Summary of the invention
The embodiment of the present invention provides a kind of content delivery method and device, the list in a manner of solving existing content of platform pushOne, attract the ineffective problem of user.
In order to solve the above-mentioned technical problem, the present invention is implemented as follows:
In a first aspect, the embodiment of the invention provides a kind of content delivery methods, which comprises
Task to be pushed is pushed by the first push strategy, wherein the first push strategy includes at least two push dimensionsDegree, the task to be pushed include at least two class content to be pushed, and every kind of push dimension and every class content to be pushed correspond；
The attraction data volume of the first kind content to be pushed in preset duration is obtained, and is obtained in the preset durationThe attraction data volume of interior object content, the object content are and inhale in the content of the first kind content to be pushed same typeThe highest content of gravitation data volume；
When the attraction data volume of the first kind content to be pushed is less than the attraction data volume of the object content,It is corresponding with reference to push feature to obtain the object content；
It is optimized based on described with reference to push feature pair push dimension corresponding with the first kind content to be pushed；
By the new task to be pushed of the second push strategy push, the second push strategy includes the push after optimizationDimension.
Optionally, the push dimension includes the first push parameter, and the first push parameter is push time, push canalThe classification channel in road, the content-form of push or push.
It optionally, include pushing parameter with the second of the first push parameter same type with reference to push feature describedWhen, it is described based on the step optimized with reference to push feature pair push dimension corresponding with the first kind content to be pushedSuddenly, comprising:
The first push parameter in push dimension corresponding with the first kind content to be pushed is replaced with described secondPush parameter, the push dimension after being optimized.
Optionally, described the step of new task to be pushed is pushed by the second push strategy, comprising:
Keyword is extracted from the object content；
Described new to filter out the preferred push content including the keyword in push task；
Corresponding preferred push content is pushed by each push dimension.
Optionally, the first push strategy includes the first push dimension, described to push by the first push strategy wait pushThe step of task, comprising:
It pushes by the first push dimension and is pushed to the second class corresponding with the first push dimension in push taskContent.
Optionally, the first push strategy further includes push substrategy, and the push substrategy is enlivens substrategy, non-Enliven at least one in substrategy, class substrategy of hanging down or keyword substrategy.
Optionally, described described to corresponding with the first push dimension in push task by the first push dimension pushThe step of one kind push content, comprising:
It is described to push dimension pair with described first in push task to target user's push by the first push dimensionThe refinement content in a kind of push content answered, the target user is user corresponding with the push substrategy, described thinChange content is content corresponding with the push substrategy.
Optionally, the attraction data volume includes pageview, click volume, the amount of thumbing up, sharing amount, transfer amount, comment amountWith at least one in resource data amount.
Second aspect, the embodiment of the present invention also provide a kind of content push device, comprising:
Pushing module, for pushing task to be pushed by the first push strategy, wherein the first push strategy includes extremelyFew two kinds of push dimensions, the task to be pushed include at least two class content to be pushed, and every kind of push dimension waits pushing with every classContent corresponds；
First obtains module, for obtaining the attraction data volume of the first kind content to be pushed in preset duration, andThe attraction data volume of the object content in the preset duration is obtained, the object content is in waiting pushing with the first kindHold the highest content of attraction data volume in the content of same type；
Second obtains module, is less than the object content for the attraction data volume in the first kind content to be pushedAttraction data volume when, obtain the object content it is corresponding with reference to push feature；
Optimization module, for being tieed up based on described with reference to the push corresponding with the first kind content to be pushed of push feature pairDegree optimizes；
The pushing module is also used to the to be pushed task new by the second push strategy push, the second push strategyIncluding the push dimension after optimization.
Optionally, the push dimension includes the first push parameter, and the first push parameter is push time, push canalThe classification channel in road, the content-form of push or push.
It optionally, include pushing parameter with the second of the first push parameter same type with reference to push feature describedWhen, the optimization module is also used to the first push parameter in push dimension corresponding with the first kind content to be pushedReplace with the second push parameter, the push dimension after being optimized.
Optionally, the pushing module includes:
Extraction unit, for extracting keyword from the object content；
Screening unit, for described new to filter out preferably pushing away including the object content feature in push taskSend content；
Push unit, for pushing corresponding preferred push content by the push dimension after optimization.
Optionally, the first push strategy includes the first push dimension, and the pushing module is also used to by described firstPush dimension is pushed to the second class push content corresponding with the first push dimension in push task.
Optionally, the first push strategy further includes push substrategy, and the push substrategy is enlivens substrategy, non-Enliven substrategy, class substrategy of hanging down or keyword substrategy.
Optionally, the pushing module is also used to described wait push to target user's push by the first push dimensionRefinement content in task in a kind of push content corresponding with the first push dimension, the target user is to push away with describedSend substrategy corresponding user, the refinement content is content corresponding with the push substrategy.
Optionally, the attraction data volume includes pageview, click volume, the amount of thumbing up, sharing amount, transfer amount, comment amountWith at least one in resource data amount.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment, including processor, memory and are stored in describedIt is real when the computer program is executed by the processor on memory and the computer program that can run on the processorNow the step of content delivery method as described above.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, the computer-readable storageComputer program is stored on medium, the computer program realizes content delivery method as described above when being executed by processorThe step of.
In embodiments of the present invention, it first passes through the first push strategy and pushes task to be pushed, then obtain with all kinds of wait push awaySend in content same type content the highest content of attraction data volume corresponding with reference to push feature, based on reference to push feature comeOptimize corresponding push dimension, and new appoints wait push by the second push strategy push for including the push dimension after optimizationBusiness.In this way, the push dimension after optimization can push in feature from reference and learn to the attraction data volume for how improving content,The push effect of new push task is improved, so that pushing the new task to be pushed of strategy push with more attraction by secondPower, and then the user volume of platform can be improved.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, completeSite preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hairEmbodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative effortsExample, shall fall within the protection scope of the present invention.
Referring to Fig. 1, Fig. 1 is a kind of flow chart of content delivery method provided in an embodiment of the present invention, as shown in Figure 1,The following steps are included:
Step 101: pushing task to be pushed by the first push strategy, wherein the first push strategy includes at least twoKind push dimension, the task to be pushed include at least two class content to be pushed, every kind of push dimension and every class content to be pushedIt corresponds.
In the embodiment of the present invention, the task to be pushed be the operator of platform be attract user enter platform, stay in it is flatPlatform and the diversified content pushed.Task to be pushed includes the content to be pushed of plurality of classes, can be according to the attribute of contentCarrying out the differentiation of classification, wherein a content can be pertaining only to a classification, also may belong to multiple classifications, such as: UEFA Champions League is determinedThe result of match may belong to Sport Class, also may belong to news category.
The first corresponding every other content to be pushed of type of push strategy has corresponding push dimension, and every kind of push dimension is used forPush corresponding a kind of content to be pushed.Push dimension can push in wait push according to the characteristics of content to be pushed to userHold, to attract user.
Each push dimension can be while carry out and non-interfering, i.e., one push dimension to corresponding one kind toIn the case that push content is pushed, another push dimension can also be pushed away corresponding another kind of content to be pushedIt send.
Platform in the embodiment of the present invention, can be Web Community, including forum, discussion bar, announcement board, group discuss, it is aAt least one of in the publication of people's knowledge and personal space (individual center).Platform can be the operation in the form of website, can also be withIt is the form operation of application software.
Step 102: obtaining the attraction data volume of the first kind content to be pushed in preset duration, and obtain describedThe attraction data volume of object content in preset duration, the object content are and the first kind content to be pushed same typeThe highest content of attraction data volume in content.
In the embodiment of the present invention, in platform other than the content of operator push, user oneself can also make content simultaneouslyIt is pushed in platform, for other users consumption, so that the content for being supplied to user on platform not only includes that platform operation side pushes awayThe content sent further includes the content of numerous users oneself production.
First kind content to be pushed can be any sort content to be pushed that above-mentioned task to be pushed includes.It is waited in the first kindAfter pushing content push preset duration, the attraction data volume of first kind content to be pushed in preset duration is obtained, is obtained simultaneouslyWith the attraction data volume of the other content of first kind content to be pushed same type in preset duration, so that it is complete to obtain the typeAttraction data volume of portion's content in preset duration, and then can determine the type attraction data volume in preset durationHighest object content.Object content can be the content of operator push, be also possible to the content of user's push.
The attraction data volume of above content is to indicate that a kind of data of content attraction height embody, attraction data volumeHigher expression content attraction is higher, more can improve user volume for platform；The lower expression content attraction of attraction data volumeIt is lower, it is difficult to user be attracted to result even in the loss of platform user amount.
Step 103: being less than the attraction of the object content in the attraction data volume of the first kind content to be pushedWhen data volume, it is corresponding with reference to push feature to obtain the object content.
After step 102 determines object content, by the attraction data volume of first kind content to be pushed and object contentAttraction data volume is compared.
When the attraction data volume of first kind content to be pushed is equal to the attraction data volume of object content, it is believed thatFirst kind content to be pushed is that object content or first kind content to be pushed and object content have same attraction.
When the attraction data volume of first kind content to be pushed is less than the attraction data volume of object content, it is believed that firstThe inadequate object content of class content to be pushed is attractive.At this time, it may be necessary to the corresponding reference push feature of object content is obtained, so as toLearn how to attract user by reference to push feature in push dimension.
It is in the corresponding push dimension of object content with reference to push feature when object content is the content of operator pushAt least one of push parameter；When object content is the content of user's push, since the content of user's push may be a kind ofThe not systematic algorithm support of chance event, therefore can be the push time of object content, push canal with reference to feature is pushedAt least one of in road, the content-form of push and the classification of push channel.
Such as: object content is the film review that a picture and text of 10 points of user's morning push combine, then can with reference to push featureWith include 10 points of the morning push the time, picture and text combine push content-form and push movie channel at least one of；Object content is user to play the game live streaming of box form push, then may include the push canal for playing frame push with reference to push featureAt least one of in the GameChannel in road, the push content-form of live streaming and push.
It should be noted that when first kind content to be pushed includes multiple contents, the above-mentioned attraction with object contentThe attraction data volume for the first kind content to be pushed that data volume compares, can be for attraction data volume in above-mentioned multiple contents mostThe attraction data volume of high content is also possible to the average value of the attraction data volume of above-mentioned multiple contents, does not limit thisIt is fixed.
Step 104: based on it is described with reference to corresponding with the first kind content to be pushed push dimension of push feature pair intoRow optimization.
It is carried out based on the reference of user can be attracted to push feature pair push dimension corresponding with first kind content to be pushedAfter optimization, the push dimension after enabling to optimization also has the characteristics that attract user with reference to push feature, and then improves subsequentTo the attraction data volume of first kind content to be pushed.
Step 105: pushing new task to be pushed by the second push strategy, the second push strategy includes after optimizingThe push dimension.
Push dimension after optimization can more attract user than the push dimension before optimization, therefore including the push after optimizationThe task to be pushed of second push strategy push of dimension can be pushed away than the first push strategy including the push dimension before optimizationThe task to be pushed sent obtains higher attraction data volume, i.e., can more attract user, so that using the second push planThe platform of the slightly new task to be pushed of push can more attract user.
It should be noted that the second push strategy is compared to the first push strategy, wherein can be a push dimension and obtainDo not optimized to other push dimensions are optimized, be also possible to multiple push dimensions obtain optimizing other push dimensions do not obtain it is excellentChange, can also be that whole push dimensions is all optimized, be not construed as limiting herein.
It in the embodiment of the present invention, first passes through the first push strategy and pushes task to be pushed, then obtain with all kinds of wait pushIn content same type content the highest content of attraction data volume it is corresponding with reference to push feature, based on reference to push feature come excellentChange corresponding push dimension, and new appoints wait push by the second push strategy push for including the push dimension after optimizationBusiness.In this way, the push dimension after optimization can push in feature from reference and learn to the attraction data volume for how improving content,The push effect of new push task is improved, so that pushing the new task to be pushed of strategy push with more attraction by secondPower, and then the user volume of platform can be improved.
Referring to Fig. 2, Fig. 2 is the flow chart of another content delivery method provided in an embodiment of the present invention.The present embodimentIn, push dimension includes the first push parameter, includes pushing away with the second of the first push parameter same type with reference to push featureSend parameter.Method is as shown in Figure 2, comprising the following steps:
Step 201: pushing task to be pushed by the first push strategy, wherein the first push strategy includes at least twoKind push dimension, the task to be pushed include at least two class content to be pushed, every kind of push dimension and every class content to be pushedIt corresponds.
The realization process and beneficial effect of step 201 can be corresponded to referring to the description in step 101, and details are not described herein again.
As shown in figure 3, platform includes basic resource data, wherein land resource including premium content and content.In high-qualityHolding is the task to be pushed being pushed.Task to be pushed can be the premium content of operator oneself production, be also possible to useFamily, which is contributed to operator, obtains the premium content of remuneration, and operator is authorized to the excellent of popularization after can also be user's push platformMatter content.
The content-form of premium content can be text, picture, picture and text combination, video and live streaming etc., not limit hereinIt is fixed.
Content landing resource is for pushing the resource of task to be pushed in platform, may include vest account and classificationChannel, task to be pushed need to push all kinds of content to be pushed in platform by multiple vest accounts, have both formed platform and comparedLively phenomenon plays the role of attracting user again.Channel of classifying is used for the classification according to task to be pushed, in a channelDisplay belongs to of a sort content to be pushed, and then achievees the purpose that show all kinds of content to be pushed to user.In addition, content is fallenGround resource also may include individual center, i.e., the interested content of user is directly pushed to the individual center of user.
In an optional embodiment, the first push strategy includes the first push dimension, and the step 201 canTo include:
It pushes by the first push dimension and is pushed to the second class corresponding with the first push dimension in push taskContent.
As shown in figure 3, platform is provided there are many pushing parameter to form push dimension, the first push dimension be can be by pushing awayOne or more combination formation in the classification channel of time, push channel, the content-form of push and push are sent, platform canCorresponding second class is pushed into content push into platform according to the first push dimension, to attract user.
Wherein, the second class content to be pushed can be pushed to push time point or the push of platform by the push time for platformPeriod.The difference of the characteristics of push times of difference push dimensions are generally according to content to be pushed and different from, such as: it is hotPoint news can push for morning, and amusement information can push at night.
Push channel is the push mode that the second class content to be pushed is pushed to platform user by platform, be can be secondThe push of class content to be pushed in user enters the content push region of platform homepage, be also possible to when user does not enter platform withThe mode of notification message pushes the second class content to be pushed to user, can also be that user enters in platform and waits pushing with the second classThe second class content to be pushed is pushed to user in the form of playing frame when the relevant channel of content, is not construed as limiting herein.
The content-form of push includes the forms such as text, picture, picture and text combination, audio, video and live streaming, in push dimensionIncluding push the time and push content-form when, platform according to push dimension push the second class content to be pushed can be notSecond class content to be pushed of different content form is pushed to user by the same push time.
The classification channel of push can be understood as platform when pushing the second class content to be pushed according to push dimension, by theTwo class content to be pushed push to corresponding classification channel in platform.Such as: the second class content to be pushed is about oneThe match of Football World Championship, then the content to be pushed can be pushed sports channel or Football channel on platform.
Wherein, classification channel can also include theme (IP) channel, be used to specially show in channel related to the themeContent, convenient for for rapidly entering topic channel.Such as: during Football World Championship match, world cup frequency is added on platformRoad is for specially showing content related with Football World Championship.
In present embodiment, platform is pushed according to the first push dimension and is pushed to the second class corresponding in push taskContent, platform push other corresponding classes according to other push dimensions and push content, and multiple push dimensions are shared out the work and help one another, convenient for flatPlatform completes the push of task to be pushed.
Optionally, the first push strategy further includes push substrategy, and the push substrategy is enlivens substrategy, non-Enliven at least one in substrategy, class substrategy of hanging down or keyword substrategy.
As shown in figure 3, platform be also provided with push substrategy come advanced optimize push parameter composition push dimension,In, push substrategy is that the characteristic of user is combined on the basis of pushing dimension, and auxiliary push dimension improves push precision.
Wherein, enlivening substrategy is to be directed to create any active ues group that content is consumed for other users in platform, non-liveJump substrategy is the inactive users group for consumption content.The ratio of any active ues and inactive users in platform is about2:8, any active ues and inactive users are different for the point-of-interest of content.Push dimension, which combines, enlivens substrategy and inactiveSubstrategy, the content to be pushed for enabling to any active ues to receive more meets the interest of any active ues, so that inactive usersThe content to be pushed received more meets the interest of inactive users.
Likewise, class substrategy of hanging down can equally distinguish the different point of interest of user with keyword substrategy, and then improveThe push quality of content to be pushed improves the attraction data volume of content to be pushed.
Therefore, it when the first push strategy further includes push substrategy, each push dimension can be advanced optimized treats and push awayThe push accuracy of content is sent, and then improves platform to the attraction of user.
In another optional embodiment, in the case where the first push strategy further includes above-mentioned push substrategy, stepRapid 201 can be with are as follows:
It is described to push dimension pair with described first in push task to target user's push by the first push dimensionThe refinement content in a kind of push content answered, the target user is user corresponding with the push substrategy, described thinChange content is content corresponding with the push substrategy.
For pushing substrategy and be to enliven substrategy and inactive substrategy: being not associated in push dimension and enliven substrategyWhen with inactive substrategy, its corresponding a kind of content to be pushed can be issued any active ues and inactive users by push dimension；And when push dimension combines and enlivens substrategy and inactive substrategy, push dimension can be its corresponding a kind of content to be pushedThe middle interested content push of any active ues to any active ues, inactive users sense in its corresponding a kind of content to be pushed is emergingThe content push of interest is to inactive users.
Likewise, class substrategy of hanging down can distinguish the user of different vertical classes, and such as: user A only joins U.S.'s professional basketballThe content for matching (National Basketball Association, abbreviation NBA) is interested, and user B is only to Chinese professional basketballThe content of league matches (China Basketball Association, abbreviation CBA) is interested, and content to be pushed is and basketball phaseIn the case where the content of pass, in the unbonded vertical class substrategy of push dimension, push dimension can be complete content relevant to basketballPortion is pushed to user A and user B；And when push dimension combines and hangs down class substrategy, push dimension meeting handle is relevant to basketballContent push relevant to NBA is to user A, content push relevant with CBA in content relevant with basketball to use in contentFamily B.
Keyword substrategy can also distinguish the user of different keywords, mode from the corresponding user group of push dimensionClose with the principle of vertical class substrategy, details are not described herein again.
In present embodiment, first pushes strategy by each push dimension and pushes being collectively formed for substrategy, can be into oneThe push accuracy of the task to be pushed of step optimization the first push strategy push, and then platform is improved to the attraction of user.
It should be noted that initial push dimension (i.e. without the push dimension of optimization) can be to be in advance based on and respectively push awayParameter and each push substrategy is sent to carry out strategy value calculating, the combination of the highest push parameter of obtained strategy value.Each push dimensionDegree can be the combination of identical push parameter, or the combination of difference push parameter.
Step 202: obtaining the attraction data volume of the first kind content to be pushed in preset duration, and obtain describedThe attraction data volume of object content in preset duration, the object content are and the first kind content to be pushed same typeThe highest content of attraction data volume in content.
Wherein, attraction data volume may include pageview, click volume, the amount of thumbing up, sharing amount, transfer amount, comment amount andAt least one of in resource data amount.Wherein, resource data is the resource that user is directed to that content is granted, and resource data can be useThe money that family is granted is also possible to virtual present or virtually dress up that user buys on platform, such as: virtual present can be usedIn being granted in live streaming, money can be used for carrying out beating reward to article.
Platform can determine the number of resources of each content according to each content various forms of resource datas obtainedAccording to amount.It can be the virtual present received by content, virtually dressing up determines the resource data amount of content, example with the number of moneySuch as: the sum of the number of receiving for receiving number and money of virtual present receiving number, virtually dressing up is used as resource data amount；?It can be through virtual present, virtually dress up with the magnitude of value of money and determine the resource data amount of content, such as: content A is obtainedThe amount of money given is 5 pieces, and when the amount of money that content B is received is 100 pieces, the resource data amount of content B is the resource of content A20 times of data volume.
Platform can count the parameters amount that attraction data volume includes and be calculated, and obtain the attraction number of contentAccording to amount.Such as: in the case where attraction data volume includes click volume, using the click volume of content as the attraction force data of contentAmount；Alternatively, include click volume and in the case where the amount of thumbing up in attraction data volume, can the amount of will click on and the amount of thumbing up and value workFor attraction data volume, can also the amount of will click on and the amount of thumbing up combine weight proportion that the attraction data volume of content is calculated,Such as: the amount of will click on and the product of the first weighted value are plus the amount of thumbing up and the attraction product of the second weighted value and that value is as contentForce data amount.Include click volume and resource data amount in attraction data volume, perhaps including the amount of thumbing up and resource data amount orIncluding sharing amount, transfer amount, comment amount and resource data amount etc. in the case of other, it is referred to above-mentioned summing value or combines weightRatio is calculated, and can also be calculated using other modes, is not construed as limiting herein.
Step 203: being less than the attraction of the object content in the attraction data volume of the first kind content to be pushedWhen data volume, it is corresponding with reference to push feature to obtain the object content.
The realization process and beneficial effect of step 202 and step 203 can be corresponded to referring to the description in step 102 and 103,Details are not described herein again.
Step 204: the first push parameter in push dimension corresponding with the first kind content to be pushed is replaced withSecond push parameter, the push dimension after being optimized.
In the present embodiment, it is described first push parameter can for push the time, push channel, push content-form or push awayThe classification channel sent.Certainly, in other embodiments of the invention, the content that can also will be pushed the time, push channel, pushMore persons in form or the classification channel of push are as the first push parameter.
It is the first kind content to be pushed corresponding first push time in the first push parameter, and described with reference to push featureIn the case where including the object content corresponding second push time, step 204 is specifically as follows: will be in push dimension with described theA kind of content to be pushed corresponding first push time replaced with for the second push time, the push dimension after being optimized.
It is the corresponding first push channel of first kind content to be pushed in the first push parameter, and described with reference to push featureIn the case where including the corresponding second push channel of object content, step 204 is specifically as follows: will be in push dimension with described theA kind of content to be pushed corresponding first pushes channel and replaces with the second push channel, the push dimension after being optimized.
It is the corresponding first content form of first kind content to be pushed in the first push parameter, and described with reference to push featureIn the case where including corresponding second content-form of object content, step 204 is specifically as follows: will be in push dimension with described theThe corresponding first content form of a kind of content to be pushed replaces with the second content-form, the push dimension after being optimized.
It is the corresponding first push classification channel of first kind content to be pushed in the first push parameter, and described with reference to pushIn the case that feature includes the corresponding second push classification channel of object content, step 204 is specifically as follows: will be in push dimensionThe first push classification channel corresponding with the first kind content to be pushed replaces with the second push classification channel, after obtaining optimizationThe push dimension.
It is replaced with by the first push parameter that will be pushed in dimension with reference to the second push parameter in push feature, thusThe push dimension after optimization is enabled to learn to reference to push the feature for attracting user possessed by feature, it is excellent in order to improveThe attraction data volume of the content to be pushed of push dimension push after change.
As shown in figure 3, the foundation by the attraction data volume of all kinds of content to be pushed as optimization push dimension, so thatPush dimension after optimization has the characteristics that attract user, and then improves the attraction force data of the content to be pushed of subsequent pushAmount.
Step 205: pushing new task to be pushed by the second push strategy, the second push strategy includes after optimizingThe push dimension.
The realization process and beneficial effect of step 205 can be corresponded to referring to the description in step 105, and details are not described herein again.
In an optional embodiment, step 205 may include:
Keyword is extracted from the object content；
Described new to filter out the preferred push content including the keyword in push task；
Corresponding preferred push content is pushed by each push dimension.
Object content may be considered the Hot Contents of user's current interest, and keyword is to have to represent in object contentThe word of property, keyword can show that keyword can be the party concerned of object content by platform to the analysis of object contentTitle (name, abbreviation, pet name etc.), be also possible to theme, time, place of object content etc..Such as: object content is certainPosition star derailed related content when, keyword may include the name of the star, the name of the star companion, " derailed " and" one or more combinations in small three ".
After determining keyword, i.e., from new to filter out preferred push content in push task, due in preferably pushingHolding includes keyword, that is, thinks that preferably pushing content is content related or approximate to object content, be that can equally attract useFamily logs in the content that platform is checked.
Wherein, it only push dimension in part may be based on being optimized with reference to push feature in the second push strategy, separatelyA part is not optimized.No matter push whether dimension optimizes, each push dimension in the second push strategy is used toPush the preferred push content in corresponding content to be pushed.
As shown in figure 3, platform is also using attraction data volume as the foundation of optimization content to be pushed, platform presses each pushDimension pushes corresponding preferred push content, so as to continue the content that the push on platform attracts user.
In present embodiment, the keyword of object content can be extracted, and filter out in new content to be pushed includingThe preferred push content of keyword reaches the work that attractive preferred push content is determined from new content to be pushedWith, the preferred push content of push dimension push is recycled, the attraction of push content is improved, convenient for attracting user to use platform,Improve the user volume of platform.
It include the second push identical with the first push parameter in push dimension in reference push feature in the present embodimentWhen parameter, the first push parameter for pushing dimension is replaced with into the second push parameter, is mentioned so that the push dimension after optimization hasThe characteristics of attraction data volume of high content to be pushed, so that the second push strategy including the push dimension after optimization pushes awayThe attraction for the new task to be pushed sent is improved, and then the user volume of platform can be improved.
Referring to Fig. 4, Fig. 4 is a kind of structure chart of content push device provided in an embodiment of the present invention, as shown in figure 4,Content push device 400 includes that pushing module 401, first obtains the acquisition module 403 of module 402, second and optimization module 404,Wherein:
Pushing module 401, for pushing task to be pushed by the first push strategy, wherein the first push strategy packetAt least two push dimensions are included, the task to be pushed includes at least two class content to be pushed, and every kind of push dimension is waited for every classContent is pushed to correspond；
First obtains module 402, for obtaining the attraction data volume of the first kind content to be pushed in preset duration, withAnd the attraction data volume of the object content in the preset duration is obtained, the object content is to wait pushing with the first kindThe highest content of attraction data volume in the content of content same type；
Second obtains module 403, is less than the target for the attraction data volume in the first kind content to be pushedWhen the attraction data volume of content, it is corresponding with reference to push feature to obtain the object content；
Optimization module 404, for being pushed based on the reference, feature pair is corresponding with the first kind content to be pushed to be pushed awayDimension is sent to optimize；
The pushing module 401 is also used to the to be pushed task new by the second push strategy push, the second push planIt slightly include the push dimension after optimization.
Optionally, the push dimension includes the first push parameter, and the first push parameter is push time, push canalThe classification channel in road, the content-form of push or push.
It optionally, include pushing parameter with the second of the first push parameter same type with reference to push feature describedWhen；
The optimization module 404 is also used to first in push dimension corresponding with the first kind content to be pushedPush parameter replaces with the second push parameter, the push dimension after being optimized.
Optionally, as shown in figure 5, the pushing module 401 includes:
Extraction unit 4011, for extracting keyword from the object content；
Screening unit 4012, for described new to be filtered out in push task including the excellent of the object content featureChoosing push content；
Push unit 4013, for pushing corresponding preferred push content by the push dimension after optimization.
Optionally, the first push strategy includes the first push dimension, and the pushing module 401 is also used to by describedFirst push dimension is pushed to the second class push content corresponding with the first push dimension in push task.
Optionally, the first push strategy further includes push substrategy, and the push substrategy is enlivens substrategy, non-Enliven substrategy, class substrategy of hanging down or keyword substrategy.
Optionally, the pushing module 401 is also used to described wait push away to target user's push by the first push dimensionSend the refinement content in task in a kind of push content corresponding with the first push dimension, the target user be with it is describedThe corresponding user of substrategy is pushed, the refinement content is content corresponding with the push substrategy.
Optionally, the attraction data volume includes pageview, click volume, the amount of thumbing up, sharing amount, transfer amount, comment amountWith at least one in resource data amount.
The content push device 400 of inventive embodiments can be realized content push device in the embodiment of the method for Fig. 1 to Fig. 3The each process realized, to avoid repeating, which is not described herein again.
The content push device 400 of the embodiment of the present invention, the push dimension after optimization can push feature middle school from referenceThe attraction data volume for how improving content is practised, the push effect of new push task is improved, so that by the second push strategyThe new task to be pushed of push is more attractive, and then the user volume of platform can be improved.
A kind of hardware structural diagram of Fig. 6 content push device of each embodiment to realize the present invention.
The content push device 600 includes but is not limited to: radio frequency unit 601, network module 602, audio output unit603, input unit 604, sensor 605, display unit 606, user input unit 607, interface unit 608, memory 609,The components such as processor 610 and power supply 611.It will be understood by those skilled in the art that content push device knot shown in Fig. 6Structure does not constitute the restriction to content driving means, and content push device may include components more more or fewer than diagram, orPerson combines certain components or different component layouts.In embodiments of the present invention, content push device includes but is not limited to handMachine, tablet computer, laptop, palm PC, car-mounted terminal, wearable device and pedometer etc..
Wherein, processor 610 is used for: pushing task to be pushed by the first push strategy, wherein the first push strategyIncluding at least two push dimensions, the task to be pushed includes at least two class content to be pushed, every kind of push dimension and every classContent to be pushed corresponds；The attraction data volume of the first kind content to be pushed in preset duration is obtained, and is obtainedThe attraction data volume of object content in the preset duration, the object content are similar with the first kind content to be pushedThe highest content of attraction data volume in the content of type；It is less than in the attraction data volume of the first kind content to be pushed describedWhen the attraction data volume of object content, it is corresponding with reference to push feature to obtain the object content；Based on described with reference to pushFeature pair push dimension corresponding with the first kind content to be pushed optimizes；By the second push strategy push it is new wait push awayTask is sent, the second push strategy includes the push dimension after optimization.
Optionally, the push dimension includes the first push parameter, and the first push parameter is push time, push canalThe classification channel in road, the content-form of push or push.
It optionally, include pushing parameter with the second of the first push parameter same type with reference to push feature describedWhen, the processor 610 is described corresponding with the first kind content to be pushed with reference to push feature pair based on described in executionWhen the step that push dimension optimizes, comprising: by first in push dimension corresponding with the first kind content to be pushedPush parameter replaces with the second push parameter, the push dimension after being optimized.
Optionally, the processor 610 is executing described the step of pushing new task to be pushed by the second push strategyWhen, comprising: keyword is extracted from the object content；Described new to filter out in push task including the keyThe preferred push content of word；Corresponding preferred push content is pushed by each push dimension.
Optionally, it includes the first push dimension that first push is tactful, and the processor 610 is described by first in executionPush strategy is when pushing the step wait push task, comprising: by the first push dimension push in push task with it is describedCorresponding second class of first push dimension pushes content.
Optionally, the first push strategy further includes push substrategy, and the push substrategy is enlivens substrategy, non-Enliven at least one in substrategy, class substrategy of hanging down or keyword substrategy.
Optionally, the processor 610 execute it is described described in push task by the first push dimension pushWhen the step of a kind of push content corresponding with the first push dimension, comprising: pushed away by the first push dimension to target userThe refinement content in a kind of push content corresponding with the first push dimension in push task is sent, the target is usedFamily is user corresponding with the push substrategy, and the refinement content is content corresponding with the push substrategy.
Optionally, the attraction data volume includes pageview, click volume, the amount of thumbing up, sharing amount, transfer amount, comment amountWith at least one in resource data amount.
Content push device 600 can be realized each process that content push device is realized in previous embodiment, to avoidIt repeats, which is not described herein again.
The content push device 600 of the embodiment of the present invention, the push dimension after optimization can push feature middle school from referenceThe attraction data volume for how improving content is practised, the push effect of new push task is improved, so that by the second push strategyThe new task to be pushed of push is more attractive, and then the user volume of platform can be improved.
It should be understood that the embodiment of the present invention in, radio frequency unit 601 can be used for receiving and sending messages or communication process in, signalSend and receive, specifically, by from base station downlink data receive after, to processor 610 handle；In addition, by uplinkData are sent to base station.In general, radio frequency unit 601 includes but is not limited to antenna, at least one amplifier, transceiver, couplingDevice, low-noise amplifier, duplexer etc..In addition, radio frequency unit 601 can also by wireless communication system and network and other setStandby communication.
Content push device provides wireless broadband internet by network module 602 for user and accesses, as helped to useIt sends and receive e-mail, browse webpage and access streaming video etc. in family.
Audio output unit 603 can be received by radio frequency unit 601 or network module 602 or in memory 609The audio data of storage is converted into audio signal and exports to be sound.Moreover, audio output unit 603 can also provide with it is interiorHold the relevant audio output of specific function of the execution of driving means 600 (for example, call signal receives sound, message sink soundEtc.).Audio output unit 603 includes loudspeaker, buzzer and receiver etc..
Input unit 604 is for receiving audio or video signal.Input unit 604 may include graphics processor(Graphics Processing Unit, GPU) 6041 and microphone 6042, graphics processor 6041 is in video acquisition modeOr the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries outReason.Treated, and picture frame may be displayed on display unit 606.Through graphics processor 6041, treated that picture frame can be depositedStorage is sent in memory 609 (or other storage mediums) or via radio frequency unit 601 or network module 602.MikeWind 6042 can receive sound, and can be audio data by such acoustic processing.Treated audio data can beThe format output that mobile communication base station can be sent to via radio frequency unit 601 is converted in the case where telephone calling model.
Content push device 600 further includes at least one sensor 605, for example, optical sensor, motion sensor and itsHis sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can basisThe light and shade of ambient light adjusts the brightness of display panel 6061, and proximity sensor can be moved to ear in content driving means 600Bian Shi closes display panel 6061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect each sideThe size of (generally three axis) acceleration upwards, can detect that size and the direction of gravity, can be used to identify content and push away when staticSend device posture (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), (such as the step counting of Vibration identification correlation functionDevice, percussion) etc.；Sensor 605 can also include fingerprint sensor, pressure sensor, iris sensor, molecule sensor, topSpiral shell instrument, barometer, hygrometer, thermometer, infrared sensor etc., details are not described herein.
Display unit 606 is for showing information input by user or being supplied to the information of user.Display unit 606 can wrapDisplay panel 6061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode can be usedForms such as (Organic Light-Emitting Diode, OLED) configure display panel 6061.
User input unit 607 can be used for receiving the number or character information of input, and generate and content push deviceUser setting and function control related key signals input.Specifically, user input unit 607 includes touch panel 6071And other input equipments 6072.Touch panel 6071, also referred to as touch screen collect the touch behaviour of user on it or nearbyMake (for example user uses any suitable objects or attachment such as finger, stylus on touch panel 6071 or in touch panelOperation near 6071).Touch panel 6071 may include both touch detecting apparatus and touch controller.Wherein, it touchesDetection device detects the touch orientation of user, and detects touch operation bring signal, transmits a signal to touch controller；TouchingIt touches controller and receives touch information from touch detecting apparatus, and be converted into contact coordinate, then give processor 610, connectIt receives the order that processor 610 is sent and is executed.Furthermore, it is possible to using resistance-type, condenser type, infrared ray and surface acoustic waveEqual multiple types realize touch panel 6071.In addition to touch panel 6071, user input unit 607 can also include other inputsEquipment 6072.Specifically, other input equipments 6072 can include but is not limited to physical keyboard, function key (such as volume controlKey, switch key etc.), trace ball, mouse, operating stick, details are not described herein.
Further, touch panel 6071 can be covered on display panel 6061, when touch panel 6071 is detected at itOn or near touch operation after, send processor 610 to determine the type of touch event, be followed by subsequent processing device 610 according to touchingThe type for touching event provides corresponding visual output on display panel 6061.Although in Fig. 6, touch panel 6071 and displayPanel 6061 is the function that outputs and inputs of realizing content push device as two independent components, but in certain implementationsIn example, touch panel 6071 and display panel 6061 can be integrated and be realized the function that outputs and inputs of content push device,Specifically herein without limitation.
Interface unit 608 is the interface that external device (ED) is connect with content push device 600.For example, external device (ED) can wrapInclude wired or wireless headphone port, external power supply (or battery charger) port, wired or wireless data port, storageCard port, port, the port audio input/output (I/O), video i/o port, ear for connecting the device with identification moduleGenerator terminal mouth etc..Interface unit 608 can be used for receiving the input (for example, data information, electric power etc.) from external device (ED)And by one or more elements that the input received is transferred in content push device 600 or it can be used for pushing away in contentIt send and transmits data between device 600 and external device (ED).
Memory 609 can be used for storing software program and various data.Memory 609 can mainly include storing program areaThe storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one functionSound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such asAudio data, phone directory etc.) etc..In addition, memory 609 may include high-speed random access memory, it can also include non-easyThe property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 610 is the control centre of content push device, is pushed using various interfaces and connection entire contentThe various pieces of device by running or execute the software program and/or module that are stored in memory 609, and are called and are depositedThe data in memory 609 are stored up, the various functions and processing data of content push device are executed, thus to content driving meansCarry out integral monitoring.Processor 610 may include one or more processing units；Preferably, processor 610 can be integrated using processingDevice and modem processor, wherein the main processing operation system of application processor, user interface and application program etc., modulationDemodulation processor mainly handles wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processingIn device 610.
Content push device 600 can also include the power supply 611 (such as battery) powered to all parts, it is preferred that electricitySource 611 can be logically contiguous by power-supply management system and processor 610, to realize that management is filled by power-supply management systemThe functions such as electricity, electric discharge and power managed.
In addition, content push device 600 includes some unshowned functional modules, details are not described herein.
Preferably, the embodiment of the present invention also provides a kind of content push device, including processor 610, and memory 609 is depositedThe computer program that can be run on memory 609 and on the processor 610 is stored up, the computer program is by processor 610Each process of above content method for pushing embodiment is realized when execution, and can reach identical technical effect, to avoid repeating,Which is not described herein again.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage mediumCalculation machine program realizes each process of above content method for pushing embodiment, and energy when the computer program is executed by processorReach identical technical effect, to avoid repeating, which is not described herein again.Wherein, the computer readable storage medium, such as onlyRead memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, abbreviationRAM), magnetic or disk etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-rowHis property includes, so that the process, method, article or the device that include a series of elements not only include those elements, andAnd further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsicElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to doThere is also other identical elements in the process, method of element, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment sideMethod can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many casesThe former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior artThe part contributed out can be embodied in the form of software products, which is stored in a storage mediumIn (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, serviceDevice, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specificEmbodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the artUnder the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very muchForm belongs within protection of the invention.