CN104035926A - Internet information release method and system - Google Patents
Internet information release method and system Download PDFInfo
- Publication number
- CN104035926A CN104035926A CN201310068649.2A CN201310068649A CN104035926A CN 104035926 A CN104035926 A CN 104035926A CN 201310068649 A CN201310068649 A CN 201310068649A CN 104035926 A CN104035926 A CN 104035926A
- Authority
- CN
- China
- Prior art keywords
- grp
- reach
- input
- input activity
- activity
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention provides an Internet information release method and system. The method includes obtaining user browsing behaviors of publicity information in the same type in a plurality of historical release activities; obtaining the total number of times of exposure of the publicity information in the type in every release activity in accordance with the obtained user browsing behaviors; obtaining a total gross rating point (GRP) of the publicity information in the type in the release activity according to the total number of audience in every release activity; determining the N + Reach in every release activity in accordance with the viewing times of the same user for the publicity information in the same release activity; obtaining the functional relationship between the GRP and the N + Reach according to GRPs and N + Reach of the plurality of release activities; managing subsequent release of the publicity information in the type in accordance with the obtained functional relationship.
Description
Technical field
The present invention relates to field of information processing, relate in particular to a kind of input and system of internet information.
Background technology
The effect of advertisement putting refers to that advertiser is after throwing in advertisement, by throw in that media bring in brand value, sales volume or otherwise growth.Arrival rate curve (Reach Curve) is a kind of important indicator of weighing advertisement delivery effect.The curve that arrival rate curve is comprised of injected volume and the arrival rate of advertising campaign, it can accurately reflect the growth pattern of watching the number of advertisement along with the increase of injected volume.In arrival rate curve map, ordinate is arrival rate (Reach), and horizontal ordinate is general, adopts total audience ratings to represent.Total audience ratings in TV refers to the audience ratings sum of certain a period of time, for internet, the total audience ratings of GRP (Gross Rating Points) generally refers at a specific region and the total degree of the advertising creative of certain advertising campaign of all target audience flows in the time.Therefore, arrival rate curve can be by client for predicting the arrival rate of expecting under specific injected volume, as the reference value of passing judgment on himself advertisement delivery effect, thereby makes client can carry out better the budget allocation of media-planning.
Traditional media conventionally adopts the method for sampling when generating arrival rate curve, by the mode of stratified sampling, obtain representative sample, each sample is with it with weight coefficient, make final sample population can represent the view as a whole population of location, and reflect medium audience situation and coverage effect by the viewing behavior of real-time tracing sample.For the GRP of certain arrival rate to be estimated, media-planning makes according to the historical data of rating sample the media-planning that injected volume just equals this GRP, by the historical viewing-data of sample under this media-planning, estimates the arrival rate under this GRP.The shortcoming that such media are estimated instrument is that the man power and material that need to cost a lot of money removes to build representational sample, only supports to formulate according to period and advertisement position the advertisement mode of waiting simultaneously.And than traditional media, more diversification of the advertisement mode on internet.In the epoch advertisement of large data in future, from the purchase of a location advertising, can develop into gradually and move and inspire concrete exposure and buy advertisement.Therefore, formulate the method for media-planning and be not suitable for the result estimate solution based on exposure.
Summary of the invention
The invention provides a kind of input and system of internet information, the technical matters that solve is impression information how effectively.
For solving the problems of the technologies described above, the invention provides following technical scheme:
A put-on method for internet information, comprising:
The user browsing behavior of the advertisement information that obtains same type in a plurality of historical input activities;
According to the user browsing behavior obtaining, obtain the exposure total degree of the advertisement information of the type in each input activity;
According to the sum of audient in each input activity, the total audience ratings GRP of the advertisement information that obtains the type in this input activity; And, and according in same input activity, same user watches the number of times of this advertisement information, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
According to the GRP of a plurality of input activities and N+Reach, obtain the funtcional relationship between GRP and N+Reach;
According to the funtcional relationship obtaining, the follow-up input of the advertisement information of the type is managed.
Preferably, described method also has the function f (GRP between following features: GRP and N+Reach
i) can make
value minimum, wherein GRPi represents the GRP of i historical input activity, with Reachi, represents i movable N+Reach, wherein the Monitoring Data of one group of history input activity can be expressed as D={ (GRPi, Reachi) | i=1,2 ..., M}; Wherein, M is the sum of historical input activity, and GRPi and Reachi are nonnegative real number.
Preferably, described method also has following features: the funtcional relationship between described GRP and N+Reach is linear function f (GRP)=a * GRP+b, wherein:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
Preferably, described method also has following features: the funtcional relationship between described GRP and N+Reach is curvilinear function f (GRP)=(ea * GRP+b-1)/(ea * GRP+b+1) with exponential form, and wherein parameter a and b are by minimizing
calculate.
