CN115131079A - Data processing-based advertisement putting effect prediction method and device - Google Patents
Data processing-based advertisement putting effect prediction method and device Download PDFInfo
- Publication number
- CN115131079A CN115131079A CN202211022062.3A CN202211022062A CN115131079A CN 115131079 A CN115131079 A CN 115131079A CN 202211022062 A CN202211022062 A CN 202211022062A CN 115131079 A CN115131079 A CN 115131079A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- data
- page
- statistical
- advertisement putting
- 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
Images
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
- G06Q30/0242—Determining effectiveness of advertisements
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an advertisement putting effect prediction method and device based on data processing, and belongs to the technical field of data processing. The method comprises the step S100: acquiring the type of the activated data channel loaded this time, and increasing the statistical times of the data channel loaded this time; s200, acquiring page operation data of a target display page in a preset time period; s300: obtaining a plurality of different statistic times values and page operation data corresponding to a plurality of different types of data channels; s400: fitting the statistical times of the different types of data channels in the next statistical period; s500: and predicting the advertisement putting effect based on the fitted statistical times of the different types of data channels and the page operation data. The device comprises a commodity loading unit, a channel counting unit, a frequency fitting unit and an effect predicting unit. The invention can realize the advertisement putting effect of different data channels and adjust the advertisement putting strategy.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to an advertisement putting effect prediction method and device based on data processing.
Background
Most of the traditional advertisements are put on traditional media such as public places, televisions, newspapers, books and the like, and once the advertisements are put on the traditional media, the advertisements cannot be updated or changed for a short time. With the gradual popularization of the mobile internet, the mobile terminal advertisement is gradually popular, and personalized advertisement recommendation by means of user data becomes a new advertisement promotion mode. With the advent of the revolution in advertising delivery methods. Most of traditional advertisements are passively displayed and statically displayed in an unchangeable mode, in the era of mobile internet, the advertisements pay more attention to interaction with users, the display modes and the putting modes are rich and colorful, and active display (active push) and passive asking are available. Examples of the former are browser page advertisements, browser page keyword cues, etc., where advertisements are actively shown, but users are passively received; examples of the latter, such as graphic codes, dynamic codes, pan-tilt, etc., require active user involvement, with the user being more viscid.
The advertisement is a high-risk investment, and before operation, the effect generated by the advertisement investment is accurately judged and predicted; otherwise, blind investment is not only wasted, but the expected effect is not achieved, and sometimes negative effects are generated. Therefore, comprehensive and effective advertisement effect evaluation and prediction are carried out, which are necessary and beneficial for advertisers and advertisers.
Advertisers can usually adopt a plurality of ways to simultaneously launch advertisements, but the launching cost and the launching effect of different advertisement launching ways are different. If the advertisement putting effect of different approaches that have been put earlier is reasonably evaluated under the condition of limited advertisement budget, so as to provide a reference for the advertisement putting strategy of the next period, it becomes one of the technical problems faced by those skilled in the art.
Disclosure of Invention
In order to solve the technical problem, the invention provides an advertisement putting effect prediction method and device based on data processing.
The invention can realize the advertisement putting effect of different data channels and adjust the advertisement putting strategy.
In a first aspect of the present invention, a data processing-based advertisement delivery effectiveness prediction method is provided, where the method includes the following steps:
s100: when the target object is detected to be loaded and displayed, acquiring the type of the data channel which activates the current loading, and increasing the statistical times of the data channel which is loaded at the current time;
the target object is a commodity corresponding to the advertisement;
s200, acquiring page operation data of a target display page in a preset time period, wherein the target display page is a page on which the target object is loaded and displayed, and the preset time period is a time period in which the target display page is displayed in the foreground;
s300: when the preset number of statistical periods is over, acquiring a plurality of different statistical times values and page operation data corresponding to a plurality of different types of data channels;
s400: fitting the statistical times values of the different types of data channels in the next statistical period based on the plurality of different statistical times values;
s500: and predicting the advertisement putting effect based on the fitted statistical times of the different types of data channels and the page operation data.
The page operation data of the target display page within the preset time period obtained in the step S200 includes one of the following data or any combination thereof:
and the target user browses the detailed page of the commodity, the browsing time of the evaluation page, the time of communicating with the online customer service, the operation of clicking to join a shopping cart and the operation of clicking to purchase.
After the step S500, the method further includes:
s600: and adjusting the number distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect, and returning to the step S100.
In the process of executing the method, the data channel is an advertisement putting path; different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a display page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the display page.
The target user activating the advertisement placement path comprises:
when the advertisement putting path is one of an advertisement link, an advertisement picture and an advertisement video, the target user clicks the advertisement link, the advertisement picture or the advertisement video;
when the advertisement putting path is an advertisement two-dimensional code, a target user scans the advertisement two-dimensional code through an image terminal;
and when the advertisement putting path is the advertisement search keyword, inputting the advertisement search keyword by a target user through a search engine.
In a second aspect of the present invention, an advertisement delivery effect prediction apparatus based on data processing is provided, where the apparatus includes a commodity loading unit, a channel statistics unit, a frequency fitting unit, and an effect prediction unit;
the functions realized by each unit are as follows:
the commodity loading unit is used for loading and displaying the commodity corresponding to the advertisement on a target page,
the channel statistical unit comprises a frequency statistical unit and a page data storage unit;
the number counting unit is used for counting the number of activated accumulated times of different types of data channels in a plurality of different counting periods;
the page data storage unit is used for storing page operation data of a target display page within a preset time period, wherein the preset time period is a time period for the target display page to be displayed in the foreground;
the number fitting unit is used for fitting to obtain the statistical number value of the different types of data channels in the next statistical period according to the number of the activated accumulated times of the different types of data channels in a plurality of different statistical periods, which is obtained by statistics of the number statistical unit;
the effect prediction unit is used for predicting the advertisement putting effect based on the statistical times of the data channels of different types which are fitted by the times fitting unit and the page operation data stored by the page data storage unit.
The page data storage unit stores page operation data of a target display page in a preset time period, and the page operation data comprises one of the following data or any combination of the following data:
and the target user browses the detailed page of the commodity, the browsing time of the evaluation page, the time of communicating with the online customer service, the operation of clicking to join a shopping cart and the operation of clicking to purchase.
The data channel is an advertisement putting path; different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a target page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the target page.
As a further improvement, the device further comprises an advertisement putting adjusting unit;
the advertisement putting adjusting unit adjusts the number distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect obtained by the effect prediction unit.
The number fitting unit comprises a fitting function based on an R language;
the fitting function based on the R language takes the statistical times of different types of data channels as a dependent variable and takes the activated accumulated times of different types of data channels in a plurality of different statistical periods as an independent variable to carry out fitting.
The invention can objectively count the number of times that different types of data channels are activated in a plurality of different counting periods, the page operation data of a target display page in a preset time period and other actual operation data closely related to the user advertisement behaviors, then fit the number of times that different types of data channels are activated in a plurality of different counting periods based on the number of times that R language is counted by the number counting unit according to different types of data channels, obtain the number of times of statistics of the different types of data channels in the next counting period, finally predict the advertisement putting effect based on the number of times of statistics of the different types of data channels fitted by the number fitting unit and the page operation data stored by the page data storage unit, and perform corresponding advertisement data prediction after identifying and processing the independent advertisement data by using the data channels as different dimensions, and the subsequent advertisement putting strategy is more targeted.
Further advantages of the invention will be apparent in the detailed description section in conjunction with the drawings attached hereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating an advertisement placement effectiveness prediction method based on data processing according to an embodiment of the present invention;
FIG. 2 is a statistical schematic diagram of a plurality of different statistics corresponding to different types of data channels when the method of FIG. 1 is implemented;
FIG. 3 is a schematic diagram of a further preferred embodiment of the method of FIG. 1;
fig. 4 is a schematic diagram illustrating a unit composition of an advertisement placement effect prediction apparatus based on data processing according to an embodiment of the present invention;
fig. 5-6 are schematic diagrams of further preferred embodiments of the data processing-based advertisement impression prediction device shown in fig. 4.
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
Fig. 1 is a flowchart illustrating a method for predicting advertisement placement effectiveness based on data processing according to an embodiment of the present invention.
In fig. 1, the method includes steps S100 to S500, each of which is implemented as follows:
s100: when the target object is detected to be loaded and displayed, acquiring the type of the data channel which activates the current loading, and increasing the statistical times of the data channel which is loaded at the current time;
the target object is a commodity corresponding to the advertisement;
s200, acquiring page operation data of a target display page in a preset time period, wherein the target display page is a page on which the target object is loaded and displayed, and the preset time period is a time period in which the target display page is displayed in the foreground;
s300: when the preset number of statistical periods is over, acquiring a plurality of different statistical times values and page operation data corresponding to a plurality of different types of data channels;
s400: fitting the statistical times values of the different types of data channels in the next statistical period based on the plurality of different statistical times values;
s500: and predicting the advertisement putting effect based on the fitted statistical times of the different types of data channels and the page operation data.
One of the technical problems to be solved by the present invention is to count the advertisement behavior data of different delivery routes, so that in the first step, it must be identified in which delivery route the current advertisement behavior occurs.
In this embodiment, statistics is performed in a manner that the number of detection times of data channel activation is increased incrementally.
Specifically, the data channel is an advertisement putting path;
different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a display page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the display page.
Therefore, there are various advertisement delivery routes related in this embodiment, which can be classified into three categories according to different activation types:
the type one is as follows: when the advertisement putting path is one of an advertisement link, an advertisement picture and an advertisement video, the target user clicks the advertisement link, the advertisement picture or the advertisement video;
type two: when the advertisement putting path is an advertisement two-dimensional code, a target user scans the advertisement two-dimensional code through an image terminal;
type three: and when the advertisement putting path is the advertisement search keyword, inputting the advertisement search keyword by a target user through a search engine.
Therefore, referring to fig. 2, fig. 2 is a statistical schematic diagram illustrating a plurality of different statistical count values corresponding to different types of data channels when the method described in fig. 1 is implemented.
In fig. 2, a number of different statistical periods are schematically indicated, including weekday statistical periods T1, T2 and non-weekday statistical periods T3, T4;
figure 2 also schematically separates the ad placement paths into four cases,
the first three cases correspond to types one to three (the first data channel, the second data channel, and the third data channel) of the above three cases, respectively, and types other than the type one, the type two, and the type three are classified as other data channels.
In the figure, ai, bi, ci, and di (i =1, 2, 3, 4) correspond to the number of times that the corresponding data channel is activated in different statistical periods.
For example, when the target user scans the advertisement two-dimensional code through the image terminal in a certain statistical period, the second data channel of the corresponding statistical period is activated once, and therefore, bi is incremented by 1.
Obviously, only the number of times of statistics is not enough, and therefore, as one of the core improvements of the present invention, the S200 further obtains page operation data of a target display page within a preset time period, where the target display page is a page on which the target object is loaded and displayed, and the preset time period is a time period in which the target display page is displayed in the foreground;
specifically, the page operation data of the target display page obtained in step S200 in the preset time period includes one of the following data or any combination thereof:
and the target user browses the detailed page of the commodity, the browsing time of the evaluation page, the time of communicating with the online customer service, the operation of clicking to join a shopping cart and the operation of clicking to purchase.
Obviously, the page operation data can really reflect whether the activation operation constitutes a real advertisement putting effect.
A further advantage of the present invention is that step S400 is to fit statistical times values of the different types of data channels in the next statistical period based on the plurality of different statistical times values.
Obviously, the focus of the present invention is on the subsequent policy adjustment, and therefore, a corresponding prediction needs to be performed based on the historical data, that is, step S500, and the advertisement delivery effect prediction is performed based on the fitted statistical times of the different types of data channels and the page operation data.
It can be seen that steps S100 to S500 in the embodiment of the present invention are an integral solution associated in a front-back manner, and are all none, and especially, the page operation data therein and the statistical times of the different types of data channels fitted in the next statistical period make the data acquisition richer and the adjustment of the delivery policy more targeted.
As a further preference, see fig. 3, fig. 3 is a schematic view of a further preferred embodiment of the method described in fig. 1.
In fig. 3, on the basis of fig. 1, after the step S500, the method further includes:
s600: and adjusting the number distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect, and returning to the step S100.
Next, taking the data statistics of fig. 2 as an example, a specific embodiment of the method steps involved in prediction and fitting in the method described in the present application is given.
The existing data set (dependent variable) on which the prediction and fitting is based is as follows:
the number of statistics for different statistical periods of data channel i (i =1, 2, 3);
in the embodiment of the present invention, only the existing three data channels, i.e., the type one to the type three (the first data channel, the second data channel, and the third data channel) in the aforementioned three cases, are currently considered, and the other data channels except for the type one, the type two, and the type three are not considered for the moment.
Recording the activation times of the data channel i in the statistic time interval Tj as Numij;
counting the time length of the time interval Tj to be | Tj |;
the standard of the non-working day statistical time period is idleF; the standard of the working day statistical time interval is workF;
preferably, idleF = 50; workF = 100;
in page operation data in a preset time period, different weight values W are respectively given to the detailed page browsing time, the evaluation page browsing time, the time of communicating with online customer service, the operation of clicking to add a shopping cart, the operation of clicking to buy and the like of the commodity by a target user, and the weight values are increased progressively;
note that the detail page view time t1, the evaluation page view time t2, and the time of communication with the online customer service t3, when ti is greater than 0 (i =1, 2, 3),
t1 has a weight of w1, t2 has a weight of w2, and t3 has a weight of w 3;
1>w3>w2>w1>0。
assuming that the working day statistical time periods are T1, T2 and … … Tn, and the non-working day statistical time periods are S1, S2 and … … Sk; n and k are both greater than 2;
the advertisement placement effectiveness score Scorei for channel i is calculated as follows:
wherein, the first and the second end of the pipe are connected with each other,
Presetting an effect scoring threshold value Fset;
establishing a fitting relation between the score Scorei of the advertisement putting and the weight W of the statistical time interval Ti, Sk and page operation data:
preferably, the fitting relation is as follows:
Likewise, the fitting may also be performed with the accumulated number Fnum of times that different types of data channels are activated in a plurality of different statistical periods as an argument.
Namely, it is
Numi is the total number of increments of period Ti, Numk is the total number of increments of period Sk,
preferably, the fitting relation is as follows:
wherein a, b, c and d are parameters to be fitted.
Accordingly, the fitting can be performed by using the R language, the statistical times of different types of data channels as dependent variables and the accumulated times of different types of data channels activated in different statistical periods as independent variables, so that the statistical times of the different types of data channels in the next statistical period are fitted;
when the advertisement putting score Scorei corresponding to the statistic times of the different types of data channels in the next statistic period obtained by fitting is greater than the preset effect score threshold Fset, the advertisement putting can be increased in the data channels and/or the corresponding statistic period, that is, the number distribution and/or the time distribution of the different types of data channels are adjusted based on the prediction result of the advertisement putting effect obtained by the effect prediction unit.
It should be noted that the fitting relation is only illustrative, and in the specific fitting, a polynomial fitting function of the independent variable and the dependent variable may also be established, and other forms may also be adopted, for example, a fitting formula of a hyperbolic function and a parabolic function, which is not specifically limited in the present invention.
However, as one skilled in the art will appreciate, the above prediction process is not limited to R function fitting, and may be implemented by using other prediction models or methods, and may perform other quantization on the raw data to adapt to the corresponding prediction models or methods.
For example, a neural network prediction model may be used, the input is multidimensional data (working day period length Ti, non-working day period length Tj … …), and the output is also multidimensional data (optimal delivery period, optimal delivery duration … …), and any model or method or fitting function that can realize the above prediction output is within the scope of the present invention.
However, the R function is a preferred embodiment of the present invention, because the R language does not require a complex model training and updating process, and can also represent the correlation between different variables, it is also not complex to implement, and meanwhile, the R language can be directly inherited, developed and utilized based on the business software Spus, which reduces the later development cost.
Referring next to fig. 4-5, schematic diagrams of unit compositions of a data processing-based advertisement delivery performance prediction apparatus according to different embodiments of the present invention are respectively shown.
In fig. 4, an advertisement placement effect prediction apparatus based on data processing is shown, the apparatus including a commodity loading unit, a channel counting unit, a number fitting unit, and an effect prediction unit;
the commodity loading unit is used for loading and displaying commodities corresponding to the advertisements on a target page, and the channel counting unit comprises a frequency counting unit and a page data storage unit;
the number counting unit is used for counting the number of activated accumulated times of different types of data channels in a plurality of different counting periods;
the page data storage unit is used for storing page operation data of a target display page within a preset time period, wherein the preset time period is a time period for the target display page to be displayed in the foreground;
the number fitting unit is used for fitting the statistical number value of the different types of data channels in the next statistical period according to the activated cumulative number of the different types of data channels in the different statistical periods counted by the number statistical unit;
the effect prediction unit is used for predicting the advertisement putting effect based on the statistical times of the data channels of different types which are fitted by the times fitting unit and the page operation data stored by the page data storage unit.
The page data storage unit stores page operation data of a target display page in a preset time period, and the page operation data comprises one of the following data or any combination of the following data:
and the target user browses the detailed page of the commodity, the browsing time of the evaluation page, the time of communicating with the online customer service, the operation of clicking to join a shopping cart and the operation of clicking to purchase.
The data channel is an advertisement putting path; different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a target page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the target page.
On the basis of fig. 4, see fig. 5. Fig. 5 shows that the apparatus further comprises an advertisement placement adjustment unit; the advertisement putting adjusting unit adjusts the number distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect obtained by the effect prediction unit.
Further, referring to fig. 6, the degree fitting unit includes a fitting function based on R language; the fitting function based on the R language takes the statistical times of different types of data channels as dependent variables and takes the activated accumulated times of different types of data channels in a plurality of different statistical periods as independent variables to carry out fitting.
As one skilled in the art will appreciate, the above prediction process is not limited to R function fitting based on R language, and may be implemented by using other prediction models or methods, and may also perform other quantization on the raw data to adapt to the corresponding prediction models or methods.
For example, a neural network prediction model may be used, the input is multidimensional data (working day period length Ti, non-working day period length Tj … …), and the output is also multidimensional data (optimal delivery period, optimal delivery duration … …), and any model or method or fitting function that can realize the above prediction output is within the scope of the present invention.
However, the R function is a preferred embodiment of the present invention, because the R language does not need a complex model training and updating process, and can also represent the correlation between different variables, it is also not complex to implement, and meanwhile, the R language can be directly inherited, developed and utilized based on the business software Splus, which reduces the later development cost.
The invention can objectively count the number of times that different types of data channels are activated in a plurality of different counting periods, the page operation data of a target display page in a preset time period and other actual operation data closely related to the user advertisement behaviors, then fit the number of times that different types of data channels are activated in a plurality of different counting periods based on the number of times that R language is counted by the number counting unit according to different types of data channels, obtain the number of times of statistics of the different types of data channels in the next counting period, finally predict the advertisement putting effect based on the number of times of statistics of the different types of data channels fitted by the number fitting unit and the page operation data stored by the page data storage unit, and perform corresponding advertisement data prediction after identifying and processing the independent advertisement data by using the data channels as different dimensions, and the subsequent advertisement putting strategy is more targeted.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
The present invention is not limited to the specific module structure described in the prior art. The prior art mentioned in the background section can be used as part of the invention to understand the meaning of some technical features or parameters. The scope of the present invention is defined by the claims.
Claims (10)
1. A data processing-based advertisement putting effect prediction method is characterized by comprising the following steps:
s100: when the target object is detected to be loaded and displayed, acquiring the type of the data channel which activates the current loading, and increasing the statistical times of the data channel which is loaded at the current time;
the target object is a commodity corresponding to the advertisement;
s200, acquiring page operation data of a target display page in a preset time period, wherein the target display page is a page on which the target object is loaded and displayed, and the preset time period is a time period in which the target display page is displayed in the foreground;
s300: when the preset number of statistical cycles is over, obtaining a plurality of different statistical times values and page operation data corresponding to a plurality of different types of data channels;
s400: fitting the statistical times values of the different types of data channels in the next statistical period based on the plurality of different statistical times values;
s500: and predicting the advertisement putting effect based on the fitted statistical times of the different types of data channels and the page operation data.
2. The data processing-based advertisement delivery effect prediction method according to claim 1, wherein:
the data channel is an advertisement putting path; different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a display page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the display page.
3. The data processing-based advertisement delivery effect prediction method according to claim 2, wherein:
the target user activating the advertisement placement path, including:
when the advertisement putting path is one of an advertisement link, an advertisement picture and an advertisement video, the target user clicks the advertisement link, the advertisement picture or the advertisement video;
when the advertisement putting path is an advertisement two-dimensional code, a target user scans the advertisement two-dimensional code through an image terminal;
and when the advertisement putting path is the advertisement search keyword, inputting the advertisement search keyword by a target user through a search engine.
4. The data processing-based advertisement delivery effect prediction method according to claim 1, characterized in that:
in step S200, the page operation data of the target display page within the preset time period includes one of the following data or any combination thereof:
and the target user browses time to the detailed page of the commodity, browses time to the evaluation page, communicates with the online customer service, clicks to join a shopping cart operation and clicks to buy the operation.
5. The data processing-based advertisement delivery effect prediction method according to claim 1, wherein:
after step S500, the method further comprises:
s600: and adjusting the quantity distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect, and returning to the step S100.
6. An advertisement putting effect prediction device based on data processing comprises a commodity loading unit, a channel counting unit, a frequency fitting unit and an effect prediction unit;
the method is characterized in that:
the commodity loading unit is used for loading and displaying the commodity corresponding to the advertisement on a target page,
the channel statistical unit comprises a frequency statistical unit and a page data storage unit;
the number counting unit is used for counting the number of activated accumulated times of different types of data channels in a plurality of different counting periods;
the page data storage unit is used for storing page operation data of a target display page within a preset time period, wherein the preset time period is a time period for the target display page to be displayed in the foreground;
the number fitting unit is used for fitting the statistical number value of the different types of data channels in the next statistical period according to the activated cumulative number of the different types of data channels in the different statistical periods counted by the number statistical unit;
the effect prediction unit is used for predicting the advertisement putting effect based on the statistical times of the data channels of different types which are fitted by the times fitting unit and the page operation data stored by the page data storage unit.
7. A data-processing-based advertisement placement prediction apparatus according to claim 6, characterized in that:
the page data storage unit stores page operation data of a target display page in a preset time period, and the page operation data comprises one of the following data or any combination of the following data:
and the target user browses the detailed page of the commodity, the browsing time of the evaluation page, the time of communicating with the online customer service, the operation of clicking to join a shopping cart and the operation of clicking to purchase.
8. The data-processing-based advertisement delivery effect prediction apparatus according to claim 6, wherein:
the data channel is an advertisement putting path; different advertisement putting paths correspond to different data channel types, and the advertisement putting paths comprise one of advertisement links, advertisement two-dimensional codes, advertisement search keywords, advertisement pictures and advertisement videos or any combination thereof;
and when the target user activates the advertisement putting path, entering a target page of the target object through a data channel type corresponding to the advertisement putting path, and loading and displaying the commodity on the target page.
9. The data-processing-based advertisement delivery effect prediction apparatus according to claim 6, wherein:
the device also comprises an advertisement putting adjusting unit;
the advertisement putting adjusting unit adjusts the number distribution and/or the time distribution of the data channels of different types based on the prediction result of the advertisement putting effect obtained by the effect prediction unit.
10. A data-processing-based advertisement placement prediction apparatus according to claim 6, characterized in that:
the number fitting unit comprises a fitting function based on an R language;
the fitting function based on the R language takes the statistical times of different types of data channels as dependent variables and takes the activated accumulated times of different types of data channels in a plurality of different statistical periods as independent variables to carry out fitting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211022062.3A CN115131079B (en) | 2022-08-25 | 2022-08-25 | Data processing-based advertisement putting effect prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211022062.3A CN115131079B (en) | 2022-08-25 | 2022-08-25 | Data processing-based advertisement putting effect prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115131079A true CN115131079A (en) | 2022-09-30 |
| CN115131079B CN115131079B (en) | 2022-12-09 |
Family
ID=83387997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211022062.3A Active CN115131079B (en) | 2022-08-25 | 2022-08-25 | Data processing-based advertisement putting effect prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115131079B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330467A (en) * | 2022-10-12 | 2022-11-11 | 南通中泓网络科技有限公司 | Marketing advertisement click prediction method |
| CN115545779A (en) * | 2022-10-11 | 2022-12-30 | 西窗科技(苏州)有限公司 | Big data-based advertisement delivery early warning management method and system |
| CN116308538A (en) * | 2023-03-01 | 2023-06-23 | 深圳市明源云科技有限公司 | Method for processing release of message, electronic equipment and readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012088994A (en) * | 2010-10-21 | 2012-05-10 | Opto:Kk | Advertising effect analysis system and method of the same |
| US20130073473A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods & services, entertainment and auctions, with geospatial mapping technology |
| CN103824217A (en) * | 2014-03-20 | 2014-05-28 | 上海酷屏信息技术有限公司 | System and method for realizing advertisement putting, effect optimization and statistics in smart phone |
| CN105574132A (en) * | 2015-12-15 | 2016-05-11 | 海信集团有限公司 | Multimedia file recommendation method and terminal |
| CN108053050A (en) * | 2017-11-14 | 2018-05-18 | 广州优视网络科技有限公司 | Clicking rate predictor method, device, computing device and storage medium |
| CN108763515A (en) * | 2018-05-31 | 2018-11-06 | 天津理工大学 | A kind of time-sensitive personalized recommendation method decomposed based on probability matrix |
| CN109242521A (en) * | 2017-07-11 | 2019-01-18 | 阿里巴巴集团控股有限公司 | A kind of distribution method and device of predetermined consumption amount |
| TWM573493U (en) * | 2018-11-02 | 2019-01-21 | 優愛德股份有限公司 | System for predicting conversion probability by visitors' browsing paths |
| CN111091400A (en) * | 2018-10-23 | 2020-05-01 | 第四范式（北京）技术有限公司 | Method and device for generating advertisement conversion prediction model and delivering advertisement |
| CN112036929A (en) * | 2020-07-31 | 2020-12-04 | 深圳市彬讯科技有限公司 | Advertisement putting method, device, equipment and storage medium applied to special field |
| CN113449260A (en) * | 2020-03-24 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Advertisement click rate prediction method, training method and device of model and storage medium |
| CN114663155A (en) * | 2022-04-01 | 2022-06-24 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and device, equipment, medium and product thereof |
-
2022
- 2022-08-25 CN CN202211022062.3A patent/CN115131079B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012088994A (en) * | 2010-10-21 | 2012-05-10 | Opto:Kk | Advertising effect analysis system and method of the same |
| US20130073473A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods & services, entertainment and auctions, with geospatial mapping technology |
| CN103824217A (en) * | 2014-03-20 | 2014-05-28 | 上海酷屏信息技术有限公司 | System and method for realizing advertisement putting, effect optimization and statistics in smart phone |
| CN105574132A (en) * | 2015-12-15 | 2016-05-11 | 海信集团有限公司 | Multimedia file recommendation method and terminal |
| CN109242521A (en) * | 2017-07-11 | 2019-01-18 | 阿里巴巴集团控股有限公司 | A kind of distribution method and device of predetermined consumption amount |
| CN108053050A (en) * | 2017-11-14 | 2018-05-18 | 广州优视网络科技有限公司 | Clicking rate predictor method, device, computing device and storage medium |
| CN108763515A (en) * | 2018-05-31 | 2018-11-06 | 天津理工大学 | A kind of time-sensitive personalized recommendation method decomposed based on probability matrix |
| CN111091400A (en) * | 2018-10-23 | 2020-05-01 | 第四范式（北京）技术有限公司 | Method and device for generating advertisement conversion prediction model and delivering advertisement |
| TWM573493U (en) * | 2018-11-02 | 2019-01-21 | 優愛德股份有限公司 | System for predicting conversion probability by visitors' browsing paths |
| CN113449260A (en) * | 2020-03-24 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Advertisement click rate prediction method, training method and device of model and storage medium |
| CN112036929A (en) * | 2020-07-31 | 2020-12-04 | 深圳市彬讯科技有限公司 | Advertisement putting method, device, equipment and storage medium applied to special field |
| CN114663155A (en) * | 2022-04-01 | 2022-06-24 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and device, equipment, medium and product thereof |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545779A (en) * | 2022-10-11 | 2022-12-30 | 西窗科技(苏州)有限公司 | Big data-based advertisement delivery early warning management method and system |
| CN115545779B (en) * | 2022-10-11 | 2023-09-01 | 西窗科技(苏州)有限公司 | Early warning management method and system for advertisement delivery based on big data |
| CN115330467A (en) * | 2022-10-12 | 2022-11-11 | 南通中泓网络科技有限公司 | Marketing advertisement click prediction method |
| CN116308538A (en) * | 2023-03-01 | 2023-06-23 | 深圳市明源云科技有限公司 | Method for processing release of message, electronic equipment and readable storage medium |
| CN116308538B (en) * | 2023-03-01 | 2024-03-15 | 深圳市明源云科技有限公司 | Method for processing release of message, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115131079B (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115131079B (en) | Data processing-based advertisement putting effect prediction method and device | |
| US20080275764A1 (en) | Content management system and method | |
| KR101161084B1 (en) | Platform for mobile advertising and microtargeting of promotions | |
| US20220277348A1 (en) | Conversion Timing Prediction for Networked Advertising | |
| US20050144069A1 (en) | Method and system for providing targeted graphical advertisements | |
| US20100223641A1 (en) | System and method for predicting the optimum delivery of multimedia content based on human behavior patterns | |
| US20090164310A1 (en) | Method for providing mobile commerce and revenue optimization | |
| KR101818827B1 (en) | Apparatus for inducing advertisement competition based on contents preference | |
| US20070299789A1 (en) | Assessing and Monetizing Bandwidth Usage in a Networked Mobile Application | |
| EP2606459A2 (en) | Unified data management platform | |
| WO2009114561A2 (en) | Cognitive scheduler for mobile platforms | |
| US20100235232A1 (en) | Advertisement providing system and method thereof | |
| US20200219145A1 (en) | Bidding Agent with Optimized Reach Limitation by Segment | |
| JP2003331105A (en) | Ad-market system and method | |
| US20070041363A1 (en) | Search and navigation method within voice over internet protocol (VOIP) advertisements player | |
| US10068261B1 (en) | In-flight campaign optimization | |
| CN101809602A (en) | Advertisement effect determining method, advertisement effect determining system, and advertisement effect determining program | |
| JP4159832B2 (en) | Content providing server device, content providing method, and content providing program | |
| US20130030921A1 (en) | Serving advertisements based on user data | |
| KR20000050071A (en) | Advertisement method using codeless communication terminal | |
| KR102167756B1 (en) | Apparatus and method for managing advertisements | |
| US20200219143A1 (en) | Bidding Agent Using Metadata for Data Augmenter to Limit Ad Reach to Subcategories of Targeted Users | |
| US7953640B2 (en) | Method and system for determining a value of a portion of content | |
| US20180285926A1 (en) | Method and apparatus to add modular media content to syndicated emails | |
| KR20080095312A (en) | Method and apparatus for providing advertisement information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |