CN108804448A - The method and apparatus for generating information to be pushed - Google Patents

The method and apparatus for generating information to be pushed Download PDF

Info

Publication number
CN108804448A
CN108804448A CN201710293331.2A CN201710293331A CN108804448A CN 108804448 A CN108804448 A CN 108804448A CN 201710293331 A CN201710293331 A CN 201710293331A CN 108804448 A CN108804448 A CN 108804448A
Authority
CN
China
Prior art keywords
picture
pushed
materials
information
title
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
CN201710293331.2A
Other languages
Chinese (zh)
Inventor
江志敏
王修飞
陈敏
韩聪
贺登武
王鲁光
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.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology 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 Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201710293331.2A priority Critical patent/CN108804448A/en
Publication of CN108804448A publication Critical patent/CN108804448A/en
Pending legal-status Critical Current

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This application discloses the method and apparatus for generating information to be pushed.One specific implementation mode of this method includes:Obtain push material, wherein push material includes textual materials and picture materials;Core word is extracted from above-mentioned textual materials, and title to be pushed is determined based on the core word extracted;According to the correlation of above-mentioned picture materials and preset information to be pushed keyword, the picture as picture to be pushed is determined from above-mentioned picture materials;Information to be pushed is generated based on above-mentioned title to be pushed and above-mentioned picture to be pushed.The embodiment can automatically generate or optimize to information to be pushed, and then improve the validity of information push.

Description

The method and apparatus for generating information to be pushed
Technical field
This application involves field of computer technology, and in particular to technical field of data processing, more particularly to generate and wait pushing The method and apparatus of information.
Background technology
It is also known as " Web broadcast " by certain technical standard or agreement, on the internet to generate information to be pushed A technology of information overload is reduced by pushing the information that user needs.Information to be pushed technology is generated to select by active Wait for that push generates information to be pushed to user, effective information to be pushed can reduce user when searching for spent on network Between.
However, the existing usually manual setting of information to be pushed, human factor is affected, and quality is irregular, Influence the validity of information push.And manual examination and verification and optimization information to be pushed, heavy workload.Therefore, it is necessary to make full use of number According to treatment technology, information to be pushed is generated, improves the validity of information push.
Invention content
The purpose of the application is to propose a kind of improved method and apparatus for generating information to be pushed, to solve above carry on the back The technical issues of scape technology segment is mentioned.
In a first aspect, this application provides a kind of method generating information to be pushed, this method includes:Obtain push element Material, wherein push material includes textual materials and picture materials;Core word is extracted from above-mentioned textual materials, and is based on being extracted Core word determine title to be pushed;According to the correlation of above-mentioned picture materials and preset information to be pushed keyword, from upper State the picture determined in picture materials as picture to be pushed;It is generated based on above-mentioned title to be pushed and above-mentioned picture to be pushed Information to be pushed.
In some embodiments, core word is extracted from above-mentioned textual materials, and is determined based on the core word extracted and waits pushing away The title is sent to include:Core word is extracted from above-mentioned textual materials, and judges the core word and preset information to be pushed keyword Whether the degree of association is more than default degree of association threshold value;If so, generating title to be pushed according to the core word extracted;Otherwise, according to Default title generates title to be pushed.
In some embodiments, according to the meter to above-mentioned picture materials and the correlation of preset information to be pushed keyword It calculates, determines that the picture as picture to be pushed includes from above-mentioned picture materials:To the picture element in above-mentioned picture materials It is identified;Above-mentioned picture materials are cut according to the picture element identified to obtain picture to be selected;Calculate picture to be selected In picture element and preset information to be pushed keyword the degree of association;Selection include and preset information to be pushed keyword The maximum picture element of the degree of association picture to be selected be used as picture to be pushed.
In some embodiments, above-mentioned picture materials are cut according to the picture element identified to obtain picture to be selected Including:Obtain the profile that picture element is preset in picture materials;It is cut out from above-mentioned picture materials according to the pre-determined distance with contour line Default picture element is cut as picture to be selected.
In some embodiments, further include after the picture element in above-mentioned picture materials being identified:To each figure Piece material:It is overlapping to judge whether default picture element has with other picture elements;If so, accounting for default picture in response to lap The ratio of element is more than preset ratio threshold value, screens out the picture materials.
Second aspect, present invention also provides a kind of device generating information to be pushed, which includes:Acquisition module, It is configured to obtain push material, wherein push material includes textual materials and picture materials;Title determining module, configuration are used In extracting core word from above-mentioned textual materials, and title to be pushed is determined based on the core word extracted;Picture determining module, matches It sets for the correlation according to above-mentioned picture materials and preset information to be pushed keyword, is determined from above-mentioned picture materials Picture as picture to be pushed;Generation module is configured to generate based on above-mentioned title to be pushed and above-mentioned picture to be pushed Information to be pushed.
In some embodiments, title determining module is also configured to:Core word is extracted from above-mentioned textual materials, and is judged Whether the degree of association of the core word and preset information to be pushed keyword is more than default degree of association threshold value;If so, according to being carried The core word taken generates title to be pushed;Otherwise, title to be pushed is generated according to default title.
In some embodiments, picture determining module includes:Recognition unit is configured to the figure in above-mentioned picture materials Piece element is identified;Unit is cut, is configured to that above-mentioned picture materials cut according to the picture element identified To picture to be selected;Computing unit, the picture element and preset information to be pushed keyword for being configured to calculate in picture to be selected The degree of association;Determination unit is configured to selection and includes the maximum picture of the degree of association with preset information to be pushed keyword The picture to be selected of element is used as picture to be pushed.
In some embodiments, unit is cut further to be configured to:Obtain the wheel that picture element is preset in picture materials It is wide;Default picture element is cut out as picture to be selected from above-mentioned picture materials according to the pre-determined distance with contour line.
In some embodiments, picture determining module further includes screening out unit, is configured to:To each picture materials:Sentence It is overlapping whether disconnected default picture element has with other picture elements;If so, accounting for the ratio of default picture element in response to lap Example is more than preset ratio threshold value, screens out the picture materials.
The third aspect, present invention also provides a kind of computing devices, including:One or more processors;Storage device is used In the one or more programs of storage;When the one or more program is executed by said one or multiple processors so that this Or multiple processors realize above-mentioned method.
The method and apparatus provided by the present application for generating information to be pushed push material by acquisition, wherein push material Including textual materials and picture materials, then, core word is extracted from above-mentioned textual materials, and determine based on the core word extracted Title to be pushed, then the correlation according to above-mentioned picture materials and preset information to be pushed keyword, plain from above-mentioned picture The picture as picture to be pushed is determined in material, is then based on above-mentioned title to be pushed and above-mentioned picture to be pushed generates and waits pushing away It delivers letters breath.Due to can according to push material determine title push and picture to be pushed, so as to information to be pushed oneself It is dynamic to generate or optimize, and then improve the validity of information push.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other Feature, objects and advantages will become more apparent upon:
Fig. 1 is that this application can be applied to exemplary system architecture figures therein;
Fig. 2 is the flow chart according to one embodiment of the method for the generation information to be pushed of the application;
Fig. 3 a, Fig. 3 b, Fig. 3 c are shown according to the application scenarios of the embodiment of the method for the generation information to be pushed of the application It is intended to;
Fig. 4 is the flow chart according to another embodiment of the method for the generation information to be pushed of the application;
Fig. 5 is the structural schematic diagram according to one embodiment of the generation information to be pushed device of the application;
Fig. 6 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present application Figure.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the method that can apply the generation information to be pushed of the application or the reality for generating information to be pushed device Apply the exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105. Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with server 105 with using terminal equipment 101,102,103, to receive or send out Send message etc..Various telecommunication customer end applications can be installed on terminal device 101,102,103, such as browser application, searched The application of rope class, the application of information push class, the application of shopping class, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments for having display screen, including but not limited to intelligent hand Machine, tablet computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc. Deng.
Server 105 can be to provide the server of various services, such as to browser on terminal device 101,102,103 The background server etc. supported using offers such as, information push class applications.Server 105 can divide the data received Processing, the servers 105 such as analysis can feed back to handling result (such as handling result to the web-page requests data received) Terminal device can also be carried out the processing such as analyzing, and be stored to the data received, be sent in response to other-end equipment The corresponding data of storage is fed back to the other-end equipment by request of data (such as web-page requests).
It should be noted that the method for generation information to be pushed provided herein is generally executed by server 105, but It is not excluded for the possibility executed by terminal device 101,102,103.Correspondingly, it generates information to be pushed device and is generally located on service In device 105, but it is not excluded for the possibility being arranged in terminal device 101,102,103.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need It wants, can have any number of terminal device, network and server.For example, when generating for the embodiment of the present application waits for push letter When breath method is executed by terminal device, the number of server and network may be zero.
With continued reference to Fig. 2, the flow of one embodiment of the method for the generation information to be pushed according to the application is shown 200.The method of the generation information to be pushed, includes the following steps:
Step 201, push material is obtained, wherein push material includes textual materials and picture materials.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated It is engaged in device 105) it first can be from the push material locally or remotely obtained for generating information to be pushed.Wherein, push element Material can be the material of the content for expressing the information pushed to user.
In the present embodiment, push material may include textual materials and picture materials.Textual materials can be used for The relevant word of content to be pushed is described, picture materials for example can be to the relevant displaying picture of content to be pushed.Such as it wants A automobile is pushed to user, above-mentioned textual materials can be the descriptive text to the appearance, performance, evaluation of this automobile etc., Above-mentioned picture materials can be photo, animation, schematic diagram of this automobile etc..In practice, picture can show one or more A picture element then can not only show picture element to be pushed in picture materials, can also show related to information to be pushed Other picture elements, as automobile picture materials in can not only have auto graph element, can also have the figures such as road, personage Piece element.
It is appreciated that when being stored with push material on above-mentioned electronic equipment, these push elements can be obtained from local Material.In some cases, user can also send push material by terminal device to above-mentioned electronic equipment.For example, advertiser The description information that promotion item can be uploaded to above-mentioned electronic equipment by the client of terminal operating, using as promotion item Material is promoted, at this point, above-mentioned electronic equipment, which can remotely obtain these, promotes material.Optionally, the popularization element of promotion item Material can be the content of pages of the landing page associated by the advertising information that advertiser provides.In some cases, above-mentioned electronics is set It is standby can also be remotely from the crawls such as other Website servers and the relevant picture materials of promotion item etc..
Step 202, core word is extracted from above-mentioned textual materials, and title to be pushed is determined based on the core word extracted.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated Business device 105) core word can be then extracted from above-mentioned textual materials, and the core word to being extracted carries out Semantic judgement, root It is judged that result determines title to be pushed.
Here, above-mentioned electronic equipment can be put forward above-mentioned textual materials by statistical analysis mode or semantic analysis mode etc. Take core word.For example, above-mentioned electronic equipment the frequency of occurrences of each word present in the above can be carried out statistics and Sequence, and then choose the frequency of occurrences and sort forward one or more words as the core word extracted.For another example above-mentioned Electronic equipment can carry out the processing such as full cutting method with above-mentioned textual materials, content segmentation at word;Again to obtained word into Row importance calculates (for example, by using reverse document-frequency method (the Term Frequency-Inverse Document of word frequency- Frequency, TF-IDF)), core word is obtained based on the result of importance calculating.It is worth noting that the core extracted Word can there are one or it is multiple, the application does not limit this.
Then, above-mentioned electronic equipment can carry out Semantic judgement to the core word extracted, to determine extracted core Whether word can accurately express the core meaning for the information to be pushed to be generated.For example, above-mentioned electronic equipment can be first to being carried The core word taken is extended, and obtains its synonym, near synonym etc., then these words after extending and text material or picture are plain Material is matched, if the ratio that the material number being matched to accounts for total material number is more than preset ratio threshold value, it is determined that extracted Core word can accurately express the core meaning for the information to be pushed to be generated.It is appreciated that picture materials can have to figure The character description information that piece content is described, such as the description information of a car photo can be " automobile " etc..At this point, expanding Matching for word after exhibition and picture materials can be matching with the description information of picture materials.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can also get it is preset wait for push letter Cease keyword.Wherein, push is corresponding when information to be pushed keyword can be used for matching to search key input by user Ground information to be pushed.For example, when the method for the generation information to be pushed of the present embodiment is applied to the advertisement element provided advertiser When material generates advertising information (information to be pushed), the search key that advertiser can be preset with advertising information is (preset Information to be pushed keyword), the search key of advertising information can be used for when user inputs the search key to advertisement Information is selected and is shown.At this point, above-mentioned electronic equipment can from above-mentioned textual materials extract core word after, further The degree of association of extracted core word and preset information to be pushed keyword is calculated, and whether judges the degree of association being calculated More than default degree of association threshold value, if so, generating title to be pushed according to the core word extracted;Otherwise, it is given birth to according to default title At title to be pushed.Wherein, the degree of association between the core word and preset information to be pushed keyword that are extracted can pass through The Text similarity computing method of such as Jaccard etc calculates.
It is worth noting that being generated when pushing title according to the core word extracted, above-mentioned electronic equipment can be by institute The core word of extraction, which is set out, to be come, and the sentence where can also taking core word is arranged, and the application does not limit herein.According to Default title generates when pushing title, above-mentioned electronic equipment can to presetting the predetermined symbol in title, such as telephone number or Asterisk wildcard etc. is identified and removes, to carry out semantic optimization to default title.It might have in practice, before and after predetermined symbol pair The word that predetermined symbol illustrates, the word as may have " please call hot line " before telephone number, above-mentioned electronic equipment It can be deleted together.For asterisk wildcard, above-mentioned electronic equipment can be preset with corresponding deletion rule, such as adjacent three Space asterisk wildcard can delete two space asterisk wildcards etc..
Step 203, the correlation according to above-mentioned picture materials and preset information to be pushed keyword, from picture materials Select picture as picture to be pushed.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated Business device 105) can also then correlation calculations be carried out to above-mentioned picture materials and preset information to be pushed keyword, and be based on The correlation selects picture as picture to be pushed from picture materials.
In general, picture materials can have description information, which can be vocabulary, phrase or sentence.Above-mentioned electricity Sub- equipment can extract picture keyword from description information, and it is crucial with preset information to be pushed then to calculate picture keyword The correlation of word.Some picture materials may also not have description information, and at this moment, above-mentioned electronic equipment can identify in picture materials Picture element, and the picture keyword of picture materials is extracted according to the picture element that recognizes, if picture materials include certain The automobile of a model, the description information that above-mentioned electronic equipment can obtain the automobile of the model therefrom extract picture keyword.It can To understand, picture keyword can by one or more, preset information to be pushed keyword can also there are one or it is multiple, on Stating electronic equipment can be by the well known text of cosine similarity (cosine similarity) algorithm, Jaccard coefficients etc This similarity calculating method carries out the correlation calculations of above-mentioned picture materials and preset information to be pushed keyword.Wherein, Obtained text similarity numerical value can be as the magnitude of the correlation.By taking Jaccard coefficient methods as an example, picture materials with Correlation magnitude (degree of correlation)=picture keyword of preset information to be pushed keyword is crucial with preset information to be pushed Number/picture keyword of the word shared between word has unified the number for the word for including with preset information to be pushed keyword.
In the present embodiment, above-mentioned electronic equipment can select picture according to correlativity calculation result from picture materials. Above-mentioned electronic equipment can arrange picture materials according to the correlation magnitude being calculated is descending, and selection is pre- successively If number or correlation magnitude are more than the picture materials of default relevance threshold, such as above-mentioned electronic equipment can select to come the One picture materials.Above-mentioned electronic equipment can be using the picture for the picture materials selected as picture to be pushed, can also The picture materials selected are handled to obtain the picture as picture to be pushed.
Step 204, information to be pushed is generated based on above-mentioned title to be pushed and above-mentioned picture to be pushed.
In the present embodiment, above-mentioned electronic equipment may further be by the title to be pushed determined by step 202 and logical Picture push for crossing step 203 determination is combined, the processing generation information to be pushed such as typesetting.Such as above-mentioned electronic equipment can To be previously stored with information model, information model can be determined according to the title of information to be pushed, and title to be pushed and will wait for The corresponding position that push picture is packed into template generates information to be pushed.
In some optional realization methods of the present embodiment, title to be pushed determined by above-mentioned electronic equipment can have more Item, picture to be pushed can have multiple, and preset information to be pushed keyword can also have multiple.At this point, above-mentioned electronic equipment It can be respectively to the title of each title to be pushed He picture to be pushed, preset information to be pushed keyword and picture to be pushed Title (such as brand name), the picture element title of title to be pushed and picture to be pushed, preset information to be pushed keyword Arbitrary combination and correlation calculations are carried out with the picture element title of picture to be pushed, take the correlation in each combination higher Title to be pushed, picture to be pushed generate information to be pushed.
As an application scenarios, the method provided by the present application for generating information to be pushed can be applied to answer for browser With the background server for providing support.The browser application can be installed and run on various terminal equipment.User can pass through Various information are searched for or browsed to operation and the browser application of terminal device.Advertiser can be pushed extensively by browser to user Accuse information (information to be pushed).Advertiser can provide ad material (push material) to background server, such as textual materials, figure Piece material etc..Background server can obtain these ad materials, and core word is then extracted from textual materials, and be based on being carried The core word taken determines advertisement title (title to be pushed).Meanwhile background server can also be according to the picture in ad material Material and predetermined keyword (preset information to be pushed keyword, for example, advertiser's purchase competing words) correlation, from wide Accuse the picture determined in the picture materials of material as advertising pictures (picture to be pushed).Finally, background server can incite somebody to action Identified advertisement title and advertising pictures, which are combined, generates advertising information (information to be pushed).
In order to more intuitively illustrate effect that the present embodiment reaches, a, Fig. 3 b and Fig. 3 c are please referred to Fig.3.In Fig. 3 a, user By browser searches automobile, a plurality of pushed information including advertising information 301 may search for.Wherein, advertising information 301 be that advertiser is preset.As shown in Figure 3b, which can be linked to the page 302, and the page 302 is wide to this Accuse the information automobile to be pushed detailed description information, these detailed description information include advertiser edit be uploaded to from the background clothes The textual materials 3021 and picture materials 3022 of business device.Background server can execute the side of the generation information to be pushed of the application Method by the page 302 textual materials 3021 and picture materials 3022 handle, generate advertising information as illustrated in figure 3 c 301 ' are shown.By the comparison of Fig. 3 a and 3c it is found that advertising information 301 ' is configured with picture, the prominent main points " sedan-chair of title description Vehicle ", " 100,000 ", " trendy ", compared with advertising information 301, the validity higher of information push.
Therefore, the method for the generation information to be pushed of the present embodiment waits for push mark due to that can be determined according to push material It inscribes and picture to be pushed, so as to automatically generate or optimize to information to be pushed, and then improves the validity of information push.
With continued reference to Fig. 4, the stream of another embodiment of the method for the generation information to be pushed according to the application is shown Journey 400.The method of the generation information to be pushed, includes the following steps:
Step 401, push material is obtained, wherein push material includes textual materials and picture materials.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated It is engaged in device 105) it first can be from the push material locally or remotely obtained for generating information to be pushed.Wherein, push element Material can be the material of the content for expressing the information pushed to user.Here, push material may include textual materials and Picture materials.May include one or more picture elements, such as automobile, personage in each picture materials.
Step 402, core word is extracted from above-mentioned textual materials, and title to be pushed is determined based on the core word extracted.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated Business device 105) core word can be then extracted from above-mentioned textual materials, and the core word to being extracted carries out Semantic judgement, root It is judged that result determines title to be pushed.Here, above-mentioned electronic equipment can pass through statistical analysis mode to above-mentioned textual materials Or semantic analysis mode etc. extracts core word.The core word extracted can there are one or it is multiple, the application does not limit this. Then, whether above-mentioned electronic equipment can carry out Semantic judgement to the core word extracted, can with the core word for determining extracted Accurately express the core meaning for the information to be pushed to be generated.If the core word extracted can accurately express waiting for of being generated The core meaning of pushed information generates title to be pushed according to the core word extracted;Otherwise, it is generated according to default title and waits pushing away Send title.
Step 403, the picture element in above-mentioned picture materials is identified.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated Business device 105) picture element in above-mentioned picture materials can be then identified.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can preset the identification of picture element Picture element is identified in rule, for example, when recognizing cylinder, may be picture element " cup ", recognize rectangle When, may be picture element " smart mobile phone " etc., above-mentioned electronic equipment can also be to a certain number of picture element sample extractions Characteristic point simultaneously stores, and when carrying out picture element identification, the characteristic point of each picture element in picture can be extracted, with sample characteristics point It is matched, the picture element in picture materials is determined according to the picture element being matched to.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can also be previously stored with picture element Picture element template, according to the pixel after the matching of picture element template and picture materials, such as outline or gray processing Matching etc., chooses the picture element template being matched to and is determined as the picture element recognized from picture materials.
In some optional realization methods of the present embodiment, after the picture element in picture materials is identified, It is overlapping that above-mentioned electronic equipment can also judge each picture materials whether default picture element has with other picture elements, if It is to judge whether the ratio that lap accounts for default picture element is more than preset ratio threshold value, if being more than preset ratio threshold value, sieve Except the picture materials.Wherein, default picture element can be picture element related with information to be pushed, for example, waiting for push letter Breath is the advertising information of a automobile, and default picture element can be automobile.May include " automobile " and " people in picture materials Two kinds of picture elements of object ", the two may have overlapping.The ratio that lap accounts for default picture element can be the picture of lap The ratio for the pixel number that the profile of vegetarian refreshments number and default picture element includes.Preset ratio threshold value (such as 20%) can be It is manually set, it can also be according to the identification difficulty of the sample to certain amount with different overlap proportion picture elements (as led to The measurement of cost duration is crossed, spends the longer identification difficulty of duration bigger), it is obtained by machine learning method, the application does not do this It limits.By the step, above-mentioned electronic equipment can screen out the picture element interfered by other picture elements, avoid influencing information Push effect.
Step 404, picture materials are cut according to the picture element identified to obtain picture to be selected.
In the present embodiment, in the present embodiment, the electronic equipment (example of the method operation of information to be pushed thereon is generated Server 105 as shown in Figure 1) picture element can then be cut according to the picture element that identification obtains, to obtain The picture for including default picture element, as picture to be selected.In some implementations, above-mentioned electronic equipment can obtain picture materials In preset the profile of picture element, and cut out default picture element conduct from picture materials according to the pre-determined distance with contour line Picture to be selected.Cut pre-determined distance according to contour line to ensure the integrality of default picture element more.Wherein, with contour line Pre-determined distance such as can be 1 centimetre, 1 pixel.
Step 405, the degree of association of the picture element and preset information to be pushed keyword in picture to be selected is calculated.
It is appreciated that after being identified to picture element, the electronic equipment of the method operation of information to be pushed thereon is generated (such as server 105 shown in FIG. 1) can obtain the description information or keyword to picture element.In the present embodiment, on Stating electronic equipment may further be according to the description information or keyword, and the picture element calculated in picture to be selected is waited for preset The degree of association of pushed information keyword.Calculation of relationship degree method is consistent with the correlation magnitude calculation method involved in step 203, Details are not described herein.
Step 406, selection is comprising to be selected with the maximum picture element of the degree of association of preset information to be pushed keyword Picture is used as picture to be pushed.
In the present embodiment, electronic equipment (such as the clothes shown in FIG. 1 of the method operation of information to be pushed thereon are generated Business device 105) it can be selected comprising the degree of association with preset information to be pushed keyword most according to the degree of association being calculated The picture to be selected of big picture element is used as picture to be pushed.
Step 407, information to be pushed is generated based on above-mentioned title to be pushed and above-mentioned picture to be pushed.
In the present embodiment, above-mentioned electronic equipment may further be by the title to be pushed determined by step 402 and logical Picture push for crossing step 406 determination is combined, the processing generation information to be pushed such as typesetting.Such as above-mentioned electronic equipment can To be previously stored with information model, information model can be determined according to the title of information to be pushed, and title to be pushed and will wait for The corresponding position that push picture is packed into template generates information to be pushed.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the side of the generation information to be pushed in the present embodiment The flow 400 of method highlights the step of determining picture to be pushed according to picture materials.The scheme of the present embodiment description can be with as a result, Picture materials are handled to obtain specific picture element, the more effective picture of information to be pushed is configured to realize.
With further reference to Fig. 5, as the realization of the method to above-mentioned generation information to be pushed, this application provides a kind of lifes At one embodiment of information to be pushed device, the device embodiment is corresponding with embodiment of the method shown in Fig. 2.
As shown in figure 5, the generation information to be pushed device 500 of the present embodiment includes:Acquisition module 501, title determine mould Block 502, picture determining module 503 and generation module 504.Wherein, acquisition module 501 may be configured to obtain push material, Wherein, push material may include textual materials and picture materials;Title determining module 502 may be configured to from above-mentioned word Story extraction core word, and title to be pushed is determined based on the core word extracted;Picture determining module 503 may be configured to According to the correlation of above-mentioned picture materials and preset information to be pushed keyword, determined from above-mentioned picture materials as waiting for Push the picture of picture;Generation module 504 may be configured to generate based on above-mentioned title to be pushed and above-mentioned picture to be pushed Information to be pushed.
In some optional realization methods of the present embodiment, title determining module 502 can also be configured to:From above-mentioned text Word story extraction core word, and judge whether the core word and the degree of association of preset information to be pushed keyword are more than default close Connection degree threshold value;If so, generating title to be pushed according to the core word extracted;Otherwise, it is generated according to default title and waits for push mark Topic.
In some optional realization methods of the present embodiment, picture determining module 503 can also include:Recognition unit is (not Show), it may be configured to that the picture element in above-mentioned picture materials is identified;Cut unit (not shown), Ke Yipei It sets for being cut to obtain picture to be selected to above-mentioned picture materials according to the picture element identified;Computing unit (does not show Go out), it may be configured to calculate the degree of association of the picture element and preset information to be pushed keyword in picture to be selected;It determines Unit (not shown) may be configured to selection comprising first with the maximum picture of the degree of association of preset information to be pushed keyword The picture to be selected of element is used as picture to be pushed.In some implementations, cutting unit can also further be configured to:Obtain picture The profile of picture element is preset in material;According to the pre-determined distance with contour line default picture member is cut out from above-mentioned picture materials Element is used as picture to be selected.In other realizations, picture determining module 503 can also include screening out unit (not shown), can be with It is configured to:To each picture materials:It is overlapping to judge whether default picture element has with other picture elements;If so, judging weight Whether the ratio that folded part accounts for default picture element is more than preset ratio threshold value;If being more than preset ratio threshold value, the picture is screened out Material.
It is worth noting that the method for generating all modules described in the device 500 of information to be pushed and being described with reference to figure 2 In each step it is corresponding.Device 500 is equally applicable to above with respect to the operation and feature of method description and wherein wrap as a result, The module or unit contained, details are not described herein.
It will be understood by those skilled in the art that the device 500 of above-mentioned generation information to be pushed further includes some other known Structure, such as processor, memory etc., in order to unnecessarily obscure embodiment of the disclosure, these well known structures are in Figure 5 It is not shown.
Below with reference to Fig. 6, it illustrates the computers suitable for terminal device/server for realizing the embodiment of the present application The structural schematic diagram of system 600.Terminal device/server shown in Fig. 6 is only an example, should not be to the embodiment of the present application Function and use scope bring any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and Execute various actions appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data. CPU601, ROM 602 and RAM603 is connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to bus 604。
It is connected to I/O interfaces 605 with lower component:Include the importation 606 of keyboard or touch screen etc.;Including such as cathode The output par, c 607 of ray tube (CRT), liquid crystal display (LCD) etc.;Storage section 608 including hard disk etc.;And including all The communications portion 609 of such as network interface card of LAN card, modem.Communications portion 609 via such as internet network Execute communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as disk, CD, Magneto-optic disk, semiconductor memory etc. are mounted on driver 610 as needed, in order to from the computer journey read thereon Sequence is mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium On computer program, which includes the program code for method shown in execution flow chart.In such reality It applies in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media 611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes Above-mentioned function.It should be noted that the non-volatile computer-readable medium involved by the application can be non-volatile calculating Machine readable signal medium or non-volatile computer readable storage medium storing program for executing either the two arbitrarily combine.It is non-volatile What computer readable storage medium for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor is System, device or device, or the arbitrary above combination.The more specific example of non-volatile computer readable storage medium storing program for executing can be with Including but not limited to:Electrical connection, portable computer diskette with one or more conducting wires, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc Read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this application, Non-volatile computer readable storage medium storing program for executing, which can be any, includes or the tangible medium of storage program, which can be commanded The either device use or in connection of execution system, device.And in this application, computer-readable signal media can Using including in a base band or as a carrier wave part propagate data-signal, wherein carrying computer-readable program generation Code.The data-signal of this propagation may be used diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned arbitrary Suitable combination.Computer-readable signal media can also be any computer-readable other than computer readable storage medium Medium, the computer-readable medium can send, propagate either transmission for being used by instruction execution system, device or device Or program in connection.The program code for including on computer-readable medium can pass with any suitable medium It is defeated, including but not limited to:Wirelessly, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction Combination realize.
Being described in module involved in the embodiment of the present application can be realized by way of software, can also be by hard The mode of part is realized.Described module can also be arranged in the processor, for example, can be described as:A kind of processor packet Include acquisition module, title determining module, picture determining module and generation module.Wherein, the title of these modules is in certain situation Under do not constitute restriction to the unit itself, for example, acquisition module is also described as, " configuration obtains the mould of push material Block ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be Included in device described in above-described embodiment;Can also be individualism, and without be incorporated the device in.Above-mentioned calculating Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should Device:Obtain push material, wherein push material includes textual materials and picture materials;Core is extracted from above-mentioned textual materials Word, and title to be pushed is determined based on the core word extracted;It is crucial according to above-mentioned picture materials and preset information to be pushed The correlation of word determines the picture as picture to be pushed from above-mentioned picture materials;Based on above-mentioned title to be pushed and upper It states picture to be pushed and generates information to be pushed.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein Can technical characteristic replaced mutually and the technical solution that is formed.

Claims (12)

1. a kind of method generating information to be pushed, which is characterized in that the method includes:
Obtain push material, wherein the push material includes textual materials and picture materials;
Core word is extracted from the textual materials, and title to be pushed is determined based on the core word extracted;
According to the correlation of the picture materials and preset information to be pushed keyword, determine to make from the picture materials For the picture of picture to be pushed;
Information to be pushed is generated based on the title to be pushed and the picture to be pushed.
2. according to the method described in claim 1, it is characterized in that, described extract core word from the textual materials, and it is based on The core word extracted determines that title to be pushed includes:
Core word is extracted from the textual materials, and judges the pass of the core word and the preset information to be pushed keyword Whether connection degree is more than default degree of association threshold value;
If so, generating title to be pushed according to the core word extracted;
Otherwise, title to be pushed is generated according to default title.
3. according to the method described in claim 1, it is characterized in that, the foundation waits pushing to the picture materials with preset The calculating of the correlation of information key determines that the picture as picture to be pushed includes from the picture materials:
Picture element in the picture materials is identified;
The picture materials are cut according to the picture element identified to obtain picture to be selected;
Calculate the degree of association of the picture element and preset information to be pushed keyword in the picture to be selected;
Select comprising with the picture to be selected of the maximum picture element of the degree of association of preset information to be pushed keyword as waiting pushing away Send picture.
4. according to the method described in claim 3, it is characterized in that, described plain to the picture according to the picture element identified Material is cut to obtain picture to be selected:
Obtain the profile that picture element is preset in picture materials;
Default picture element is cut out as picture to be selected from the picture materials according to the pre-determined distance with contour line.
5. according to the method described in claim 3, it is characterized in that, the picture element in the picture materials is known Further include after not:
To each picture materials:
It is overlapping to judge whether default picture element has with other picture elements;
If so, it is more than preset ratio threshold value to account for the ratio of default picture element in response to lap, the picture materials are screened out.
6. a kind of device generating information to be pushed, which is characterized in that described device includes:
Acquisition module is configured to obtain push material, wherein the push material includes textual materials and picture materials;
Title determining module is configured to extract core word from the textual materials, and is waited for based on the core word determination extracted Push title;
Picture determining module is configured to the correlation according to the picture materials and preset information to be pushed keyword, from The picture as picture to be pushed is determined in the picture materials;
Generation module is configured to generate information to be pushed based on the title to be pushed and the picture to be pushed.
7. device according to claim 6, which is characterized in that the title determining module is also configured to:
Core word is extracted from the textual materials, and judges the pass of the core word and the preset information to be pushed keyword Whether connection degree is more than default degree of association threshold value;
If so, generating title to be pushed according to the core word extracted;
Otherwise, title to be pushed is generated according to default title.
8. device according to claim 6, which is characterized in that the picture determining module includes:
Recognition unit is configured to that the picture element in the picture materials is identified;
Unit is cut, is configured to that the picture materials are cut according to the picture element identified to obtain picture to be selected;
Computing unit is configured to calculate the pass of the picture element and preset information to be pushed keyword in the picture to be selected Connection degree;
Determination unit, being configured to selection includes and the maximum picture element of the degree of association of preset information to be pushed keyword Picture to be selected is used as picture to be pushed.
9. device according to claim 8, which is characterized in that the cutting unit is further configured to:
Obtain the profile that picture element is preset in picture materials;
Default picture element is cut out as picture to be selected from the picture materials according to the pre-determined distance with contour line.
10. device according to claim 8, which is characterized in that the picture determining module further includes screening out unit, configuration For:
To each picture materials:
It is overlapping to judge whether default picture element has with other picture elements;
If so, it is more than preset ratio threshold value to account for the ratio of default picture element in response to lap, the picture materials are screened out.
11. a kind of computing device, including:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors so that one or more of processors are real The now method as described in any in claim 1-5.
12. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the program The method as described in any in claim 1-5 is realized when being executed by processor.
CN201710293331.2A 2017-04-28 2017-04-28 The method and apparatus for generating information to be pushed Pending CN108804448A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710293331.2A CN108804448A (en) 2017-04-28 2017-04-28 The method and apparatus for generating information to be pushed

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710293331.2A CN108804448A (en) 2017-04-28 2017-04-28 The method and apparatus for generating information to be pushed

Publications (1)

Publication Number Publication Date
CN108804448A true CN108804448A (en) 2018-11-13

Family

ID=64069644

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710293331.2A Pending CN108804448A (en) 2017-04-28 2017-04-28 The method and apparatus for generating information to be pushed

Country Status (1)

Country Link
CN (1) CN108804448A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109828771A (en) * 2019-01-18 2019-05-31 深圳壹账通智能科技有限公司 File push method, apparatus, computer equipment and storage medium
CN110245257A (en) * 2019-05-31 2019-09-17 阿里巴巴集团控股有限公司 The generation method and device of pushed information
CN110941766A (en) * 2019-12-10 2020-03-31 北京字节跳动网络技术有限公司 Information pushing method and device, computer equipment and storage medium
CN112068920A (en) * 2020-09-22 2020-12-11 深圳市欢太科技有限公司 Content display method and device, electronic equipment and readable storage medium
CN114710554A (en) * 2022-03-30 2022-07-05 北京奇艺世纪科技有限公司 Message processing method and device, electronic equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504108A (en) * 2014-12-30 2015-04-08 百度在线网络技术(北京)有限公司 Information search method and device
WO2015055067A1 (en) * 2013-10-17 2015-04-23 Tencent Technology (Shenzhen) Company Limited Method and apparatus for pushing messages

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015055067A1 (en) * 2013-10-17 2015-04-23 Tencent Technology (Shenzhen) Company Limited Method and apparatus for pushing messages
CN104504108A (en) * 2014-12-30 2015-04-08 百度在线网络技术(北京)有限公司 Information search method and device

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109828771A (en) * 2019-01-18 2019-05-31 深圳壹账通智能科技有限公司 File push method, apparatus, computer equipment and storage medium
CN110245257A (en) * 2019-05-31 2019-09-17 阿里巴巴集团控股有限公司 The generation method and device of pushed information
CN110245257B (en) * 2019-05-31 2023-11-21 创新先进技术有限公司 Push information generation method and device
CN110941766A (en) * 2019-12-10 2020-03-31 北京字节跳动网络技术有限公司 Information pushing method and device, computer equipment and storage medium
CN110941766B (en) * 2019-12-10 2023-10-20 北京字节跳动网络技术有限公司 Information pushing method, device, computer equipment and storage medium
CN112068920A (en) * 2020-09-22 2020-12-11 深圳市欢太科技有限公司 Content display method and device, electronic equipment and readable storage medium
CN114710554A (en) * 2022-03-30 2022-07-05 北京奇艺世纪科技有限公司 Message processing method and device, electronic equipment and storage medium
CN114710554B (en) * 2022-03-30 2024-04-26 北京奇艺世纪科技有限公司 Message processing method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107172151B (en) Method and device for pushing information
CN107577807B (en) Method and device for pushing information
CN108804450B (en) Information pushing method and device
CN108805594B (en) Information pushing method and device
CN108804448A (en) The method and apparatus for generating information to be pushed
CN107679217B (en) Associated content extraction method and device based on data mining
CN109145280A (en) The method and apparatus of information push
CN107797982B (en) Method, device and equipment for recognizing text type
CN107526718B (en) Method and device for generating text
CN107908789A (en) Method and apparatus for generating information
CN106874467A (en) Method and apparatus for providing Search Results
CN108228906B (en) Method and apparatus for generating information
CN106845999A (en) Risk subscribers recognition methods, device and server
CN106919711B (en) Method and device for labeling information based on artificial intelligence
CN106993030A (en) Information-pushing method and device based on artificial intelligence
CN107958078A (en) Information generating method and device
CN110427453B (en) Data similarity calculation method, device, computer equipment and storage medium
CN109522399B (en) Method and apparatus for generating information
CN104462186A (en) Method and device for voice search
CN108073708A (en) Information output method and device
CN107766498A (en) Method and apparatus for generating information
CN114445179A (en) Service recommendation method and device, electronic equipment and computer readable medium
CN108256078B (en) Information acquisition method and device
CN109981712B (en) Method and device for pushing information
CN108959289B (en) Website category acquisition method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination