CN104933603A - A method and an apparatus for advertisement displaying - Google Patents

A method and an apparatus for advertisement displaying Download PDF

Info

Publication number
CN104933603A
CN104933603A CN201510386612.3A CN201510386612A CN104933603A CN 104933603 A CN104933603 A CN 104933603A CN 201510386612 A CN201510386612 A CN 201510386612A CN 104933603 A CN104933603 A CN 104933603A
Authority
CN
China
Prior art keywords
advertisement
rate
effect information
display effect
advertisements
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201510386612.3A
Other languages
Chinese (zh)
Inventor
刘林
叶铮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201510386612.3A priority Critical patent/CN104933603A/en
Publication of CN104933603A publication Critical patent/CN104933603A/en
Pending legal-status Critical Current

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The embodiment of the invention discloses a method and an apparatus for advertisement displaying. The method comprises the following steps: in a display phase, when a first advertisement needs to be displayed, at least one second advertisement is selected from all the related advertisements through correlation between the first advertisement recorded in a learning phase and each related advertisement; the correlation between the first advertisement and each related advertisement is determined through utilization of first display effect information of the first advertisement and second display effect information displayed in a related mode by the first advertisement and each related advertisement; and the first advertisement and the at least one second advertisement are displayed in a related mode. According to the embodiment of the invention, through recording of the correlation between the advertisements in the learning phase and displaying in a related mode a plurality of advertisements which have relatively strong relation in the display phase, a purpose of raising advertisement displaying effect is reached. Since human intervention is not needed, a lot of human workloads are reduced, and problems of displaying in a related mode the advertisements which do not have strong correlation are avoided.

Description

Advertisement display method and device
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for displaying an advertisement.
Background
When a user watches advertisements on a video website, a plurality of advertisements are displayed on a plurality of advertisement positions on the same page, and the advertisements may come from a plurality of advertisers and have different contents. For multiple advertisements displayed simultaneously, the correlation between the advertisements may affect the presentation of the advertisements, an advertising combination such as fast food and weight loss may reduce the overall presentation, while an advertising combination of automobiles and lubricating oils may increase the overall presentation.
In order to improve the overall display effect, a plurality of advertisements with stronger relevance need to be displayed on a plurality of advertisement positions of the same page. In the prior art, advertisements with stronger relevance are designated manually. For example, when it is necessary to display advertisement a on a page, advertisement B, which is relatively strongly related to advertisement a, is manually specified, and advertisement a and advertisement B are simultaneously displayed on a plurality of advertisement spots of the same page.
In the above manner, each time the advertisement is displayed, the advertisement with stronger relevance needs to be manually specified, which is inefficient, and the manually specified advertisement with stronger relevance may not be correct.
Disclosure of Invention
The embodiment of the invention discloses a method and a device for displaying advertisements, which are used for associating and displaying a plurality of advertisements with stronger relevance in a display stage by recording the relevance among the advertisements in a learning stage.
In order to achieve the purpose, the embodiment of the invention discloses the following technical scheme:
the embodiment of the invention provides an advertisement display method, which comprises the following steps:
in the display stage, when a first advertisement needs to be displayed, at least one second advertisement is selected from all the associated advertisements by utilizing the correlation between the first advertisement and each associated advertisement recorded in the learning stage; wherein the correlation between the first advertisement and each associated advertisement is determined by using first display effect information of the first advertisement and second display effect information displayed in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and displaying the first advertisement and the at least one second advertisement in association.
Preferably, the display stage further comprises:
a learning stage, wherein first display effect information of the first advertisement is collected; aiming at a plurality of associated advertisements corresponding to a first advertisement, collecting second display effect information displayed by the first advertisement in association with each associated advertisement;
determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
a correlation between the first advertisement and each associated advertisement is recorded.
Preferably, the determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement specifically includes:
determining a first numerical value corresponding to the first advertisement by using the first display effect information;
determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement;
determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein the larger the second value divided by the first value, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value.
Preferably, when the first display effect information specifically includes a first skip rate, a first click rate, and a first like rate, and the second display effect information specifically includes a second skip rate, a second click rate, and a second like rate; the determining a first numerical value corresponding to the first advertisement by using the first display effect information specifically includes: determining the first value to be (1-first loss rate) first click rate (first like rate);
the determining, by using the second display effect information corresponding to each associated advertisement, each second numerical value corresponding to the first advertisement and each associated advertisement specifically includes: determining the second value to be (1-second loss rate) second click rate second like rate.
Preferably, the selecting at least one second advertisement from all the associated advertisements by using the correlation between the first advertisement and each associated advertisement specifically includes:
acquiring the quantity of second advertisements displayed in association with the first advertisements, sequencing each associated advertisement according to the sequence of strong and weak relevance by utilizing the relevance between the first advertisements and each associated advertisement, and selecting the quantity of associated advertisements from all associated advertisements as the second advertisements according to the sequencing result from the associated advertisement with the strongest relevance with the first advertisements.
Preferably, the correlation between the first advertisement and the associated advertisement selected from all associated advertisements as the second advertisement is greater than 1.
Preferably, the associating displays the first advertisement and the at least one second advertisement, specifically including:
displaying the first advertisement and the at least one second advertisement simultaneously on the same page; or,
in the tile advertisement, the first advertisement and the at least one second advertisement are displayed in a carousel.
The embodiment of the invention provides an advertisement display method, which comprises the following steps:
in the display stage, inquiring the correlation between each advertisement and each associated advertisement recorded in the learning stage, and determining the advertisement combination with the strongest correlation, wherein the advertisement combination comprises a plurality of advertisements; wherein, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information of the advertisement and the second display effect information displayed by the advertisement in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and displaying a plurality of advertisements in the advertisement combination in an associated mode.
Preferably, the display stage further comprises: a learning stage, aiming at each advertisement, collecting first display effect information of the advertisement; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information displayed by the advertisements in association with each associated advertisement;
determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
the correlation between the advertisement and each associated advertisement is recorded.
Preferably, the determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement specifically includes:
determining a first numerical value corresponding to the advertisement by using the first display effect information;
determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement;
determining a value of each second value divided by the first value as a correlation between the advertisement and each associated advertisement; wherein the larger the value of the second numerical value divided by the first numerical value, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second numerical value.
Preferably, when the first display effect information specifically includes a first skip rate, a first click rate, and a first like rate, and the second display effect information specifically includes a second skip rate, a second click rate, and a second like rate; the determining a first numerical value corresponding to the advertisement by using the first display effect information specifically includes: determining the first value to be (1-first loss rate) first click rate (first like rate);
the determining, by using the second display effect information corresponding to each associated advertisement, each advertisement and each second numerical value corresponding to each associated advertisement specifically includes: determining the second value to be (1-second loss rate) second click rate second like rate.
Preferably, the associating displays a plurality of advertisements in the advertisement combination, specifically including:
simultaneously displaying a plurality of advertisements in the advertisement combination on the same page; or,
in the tile advertisement, a carousel displays a plurality of advertisements within the advertisement set.
The embodiment of the invention provides a device for displaying advertisements, which specifically comprises:
the selection module is used for selecting at least one second advertisement from all the associated advertisements by utilizing the correlation between the first advertisement and each associated advertisement recorded in the learning stage when the first advertisement needs to be displayed in the display stage; wherein the correlation between the first advertisement and each associated advertisement is determined by using first display effect information of the first advertisement and second display effect information displayed in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
a display module for displaying the first advertisement and the at least one second advertisement in association.
Preferably, the learning module is configured to collect first display effect information of the first advertisement in a learning phase; aiming at a plurality of associated advertisements corresponding to a first advertisement, collecting second display effect information displayed by the first advertisement in association with each associated advertisement; determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
a correlation between the first advertisement and each associated advertisement is recorded.
Preferably, the learning module is specifically configured to determine a first numerical value corresponding to the first advertisement by using the first display effect information in a process of determining a correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement; determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein the larger the second value divided by the first value, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value.
Preferably, when the first display effect information specifically includes a first skip rate, a first click rate, and a first like rate, and the second display effect information specifically includes a second skip rate, a second click rate, and a second like rate; the learning module is further configured to determine, in a process of determining a first numerical value corresponding to the first advertisement by using the first display effect information, that the first numerical value is (1-a first loss rate) × a first click rate × a first like rate; in the process of determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) second click rate second like rate.
Preferably, the selecting module is specifically configured to, in a process of selecting at least one second advertisement from all associated advertisements by using the correlation between the first advertisement and each associated advertisement recorded in the learning stage, obtain the number of second advertisements displayed in association with the first advertisement, sort each associated advertisement in an order of strong or weak correlation by using the correlation between the first advertisement and each associated advertisement, and select the number of associated advertisements from all associated advertisements as the second advertisements according to a result of the sorting from the associated advertisement with the strongest correlation with the first advertisement.
Preferably, the correlation between the first advertisement and the associated advertisement selected from all associated advertisements as the second advertisement is greater than 1.
Preferably, the display module is specifically configured to display the first advertisement and the at least one second advertisement simultaneously on the same page in a process of displaying the first advertisement and the at least one second advertisement in an associated manner; alternatively, in the tile advertisement, the first advertisement and the at least one second advertisement are displayed in a carousel.
The embodiment of the invention provides a device for displaying advertisements, which specifically comprises:
the selection module is used for inquiring the correlation between each advertisement and each associated advertisement recorded in the learning stage in the display stage and determining the advertisement combination with the strongest correlation, wherein the advertisement combination comprises a plurality of advertisements; wherein, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information of the advertisement and the second display effect information displayed by the advertisement in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and the display module is used for displaying a plurality of advertisements in the advertisement combination in an associated manner.
Preferably, the method further comprises the following steps: the learning module is used for collecting first display effect information of each advertisement in a learning stage; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information displayed by the advertisements in association with each associated advertisement;
determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
the correlation between the advertisement and each associated advertisement is recorded.
Preferably, the learning module is specifically configured to determine a first numerical value corresponding to each of the advertisements by using the first display effect information in a process of determining a correlation between the advertisement and each of the associated advertisements by using the first display effect information and the second display effect information corresponding to each of the associated advertisements; determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the advertisement and each associated advertisement; wherein the larger the value of the second numerical value divided by the first numerical value, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second numerical value.
Preferably, when the first display effect information specifically includes a first skip rate, a first click rate, and a first like rate, and the second display effect information specifically includes a second skip rate, a second click rate, and a second like rate; the learning module is further configured to determine, in a process of determining a first numerical value corresponding to the advertisement by using the first display effect information, that the first numerical value is (1-first skip rate) × first click rate × first like rate; in the process of determining the advertisement and each second numerical value corresponding to each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) × second click rate × second like rate.
Preferably, the display module is specifically configured to display the multiple advertisements in the advertisement combination on the same page simultaneously in a process of displaying the multiple advertisements in the advertisement combination in an associated manner; alternatively, in a tile ad, a carousel displays multiple ads within the ad grouping.
Based on the technical scheme, compared with the prior art, the embodiment of the invention has at least the following advantages that the purpose of improving the advertisement display effect is achieved by recording the correlation among the advertisements in the learning stage and associating and displaying a plurality of advertisements with stronger correlation in the display stage. Because manual intervention is not needed, a large amount of manual workload is reduced, and the problem that the associated display is not the advertisement with stronger relevance is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for displaying an advertisement according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for displaying an advertisement according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an advertisement display apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an advertisement display apparatus according to a fourth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
In view of the problems in the prior art, an embodiment of the present invention provides an advertisement display method, which is used for simultaneously displaying multiple advertisements on the same page or displaying multiple advertisements in a tile advertisement in a carousel manner. When a plurality of advertisements are displayed, one advertisement is a main advertisement, and the other advertisements can be auxiliary advertisements corresponding to the main advertisement. The main advertisement refers to an advertisement which needs to be displayed in a page or a patch advertisement, and the auxiliary advertisement can be selected based on the main advertisement. In the embodiment of the invention, when the auxiliary advertisement is selected for the main advertisement, the advertisement with stronger correlation with the main advertisement is selected as the auxiliary advertisement so as to improve the display effect of the main advertisement and the auxiliary advertisement. Wherein, the number of the main advertisement is 1, and the number of the auxiliary advertisement is 1 or more. When the number of the auxiliary advertisements is 1, the advertisement with the strongest correlation with the main advertisement can be selected as the auxiliary advertisement; when the number of the secondary advertisements is plural (e.g., 3), the advertisement having the strongest correlation with the primary advertisement, the advertisement having the second strongest correlation with the primary advertisement, and the advertisement having the third strongest correlation with the primary advertisement may be selected as the secondary advertisement.
In order to realize the technical scheme, the embodiment of the invention provides two stages. The first phase is a learning phase in which correlations between the main advertisement and each associated advertisement are generated. The second phase is a display phase, in which at least one auxiliary advertisement with strong relevance is selected for the main advertisement based on the relevance between the main advertisement and each associated advertisement, and the main advertisement and the at least one auxiliary advertisement are displayed on the same page at the same time, or the main advertisement and the at least one auxiliary advertisement are displayed in a carousel mode in the patch advertisement.
In the following description, the primary advertisement is referred to as a first advertisement, and the finally selected secondary advertisement is referred to as a second advertisement.
Based on the above description, as shown in fig. 1, the method for displaying an advertisement may specifically include the following steps:
step 101, collecting first display effect information of a first advertisement in a learning stage; and aiming at a plurality of associated advertisements corresponding to the first advertisement, collecting second display effect information which is displayed by the first advertisement and each associated advertisement in an associated manner, determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement, and recording the correlation between the first advertisement and each associated advertisement.
The display effect information specifically includes, but is not limited to, one or any combination of the following: a loss of jump rate, a click rate, a like rate. Wherein, the loss rate (Bounce) is the rate at which the advertisement is closed, that is, the rate at which the user closes the advertisement during watching the advertisement, and a lower loss rate indicates a better display effect. The Click rate (Click) is the rate of the advertisement being clicked and viewed, that is, the rate of the advertisement being clicked and viewed by the user, when the user clicks the advertisement, it can be considered that the higher the Click rate is, the better the display effect is. The Like rate (Like) is a rate at which the advertisement is liked by the user, the user may be allowed to select whether to Like or dislike the advertisement when the advertisement is presented, and the rate at which the user likes the advertisement is the Like rate, and a higher Like rate indicates a better presentation effect. When the advertisement is displayed, the user can select the advertisement which is liked or disliked by setting the like option and the dislike option, and then the ratio that the user likes the advertisement is determined.
The associated advertisement corresponding to the first advertisement refers to an advertisement displayed on the same page as the first advertisement, or an advertisement displayed in the same tile advertisement as the first advertisement.
In the patch advertisement, a plurality of advertisements are usually broadcast in turn, and can be mutually associated advertisements; alternatively, only two adjacent advertisements may be correlated advertisements because the correlation effect between only two adjacent advertisements is relatively large. For example, when advertisement a, advertisement B, and advertisement C appear in the carousel in the tile advertisement, the associated advertisements of advertisement a are advertisement B and advertisement C, the associated advertisements of advertisement B are advertisement a and advertisement C, and the associated advertisements of advertisement C are advertisement a and advertisement B; or the advertisement associated with the advertisement A is the advertisement B, the advertisement associated with the advertisement B is the advertisement A and the advertisement C, and the advertisement associated with the advertisement C is the advertisement B.
The method comprises the steps of displaying a first advertisement and an associated advertisement in an associated mode, wherein the step of displaying the first advertisement and the associated advertisement in the associated mode means that the first advertisement and the associated advertisement are displayed on the same page at the same time; alternatively, in a tile ad, the carousel displays the first ad and the associated ad.
In the initial stage of advertisement putting, all advertisements are randomly put without considering relevance influence, and the process is a learning stage. In the learning phase, the presentation effectiveness information of each advertisement is collected, and the presentation effectiveness information of each advertisement displayed in association with other advertisements is collected. For example, when the advertisement a and the advertisement B are displayed on the same page, the display effect information of the advertisement a, the display effect information of the advertisement B, and the display effect information displayed in association with the advertisement a and the advertisement B may be collected; when the advertisement A and the advertisement C are displayed on the same page, the showing effect information of the advertisement A can be collected, the showing effect information of the advertisement C can be collected, and the showing effect information displayed by associating the advertisement A and the advertisement C can be collected; when the advertisement A, the advertisement B and the advertisement C are displayed on the same page, the display effect information of the advertisement A, the display effect information of the advertisement B, the display effect information of the advertisement C, the display effect information of the advertisement A and the advertisement B which are displayed in a correlation mode, the display effect information of the advertisement A and the advertisement C which are displayed in a correlation mode and the display effect information of the advertisement B and the advertisement C which are displayed in a correlation mode can be collected. In the whole learning stage, the display effect information is continuously collected, the average value of the collected display effect information of all the advertisements A is finally obtained, the display effect information of the advertisements A can be obtained, the average value of the collected display effect information of all the advertisements A and B which are displayed in an associated manner can be obtained, the display effect information of each advertisement A and B which are displayed in an associated manner can be obtained, and by analogy, the display effect information of each advertisement and the display effect information of each advertisement which is displayed in an associated manner with other advertisements can be collected.
In the embodiment of the present invention, the determining, by using the first display effect information and the second display effect information corresponding to each associated advertisement, a correlation between the first advertisement and each associated advertisement specifically includes, but is not limited to, the following manners: determining a first numerical value corresponding to the first advertisement by using the first display effect information; for each associated advertisement, determining a first advertisement and each second numerical value corresponding to each associated advertisement by using the second display effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein, the larger the value of the second value divided by the first value is, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value is.
For example, when the advertisement a is the first advertisement, the first display effect information of the advertisement a is used to determine the first numerical value corresponding to the advertisement a. And aiming at the related advertisement (advertisement B) of the advertisement A, determining a second numerical value corresponding to the advertisement A and the advertisement B by utilizing the second display effect information corresponding to the advertisement B. And aiming at the related advertisement (advertisement C) of the advertisement A, determining a second numerical value corresponding to the advertisement A and the advertisement C by utilizing the second showing effect information corresponding to the advertisement C.
When the first display effect information comprises a first skipping rate, a first click rate and a first like rate, and the second display effect information comprises a second skipping rate, a second click rate and a second like rate; determining a first numerical value corresponding to the first advertisement by using the first display effect information, specifically including but not limited to the following modes: the first value is determined to be (1-first loss rate) first click rate and first like rate. Determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement, which includes, but is not limited to, the following ways: the second value is determined to be (1-second loss rate) second click rate and second like rate.
It should be noted that, for different combinations of the presentation effect information, the determining manner of the first numerical value and the second numerical value is similar to the above manner, for example, when the first presentation effect information includes a first skip rate and a first click rate, and the second presentation effect information includes a second skip rate and a second click rate, the first numerical value corresponding to the first advertisement is determined by using the first presentation effect information, which specifically includes but is not limited to the following manners: the first value is determined to be (1-first rate of loss) first click rate. Determining a second numerical value corresponding to the first advertisement and the associated advertisement by using the second showing effect information corresponding to the associated advertisement, which specifically includes but is not limited to the following modes: the second value is determined to be (1-second loss rate) second click rate. For the determination manner of the numerical value under the combination of other presentation effect information, repeated description is omitted in the embodiment of the present invention.
When the advertisement a is the first advertisement, assuming that Ba represents the loss rate of the advertisement a, Ca represents the click rate of the advertisement a, and La represents the like rate of the advertisement a, the first value corresponding to the advertisement a is (1-Ba) × Ca × La. For the associated advertisement (advertisement B) of advertisement a, assuming that Bab represents the loss rate of the associated display of advertisement a and advertisement B, Cab represents the click rate of the associated display of advertisement a and advertisement B, and Lab represents the like rate of the associated display of advertisement a and advertisement B, the second value corresponding to advertisement a and advertisement B is (1-Bab) × Cab.
Through the above processing, a first value corresponding to the advertisement a (i.e. the first advertisement) and a second value corresponding to the advertisements a and B (i.e. the associated advertisements) can be obtained. Thereafter, a correlation between ad a and ad B may be determined using the second value and the first value, the correlation between ad a and ad B being the second value divided by the first value. Wherein the greater the value of the second value divided by the first value (i.e., relevance), the greater the relevance between ad a and ad B. When the value obtained by dividing the second numerical value by the first numerical value is greater than 1, the advertisement A and the advertisement B are in positive correlation, and when the advertisement A and the advertisement B are displayed in a correlated manner, the display effect of the advertisement A is improved, and the display effect of the advertisement B is improved. When the value obtained by dividing the second numerical value by the first numerical value is smaller than 1, the negative correlation between the advertisement A and the advertisement B is indicated, and when the advertisement A and the advertisement B are displayed in a correlated manner, the display effect of the advertisement A is reduced, and the display effect of the advertisement B is reduced.
After the correlation between the first advertisement and each associated advertisement is obtained, the correlation between the first advertisement and each associated advertisement may also be recorded in a storage medium. The specific recording method may be the method shown in table 1, or the method shown in table 2. In any way, as long as the correlation between the first advertisement and each associated advertisement can be recorded, which is not described in detail in the embodiment of the present invention.
TABLE 1 correlation record Table
First advertisement Association advertisement/relevance
Advertisement A Advertisement B/1.5
Advertisement A Advertisement C/1.2
Advertisement B Advertisement A/1.5
Advertisement B Advertisement C/0.8
Advertisement C Advertisement A/1.2
Advertisement C Advertisement B/0.8
TABLE 2 correlation record Table
First advertisement Association advertisement/relevance
Advertisement A Advertisement B/1.5, advertisement C/1.2
Advertisement B Advertisement A/1.5, advertisement C/0.8
Advertisement C Advertisement A/1.2, advertisement B/0.8
The step 101 is an optional step before the display stage, the step 101 may be executed before the display stage, or the step 101 may not be executed in practical applications, and the correlation between the first advertisement and each associated advertisement is stored in other manners, which is not described in detail in this embodiment of the present invention.
And 102, in the display stage, when the first advertisement needs to be displayed, selecting at least one second advertisement from all the associated advertisements by utilizing the correlation (obtained from the storage medium) between the first advertisement and each associated advertisement, and displaying the first advertisement and the at least one second advertisement in an associated manner.
In the embodiment of the present invention, the process of selecting at least one second advertisement from all associated advertisements by using the correlation between the first advertisement and each associated advertisement specifically includes, but is not limited to, the following ways: the method comprises the steps of obtaining the number of second advertisements displayed in association with a first advertisement, sequencing each associated advertisement according to the sequence of strong and weak relevance by utilizing the relevance between the first advertisement and each associated advertisement, and selecting the number of associated advertisements from all associated advertisements as the second advertisements according to the sequencing result from the associated advertisement with the strongest relevance with the first advertisement.
The number of the second advertisements displayed in association with the first advertisements can be arbitrarily set according to actual needs, and if 4 advertisements are simultaneously displayed on the same page, the number of the second advertisements displayed in association with the first advertisements is 3; in the tile advertisement, if the number of advertisements displayed in carousel is 4, the number of second advertisements displayed in association with the first advertisements is 3. When the number of the second advertisements displayed in association with the first advertisements is 3, the association advertisement having the strongest correlation with the first advertisement, the association advertisement having the second strongest correlation with the first advertisement, and the association advertisement having the third strongest correlation with the first advertisement are selected as the second advertisements from all the association advertisements, using the correlation between the first advertisement and each of the association advertisements.
Wherein, when the associated advertisement is selected as the second advertisement from all the associated advertisements, the correlation between the first advertisement and the associated advertisement selected as the second advertisement from all the associated advertisements is greater than 1.
In the embodiment of the present invention, the process of displaying the first advertisement and the at least one second advertisement in association specifically includes, but is not limited to, the following ways: simultaneously displaying the first advertisement and at least one second advertisement on the same page; alternatively, in the tile advertisement, the carousel displays the first advertisement and the at least one second advertisement.
When the time of the learning phase exceeds the preset time or the data collected in the learning phase is greater than the preset threshold value, the correlation record table recorded in the learning phase can already guide the subsequent advertisement display, so the learning phase is ended, and the display phase is started. In the display stage, a first advertisement is determined, the first advertisement is used for inquiring the relevance record table shown in the table 1 or the table 2 so as to select at least one second advertisement from all the associated advertisements, and the first advertisement and the at least one second advertisement are displayed in an associated mode.
For example, if the number of second advertisements displayed in association with the first advertisement is 2 when the first advertisement is advertisement a, first, since the correlation between advertisement B and advertisement a is 1.5 and the correlation between advertisement C and advertisement a is 1.2, advertisement B is the second advertisement having the strongest correlation with advertisement a, and advertisement B is selected as the second advertisement. After selecting advertisement B, continuing to select the advertisement having the second highest relevance to advertisement A from the remaining associated advertisements, advertisement C is selected as the second advertisement because advertisement C is the advertisement having the second highest relevance to advertisement A. Through the above process, advertisement B and advertisement C are selected as the second advertisement.
Based on the relevance record table shown in table 1 or table 2, when a second advertisement is selected from all associated advertisements, an advertisement having a relevance greater than 1 to the first advertisement may be selected as the second advertisement, and an advertisement having a relevance less than 1 to the first advertisement may not be selected as the second advertisement.
The advertisement may be a specific advertisement or an advertisement tag. For example, advertisement a is a real advertisement for car a, advertisement B is a real advertisement for lube a; alternatively, advertisement a is an automobile type (advertisement tag) advertisement that includes all advertisements related to automobiles, and advertisement B is a lube oil type (advertisement tag) advertisement that includes all advertisements related to lube oil.
Based on the technical scheme, compared with the prior art, the embodiment of the invention has at least the following advantages that the purpose of improving the advertisement display effect is achieved by recording the correlation among the advertisements in the learning stage and associating and displaying a plurality of advertisements with stronger correlation in the display stage. Because manual intervention is not needed, a large amount of manual workload is reduced, and the problem that the associated display is not the advertisement with stronger relevance is avoided.
Example two
The second embodiment of the invention provides an advertisement display method, which is used for simultaneously displaying a plurality of advertisements on the same page or alternatively displaying a plurality of advertisements in a paster advertisement in a broadcasting manner. In the embodiment of the invention, two stages are provided. The first phase is a learning phase in which correlations between each advertisement and each associated advertisement are generated. The second phase is a display phase, in which an advertisement combination is selected based on the correlation between each advertisement and each associated advertisement, and a plurality of advertisements in the advertisement combination are displayed on the same page at the same time, or the advertisements in the advertisement combination are displayed in a carousel mode in the patch advertisement.
Based on the above description, as shown in fig. 2, the method for displaying an advertisement may specifically include the following steps:
step 201, in a learning phase, aiming at each advertisement, collecting first display effect information of the advertisement; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information of the advertisements and each associated advertisement; and determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement, and recording the correlation between the advertisement and each associated advertisement.
The display effect information specifically includes, but is not limited to, one or any combination of the following: a loss of jump rate, a click rate, a like rate. Wherein, the loss rate (Bounce) is the rate at which the advertisement is closed, that is, the rate at which the user closes the advertisement during watching the advertisement, and a lower loss rate indicates a better display effect. The Click rate (Click) is the rate of the advertisement being clicked and viewed, that is, the rate of the advertisement being clicked and viewed by the user, when the user clicks the advertisement, it can be considered that the higher the Click rate is, the better the display effect is. The Like rate (Like) is a rate at which the advertisement is liked by the user, the user may be allowed to select whether to Like or dislike the advertisement when the advertisement is presented, and the rate at which the user likes the advertisement is the Like rate, and a higher Like rate indicates a better presentation effect. When the advertisement is displayed, the user can select the advertisement which is liked or disliked by setting the like option and the dislike option, and then the ratio that the user likes the advertisement is determined.
For each advertisement, the associated advertisement corresponding to the advertisement refers to an advertisement displayed on the same page as the advertisement, or an advertisement displayed in the same tile advertisement as the advertisement.
In the patch advertisement, a plurality of advertisements are usually broadcast in turn, and can be mutually associated advertisements; alternatively, only two adjacent advertisements may be correlated advertisements because the correlation effect between only two adjacent advertisements is relatively large. For example, when advertisement a, advertisement B, and advertisement C appear in the carousel in the tile advertisement, the associated advertisements of advertisement a are advertisement B and advertisement C, the associated advertisements of advertisement B are advertisement a and advertisement C, and the associated advertisements of advertisement C are advertisement a and advertisement B; or the advertisement associated with the advertisement A is the advertisement B, the advertisement associated with the advertisement B is the advertisement A and the advertisement C, and the advertisement associated with the advertisement C is the advertisement B.
The method comprises the steps that for each advertisement, the advertisement and the associated advertisement are displayed in an associated mode, namely the advertisement and the associated advertisement are displayed on the same page at the same time; alternatively, in a tile ad, the carousel displays the ad and associated ads.
In the initial stage of advertisement putting, all advertisements are randomly put without considering relevance influence, and the process is a learning stage. In the learning phase, the presentation effectiveness information of each advertisement is collected, and the presentation effectiveness information of each advertisement displayed in association with other advertisements is collected. For example, when the advertisement a and the advertisement B are displayed on the same page, the display effect information of the advertisement a, the display effect information of the advertisement B, and the display effect information displayed in association with the advertisement a and the advertisement B may be collected; when the advertisement A and the advertisement C are displayed on the same page, the showing effect information of the advertisement A can be collected, the showing effect information of the advertisement C can be collected, and the showing effect information displayed by associating the advertisement A and the advertisement C can be collected; when the advertisement A, the advertisement B and the advertisement C are displayed on the same page, the display effect information of the advertisement A, the display effect information of the advertisement B, the display effect information of the advertisement C, the display effect information of the advertisement A and the advertisement B which are displayed in a correlation mode, the display effect information of the advertisement A and the advertisement C which are displayed in a correlation mode and the display effect information of the advertisement B and the advertisement C which are displayed in a correlation mode can be collected. In the whole learning stage, the display effect information is continuously collected, the average value of the collected display effect information of all the advertisements A is finally obtained, the display effect information of the advertisements A can be obtained, the average value of the collected display effect information of all the advertisements A and B which are displayed in an associated manner can be obtained, the display effect information of each advertisement A and B which are displayed in an associated manner can be obtained, and by analogy, the display effect information of each advertisement and the display effect information of each advertisement which is displayed in an associated manner with other advertisements can be collected.
In the embodiment of the present invention, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information and the second display effect information corresponding to each associated advertisement, which specifically includes but is not limited to the following manners: determining a first numerical value corresponding to the advertisement by using the first display effect information; for each associated advertisement, determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second display effect information corresponding to each associated advertisement; determining the relevance of each second value divided by the first value as the correlation between the advertisement and each associated advertisement; wherein, the larger the value of the second value divided by the first value is, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second value is.
For example, for advertisement a, a first numerical value corresponding to advertisement a is determined by using the first exhibition effectiveness information of advertisement a. And aiming at the related advertisement (advertisement B) of the advertisement A, determining a second numerical value corresponding to the advertisement A and the advertisement B by utilizing the second display effect information corresponding to the advertisement B. And aiming at the related advertisement (advertisement C) of the advertisement A, determining a second numerical value corresponding to the advertisement A and the advertisement C by utilizing the second showing effect information corresponding to the advertisement C.
When the first display effect information comprises a first skipping rate, a first click rate and a first like rate, and the second display effect information comprises a second skipping rate, a second click rate and a second like rate; determining a first numerical value corresponding to the advertisement by using the first display effect information specifically includes, but is not limited to, the following modes: the first value is determined to be (1-first loss rate) first click rate and first like rate. Determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement, which specifically includes but is not limited to the following ways: the second value is determined to be (1-second loss rate) second click rate and second like rate.
It should be noted that, for different combinations of the presentation effect information, the determining manner of the first numerical value and the second numerical value is similar to the above manner, for example, when the first presentation effect information includes a first skip rate and a first click rate, and the second presentation effect information includes a second skip rate and a second click rate, the first numerical value corresponding to the advertisement is determined by using the first presentation effect information, which specifically includes but is not limited to the following manners: the first value is determined to be (1-first rate of loss) first click rate. Determining a second numerical value corresponding to the advertisement and the associated advertisement by using the second showing effect information corresponding to the associated advertisement, which specifically includes but is not limited to the following modes: the second value is determined to be (1-second loss rate) second click rate. For the determination manner of the numerical value under the combination of other presentation effect information, repeated description is omitted in the embodiment of the present invention.
For advertisement a, assuming that Ba represents the loss rate of advertisement a, Ca represents the click rate of advertisement a, and La represents the like rate of advertisement a, the corresponding first value of advertisement a is (1-Ba) × Ca × La. For the associated advertisement (advertisement B) of advertisement a, assuming that Bab represents the loss rate of the associated display of advertisement a and advertisement B, Cab represents the click rate of the associated display of advertisement a and advertisement B, and Lab represents the like rate of the associated display of advertisement a and advertisement B, the second value corresponding to advertisement a and advertisement B is (1-Bab) × Cab. Through the above processing, a first value corresponding to the advertisement a and a second value corresponding to the advertisement a and the advertisement B (i.e. the associated advertisement) can be obtained. Thereafter, a correlation between ad a and ad B may be determined using the second value and the first value, the correlation between ad a and ad B being the second value divided by the first value. Wherein the greater the value of the second value divided by the first value (i.e., relevance), the greater the relevance between ad a and ad B. When the value obtained by dividing the second numerical value by the first numerical value is greater than 1, the advertisement A and the advertisement B are in positive correlation, and when the advertisement A and the advertisement B are displayed in a correlated manner, the display effect of the advertisement A is improved, and the display effect of the advertisement B is improved. When the value obtained by dividing the second numerical value by the first numerical value is smaller than 1, the negative correlation between the advertisement A and the advertisement B is indicated, and when the advertisement A and the advertisement B are displayed in a correlated manner, the display effect of the advertisement A is reduced, and the display effect of the advertisement B is reduced.
For each advertisement, after the correlation between the advertisement and each associated advertisement is obtained, the correlation between the advertisement and each associated advertisement may also be recorded in the storage medium. The specific recording method may be the method shown in table 1, or the method shown in table 2. In any way, as long as the correlation between each advertisement and each associated advertisement can be recorded, which is not described in detail in the embodiment of the present invention.
Step 201 is an optional step before the display stage, and step 201 may be performed before the display stage, or step 201 may not be performed in practical applications, and the correlation between each advertisement and each associated advertisement is stored in other manners, which is not described in detail in this embodiment of the present invention.
In the displaying stage, the correlation between each advertisement and each associated advertisement is queried (obtained from the storage medium), and the advertisement combination with the strongest correlation is determined, wherein the advertisement combination comprises a plurality of advertisements, and the advertisements in the advertisement combination are displayed in an associated manner, step 202.
In the embodiment of the present invention, the process of associating and displaying a plurality of advertisements in an advertisement combination specifically includes, but is not limited to, the following ways: simultaneously displaying a plurality of advertisements in the advertisement combination on the same page; alternatively, in a tile ad, a carousel displays multiple ads within a combination of ads.
When the time of the learning phase exceeds the preset time or the data collected in the learning phase is greater than the preset threshold value, the correlation record table recorded in the learning phase can already guide the subsequent advertisement display, so the learning phase is ended, and the display phase is started. In the display stage, the relevance record table shown in table 1 or table 2 is directly inquired to obtain the advertisement combination with the strongest relevance, and a plurality of advertisements in the advertisement combination are displayed in an associated manner. For example, when the relevance record table shown in table 1 or table 2 is directly looked up, the combination of advertisements with the strongest relevance is obtained as the combination of advertisement a and advertisement B, and thus advertisement a and advertisement B are displayed in association with each other.
The advertisement may be a specific advertisement or an advertisement tag. For example, advertisement a is a real advertisement for car a, advertisement B is a real advertisement for lube a; alternatively, advertisement a is an automobile type (advertisement tag) advertisement that includes all advertisements related to automobiles, and advertisement B is a lube oil type (advertisement tag) advertisement that includes all advertisements related to lube oil.
Based on the technical scheme, compared with the prior art, the embodiment of the invention has at least the following advantages that the purpose of improving the advertisement display effect is achieved by recording the correlation among the advertisements in the learning stage and associating and displaying a plurality of advertisements with stronger correlation in the display stage. Because manual intervention is not needed, a large amount of manual workload is reduced, and the problem that the associated display is not the advertisement with stronger relevance is avoided.
EXAMPLE III
Based on the same inventive concept as the above method, an embodiment of the present invention further provides an advertisement display apparatus, as shown in fig. 3, the advertisement display apparatus specifically includes:
a selection module 11, configured to, in a display phase, select at least one second advertisement from all associated advertisements by using the correlation between the first advertisement and each associated advertisement recorded in the learning phase when the first advertisement needs to be displayed; wherein the correlation between the first advertisement and each associated advertisement is determined by using first display effect information of the first advertisement and second display effect information displayed in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
a display module 12, configured to display the first advertisement and the at least one second advertisement in association.
Preferably, the apparatus for displaying an advertisement further includes:
the learning module 13 is configured to collect first display effect information of the first advertisement in a learning phase; aiming at a plurality of associated advertisements corresponding to a first advertisement, collecting second display effect information displayed by the first advertisement in association with each associated advertisement; determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
a correlation between the first advertisement and each associated advertisement is recorded.
The learning module 13 is specifically configured to determine a first numerical value corresponding to the first advertisement by using the first display effect information in a process of determining a correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement; determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein the larger the second value divided by the first value, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value.
When the first showing effect information specifically comprises a first skipping rate, a first click rate and a first like rate, and the second showing effect information specifically comprises a second skipping rate, a second click rate and a second like rate;
the learning module 13 is further configured to determine, in the process of determining a first value corresponding to the first advertisement by using the first display effect information, that the first value is (1-first skip rate) × first click rate × first like rate; in the process of determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) second click rate second like rate.
Preferably, the selecting module 11 is specifically configured to, in a process of selecting at least one second advertisement from all associated advertisements by using the correlation between the first advertisement and each associated advertisement recorded in the learning stage, obtain the number of second advertisements displayed in association with the first advertisement, sort each associated advertisement in an order of strong or weak correlation by using the correlation between the first advertisement and each associated advertisement, and select the number of associated advertisements from all associated advertisements as the second advertisements according to a result of the sorting from the associated advertisement with the strongest correlation with the first advertisement.
Preferably, the correlation between the first advertisement and the associated advertisement selected from all associated advertisements as the second advertisement is greater than 1.
The display module 12 is specifically configured to display the first advertisement and the at least one second advertisement simultaneously on the same page in a process of displaying the first advertisement and the at least one second advertisement in an associated manner; alternatively, in the tile advertisement, the first advertisement and the at least one second advertisement are displayed in a carousel.
The modules of the device can be integrated into a whole or can be separately deployed. The modules can be combined into one module, and can also be further split into a plurality of sub-modules.
Example four
Based on the same inventive concept as the above method, an embodiment of the present invention further provides an advertisement display apparatus, as shown in fig. 4, the advertisement display apparatus specifically includes:
a selection module 21, configured to, in a display stage, query a correlation between each advertisement and each associated advertisement recorded in a learning stage, and determine an advertisement combination with the strongest correlation, where the advertisement combination includes multiple advertisements; wherein, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information of the advertisement and the second display effect information displayed by the advertisement in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and the display module 22 is used for displaying a plurality of advertisements in the advertisement combination in an associated manner.
Preferably, the apparatus for displaying an advertisement further includes: the learning module 23 is configured to, in a learning phase, collect, for each advertisement, first display effect information of the advertisement; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information displayed by the advertisements in association with each associated advertisement; determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement; the correlation between the advertisement and each associated advertisement is recorded.
The learning module 23 is specifically configured to determine a first numerical value corresponding to each associated advertisement by using the first display effect information in a process of determining a correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement; determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the advertisement and each associated advertisement; wherein the larger the value of the second numerical value divided by the first numerical value, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second numerical value.
Preferably, when the first display effect information specifically includes a first skip rate, a first click rate, and a first like rate, and the second display effect information specifically includes a second skip rate, a second click rate, and a second like rate; the learning module 23 is further configured to determine, in the process of determining a first numerical value corresponding to the advertisement by using the first display effect information, that the first numerical value is (1-a first loss rate) × a first click rate × a first like rate; in the process of determining the advertisement and each second numerical value corresponding to each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) × second click rate × second like rate.
Preferably, the display module 22 is specifically configured to display multiple advertisements in the advertisement assembly on the same page simultaneously in a process of displaying multiple advertisements in the advertisement assembly in an associated manner; alternatively, in a tile ad, a carousel displays multiple ads within the ad grouping.
The modules of the device can be integrated into a whole or can be separately deployed. The modules can be combined into one module, and can also be further split into a plurality of sub-modules.
For the system/apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (24)

1. A method of advertisement display, the method comprising the steps of:
in the display stage, when a first advertisement needs to be displayed, at least one second advertisement is selected from all the associated advertisements by utilizing the correlation between the first advertisement and each associated advertisement recorded in the learning stage; wherein the correlation between the first advertisement and each associated advertisement is determined by using first display effect information of the first advertisement and second display effect information displayed in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and displaying the first advertisement and the at least one second advertisement in association.
2. The method of claim 1, wherein the display phase is preceded by:
a learning stage, wherein first display effect information of the first advertisement is collected; aiming at a plurality of associated advertisements corresponding to a first advertisement, collecting second display effect information displayed by the first advertisement in association with each associated advertisement;
determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
a correlation between the first advertisement and each associated advertisement is recorded.
3. The method of claim 2, wherein the determining the correlation between the first advertisement and each associated advertisement using the first presentation effectiveness information and the second presentation effectiveness information corresponding to each associated advertisement specifically comprises:
determining a first numerical value corresponding to the first advertisement by using the first display effect information;
determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement;
determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein the larger the second value divided by the first value, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value.
4. The method of claim 3,
when the first showing effect information specifically comprises a first skipping rate, a first click rate and a first like rate, and the second showing effect information specifically comprises a second skipping rate, a second click rate and a second like rate;
the determining a first numerical value corresponding to the first advertisement by using the first display effect information specifically includes: determining the first value to be (1-first loss rate) first click rate (first like rate);
the determining, by using the second display effect information corresponding to each associated advertisement, each second numerical value corresponding to the first advertisement and each associated advertisement specifically includes: determining the second value to be (1-second loss rate) second click rate second like rate.
5. The method of claim 1, wherein the selecting at least one second advertisement from all associated advertisements using the correlation between the first advertisement and each associated advertisement comprises:
acquiring the quantity of second advertisements displayed in association with the first advertisements, sequencing each associated advertisement according to the sequence of strong and weak relevance by utilizing the relevance between the first advertisements and each associated advertisement, and selecting the quantity of associated advertisements from all associated advertisements as the second advertisements according to the sequencing result from the associated advertisement with the strongest relevance with the first advertisements.
6. The method of claim 5 wherein the correlation between the first advertisement and an associated advertisement selected from all associated advertisements as a second advertisement is greater than 1.
7. The method of claim 1, wherein the associating displays the first advertisement and the at least one second advertisement, in particular comprising:
displaying the first advertisement and the at least one second advertisement simultaneously on the same page; or,
in the tile advertisement, the first advertisement and the at least one second advertisement are displayed in a carousel.
8. A method of advertisement display, the method comprising the steps of:
in the display stage, inquiring the correlation between each advertisement and each associated advertisement recorded in the learning stage, and determining the advertisement combination with the strongest correlation, wherein the advertisement combination comprises a plurality of advertisements; wherein, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information of the advertisement and the second display effect information displayed by the advertisement in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and displaying a plurality of advertisements in the advertisement combination in an associated mode.
9. The method of claim 8, wherein the display phase is preceded by:
a learning stage, aiming at each advertisement, collecting first display effect information of the advertisement; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information displayed by the advertisements in association with each associated advertisement;
determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
the correlation between the advertisement and each associated advertisement is recorded.
10. The method of claim 9, wherein the determining the correlation between the advertisement and each associated advertisement using the first presentation effectiveness information and the second presentation effectiveness information corresponding to each associated advertisement specifically comprises:
determining a first numerical value corresponding to the advertisement by using the first display effect information;
determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement;
determining a value of each second value divided by the first value as a correlation between the advertisement and each associated advertisement; wherein the larger the value of the second numerical value divided by the first numerical value, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second numerical value.
11. The method of claim 10,
when the first showing effect information specifically comprises a first skipping rate, a first click rate and a first like rate, and the second showing effect information specifically comprises a second skipping rate, a second click rate and a second like rate;
the determining a first numerical value corresponding to the advertisement by using the first display effect information specifically includes: determining the first value to be (1-first loss rate) first click rate (first like rate);
the determining, by using the second display effect information corresponding to each associated advertisement, each advertisement and each second numerical value corresponding to each associated advertisement specifically includes: determining the second value to be (1-second loss rate) second click rate second like rate.
12. The method of claim 8, wherein the associating displays a plurality of advertisements within the advertisement portfolio, particularly comprising:
simultaneously displaying a plurality of advertisements in the advertisement combination on the same page; or,
in the tile advertisement, a carousel displays a plurality of advertisements within the advertisement set.
13. An advertisement display device, characterized in that the device specifically comprises:
the selection module is used for selecting at least one second advertisement from all the associated advertisements by utilizing the correlation between the first advertisement and each associated advertisement recorded in the learning stage when the first advertisement needs to be displayed in the display stage; wherein the correlation between the first advertisement and each associated advertisement is determined by using first display effect information of the first advertisement and second display effect information displayed in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
a display module for displaying the first advertisement and the at least one second advertisement in association.
14. The apparatus of claim 13, further comprising:
the learning module is used for collecting first display effect information of the first advertisement in a learning stage; aiming at a plurality of associated advertisements corresponding to a first advertisement, collecting second display effect information displayed by the first advertisement in association with each associated advertisement; determining the correlation between the first advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
a correlation between the first advertisement and each associated advertisement is recorded.
15. The apparatus of claim 14,
the learning module is specifically configured to determine a first numerical value corresponding to the first advertisement by using the first display effect information in a process of determining a correlation between the first advertisement and each associated advertisement by using the first display effect information and second display effect information corresponding to each associated advertisement; determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the first advertisement and each associated advertisement; wherein the larger the second value divided by the first value, the stronger the correlation between the first advertisement and the associated advertisement corresponding to the second value.
16. The apparatus of claim 15,
when the first showing effect information specifically comprises a first skipping rate, a first click rate and a first like rate, and the second showing effect information specifically comprises a second skipping rate, a second click rate and a second like rate;
the learning module is further configured to determine, in a process of determining a first numerical value corresponding to the first advertisement by using the first display effect information, that the first numerical value is (1-a first loss rate) × a first click rate × a first like rate; in the process of determining each second numerical value corresponding to the first advertisement and each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) second click rate second like rate.
17. The apparatus of claim 13,
the selection module is specifically configured to, in a process of selecting at least one second advertisement from all associated advertisements by using the correlation between the first advertisement and each associated advertisement recorded in the learning stage, acquire the number of second advertisements displayed in association with the first advertisement, sort each associated advertisement in an order of strong or weak correlation by using the correlation between the first advertisement and each associated advertisement, and select the number of associated advertisements from all associated advertisements as the second advertisements according to a sorting result starting from the associated advertisement with the strongest correlation with the first advertisement.
18. The apparatus of claim 17, wherein a correlation between the first advertisement and an associated advertisement selected from all associated advertisements as a second advertisement is greater than 1.
19. The apparatus of claim 13,
the display module is specifically configured to display the first advertisement and the at least one second advertisement simultaneously on the same page in a process of displaying the first advertisement and the at least one second advertisement in an associated manner; alternatively, in the tile advertisement, the first advertisement and the at least one second advertisement are displayed in a carousel.
20. An advertisement display device, characterized in that the device specifically comprises:
the selection module is used for inquiring the correlation between each advertisement and each associated advertisement recorded in the learning stage in the display stage and determining the advertisement combination with the strongest correlation, wherein the advertisement combination comprises a plurality of advertisements; wherein, for each advertisement, the correlation between the advertisement and each associated advertisement is determined by using the first display effect information of the advertisement and the second display effect information displayed by the advertisement in association with each associated advertisement; the display effect information includes one or any combination of the following: a loss rate, a click rate, a like rate; wherein the skipping rate is a rate of closing the advertisement, the click-through rate is a rate of clicking to view the advertisement, and the like rate is a rate of liking the advertisement by the user;
and the display module is used for displaying a plurality of advertisements in the advertisement combination in an associated manner.
21. The apparatus of claim 20, further comprising:
the learning module is used for collecting first display effect information of each advertisement in a learning stage; aiming at a plurality of associated advertisements corresponding to the advertisements, collecting second display effect information displayed by the advertisements in association with each associated advertisement;
determining the correlation between the advertisement and each associated advertisement by using the first display effect information and the second display effect information corresponding to each associated advertisement;
the correlation between the advertisement and each associated advertisement is recorded.
22. The apparatus of claim 21,
the learning module is specifically configured to determine a first numerical value corresponding to each associated advertisement by using the first display effect information in a process of determining a correlation between the advertisement and each associated advertisement by using the first display effect information and second display effect information corresponding to each associated advertisement; determining each second numerical value corresponding to the advertisement and each associated advertisement by using the second showing effect information corresponding to each associated advertisement; determining a value of each second value divided by the first value as a correlation between the advertisement and each associated advertisement; wherein the larger the value of the second numerical value divided by the first numerical value, the stronger the correlation between the advertisement and the associated advertisement corresponding to the second numerical value.
23. The apparatus of claim 22,
when the first showing effect information specifically comprises a first skipping rate, a first click rate and a first like rate, and the second showing effect information specifically comprises a second skipping rate, a second click rate and a second like rate;
the learning module is further configured to determine, in a process of determining a first numerical value corresponding to the advertisement by using the first display effect information, that the first numerical value is (1-first skip rate) × first click rate × first like rate; in the process of determining the advertisement and each second numerical value corresponding to each associated advertisement by using the second display effect information corresponding to each associated advertisement, determining the second numerical value as (1-second skip rate) × second click rate × second like rate.
24. The apparatus of claim 20,
the display module is specifically configured to display multiple advertisements in the advertisement combination on the same page at the same time in a process of displaying the multiple advertisements in the advertisement combination in an associated manner; alternatively, in a tile ad, a carousel displays multiple ads within the ad grouping.
CN201510386612.3A 2015-06-30 2015-06-30 A method and an apparatus for advertisement displaying Pending CN104933603A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510386612.3A CN104933603A (en) 2015-06-30 2015-06-30 A method and an apparatus for advertisement displaying

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510386612.3A CN104933603A (en) 2015-06-30 2015-06-30 A method and an apparatus for advertisement displaying

Publications (1)

Publication Number Publication Date
CN104933603A true CN104933603A (en) 2015-09-23

Family

ID=54120759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510386612.3A Pending CN104933603A (en) 2015-06-30 2015-06-30 A method and an apparatus for advertisement displaying

Country Status (1)

Country Link
CN (1) CN104933603A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107169785A (en) * 2017-03-31 2017-09-15 北京奇艺世纪科技有限公司 A kind of advertisement placement method and device
WO2017177859A1 (en) * 2016-04-11 2017-10-19 腾讯科技(深圳)有限公司 Video playing method and device, and computer readable storage medium
CN107563813A (en) * 2017-09-05 2018-01-09 北京奇艺世纪科技有限公司 A kind of control method and system of the PDB advertisement pushings frequency
CN108027931A (en) * 2015-09-29 2018-05-11 Line株式会社 Information processor, control method and program
WO2019218884A1 (en) * 2018-05-16 2019-11-21 阿里巴巴集团控股有限公司 Multi-advertisement collaborative delivery, display method and apparatus, and electronic device

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1689002A (en) * 2002-09-24 2005-10-26 Google公司 Serving advertisements based on content
CN1689017A (en) * 2002-08-27 2005-10-26 Google公司 Method for providing advertising listing variance in distribution feeds
CN1842833A (en) * 2003-06-30 2006-10-04 Google公司 Promoting and or demoting an advertisement from an advertising spot of one type to an advertising spot of another type
CN101071445A (en) * 2007-06-22 2007-11-14 腾讯科技(深圳)有限公司 Classified sample set optimizing method and content-related advertising server
CN101770486A (en) * 2008-12-30 2010-07-07 北京搜狗科技发展有限公司 Advertising method and system
WO2010134724A2 (en) * 2009-05-18 2010-11-25 팅크웨어(주) Method and apparatus for providing dynamic advertisements
CN102024218A (en) * 2009-09-14 2011-04-20 腾讯科技(深圳)有限公司 Method and apparatus for delivering advertisement
CN102346899A (en) * 2011-10-08 2012-02-08 亿赞普(北京)科技有限公司 Method and device for predicting advertisement click rate based on user behaviors
CN102687168A (en) * 2009-11-03 2012-09-19 雅虎公司 Sequenced video overlay advertisements
US20130066715A1 (en) * 2011-09-09 2013-03-14 Dennoo Inc. Methods and systems for time-variable cps based on user interaction with advertisement
CN103794159A (en) * 2012-10-30 2014-05-14 中国电信股份有限公司 Method, device and system for playing multimedia advertisements
CN104200380A (en) * 2014-09-18 2014-12-10 北京国双科技有限公司 Promotion information positioning method and device
US20150019347A1 (en) * 2013-03-15 2015-01-15 Nabil Naghdy Viewport based display of advertisements
CN104661056A (en) * 2013-11-19 2015-05-27 财团法人资讯工业策进会 Interactive advertisement providing method and system

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1689017A (en) * 2002-08-27 2005-10-26 Google公司 Method for providing advertising listing variance in distribution feeds
CN1689002A (en) * 2002-09-24 2005-10-26 Google公司 Serving advertisements based on content
CN1842833A (en) * 2003-06-30 2006-10-04 Google公司 Promoting and or demoting an advertisement from an advertising spot of one type to an advertising spot of another type
CN101071445A (en) * 2007-06-22 2007-11-14 腾讯科技(深圳)有限公司 Classified sample set optimizing method and content-related advertising server
CN101770486A (en) * 2008-12-30 2010-07-07 北京搜狗科技发展有限公司 Advertising method and system
WO2010134724A2 (en) * 2009-05-18 2010-11-25 팅크웨어(주) Method and apparatus for providing dynamic advertisements
CN102024218A (en) * 2009-09-14 2011-04-20 腾讯科技(深圳)有限公司 Method and apparatus for delivering advertisement
CN102687168A (en) * 2009-11-03 2012-09-19 雅虎公司 Sequenced video overlay advertisements
US20130066715A1 (en) * 2011-09-09 2013-03-14 Dennoo Inc. Methods and systems for time-variable cps based on user interaction with advertisement
CN102346899A (en) * 2011-10-08 2012-02-08 亿赞普(北京)科技有限公司 Method and device for predicting advertisement click rate based on user behaviors
CN103794159A (en) * 2012-10-30 2014-05-14 中国电信股份有限公司 Method, device and system for playing multimedia advertisements
US20150019347A1 (en) * 2013-03-15 2015-01-15 Nabil Naghdy Viewport based display of advertisements
CN104661056A (en) * 2013-11-19 2015-05-27 财团法人资讯工业策进会 Interactive advertisement providing method and system
CN104200380A (en) * 2014-09-18 2014-12-10 北京国双科技有限公司 Promotion information positioning method and device

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108027931A (en) * 2015-09-29 2018-05-11 Line株式会社 Information processor, control method and program
WO2017177859A1 (en) * 2016-04-11 2017-10-19 腾讯科技(深圳)有限公司 Video playing method and device, and computer readable storage medium
US10735817B2 (en) 2016-04-11 2020-08-04 Tencent Technology (Shenzhen) Company Limited Video playback method and apparatus, and computer readable storage medium
CN107169785A (en) * 2017-03-31 2017-09-15 北京奇艺世纪科技有限公司 A kind of advertisement placement method and device
CN107563813A (en) * 2017-09-05 2018-01-09 北京奇艺世纪科技有限公司 A kind of control method and system of the PDB advertisement pushings frequency
CN107563813B (en) * 2017-09-05 2021-01-22 北京奇艺世纪科技有限公司 PDB advertisement push frequency control method and system
WO2019218884A1 (en) * 2018-05-16 2019-11-21 阿里巴巴集团控股有限公司 Multi-advertisement collaborative delivery, display method and apparatus, and electronic device

Similar Documents

Publication Publication Date Title
CN104933603A (en) A method and an apparatus for advertisement displaying
JP6821149B2 (en) Information processing using video for advertisement distribution
CN109214842B (en) Information popularization method, device and equipment
CN102811371B (en) The method, system and device that intelligent television application program is recommended
CN105550903A (en) Target user determination method and apparatus
US20090319517A1 (en) Query identification and association
JP5795387B2 (en) Method, system and computer readable recording medium for recommending other users or objects by considering the presence of at least one user
EP2242016A1 (en) Touchpoint customization system
RU2010121864A (en) ATTACHING COUPLES PROPERTY-VALUE, RE-RANING AND FILTERING OF ANNOUNCEMENTS
WO2009116198A1 (en) Advertisement medium determination device and advertisement medium determination method
WO2016170728A1 (en) Targeted advertising based on viewed advertisments and viewing time condition
CN104484406B (en) The dispensing analysis method and device of recommending data
CN105045831A (en) Message push method and apparatus
CN111814034A (en) Information processing method, information processing apparatus, storage medium, and electronic device
US20190050890A1 (en) Video dotting placement analysis system, analysis method and storage medium
CN105184611A (en) Advertising effect quantification method and display system
KR20140109607A (en) Methods and apparatuses for deducing a viewing household member profile
CN103530796B (en) The active period detection method of application program and active period detection system
CN102985938A (en) A method and apparatus for creating recommendations for a user
CN104915864B (en) The method and device that the dispensing effect of impression information is evaluated and tested
US20110282741A1 (en) Method for offering advertisement according to search intention segmentation and system for executing the method
Piątkowska et al. A systematic literature review on ambush marketing in sport
Gamage et al. Product placement versus traditional TV commercials: new insights on their impacts on brand recall and purchase intention
der Waldt et al. Product placement: exploring effects of product usage by principal actors
JP2010211385A (en) Information providing device and information providing method and information providing program

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20150923