CN106355429A - Image material recommendation method and device - Google Patents

Image material recommendation method and device Download PDF

Info

Publication number
CN106355429A
CN106355429A CN201610676576.9A CN201610676576A CN106355429A CN 106355429 A CN106355429 A CN 106355429A CN 201610676576 A CN201610676576 A CN 201610676576A CN 106355429 A CN106355429 A CN 106355429A
Authority
CN
China
Prior art keywords
advertising image
image material
key word
recommendation
recommended
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610676576.9A
Other languages
Chinese (zh)
Inventor
吴宏刚
闫铭
陆子龙
张卫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiaomi Mobile Software Co Ltd
Original Assignee
Beijing Xiaomi Mobile Software Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Xiaomi Mobile Software Co Ltd filed Critical Beijing Xiaomi Mobile Software Co Ltd
Priority to CN201610676576.9A priority Critical patent/CN106355429A/en
Publication of CN106355429A publication Critical patent/CN106355429A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a image material recommendation method and device, comprising: acquiring a text information entered by the users; generating a keyword associated with the text information; acquiring the recommended advertisement image material according to the keyword; and outputs the recommended advertisement image material. The image material recommendation method and device can recommend the advertisement material material to the user according to the text information input by the user, and provides the user with more reference material, thus improving the efficiency and effect of advertisement delivery.

Description

The recommendation method and device of picture material
Technical field
It relates to field of computer technology, particularly to a kind of recommendation method and device of picture material.
Background technology
With the continuous development of network technology, the Internet has become as requisite a kind of letter in people's live and work Breath communication media.Therefore, a lot of advertisers can be by the advertisement putting of oneself product in the Internet.The advertisement of product can include A lot of materials, such as text material, picture material and sound material etc..Wherein, the click to advertisement for the picture material of advertisement Rate has large effect, and attractive image can guide more users to click on advertisement, increases the clicking rate of advertisement.
At present, some advertisers, when throwing in the advertisement of some products, typically by investigation and can only rely on oneself The advertisement putting of these products for advertisement selection picture material to be thrown in, and is gone out by experience by advertising platform.Cause This, require a great deal of time so that the inefficiency of advertisement putting in the selection of picture material, and effect is poor.
Content of the invention
In order to solve above-mentioned technical problem, the disclosure provides a kind of recommendation method and device of picture material.
According to the embodiment of the present disclosure in a first aspect, provide a kind of picture material recommendation method, comprising:
Obtain the text message of user input；
Generate the key word with described associate text information；
The advertising image material recommended is obtained according to described key word；
Export the advertising image material of described recommendation.
Optionally, the described key word generating with described associate text information, comprising:
The relative words set with described associate text information is obtained from the relative words set prestoring；
The word that relative words set with described associate text information is included is as described key word.
Optionally, the described key word generating with described associate text information, comprising:
Obtain the topic model of training in advance；
Described text message is inputted described topic model, to generate Topic word as described key word.
Optionally, the described advertising image material obtaining recommendation according to described key word, comprising:
Crawled from internet with the advertising image material of described key word association as pushing away using spiders technology The advertising image material recommended.
Optionally, the described advertising image material obtaining recommendation according to described key word, comprising:
Using in the advertising image pre-building material database with the advertising image material of described Keywords matching as recommending Advertising image material.
Optionally, methods described also includes:
Obtain the historical search record data in internet；
Multiple relative words set are generated based on described historical search record data；
The multiple relative words set generating are stored.
Optionally, described based on described historical search record data generate multiple relative words set, comprising:
Classification process is carried out to described historical search record data using simrank algorithm, to generate multiple related datas Set.
Optionally it is characterised in that methods described also includes:
Obtain with reference to advertising image material and the described reference corresponding key word of advertising image material；
Store described with being associated with corresponding key word with reference to advertising image material, to set up advertising image material Storehouse.
Optionally, the described advertising image material exporting described recommendation, comprising:
Respectively the advertising image material of described recommendation is input to the advertising image material Evaluation Model on Quality of training in advance, To obtain the corresponding quality scale of advertising image material of described recommendation；
By the advertising image material of described recommendation, according to quality scale, order from high to low is ranked up；
Export the advertising image material of described recommendation according to described sequence.
According to the second aspect of the embodiment of the present disclosure, provide a kind of recommendation apparatus of picture material, comprising:
First acquisition module, is configured to obtain the text message of user input；
Generation module, is configurable to generate the key word with described associate text information；
Second acquisition module, is configured to obtain, according to described key word, the advertising image material recommended；
Output module, is configured to export the advertising image material of described recommendation.
Optionally, described generation module includes:
First acquisition submodule, is configured to obtain from the relative words set prestoring and described associate text information Relative words set；
Determination sub-module, be configured to word that the relative words set with described associate text information is included as Described key word.
Optionally, described generation module includes:
Second acquisition submodule, is configured to obtain the topic model of training in advance；
Generate submodule, be configured to by described text message input described topic model, using generate Topic word as Described key word.
Optionally, described second acquisition module includes:
Crawl submodule, be configured to crawl from internet and described key word association using spiders technology Advertising image material is as the advertising image material recommended.
Optionally, described second acquisition module includes:
Recommend submodule, be configured to the advertisement with described Keywords matching in the advertising image pre-building material database Picture material is as the advertising image material recommended.
Optionally, described device also includes:
3rd acquisition module, is configured to obtain the historical search record data in internet；
Set generation module, is configured to generate multiple relative words set based on described historical search record data；
Memory module, is configured to be stored the multiple relative words set generating.
Optionally, described set generation module includes:
Process submodule, be configured to carry out classification process using simrank algorithm to described historical search record data, To generate multiple related data set.
Optionally, described device also includes:
4th acquisition module, is configured to obtain with reference to advertising image material and described reference advertising image material correspondence Key word；
Set up module, be configured to store described with being associated with corresponding key word with reference to advertising image material, To set up advertising image material database.
Optionally, described output module includes:
Input submodule, is configured to the advertising image material of described recommendation is input to the advertisement figure of training in advance Pixel material Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of described recommendation；
Sorting sub-module, be configured to by the advertising image material of described recommendation according to quality scale order from high to low It is ranked up；
Output sub-module, is configured to export the advertising image material of described recommendation according to described sequence.
According to the third aspect of the embodiment of the present disclosure, provide a kind of recommendation apparatus of picture material, comprising:
Processor；
For storing the memorizer of processor executable；
Wherein, described processor is configured to:
Obtain the text message of user input；
Generate the key word with described associate text information；
The advertising image material recommended is obtained according to described key word；
Export the advertising image material of described recommendation.
The technical scheme that embodiment of the disclosure provides can include following beneficial effect:
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtaining the text envelope of user input Breath, generates the key word with text information association, obtains, according to this key word, the advertising image material recommended, and exports recommendation Advertising image material.So as to the text message according to user input, to user's recommended advertisements picture material, it is that user carries For more with reference to material, improve efficiency and the effect of advertisement putting.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, can obtain the text envelope of user input Breath, obtains the relative words set with above-mentioned associate text information from the relative words set prestoring, will be with text information The word that the relative words set of association includes, as key word, obtains, according to this key word, the advertising image material recommended, And export the advertising image material of recommendation.So as to the text message according to user input, to user's recommended advertisements image element Material, provides the user more reference materials, is favorably improved efficiency and the effect of advertisement putting.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, can obtain the text envelope of user input Breath, then obtain the topic model of training in advance, above-mentioned text message is inputted this topic model, to generate Topic word as pass Keyword, obtains, according to this key word, the advertising image material recommended, and exports the advertising image material of recommendation.So as to basis The text message of user input, to user's recommended advertisements picture material, provides the user more reference materials, is favorably improved The efficiency of advertisement putting and effect.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtaining the text envelope of user input Breath, generates the key word with text information association, is crawled using spiders technology and close with this key word from internet The advertising image material of connection is as the advertising image material recommended, and exports the advertising image material of recommendation.So as to basis The text message of user input, obtains recommended advertisements picture material from more rich advertising image material, and recommends to user Advertising image material, provides the user more reference materials further, and improves efficiency and the effect of advertisement putting.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtaining the text envelope of user input Breath, generates and the key word of text information association, by the advertising image pre-building material database with above-mentioned Keywords matching Advertising image material as the advertising image material recommended, and export the advertising image material of recommendation.So as to according to The text message of family input, obtains the recommended advertisements picture material of better quality, and to user's recommended advertisements picture material, is use Family provides more reference materials, and further increases efficiency and the effect of advertisement putting.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by based on the historical search note getting Record data genaration multiple relative words set, then obtain the text message of user input, obtain from the relative words set prestoring Take the relative words set with associate text information, the word that the relative words set with associate text information is included as Key word, obtains, according to this key word, the advertising image material recommended, and exports the advertising image material of recommendation.So as to root According to the text message of user input, to user's recommended advertisements picture material, provide the user more reference materials, contribute to carrying The efficiency of high advertisement putting and effect.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtain with reference to advertising image material with And with reference to the corresponding key word of advertising image material, will deposit with being associated with corresponding key word with reference to advertising image material Storage, to set up advertising image material database.Obtain the text message of user input again, generate the key with text information association Word, and using in the above-mentioned advertising image material database pre-building with the advertising image material of above-mentioned Keywords matching as recommending Advertising image material, the advertising image material that output is recommended.So as to the text message according to user input, recommend to user Advertising image material, provides the user more reference materials, has been favorably improved efficiency and the effect of advertisement putting.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, according to quality scale order from high to low The advertising image material of the recommendation getting is ranked up, and the advertising image material recommended according to above-mentioned sequence output.From And user priority can be made to see the higher advertising image material of quality, and provide the user more reference materials, further Improve efficiency and the effect of advertisement putting.
It should be appreciated that above general description and detailed description hereinafter are only exemplary and explanatory, not The disclosure can be limited.
Brief description
Accompanying drawing herein is merged in description and constitutes the part of this specification, shows the enforcement meeting the disclosure Example, and be used for explaining the principle of the disclosure together with description.
Fig. 1 is a kind of flow chart of the recommendation method of picture material according to an exemplary embodiment for the disclosure；
Fig. 2 is the flow chart of the recommendation method of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 3 is the flow chart of the recommendation method of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 4 is a kind of block diagram of the recommendation apparatus of picture material according to an exemplary embodiment for the disclosure；
Fig. 5 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 6 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 7 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 8 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Fig. 9 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Figure 10 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Figure 11 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Figure 12 is the block diagram of the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure；
Figure 13 is that an a kind of structure of the recommendation apparatus of picture material according to an exemplary embodiment for the disclosure is shown It is intended to.
Specific embodiment
Here will in detail exemplary embodiment be illustrated, its example is illustrated in the accompanying drawings.Explained below is related to During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they be only with such as appended The example of the consistent apparatus and method of some aspects being described in detail in claims, the disclosure.
The term using in the disclosure is the purpose only merely for description specific embodiment, and is not intended to be limiting the disclosure. " a kind of ", " described " and " being somebody's turn to do " of singulative used in disclosure and the accompanying claims book is also intended to including most Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein refers to and wraps Containing one or more associated any or all possible combination listing project.
It will be appreciated that though various information may be described using term first, second, third, etc. in the disclosure, but this A little information should not necessarily be limited by these terms.These terms are only used for same type of information is distinguished from each other out.For example, without departing from In the case of disclosure scope, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ... When " or " in response to determining ".Term " longitudinal ", " horizontal ", " on ", D score, "front", "rear", "left", "right", " vertical ", " water Flat ", " top ", " bottom " " interior ", the orientation of instruction such as " outward " or position relationship be based on orientation shown in the drawings or position relationship, only It is for the ease of the description disclosure and to simplify description, rather than the device of instruction or hint indication or element must have specifically Orientation, with specific azimuth configuration and operation, therefore it is not intended that restriction of this disclosure.
It should be noted that unless otherwise prescribed and limit, should be interpreted broadly term " installation ", " being connected ", " connection ", For example, it may be mechanically connected or electrical connection or two element internals connection, can be joined directly together it is also possible to It is indirectly connected to by intermediary, for the ordinary skill in the art, described art can be understood as the case may be The concrete meaning of language.
As shown in figure 1, Fig. 1 is a kind of flow process of the recommendation method of the picture material according to an exemplary embodiment Figure, the method can apply in terminal unit or server.It will be understood by those skilled in the art that this terminal unit is permissible The including but not limited to mobile terminal device of such as smart mobile phone, panel computer, pocket computer on knee and desktop computer Etc..The method comprises the following steps:
In a step 101, obtain the text message of user input.
In general, the advertisement of product can include a lot of materials, such as text material, picture material and sound material Deng.Wherein, picture material is the material of pictorial form.In the present embodiment, when user wants to be retrieved as certain Products Show During advertising image material, need to input the text message related with this product first.For example, the title of input product, product Attribute, the feature of product, the classification of product and the brief introduction of product and description etc., to be retrieved as the advertisement of this Products Show Picture material.Therefore, above-mentioned text message is some text messages related to the corresponding product of advertisement to be put.Can manage Solution, the disclosure does not limit to the concrete form of text message and content aspect.
In a step 102, generate the key word with text information association.
In the present embodiment, can be generated and the associated plurality of key word of text information according to above-mentioned text message, These key words can be to have similar names with the said goods, or same classification, or same alike result, or has identical Or the description vocabulary of some textual forms of the product of similar features.
For example, when certain manufacturer computer wants the advertising image material that the computer being retrieved as its new release is recommended, can be first Input some text messages, these text messages can be the title of computer, or the configuration information of computer, or to electricity Information of description of new characteristic of brain etc..As it is assumed that this computer employs certain advanced technology improves display screen and show Effect, then the text message inputting can be the title of this advanced technology or display screen improve after effect description Etc..Then, some key words can be generated according to these text messages, these key words can be the computer product of other classes Some vocabulary is described, e.g., other has the title of the computers of similar configuration, or the letter of other computer using similar techniques Jie's key vocabularies etc..It is appreciated that above-mentioned key word can be the vocabulary being arbitrarily associated with text information, the disclosure pair The concrete form of above-mentioned key word and content and quantitative aspects do not limit.
In one implementation, the phase with above-mentioned associate text information can be obtained from the relative words set prestoring Close lexical set, and the word that the relative words set with text information association is included is as above-mentioned key word.
Specifically, it is possible, firstly, to being pre-created and storing multiple relative words set, wrap in each relative words set Containing multiple related vocabulary, these vocabulary can have associated relation in terms of certain attribute.As same related term collects Vocabulary in conjunction could be for describing the vocabulary of same or similar attribute things.Because each vocabulary may be with multiple attribute sides Face is relevant, therefore, can also include identical vocabulary in different relative words set, in other words, same vocabulary can Multiple relative words set can be corresponded to.For example, relative words set a can include the various vocabulary for describing color, its In can include " red ", relative words set b can include the various vocabulary for describing dress ornament, wherein can also include " red ".
Then, the relative words set with above-mentioned associate text information can be obtained from the relative words set prestoring. Wherein, can be to comprise to decompose out at least from above-mentioned text message with the relative words set of above-mentioned associate text information The set of one emphasis vocabulary.Specifically, first above-mentioned text message can be carried out with semantic parsing and sentence decomposes, to decompose Go out the emphasis vocabulary that one or more text packets contain, then, search from the relative words set prestoring and comprise at least The set of one above-mentioned emphasis vocabulary, as the relative words set with above-mentioned associate text information.
For example, it is assumed that the emphasis vocabulary of above-mentioned text message includes a, b, c, the relative words set a prestoring includes vocabulary L, o, j, h, g, a, relative words set b includes vocabulary h, b, r, f, c, relative words set c include vocabulary i, t, d, x, d, e, F, relative words set d includes vocabulary q, p, n.Then from the foregoing, it will be observed that relative words set a includes the emphasis vocabulary of text message A, relative words set b include emphasis vocabulary b, c of text message, do not include text message in relative words set c and d Emphasis vocabulary, hence, it can be determined that relative words set a and relative words set b is related to above-mentioned associate text information Lexical set.
Finally, all relative words unions of sets with associate text information are concentrated all words including as with upper State the key word of associate text information.
The topic model of training in advance in another kind of implementation, can also be obtained, should by the input of above-mentioned text message Topic model, to generate Topic word as key word.
Specifically, it is possible, firstly, to obtain the good topic model of training in advance, can obtain from locally stored data This topic model is it is also possible to obtain this topic model from other terminals or server.This topic model can be by originally setting Standby training or miscellaneous equipment training.The disclosure does not limit to the source aspect of this topic model.
In the present embodiment, topic model can be trained in the following way: obtain some text sentence samples, and obtain Take these corresponding Topic words of text sentence sample.Then, using these text sentence samples and corresponding Topic word, Training obtains topic model.For example, it is possible to these text sentence samples are inputted topic model to be trained, special obtained by calculating Value indicative, the eigenvalue obtaining is compared with the eigenvalue of these corresponding Topic words of text sentence sample, with poor Value function, and treat the parameter of training topic model and be adjusted, repeat above-mentioned training process, until the difference functions that obtain are received Till holding back.
Then, above-mentioned text message can be inputted the topic model that this trains, this topic model is to above-mentioned text envelope Breath carries out Treatment Analysis, obtains the eigenvalue of corresponding Topic word, and generates corresponding Topic word as key word.
In step 103, the advertising image material recommended is obtained according to above-mentioned key word.
In the present embodiment, some advertising image elements related to above-mentioned key word can be obtained according to above-mentioned key word Material, as the advertising image material recommended.The advertising image material related to above-mentioned key word can once be used in network The related advertising image material of the key word to above-mentioned at least predetermined number crossed.
For example, it is assumed that above-mentioned key word includes 3 key words, then can preset above-mentioned predetermined number is 1, or 2, Or 3.When predetermined number is 1, the advertising image material related to above-mentioned key word can be any with above-mentioned key word One, or any two, or the advertising image material that whole key word is related.When predetermined number is 2, with above-mentioned key The related advertising image material of word can be and any two in above-mentioned key word, or the advertising image that whole key word is related Material.When predetermined number be 3 when, the advertising image material related to above-mentioned key word can be with above-mentioned key word in all close The related advertising image material of keyword.It is appreciated that the disclosure is not to limiting in this respect.
In one implementation, can be crawled from internet using spiders technology wide with crucial word association Accuse picture material as the advertising image material recommended.
For example, specifically, spiders technology can be adopted, according to predetermined rule, extract from internet The webpage of the key word of existing above-mentioned at least predetermined number.Then, obtain advertisement related web page from above-mentioned webpage, and from advertisement phase Close in webpage and extract corresponding advertising image material, as the advertising image material recommended.
In another kind of implementation, can be by the advertisement with Keywords matching in the advertising image pre-building material database Picture material is as the advertising image material recommended.
Specifically, can according to above-mentioned key word, from the advertising image material database pre-building search with above-mentioned to The advertising image material of the Keywords matching of few predetermined number, and using the advertising image finding out material as the advertisement figure recommended Pixel material.
In the present embodiment, advertising image material database can be set up in the following way: it is possible, firstly, to obtain existing one A little higher advertising image materials of quality and corresponding key word, using these advertising image materials as with reference to advertising image element Material.Then, will store with being associated with reference to advertising image material and corresponding key word, to generate advertising image material database. And, can also continue to obtain the higher reference advertising image material of more multimass and corresponding key word, and associatedly deposit Store up in advertising image material database, to supplement to advertising image material database.
At step 104, the advertising image material that output is recommended.
In the present embodiment, after getting the advertising image material of recommendation, need the advertising image material recommended output, With for reference.In general it is recommended that advertising image material quality may uneven, so, be more desirable to quality Preferably advertising image material preferential recommendation, to user, makes user priority see the high advertising image material of quality.Therefore, it can First the quality of the advertising image material recommended is estimated, and the advertising image material recommended according to the result output of assessment.
Specifically, it is possible, firstly, to respectively the advertising image material of recommendation be input to the advertising image element of training in advance In material Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of recommendation.As can be by advertisement to be assessed Picture material is input to the advertising image material Evaluation Model on Quality of training in advance, and advertising image material Evaluation Model on Quality is permissible Feature extraction and classification are carried out to advertising image material to be assessed, thus quality is carried out to advertising image material to be assessed commenting Estimate.Then, by the advertising image material of recommendation, according to quality scale, order from high to low is ranked up.And according to above-mentioned sequence The advertising image material that output is recommended.
In the present embodiment, advertising image material Evaluation Model on Quality can be trained in the following way: firstly, it is necessary to pre- The first collection sample of advertising image material and corresponding quality scale, with the sample of advertising image material that collects and right The quality scale answered continually enters treats training pattern, and constantly adjusts the parameter of this model, until this model can compare accurately The sample evaluating advertising image material quality scale, thus training obtain advertising image material Evaluation Model on Quality.When So, any other method training advertising image material Evaluation Model on Quality that is as known in the art and being likely to occur in the future The disclosure can be applied to, the disclosure trains the concrete mode aspect of advertising image material Evaluation Model on Quality not limit to it Fixed.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtaining the text envelope of user input Breath, generates the key word with text information association, obtains, according to this key word, the advertising image material recommended, and exports recommendation Advertising image material.So as to the text message according to user input, to user's recommended advertisements picture material, it is that user carries For more with reference to material, improve efficiency and the effect of advertisement putting.
As shown in Fig. 2 the flow process of the recommendation method of another kind of picture material according to an exemplary embodiment for the Fig. 2 Figure, this embodiment describes the process generating with the key word of associate text information in detail, and the method can apply to terminal and sets In standby or server, comprise the following steps:
In step 201, obtain the historical search record data in internet.
In the present embodiment, the historical search record data of part or all of user can be collected from internet, should When historical search record data can be by arbitrarily searching for, the historical record data staying.
In step 202., multiple relative words set are generated based on historical search record data.
In the present embodiment, multiple relative words set can be generated based on above-mentioned historical search record data.Specifically come Say, classification process can be carried out to historical search record data using simrank algorithm, to generate multiple related data set.
Wherein, simrank algorithm is that a kind of topology information based on figure is similar to weigh object in structural context The pervasive algorithm of degree, is intuitively meant that the similarity calculating other relevant objects using the similarity of existing object. Using the core concept that simrank algorithm tries to achieve similarity it is: if two objects and (be them cited in similar object Have and similar enter adjacent side structure), then this two objects are also similar.
It is appreciated that using other modes multiple relative words set can also generate, as known in the art and Any other being likely to occur in the future can be answered based on the method that historical search record data generates multiple relative words set For the disclosure, the disclosure is not to limiting in this respect.
In step 203, the multiple relative words set generating are stored.
In step 204, obtain the text message of user input.
In step 205, obtain the relative words set with associate text information from the relative words set prestoring.
In step 206, the word relative words set with associate text information being included is as key word.
In step 207, the advertising image material recommended is obtained according to above-mentioned key word.
In a step 208, the advertising image material that output is recommended.
It should be noted that for identical step in Fig. 1 embodiment, no longer gone to live in the household of one's in-laws on getting married in above-mentioned Fig. 2 embodiment State, related content can be found in Fig. 1 embodiment.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by based on the historical search note getting Record data genaration multiple relative words set, then obtain the text message of user input, obtain from the relative words set prestoring Take the relative words set with associate text information, the word that the relative words set with associate text information is included as Key word, obtains, according to this key word, the advertising image material recommended, and exports the advertising image material of recommendation.So as to root According to the text message of user input, to user's recommended advertisements picture material, provide the user more reference materials, contribute to carrying The efficiency of high advertisement putting and effect.
As shown in figure 3, Fig. 3 is the flow process of the recommendation method of another kind of picture material according to an exemplary embodiment Figure, this embodiment describes the process obtaining the advertising image material recommended according to key word in detail, and the method can apply to In terminal unit or server, comprise the following steps:
In step 301, obtain with reference to advertising image material and with reference to the corresponding key word of advertising image material.
In step 302, will store with being associated with corresponding key word with reference to advertising image material, to set up advertisement Picture material storehouse.
In the present embodiment, it is possible, firstly, to obtain the higher advertising image material of some quality existing and corresponding Key word, using these advertising image materials as with reference to advertising image material.Then, will be with reference to advertising image material and corresponding Key word stores with being associated, to generate advertising image material database.And, can also continue to obtain the higher ginseng of more multimass Examine advertising image material and corresponding key word, and associatedly store in advertising image material database, with to advertising image element Material storehouse is supplemented.
In step 303, obtain the text message of user input.
In step 304, generate the key word with text information association.
In step 305, by the advertisement figure with above-mentioned Keywords matching in the above-mentioned advertising image material database pre-building Pixel material is as the advertising image material recommended.
Within step 306, the advertising image material that output is recommended.
It should be noted that for identical step in Fig. 1 embodiment, no longer gone to live in the household of one's in-laws on getting married in above-mentioned Fig. 3 embodiment State, related content can be found in Fig. 1 embodiment.
The recommendation method of the picture material that above-described embodiment of the disclosure provides, by obtain with reference to advertising image material with And with reference to the corresponding key word of advertising image material.To deposit with being associated with corresponding key word with reference to advertising image material Storage, to set up advertising image material database.Obtain the text message of user input again, generate the key with text information association Word, and using in the above-mentioned advertising image material database pre-building with the advertising image material of above-mentioned Keywords matching as recommending Advertising image material, the advertising image material that output is recommended.So as to the text message according to user input, recommend to user Advertising image material, provides the user more reference materials, has been favorably improved efficiency and the effect of advertisement putting.
Although it should be noted that describe the operation of method of disclosure in the accompanying drawings with particular order, this does not require that Or hint must execute these operations according to this particular order, or having to carry out all shown operation just enables the phase The result hoped.On the contrary, the step described in flow chart can change execution sequence.Additionally or alternatively, it is convenient to omit some Step, multiple steps is merged into a step execution, and/or a step is decomposed into execution of multiple steps.
Corresponding with the recommendation embodiment of the method for aforementioned picture material, the disclosure additionally provides the recommendation apparatus of picture material Embodiment.
As shown in figure 4, Fig. 4 is a kind of recommendation apparatus frame of picture material according to an exemplary embodiment for the disclosure Figure, this device includes: the first acquisition module 401, generation module 402, the second acquisition module 403 and output module 404.
Wherein, the first acquisition module 401, is configured to obtain the text message of user input.
In general, the advertisement of product can include a lot of materials, such as text material, picture material and sound material Deng.Wherein, picture material is the material of pictorial form.In the present embodiment, when user wants to be retrieved as certain Products Show During advertising image material, need to input the text message related with this product first.For example, the title of input product, product Attribute, the feature of product, the classification of product and the brief introduction of product and description etc., to be retrieved as the advertisement of this Products Show Picture material.Therefore, above-mentioned text message is some text messages related to the corresponding product of advertisement to be put.Can manage Solution, the disclosure does not limit to the concrete form of text message and content aspect.
Generation module 402, is configurable to generate the key word with associate text information.
In the present embodiment, can be generated and the associated plurality of key word of text information according to above-mentioned text message, These key words can be to have similar names with the said goods, or same classification, or same alike result, or has identical Or the description vocabulary of some textual forms of the product of similar features.
In one implementation, the phase with above-mentioned associate text information can be obtained from the relative words set prestoring Close lexical set, and the word that the relative words set with text information association is included is as above-mentioned key word.
The topic model of training in advance in another kind of implementation, can also be obtained, should by the input of above-mentioned text message Topic model, to generate Topic word as key word.
Second acquisition module 403, is configured to obtain, according to above-mentioned key word, the advertising image material recommended.
In the present embodiment, some advertising image elements related to above-mentioned key word can be obtained according to above-mentioned key word Material, as the advertising image material recommended.The advertising image material related to above-mentioned key word can once be used in network The related advertising image material of the key word to above-mentioned at least predetermined number crossed.
In one implementation, can be crawled from internet using spiders technology wide with crucial word association Accuse picture material as the advertising image material recommended.
In another kind of implementation, can be by the advertisement with Keywords matching in the advertising image pre-building material database Picture material is as the advertising image material recommended.
Output module 404, is configured to export the advertising image material recommended.
In the present embodiment, after getting the advertising image material of recommendation, need the advertising image material recommended output, With for reference.In general it is recommended that advertising image material quality may uneven, so, be more desirable to quality Preferably advertising image material preferential recommendation, to user, makes user see the quality of the high advertising image material of quality at first.Cause This, can first be estimated to the quality of the advertising image material recommended, and the advertisement figure recommended according to the result output of assessment Pixel material.
Specifically, it is possible, firstly, to respectively the advertising image material of recommendation be input to the advertising image element of training in advance In material Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of recommendation.As can be by advertisement to be assessed Picture material is input to the advertising image material Evaluation Model on Quality of training in advance, and advertising image material Evaluation Model on Quality is permissible Feature extraction and classification are carried out to advertising image material to be assessed, thus quality is carried out to advertising image material to be assessed commenting Estimate.Then, by the advertising image material of recommendation, according to quality scale, order from high to low is ranked up.And according to above-mentioned sequence The advertising image material that output is recommended.
As seen from the above-described embodiment, this embodiment can be generated and the text by obtaining the text message of user input The key word of information association, obtains, according to this key word, the advertising image material recommended, and exports the advertising image material of recommendation. So as to the text message according to user input, to user's recommended advertisements picture material, provide the user more reference elements Material, improves efficiency and the effect of advertisement putting.
As shown in figure 5, Fig. 5 is the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure Block diagram, on the basis of aforementioned embodiment illustrated in fig. 4, generation module 402 may include that the first acquisition submodule to this embodiment 501 and determination sub-module 502.
Wherein, the first acquisition submodule 501, is configured to obtain and above-mentioned text envelope from the relative words set prestoring The relative words set of breath association.
Determination sub-module 502, the word being configured to include the relative words set with text information association is made For key word.
In the present embodiment, it is possible, firstly, to being pre-created and storing multiple relative words set, each relative words set In comprise the vocabulary of multiple correlations, these vocabulary can have associated relation in terms of certain attribute.Because each vocabulary can Can be relevant with multiple attribute aspects, therefore, in different relative words set, identical vocabulary can also be included, for changing It, same vocabulary likely corresponds to multiple relative words set.
Then, the relative words set with above-mentioned associate text information can be obtained from the relative words set prestoring. Wherein, can be to comprise to decompose out at least from above-mentioned text message with the relative words set of above-mentioned associate text information The set of one emphasis vocabulary.Specifically, first above-mentioned text message can be carried out with semantic parsing and sentence decomposes, to decompose Go out the emphasis vocabulary that one or more text packets contain, then, search from the relative words set prestoring and comprise at least The set of one above-mentioned emphasis vocabulary, as the relative words set with above-mentioned associate text information.
Finally, all relative words unions of sets with associate text information are concentrated all words including as with upper State the key word of associate text information.
As seen from the above-described embodiment, this embodiment can obtain the text message of user input, from the relative words prestoring The relative words set with above-mentioned associate text information is obtained, by the relative words set with text information association in set Including word as key word, the advertising image material recommended is obtained according to this key word, and exports the advertising image of recommendation Material.So as to the text message according to user input, to user's recommended advertisements picture material, provide the user more ginsengs Examine material, be favorably improved efficiency and the effect of advertisement putting.
As shown in fig. 6, Fig. 6 is the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure Block diagram, on the basis of aforementioned embodiment illustrated in fig. 4, generation module 402 may include that the second acquisition submodule to this embodiment 601 and generate submodule 602.
Wherein, the second acquisition submodule 601, is configured to obtain the topic model of training in advance.
In the present embodiment, the good topic model of training in advance can be obtained, can obtain from locally stored data This topic model is it is also possible to obtain this topic model from other terminals or server.This topic model can be by originally setting Standby training or miscellaneous equipment training.The disclosure does not limit to the source aspect of this topic model.
In the present embodiment, topic model can be trained in the following way: obtain some text sentence samples, and obtain Take these corresponding Topic words of text sentence sample.Then, using these text sentence samples and corresponding Topic word, Training obtains topic model.For example, it is possible to these text sentence samples are inputted topic model to be trained, special obtained by calculating Value indicative, the eigenvalue obtaining is compared with the eigenvalue of these corresponding Topic words of text sentence sample, with poor Value function, and treat the parameter of training topic model and be adjusted, repeat above-mentioned training process, until the difference functions that obtain are received Till holding back.
Generate submodule 602, be configured to for above-mentioned text message to input this topic model, using generate Topic word as Key word.
In the present embodiment, above-mentioned text message can be inputted the topic model that this trains, this topic model is to upper State text message and carry out Treatment Analysis, obtain the eigenvalue of corresponding Topic word, and generate corresponding Topic word as pass Keyword.
As seen from the above-described embodiment, this embodiment can obtain the text message of user input, then obtains training in advance Topic model, above-mentioned text message is inputted this topic model, to generate Topic word as key word, is obtained according to this key word Take the advertising image material of recommendation, and export the advertising image material of recommendation.So as to the text message according to user input, To user's recommended advertisements picture material, provide the user more reference materials, be favorably improved efficiency and the effect of advertisement putting Really.
As shown in fig. 7, Fig. 7 is the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure Block diagram, on the basis of aforementioned embodiment illustrated in fig. 4, the second acquisition module 403 may include that and crawls submodule this embodiment 701.
Wherein, crawl submodule 701, be configured to crawl from internet and above-mentioned key using spiders technology The advertising image material of word association is as the advertising image material recommended.
In the present embodiment, spiders technology can be adopted, according to predetermined rule, extract from internet and occur The webpage of the key word of above-mentioned at least predetermined number.Then, obtain advertisement related web page from above-mentioned webpage, and related from advertisement Corresponding advertising image material is extracted, as the advertising image material recommended in webpage.
As seen from the above-described embodiment, this embodiment can be generated and the text by obtaining the text message of user input The key word of information association, crawls the advertising image material with this crucial word association using spiders technology from internet As the advertising image material recommended, and export the advertising image material of recommendation.So as to the text envelope according to user input Breath, obtains recommended advertisements picture material from more rich advertising image material, and to user's recommended advertisements picture material, enters one Step provides the user more reference materials, and improves efficiency and the effect of advertisement putting.
As shown in figure 8, Fig. 8 is the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure Block diagram, on the basis of aforementioned embodiment illustrated in fig. 4, the second acquisition module 403 may include that recommendation submodule to this embodiment 801.
Wherein it is recommended that submodule 801, be configured to by the advertising image pre-building material database with above-mentioned key word The advertising image material joined is as the advertising image material recommended.
In the present embodiment, can according to above-mentioned key word, from the advertising image material database pre-building search with upper State the advertising image material of at least Keywords matching of predetermined number, and the advertising image finding out material is wide as recommend Accuse picture material.
As seen from the above-described embodiment, this embodiment can be generated and the text by obtaining the text message of user input The key word of information association, the advertising image material with above-mentioned Keywords matching in the advertising image pre-building material database is made For the advertising image material recommended, and export the advertising image material of recommendation.So as to the text message according to user input, Obtain the recommended advertisements picture material of better quality, and to user's recommended advertisements picture material, provide the user more references Material, and further increase efficiency and the effect of advertisement putting.
As shown in figure 9, Fig. 9 is the recommendation apparatus of another kind of picture material according to an exemplary embodiment for the disclosure Block diagram, on the basis of aforementioned embodiment illustrated in fig. 5, this device can further include this embodiment: the 3rd acquisition module 405, gather generation module 406 and memory module 407.
Wherein, the 3rd acquisition module 405, is configured to obtain the historical search record data in internet.
In the present embodiment, the historical search record data of part or all of user can be collected from internet, should When historical search record data can be by arbitrarily searching for, the historical record data staying.
Set generation module 406, is configured to generate multiple relative words set based on historical search record data.
In the present embodiment, multiple relative words set can be generated based on above-mentioned historical search record data.Specifically come Say, classification process can be carried out to historical search record data using simrank algorithm, to generate multiple related data set.
Memory module 407, is configured to be stored the multiple relative words set generating.
As seen from the above-described embodiment, this embodiment can be multiple by being generated based on the historical search record data getting Relative words set, then obtain the text message of user input, obtain from the relative words set prestoring and close with text message Connection relative words set, the word that the relative words set with associate text information is included as key word, according to this Key word obtains the advertising image material recommended, and exports the advertising image material of recommendation.So as to according to user input Text message, to user's recommended advertisements picture material, provides the user more reference materials, is favorably improved advertisement putting Efficiency and effect.
As shown in Figure 10, Figure 10 is the recommendation dress of another kind of picture material according to an exemplary embodiment for the disclosure Put block diagram, on the basis of aforementioned embodiment illustrated in fig. 9, set generation module 406 may include that process submodule to this embodiment 1001.
Wherein, process submodule 1001, be configured to using simrank algorithm, above-mentioned historical search record data be carried out Classification is processed, to generate multiple related data set.
As seen from the above-described embodiment, this embodiment is passed through to generate multiple related data set using simrank algorithm, improves Generate the efficiency of related data set.
As shown in figure 11, Figure 11 is the recommendation dress of another kind of picture material according to an exemplary embodiment for the disclosure Put block diagram, on the basis of aforementioned embodiment illustrated in fig. 6, this device can further include this embodiment: the 4th acquisition mould Block 408 and set up module 409.
Wherein, the 4th acquisition module 408, is configured to obtain with reference to advertising image material and with reference to advertising image material Corresponding key word.
Set up module 409, be configured to store with being associated with corresponding key word with reference to advertising image material, with Set up advertising image material database.
In the present embodiment, it is possible, firstly, to obtain the higher advertising image material of some quality existing and corresponding Key word, using these advertising image materials as with reference to advertising image material.Then, will be with reference to advertising image material and corresponding Key word stores with being associated, to generate advertising image material database.And, can also continue to obtain the higher ginseng of more multimass Examine advertising image material and corresponding key word, and associatedly store in advertising image material database, with to advertising image element Material storehouse is supplemented.
As seen from the above-described embodiment, this embodiment is passed through to obtain with reference to advertising image material and with reference to advertising image material Corresponding key word, will be stored with corresponding key word with reference to advertising image material with being associated, to set up advertising image element Material storehouse.Obtain the text message of user input again, generate the key word with text information association, and above-mentioned by pre-build With the advertising image material of above-mentioned Keywords matching as the advertising image material recommended in advertising image material database, output is recommended Advertising image material.So as to the text message according to user input, to user's recommended advertisements picture material, it is that user carries For more with reference to material, efficiency and the effect of advertisement putting have been favorably improved it.
As shown in figure 12, Figure 12 is the recommendation dress of another kind of picture material according to an exemplary embodiment for the disclosure Put block diagram, this embodiment on the basis of aforementioned embodiment illustrated in fig. 4, output module 404, may include that input submodule 1201, sorting sub-module 1202 and output sub-module 1203.
Wherein, input submodule 1201, are configured to for the advertising image material of recommendation to be input to training in advance Advertising image material Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of recommendation.
In the present embodiment, respectively the advertising image material of recommendation can be input to the advertising image material of training in advance In Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of recommendation.As can be by advertisement figure to be assessed Pixel material is input to the advertising image material Evaluation Model on Quality of training in advance, and advertising image material Evaluation Model on Quality can be right Advertising image material to be assessed carries out feature extraction and classification, thus carry out quality to advertising image material to be assessed commenting Estimate.
In the present embodiment, advertising image material Evaluation Model on Quality can be trained in the following way: firstly, it is necessary to pre- The first collection sample of advertising image material and corresponding quality scale, with the sample of advertising image material that collects and right The quality scale answered continually enters treats training pattern, and constantly adjusts the parameter of this model, until this model can compare accurately The sample evaluating advertising image material quality scale, thus training obtain advertising image material Evaluation Model on Quality.When So, any other method training advertising image material Evaluation Model on Quality that is as known in the art and being likely to occur in the future The disclosure can be applied to, the disclosure trains the concrete mode aspect of advertising image material Evaluation Model on Quality not limit to it Fixed.
Sorting sub-module 1202, be configured to by recommend advertising image material according to quality scale order from high to low It is ranked up.
Output sub-module 1203, is configured to the advertising image material recommended according to above-mentioned sequence output.
As seen from the above-described embodiment, order from high to low is wide to the recommendation getting according to quality scale for this embodiment Accuse picture material to be ranked up, and the advertising image material recommended according to above-mentioned sequence output.Such that it is able to make user priority see To the higher advertising image material of quality, and provide the user more reference materials, further increase the effect of advertisement putting Rate and effect.
It should be appreciated that said apparatus can be set in advance in terminal or server it is also possible to by download etc. mode And be loaded in terminal or server.Corresponding module in said apparatus can be mutual with the module in terminal or server Cooperation is to realize the suggested design of picture material.
For device embodiment, because it corresponds essentially to embodiment of the method, thus real referring to method in place of correlation The part applying example illustrates.Device embodiment described above is only schematically, wherein said as separating component The unit illustrating can be or may not be physically separate, as the part that unit shows can be or can also It is not physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can be according to actual Need to select the purpose to realize disclosure scheme for some or all of module therein.Those of ordinary skill in the art are not paying In the case of going out creative work, you can to understand and to implement.
Accordingly, the disclosure also provides a kind of recommendation apparatus of picture material, and this device includes processor；For storing The memorizer of processor executable；Wherein, this processor is configured to:
Obtain the text message of user input；
Generate the key word with described associate text information；
The advertising image material recommended is obtained according to described key word；
Export the advertising image material of described recommendation.
Figure 13 is an a kind of structural representation of the recommendation apparatus 9900 of the picture material according to an exemplary embodiment Figure.For example, device 9900 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, put down Board device, armarium, body-building equipment, personal digital assistant etc..
With reference to Figure 13, device 9900 can include following one or more assemblies: process assembly 9902, memorizer 9904, Power supply module 9906, multimedia groupware 9908, audio-frequency assembly 9910, the interface 9912 of input/output (i/o), sensor cluster 9914, and communication component 9916.
The integrated operation of the usual control device 9900 of process assembly 9902, such as with display, call, data communication, Camera operation and record operate associated operation.Treatment element 9902 can include one or more processors 9920 to execute Instruction, to complete all or part of step of above-mentioned method.Additionally, process assembly 9902 can include one or more moulds Block, is easy to the interaction between process assembly 9902 and other assemblies.For example, process assembly 9902 can include multi-media module, To facilitate the interaction between multimedia groupware 9908 and process assembly 9902.
Memorizer 9904 is configured to store various types of data to support the operation in device 9900.These data Example include on device 9900 operation any application program or method instruction, contact data, telephone book data, Message, picture, video etc..Memorizer 9904 can by any kind of volatibility or non-volatile memory device or they Combination is realized, such as static RAM (sram), Electrically Erasable Read Only Memory (eeprom), erasable can Program read-only memory (eprom), programmable read only memory (prom), read only memory (rom), magnetic memory, flash memory Reservoir, disk or CD.
Power supply module 9906 provides electric power for the various assemblies of device 9900.Power supply module 9906 can include power management System, one or more power supplys, and other generate, manage and distribute, with for device 9900, the assembly that electric power is associated.
Multimedia groupware 9908 includes the screen of one output interface of offer between described device 9900 and user.? In some embodiments, screen can include liquid crystal display (lcd) and touch panel (tp).If screen includes touch panel, Screen may be implemented as touch screen, to receive the input signal from user.Touch panel includes one or more touch and passes Sensor is with the gesture on sensing touch, slip and touch panel.Described touch sensor can not only sensing touch or slip be dynamic The border made, but also the detection persistent period related to described touch or slide and pressure.In certain embodiments, many Media component 9908 includes a front-facing camera and/or post-positioned pick-up head.When device 9900 is in operator scheme, such as shoot mould When formula or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each preposition shooting Head and post-positioned pick-up head can be the optical lens system of a fixation or have focusing and optical zoom capabilities.
Audio-frequency assembly 9910 is configured to output and/or input audio signal.For example, audio-frequency assembly 9910 includes a wheat Gram wind (mic), when device 9900 is in operator scheme, such as call model, logging mode and speech recognition mode when, mike quilt It is configured to receive external audio signal.The audio signal being received can be further stored in memorizer 9904 or via communication Assembly 9916 sends.In certain embodiments, audio-frequency assembly 9910 also includes a speaker, for exports audio signal.
I/o interface 9912 is for providing interface, above-mentioned peripheral interface module between process assembly 9902 and peripheral interface module Can be keyboard, click wheel, button etc..These buttons may include but be not limited to: home button, volume button, start button and Locking press button.
Sensor cluster 9914 includes one or more sensors, for providing the state of various aspects to comment for device 9900 Estimate.For example, sensor cluster 9914 can detect/the closed mode of opening of device 9900, the relative localization of assembly, such as institute State the display that assembly is device 9900 and keypad, sensor cluster 9914 can be with detection means 9900 or device 9,900 1 The position change of individual assembly, user is presence or absence of with what device 9900 contacted, device 9900 orientation or acceleration/deceleration and dress Put 9900 temperature change.Sensor cluster 9914 can include proximity transducer, is configured to do not having any physics The presence of object nearby is detected during contact.Sensor cluster 9914 can also include optical sensor, such as cmos or ccd image sensing Device, for using in imaging applications.In certain embodiments, this sensor cluster 9914 can also include acceleration sensing Device, gyro sensor, Magnetic Sensor, pressure transducer, microwave remote sensor or temperature sensor.
Communication component 9916 is configured to facilitate the communication of wired or wireless way between device 9900 and other equipment.Dress Put 9900 and can access wireless network based on communication standard, such as wifi, 2g or 3g, or combinations thereof.Exemplary at one In embodiment, communication component 9916 receives related from the broadcast singal of external broadcasting management system or broadcast via broadcast channel Information.In one exemplary embodiment, described communication component 9916 also includes near-field communication (nfc) module, to promote short distance Communication.For example, RF identification (rfid) technology, Infrared Data Association (irda) technology, ultra broadband can be based in nfc module (uwb) technology, bluetooth (bt) technology and other technologies are realizing.
In the exemplary embodiment, device 9900 can be by one or more application specific integrated circuits (asic), numeral Signal processor (dsp), digital signal processing appts (dspd), PLD (pld), field programmable gate array (fpga), controller, microcontroller, microprocessor or other electronic components are realized, for executing said method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided As included the memorizer 9904 instructing, above-mentioned instruction can be executed by the processor 9920 of device 9900 to complete said method.Example If, described non-transitorycomputer readable storage medium can be rom, random access memory (ram), cd-rom, tape, soft Disk and optical data storage devices etc..
Those skilled in the art, after considering description and putting into practice invention disclosed herein, will readily occur to its of the disclosure Its embodiment.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or Person's adaptations are followed the general principle of the disclosure and are included the undocumented common knowledge in the art of the disclosure Or conventional techniques.Description and embodiments be considered only as exemplary, the true scope of the disclosure and spirit by following Claim is pointed out.
It should be appreciated that the disclosure is not limited to be described above and precision architecture illustrated in the accompanying drawings, and And various modifications and changes can carried out without departing from the scope.The scope of the present disclosure only to be limited by appended claim.

Claims (19)

1. a kind of recommendation method of picture material is it is characterised in that methods described includes:
Obtain the text message of user input；
Generate the key word with described associate text information；
The advertising image material recommended is obtained according to described key word；
Export the advertising image material of described recommendation.
2. method according to claim 1 is it is characterised in that the key word of described generation and described associate text information, Including:
The relative words set with described associate text information is obtained from the relative words set prestoring；
The word that relative words set with described associate text information is included is as described key word.
3. method according to claim 1 is it is characterised in that the key word of described generation and described associate text information, Including:
Obtain the topic model of training in advance；
Described text message is inputted described topic model, to generate Topic word as described key word.
4. method according to claim 1 is it is characterised in that described obtain, according to described key word, the advertising image recommended Material, comprising:
Using spiders technology crawl from internet with described key word association advertising image material as recommend Advertising image material.
5. method according to claim 1 is it is characterised in that described obtain, according to described key word, the advertising image recommended Material, comprising:
Using in the advertising image pre-building material database with the advertising image material of described Keywords matching as the advertisement recommended Picture material.
6. method according to claim 2 is it is characterised in that methods described also includes:
Obtain the historical search record data in internet；
Multiple relative words set are generated based on described historical search record data；
The multiple relative words set generating are stored.
7. method according to claim 6 it is characterised in that described based on described historical search record data generate multiple Relative words set, comprising:
Classification process is carried out to described historical search record data using simrank algorithm, to generate multiple related data set.
8. method according to claim 5 is it is characterised in that methods described also includes:
Obtain with reference to advertising image material and the described reference corresponding key word of advertising image material；
Store described with being associated with corresponding key word with reference to advertising image material, to set up advertising image material database.
9. method according to claim 1 is it is characterised in that the advertising image material of the described recommendation of described output, comprising:
Respectively the advertising image material of described recommendation is input to the advertising image material Evaluation Model on Quality of training in advance, to obtain Take the corresponding quality scale of advertising image material of described recommendation；
By the advertising image material of described recommendation, according to quality scale, order from high to low is ranked up；
Export the advertising image material of described recommendation according to described sequence.
10. a kind of recommendation apparatus of picture material are it is characterised in that described device includes:
First acquisition module, is configured to obtain the text message of user input；
Generation module, is configurable to generate the key word with described associate text information；
Second acquisition module, is configured to obtain, according to described key word, the advertising image material recommended；
Output module, is configured to export the advertising image material of described recommendation.
11. devices according to claim 10 are it is characterised in that described generation module includes:
First acquisition submodule, is configured to acquisition from the relative words set prestoring related to described associate text information Lexical set；
Determination sub-module, is configured to the word that includes the relative words set with described associate text information as described Key word.
12. devices according to claim 10 are it is characterised in that described generation module includes:
Second acquisition submodule, is configured to obtain the topic model of training in advance；
Generate submodule, be configured to for described text message to input described topic model, to generate Topic word as described Key word.
13. devices according to claim 10 are it is characterised in that described second acquisition module includes:
Crawl submodule, be configured to crawl the advertisement with described key word association from internet using spiders technology Picture material is as the advertising image material recommended.
14. devices according to claim 10 are it is characterised in that described second acquisition module includes:
Recommend submodule, be configured to the advertising image with described Keywords matching in the advertising image pre-building material database Material is as the advertising image material recommended.
15. devices according to claim 11 are it is characterised in that described device also includes:
3rd acquisition module, is configured to obtain the historical search record data in internet；
Set generation module, is configured to generate multiple relative words set based on described historical search record data；
Memory module, is configured to be stored the multiple relative words set generating.
16. devices according to claim 15 are it is characterised in that described set generation module includes:
Process submodule, be configured to carry out classification process using simrank algorithm to described historical search record data, with life Become multiple related data set.
17. devices according to claim 14 are it is characterised in that described device also includes:
4th acquisition module, is configured to obtain with reference to advertising image material and the described reference corresponding pass of advertising image material Keyword；
Set up module, be configured to store described with being associated with corresponding key word with reference to advertising image material, to build Vertical advertising image material database.
18. devices according to claim 10 are it is characterised in that described output module includes:
Input submodule, is configured to the advertising image material of described recommendation is input to the advertising image element of training in advance Material Evaluation Model on Quality, to obtain the corresponding quality scale of advertising image material of described recommendation；
Sorting sub-module, is configured to that order from high to low is carried out according to quality scale by the advertising image material of described recommendation Sequence；
Output sub-module, is configured to export the advertising image material of described recommendation according to described sequence.
A kind of 19. recommendation apparatus of picture material are it is characterised in that include:
Processor；
For storing the memorizer of processor executable；
Wherein, described processor is configured to:
Obtain the text message of user input；
Generate the key word with described associate text information；
The advertising image material recommended is obtained according to described key word；
Export the advertising image material of described recommendation.
CN201610676576.9A 2016-08-16 2016-08-16 Image material recommendation method and device Pending CN106355429A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610676576.9A CN106355429A (en) 2016-08-16 2016-08-16 Image material recommendation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610676576.9A CN106355429A (en) 2016-08-16 2016-08-16 Image material recommendation method and device

Publications (1)

Publication Number Publication Date
CN106355429A true CN106355429A (en) 2017-01-25

Family

ID=57844914

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610676576.9A Pending CN106355429A (en) 2016-08-16 2016-08-16 Image material recommendation method and device

Country Status (1)

Country Link
CN (1) CN106355429A (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107562963A (en) * 2017-10-12 2018-01-09 杭州群核信息技术有限公司 A kind of method and apparatus screened house ornamentation design and render figure
WO2018145590A1 (en) * 2017-02-13 2018-08-16 腾讯科技（深圳）有限公司 Emoticon picture recommendation method and device, server cluster and storage medium
CN108415961A (en) * 2018-02-06 2018-08-17 厦门集微科技有限公司 A kind of advertising pictures recommendation method and device
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
CN109783798A (en) * 2018-12-12 2019-05-21 平安科技（深圳）有限公司 Method, apparatus, terminal and the storage medium of text information addition picture
CN109783749A (en) * 2018-12-10 2019-05-21 深圳变设龙信息科技有限公司 A kind of Material for design intelligent recommendation method, apparatus and terminal device
CN110020200A (en) * 2019-03-15 2019-07-16 微梦创科网络科技（中国）有限公司 A kind of personalized recommendation method and system based on history material
CN110471721A (en) * 2018-05-10 2019-11-19 北京京东尚科信息技术有限公司 Page display method and system, electronic equipment and storage medium
CN110858914A (en) * 2018-08-23 2020-03-03 北京优酷科技有限公司 Video material recommendation method and device
CN111259180A (en) * 2020-01-14 2020-06-09 广州视源电子科技股份有限公司 Image pushing method and device, electronic equipment and storage medium
CN111598638A (en) * 2019-02-21 2020-08-28 北京沃东天骏信息技术有限公司 Click rate determination method, device and equipment
CN111790158A (en) * 2019-10-31 2020-10-20 厦门雅基软件有限公司 Game scene editing method and device, electronic equipment and readable storage medium
CN112256907A (en) * 2020-11-17 2021-01-22 携程计算机技术（上海）有限公司 Travel strategy editing method, system, equipment and storage medium based on photo library
CN112651332A (en) * 2020-12-24 2021-04-13 携程旅游信息技术（上海）有限公司 Scene facility identification method, system, equipment and storage medium based on photo library
CN113220917A (en) * 2020-02-06 2021-08-06 阿里巴巴集团控股有限公司 Background map recommendation method, device and storage medium
CN110580299B (en) * 2018-06-08 2023-11-07 北京京东尚科信息技术有限公司 Method, system, equipment and storage medium for generating matching diagram of recommended language of object

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6611348B1 (en) * 1999-07-30 2003-08-26 Banta Corporation System and method for communication over a TCP/IP network with an appletalk network for publishing and printing services
US6738155B1 (en) * 1999-07-30 2004-05-18 Banta Corporation System and method of providing publishing and printing services via a communications network
CN101859423A (en) * 2009-04-10 2010-10-13 索尼公司 Server apparatus, method of producing advertisement information, and program
CN103699625A (en) * 2013-12-20 2014-04-02 北京百度网讯科技有限公司 Method and device for retrieving based on keyword
CN104391942A (en) * 2014-11-25 2015-03-04 中国科学院自动化研究所 Short text characteristic expanding method based on semantic atlas

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6611348B1 (en) * 1999-07-30 2003-08-26 Banta Corporation System and method for communication over a TCP/IP network with an appletalk network for publishing and printing services
US6738155B1 (en) * 1999-07-30 2004-05-18 Banta Corporation System and method of providing publishing and printing services via a communications network
CN101859423A (en) * 2009-04-10 2010-10-13 索尼公司 Server apparatus, method of producing advertisement information, and program
CN103699625A (en) * 2013-12-20 2014-04-02 北京百度网讯科技有限公司 Method and device for retrieving based on keyword
CN104391942A (en) * 2014-11-25 2015-03-04 中国科学院自动化研究所 Short text characteristic expanding method based on semantic atlas

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018145590A1 (en) * 2017-02-13 2018-08-16 腾讯科技（深圳）有限公司 Emoticon picture recommendation method and device, server cluster and storage medium
US10824669B2 (en) 2017-02-13 2020-11-03 Tencent Technology (Shenzhen) Company Limited Sticker recommendation method and apparatus, server cluster, and storage medium
CN107562963B (en) * 2017-10-12 2021-04-20 杭州群核信息技术有限公司 Method and device for screening home decoration design rendering graph
CN107562963A (en) * 2017-10-12 2018-01-09 杭州群核信息技术有限公司 A kind of method and apparatus screened house ornamentation design and render figure
CN108415961A (en) * 2018-02-06 2018-08-17 厦门集微科技有限公司 A kind of advertising pictures recommendation method and device
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
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
CN110471721A (en) * 2018-05-10 2019-11-19 北京京东尚科信息技术有限公司 Page display method and system, electronic equipment and storage medium
CN110471721B (en) * 2018-05-10 2024-06-18 北京京东尚科信息技术有限公司 Page display method and system, electronic equipment and storage medium
CN110580299B (en) * 2018-06-08 2023-11-07 北京京东尚科信息技术有限公司 Method, system, equipment and storage medium for generating matching diagram of recommended language of object
CN110858914A (en) * 2018-08-23 2020-03-03 北京优酷科技有限公司 Video material recommendation method and device
CN110858914B (en) * 2018-08-23 2021-11-26 阿里巴巴（中国）有限公司 Video material recommendation method and device
CN109783749A (en) * 2018-12-10 2019-05-21 深圳变设龙信息科技有限公司 A kind of Material for design intelligent recommendation method, apparatus and terminal device
CN109783798A (en) * 2018-12-12 2019-05-21 平安科技（深圳）有限公司 Method, apparatus, terminal and the storage medium of text information addition picture
CN111598638A (en) * 2019-02-21 2020-08-28 北京沃东天骏信息技术有限公司 Click rate determination method, device and equipment
CN111598638B (en) * 2019-02-21 2023-11-07 北京沃东天骏信息技术有限公司 Click rate determination method, device and equipment
CN110020200A (en) * 2019-03-15 2019-07-16 微梦创科网络科技（中国）有限公司 A kind of personalized recommendation method and system based on history material
CN111790158A (en) * 2019-10-31 2020-10-20 厦门雅基软件有限公司 Game scene editing method and device, electronic equipment and readable storage medium
CN111259180B (en) * 2020-01-14 2024-04-19 广州视源电子科技股份有限公司 Image pushing method, device, electronic equipment and storage medium
CN111259180A (en) * 2020-01-14 2020-06-09 广州视源电子科技股份有限公司 Image pushing method and device, electronic equipment and storage medium
CN113220917A (en) * 2020-02-06 2021-08-06 阿里巴巴集团控股有限公司 Background map recommendation method, device and storage medium
CN113220917B (en) * 2020-02-06 2022-04-12 阿里巴巴集团控股有限公司 Background map recommendation method, device and storage medium
CN112256907A (en) * 2020-11-17 2021-01-22 携程计算机技术（上海）有限公司 Travel strategy editing method, system, equipment and storage medium based on photo library
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
CN112651332A (en) * 2020-12-24 2021-04-13 携程旅游信息技术（上海）有限公司 Scene facility identification method, system, equipment and storage medium based on photo library

Similar Documents

Publication Publication Date Title
CN106355429A (en) Image material recommendation method and device
CN106896932B (en) A kind of candidate's words recommending method and device
CN109189987A (en) Video searching method and device
CN108304441A (en) Network resource recommended method, device, electronic equipment, server and storage medium
CN110175223A (en) A kind of method and device that problem of implementation generates
CN110399548A (en) A kind of search processing method, device, electronic equipment and storage medium
CN106600331A (en) Method and apparatus for running advertisements
CN105095427A (en) Search recommendation method and device
CN106055707A (en) Bullet screen display method and device
CN104035995A (en) Method and device for generating group tags
CN106202223A (en) Content collection method, device and for collecting the device of content in application program
CN105068976A (en) Ticket information exhibition method and device
CN106789551B (en) Conversation message methods of exhibiting and device
CN107797729A (en) Method for showing interface and device
CN106126632A (en) Recommend method and device
CN107230137A (en) Merchandise news acquisition methods and device
CN105227778A (en) The method of event notification, device, terminal and server
CN105677392A (en) Method and apparatus for recommending applications
CN107045541A (en) data display method and device
CN109144285A (en) A kind of input method and device
CN105373580A (en) Method and device for displaying subjects
CN107622074A (en) A kind of data processing method, device and computing device
CN104461348A (en) Method and device for selecting information
CN107122430A (en) Search result display methods and device
US11546663B2 (en) Video recommendation method and apparatus

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170125