Preferably, described method also has following features: according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed, comprising:
When obtaining the arrival rate of input activity, needed total exposure amount while obtaining this arrival rate according to the funtcional relationship of calculating;
According to total exposure amount, calculate the input cost of the input activity of this advertisement information.
Preferably, described method also has following features: according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed, comprising:
Obtain the funtcional relationship between GRP and N+Reach in each input activity;
When obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtain GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity;
According to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input.
A jettison system for internet information, comprising:
The first acquisition device, for obtaining same advertisement information at the user browsing behavior of a plurality of historical input activities;
Statistic device, is connected with described the first acquisition device, for according to the user browsing behavior obtaining, obtains the exposure total degree of this advertisement information in each input activity;
Calculation element, is connected with described statistic device, according to the sum of audient in each input activity, obtains the GRP of this advertisement information in this input activity; And, and according in same input activity, same user watches the number of times of this advertisement information, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
The second acquisition device, is connected with described calculation element, according to the GRP of a plurality of input activities and N+Reach, obtains the funtcional relationship between GRP and N+Reach;
Management devices, is connected with described the second acquisition device, for according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed.
Preferably, described system also has the function f (GRP between following features: GRP and N+Reach
i) can make
value minimum, wherein GRPi represents the GRP of i historical input activity, with Reachi, represents i movable N+Reach, wherein the Monitoring Data of one group of history input activity can be expressed as D={ (GRPi, Reachi) | i=1,2 ..., M}; Wherein, M is the sum of historical input activity, and GRPi and Reachi are nonnegative real number.
Preferably, described system also has following features: the funtcional relationship between described GRP and N+Reach is linear function f (GRP)=a * GRP+b, wherein:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
Preferably, described system also has following features: the funtcional relationship between described GRP and N+Reach is curvilinear function f (GRP)=(ea * GRP+b-1)/(ea * GRP+b+1) with exponential form, and wherein parameter a and b are by minimizing
calculate.
Preferably, described system also has following features: described management devices, comprising:
The first acquisition module, for when obtaining the arrival rate of input activity, needed total exposure amount while obtaining this arrival rate according to the funtcional relationship of calculating;
Computing module, for according to total exposure amount, calculates the input cost of the input activity of this advertisement information.
Preferably, described system also has following features: described management devices, comprising:
The second acquisition module, for obtaining the funtcional relationship between each input activity GRP and N+Reach;
The 3rd acquisition module, is connected with described the second acquisition module, for when obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtains GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity;
Select module, be connected with described the 3rd acquisition module, according to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input.
Embodiment provided by the invention, first monitor historical advertisement putting activity with accumulation Monitoring Data, then according to Monitoring Data, generate client's arrival rate curve, by using the true GRP monitoring in history input activity and arrival rate as input data, by data modeling, excavate GRP implicit in client's self historical data and the function between arrival rate, to generate the distinctive arrival rate curve of client, and adopted the distinctive full flow Monitoring Data in internet directly exposure and arrival rate to be carried out to modeling, avoided generating the sampling process arriving in rate curve, therefore can be applicable to well the result estimate solution based on exposure, again according to obtaining model, advertisement is carried out to autotelic input, improve rating scope and the coverage effect of advertisement.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the input embodiment of internet information provided by the invention;
Fig. 2 is the schematic flow sheet of the function acquisition methods between GRP and arrival rate in the present invention;
Fig. 3 is the schematic diagram of the function between GRP and arrival rate in the present invention;
Fig. 4 is the structural representation of information jettison system embodiment provided by the invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, the present invention is described in further detail below in conjunction with the accompanying drawings and the specific embodiments.It should be noted that, in the situation that not conflicting, the embodiment in the application and the feature in embodiment be combination in any mutually.
Fig. 1 is the schematic flow sheet of the input embodiment of internet information provided by the invention.Embodiment of the method shown in Fig. 1, comprising:
Step 101, the user browsing behavior of advertisement information in a plurality of historical input activities that obtains same type.
Wherein the advertisement information of same type can have a plurality of different definition, for example, and same client's advertisement information, the advertisement information of same publicity website or the advertisement information of same class commodity; Certainly, can also be by the further refinement of type, as the whole advertisement informations of same client in same website.
Step 102, according to the user browsing behavior that obtains, obtain the exposure total degree of the advertisement information of the type in each input activity;
Step 103, according to the sum of audient in each input activity, the total audience ratings of the advertisement information that obtains the type in this input activity; And, and according in same input activity, same user watches the number of times of the advertisement information of the type, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
Wherein total audience is for throwing in the number that can watch this advertisement in region;
Step 104, according to the GRP of a plurality of input activities and N+Reach, obtain the funtcional relationship between GRP and N+Reach;
The funtcional relationship that step 105, basis obtain, manages the follow-up input of this advertising campaign.
Embodiment of the method provided by the invention, the arrival rate curve that collects each frequency carries out integral body and throws in effect displaying, according to data fitting method, obtain after the fitting function of N+Reach of the different frequencys, the function curve of each function is the arrival rate curve of the matching N+ frequency out.The arrival rate curve of each frequency is listed in same curve map, the whole structure that can clearly show client coverage goal crowd when the exposure of input appointment, according to by effect as a reference, carry out the input of follow-up l again, make input have more purpose.
When receiving certain client's advertisement putting request, obtain the corresponding relation of this client GRP and N+Reach on difference publicity website;
According to this corresponding relation, determine required time and the operation cost of GRP that will reach expection;
According to required time and operation cost, select optimum publicity website to carry out advertisement putting.
Further, receive a certain client to a plurality of advertisement informations of identical product after, according to the corresponding relation of each advertisement information GRP and N+Reach on same website;
Select and throw in the best advertisement information of effect, wherein throw in the best advertisement information of effect and refer to the advertisement information that can bring maximum arrival rate under same GRP drops into
Increase the input dynamics of the best advertisement information of this input effect;
Again or,
In conjunction with such scheme, be chosen on optimum website and throw in optimum advertisement information, realize the optimum efficiency of advertisement putting.
Below embodiment of the method provided by the invention is described further:
Below take this advertisement information describes as advertising message as example, and wherein this advertisement information can be also other other information that help users to understand.
For the advertising campaign of throwing on the internet, by adding monitoring code or add technological means such as monitoring script etc. to obtain unique identification and the network behavior of Internet user when the advertisement position of browse advertisements activity in website in advertisement, and store into for storing the log server of data by Internet Transmission.
The Monitoring Data of a historical input activity is taken out from log server, then according to the user behaviors log of browsing of all Cookie in Monitoring Data, add up the exposure total degree of this advertising campaign and the N+Reach of each frequency, wherein:
Exposure total degree is the total degree that all Internet users browse advertisement in this input activity;
N+Reach is for this reason in input activity, and the sum that the access frequency is more than or equal to the visiting Cookie of N time accounts for the number percent of whole Cookie.
Exposure total degree is converted into GRP:
Internet advertising GRP=advertisement exposure total degree ÷ total audience * 100,
For Internet advertising, total audience is for throwing in netizen's sum of region.
The GRP of all historical input activities is become to scatter diagram with N+Reach data creating, and obtain the funtcional relationship between GRP and N+Reach according to each data point matching.Wherein:
For each different frequency N, GRP and the N+Reach of all historical input activity calculating in previous step are made into scatter diagram.Wherein, the corresponding activity of each data point in scatter diagram, the horizontal ordinate of data point is movable GRP, ordinate is movable N+Reach.
For some N, according to all data points in scatter diagram, derive the funtcional relationship between GRP and N+Reach.Here use GRP
ithe GRP that represents i input activity, uses Reach
irepresent i movable N+Reach.The Monitoring Data of one group of historical input activity can be expressed as D={ (GRP so
i, Reach
i) | i=1,2 ..., M}.Wherein, M is the sum of input activity, GRP
iand Reach
ibe nonnegative real number.
The matching target of carrying out data fitting according to each input activity is the funtcional relationship between GRP and N+Reach, finds a function (being designated as f), with the functional value of f (GRP), estimates corresponding N+Reach.
In practical application, have several different methods from historical data D, to derive optimum function f, common method comprises regretional analysis and method of interpolation etc.In derivation, optimum function is tried to achieve based on minimizing functional value for estimating and the error between real N+Reach.
After calculating optimal function f, we just can set up the exposure of advertisement and the contact between arrival rate, and utilize this contact to manage the input of advertising campaign.For example:
During the arrival rate of given input activity, according to the inverse function of the function f of calculating, obtain needed total exposure amount while reaching arrival rate, thereby estimate the total input that need to carry out advertisement putting;
For given total injected volume, obtain the funtcional relationship between GRP and N+Reach in each input activity; When obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtain GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity, and according to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input; By obtaining the arrival rate of exposure on different media resources, thereby select the media of effect optimum further to throw in.
Except above-mentioned two examples, according to this method matching arrival rate curve out, be also applicable to anyly need to estimate arrival rate or according to arrival rate, estimate the application scenarios of exposure according to exposure.
Than traditional method, technical advantage of the present invention is:
The present invention generates and arrives the Internet advertising data that rate curve uses and be full flow monitoring, and the GRP and the arrival rate that therefore for generating, arrive rate curve are actual value, have avoided the error of bringing due to sampling in the methods of sampling; According to the activity data in a large amount of Internet advertising data with identical input pattern (as client's character, media resource etc.), generate the arrival rate curve that this class is thrown in pattern, thereby be embodied as the function of customization arrival rate curve.
Fig. 2 is the schematic flow sheet of the function acquisition methods between GRP and arrival rate in the present invention.Described in Fig. 2, method comprises the steps:
210: Internet advertising monitoring system, for storing, record and extract the network behavior information of the subscriber computer of each visiting user object (being Cookie) representative;
First be that each visiting Cookie distributes a unique identification (ID), extract and record the information of the subscriber computer of each Cookie representative in server, comprise one or more in the machine informations such as IP address, browser type and version thereof, OS Type and version and screen resolution.
The information of the Cookie subscriber computer of record and/or to browse behavior as shown in table 1.
Visiting | ID | IP address | Browser | Browse behavior |
Cookie1 | 10889560 | 202.168.1.0 | IE6?V1 | Movable 1 |
Cookie2 | 10889561 | 202.168.1.1 | IE6?V1 | Movable 1 |
Cookie1 | 10889560 | 202.168.1.0 | IE8 | Movable 2 |
…… | ? | ? | ? | ? |
Table 1
220: historical data statistical module, counts GRP and the Reach data of each input activity for the daily record from monitoring of the advertisement system;
For example: movable 1 has thrown in the time of 1 month, and server has been received the travel log of 1,000,000 this movable advertisement altogether, every daily record comprises the much informations such as the ID of Cookie and IP address, browser type and version thereof.According to the content of every daily record, add up, this movable total exposure amount is 1,000,000.Among the Cookie of these exposures of generation, there are 350,000 Cookie to watch once or once above this advertisement, there are 200,000 to watch secondary or above this advertisement of secondary.The total number of persons of supposing the audient of this region is 500,000, and all cookie number is also 500,000, and so each statistics of movable 1 can be calculated as follows:
GRP=1,000,000/500,000×100=200;
1+Reach=350,000/500,000=70%;
2+Reach=200,000/500,000=40%。
Each activity is carried out respectively to data statistics, can obtain GRP and the N+Reach of all input activities.
As shown in table 2, the GRP of 3 actual advertisement activities and 1+Reach are to the statistics of 5+Reach.
Movable | GRP | 1+Reach | 2+Reach | 3+Reach | 4+Reach | 5+Reach |
Movable 1 | 3.8 | 3% | 2% | 1% | 1% | 1% |
Movable 2 | 6.2 | 4% | 3% | 2% | 1% | 1% |
Movable 3 | 19.3 | 11% | 6% | 4% | 3% | 2% |
…… | ? | ? | ? | ? | ? | ? |
Table 2
230: Function Fitting module, for go out the funtcional relationship between GRP and each frequency N+Reach according to the Monitoring Data the Fitting Calculation of input activity;
For the historical data of collecting, GRP is used as to the independent variable of objective function, fixedly the worthwhile dependent variable of making objective function of the N+Reach of frequency N, utilizes Function Fitting or method of interpolation to obtain the funtcional relationship between GRP and 1+Reach.For example, while estimating the funtcional relationship between GRP and 1+Reach, by each movable GRP and 1+Reach, calculate, i.e. the data of the 2nd row and the 3rd row in table 2.
The method of utilizing data point to carry out Function Fitting has a lot, shows as an example the process of Function Fitting in this example with regretional analysis.
The method of regretional analysis is obtained best objective function f by minimize the functional value of objective function and the residual error between true Reach in historical data.Under different preconditions, diversified regression model can be used to same regretional analysis problem.The linear regression analysis of standard of take is below described the process of regretional analysis as example.The target of linear regression is from linear function set { f (GRP)=a * GRP+b|a, b is real number } based on following target, select best parameter a and b, make the gap between corresponding functional value and real Reach as much as possible little, obtain a and the b that meet following formula.
Frequency N for fixing, uses GRP
ithe GRP that represents i input activity, Reach
irepresent i movable N+Reach, the thought based on least square method, optimum parameter a and b equal respectively:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
According to the parameter a of above-mentioned optimum and b, corresponding linear function f (x)=ax+b is required GRP and the corresponding relation between Reach.For example, for GRP and the 1+Reach of 3 groups of activities of table 2, calculate, linear regression fit optimal function is out as minor function:
1+Reach=0.004×GRP+0.011
Except linear function, if the funtcional relationship between hypothesis GRP and N+Reach is curvilinear function f (GRP)=(e
a * GRP+b-1)/(e
a * GRP+b+ 1) mathematical method, solving by nonlinear optimization minimizes
can simulate optimal function is as minor function
1+Reach=(e
0.012×0.55+b-1)/(e
0.012×GRP+0.55+1)
240: arrival rate curve generation module, for matching GRP and the function between N+Reach is out converted into the curve map of N+Reach, and the arrival rate curve that collects each frequency to be when showing that client throws in different flow, whole trend of throwing in effect changes.
Obtain after the function between GRP and N+Reach, by describing function curve, draw arrival rate curve.In curve map, horizontal ordinate is GRP, and ordinate is Reach;
Fig. 3 is the schematic diagram of the function between GRP and arrival rate in the present invention.At all arrival rate curves, in same curve map, draw, show that the integral body under different exposures is thrown in effect.
Fig. 4 is the structural representation of information jettison system embodiment provided by the invention.System shown in Figure 4 embodiment, comprising:
The first acquisition device 401, for obtaining the advertisement information of same type at the user browsing behavior of a plurality of historical input activities;
Statistic device 402, is connected with described the first acquisition device 401, for according to the user browsing behavior obtaining, obtains the exposure total degree of the advertisement information of the type in each input activity;
Calculation element 403, is connected with described statistic device 402, according to the sum of audient in each input activity, and the total audience ratings of the advertisement information that obtains the type in this input activity; And, and according in same input activity, same user watches the number of times of this advertisement information, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
The second acquisition device 404, is connected with described calculation element 403, according to the GRP of a plurality of input activities and N+Reach, obtains the funtcional relationship between GRP and N+Reach;
Management devices 405, is connected with described the second acquisition device 404, for according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed.
Wherein, described the second acquisition device 404, for:
For each different frequency N, the GRP of all input activities and N+Reach are made into scatter diagram; Wherein, the corresponding activity of each data point in scatter diagram, the horizontal ordinate of data point is movable GRP, ordinate is movable N+Reach;
For some N, according to all data points in scatter diagram, derive the funtcional relationship between GRP and N+Reach, wherein GRP
ithe GRP that represents i input activity, uses Reach
irepresent i movable N+Reach, wherein the Monitoring Data of one group of input activity can be expressed as D={ (GRP
i, Reach
i) | i=1,2 ..., M}; Wherein, M is the sum of input activity, GRP
i, and Reach
ibe nonnegative real number;
The matching target of carrying out data fitting according to the Monitoring Data of every group of input activity is the funtcional relationship between GRP and n+Reach, finds a function f (GRP), is used for estimating corresponding N+Reach or estimating corresponding GRP according to N+Reach according to GRP.
Wherein, the funtcional relationship between described GRP and N+Reach is linear function f (GRP)=a * GRP+b, a wherein, and b is real number, and the value of a and b can make
value minimum.
Wherein:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
Except linear function, if the funtcional relationship between hypothesis GRP and N+Reach is curvilinear function f (GRP)=(e with exponential form
a * GRP+b-1)/(e
a * GRP+b+ 1) mathematical method that, parameter a and b solve by nonlinear optimization minimizes
calculate.
Wherein, described management devices 405, comprising:
The first acquisition module, for when obtaining the arrival rate of input activity, needed total exposure amount while obtaining this arrival rate according to the funtcional relationship of calculating;
Computing module, for according to total exposure amount, calculates the input cost of the input activity of this advertisement information.
Wherein, described management devices 405, comprising:
The second acquisition module, for obtaining the funtcional relationship between each input activity GRP and N+Reach;
The 3rd acquisition module, is connected with described the second acquisition module, for when obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtains GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity;
Select module, be connected with described the 3rd acquisition module, according to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input.
System embodiment provided by the invention, the arrival rate curve that collects each frequency carries out the integral body input effect displaying of input activity, according to data fitting method, obtain after the fitting function of N+Reach of the different frequencys, the function curve of each function is the arrival rate curve of the matching N+ frequency out.The arrival rate curve of each frequency is listed in same curve map, the whole structure that can clearly show client coverage goal crowd when the exposure of input appointment, according to by effect as a reference, carry out the input of follow-up l again, make input have more purpose.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited to this, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain described in claim.
Claims (12)
1. a put-on method for internet information, is characterized in that, comprising:
The user browsing behavior of the advertisement information that obtains same type in a plurality of historical input activities;
According to the user browsing behavior obtaining, obtain the exposure total degree of the advertisement information of the type in each input activity;
According to the sum of audient in each input activity, the total audience ratings GRP of the advertisement information that obtains the type in this input activity; And, and according in same input activity, same user watches the number of times of this advertisement information, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
According to the GRP of a plurality of input activities and N+Reach, obtain the funtcional relationship between GRP and N+Reach;
According to the funtcional relationship obtaining, the follow-up input of the advertisement information of the type is managed.
2. method according to claim 1, is characterized in that, the function f (GRP between GRP and N+Reach
i) can make
value minimum, GRP wherein
ithe GRP that represents i historical input activity, represents i movable N+Reach with Reachi, and wherein the Monitoring Data of one group of historical input activity can be expressed as D={ (GRP
i, Reach
i) | i=1,2 ..., M}; Wherein, M is the sum of historical input activity, GRP
iand Reach
ibe nonnegative real number.
3. method according to claim 2, is characterized in that, the funtcional relationship between described GRP and N+Reach is linear function f (GRP)=a * GRP+b, wherein:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
4. method according to claim 2, is characterized in that, the funtcional relationship between described GRP and N+Reach is curvilinear function f (GRP)=(e with exponential form
a * GRP+b-1)/(e
a * GRP+b+ 1), wherein parameter a and b by minimizing
calculate.
5. method according to claim 1, is characterized in that, according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed, and comprising:
When obtaining the arrival rate of input activity, needed total exposure amount while obtaining this arrival rate according to the funtcional relationship of calculating;
According to total exposure amount, calculate the input cost of the input activity of this advertisement information.
6. method according to claim 1, is characterized in that, according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed, and comprising:
Obtain the funtcional relationship between GRP and N+Reach in each input activity;
When obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtain GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity;
According to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input.
7. a jettison system for internet information, is characterized in that, comprising:
The first acquisition device, for obtaining same advertisement information at the user browsing behavior of a plurality of historical input activities;
Statistic device, is connected with described the first acquisition device, for according to the user browsing behavior obtaining, obtains the exposure total degree of this advertisement information in each input activity;
Calculation element, is connected with described statistic device, according to the sum of audient in each input activity, obtains the GRP of this advertisement information in this input activity; And, and according in same input activity, same user watches the number of times of this advertisement information, determines the N+Reach in each input activity; Wherein:
GRP=total degree ÷ total audience * 100 of exposing;
N+Reach accesses the number percent that sum that the frequency is more than or equal to the visiting Cookie of N time accounts for whole Cookie in same input activity, N is positive integer;
The second acquisition device, is connected with described calculation element, according to the GRP of a plurality of input activities and N+Reach, obtains the funtcional relationship between GRP and N+Reach;
Management devices, is connected with described the second acquisition device, for according to the funtcional relationship obtaining, the follow-up input of this advertisement information is managed.
8. system according to claim 7, is characterized in that, the function f (GRP between GRP and N+Reach
i) can make
value minimum, wherein GRPi represents the GRP of i historical input activity, uses Reach
irepresent i movable N+Reach, wherein the Monitoring Data of one group of historical input activity can be expressed as D={ (GRP
i, Reach
i) | i=1,2 ..., M}; Wherein, M is the sum of historical input activity, GRP
iand Reach
ibe nonnegative real number.
9. system according to claim 8, is characterized in that, the funtcional relationship between described GRP and N+Reach is linear function f (GRP)=a * GRP+b, wherein:
Wherein AveGRP and AveReach are respectively all GRP and the mean value of Reach,
10. system according to claim 8, is characterized in that, the funtcional relationship between described GRP and N+Reach is curvilinear function f (GRP)=(e with exponential form
a * GRP+b-1)/(e
a * GRP+b+ 1), wherein parameter a and b by minimizing
calculate.
11. systems according to claim 7, is characterized in that, described management devices, comprising:
The first acquisition module, for when obtaining the arrival rate of input activity, needed total exposure amount while obtaining this arrival rate according to the funtcional relationship of calculating;
Computing module, for according to total exposure amount, calculates the input cost of the input activity of this advertisement information.
12. systems according to claim 7, is characterized in that, described management devices, comprising:
The second acquisition module, for obtaining the funtcional relationship between each input activity GRP and N+Reach;
The 3rd acquisition module, is connected with described the second acquisition module, for when obtaining total injected volume, according to the funtcional relationship between GRP and N+Reach in each input activity, obtains GRP and arrival rate corresponding to this GRP of described total injected volume in each input activity;
Select module, be connected with described the 3rd acquisition module, according to the arrival rate in each input activity, select the high input activity of arrival rate to carry out follow-up input.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310068649.2A CN104035926B (en) | 2013-03-05 | 2013-03-05 | A kind of dispensing of internet information and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310068649.2A CN104035926B (en) | 2013-03-05 | 2013-03-05 | A kind of dispensing of internet information and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104035926A true CN104035926A (en) | 2014-09-10 |
CN104035926B CN104035926B (en) | 2017-05-31 |
Family
ID=51466697
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310068649.2A Active CN104035926B (en) | 2013-03-05 | 2013-03-05 | A kind of dispensing of internet information and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104035926B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104967878A (en) * | 2014-11-19 | 2015-10-07 | 腾讯科技(北京)有限公司 | Data processing method and server |
CN104992342A (en) * | 2015-05-11 | 2015-10-21 | 腾讯科技(北京)有限公司 | Method for determining the effectiveness of popularizing information release, monitoring server, and terminal |
CN105578249A (en) * | 2014-10-10 | 2016-05-11 | 腾讯科技(北京)有限公司 | Information processing method and server |
CN106296233A (en) * | 2015-05-12 | 2017-01-04 | 腾讯科技(成都)有限公司 | A kind of computer system and number-of-registration based on computer system determine method |
CN106656943A (en) * | 2015-11-03 | 2017-05-10 | 秒针信息技术有限公司 | Network user attribute matching method and device |
CN106651417A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Analysis method of advertisement releasing information and apparatus thereof |
CN108269114A (en) * | 2016-12-30 | 2018-07-10 | 深圳市优朋普乐传媒发展有限公司 | A kind of determining method and device of advertisement inventory |
CN109801106A (en) * | 2019-01-17 | 2019-05-24 | 有米科技股份有限公司 | A kind of advertisement delivery effect predictor method, device, server and storage medium |
CN110069708A (en) * | 2019-04-02 | 2019-07-30 | 北京数字新思科技有限公司 | A kind of promotion effect predictor method, device, medium and equipment promoted across medium |
CN110298711A (en) * | 2019-07-12 | 2019-10-01 | 秒针信息技术有限公司 | Advertisement arrival rate determines method, apparatus, storage medium and advertisement delivery method |
CN110377863A (en) * | 2019-07-29 | 2019-10-25 | 秒针信息技术有限公司 | A kind of the expansion approximating method and expansion fitting device of browsing stock assessment point |
CN112231369A (en) * | 2020-09-22 | 2021-01-15 | 北京明略昭辉科技有限公司 | Arrival rate curve fitting method and device |
CN112446740A (en) * | 2020-12-11 | 2021-03-05 | 恩亿科(北京)数据科技有限公司 | Advertisement data curve generation method and system, electronic device and storage medium |
CN112734090A (en) * | 2020-12-30 | 2021-04-30 | 上海嗨普智能信息科技股份有限公司 | Target curve acquisition method based on information data processing |
CN113190588A (en) * | 2021-04-20 | 2021-07-30 | 北京异乡旅行网络科技有限公司 | Distribution method, distribution device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030074252A1 (en) * | 2001-10-12 | 2003-04-17 | Avenue A, Inc. | System and method for determining internet advertising strategy |
CN101431524A (en) * | 2007-11-07 | 2009-05-13 | 阿里巴巴集团控股有限公司 | Method and device for implementing oriented network advertisement delivery |
US20090254420A1 (en) * | 2008-04-03 | 2009-10-08 | Clear Channel Management Services, Inc. | Maximizing Advertising Performance |
CN102521767A (en) * | 2011-12-13 | 2012-06-27 | 亿赞普(北京)科技有限公司 | Method and system for publishing network advertising information |
CN102800005A (en) * | 2012-07-20 | 2012-11-28 | 北京亿赞普网络技术有限公司 | Network advertisement putting method and device |
-
2013
- 2013-03-05 CN CN201310068649.2A patent/CN104035926B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030074252A1 (en) * | 2001-10-12 | 2003-04-17 | Avenue A, Inc. | System and method for determining internet advertising strategy |
CN101431524A (en) * | 2007-11-07 | 2009-05-13 | 阿里巴巴集团控股有限公司 | Method and device for implementing oriented network advertisement delivery |
US20090254420A1 (en) * | 2008-04-03 | 2009-10-08 | Clear Channel Management Services, Inc. | Maximizing Advertising Performance |
CN102521767A (en) * | 2011-12-13 | 2012-06-27 | 亿赞普(北京)科技有限公司 | Method and system for publishing network advertising information |
CN102800005A (en) * | 2012-07-20 | 2012-11-28 | 北京亿赞普网络技术有限公司 | Network advertisement putting method and device |
Non-Patent Citations (1)
Title |
---|
张大勇: "个性化网络广告推荐技术研究评述", 《哈尔滨工业大学学报(社会科学版)》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105578249A (en) * | 2014-10-10 | 2016-05-11 | 腾讯科技(北京)有限公司 | Information processing method and server |
CN105578249B (en) * | 2014-10-10 | 2019-11-12 | 腾讯科技(北京)有限公司 | Information processing method and server |
CN104967878A (en) * | 2014-11-19 | 2015-10-07 | 腾讯科技(北京)有限公司 | Data processing method and server |
CN104967878B (en) * | 2014-11-19 | 2019-05-14 | 腾讯科技(北京)有限公司 | A kind of data processing method and server |
CN104992342A (en) * | 2015-05-11 | 2015-10-21 | 腾讯科技(北京)有限公司 | Method for determining the effectiveness of popularizing information release, monitoring server, and terminal |
US10719847B2 (en) | 2015-05-11 | 2020-07-21 | Tencent Technology (Shenzhen) Company Limited | Method for determining validity of delivering of promotion information, monitoring server and terminal |
CN104992342B (en) * | 2015-05-11 | 2019-08-13 | 腾讯科技(北京)有限公司 | Promotion message delivery effectiveness determines method, monitoring server and terminal |
CN106296233A (en) * | 2015-05-12 | 2017-01-04 | 腾讯科技(成都)有限公司 | A kind of computer system and number-of-registration based on computer system determine method |
CN106296233B (en) * | 2015-05-12 | 2020-11-03 | 腾讯科技(成都)有限公司 | Computer system and registration quantity determination method based on computer system |
CN106651417A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Analysis method of advertisement releasing information and apparatus thereof |
CN106651417B (en) * | 2015-10-30 | 2021-08-10 | 北京国双科技有限公司 | Advertisement delivery information analysis method and device |
CN106656943A (en) * | 2015-11-03 | 2017-05-10 | 秒针信息技术有限公司 | Network user attribute matching method and device |
CN106656943B (en) * | 2015-11-03 | 2019-09-17 | 秒针信息技术有限公司 | A kind of matching process and device of network user's attribute |
CN108269114A (en) * | 2016-12-30 | 2018-07-10 | 深圳市优朋普乐传媒发展有限公司 | A kind of determining method and device of advertisement inventory |
CN109801106A (en) * | 2019-01-17 | 2019-05-24 | 有米科技股份有限公司 | A kind of advertisement delivery effect predictor method, device, server and storage medium |
CN109801106B (en) * | 2019-01-17 | 2020-10-02 | 有米科技股份有限公司 | Advertisement putting effect estimation method and device, server and storage medium |
CN110069708A (en) * | 2019-04-02 | 2019-07-30 | 北京数字新思科技有限公司 | A kind of promotion effect predictor method, device, medium and equipment promoted across medium |
CN110298711A (en) * | 2019-07-12 | 2019-10-01 | 秒针信息技术有限公司 | Advertisement arrival rate determines method, apparatus, storage medium and advertisement delivery method |
CN110377863A (en) * | 2019-07-29 | 2019-10-25 | 秒针信息技术有限公司 | A kind of the expansion approximating method and expansion fitting device of browsing stock assessment point |
CN110377863B (en) * | 2019-07-29 | 2021-12-28 | 秒针信息技术有限公司 | Expansion fitting method and device for browsing resource evaluation points |
CN112231369A (en) * | 2020-09-22 | 2021-01-15 | 北京明略昭辉科技有限公司 | Arrival rate curve fitting method and device |
CN112446740A (en) * | 2020-12-11 | 2021-03-05 | 恩亿科(北京)数据科技有限公司 | Advertisement data curve generation method and system, electronic device and storage medium |
CN112446740B (en) * | 2020-12-11 | 2024-06-11 | 恩亿科(北京)数据科技有限公司 | Advertisement data curve generation method, system, electronic equipment and storage medium |
CN112734090A (en) * | 2020-12-30 | 2021-04-30 | 上海嗨普智能信息科技股份有限公司 | Target curve acquisition method based on information data processing |
CN113190588A (en) * | 2021-04-20 | 2021-07-30 | 北京异乡旅行网络科技有限公司 | Distribution method, distribution device and storage medium |
CN113190588B (en) * | 2021-04-20 | 2024-06-28 | 北京异乡旅行网络科技有限公司 | Distribution method, distribution device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104035926B (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104035926A (en) | Internet information release method and system | |
US10679260B2 (en) | Cross-device message touchpoint attribution | |
US20170091810A1 (en) | Brand engagement touchpoint attribution using brand engagement event weighting | |
US20190244240A1 (en) | Statistical marketing attribution correlation | |
US20220215409A1 (en) | Performing interactive updates to a precalculated cross-channel predictive model | |
US9015128B2 (en) | Method and system for measuring social influence and receptivity of users | |
US20170337578A1 (en) | Dynamic media buy optimization using attribution-informed media buy execution feeds | |
US20160210657A1 (en) | Real-time marketing campaign stimuli selection based on user response predictions | |
US10163130B2 (en) | Methods and apparatus for identifying a cookie-less user | |
US20170323330A1 (en) | Media spend management using real-time predictive modeling of touchpoint exposure effects | |
US20160210656A1 (en) | System for marketing touchpoint attribution bias correction | |
US20160210661A1 (en) | Managing digital media spend allocation using calibrated user-level attribution data | |
US20150186925A1 (en) | Media spend optimization using engagement metrics in a cross-channel predictive model | |
US20170300939A1 (en) | Optimizing promotional offer mixes using predictive modeling | |
JP2020061174A (en) | Method and apparatus for measuring effect of information delivered to mobile devices | |
EP2779073A1 (en) | Method and system for determining changes in brand awareness after exposure to on-line advertisements | |
US20170337505A1 (en) | Media spend management using real-time predictive modeling of media spend effects on inventory pricing | |
CN105474654B (en) | Digital media advertisement system and method for the system | |
KR101981612B1 (en) | Analysis of the results of the influencer marketing implementation service delivery method | |
CN112348548A (en) | Message delivery method and device, electronic equipment and readable storage medium | |
KR101605029B1 (en) | System for providing online coupon service and method and apparatus therefor | |
Jena et al. | Role of marketing automation software tools in improving or boosting sales | |
CN103745388A (en) | Advertisement splitting method and system | |
CN108985810A (en) | A kind of method and apparatus that party in request's platform carries out advertisement dispensing | |
KR102382405B1 (en) | Method and system for providing advertising |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 100102 Beijing, Chaoyang District Fu Tong East Street, building 1, room 5, room 321008 Applicant after: The second hand information technology Co. Ltd. Address before: Beijing City, a small town east of Changping District road 102218 in No. 398 Coal Construction Group No. 1 building, 5 floor second hand system Applicant before: Beijing Sibotu Information Technology Co., Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |