CN109697239A - Method for generating the method for graph text information and for generating image data base - Google Patents
Method for generating the method for graph text information and for generating image data base Download PDFInfo
- Publication number
- CN109697239A CN109697239A CN201811407298.2A CN201811407298A CN109697239A CN 109697239 A CN109697239 A CN 109697239A CN 201811407298 A CN201811407298 A CN 201811407298A CN 109697239 A CN109697239 A CN 109697239A
- Authority
- CN
- China
- Prior art keywords
- image
- keyword
- information
- data base
- description
- 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
- 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
- G06F16/53—Querying
- G06F16/538—Presentation of query results
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses the method for generating graph text information and the method for generating image data base.The specific embodiment for being used to generate graph text information method includes: that title keyword and content topic are obtained to figure information；It is chosen and title keyword and the matched image of content topic from image data base, wherein image data base is generated based on iamge description；By the image insertion of selection to generate target graph text information in figure information.The embodiment helps to reduce figure cost.
Description
Technical field
This application involves field of computer technology, and in particular to for generating the method for graph text information and for generation figure
As the method for database.
Background technique
Fast development and the universal of mobile terminal of Internet technology change traditional information (such as news) display platform
Show form with content.Compared with traditional plain text information, the information that both pictures and texts are excellent more can reader note
Meaning.
In the related technology by the artificial figure realization information that both pictures and texts are excellent, however artificial figure is one time-consuming
Laborious and inefficient work.
Summary of the invention
The embodiment of the present application proposes the method for generating graph text information and the method for generating image data base.
In a first aspect, some embodiments of the present application provide a kind of method for generating graph text information, this method packet
It includes: obtaining title keyword and content topic to figure information；It is chosen and title keyword and interior from image data base
Hold the matched image of theme, wherein image data base is generated based on iamge description；The image of selection is inserted into figure information
In, generate target graph text information.
Second aspect, some embodiments of the present application provide a kind of method for generating graph text information, this method packet
It includes: obtaining title keyword and content topic to figure information；It is determined based on title keyword and content topic wait choose
The classification of image；The image data base with categorical match is chosen from least one image data base；From the image data of selection
It is chosen and title keyword and the matched image of content topic in library, wherein at least one image data base is based on image
Description generates；By the image insertion of selection to generate target graph text information in figure information.
The third aspect, some embodiments of the present application provide a kind of method for generating image data base, this method
It include: acquisition image collection, the image in image collection is the figure in graph text information；For the image in image collection, obtain
The description information for taking the image, the image that at least one keyword is extracted from the description information of the image as the image close
Keyword；Based on image collection and extracted image keyword, image data base is generated.
Fourth aspect, some embodiments of the present application provide a kind of electronic equipment, comprising: one or more processors；
Storage device is stored thereon with one or more programs, when one or more programs are executed by one or more processors, makes
Obtain method of the one or more processors realization as described in first aspect to the third aspect.
5th aspect, some embodiments of the present application provide a kind of computer-readable medium, are stored thereon with computer
Program realizes the method as described in first aspect to the third aspect when computer program is executed by processor.
Method provided by the embodiments of the present application for generating graph text information and the method for generating image data base,
By obtaining title keyword and content topic to figure information, later from the image data generated based on iamge description
Selection and title keyword and the matched image of content topic in library, finally by the image insertion of selection to raw in figure information
At target graph text information, to help to reduce figure cost.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application its
Its feature, objects and advantages will become more apparent upon:
Fig. 1 is that some embodiments of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for generating image data base of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for generating image data base of the application；
Fig. 4 is the flow chart according to one embodiment of the method for generating graph text information of the application；
Fig. 5 is the flow chart according to one embodiment of the method for generating graph text information of the application；
Fig. 6 is the flow chart according to another embodiment of the method for generating graph text information of the application；
Fig. 7 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that being
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, system architecture 100 may include server 101,103 and network 102.Network 102 is to take
It is engaged in providing the medium of communication link between device 101 and 103.Network 102 may include various connection types, such as wired, wireless
Communication link or glass fiber cables etc..
Server 101 can be the server for generating image data base.The available image collection of server 101
(for example, obtaining image collection from server 103) obtains the description information of each image later and therefrom extracts image key
Word generates image image data base corresponding with figure related term.
Server 101 can also be the server that figure is carried out to information.Server 101 can be from information
Middle acquisition title keyword and content topic, and matched image is selected from the image data base generated based on iamge description
It is inserted into information and generates the information that both pictures and texts are excellent.
Server 102 can be the server for storing image or graph text information.
It should be noted that for generating the method for image data base or for generating provided by the embodiment of the present application
The method of graph text information is generally executed by server 101.
It should be noted that server 101,103 can be hardware, it is also possible to software.When server 101,103 is
When hardware, the distributed server cluster of multiple server compositions may be implemented into, individual server also may be implemented into.When
When server is software, multiple softwares or software module (such as providing Distributed Services) may be implemented into, it can also be real
Ready-made single software or software module.It is not specifically limited herein.
It should be pointed out that the local of server 101 can also directly store image collection, server 101 can be direct
Obtain local image collection.At this point, exemplary system architecture 100 can not include server 103.
It should be understood that the number of network and server in Fig. 1 is only schematical.According to needs are realized, can have
There are the network and server of any suitable number.
With continued reference to Fig. 2, one embodiment of the method for generating image data base according to the application is shown
Process 200.The method for being used to generate image data base, may comprise steps of 201~203.
Step 201, image collection is obtained.
In the present embodiment, for generating the executing subject (such as server 101 of Fig. 1) of the method for image data base
Image collection can be obtained from Local or Remote.Wherein, the image in image collection can be the figure in graph text information.Figure
Literary information may include content of text and figure.For example, graph text information can be the informations such as news, blog article.
Here, the image in image collection can be above-mentioned executing subject or the server different from above-mentioned executing subject
It is obtained from the server for storing image or graph text information.For example, being climbed from the webpage in web page server by web crawlers
Take figure.
Step 202, for each image in image collection, the description information of the image is obtained, from the description of the image
Image keyword of at least one keyword as the image is extracted in information.
In the present embodiment, for each image in image collection, the execution of the method for generating image data base
Main body (such as server 101 of Fig. 1) can obtain the description information of the image first, then from the description information of acquisition
Extract image keyword of at least one keyword as the image.The description information of image can be includes in image
The character express of feature (for example, scene, conspicuousness object etc. in image).Here it is possible to using participle technique from description
Keyword is extracted in information.
In some optional implementations of the present embodiment, the description information of image can be obtained as follows:
Image recognition (such as passing through image recognition model) is carried out to image, the description of image is then generated according to image recognition result
Information.As an example, by image recognition, can determine that the scene of image is in parlor and image for a certain image
Conspicuousness object is one chair, then the description information of the image can be " having a chair in parlor ".
In some optional implementations of the present embodiment, iamge description technology (Image Caption can be passed through
Technique) description information of image is obtained.For example, can input an image into trained image description model,
Obtain description information corresponding with input picture.Here, image description model can be used for characterizing input picture and description information
Between corresponding relationship.In the example, LSTM (Long Short-Term Memory, shot and long term memory network) can be used
The encoder frame of unit is as image description model.
Optionally, above-mentioned image description model can be trained as follows and be obtained:
Firstly, obtaining multiple images from pre-generated image description data library and corresponding with each image retouching
State information.Wherein, image and description information corresponding with image are stored in image description data library.
Then, using each image in above-mentioned multiple images as input, description information corresponding with input picture is made
For output, initial pictures descriptive model is trained using the method for machine learning, obtains image description model.
Optionally, above-mentioned image description data library can generate as follows:
Firstly, obtaining graph text information set from Local or Remote.
Later, for each graph text information in above-mentioned graph text information set, obtain figure in the graph text information and
Description information corresponding with figure is extracted from the content of text of the graph text information.
Finally, figure and its corresponding description information are performed in accordance with storage, image description data library is established.
In some optional implementations of the present embodiment, the description information of each image can be natural language and retouch
The sentence stated.At least one above-mentioned keyword may include noun included in the sentence of natural language description and/or describe
Word.Accordingly, for each image in image collection, at least one keyword work is extracted from the description information of the image
May include following two step for the image keyword of the image:
The first step segments the sentence of natural language description, and the sentence for obtaining the natural language description is included
Noun and/or adjective.
Above-mentioned noun and/or adjective are extracted as the image keyword of the image by second step.
As an example, the description information of an image is " having a chair in parlor ", word segmentation processing is carried out to the sentence,
Noun wherein included " parlor ", " chair " are obtained, then can be the figure by " parlor ", " chair " the two keyword extractions
The image keyword of picture.
Step 203, it is based on image collection and extracted image keyword, generates image data base.
In the present embodiment, for generating the executing subject (such as server 101 of Fig. 1) of the method for image data base
Image collection can be used and the extracted image keyword of step 202 establishes image data base.As an example, can will be upper
The each image and its image keyword stated in image collection are performed in accordance with storage, establish image data base.
With continued reference to Fig. 3, it illustrates an applied fields according to the method for generating image data base of the application
Scape 300.In the application scenarios 300 of Fig. 3, server 302 obtains image collection from local, and wherein image 301 is image collection
In an image.Later, image 301 is input in trained image description model, obtains a description information " Huang
The flower of color rises sheer from wilderness ".Word segmentation processing is carried out to foregoing description information, obtains noun therein " flower ", " wilderness " and shape
Hold word " yellow ", and by above three crucial phrase at the image keyword (that is, " flower ", " wilderness ", " yellow ") of image 301.
Then, it is used as a data record storage into database image 301 and image keyword " flower ", " wilderness ", " yellow ".
Similarly, other images in image collection are similarly handled and is stored, finally obtain image data base.
Method provided by the embodiments of the present application for generating image data base, by collecting the figure in graph text information,
Obtain the description information of each figure later, and from description information extract image keyword, finally the figure based on collection and
The image keyword of extraction generates image data base, to help to reduce figure cost.
With further reference to Fig. 4, another embodiment of the method for generating image data base according to the application is shown
Process 400.The method for being used to generate image data base, may comprise steps of 401~405.
Step 401, image collection is obtained.
In the present embodiment, for generating the executing subject (such as server 101 of Fig. 1) of the method for image data base
Image collection can be obtained from Local or Remote.Wherein, the image in image collection can be the figure in graph text information.Figure
Literary information may include content of text and figure.For example, graph text information can be the informations such as news, blog article.
Step 402, for each image in image collection, the description information of the image is obtained, from the description of the image
Image keyword of at least one keyword as the image is extracted in information.
In the present embodiment, for each image in image collection, the execution of the method for generating image data base
Main body (such as server 101 of Fig. 1) can obtain the description information of the image first, then from the description information of acquisition
Extract image keyword of at least one keyword as the image.The description information of image can be includes in image
The character express of feature (for example, scene, conspicuousness object etc. in image).Here it is possible to using participle technique from description
Keyword is extracted in information.
Step 403, the similarity between the image keyword of different images in image collection is determined.
In the present embodiment, for generating the executing subject (such as server 101 of Fig. 1) of the method for image data base
It can determine the similarity between the image keyword of different images in image collection.As an example, in image collection
Any two image A and B, can calculate the similarity between the image keyword of image A and the image keyword of image B.
Step 404, the similarity between the image keyword based on different images carries out the image in image collection
Classification, obtains at least one set of sub-images.
In the present embodiment, for generating the executing subject (such as server 101 of Fig. 1) of the method for image data base
The similarity size that can use between the image keyword of different images divides each image in above-mentioned image collection
Class (for example, being classified by cluster), obtaining at least one set of sub-images, (each set of sub-images represents a classification
Image).
Step 405, at least one image data base corresponding at least one set of sub-images is generated.
In the present embodiment, for each set of sub-images at least one above-mentioned set of sub-images, for generating figure
As the method for database executing subject (such as server 101 of Fig. 1) can by the set of sub-images each image and
Its image keyword is performed in accordance with storage, obtains image data base corresponding with the set of sub-images.
As an example, image collection includes 1,000,000 images, it can should using the similarity between image keyword
Image collection is divided into 1000 set of sub-images (it is assumed that each set of sub-images includes 1000 images), and then establishes
1000 image data bases.If only establish an image data base, obtains an image and at most need to match 1,000,000 times.
In contrast, an image is obtained in the present embodiment at most to need to match 2000 times and (determine that matched image data base is most
Need to match 1000 times, retrieve matched database and at most need to match 1000 times), to effectively increase retrieval image
Efficiency.
Figure 4, it is seen that being used to generate image data base in the present embodiment compared with the corresponding embodiment of Fig. 2
Method process 400 embody using the similarity between image keyword to image carry out classification and according to inhomogeneity
Other image establishes the step of different image data bases.The scheme of the present embodiment description can effectively improve retrieval figure as a result,
The efficiency of picture.
With further reference to Fig. 5, it illustrates one embodiment according to the method for generating graph text information of the application
Process 500.The method for being used to generate graph text information may comprise steps of 501~503.
Step 501, title keyword and content topic are obtained to figure information.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
To obtain title keyword and content topic to figure information.Here, it can be to figure information and need to carry out figure
Information (for example, only including the news of content of text).
In some optional implementations of the present embodiment, step 501 can specifically include following steps:
Firstly, obtaining the title and content of text to figure information.
Later, keyword is extracted from title using participle technique as title keyword.
Then, content of text is input in trained text subject model, obtains the content master to figure information
Topic.Wherein, content topic may include subject key words.Here, text subject model can characterize content of text and content master
Corresponding relationship between topic.
Text subject model is to a kind of modeling method for implying theme in text.It is generally acknowledged that each of article
Word is all by " with some theme of certain probability selection, and with some word of certain probability selection from this theme ".Text
This topic model training method may include LSA (Latent semantic analysis, Latent Semantic analysis), pLSA
(Probabilistic latent semantic analysis, the analysis of probability Latent Semantic), LDA (Latent
Dirichlet allocation, hidden Di Li Cray distribution) etc..The training of text subject model is to study and answer extensively at present
Well-known technique, details are not described herein.
Step 502, it is chosen and title keyword and the matched image of content topic from image data base.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
To choose the image to match with the title keyword of step 502 acquisition and content topic in image data base.Wherein, image
Database is generated based on iamge description.
In some optional implementations of the present embodiment, step 502 can specifically include following steps: firstly, really
Determine the image keyword of image included by image data base and the similarity of above-mentioned title keyword and above content theme；
Then, the image that similarity is greater than or equal to preset threshold is chosen.As an example, image can be chosen from image data base
Keyword and title keyword and the similarity of content topic are greater than or equal to the image of similarity threshold (such as 90%).
In some optional implementations of the present embodiment, image data base can specifically pass through following three step
It generates:
The first step obtains image collection.Wherein, the image in image collection is the figure in graph text information.
Second step obtains the description information of the image for each image in image collection, from the description of the image
Image keyword of at least one keyword as the image is extracted in information.
Third step is based on image collection and extracted image keyword, generates image data base.
The specific descriptions of the above-mentioned first step to third step can refer in the corresponding embodiment of Fig. 2 about step 201~step
Rapid 203 specific descriptions, this will not be repeated here.
It is alternatively possible to obtain the description of image by iamge description technology (Image Caption Technique)
Information.For example, can input an image into trained image description model, description letter corresponding with input picture is obtained
Breath.Here, image description model can be used for characterizing the corresponding relationship between input picture and description information.It, can in the example
To be retouched using the encoder frame of LSTM (Long Short-Term Memory, shot and long term memory network) unit as image
State model.
Optionally, above-mentioned image description model can be trained as follows and be obtained:
Firstly, obtaining multiple images from pre-generated image description data library and corresponding with each image retouching
State information.Wherein, image and description information corresponding with image are stored in image description data library.
Then, using each image in above-mentioned multiple images as input, description information corresponding with input picture is made
For output, initial pictures descriptive model is trained using the method for machine learning, obtains image description model.
Optionally, above-mentioned image description data library can generate as follows:
Firstly, obtaining graph text information set from Local or Remote.
Later, for each graph text information in above-mentioned graph text information set, obtain figure in the graph text information and
Description information corresponding with figure is extracted from the content of text of the graph text information.
Finally, figure and its corresponding description information are performed in accordance with storage, image description data library is established.
In some optional implementations of the present embodiment, the description information of each image can be natural language and retouch
The sentence stated.At least one above-mentioned keyword may include noun included in the sentence of natural language description and/or describe
Word.Accordingly, for each image in image collection, at least one keyword work is extracted from the description information of the image
May include following two step for the image keyword of the image:
The first step segments the sentence of natural language description, and the sentence for obtaining the natural language description is included
Noun and/or adjective.
Above-mentioned noun and/or adjective are extracted as the image keyword of the image by second step.
As an example, the description information of an image is " having a chair in parlor ", word segmentation processing is carried out to the sentence,
Noun wherein included " parlor ", " chair " are obtained, then can be the figure by " parlor ", " chair " the two keyword extractions
The image keyword of picture.
Step 503, by the image insertion of selection to generate target graph text information in figure information.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
With by choose image according to it is preset insertion rule (for example, insertion image keyword where paragraph after etc.) be inserted into
To generate the information that both pictures and texts are excellent in figure information.
Method provided by the embodiments of the present application for generating graph text information, by obtaining the title pass to figure information
Keyword and content topic choose matched image from the image data base generated based on iamge description later, will finally choose
Image insertion in figure information generate target graph text information, thus facilitate reduce figure cost.
With further reference to Fig. 6, it illustrates another embodiments according to the method for generating graph text information of the application
Process 600.The method for being used to generate graph text information may comprise steps of 601~605.
Step 601, title keyword and content topic are obtained to figure information.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
To obtain title keyword and content topic to figure information.Here, it can be to figure information and need to carry out figure
Information (for example, only including the news of content of text).
The specific steps for obtaining title keyword and content topic can refer in the corresponding embodiment of Fig. 5 about acquisition
The description of title keyword and the specific steps of content topic, details are not described herein.
Step 602, the classification of image to be chosen is determined based on title keyword and content topic.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
To determine the classification of image to be chosen based on title keyword and content topic.As an example, step 601 can be obtained
Title keyword and content topic are merged, and determine the classification of image to be chosen.
Step 603, the image data base with categorical match is chosen from least one image data base.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
To choose the image data base that the classification determined with step 602 matches from least one image data base.Wherein, above-mentioned
At least one image data base is generated based on iamge description.
In some optional implementations of the present embodiment, image data base can specifically pass through following five steps
It generates:
The first step obtains image collection.Wherein, the image in image collection is the figure in graph text information.
Second step obtains the description information of the image for each image in image collection, from the description of the image
Image keyword of at least one keyword as the image is extracted in information.
Third step determines the similarity between the image keyword of different images in image collection.
4th step, the similarity between the image keyword based on different images, divides the image in image collection
Class obtains at least one set of sub-images.
5th step generates and at least one corresponding image data base at least one above-mentioned set of sub-images.
The specific descriptions of the above-mentioned first step to the 5th step can refer in the corresponding embodiment of Fig. 4 about step 401~step
Rapid 405 specific descriptions, this will not be repeated here.
Step 604, it is chosen and title keyword and the matched image of content topic from the image data base of selection.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
It is chosen and title keyword and the matched image of content topic in the image data base chosen with step 603.As an example, can
It is greater than or equal to choosing image keyword and the similarity of title keyword and content topic from the image data base of selection
The image of similarity threshold (such as 90%).
Step 605, by the image insertion of selection to generate target graph text information in figure information.
It in the present embodiment, can for generating the executing subject (such as server 101 of Fig. 1) of the method for graph text information
With by choose image according to it is preset insertion rule (for example, insertion image keyword where paragraph after etc.) be inserted into
To generate the information that both pictures and texts are excellent in figure information.
From fig. 6 it can be seen that being used to generate graph text information in the present embodiment compared with the corresponding embodiment of Fig. 5
The process 600 of method embody using the classification that title keyword and content topic determine choose matched image data base with
And the step of image is chosen from matched image data base.The scheme of the present embodiment description can effectively improve figure as a result,
Efficiency.
Below with reference to Fig. 7, it illustrates the electronic equipment for being suitable for being used to realize the embodiment of the present application (such as the services of Fig. 1
Device 101) computer system 700 structural schematic diagram.Electronic equipment shown in Fig. 7 is only an example, should not be to this Shen
Please embodiment function and use scope bring any restrictions.
As shown in fig. 7, computer system 700 includes one or more central processing unit (CPU) 701, it can basis
The program that is stored in read-only memory (ROM) 702 is loaded into random access storage device (RAM) from storage section 708
Program in 703 and execute various movements appropriate and processing.In RAM 703, be also stored with system 700 operate it is required
Various programs and data.CPU 701, ROM 702 and RAM 703 are connected with each other by bus 704.Input/output (I/O)
Interface 705 is also connected to bus 704.
I/O interface 705 is connected to lower component: the importation 706 including mouse, keyboard etc.；Including such as organic hair
The output par, c 707 of optical diode (OLED) display, liquid crystal display (LCD) etc. and loudspeaker etc.；Including hard disk etc.
Storage section 708；And the communications portion 709 of the network interface card including LAN card, modem etc..Communications portion
709 execute communication process via the network of such as internet.Driver 710 is also connected to I/O interface 705 as needed.It is removable
Medium 711, such as disk, CD, magneto-optic disk, semiconductor memory etc. are unloaded, is mounted on driver 710 as needed, with
Convenient for being mounted into storage section 708 as needed from the computer program read thereon.
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 be carried on computer-readable Jie
Computer program in matter, the computer program include the program code for method shown in execution flow chart.Such
In embodiment, which can be downloaded and installed from network by communications portion 709, and/or from detachable
Medium 711 is mounted.When the computer program is executed by central processing unit (CPU) 701, execute in the present processes
The above-mentioned function of limiting.
It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be ---
But be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above group
It closes.The more specific example of computer readable storage medium can include but is not limited to: have the electricity of one or more conducting wires
Connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (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 this application, computer readable storage medium can be any packet
Contain or store the tangible medium of program, which can be commanded execution system, device or device use or in connection
It uses.And in this application, computer-readable signal media may include propagating in a base band or as carrier wave a part
Data-signal, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of shapes
Formula, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also
It can be any computer-readable medium other than computer readable storage medium, which can send, pass
It broadcasts or transmits for by the use of instruction execution system, device or device or program in connection.Computer
The program code for including on readable medium can transmit with any suitable medium, including but not limited to: wireless, electric wire, light
Cable, RF etc. or above-mentioned any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be held as an independent software package
Part executes on the remote computer or holds on a remote computer or server completely on the user computer for row, part
Row.In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network
(LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as using because of spy
Service provider is netted to connect by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can be with
A part of a module, program segment or code is represented, a part of the module, program segment or code includes one or more
A executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, box
Middle marked function can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated
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.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in server described in above-described embodiment；It is also possible to individualism, and without in the supplying server.On
It states computer-readable medium and carries one or more program, when said one or multiple programs are executed by the server
When, so that the server: obtaining title keyword and content topic to figure information；From image data base choose with
Title keyword and the matched image of content topic, wherein image data base is generated based on iamge description；By the image of selection
Insertion is to generate target graph text information in figure information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Art technology
Personnel should be appreciated that invention scope involved in the application, however it is not limited to skill made of the specific combination of above-mentioned technical characteristic
Art scheme, while should also cover in the case where not departing from foregoing invention design, by above-mentioned technical characteristic or its equivalent feature into
Row any combination and the other technical solutions formed.Such as features described above and (but being not limited to) disclosed herein have class
Technical characteristic like function is replaced mutually and the technical solution that is formed.
Claims (15)
1. a kind of method for generating graph text information characterized by comprising
Title keyword and content topic are obtained to figure information；
It is chosen and the title keyword and the matched image of the content topic from image data base, wherein described image
Database is generated based on iamge description；
The image insertion of selection is described to generate target graph text information in figure information.
2. the method according to claim 1, wherein described image database is generated especially by following steps:
Image collection is obtained, the image in described image set is the figure in graph text information；
For the image in described image set, obtain the description information of the image, from the description information of the image extract to
Few image keyword of the keyword as the image；
Based on described image set and extracted image keyword, image data base is generated.
3. according to the method described in claim 2, it is characterized in that, the description information for obtaining the image, comprising:
By in image input image description model trained in advance, the description information of the image is obtained, wherein described image is retouched
Model is stated for characterizing the corresponding relationship between input picture and description information.
4. according to the method described in claim 3, it is characterized in that, described image descriptive model is trained as follows
It arrives:
Multiple images and description information corresponding with described multiple images are obtained from pre-generated image description data library；
Using the image in described multiple images as input, description information corresponding with input picture is used as and is exported, trained
To described image descriptive model.
5. according to the method described in claim 4, it is characterized in that, described image descriptive data base generates as follows:
Obtain graph text information set；
For the graph text information in graph text information set, the figure and description corresponding with figure letter in the graph text information are obtained
Breath；
Based on acquired figure and description information corresponding with figure, described image descriptive data base is generated.
6. the method according to any one of claim 2 to 5, which is characterized in that for the image in described image set,
The description information of the image is the sentence of natural language description, at least one described keyword includes the natural language description
The noun and/or adjective that sentence is included；The conduct of at least one keyword is extracted in the description information from the image should
The image keyword of image, comprising:
The sentence of the natural language description is segmented, the noun that the sentence of the natural language description is included is obtained
And/or adjective；
The noun and/or adjective are extracted as to the image keyword of the image.
7. the method according to any one of claim 2 to 6, which is characterized in that described to be based on described image set and institute
The image keyword of extraction generates image data base, comprising:
Determine the similarity between the image keyword of different images in described image set；
Similarity between image keyword based on different images, classifies to the image in described image set, obtains
At least one set of sub-images；
Generate at least one image data base corresponding at least one described set of sub-images.
8. method according to any one of claim 1 to 7, which is characterized in that it is described from image data base choose with
The title keyword and the matched image of the content topic, comprising:
Determine the image keyword and the title keyword and the content topic of image included by described image database
Similarity；
Choose the image that the similarity is greater than or equal to preset threshold.
9. method according to any one of claim 1 to 8, which is characterized in that described to obtain mark to figure information
Inscribe keyword and content topic, comprising:
Obtain the title and content of text to figure information；
The title keyword is extracted from the title；
The content of text is input in text subject model trained in advance, obtains the content topic.
10. a kind of method for generating graph text information characterized by comprising
Title keyword and content topic are obtained to figure information；
The classification of image to be chosen is determined based on the title keyword and the content topic；
The image data base with the categorical match is chosen from least one image data base, wherein at least one described figure
As database is generated based on iamge description；
It is chosen and the title keyword and the matched image of the content topic from the image data base of selection；
The image insertion of selection is described to generate target graph text information in figure information.
11. according to the method described in claim 10, it is characterized in that, at least one described image data base as follows
It generates:
Image collection is obtained, the image in described image set is the figure in graph text information；
For the image in described image set, obtain the description information of the image, from the description information of the image extract to
Few image keyword of the keyword as the image；
Determine the similarity between the image keyword of different images in described image set；
Similarity between image keyword based on different images, classifies to the image in described image set, obtains
At least one set of sub-images；
Generate at least one image data base corresponding at least one described set of sub-images.
12. a kind of method for generating image data base characterized by comprising
Image collection is obtained, the image in described image set is the figure in graph text information；
For the image in described image set, obtain the description information of the image, from the description information of the image extract to
Few image keyword of the keyword as the image；
Based on described image set and extracted image keyword, image data base is generated.
13. according to the method for claim 12, described be based on described image set and extracted image keyword, generate
Image data base, comprising:
Determine the similarity between the image keyword of different images；
Similarity between image keyword based on different images, classifies to the image in described image set, obtains
At least one set of sub-images；
Generate at least one image data base corresponding at least one described set of sub-images.
14. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any one of claims 1 to 13.
15. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
The now method as described in any one of claims 1 to 13.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811407298.2A CN109697239B (en) | 2018-11-23 | 2018-11-23 | Method for generating teletext information |
| PCT/CN2019/119914 WO2020103899A1 (en) | 2018-11-23 | 2019-11-21 | Method for generating inforgraphic information and method for generating image database |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811407298.2A CN109697239B (en) | 2018-11-23 | 2018-11-23 | Method for generating teletext information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109697239A true CN109697239A (en) | 2019-04-30 |
| CN109697239B CN109697239B (en) | 2022-05-31 |
Family
ID=66230118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811407298.2A Active CN109697239B (en) | 2018-11-23 | 2018-11-23 | Method for generating teletext information |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109697239B (en) |
| WO (1) | WO2020103899A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209862A (en) * | 2019-05-22 | 2019-09-06 | 招商局金融科技有限公司 | Text matches drawing method, electronic device and computer readable storage medium |
| CN110222189A (en) * | 2019-06-19 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| WO2020103899A1 (en) * | 2018-11-23 | 2020-05-28 | 连尚（新昌）网络科技有限公司 | Method for generating inforgraphic information and method for generating image database |
| CN111753078A (en) * | 2019-07-12 | 2020-10-09 | 北京京东尚科信息技术有限公司 | Image paragraph description generation method, device, medium and electronic equipment |
| CN112015936A (en) * | 2020-08-27 | 2020-12-01 | 北京字节跳动网络技术有限公司 | Method, device, electronic equipment and medium for generating article display diagram |
| WO2021008213A1 (en) * | 2019-07-12 | 2021-01-21 | 智慧芽信息科技(苏州)有限公司 | Image database establishing method, searching method, electronic device, and storage medium |
| CN112287173A (en) * | 2020-10-30 | 2021-01-29 | 北京有竹居网络技术有限公司 | Method and apparatus for generating information |
| CN112613293A (en) * | 2020-12-29 | 2021-04-06 | 北京中科闻歌科技股份有限公司 | Abstract generation method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010021937A1 (en) * | 2000-02-28 | 2001-09-13 | Lorenzo Cicchitelli | Automatically selecting fonts |
| CN102693231A (en) * | 2011-03-23 | 2012-09-26 | 百度在线网络技术（北京）有限公司 | Method, device and device for confirming atlas according to images from network |
| CN104657375A (en) * | 2013-11-20 | 2015-05-27 | 中国科学院深圳先进技术研究院 | Image-text theme description method, device and system |
| CN107103073A (en) * | 2017-04-21 | 2017-08-29 | 北京恒冠网络数据处理有限公司 | A kind of image indexing system |
| US20180173681A1 (en) * | 2016-12-21 | 2018-06-21 | Ten-X, Llc | System and method for generating content pertaining to real property assets |
| CN108304431A (en) * | 2017-06-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image search method and device, equipment, storage medium |
| CN108733779A (en) * | 2018-05-04 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | The method and apparatus of text figure |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090112830A1 (en) * | 2007-10-25 | 2009-04-30 | Fuji Xerox Co., Ltd. | System and methods for searching images in presentations |
| CN106951493A (en) * | 2017-03-14 | 2017-07-14 | 北京搜狐新媒体信息技术有限公司 | Automatic figure methods of exhibiting and device without figure news |
| CN107193962B (en) * | 2017-05-24 | 2021-06-11 | 百度在线网络技术（北京）有限公司 | Intelligent map matching method and device for Internet promotion information |
| CN109697239B (en) * | 2018-11-23 | 2022-05-31 | 南京尚网网络科技有限公司 | Method for generating teletext information |
-
2018
- 2018-11-23 CN CN201811407298.2A patent/CN109697239B/en active Active
-
2019
- 2019-11-21 WO PCT/CN2019/119914 patent/WO2020103899A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010021937A1 (en) * | 2000-02-28 | 2001-09-13 | Lorenzo Cicchitelli | Automatically selecting fonts |
| CN102693231A (en) * | 2011-03-23 | 2012-09-26 | 百度在线网络技术（北京）有限公司 | Method, device and device for confirming atlas according to images from network |
| CN104657375A (en) * | 2013-11-20 | 2015-05-27 | 中国科学院深圳先进技术研究院 | Image-text theme description method, device and system |
| US20180173681A1 (en) * | 2016-12-21 | 2018-06-21 | Ten-X, Llc | System and method for generating content pertaining to real property assets |
| CN107103073A (en) * | 2017-04-21 | 2017-08-29 | 北京恒冠网络数据处理有限公司 | A kind of image indexing system |
| CN108304431A (en) * | 2017-06-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image search method and device, equipment, storage medium |
| CN108733779A (en) * | 2018-05-04 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | The method and apparatus of text figure |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020103899A1 (en) * | 2018-11-23 | 2020-05-28 | 连尚（新昌）网络科技有限公司 | Method for generating inforgraphic information and method for generating image database |
| CN110209862A (en) * | 2019-05-22 | 2019-09-06 | 招商局金融科技有限公司 | Text matches drawing method, electronic device and computer readable storage medium |
| CN110209862B (en) * | 2019-05-22 | 2021-06-25 | 招商局金融科技有限公司 | Text matching method, electronic device and computer readable storage medium |
| CN110222189A (en) * | 2019-06-19 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN111753078A (en) * | 2019-07-12 | 2020-10-09 | 北京京东尚科信息技术有限公司 | Image paragraph description generation method, device, medium and electronic equipment |
| WO2021008213A1 (en) * | 2019-07-12 | 2021-01-21 | 智慧芽信息科技(苏州)有限公司 | Image database establishing method, searching method, electronic device, and storage medium |
| CN111753078B (en) * | 2019-07-12 | 2024-02-02 | 北京京东尚科信息技术有限公司 | Image paragraph description generation method, device, medium and electronic equipment |
| CN112015936A (en) * | 2020-08-27 | 2020-12-01 | 北京字节跳动网络技术有限公司 | Method, device, electronic equipment and medium for generating article display diagram |
| CN112015936B (en) * | 2020-08-27 | 2021-10-26 | 北京字节跳动网络技术有限公司 | Method, device, electronic equipment and medium for generating article display diagram |
| CN112287173A (en) * | 2020-10-30 | 2021-01-29 | 北京有竹居网络技术有限公司 | Method and apparatus for generating information |
| CN112613293A (en) * | 2020-12-29 | 2021-04-06 | 北京中科闻歌科技股份有限公司 | Abstract generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109697239B (en) | 2022-05-31 |
| WO2020103899A1 (en) | 2020-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697239A (en) | Method for generating the method for graph text information and for generating image data base | |
| CN107679039B (en) | Method and device for determining statement intention | |
| CN110287479B (en) | Named entity recognition method, electronic device and storage medium | |
| CN107491547B (en) | Search method and device based on artificial intelligence | |
| CN107491534B (en) | Information processing method and device | |
| CN107346336B (en) | Information processing method and device based on artificial intelligence | |
| CN109543058B (en) | Method, electronic device, and computer-readable medium for detecting image | |
| CN109117777A (en) | The method and apparatus for generating information | |
| CN108171276A (en) | For generating the method and apparatus of information | |
| CN108121699B (en) | Method and apparatus for outputting information | |
| CN106919711B (en) | Method and device for labeling information based on artificial intelligence | |
| CN109241286A (en) | Method and apparatus for generating text | |
| CN109408824A (en) | Method and apparatus for generating information | |
| CN110275963A (en) | Method and apparatus for output information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN112131881B (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN109325121A (en) | Method and apparatus for determining the keyword of text | |
| US20240143684A1 (en) | Information presentation method and apparatus, and device and medium | |
| CN109583389A (en) | Draw this recognition methods and device | |
| CN109284367A (en) | Method and apparatus for handling text | |
| CN109271624A (en) | A kind of target word determines method, apparatus and storage medium | |
| CN110019948A (en) | Method and apparatus for output information | |
| Fuad et al. | Analysis and classification of mobile apps using topic modeling: A case study on Google Play Arabic apps | |
| CN113011126B (en) | Text processing method, text processing device, electronic equipment and computer readable storage medium | |
| CN111800650B (en) | Video dubbing method and device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200702 Address after: Room 909, No. 12, Huangshan Road, Jianye District, Nanjing City, Jiangsu Province Applicant after: Nanjing Shangwang Network Technology Co.,Ltd. Address before: 312599 B-2, 3 floor, Jiayi Plaza, 127 East Renmin Road, Nanming street, Xinchang, Shaoxing, Zhejiang Applicant before: LIANSHANG (XINCHANG) NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |