CN104239535B - A kind of method, server, terminal and system for word figure - Google Patents
A kind of method, server, terminal and system for word figure Download PDFInfo
- Publication number
- CN104239535B CN104239535B CN201410485930.0A CN201410485930A CN104239535B CN 104239535 B CN104239535 B CN 104239535B CN 201410485930 A CN201410485930 A CN 201410485930A CN 104239535 B CN104239535 B CN 104239535B
- Authority
- CN
- China
- Prior art keywords
- picture
- keyword
- text
- pictures
- word
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method for word figure, including：Receive the text sent by social networking application, at least one keyword is extracted from the text, from the correspondence of picture and keyword, determine picture corresponding with least one keyword, the text and the corresponding picture are sent, so that the social networking application of terminal shows the text and the corresponding picture at the same time.Method provided in an embodiment of the present invention for word figure, can be automatically word figure, so as to improve as the efficiency of word figure.
Description
Technical field
The present invention relates to Internet technical field, and in particular to a kind of for the method for word figure, server, terminal and to be
System.
Background technology
With the development of social networks, more and more people like delivering mood and thoughts in social networks, then
Some U.S.'s figures can be added below word, such as：After wechat circle of friends is delivered and had a talk about, it will usually add a landscape figure or
Figure map, to strengthen the appeal that this is had a talk about.
It was found by the inventors of the present invention that being all after passage is delivered in the prior art, it is required for adding picture manually,
User needs to ransack suitable picture from picture library, causes picture to add inefficiency.
The content of the invention
The embodiment of the present invention provide a kind of method for word figure, can be word figure automatically, thus improve for
The efficiency of word figure.The embodiment of the present invention additionally provides corresponding server, terminal and system.
First aspect present invention provides a kind of method for word figure, including：
Receive the text sent by social networking application；
At least one keyword is extracted from the text；
From the correspondence of picture and keyword, picture corresponding with least one keyword is determined；
The text and the corresponding picture are sent, so that the social networking application of terminal shows the text and described at the same time
Corresponding picture.
Second aspect of the present invention provides a kind of method for word figure, including：
Receive the text that user is inputted by social networking application platform；
The text is sent to server, so that at least one keyword of the server in the text determines
The corresponding picture of the text；
Receive the text and the picture that the server is sent；
The text and the picture are shown on the social networking application platform at the same time.
Third aspect present invention provides a kind of server, including：
Receiving unit, for receiving the text sent by social networking application；
Keyword resolution unit, for extracting at least one keyword from the text that the receiving unit receives；
Determination unit, for from the correspondence of picture and keyword, determining to extract with the keyword resolution unit
Each corresponding picture of keyword at least one keyword gone out；
Transmitting element, for the corresponding figure for sending the text to the terminal and the determination unit determines
Piece, so that the social networking application of the terminal shows the text and the corresponding picture of each keyword at the same time.
Fourth aspect present invention provides a kind of terminal, including：
Receiving unit, the text inputted for receiving user by social networking application platform；
Transmitting element, for sending the text of the receiving unit reception to server, so that the server root
The corresponding picture of the text is determined according at least one keyword in the text；
The receiving unit, is additionally operable to receive the text and the picture that the server is sent；
Display unit, shows the text that the receiving unit receives and described at the same time on the social networking application platform
Picture.
Fifth aspect present invention provides a kind of system for word figure, including：Server and terminal,
The terminal is used for：The text that user is inputted by social networking application platform is received, the text is sent to server,
So that at least one keyword of the server in the text determines the corresponding picture of the text；
The server is used for：The text inputted by social networking application platform is received, at least one is extracted from the text
A keyword, from the correspondence of picture and keyword, determines corresponding with each keyword at least one keyword
Picture, the text and the corresponding picture are sent, so that the social networking application of terminal shows the text and described at the same time
Corresponding picture；
The terminal is used for：The text and the picture that the server is sent are received, is put down in the social networking application
The text and the picture are shown on platform at the same time.
A kind of method for word figure provided in an embodiment of the present invention, including：Receive the text sent by social networking application
This, extracts at least one keyword from the text, from the correspondence of picture and keyword, determines and described at least one
The corresponding picture of a keyword, sends the text and the corresponding picture, so that the social networking application of terminal shows institute at the same time
State text and the corresponding picture.With needing to be manually word figure in the prior art, figure inefficiency is caused to be compared, this
The method for word figure that inventive embodiments provide, can be automatically word figure, so as to improve as the effect of word figure
Rate.
Brief description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is an embodiment schematic diagram of the method that the embodiment of the present invention is word figure；
Fig. 2 is the schematic diagram for delivering text in the embodiment of the present invention on social networking application platform；
Fig. 3 is a scene example schematic of the method for word figure in the embodiment of the present invention；
Fig. 4 is the schematic diagram for showing text and picture in the embodiment of the present invention on social networking application platform；
Fig. 5 is multiple features fusion extraction process schematic diagram in the embodiment of the present invention；
Fig. 6 is similarity mode process schematic in the embodiment of the present invention；
Fig. 7 is supernetwork model classification schematic diagram in the embodiment of the present invention；
Fig. 8 is another embodiment schematic diagram of the method for word figure in the embodiment of the present invention；
Fig. 9 is another embodiment schematic diagram of the method for word figure in the embodiment of the present invention；
The embodiment schematic diagram that it is server in the embodiment of the present invention that Figure 10, which is,；
Another embodiment schematic diagram that it is server in the embodiment of the present invention that Figure 11, which is,；
Another embodiment schematic diagram that it is server in the embodiment of the present invention that Figure 12, which is,；
Another embodiment schematic diagram that it is server in the embodiment of the present invention that Figure 13, which is,；
The embodiment schematic diagram that it is terminal in the embodiment of the present invention that Figure 14, which is,；
Another embodiment schematic diagram that it is terminal in the embodiment of the present invention that Figure 15, which is,；
Another embodiment schematic diagram that it is server in the embodiment of the present invention that Figure 16, which is,；
Another embodiment schematic diagram that it is terminal in the embodiment of the present invention that Figure 17, which is,；
Figure 18 is an embodiment schematic diagram of the system for word figure in the embodiment of the present invention.
Embodiment
The embodiment of the present invention provide a kind of method for word figure, can be word figure automatically, thus improve for
The efficiency of word figure.The embodiment of the present invention additionally provides corresponding device.The embodiment of the present invention also provides corresponding user and sets
It is standby.It is described in detail individually below.
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, the every other implementation that those skilled in the art are obtained without creative efforts
Example, belongs to the scope of protection of the invention.
Refering to Fig. 1, an embodiment of the method provided in an embodiment of the present invention for word figure includes：
101st, the text sent by social networking application platform is received.
Text in the embodiment of the present invention can be sentence, paragraph, article.Social networking application platform can be wechat, footpath between fields footpath between fields,
Microblogging or other can deliver the social networking application platform of word and picture.
Such as：The user whole family goes on a tour, and content of text is inputted in microblogging：Full of sunlight and warm one day, adult
Chat of playing card is sitting on meadow, and child aside plays kiteflying, and doggie, which rolls about on the grass, runs.As shown in Fig. 2, user
The text input to be issued in text box, the button delivered then is clicked on.
After clicking on the button delivered, terminal can be sent to this section of content of text server, and server receives this section
Text.
102nd, at least one keyword is extracted from the text.
After server receives this section of text, keyword can be extracted from the text according to the process shown in Fig. 3：Sunlight,
Meadow, kite, doggie.
103rd, from the correspondence of picture and keyword, determine and each keyword pair at least one keyword
The picture answered.
One group of picture corresponding with sunlight can be determined according to sunlight, according to meadow can determine one group it is corresponding with meadow
Picture, one group of picture corresponding with kite can be determined according to kite, and one group of figure corresponding with doggie can be determined according to doggie
Piece, then corresponds to from a keyword and an at least pictures is selected in a group picture piece as text, such as Fig. 2 described in recommendation picture dispensing
It is shown, it is final to determine 4 pictures for preparing to recommend.
104th, the text and the corresponding picture are sent so that the social networking application of terminal show at the same time the text and
The corresponding picture.
Server is to terminal sending information and prepares 4 pictures recommended, as shown in figure 4, at the microblogging interface of terminal
In will show in content and picture in Fig. 4.
A kind of method for word figure provided in an embodiment of the present invention, including：Receive the text sent by social networking application
This, extracts at least one keyword from the text, from the correspondence of picture and keyword, determines and described at least one
The corresponding picture of a keyword, sends the text and the corresponding picture, so that the social networking application of terminal shows institute at the same time
State text and the corresponding picture.With needing to be manually word figure in the prior art, figure inefficiency is caused to be compared, this
The method for word figure that inventive embodiments provide, can be automatically word figure, so as to improve as the effect of word figure
Rate.
Alternatively, on the basis of the corresponding embodiments of above-mentioned Fig. 1, the side provided in an embodiment of the present invention for word figure
It is described that at least one keyword is extracted from the text in another embodiment of method, it can include：
Noun, verb and the adjective in the text are analyzed as characteristic key words；
At least one keyword is determined from the characteristic key words according to statistics strategy.
In the embodiment of the present invention, the extractive technique of keyword can by a variety of, such as：Chinese Academy of Sciences's technology can be used
Chinese lexical analysis system (Institute of Computing Technology, the Chinese Lexical of research institute
Analysis System, ICTCLAS) and Hidden Markov chain model (Hidden Markov Model, HMM).
By automatically extracting keyword and the popular keyword of search, the length of message text is variable.For short message,
Directly specific term can be extracted by participle, such as：Name, place name, institution term, time, date, currency, percentage
Number, and automobile, finance and economics, health, physical culture, tourism, education, recruitment, culture, military affairs, extract specific verb, action, sum
It is usually no more than 12；Train storehouse to carry out word mark by keyword set in advance and carry out testing classification, finally by throwing
Ticket, selects highest 8 keywords of similarity.
For the longer content of word message, segment such as short message, incorporate and count word frequency, and to "：”、
The key symbol such as " --- ", some titles is weighted processing.
Alternatively, it is provided in an embodiment of the present invention to be on the basis of the corresponding embodiments of above-mentioned Fig. 1 or alternative embodiment
It is described from the correspondence of picture and keyword in another embodiment of the method for word figure, determine and described at least one
The corresponding picture of each keyword, can include in a keyword：
From keyword dictionary, the first preset quantity similar key is determined respectively for each keyword；
It is that each similar key determines the second preset quantity respectively from the correspondence of picture and similar key
Picture；
The product pictures of corresponding second preset quantity of same keyword and first preset quantity are distinguished
Cross-matched is carried out with the first preset quantity similar key of the same keyword, calculates the same keyword pair
The similarity value of each similar key answered and each pictures；
Output of the picture of similarity maximum as each similar key is selected for each similar key
Picture；
Selected for the same keyword from first preset quantity output picture at least one as with institute
State the corresponding picture of each keyword.
, it is necessary to pre-establish similar key dictionary by model training in the embodiment of the present invention, it is also necessary to establish picture
Storehouse, and be the upper keyword label of the configuration per pictures.
The method for building up of similar key dictionary can be the Chinese lexical for using technical research institute of the Chinese Academy of Sciences first
Analysis system segments microblogging and Chinese text, and the main noun retained in text, verb and adjective are as pass feature
Keyword；With χ2Statistical method carries out feature selecting；Using boolean's weight calculation feature weight, the feature vector after processing is made
For the training set and test set of super-network grader, super-network disaggregated model is trained to characteristic key words with super side alternative strategy
Classify.
Following steps can be included by establishing the process of label picture library：
S1, by multiple features fusion method carry out feature extraction to picture, extracts the feature of image.
Using multiple features fusion method：Including gray level co-occurrence matrixes++ 32 grades of wavelet transformation color histogram, to picture into
Row analysis.
Such as：As shown in figure 5, the side of gray level co-occurrence matrixes, wavelet transformation, 32 grades of color histograms and cluster can be used
Method extracts the feature of image, and the feature of image includes gray level image, hue, saturation, intensity, energy, inverse matrix, used
Property square, entropy, four layers of small echo etc..
S2, at least one word tag of picture generation being characterized after extraction.
It is multiple picture feature construction features vector using extraction first, then inputs the feature vector of structure respectively
Trained label picture model in advance, each label picture model include characteristic information and at least one word tag,
Classification based training is carried out at least one word tag, finally votes, determines last word tag.
S3：To scheme to search figure, the figures such as all kinds of current events on pair net, news, popular microblogging are removed using the picture under existing label
Piece, so as to further expand picture library.
Process in the embodiment of the present invention can be understood refering to the example below：
A certain number of keywords are selected from text by super-network, the priority that is pre-defined using database and again
Again Number synthesis determines 8 similar keys, and similar key is exactly the word high with the crucial Word similarity selected in text, example
Such as：High mountain and Kun Lun Mountain, each similar key randomly choose the very high picture of 8 similarities from label picture library again, always
Totally 64 pictures；Cross-matched is carried out with 8 similar keys respectively per pictures, forms picture and picture, picture and word
Between net structure, also draw every figure each keyword between similarity；It is similar to 8 finally to integrate each picture
The similarity value of keyword, take out with highest 8 pictures of 8 similar key comprehensive similarities as with the keyword phase
The picture matched somebody with somebody, is shown to user.
The process of Fig. 5 can be combined by being mutually matched between picture, then again by the process shown in Fig. 6, calculate picture it
Between similarity value, specifically can use Euclidean distance, secondary range, the method for color space distance, then melt into row distance
Close, calculate similarity.
The super-network pattern classification algorithm of Fig. 7 is mainly applied will extract in advance in extraction keyword link, function
Keyword is classified；Then corresponded to using character match and preset the picture with keyword label；By presetting
The picture library of tape label goes to expand class map space, searches for similar pictures, uses attached drawing three and the multiple features based on content of attached drawing four
Extraction algorithm is merged, and similarity measure is carried out by a variety of distances, finds the picture under same class keywords correspond to.
Alternatively, it is provided in an embodiment of the present invention to be on the basis of the corresponding embodiments of above-mentioned Fig. 1 or alternative embodiment
It is described from the correspondence of picture and keyword in another embodiment of the method for word figure, determine and described at least one
The corresponding picture of each keyword, can include in a keyword：
From the correspondence of picture and keyword, the 3rd preset quantity figure is determined respectively for each keyword
Piece；
Each keyword is subjected to cross-matched with the respective 3rd preset quantity pictures respectively, is calculated
Each keyword and the similarity value per pictures；
Similarity value is selected from the 3rd preset quantity pictures according to preceding at least one of size order sequence
Picture, as with each corresponding picture of keyword.
In the embodiment of the present invention, it is not necessary to which by the matching process of similar key, direct use is from text from extracting
Keyword, search picture to the described label picture library of upper one embodiment.
Specific picture searching process is matched according to similarity mode algorithm.
With reference to Fig. 8, illustrate the process of the word figure in the embodiment of the present invention：
As shown in figure 8, primary keyword dictionary can be established by searching for extraction keyword, then classified by super-network
Device carries out classification based training, then stores the dictionary classified, finally establishes final keyword dictionary.
In another branch, it is that picture is labelled, that is, determines keyword for picture, then by scheme to search the side of figure
Formula extends picture library, then extracts characteristics of image by multiple features fusion, then the expansion of final tape label is determined by similarity measure
Open up picture library.
During for word figure, user inputs text or message by the social networking application platform in terminal, then
The text or message are sent to server by terminal, and server extracts the keyword in the text or message, to keyword dictionary
Go to determine classification, then matched again in the extension picture library to sorted keyword to tape label, determine final recommendation figure
Piece, as shown in figure 3, determining, to 4 pictures are recommended, text and picture then to be sent to terminal, display should in social platform
Text and picture, as shown in Figure 4.
Refering to Fig. 9, another embodiment of the method provided in an embodiment of the present invention for word figure includes：
201st, the text that user is inputted by social networking application platform is received.
Text in the embodiment of the present invention can be sentence, paragraph, article.Social networking application platform can be wechat, footpath between fields footpath between fields,
Microblogging or other can deliver the social networking application platform of word and picture.
Such as：The user whole family goes on a tour, and content of text is inputted in microblogging：Full of sunlight and warm one day, adult
Chat of playing card is sitting on meadow, and child aside plays kiteflying, and doggie, which rolls about on the grass, runs.As shown in Fig. 2, user
The text input to be issued in text box, the button delivered then is clicked on.
After clicking on the button delivered, terminal can be sent to this section of content of text server, and server receives this section
Text.
202nd, the text is sent to server, so that at least one keyword of the server in the text
Determine the corresponding picture of the text.
203rd, the text and the picture that the server is sent are received.
204th, the text and the picture are shown at the same time on the social networking application platform.
Server is to terminal sending information and prepares 4 pictures recommended, as shown in figure 4, at the microblogging interface of terminal
In will show in content and picture in Fig. 4.
The text that the embodiment of the present invention is inputted using user is received by social networking application platform, the text is sent to server
This, so that at least one keyword of the server in the text determines the corresponding picture of the text, receives institute
The text of server transmission and the picture are stated, the text and the figure are shown at the same time on the social networking application platform
Piece.With needing to be manually word figure in the prior art, figure inefficiency is caused to be compared, it is provided in an embodiment of the present invention for text
The method of word figure, can be automatically word figure, so as to improve as the efficiency of word figure.
Alternatively, on the basis of the corresponding embodiments of above-mentioned Fig. 9, the side provided in an embodiment of the present invention for word figure
In another embodiment of method, it is described on the social networking application platform display at the same time show the text and the picture after,
The method further includes：
Receive deletion instruction of the user at least pictures in the picture；
Instructed according to described delete, an at least pictures described in deletion.
In the embodiment of the present invention, provide a user plurality of pictures and selected for user, user can determine to want according to demand
Picture, on the basis of improving as word figure efficiency, also improve user experience.
Refering to Figure 10, an embodiment of server 30 provided in an embodiment of the present invention includes：
Receiving unit 301, for receiving the text sent by social networking application；
Keyword resolution unit 302, for extracting at least one pass from the text that the receiving unit 301 receives
Keyword；
Determination unit 303, for from the correspondence of picture and keyword, determining and the keyword resolution unit
Each corresponding picture of keyword in the 302 at least one keywords extracted；
Transmitting element 304, corresponds to for sending each keyword that the text and the determination unit 303 determine
Picture so that the social networking application of terminal shows the text and each corresponding picture of keyword at the same time.
In the embodiment of the present invention, receiving unit 301 receives the text sent by social networking application platform, keyword resolution list
Member 302 extracts at least one keyword from the text that the receiving unit 301 receives, determination unit 303 from picture with
It is every in the definite at least one keyword extracted with the keyword resolution unit 302 in the correspondence of keyword
The corresponding picture of a keyword, transmitting element 304 sends the text and the determination unit 303 determine it is described each crucial
The corresponding picture of word, so that the social networking application of terminal shows the text and the corresponding picture of each keyword at the same time.With
Need to be manually word figure in the prior art, cause figure inefficiency to be compared, it is provided in an embodiment of the present invention to match somebody with somebody for word
The device of figure, can be automatically word figure, so as to improve as the efficiency of word figure.
Alternatively, it is provided in an embodiment of the present invention for text refering to Figure 11 on the basis of the corresponding embodiments of above-mentioned Figure 10
In another embodiment of the device of word figure, the keyword resolution unit 302 includes：
Subelement 3021 is analyzed, for analyzing noun, verb and adjective in the text as characteristic key words；
First determination subelement 3022, for the spy analyzed according to statistics strategy from the analysis subelement 3021
Levy and at least one keyword is determined in keyword.
Alternatively, it is provided in an embodiment of the present invention for text refering to Figure 12 on the basis of the corresponding embodiments of above-mentioned Figure 10
In another embodiment of the device of word figure, the determination unit 303 includes：
Second determination subelement 3031, for from keyword dictionary, determining that first is pre- respectively for each keyword
Put quantity similar key；
3rd determination subelement 3032, for from the correspondence of picture and similar key, being determined for described second
Each similar key that subelement 3031 determines determines the second preset quantity pictures respectively；
First cross-matched subelement 3033, for corresponding second determination subelement 3032 of same keyword is true
The product pictures of the second fixed preset quantity and first preset quantity are preset with the first of the same keyword respectively
Quantity similar key carries out cross-matched, calculates the corresponding each similar key of the same keyword and each figure
The similarity value of piece；
First choice subelement 3034, for selecting the first cross-matched subelement for each similar key
Output picture of the picture of the 3033 similarity maximums calculated as each similar key；
Second selection subelement 3035, for being selected for the same keyword from the first choice subelement 3034
First preset quantity output picture in select at least one as picture corresponding with each keyword.
Alternatively, it is provided in an embodiment of the present invention for text refering to Figure 13 on the basis of the corresponding embodiments of above-mentioned Figure 10
In another embodiment of the device of word figure, the determination unit 303 includes：
4th determination subelement 3036, for from the correspondence of picture and keyword, dividing for each keyword
Que Ding not the 3rd preset quantity pictures；
Second cross-matched subelement 3037, for each keyword to be determined son with the respective described 4th respectively
Definite the 3rd preset quantity pictures of unit 3036 carry out cross-matched, calculate each keyword with it is described every
The similarity value of pictures；
3rd selection subelement 3038, for selecting second cross-matched from the 3rd preset quantity pictures
The similarity value that subelement 3037 calculates sorts preceding at least pictures according to size order, as with it is described each
The corresponding picture of keyword.
Refering to Figure 14, an embodiment of terminal 40 provided in an embodiment of the present invention includes：
Receiving unit 401, the text inputted for receiving user by social networking application platform；
Transmitting element 402, for sending the text of the reception of receiving unit 401 to server, so that the clothes
At least one keyword of the business device in the text determines the corresponding picture of the text；
The receiving unit 401, is additionally operable to receive the text and the picture that the server is sent；
Display unit 403, shows the text that the receiving unit 402 receives at the same time on the social networking application platform
With the picture.
Alternatively, on the basis of the corresponding embodiments of above-mentioned Figure 14, refering to Figure 15, terminal provided in an embodiment of the present invention
In 40 another embodiment, the terminal 40 further includes：Unit 404 is deleted,
The receiving unit 401, is additionally operable to receive deletion instruction of the user at least pictures in the picture；
The deletion unit 404, the deletion for being received according to the receiving unit 401 instruct, described in deletion extremely
Few at least pictures.
Figure 16 is the structure diagram of server of the embodiment of the present invention 30.Server 30 may include input equipment 310, output
Equipment 320, processor 330 and memory 340.
Memory 340 can include read-only storage and random access memory, and provide instruction sum number to processor 330
According to.The a part of of memory 340 can also include nonvolatile RAM (NVRAM).
Memory 340 stores following element, executable modules or data structures, either their subset or
Their superset:
Operational order：Including various operational orders, various operations are used for realization.
Operating system：Including various system programs, various basic businesses and the hardware based task of processing are used for realization.
In embodiments of the present invention, processor 330 is by calling operational order (operational order that memory 340 stores
It is storable in operating system), perform following operation：
The text sent by social networking application platform is received by input equipment 310；
At least one keyword is extracted from the text；
From the correspondence of picture and keyword, determine corresponding with each keyword at least one keyword
Picture；
The text and the corresponding picture of each keyword are sent by output equipment 320, so that the social activity of terminal
Using showing the text and each corresponding picture of keyword at the same time.
In the embodiment of the present invention, server 30 can be the word figure delivered on social networking application platform, it is not necessary to user
Manual figure, improves figure efficiency.
Processor 330 controls the operation of server 30, and processor 330 can also be known as CPU (Central Processing
Unit, central processing unit).Memory 340 can include read-only storage and random access memory, and to processor 330
Instruction and data is provided.The a part of of memory 340 can also include nonvolatile RAM (NVRAM).Specifically
Application in, the various components of server 30 are coupled by bus system 350, wherein bus system 350 except includes count
Outside bus, power bus, controlling bus and status signal bus in addition etc. can also be included.But for the sake of clear explanation,
Various buses are all designated as bus system 350 in figure.
The method that the embodiments of the present invention disclose can be applied in processor 330, or be realized by processor 330.
Processor 330 is probably a kind of IC chip, has the disposal ability of signal.During realization, the above method it is each
Step can be completed by the integrated logic circuit of the hardware in processor 330 or the instruction of software form.Above-mentioned processing
Device 330 can be general processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), ready-made programmable gate array
(FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.Can realize or
Person performs disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can be microprocessor or
Person's processor can also be any conventional processor etc..The step of method with reference to disclosed in the embodiment of the present invention, can be straight
Connect and be presented as that hardware decoding processor performs completion, or performed with the hardware in decoding processor and software module combination
Into.Software module can be located at random access memory, and flash memory, read-only storage, programmable read only memory or electrically-erasable can
In the storage medium of this areas such as programmable memory, register maturation.The storage medium is located at memory 340, and processor 330 is read
Information in access to memory 340, with reference to the step of its hardware completion above method.
Alternatively, noun, verb and the adjectives that the processor is analyzed specifically for 330 in the text are used as special
Keyword is levied, at least one keyword is determined from the characteristic key words according to statistics strategy.
Alternatively, the processor 330 is specifically used for：
From keyword dictionary, the first preset quantity similar key is determined respectively for each keyword, it is described
Keyword dictionary is established using super-network sorting technique；
It is that each similar key determines the second preset quantity respectively from the correspondence of picture and similar key
Picture；
The product pictures of corresponding second preset quantity of same keyword and first preset quantity are distinguished
Cross-matched is carried out with the first preset quantity similar key of the same keyword, calculates the same keyword pair
The similarity value of each similar key answered and each pictures；
Output of the picture of similarity maximum as each similar key is selected for each similar key
Picture；
Selected for the same keyword from first preset quantity output picture at least one as with institute
State the corresponding picture of each keyword.
Alternatively, the processor 330 is specifically used for：
From the correspondence of picture and keyword, the 3rd preset quantity figure is determined respectively for each keyword
Piece；
Each keyword is subjected to cross-matched with the respective 3rd preset quantity pictures respectively, is calculated
Each keyword and the similarity value per pictures；
Similarity value is selected from the 3rd preset quantity pictures according to preceding at least one of size order sequence
Picture, as with each corresponding picture of keyword.
7 are please referred to Fig.1, it illustrates the structure diagram of the terminal involved by the embodiment of the present invention, which can use
In the method for the contact person's addition for implementing to provide in above-described embodiment.Specifically：
Terminal 1200 can include RF (Radio Frequency, radio frequency) circuit 110, include one or more
The memory 120 of computer-readable recording medium, input unit 130, display unit 140, sensor 150, voicefrequency circuit 160,
WiFi (wireless fidelity, Wireless Fidelity) module 170, include one or the processing of more than one processing core
The component such as device 180 and power supply 190.It will be understood by those skilled in the art that the terminal structure shown in Figure 10 is not formed pair
The restriction of terminal, can include than illustrating more or fewer components, either combine some components or different component cloth
Put.Wherein：
RF circuits 110 can be used for receive and send messages or communication process in, the reception and transmission of signal, especially, by base station
After downlink information receives, transfer to one or more than one processor 180 is handled；In addition, will be related to the data sending of uplink to
Base station.In general, RF circuits 110 include but not limited to antenna, at least one amplifier, tuner, one or more oscillators, use
Family identity module (SIM) card, transceiver, coupler, LNA (Low Noise Amplifier, low-noise amplifier), duplex
Device etc..In addition, RF circuits 110 can also be communicated by wireless communication with network and other equipment.The wireless communication can make
With any communication standard or agreement, include but not limited to GSM (Global System of Mobile communication, entirely
Ball mobile communcations system), GPRS (General Packet Radio Service, general packet radio service), CDMA (Code
Division Multiple Access, CDMA), WCDMA (Wideband Code Division Multiple
Access, wideband code division multiple access), LTE (Long Term Evolution, Long Term Evolution), Email, SMS (Short
Messaging Service, Short Message Service) etc..
Memory 120 can be used for storage software program and module, and processor 180 is stored in memory 120 by operation
Software program and module, so as to perform various functions application and data processing.Memory 120 can mainly include storage journey
Sequence area and storage data field, wherein, storing program area can storage program area, the application program (ratio needed at least one function
Such as sound-playing function, image player function) etc.；Storage data field can be stored uses created number according to terminal 1200
According to (such as voice data, phone directory etc.) etc..In addition, memory 120 can include high-speed random access memory, can also wrap
Include nonvolatile memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Correspondingly, memory 120 can also include Memory Controller, to provide processor 180 and input unit 130 to memory
120 access.
Input unit 130 can be used for the numeral or character information for receiving input, and produce and user setting and function
Control related keyboard, mouse, operation lever, optics or the input of trace ball signal.Specifically, input unit 130 may include to touch
Sensitive surfaces 131 and other input equipments 132.Touch sensitive surface 131, also referred to as touch display screen or Trackpad, collect and use
Family on it or neighbouring touch operation (such as user using any suitable object or annex such as finger, stylus in touch-sensitive table
Operation on face 131 or near touch sensitive surface 131), and corresponding attachment device is driven according to formula set in advance.It is optional
, touch sensitive surface 131 may include both touch detecting apparatus and touch controller.Wherein, touch detecting apparatus detection is used
The touch orientation at family, and the signal that touch operation is brought is detected, transmit a signal to touch controller；Touch controller is from touch
Touch information is received in detection device, and is converted into contact coordinate, then gives processor 180, and processor 180 can be received
The order sent simultaneously is performed.Furthermore, it is possible to using polytypes such as resistance-type, condenser type, infrared ray and surface acoustic waves
Realize touch sensitive surface 131.Except touch sensitive surface 131, input unit 130 can also include other input equipments 132.Specifically,
Other input equipments 132 can include but is not limited to physical keyboard, function key (such as volume control button, switch key etc.),
One or more in trace ball, mouse, operation lever etc..
Display unit 140 is available for the information and terminal 1200 for showing by information input by user or being supplied to user
Various graphical user interface, these graphical user interface can be made of figure, text, icon, video and its any combination.
Display unit 140 may include display panel 141, optionally, can use LCD (Liquid Crystal Display, liquid crystal
Show device), the form such as OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) configure display panel
141.Further, touch sensitive surface 131 can cover display panel 141, when touch sensitive surface 131 detects on it or neighbouring touches
After touching operation, processor 180 is sent to determine the type of touch event, is followed by subsequent processing type of the device 180 according to touch event
Corresponding visual output is provided on display panel 141.Although in Fig. 10, touch sensitive surface 131 and display panel 141 are conducts
Two independent components realize input and input function, but in some embodiments it is possible to by touch sensitive surface 131 and display
Panel 141 is integrated and realizes and outputs and inputs function.
Terminal 1200 may also include at least one sensor 150, such as optical sensor, motion sensor and other sensings
Device.Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein, ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 141, and proximity sensor can close display when terminal 1200 is moved in one's ear
Panel 141 and/or backlight.As one kind of motion sensor, gravity accelerometer can detect in all directions (generally
Three axis) acceleration size, size and the direction of gravity are can detect that when static, available for identification mobile phone posture application (ratio
Such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap)；Extremely
The other sensors such as the gyroscope that can also configure in terminal 1200, barometer, hygrometer, thermometer, infrared ray sensor, herein
Repeat no more.
Voicefrequency circuit 160, loudspeaker 161, microphone 162 can provide the audio interface between user and terminal 1200.Sound
The transformed electric signal of the voice data received can be transferred to loudspeaker 161, is converted to by loudspeaker 161 by frequency circuit 160
Voice signal exports；On the other hand, the voice signal of collection is converted to electric signal by microphone 162, is received by voicefrequency circuit 160
After be converted to voice data, it is such as another to be sent to through RF circuits 110 then after voice data output processor 180 is handled
Terminal, or voice data is exported to memory 120 further to handle.Voicefrequency circuit 160 is also possible that earplug is inserted
Hole, to provide the communication of peripheral hardware earphone and terminal 1200.
WiFi belongs to short range wireless transmission technology, and terminal 1200 can help user to receive and dispatch electricity by WiFi module 170
Sub- mail, browse webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Figure 10 shows
Go out WiFi module 170, but it is understood that, it is simultaneously not belonging to must be configured into for terminal 1200, completely can be according to need
To be omitted in the essential scope for do not change invention.
Processor 180 is the control centre of terminal 1200, utilizes various interfaces and each portion of connection whole mobile phone
Point, by running or performing the software program and/or module that are stored in memory 120, and call and be stored in memory 120
Interior data, perform the various functions and processing data of terminal 1200, so as to carry out integral monitoring to mobile phone.Optionally, handle
Device 180 may include one or more processing cores；Preferably, processor 180 can integrate application processor and modulation /demodulation processing
Device, wherein, application processor mainly handles operating system, user interface and application program etc., and modem processor is mainly located
Manage wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 180.
Terminal 1200 further includes the power supply 190 (such as battery) to all parts power supply, it is preferred that power supply can pass through electricity
Management system and processor 180 are logically contiguous, so as to realize management charging, electric discharge and power consumption by power-supply management system
The functions such as management.Power supply 190 can also include one or more direct current or AC power, recharging system, power supply event
Hinder the random components such as detection circuit, power supply changeover device or inverter, power supply status indicator.
Although being not shown, terminal 1200 can also include camera, bluetooth module etc., and details are not described herein.Specifically at this
In embodiment, the display unit of terminal is touch-screen display, and terminal has further included memory, and one or more than one
Program, one of them either more than one program storage in memory and be configured to by one or more than one
Reason device execution states one or more than one program includes the instruction for being used for being operated below：
Receive the text that user is inputted by social networking application platform；
The text is sent to server, so that at least one keyword of the server in the text determines
The corresponding picture of the text；
Receive the text and the picture that the server is sent；
The text and the picture are shown on the social networking application platform at the same time.
Assuming that above-mentioned is the first possible embodiment, then provided based on the first possible embodiment
Second of possible embodiment in, in the memory of the terminal, also comprising instructions for performing the following operations：
Receive deletion instruction of the user at least pictures in the picture；
Instructed according to described delete, an at least pictures described in deletion.
In conclusion terminal provided in this embodiment, the text inputted from reception user by social networking application platform, to clothes
Business device sends the text, so that at least one keyword of the server in the text determines that the text corresponds to
Picture, receive the text and the picture that the server is sent, institute shown at the same time on the social networking application platform
State text and the picture.With needing to be manually word figure in the prior art, figure inefficiency is caused to be compared, the present invention is real
The terminal of example offer is provided, can be automatically word figure, so as to improve as the efficiency of word figure.
As on the other hand, yet another embodiment of the invention additionally provides a kind of computer-readable recording medium, the computer
Readable storage medium storing program for executing can be computer-readable recording medium included in memory in above-described embodiment；Can also be single
Solely exist, without the computer-readable recording medium in supplying terminal.The computer-readable recording medium storage have one or
More than one program of person, the one or more programs are used for performing one by one or more than one processor
For the method for word figure, the described method includes：
Receive the text that user is inputted by social networking application platform；
The text is sent to server, so that at least one keyword of the server in the text determines
The corresponding picture of the text；
Receive the text and the picture that the server is sent；
The text and the picture are shown on the social networking application platform at the same time
Assuming that above-mentioned is the first possible embodiment, then provided based on the first possible embodiment
Second of possible embodiment in, it is described on the social networking application platform display at the same time show the text and the figure
After piece, the method further includes：
Receive deletion instruction of the user at least pictures in the picture；
Instructed according to described delete, an at least pictures described in deletion.
Refering to Figure 18, an embodiment of the system provided in an embodiment of the present invention for word figure includes：30 He of server
Terminal 40,
The terminal 40 is used for：The text that user is inputted by social networking application platform is received, the text is sent to server
This, so that at least one keyword of the server in the text determines the corresponding picture of the text；
The server 30 is used for：The text that is inputted by social networking application platform of user that receiving terminal is sent, from described
At least one keyword is extracted in text, from the correspondence of picture and keyword, is determined and at least one keyword
In each corresponding picture of keyword, send the text and the corresponding picture of each keyword to the terminal；
The terminal 40 is used for：The text and the picture that the server is sent are received, in the social networking application
The text and the picture are shown on platform at the same time.
System provided in an embodiment of the present invention for word figure, the text that user can be inputted on social networking application platform
Word carries out figure, so as to improve the efficiency of figure.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
To instruct relevant hardware to complete by program, which can be stored in a computer-readable recording medium, storage
Medium can include：ROM, RAM, disk or CD etc..
Method server, terminal and the system for word figure provided above the embodiment of the present invention has carried out in detail
Thin to introduce, specific case used herein is set forth the principle of the present invention and embodiment, and above example is said
It is bright to be only intended to help the method and its core concept for understanding the present invention；Meanwhile for those of ordinary skill in the art, foundation
The thought of the present invention, there will be changes in specific embodiments and applications, in conclusion this specification content is not
It is interpreted as limitation of the present invention.
Claims (13)
- A kind of 1. method for word figure, it is characterised in that including：The text sent by social networking application platform is received, the social networking application platform is the social activity that can deliver word and picture Application platform；At least one keyword is extracted from the text；From the correspondence of picture and keyword, picture corresponding with least one keyword is determined, the picture is Matched from extension picture library, the extension picture library includes the picture with word tag and the figure using the word tag The picture that piece is expanded in a manner of scheming to search figure；The text and the corresponding picture are sent, so that the social networking application of terminal shows the text and the correspondence at the same time Picture.
- 2. according to the method described in claim 1, it is characterized in that, described extract at least one keyword from the text, Including：Noun, verb and the adjective in the text are analyzed as characteristic key words；At least one keyword is determined from the characteristic key words according to statistics strategy.
- 3. method according to claim 1 or 2, it is characterised in that it is described from the correspondence of picture and keyword, really Fixed picture corresponding with each keyword at least one keyword, including：From keyword dictionary, the first preset quantity similar key is determined respectively for each keyword；It is that each similar key determines the second preset quantity figure respectively from the correspondence of picture and similar key Piece；By the product pictures of corresponding second preset quantity of same keyword and first preset quantity respectively with institute The the first preset quantity similar key for stating same keyword carries out cross-matched, and it is corresponding to calculate the same keyword The similarity value of each similar key and each pictures；Output picture of the picture of similarity maximum as each similar key is selected for each similar key；Selected for the same keyword from first preset quantity output picture at least one as with it is described every The corresponding picture of a keyword.
- 4. method according to claim 1 or 2, it is characterised in that it is described from the correspondence of picture and keyword, really Fixed picture corresponding with each keyword at least one keyword, including：From the correspondence of picture and keyword, the 3rd preset quantity pictures are determined respectively for each keyword；Each keyword is subjected to cross-matched with the respective 3rd preset quantity pictures respectively, is calculated described Each keyword and the similarity value per pictures；Similarity value is selected to sort preceding at least pictures according to size order from the 3rd preset quantity pictures, As with each corresponding picture of keyword.
- A kind of 5. method for word figure, it is characterised in that including：The text that user is inputted by social networking application platform is received, the social networking application platform is that can deliver word and picture Social networking application platform；The text is sent to server, so that described at least one keyword of the server in the text determine The corresponding picture of text, the picture are matched from extension picture library, and the extension picture library is included with word tag Picture and the picture that is expanded in a manner of scheming to search figure of picture using the word tag；Receive the text and the picture that the server is sent；The text and the picture are shown on the social networking application platform at the same time.
- 6. according to the method described in claim 5, it is characterized in that, described shown on the social networking application platform shows at the same time After the text and the picture, the method further includes：Receive deletion instruction of the user at least pictures in the picture；Instructed according to described delete, an at least pictures described in deletion.
- A kind of 7. server, it is characterised in that including：Receiving unit, for receiving the text sent by social networking application platform, the social networking application platform is that can deliver text The social networking application platform of word and picture；Keyword resolution unit, for extracting at least one keyword from the text that the receiving unit receives；Determination unit, for from the correspondence of picture and keyword, determining what is extracted with the keyword resolution unit Each corresponding picture of keyword at least one keyword, the picture is matched from extension picture library, described What extension picture library was expanded including the picture with word tag and using the picture of the word tag in a manner of scheming to search figure Picture；Transmitting element, for the corresponding picture for sending the text and the determination unit determines, so that the society of terminal Application is handed over to show the text and the corresponding picture of each keyword at the same time.
- 8. server according to claim 7, it is characterised in that the keyword resolution unit includes：Subelement is analyzed, for analyzing noun, verb and adjective in the text as characteristic key words；First determination subelement, for according to true in the tactful characteristic key words analyzed from the analysis subelement of statistics Fixed at least one keyword.
- 9. the server according to claim 7 or 8, it is characterised in that the determination unit includes：Second determination subelement, for from keyword dictionary, the first preset quantity to be determined respectively for each keyword Similar key, the keyword dictionary are established using super-network sorting technique；3rd determination subelement, for from the correspondence of picture and similar key, being that second determination subelement is true Fixed each similar key determines the second preset quantity pictures respectively；First cross-matched subelement, second for corresponding second determination subelement of same keyword to be determined are preset The product pictures of the quantity and first preset quantity similar pass of the first preset quantity to the same keyword respectively Keyword carries out cross-matched, calculates the similarity of the corresponding each similar key of the same keyword and each pictures Value；First choice subelement, selects the first cross-matched subelement to calculate for each similar key Output picture of the picture of similarity maximum as each similar key；Second selection subelement, it is described first pre- for being selected for the same keyword from the first choice subelement Put and at least one is selected in quantity output picture as picture corresponding with each keyword.
- 10. the server according to claim 7 or 8, it is characterised in that the determination unit includes：4th determination subelement, for from the correspondence of picture and keyword, the is determined for each keyword respectively Three preset quantity pictures；Second cross-matched subelement, for each keyword to be determined with respective 4th determination subelement respectively The 3rd preset quantity pictures carry out cross-matched, it is similar with the often pictures to calculate each keyword Angle value；3rd selection subelement, based on selecting the second cross-matched subelement from the 3rd preset quantity pictures The similarity value calculated is according to the preceding at least pictures of size order sequence, as each right with each keyword The picture answered.
- A kind of 11. terminal, it is characterised in that including：Receiving unit, the text inputted for receiving user by social networking application platform, the social networking application platform are to send out The social networking application platform of table word and picture；Transmitting element, for sending the text of the receiving unit reception to server, so that the server is according to institute State at least one keyword in text and determine the corresponding picture of the text, the picture is matched from extension picture library , the extension picture library is included the picture with word tag and is expanded using the picture of the word tag in a manner of scheming to search figure The picture of exhibition；The receiving unit, is additionally operable to receive the text and the picture that the server is sent；Display unit, shows the text of the receiving unit reception and the figure at the same time on the social networking application platform Piece.
- 12. terminal according to claim 11, it is characterised in that the terminal further includes：Delete unit,The receiving unit, is additionally operable to receive deletion instruction of the user at least pictures in the picture；The deletion unit, for the deletion instruction received according to the receiving unit, an at least pictures described in deletion.
- A kind of 13. system for word figure, it is characterised in that including：Server and terminal,The server is any servers of the claims 7-10；The terminal is the terminal described in the claims 11 or 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410485930.0A CN104239535B (en) | 2014-09-22 | 2014-09-22 | A kind of method, server, terminal and system for word figure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410485930.0A CN104239535B (en) | 2014-09-22 | 2014-09-22 | A kind of method, server, terminal and system for word figure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104239535A CN104239535A (en) | 2014-12-24 |
| CN104239535B true CN104239535B (en) | 2018-04-27 |
Family
ID=52227594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410485930.0A Active CN104239535B (en) | 2014-09-22 | 2014-09-22 | A kind of method, server, terminal and system for word figure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239535B (en) |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618223B (en) | 2015-01-20 | 2017-09-26 | 腾讯科技（深圳）有限公司 | A kind of management method of information recommendation, device and system |
| CN106033467A (en) * | 2015-03-20 | 2016-10-19 | 腾讯科技（深圳）有限公司 | Image file sharing method and device |
| CN104765472B (en) * | 2015-04-20 | 2018-06-05 | 百度在线网络技术（北京）有限公司 | Input the methods of exhibiting and device of information |
| CN104965921A (en) * | 2015-07-10 | 2015-10-07 | 陈包容 | Information matching method |
| CN105138498A (en) * | 2015-08-03 | 2015-12-09 | 小米科技有限责任公司 | Character information output method and apparatus |
| US10063751B2 (en) * | 2015-09-24 | 2018-08-28 | Qualcomm Incorporated | System and method for accessing images with a captured query image |
| CN105956008A (en) * | 2016-04-21 | 2016-09-21 | 深圳市金立通信设备有限公司 | Picture management method and terminal |
| CN106201184A (en) * | 2016-06-29 | 2016-12-07 | 腾讯科技（深圳）有限公司 | Edit methods, device and the terminal of a kind of SNS message |
| CN107784041A (en) * | 2016-08-31 | 2018-03-09 | 北京国双科技有限公司 | Judgement document's case by acquisition methods and device |
| CN106528588A (en) * | 2016-09-14 | 2017-03-22 | 厦门幻世网络科技有限公司 | Method and apparatus for matching resources for text information |
| CN106899755B (en) * | 2017-01-18 | 2021-02-23 | 宇龙计算机通信科技(深圳)有限公司 | Information sharing method, information sharing device and terminal |
| CN106844677A (en) * | 2017-01-24 | 2017-06-13 | 宇龙计算机通信科技(深圳)有限公司 | A kind of method and device of Information Sharing |
| 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 |
| CN107122492A (en) * | 2017-05-19 | 2017-09-01 | 北京金山安全软件有限公司 | Lyric generation method and device based on picture content |
| CN107748779A (en) * | 2017-10-20 | 2018-03-02 | 百度在线网络技术（北京）有限公司 | information generating method and device |
| CN108287916B (en) * | 2018-02-11 | 2021-06-15 | 北京方正阿帕比技术有限公司 | Resource recommendation method |
| CN108733779B (en) * | 2018-05-04 | 2022-10-04 | 百度在线网络技术（北京）有限公司 | Text matching method and device |
| CN110674388A (en) * | 2018-07-03 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Mapping method and device for push item, storage medium and terminal equipment |
| CN110866086A (en) * | 2018-12-29 | 2020-03-06 | 北京安妮全版权科技发展有限公司 | Article matching system |
| CN109814733B (en) * | 2019-01-08 | 2022-11-08 | 百度在线网络技术（北京）有限公司 | Input-based recommendation information generation method and device |
| CN109933681A (en) * | 2019-03-19 | 2019-06-25 | 深圳Tcl新技术有限公司 | Image searching method, device and computer readable storage medium |
| CN110096641A (en) * | 2019-03-19 | 2019-08-06 | 深圳壹账通智能科技有限公司 | Picture and text matching process, device, equipment and storage medium based on image analysis |
| CN112737919A (en) * | 2019-10-29 | 2021-04-30 | 上海连尚网络科技有限公司 | Instant message sending method and device |
| CN111640025B (en) * | 2020-06-09 | 2023-08-01 | 国泰君安证券股份有限公司 | Method for realizing information labeling processing based on label system |
| CN115981536A (en) * | 2020-09-04 | 2023-04-18 | Oppo广东移动通信有限公司 | Multimedia data display method and device, electronic equipment 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 |
| CN112256907B (en) * | 2020-11-17 | 2024-04-16 | 携程计算机技术（上海）有限公司 | Travel attack editing method, system, equipment and storage medium based on photo library |
| CN113342179A (en) * | 2021-05-26 | 2021-09-03 | 北京百度网讯科技有限公司 | Input text processing method and device, electronic equipment and storage medium |
| CN115298660A (en) * | 2022-07-01 | 2022-11-04 | 富途网络科技(深圳)有限公司 | Information mapping method, apparatus, medium, and program product based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458695A (en) * | 2008-12-18 | 2009-06-17 | 西交利物浦大学 | Mixed picture index construct and enquiry method based on key word and content characteristic and use thereof |
| CN102385578A (en) * | 2010-08-27 | 2012-03-21 | 腾讯科技（深圳）有限公司 | Picture searching method and device |
| CN103853421A (en) * | 2012-11-29 | 2014-06-11 | 北京千橡网景科技发展有限公司 | Method and equipment for character and picture mixed input |
| CN103970745A (en) * | 2013-01-27 | 2014-08-06 | 上海尤兰达张信息科技有限公司 | Method and system for generating cartoon works by network writings in real time |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8166418B2 (en) * | 2006-05-26 | 2012-04-24 | Zi Corporation Of Canada, Inc. | Device and method of conveying meaning |
| KR20110087620A (en) * | 2010-01-26 | 2011-08-03 | 광주과학기술원 | Layout based page recognition method for printed medium |
| CN102902771A (en) * | 2012-09-27 | 2013-01-30 | 百度国际科技（深圳）有限公司 | Method, device and server for searching pictures |
| TWI501172B (en) * | 2012-12-04 | 2015-09-21 | Inst Information Industry | System, method and storage medium for publishing a message on a social network website according to an image |
-
2014
- 2014-09-22 CN CN201410485930.0A patent/CN104239535B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458695A (en) * | 2008-12-18 | 2009-06-17 | 西交利物浦大学 | Mixed picture index construct and enquiry method based on key word and content characteristic and use thereof |
| CN102385578A (en) * | 2010-08-27 | 2012-03-21 | 腾讯科技（深圳）有限公司 | Picture searching method and device |
| CN103853421A (en) * | 2012-11-29 | 2014-06-11 | 北京千橡网景科技发展有限公司 | Method and equipment for character and picture mixed input |
| CN103970745A (en) * | 2013-01-27 | 2014-08-06 | 上海尤兰达张信息科技有限公司 | Method and system for generating cartoon works by network writings in real time |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104239535A (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104239535B (en) | A kind of method, server, terminal and system for word figure | |
| CN104618440B (en) | Smart machine control method and device | |
| CN104112213B (en) | The method and device of recommendation information | |
| CN106227774B (en) | Information search method and device | |
| CN109783798A (en) | Method, apparatus, terminal and the storage medium of text information addition picture | |
| CN104516887B (en) | A kind of web data searching method, device and system | |
| CN110472145A (en) | A kind of content recommendation method and electronic equipment | |
| CN104182488A (en) | Search method, server and client | |
| CN105005563B (en) | A kind of abstraction generating method and device | |
| CN110166828A (en) | A kind of method for processing video frequency and device | |
| CN110019840B (en) | Method, device and server for updating entities in knowledge graph | |
| CN107729815A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN108255954A (en) | Using search method, device, storage medium and terminal | |
| CN108205408B (en) | Message display method and device | |
| CN107545404A (en) | Bill based reminding method and device | |
| CN107402964A (en) | A kind of information recommendation method, server and terminal | |
| CN107329985A (en) | A kind of collecting method of the page, device and mobile terminal | |
| CN104063400B (en) | Data search method and data search device | |
| CN108492836A (en) | A kind of voice-based searching method, mobile terminal and storage medium | |
| CN110276010A (en) | A kind of weight model training method and relevant apparatus | |
| CN108256100A (en) | A kind of information search method, mobile terminal and Cloud Server | |
| CN110162653A (en) | A kind of picture and text sort recommendations method and terminal device | |
| CN108205568A (en) | Method and device based on label selection data | |
| CN107908770A (en) | A kind of photo searching method and mobile terminal | |
| CN110471589A (en) | Information display method and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |