with the Target Photo to corresponding storage location.
According to one or more other embodiments of the present disclosure, example eight provides a kind of pictorial information generating means, comprising:
Words of description determining module, for determining at least one object for including in Target Photo, according to described at least one
A object obtains the first words of description of the Target Photo, and, it is default scene according to the scene of the Target Photo
Probability determines the second words of description of the Target Photo；
Descriptive statement determining module, for being input to first words of description and second words of description pre-
If natural language model, obtain the picture descriptive statement of the Target Photo.
According to one or more other embodiments of the present disclosure, example nine provides a kind of mobile terminal, comprising:
One or more processing units；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processing units, so that one or more of places
Manage pictorial information generation method of the device realization as described in any in example one to seven.
According to one or more other embodiments of the present disclosure, example ten provides a kind of computer readable storage medium, thereon
It is stored with computer program, the picture letter as described in any in example one to seven is realized when which is executed by processor
Cease generation method.
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Although this is not construed as requiring these operations with institute in addition, depicting each operation using certain order
The certain order that shows executes in sequential order to execute.Under certain environment, multitask and parallel processing may be advantageous
's.Similarly, although containing several specific implementation details in being discussed above, these are not construed as to this public affairs
The limitation for the range opened.Certain features described in the context of individual embodiment can also be realized in combination single real
It applies in example.On the contrary, the various features described in the context of single embodiment can also be individually or with any suitable
The mode of sub-portfolio is realized in various embodiments.
Although having used specific to this theme of the language description of structure feature and/or method logical action, answer
When understanding that theme defined in the appended claims is not necessarily limited to special characteristic described above or movement.On on the contrary,
Special characteristic described in face and movement are only to realize the exemplary forms of claims.
Claims (10)
1. a kind of pictorial information generation method characterized by comprising
It determines at least one object for including in Target Photo, the of the Target Photo is obtained according at least one described object
One words of description, and, it is the probability of default scene according to the scene of the Target Photo, determines the second of the Target Photo
Words of description；
By first words of description and second words of description, it is input to preset natural language model, is obtained described
The picture descriptive statement of Target Photo.
2. the method according to claim 1, wherein at least one object for including in the determining Target Photo
Body obtains the first words of description of the Target Photo according at least one described object, comprising:
The Target Photo is input to preset object identification model, obtains the first words of description of the Target Photo.
3. the method according to claim 1, wherein the scene according to the Target Photo is default scene
Probability, determine the second words of description of the Target Photo, comprising:
The Target Photo is input in preset image classification model, the scene for exporting the Target Photo is default scene
Scene probability；
It is the scene probability of default scene according to the scene of the Target Photo, determines the second descriptor of the Target Photo
Language.
4. according to the method described in claim 3, it is characterized in that, the default scene is pre-set a plurality of types of fields
Scape.
5. the method according to claim 1, wherein the preset natural language model is for receiving described the
One words of description and second words of description, arrange first words of description and second words of description
Sequence obtains at least two sequence of terms, and the picture descriptive statement of the Target Photo is exported according to the sequence of terms.
6. the method according to claim 1, wherein the picture descriptive statement for obtaining the Target Photo it
Afterwards, further includes:
The picture descriptive statement is bound with the Target Photo；
The picture descriptive statement is saved with the Target Photo to corresponding storage location respectively.
7. the method according to claim 1, wherein the picture descriptive statement for obtaining the Target Photo it
Afterwards, further includes:
Voice is described according to the picture that the picture descriptive statement generates the Target Photo；
Voice is described to the picture to bind with the Target Photo；
The picture voice is described respectively to save with the Target Photo to corresponding storage location.
8. a kind of pictorial information generating means characterized by comprising
Words of description determining module, for determining at least one object for including in Target Photo, according at least one described object
Body obtains the first words of description of the Target Photo, and, it is the probability of default scene according to the scene of the Target Photo,
Determine the second words of description of the Target Photo；
Descriptive statement determining module, for being input to first words of description and second words of description preset
Natural language model obtains the picture descriptive statement of the Target Photo.
9. a kind of mobile terminal, which is characterized in that the mobile terminal includes:
One or more processing units；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processing units, so that one or more of processing fill
Set the pictorial information generation method realized as described in any in claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
The pictorial information generation method as described in any in claim 1-7 is realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910612131.8A CN110362698A (en) | 2019-07-08 | 2019-07-08 | A kind of pictorial information generation method, device, mobile terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910612131.8A CN110362698A (en) | 2019-07-08 | 2019-07-08 | A kind of pictorial information generation method, device, mobile terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110362698A true CN110362698A (en) | 2019-10-22 |
Family
ID=68218261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910612131.8A Pending CN110362698A (en) | 2019-07-08 | 2019-07-08 | A kind of pictorial information generation method, device, mobile terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362698A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091099A (en) * | 2019-12-20 | 2020-05-01 | 京东方科技集团股份有限公司 | Scene recognition model construction method, scene recognition method and device |
| CN111310867A (en) * | 2020-05-11 | 2020-06-19 | 北京金山数字娱乐科技有限公司 | Text generation method and device based on picture |
| CN111916050A (en) * | 2020-08-03 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Speech synthesis method, speech synthesis device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138618A (en) * | 2015-08-11 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for performing secondary search in combination with speech in image search |
| US20160162514A1 (en) * | 2014-12-05 | 2016-06-09 | Microsoft Corporation | Image annotation using aggregated page information from active and inactive indices |
| CN109582825A (en) * | 2018-12-07 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109635135A (en) * | 2018-11-30 | 2019-04-16 | Oppo广东移动通信有限公司 | Image index generation method, device, terminal and storage medium |
| CN109784252A (en) * | 2019-01-04 | 2019-05-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
-
2019
- 2019-07-08 CN CN201910612131.8A patent/CN110362698A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160162514A1 (en) * | 2014-12-05 | 2016-06-09 | Microsoft Corporation | Image annotation using aggregated page information from active and inactive indices |
| CN105138618A (en) * | 2015-08-11 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for performing secondary search in combination with speech in image search |
| CN109635135A (en) * | 2018-11-30 | 2019-04-16 | Oppo广东移动通信有限公司 | Image index generation method, device, terminal and storage medium |
| CN109582825A (en) * | 2018-12-07 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109784252A (en) * | 2019-01-04 | 2019-05-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091099A (en) * | 2019-12-20 | 2020-05-01 | 京东方科技集团股份有限公司 | Scene recognition model construction method, scene recognition method and device |
| CN111310867A (en) * | 2020-05-11 | 2020-06-19 | 北京金山数字娱乐科技有限公司 | Text generation method and device based on picture |
| CN111916050A (en) * | 2020-08-03 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Speech synthesis method, speech synthesis device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298413A (en) | Image characteristic extracting method, device, storage medium and electronic equipment | |
| JP2023547917A (en) | Image segmentation method, device, equipment and storage medium | |
| CN110362698A (en) | A kind of pictorial information generation method, device, mobile terminal and storage medium | |
| CN110321958A (en) | Training method, the video similarity of neural network model determine method | |
| CN112634928B (en) | Sound signal processing method and device and electronic equipment | |
| WO2022100221A1 (en) | Retrieval processing method and apparatus, and storage medium | |
| CN109685137A (en) | A kind of topic classification method, device, electronic equipment and storage medium | |
| WO2022247562A1 (en) | Multi-modal data retrieval method and apparatus, and medium and electronic device | |
| CN111666416B (en) | Method and device for generating semantic matching model | |
| CN110298851A (en) | The training method and equipment of human body segmentation's neural network | |
| CN110532983A (en) | Method for processing video frequency, device, medium and equipment | |
| CN110390493A (en) | Task management method, device, storage medium and electronic equipment | |
| CN110826567A (en) | Optical character recognition method, device, equipment and storage medium | |
| WO2022151876A1 (en) | Testing control method and apparatus for application program, and electronic device and storage medium | |
| CN110381352A (en) | Display methods, device, electronic equipment and the readable medium of virtual present | |
| CN110335195A (en) | Body color method of adjustment, device, electronic equipment and storage medium | |
| CN110414450A (en) | Keyword detection method, apparatus, storage medium and electronic equipment | |
| CN110377273A (en) | A kind of method, apparatus of data processing, medium and electronic equipment | |
| CN116227629B (en) | Information analysis method, model training method, device and electronic equipment | |
| CN110414527A (en) | Character identifying method, device, storage medium and electronic equipment | |
| CN111797822A (en) | Character object evaluation method and device and electronic equipment | |
| CN111797665A (en) | Method and apparatus for converting video | |
| CN113610228B (en) | Method and device for constructing neural network model | |
| CN114510911A (en) | Text processing method and device, computer equipment and storage medium | |
| CN114281937A (en) | Training method of nested entity recognition model, and nested entity recognition method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |
|
| RJ01 | Rejection of invention patent application after publication |