CN109697239B - Method for generating teletext information - Google Patents
Method for generating teletext information Download PDFInfo
- Publication number
- CN109697239B CN109697239B CN201811407298.2A CN201811407298A CN109697239B CN 109697239 B CN109697239 B CN 109697239B CN 201811407298 A CN201811407298 A CN 201811407298A CN 109697239 B CN109697239 B CN 109697239B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- information
- description
- database
- 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.)
- Active
Links
Images
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
Abstract
The embodiment of the application discloses a method for generating image-text information and a method for generating an image database. One specific embodiment of the method for generating the teletext information comprises: acquiring title keywords and content topics from the information of the graph to be matched; selecting an image matched with the title keyword and the content subject from an image database, wherein the image database is generated based on image description; and inserting the selected image into the information of the image to be matched to generate target image-text information. This embodiment helps to reduce the cost of mapping.
Description
Technical Field
The present application relates to the field of computer technology, and in particular, to a method for generating teletext information and a method for generating a database of images.
Background
The rapid development of internet technology and the popularization of mobile terminals have changed the traditional information (e.g., news) display platform and content display form. Compared with the traditional plain text information, the information with rich pictures and texts can attract the attention of the reader.
In the related art, the information of pictures and texts is realized by manual matching, however, the manual matching is time-consuming, labor-consuming and inefficient.
Disclosure of Invention
The embodiment of the application provides a method for generating image-text information and a method for generating an image database.
In a first aspect, some embodiments of the present application provide a method for generating teletext information, the method comprising: acquiring title keywords and content topics from the information of the graph to be matched; selecting an image matched with the title keyword and the content subject from an image database, wherein the image database is generated based on image description; and inserting the selected image into the information of the image to be matched to generate target image-text information.
In a second aspect, some embodiments of the present application provide a method for generating teletext information, the method comprising: acquiring title keywords and content topics from the information to be matched with the images; determining the category of the image to be selected based on the title key words and the content subjects; selecting an image database matched with the category from at least one image database; selecting images matched with the title keywords and the content topics from the selected image databases, wherein at least one image database is generated based on image description; and inserting the selected image into the information of the image to be matched to generate target image-text information.
In a third aspect, some embodiments of the present application provide a method for generating an image database, the method comprising: acquiring an image set, wherein images in the image set are matching images in the image-text information; for an image in an image set, obtaining description information of the image, and extracting at least one keyword from the description information of the image as an image keyword of the image; an image database is generated based on the image collection and the extracted image keywords.
In a fourth aspect, some embodiments of the present application provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in the first to third aspects.
In a fifth aspect, some embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements the method as described in the first to third aspects.
According to the method for generating the image-text information and the method for generating the image database, the title key words and the content subjects are obtained from the information of the image to be matched, then the images matched with the title key words and the content subjects are selected from the image database generated based on the image description, and finally the selected images are inserted into the information of the image to be matched to generate the target image-text information, so that the image matching cost is reduced.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram to which some embodiments of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for generating an image database according to the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for generating an image database according to the present application;
fig. 4 is a flow diagram of one embodiment of a method for generating teletext information according to the application;
fig. 5 is a flow diagram of one embodiment of a method for generating teletext information according to the application;
fig. 6 is a flow chart of another embodiment of a method for generating teletext information according to the application;
FIG. 7 is a block diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, system architecture 100 may include servers 101, 103 and network 102. Network 102 serves as a medium for providing communication links between servers 101 and 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The server 101 may be a server for generating an image database. The server 101 may acquire a set of images (e.g., acquire the set of images from the server 103), and then acquire description information of each image and extract image keywords from the description information, and generate an image database in which images correspond to image-related words.
The server 101 may also be a server for matching the information. The server 101 may obtain the title keyword and the content subject from the information, and select a matching image from an image database generated based on the image description to insert into the information to generate the information with rich image and text.
It should be noted that the method for generating the image database or the method for generating the teletext information provided by the embodiment of the present application is generally performed by the server 101.
The servers 101 and 103 may be hardware or software. When the servers 101 and 103 are hardware, they may be implemented as a distributed server cluster composed of multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the server 101 may also store the image set locally and the server 101 may directly obtain the local image set. At this point, exemplary system architecture 100 may not include server 103.
It should be understood that the number of networks and servers in fig. 1 is merely illustrative. There may be any suitable number of networks and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating an image database in accordance with the present application is shown. The method for generating the image database can comprise the following steps 201-203.
In this embodiment, the executing agent (e.g., server 101 of fig. 1) of the method for generating an image database may obtain the image collection locally or remotely. Wherein, the images in the image set can be matching images in the image-text information. The teletext information may comprise text content and a pictorial. For example, the graphics information may be news, blog, etc.
Here, the images in the image set may be acquired from a server storing the images or the teletext information by the execution subject or a server different from the execution subject. For example, the assembly graph is crawled from a web page in a web page server by a web crawler.
In the present embodiment, for each image in the image set, an executing subject (e.g., the server 101 of fig. 1) of the method for generating the image database may first acquire description information of the image, and then extract at least one keyword from the acquired description information as an image keyword of the image. The description information of the image may be a textual representation of features contained in the image (e.g., scenes, salient objects, etc. in the image). Here, a word segmentation technique may be used to extract keywords from the description information.
In some optional implementations of this embodiment, the description information of the image may be obtained by: the image is subjected to image recognition (for example, by an image recognition model), and then description information of the image is generated according to the image recognition result. As an example, for an image, through image recognition, it may be determined that a scene of the image is a living room and a salient object in the image is a chair, and the description information of the image may be "there is a chair in the living room".
In some optional implementations of the embodiment, the description information of the Image may be acquired by an Image description technology (Image capture technology). For example, the image may be input into a trained image description model, and description information corresponding to the input image may be obtained. Here, the image description model may be used to characterize a correspondence between the input image and the description information. In this example, an encoder framework of an LSTM (Long Short-Term Memory) unit may be employed as the image description model.
Optionally, the image description model may be obtained by training:
first, a plurality of images and description information corresponding to each image are acquired from an image description database generated in advance. The image description database stores images and description information corresponding to the images.
Then, each image in the plurality of images is used as input, description information corresponding to the input image is used as output, and an initial image description model is trained by using a machine learning method to obtain the image description model.
Alternatively, the image description database may be generated by:
first, a set of teletext information is acquired, either locally or remotely.
And then, for each image-text information in the image-text information set, acquiring a matching image in the image-text information and extracting description information corresponding to the matching image from the text content of the image-text information.
And finally, correspondingly storing the matching picture and the corresponding description information thereof, and establishing an image description database.
In some optional implementations of the present embodiment, the description information of each image may be a sentence described in a natural language. The at least one keyword may include a noun and/or an adjective included in a sentence described in the natural language. Correspondingly, for each image in the image set, extracting at least one keyword from the description information of the image as the image keyword of the image may include the following two steps:
firstly, segmenting words of sentences described by natural language to obtain nouns and/or adjectives contained in the sentences described by the natural language.
And secondly, extracting the nouns and/or the adjectives into image keywords of the image.
As an example, if the description information of an image is "there is a chair in the living room", and the sentence is subjected to word segmentation processing to obtain the terms "living room" and "chair" contained therein, two keywords of "living room" and "chair" may be extracted as the image keywords of the image.
In this embodiment, the executing agent (e.g., server 101 of fig. 1) of the method for generating an image database may create an image database using the image collection and the image keywords extracted in step 202. As an example, each image in the image set and its image keyword may be stored correspondingly to establish an image database.
With continued reference to FIG. 3, one application scenario 300 of a method for generating an image database according to the present application is shown. In the application scenario 300 of fig. 3, a server 302 locally obtains a set of images, where an image 301 is one image in the set of images. Then, the image 301 is input into the trained image description model, and the description information "a yellow flower stands in the wilderness" is obtained. The word segmentation processing is performed on the description information, and the nouns "flower", "wilderness" and the adjective "yellow" are obtained, and the three keywords constitute the image keywords (i.e., "flower", "wilderness" and "yellow") of the image 301. Then, the image 301 and the image keywords "flower", "wild", and "yellow" are stored as one data record in the database. Similarly, other images in the image set are processed and stored in the same way, and finally an image database is obtained.
According to the method for generating the image database, the matching images in the image-text information are collected, the description information of each matching image is obtained, the image keywords are extracted from the description information, and the image database is generated based on the collected matching images and the extracted image keywords, so that the cost of matching images is reduced.
With further reference to FIG. 4, a flow 400 of another embodiment of a method for generating an image database in accordance with the present application is shown. The method for generating the image database can comprise the following steps 401-405.
In this embodiment, the executing agent (e.g., server 101 of fig. 1) of the method for generating an image database may obtain the image collection locally or remotely. Wherein, the images in the image set can be matching images in the image-text information. The teletext information may comprise text content and a pictorial. For example, the graphics information may be news, blog, etc.
In the present embodiment, for each image in the image set, an executing subject (e.g., the server 101 of fig. 1) of the method for generating an image database may first acquire description information of the image, and then extract at least one keyword from the acquired description information as an image keyword of the image. The description information of the image may be a textual representation of features contained in the image (e.g., scenes, salient objects, etc. in the image). Here, a word segmentation technique may be used to extract keywords from the description information.
In step 403, the similarity between the image keywords of different images in the image set is determined.
In this embodiment, an executing subject (e.g., the server 101 of fig. 1) of the method for generating an image database may determine the similarity between image keywords of different images in an image set. As an example, for any two images a and B in the image set, a similarity between the image keyword of image a and the image keyword of image B may be calculated.
And step 404, classifying the images in the image set based on the similarity between the image keywords of different images to obtain at least one sub-image set.
In this embodiment, an executing subject (e.g., the server 101 in fig. 1) of the method for generating an image database may classify (e.g., classify by clustering) each image in the image sets by using the similarity between image keywords of different images, so as to obtain at least one sub-image set (each sub-image set represents an image of one category).
In this embodiment, for each sub-image set in the at least one sub-image set, an executing subject (for example, the server 101 in fig. 1) of the method for generating an image database may store each image in the sub-image set and an image keyword thereof correspondingly, so as to obtain an image database corresponding to the sub-image set.
As an example, the image set includes 100 ten thousand images, and the image set may be divided into 1000 sub-image sets (assuming that each sub-image set includes 1000 images) by using the similarity between the image keywords, thereby establishing 1000 image databases. If only one image database is established, at most 100 ten thousand matches are required to obtain one image. In contrast, in the embodiment, the maximum number of matching times is 2000 for obtaining one image (it is determined that the maximum number of matching times is 1000 for the matched image database, and the maximum number of matching times is 1000 for the matched database), so that the efficiency of searching the image is effectively improved.
As can be seen from fig. 4, compared with the embodiment shown in fig. 2, the process 400 of the method for generating an image database in this embodiment represents the steps of classifying images by using the similarity between the keywords of the images and establishing different image databases according to the images of different categories. Therefore, the scheme described by the embodiment can effectively improve the efficiency of searching the image.
With further reference to fig. 5, a flow 500 of an embodiment of a method for generating teletext information according to the application is shown. The method for generating the teletext information may comprise the following steps 501-503.
In this embodiment, an execution subject (for example, the server 101 in fig. 1) of the method for generating the teletext information may obtain the title keyword and the content subject from the information to be provided with the teletext information. Here, the information to be mapped may be information (e.g., news containing only text content) that needs to be mapped.
In some optional implementations of this embodiment, step 501 may specifically include the following steps:
firstly, a title and text content of the information to be matched are obtained.
Then, keywords are extracted from the title as title keywords by using a word segmentation technology.
And then, inputting the text content into the trained text topic model to obtain the content topic of the information to be matched with the graph. Wherein the content topic may include a topic keyword. Here, the text topic model may represent a correspondence between text content and content topics.
The text topic model is a modeling method for implicit topics in characters. Each word of an article is generally considered to be "selected with a certain probability for a topic and" selected with a certain probability for a word from this topic ". The text topic model training method may include LSA (Latent semantic analysis), pLSA (Probabilistic Latent semantic analysis), LDA (Latent Dirichlet allocation), and the like. Training of text topic models is a well-known technique that is currently widely studied and applied, and will not be described herein.
In this embodiment, an executive subject (e.g., the server 101 in fig. 1) of the method for generating the teletext information may select an image in the image database that matches the title keyword and the content subject obtained in step 502. Wherein the image database is generated based on the image description.
In some optional implementations of this embodiment, step 502 may specifically include the following steps: firstly, determining the similarity between the image keywords of the images contained in the image database and the title keywords as well as the content subjects; then, selecting the image with the similarity greater than or equal to a preset threshold value. As an example, an image in which the similarity of the image keyword with the title keyword and the content subject is greater than or equal to a similarity threshold (e.g., 90%) may be selected from the image database.
In some optional implementation manners of this embodiment, the image database may be specifically generated through the following three steps:
first, an image set is acquired. Wherein, the images in the image set are matching images in the image-text information.
And secondly, acquiring the description information of each image in the image set, and extracting at least one keyword from the description information of the image as the image keyword of the image.
And thirdly, generating an image database based on the image set and the extracted image keywords.
The detailed description of the first step to the third step may refer to the detailed description of step 201 to step 203 in the embodiment corresponding to fig. 2, which is not repeated herein.
Alternatively, description information of an Image may be acquired by an Image description technology (Image capture technology). For example, the image may be input into a trained image description model, and description information corresponding to the input image may be obtained. Here, the image description model may be used to characterize a correspondence between the input image and the description information. In this example, an encoder framework of an LSTM (Long Short-Term Memory) unit may be employed as the image description model.
Optionally, the image description model may be obtained by training:
first, a plurality of images and description information corresponding to each image are acquired from an image description database generated in advance. The image description database stores images and description information corresponding to the images.
Then, each image in the plurality of images is used as input, description information corresponding to the input image is used as output, and an initial image description model is trained by using a machine learning method to obtain the image description model.
Alternatively, the image description database may be generated by:
first, a set of teletext information is acquired, either locally or remotely.
And then, for each image-text information in the image-text information set, acquiring a matching image in the image-text information and extracting description information corresponding to the matching image from the text content of the image-text information.
And finally, correspondingly storing the matching picture and the corresponding description information thereof, and establishing an image description database.
In some optional implementations of the present embodiment, the description information of each image may be a sentence described in a natural language. The at least one keyword may include a noun and/or an adjective included in a sentence described in the natural language. Correspondingly, for each image in the image set, extracting at least one keyword from the description information of the image as the image keyword of the image may include the following two steps:
firstly, segmenting words of sentences described by natural language to obtain nouns and/or adjectives contained in the sentences described by the natural language.
And secondly, extracting the nouns and/or the adjectives into image keywords of the image.
As an example, if the description information of an image is "there is a chair in the living room", and the sentence is subjected to word segmentation processing to obtain the terms "living room" and "chair" contained therein, two keywords of "living room" and "chair" may be extracted as the image keywords of the image.
In this embodiment, an executing entity (e.g., the server 101 in fig. 1) of the method for generating the teletext information may insert the selected image into the information to be mapped according to a preset insertion rule (e.g., after inserting a paragraph where an image keyword is located, etc.), so as to generate the information with rich teletext.
According to the method for generating the image-text information, the title key words and the content subjects of the information of the image to be matched are obtained, then the matched image is selected from the image database generated based on the image description, and finally the selected image is inserted into the information of the image to be matched to generate the target image-text information, so that the image matching cost is reduced.
With further reference to fig. 6, a flow 600 of another embodiment of a method for generating teletext information according to the application is shown. The method for generating the image-text information can comprise the following steps 601-605.
Step 601, obtaining title keywords and content topics from the information to be matched.
In this embodiment, an execution subject (for example, the server 101 in fig. 1) of the method for generating the teletext information may obtain the title keyword and the content subject from the information to be provided with the teletext information. Here, the information to be mapped may be information (e.g., news containing only text content) that needs to be mapped.
For the specific steps of obtaining the title keyword and the content subject, reference may be made to the description of the specific steps of obtaining the title keyword and the content subject in the embodiment corresponding to fig. 5, which is not repeated herein.
In the present embodiment, the execution subject (e.g., the server 101 of fig. 1) of the method for generating teletext information may determine the category of the image to be selected based on the title keyword and the content subject. As an example, the title keyword and the content topic obtained in step 601 may be fused to determine the category of the image to be selected.
In this embodiment, the executing entity (e.g. server 101 of fig. 1) of the method for generating teletext information may select from at least one image database an image database matching the category determined in step 602. Wherein the at least one image database is generated based on the image description.
In some optional implementation manners of this embodiment, the image database may be specifically generated through the following five steps:
first, an image set is acquired. Wherein, the images in the image set are matching images in the image-text information.
And secondly, acquiring the description information of each image in the image set, and extracting at least one keyword from the description information of the image as the image keyword of the image.
And thirdly, determining the similarity between the image keywords of different images in the image set.
And fourthly, classifying the images in the image set based on the similarity between the image keywords of different images to obtain at least one sub-image set.
And fifthly, generating at least one image database respectively corresponding to the at least one sub-image set.
The detailed description of the first step to the fifth step may refer to the detailed description of steps 401 to 405 in the embodiment corresponding to fig. 4, and is not repeated herein.
And step 604, selecting images matched with the title keywords and the content topics from the selected image database.
In this embodiment, an executing subject (for example, the server 101 in fig. 1) of the method for generating the teletext information may select an image matching the title keyword and the content subject from the image database selected in step 603. As an example, an image in which the similarity of the image keyword with the title keyword and the content subject is greater than or equal to a similarity threshold (e.g., 90%) may be selected from the selected image database.
And 605, inserting the selected image into the information of the image to be matched to generate target image-text information.
In this embodiment, an executive body (e.g., the server 101 in fig. 1) of the method for generating the teletext information may insert the selected image into the information to be mapped according to a preset insertion rule (e.g., after inserting a paragraph where an image keyword is located, etc.), so as to generate information with rich teletext information.
As can be seen from fig. 6, compared with the embodiment shown in fig. 5, the flow 600 of the method for generating the teletext information in the embodiment represents the steps of selecting a matching image database using the category determined by the title keyword and the content subject and selecting an image from the matching image database. Therefore, the scheme described by the embodiment can effectively improve the matching efficiency.
Referring now to FIG. 7, shown is a schematic block diagram of a computer system 700 suitable for use in implementing an electronic device (e.g., server 101 of FIG. 1) of an embodiment of the present application. The electronic device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 7, the computer system 700 includes one or more Central Processing Units (CPUs) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a mouse, a keyboard, and the like; an output section 707 including a display such as an Organic Light Emitting Diode (OLED) display, a Liquid Crystal Display (LCD), and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application.
It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the server described in the above embodiments; or may exist separately and not be assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: acquiring title keywords and content topics from the information of the graph to be matched; selecting an image matched with the title keyword and the content subject from an image database, wherein the image database is generated based on image description; and inserting the selected image into the information of the image to be matched to generate target image-text information.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements in which any combination of the features described above or their equivalents does not depart from the spirit of the invention disclosed above. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A method for generating teletext information, comprising:
acquiring title keywords and content topics from the information of the graph to be matched;
determining a category based on the title keyword and the content subject;
selecting an image database matched with the category from at least one image database, wherein the at least one image database is generated based on image description;
selecting an image matched with the title keyword and the content subject from a selected image database;
inserting the selected image into the information of the image to be matched to generate target image-text information;
the acquiring of the title keyword and the content subject from the information of the to-be-matched graph comprises the following steps:
acquiring a title and text content of the information of the image to be matched;
extracting the title key words from the title;
inputting the text content into a pre-trained text theme model to obtain the content theme;
wherein the selecting an image matched with the title keyword and the content subject from the selected image database comprises:
determining similarity of image keywords of images included in the image database with the title keywords and the content subject;
and selecting the images with the similarity greater than or equal to a preset threshold value.
2. The method of claim 1, wherein the image database is generated by:
acquiring an image set, wherein images in the image set are matching images in image-text information;
for the images in the image set, obtaining description information of the images, and extracting at least one keyword from the description information of the images as an image keyword of the images;
generating an image database based on the set of images and the extracted image keywords.
3. The method of claim 2, wherein obtaining the description information of the image comprises:
and inputting the image into a pre-trained image description model to obtain description information of the image, wherein the image description model is used for representing the corresponding relation between the input image and the description information.
4. The method of claim 3, wherein the image description model is trained by:
acquiring a plurality of images and description information corresponding to the images from a pre-generated image description database;
and taking the image in the plurality of images as input, taking the description information corresponding to the input image as output, and training to obtain the image description model.
5. The method of claim 4, wherein the image description database is generated by:
acquiring a picture and text information set;
for the image-text information in the image-text information set, acquiring a matching image in the image-text information and description information corresponding to the matching image;
and generating the image description database based on the acquired matching drawing and the description information corresponding to the matching drawing.
6. The method according to any one of claims 2 to 5, wherein, for an image in the image set, the description information of the image is a natural language description sentence, and the at least one keyword comprises a noun and/or an adjective included in the natural language description sentence; the extracting at least one keyword from the description information of the image as an image keyword of the image comprises:
segmenting words of the sentences described by the natural language to obtain nouns and/or adjectives contained in the sentences described by the natural language;
and extracting the noun and/or the adjective as the image key word of the image.
7. The method of any of claims 2 to 6, wherein generating an image database based on the set of images and the extracted image keywords comprises:
determining similarity between image keywords of different images in the image set;
classifying the images in the image set based on the similarity between the image keywords of different images to obtain at least one sub-image set;
and generating at least one image database respectively corresponding to the at least one sub-image set.
8. The method of claim 1, wherein the at least one image database is generated by:
acquiring an image set, wherein images in the image set are matching images in image-text information;
for the images in the image set, obtaining description information of the images, and extracting at least one keyword from the description information of the images as an image keyword of the images;
determining similarity between image keywords of different images in the image set;
classifying the images in the image set based on the similarity between the image keywords of different images to obtain at least one sub-image set;
and generating at least one image database respectively corresponding to the at least one sub-image set.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.
10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1 to 8.
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 CN109697239A (en) | 2019-04-30 |
| CN109697239B true 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) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN110413814A (en) * | 2019-07-12 | 2019-11-05 | 智慧芽信息科技(苏州)有限公司 | Image data base method for building up, searching method, electronic equipment 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 |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AUPQ589300A0 (en) * | 2000-02-28 | 2000-03-23 | Canon Kabushiki Kaisha | Automatically selecting fonts |
| US20090112830A1 (en) * | 2007-10-25 | 2009-04-30 | Fuji Xerox Co., Ltd. | System and methods for searching images in presentations |
| US20180173681A1 (en) * | 2016-12-21 | 2018-06-21 | Ten-X, Llc | System and method for generating content pertaining to real property assets |
| 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109697239A (en) | 2019-04-30 |
| WO2020103899A1 (en) | 2020-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697239B (en) | Method for generating teletext information | |
| CN107679039B (en) | Method and device for determining statement intention | |
| CN107491534B (en) | Information processing method and device | |
| CN107491547B (en) | Search method and device based on artificial intelligence | |
| US10824874B2 (en) | Method and apparatus for processing video | |
| CN107346336B (en) | Information processing method and device based on artificial intelligence | |
| CN110301117B (en) | Method and apparatus for providing response in session | |
| CN109543058B (en) | Method, electronic device, and computer-readable medium for detecting image | |
| CN107241260B (en) | News pushing method and device based on artificial intelligence | |
| CN112131350B (en) | Text label determining method, device, terminal and readable storage medium | |
| US9613093B2 (en) | Using question answering (QA) systems to identify answers and evidence of different medium types | |
| CN109241286B (en) | Method and device for generating text | |
| US20180068221A1 (en) | System and Method of Advising Human Verification of Machine-Annotated Ground Truth - High Entropy Focus | |
| US11651015B2 (en) | Method and apparatus for presenting information | |
| CN112131881B (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN112015928A (en) | Information extraction method and device of multimedia resource, electronic equipment and storage medium | |
| CN111813993A (en) | Video content expanding method and device, terminal equipment and storage medium | |
| CN115269828A (en) | Method, apparatus, and medium for generating comment reply | |
| CN111666405B (en) | Method and device for identifying text implication relationship | |
| CN112188311A (en) | Method and apparatus for determining video material of news | |
| CN112749553B (en) | Text information processing method and device for video file and server | |
| US11949971B2 (en) | System and method for automatically identifying key dialogues in a media | |
| WO2022213864A1 (en) | Corpus annotation method and apparatus, and related device | |
| CN111209348B (en) | Method and device for outputting information | |
| CN111292114B (en) | Method and device for generating labels |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |