Invention content
The main purpose of the application is to provide a kind of advertisement sending method based on big data, be pushed away with solving to improve advertisementAccuracy, the validity sent, while preventing the technical issues of puzzlement that waste advertisements generate user.
To achieve the goals above, according to the one side of the application, a kind of advertisement pushing based on big data is providedMethod, including：
Demand is launched in the advertisement for receiving advertiser；
The user characteristics that demand obtains the intention crowd of advertisement dispensing are launched according to the advertisement；
User's portrait log database is inquired, is classified to all users according to the user characteristics of the intention crowd,Wherein, user's portrait log database is stored with user and the incidence relation with the feature tag of the user；
According to classification results, selected target user crowd launches demand to the target user crowd according to the advertisementLaunch advertisement.
Further, the method further includes：
Before inquiry user draws a portrait log database, the essential information of user is acquired；
Processing is marked to each essential information of user according to the essential information, obtains label of drawing a portrait substantially；
Before inquiry user draws a portrait log database, the behavioural information of user is acquired, the behavioural information is user in netThe operation behavior of page includes at least page browsing record, browsing object, browsing time or purchase information；
Processing is marked to the behavior of user according to the behavioural information, obtains behavior portrait label；
According to the basic portrait label and its corresponding personal information and behavior portrait label and its corresponding behaviorObtain personal user's portrait；
User's portrait log database is established, personal user's portrait of all users is stored.
Further, the essential information of the acquisition user, including at least one of below acquisition：
The personal information of user is acquired, the personal information includes age, gender, hobby, income or educational background；
The terminal device information for acquiring user, obtains the unique identification information of the terminal device；And
Acquire the geography information of user.
Further, the geography information of the acquisition user, including：
Target terminal is determined according to the unique identification information, and the geographical position of the target terminal is obtained using LBS technologiesIt sets.
Further, user's portrait log database is also stored with user and feature corresponding with the user and its spyValue indicative；
The user characteristics according to the intention crowd classify to all users, including：
Calculate the summation of the characteristic value of the user of all user characteristics including the intention crowd；
According to preset classification range, all users are classified according to the summation.
Further, demand is launched in the advertisement for receiving advertiser, including：
Demand is launched in the advertisement for recording all advertisers, and is established advertiser's large database concept and stored.
To achieve the goals above, according to the another aspect of the application, a kind of advertisement pushing based on big data is providedDevice.
Described device includes：
Demand is launched in demand receiving unit, the advertisement for receiving advertiser；
Characteristics determining unit, the user for launching the intention crowd that demand obtains advertisement dispensing according to the advertisement are specialSign；
User's taxon, for inquiring user's portrait log database, according to the user characteristics pair of the intention crowdAll users classify, wherein the user draw a portrait log database be stored with user and with the feature tag of the userIncidence relation；
Advertisement pushing unit, for according to classification results, selected target user crowd, according to the advertisement launch demand toThe target user crowd launches advertisement.
Further, described device further includes：
First information collecting unit, for before inquiry user draws a portrait log database, acquiring the essential information of user；
Portrait tag processes unit, for place to be marked to each essential information of user according to the essential informationReason, obtains label of drawing a portrait substantially；
Second information acquisition unit, for before inquiry user draws a portrait log database, acquiring the behavioural information of user, instituteIt is operation behavior of the user in webpage to state behavioural information, includes at least page browsing record, browsing object, browsing time or purchaseInformation；
Behavior tag processes unit is gone for processing to be marked to the behavior of user according to the behavioural informationFor label of drawing a portrait；
Individual's portrait generation unit, for being drawn according to the basic portrait label and its corresponding personal information and the behaviorAs label and its corresponding behavior obtain personal user's portrait；
Database generation unit stores personal user's portrait of all users for establishing user's portrait log database.
Further, the first information collecting unit includes at least one of following：
Personal information acquisition module, the personal information for acquiring user, the personal information include age, gender, loveGood, income or educational background；
Terminal device information acquisition module, the terminal device information for acquiring user obtain the terminal device onlyOne identification information；And
Geographical information collection module, the geography information for acquiring user.
Further, the geographical information collection module includes：
Data acquisition submodule obtains institute for determining target terminal according to the unique identification information using LBS technologiesState the geographical location of target terminal.
Further, user's portrait log database is also stored with user and feature corresponding with the user and its spyValue indicative；
User's taxon includes：
Computing module, the summation of the characteristic value of the user for calculating all user characteristics including the intention crowd；
Sort module, for according to preset classification range, all users to be classified according to the summation.
Further, the demand receiving unit includes：
Demand is launched in the advertisement for recording all advertisers, and is established advertiser's large database concept and stored.
In the embodiment of the present application, special by the user with intention crowd in such a way that user draws a portrait log databaseSign matching, achievees the purpose that classify to user, to realize the technique effect for improving advertisement pushing accuracy, and then solvesThe technical issues of user is harassed in reduction advertisement of having determined.
Specific implementation mode
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present applicationAttached drawing, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described embodiment is onlyThe embodiment of the application part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill peopleThe every other embodiment that member is obtained without making creative work should all belong to the model of the application protectionIt encloses.
It should be noted that the term " comprising " in the description and claims of this application and above-mentioned attached drawing and " toolHave " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unitProcess, method, system, product or equipment those of are not necessarily limited to clearly to list step or unit, but may include without clearIt is listing to Chu or for these processes, method, product or equipment intrinsic other steps or unit.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phaseMutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is the flow diagram of advertisement sending method one embodiment described herein based on big data.
The method includes S101~S104.
Demand is launched in S101, the advertisement for receiving advertiser.
Demand can be specifically launched by the advertisement that preset api interface or SDK interface advertisers send, it is described wideAccuse launch need refer to launch advertisement, intention crowd (such as women, a line city, food of liking to be beautiful, microblogging control, purchased vehicle, financing,The features such as game).
Further, demand is launched in the advertisement for receiving advertiser, including：Recording the advertisement dispensing of all advertisers needsIt asks, and establishes advertiser's large database concept and store.By the foundation of advertiser's large database concept, to carry out pipe to advertiserReason.
S102, the user characteristics that demand obtains the intention crowd of advertisement dispensing are launched according to the advertisement, pass through the meaningUser all in user's portrait log database is classified to the user characteristics of crowd, to improve the essence of advertisement pushingDegree.
S103, inquiry user's portrait log database, carry out all users according to the user characteristics of the intention crowdClassification, wherein user's portrait log database is stored with user and the incidence relation with the feature tag of the user.
Specifically, network crawler technology can be utilized to obtain third-party platform user data, and real-time update, by rightThe user data obtained in real time carries out portrait analysis, establishes the portrait of each user to get to the feature tag of each user.InstituteStating web crawlers technology and third-party platform can be received by preset data-interface (such as api interface, SDK interfaces), andData are tentatively cleaned, user's portrait log database is stored in.
The purpose of the step is that the user characteristics according to intention crowd classify to user, and solution never distinguishes user'sExtensive style, formula of casting net indifference advertisement pushing caused by the wasting of resources, while avoid advertisement caused by unintended user be strandedDisturb problem.
Specifically, user's portrait log database is also stored with user and feature corresponding with the user and its spyValue indicative；The user characteristics according to the intention crowd classify to all users, including：It includes the meaning to calculate allTo the summation of the characteristic value of the user of the user characteristics of crowd；It is according to the summation that institute is useful according to preset classification rangeClassify at family.The application is special to calculate the user including intention crowd assigning user characteristics in a manner of characteristic valueUser is carried out category division by the summation of the characteristic value of sign according to summation.Different classes of corresponding range can be specifically set, sentencedClassification belonging to the summation of breaking, it is final to realize user's classification.
Specifically, the result that user classifies can distinguish the rigid level of interest of the advertisement according to user,That is classification.Such as, user very interested can be divided into, user interested, general user, the user that loses interest in, detested very muchUser gradation is other.It should be noted that this mode that user is carried out to classifying and dividing includes but not limited to this mode.
S104, according to classification results, selected target user crowd launches demand to the target user according to the advertisementCrowd launches advertisement.
The application utilizes the matching of the user characteristics and the log database of user's portrait of advertiser intention user, realization pairUser classifies, and the accuracy for improving advertisement and launching finally is realized according to classification results, has achieved the purpose that save resource, extensivelyThe specific aim that accurate push improves advertisement is accused, the harassing and wrecking of extensive style, formula of casting net advertisement pushing to user are avoided.
Specifically, method described herein can be applied to mobile terminal, can also be applied to page end.Such as Baidu is searchedGou Deng portal websites can also be applied to net purchase platform (such as Taobao).Such as certain shopping website, by method application described hereinAfter shopping website, specifically, advertiser can carry out sending advertisement dispensing demand, example using the interface that shopping website opensSuch as, the age (20~29) of intention crowd, gender (female), commodity (nightwear) etc..The shopping website receives the advertisement and throwsAfter putting demand, need to classify to user according to advertisement dispensing, for the interested user of the commodity may be pushed awayIt send, to improve the buying rate of the commodity.
The application user draws a portrait log database using web crawlers technology real-time reception user data, so as to real-timeUser characteristics are analyzed, to the precision that the user characteristics improved according to intention crowd classify to user, are protectedIt has demonstrate,proved and has pushed advertisement interested to user in real time, to improve the push effect of advertisement.
Fig. 2 is the flow diagram for establishing user's portrait log database one embodiment.
The method includes S201~S205.
S201, inquiry user draw a portrait log database before, acquire the essential information of user.
Specifically, at least one of including acquisition is following：Acquire user personal information, the personal information include the age,Gender, hobby, income or educational background；The terminal device information for acquiring user, obtains the unique identification information of the terminal device；WithAnd the geography information of acquisition user.The unique identification information of the terminal can be the MAC Address, handset serial, hand of terminalMachine number etc., specifically, terminal device can be the equipment such as mobile phone, PC machine, notebook, pad.When the terminal device is mobile phoneWhen, the terminal device information of user can access the interface access terminal device system of webpage by user, to obtain terminalFacility information.And personal information can be obtained according to the log-on message of user, it should be noted that the personal information of userAcquisition modes include but not limited to obtained according to the log-on message of user, the mode of all personal information that can obtain userAll it is the protection domain of the application.
Further, the geography information of the acquisition user, including：Target terminal is determined according to the unique identification information,The geographical location of the target terminal is obtained using LBS technologies.
S202, processing is marked to each essential information of user according to the essential information, obtains mark of drawing a portrait substantiallyLabel.
Processing is marked to the essential information of user in the application the application, obtains the portrait mark that can represent user spyLabel, are handled by labeling, to classify to user.Specifically, the essential information of user include the age, gender, educational background,Hobby etc., as sex character can be replaced with portrait label S1.
S203, before inquiry user draws a portrait log database, acquire the behavioural information of user, the behavioural information is userIn the operation behavior of webpage, page browsing record, browsing object, browsing time or purchase information are included at least.
S204, processing is marked to the behavior of user according to the behavioural information, obtains behavior portrait label.
Specifically, user behavior characteristics such as browsing object can be indicated with A1.
S205, according to the basic portrait label and its corresponding personal information and behavior portrait label and its correspondingBehavior obtains personal user's portrait；
S206, user's portrait log database is established, stores personal user's portrait of all users.
Herein described user's portrait log database includes two parts, and the generation of personal user's portrait and group drawThe foundation of picture draws a portrait to obtain user's portrait log database according to all personal users.The application by essential information andThe labeling of behavioural information is handled, and saves the calculation amount that the later stage classifies to user according to the user characteristics of intention crowd,Improve the speed of service.
It can be seen from the above description that the present invention realizes following technique effect：Accurately advertisement pushing is introducedEffective independent visitor demand it is stronger, wish higher, user is ready to spend more times to browse more content of pages, poleBig improves user's registration amount and product popularity；The popularization power of promotion item is effectively increased, and then improves resource and cashesAbility reduces harassing and wrecking of the advertisement to user.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructionsIt is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with notThe sequence being same as herein executes shown or described step.
According to embodiments of the present invention, a kind of dress for implementing the above-mentioned advertisement sending method based on big data is additionally providedIt sets, as shown in figure 3, the device includes：
Demand is launched in demand receiving unit 10, the advertisement for receiving advertiser；
Characteristics determining unit 20, the user for launching the intention crowd that demand obtains advertisement dispensing according to the advertisement are specialSign；
User's taxon 30, for inquiring user's portrait log database, according to the user characteristics of the intention crowdClassify to all users, wherein user's portrait log database is stored with user and the feature tag with the userIncidence relation；
Advertisement pushing unit 40, for according to classification results, selected target user crowd to launch demand according to the advertisementAdvertisement is launched to the target user crowd.
The application is to be carried out to user according to the user characteristics of intention crowd by the foundation of user's portrait log databaseClassification provides foundation and improves the accuracy of advertisement pushing to improve the specific aim of advertisement pushing.
Further, described device further includes：
First information collecting unit, for before inquiry user draws a portrait log database, acquiring the essential information of user；
Portrait tag processes unit, for place to be marked to each essential information of user according to the essential informationReason, obtains label of drawing a portrait substantially；
Second information acquisition unit, for before inquiry user draws a portrait log database, acquiring the behavioural information of user, instituteIt is operation behavior of the user in webpage to state behavioural information, includes at least page browsing record, browsing object, browsing time or purchaseInformation；
Behavior tag processes unit is gone for processing to be marked to the behavior of user according to the behavioural informationFor label of drawing a portrait；
Database generation unit, for being drawn a portrait according to the basic portrait label and its corresponding personal information and the behaviorLabel and its corresponding behavior obtain user's portrait log database.
Further, the first information collecting unit includes at least one of following：Personal information acquisition module, for acquiringThe personal information of user, the personal information include age, gender, hobby, income or educational background；Terminal device information acquires mouldBlock, the terminal device information for acquiring user obtain the unique identification information of the terminal device；And geographical information collectionModule, the geography information for acquiring user.Further, the geographical information collection module includes：Data acquisition submodule,For determining target terminal according to the unique identification information, the geographical location of the target terminal is obtained using LBS technologies.
Further, user's portrait log database is also stored with user and feature corresponding with the user and its spyValue indicative；User's taxon includes：
Computing module, the summation of the characteristic value of the user for calculating all user characteristics including the intention crowd；
Sort module, for according to preset classification range, all users to be classified according to the summation.
Further, the demand receiving unit includes：
Demand is launched in the advertisement for recording all advertisers, and is established advertiser's large database concept and stored.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with generalComputing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formedNetwork on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are storedBe performed by computing device in the storage device, either they are fabricated to each integrated circuit modules or by theyIn multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specificHardware and software combines.
The foregoing is merely the preferred embodiments of the application, are not intended to limit this application, for the skill of this fieldFor art personnel, the application can have various modifications and variations.Within the spirit and principles of this application, any made by repairChange, equivalent replacement, improvement etc., should be included within the protection domain of the application.