KR20150121370A - Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor - Google Patents
Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor Download PDFInfo
- Publication number
- KR20150121370A KR20150121370A KR1020140046855A KR20140046855A KR20150121370A KR 20150121370 A KR20150121370 A KR 20150121370A KR 1020140046855 A KR1020140046855 A KR 1020140046855A KR 20140046855 A KR20140046855 A KR 20140046855A KR 20150121370 A KR20150121370 A KR 20150121370A
- Authority
- KR
- South Korea
- Prior art keywords
- advertisement
- user device
- user
- interest information
- probability
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Abstract
The present invention relates to an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, And posts the recorded recording medium. That is, it is possible to target a recommendation advertisement based on real-time advertisement analysis for determining a recommended advertisement by grouping a plurality of user apparatuses in real time based on advertisement interest information collected from a plurality of user apparatuses. Thus, the CTR (click through rate) of the user apparatus can be improved. In addition, compared to passive targeting method based on demographic-based classification of existing users, it is a technology that can be changed and reflected automatically in real time. Therefore, .
Description
The present invention relates to an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, an advertisement service apparatus, The present invention relates to a recording medium in which a plurality of user devices are grouped into user device groups by analyzing the advertisement interest of a plurality of user devices in real time and an advertisement targeting a recommended advertisement based on real- A service device, a user device receiving a recommendation advertisement based on real-time advertisement analysis, a method of targeting a recommendation advertisement based on real-time advertisement analysis, and a recording medium on which a computer program is recorded.
Twenty years have passed since the growth of the world wide web (WWW), which led to the popularization of the Internet. Internet advertising began in banner form in HOTWIRED in October 1994, two years after the first website was opened in 1992. Although text-based advertising based on PC communication is the beginning of Internet advertising, it is from HOTWIRED ads in the United States that the present form of interaction with users is possible.
Ads posted on HOTWIRED were created in September 1994 to promote AT & T's website, youwill.com, while promoting the site. hotwired.com convinced AT & T to attract online banner ads for the first time, and it was a groundbreaking idea at the time of the first banner ad to insert clicks into the phrase "Have you ever clicked your mouse right".
In the beginning, domestic Internet advertising was introduced in 1994, and developed into a banner that conveys more messages through the development of multimedia technology, focusing on simple banner advertisement. During this period, Internet advertising was developed into various forms such as electronic mail and webzine, while earning recognition as an alternative to traditional media in earnest.
Since then, the number of Internet users has reached 10 million in 1999 and the number of Internet users has surpassed 30 million in 2004, so Internet advertising has grown along with the growth of display advertisement (AD) and search AD New types of ads appeared.
As the world's first WiBro and HSDPA service was launched in Korea in 2006, wired Internet usage is becoming stagnant and mobile Internet usage is accelerating. As a result, personalized information is being used as a new Internet business center.
The Internet and mobile advertising industries have grown beyond the print media to become the two major advertising media. They are based on the characteristics of selectivity, real-time, location-based, and interactivity beyond the time and ground constraints of existing advertising media. .
An object of the present invention is to provide an advertisement service apparatus for targeting a recommendation advertisement based on real-time advertisement analysis for determining a recommendation advertisement by grouping a plurality of user apparatuses in real time based on advertisement interest information collected from a plurality of user apparatuses, A user device receiving a recommended advertisement based on analysis of advertisements, a method of targeting a recommended advertisement based on analysis of real time advertisements, and a recording medium on which a computer program is recorded.
Another object of the present invention is to provide a method and apparatus for targeting a recommendation advertisement based on real-time advertisement analysis for determining a recommendation advertisement based on a correlation between clicks of an advertisement based on probability information that a specific user device clicks another advertisement when a specific advertisement is clicked A user device receiving a recommended advertisement based on real-time advertisement analysis, a method of targeting a recommended advertisement based on real-time advertisement analysis, and a recording medium on which a computer program is recorded.
Another object of the present invention is to provide a method and apparatus for analyzing whether or not a user clicks on a web site that is actually advertised when a click occurs, A user device receiving a recommended advertisement based on real-time advertisement analysis, a method of targeting a recommended advertisement based on real-time advertisement analysis, and a recording medium on which a computer program is recorded.
The advertisement service apparatus for advertisement recommendation according to an embodiment of the present invention includes an advertisement interest information acquisition unit for receiving advertisement interest information from each of a plurality of user devices, And a probability that the first user device in the user device group will click on the second advertisement is calculated. If the probability is equal to or greater than the threshold value, the second advertisement is determined as the recommended advertisement of the second user device in the user device group And a recommendation advertisement determination unit.
As an example related to the present invention, the advertisement interest information may include information about at least one of an impression, a click, a click through rate (CTR), and a probability that a user clicks on the advertisement .
As an example related to the present invention, the user device group generator may be configured to determine a filtering priority of advertisement interest information to determine a user device group, to filter a plurality of user devices for a first advertisement according to a filtering priority, And generate at least one user device among the plurality of user devices corresponding to the schedule priority based on the result as a user device group for the first advertisement.
As an example related to the present invention, the filtering priority may be a probability that a user clicks on the advertisement, a CTR, a number of clicks, and an order of the number of impressions.
As an example related to the present invention, the number of clicks is counted only for a click corresponding to a valid click by distinguishing a valid click and a miss click, and the valid click is a time when the first user apparatus stays on the website to which the first user apparatus is advertised, And may be determined based on whether or not the additional information is requested by the website to be advertised.
As an example associated with the present invention, the probability that a first user device in a group of user devices clicks on a second advertisement is given by Equation P (probability of clicking on second ad | probability of clicking on first ad) = P Probability of clicking the first advertisement) / P (probability of clicking the first advertisement).
As an example related to the present invention, a reclassified user device group can be created by reclassifying a user device group based on a click rate of a recommended advertisement.
The user device receiving the recommendation advertisement according to the embodiment of the present invention collects advertisement interest information to be transmitted to the advertisement service device, and the advertisement interest information includes impression, click, CTR ) And a probability that a user will click on the advertisement, and transmitting the advertisement interest information to the advertisement service apparatus and receiving the recommendation advertisement based on the advertisement interest information .
As an example related to the present invention, the recommendation advertisement is determined by other user devices included in the user device group grouped by the user device, the app tracking unit re-collects the advertisement interest information about the recommended advertisement, And can be reclassified based on the advertisement interest information for the advertisement.
The advertisement service apparatus for determining a recommended advertisement according to an exemplary embodiment of the present invention includes receiving advertisement interest information from each of a plurality of user devices, generating a user device group for the first advertisement based on advertisement interest information And determining a second advertisement in the user device group as a recommendation advertisement of the second user device in the user device group when the probability that the first user device in the user device group is clicked is equal to or greater than the threshold value.
The generating of the user device group for the first advertisement based on the advertisement interest information may include determining a filtering priority of the advertisement interest information, Filtering the plurality of user devices and generating at least one of the plurality of user devices corresponding to the predetermined priority based on the filtering result as a user device group for the first advertisement.
A computer program for carrying out the method according to the above-described embodiment may be stored in the recording medium on which the computer program according to the embodiment of the present invention is recorded.
The advertisement recommendation system according to an embodiment of the present invention collects advertisement interest information to be transmitted to an advertisement service apparatus, and the advertisement interest information includes an impression, a click, a click through rate (CTR) And a probability that the user clicks the advertisement, and transmits the advertisement interest information to the advertisement service apparatus and receives the recommendation advertisement based on the advertisement interest information, Grouping the user devices into user device groups based on the advertisement interest information, calculating the probability that another user device in the user device group clicks on a specific advertisement, and, if the probability is equal to or greater than the threshold value, And an advertisement service device that is implemented to determine the advertisement.
The present invention can group the user devices based on the advertisement interest information collected from the user device in real time and determine the recommended advertisement to be transmitted to the user devices included in the grouped user device group. Thus, it is possible to expose more interesting advertisements and thereby improve the click through rate (CTR) of the user device.
In addition, compared to passive targeting method based on demographic-based classification of existing users, since the group is changed and reflected automatically in real time, a recommendation advertisement determined based on a machine learning basis is provided to the user device can do.
1 is a flowchart illustrating an advertisement recommendation method according to an embodiment of the present invention.
2 is a conceptual diagram illustrating an advertisement service apparatus according to an embodiment of the present invention.
3 is a conceptual diagram illustrating a user device group generation unit according to an embodiment of the present invention.
4 is a conceptual diagram illustrating a recommended advertisement determination unit according to an embodiment of the present invention.
5 is a conceptual diagram illustrating a recommended advertisement targeting method according to an embodiment of the present invention.
6 is a conceptual diagram illustrating reclassification of a user device group according to an embodiment of the present invention.
7 is a conceptual diagram illustrating a click rate analysis according to an embodiment of the present invention.
It is noted that the technical terms used in the present invention are used only to describe specific embodiments and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be construed in a sense generally understood by a person having ordinary skill in the art to which the present invention belongs, unless otherwise defined in the present invention, and an overly comprehensive It should not be construed as meaning or overly reduced. In addition, when a technical term used in the present invention is an erroneous technical term that does not accurately express the concept of the present invention, it should be understood that technical terms that can be understood by a person skilled in the art can be properly understood. In addition, the general terms used in the present invention should be interpreted according to a predefined or context, and should not be construed as being excessively reduced.
Furthermore, the singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. The term "comprising" or "comprising" or the like in the present invention should not be construed as necessarily including the various elements or steps described in the invention, Or may include additional components or steps.
In addition, terms including ordinals such as first, second, etc. used in the present invention can be used to describe elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.
Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, and redundant description thereof will be omitted.
In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It is to be noted that the accompanying drawings are only for the purpose of facilitating understanding of the present invention, and should not be construed as limiting the scope of the present invention with reference to the accompanying drawings.
In the conventional mobile advertisement, the advertisement recommendation techniques are classified into a plurality of user devices by analyzing the tendencies or characteristics of the users, and passive targeting of the advertisements corresponding to the classified user devices is used. It was important to classify multiple user devices through demographic analysis. Also, since the classified user device is closely related to manual targeting, it has been difficult to change the classification of the user device in real time.
According to the embodiment of the present invention, each of the plurality of user equipments can analyze the received advertisement in real time. Based on the analyzed results, a plurality of user devices can be classified into a specific user device group based on the interest of the advertisement. Also, it is possible to determine an advertisement to be recommended to other user devices included in the user device group based on the advertisement reception information of the specific user device in the user device group. That is, an advertisement corresponding to the subordinate preference of the specific user apparatus included in the user apparatus group may be recommended to another user apparatus of the same user apparatus group.
According to the embodiment of the present invention, the advertisement service apparatus analyzes the interest of the advertisement in real time based on the clicks and click through rate (CTR) collected from the user apparatus, And transmits the recommended advertisement determined in real time to the user device. In addition, there is no need to analyze the category of the advertisement of the specific advertisement separately, and it is possible to reduce the burden of the operation for the advertisement targeting by automatically recommending the advertisement through the analysis without designating the target manually. In addition, interest-based recommendation can maximize the click through rate (CTR) of the user device and more effectively target the advertisement.
1 is a flowchart illustrating an advertisement recommendation method according to an embodiment of the present invention.
The advertisement recommendation method according to the embodiment of the present invention can be applied to a commerce ad platform linked to a DMP (data management platform) to which machine learning is applied. Various information for determining a recommended advertisement to be published below can be obtained through app tracking. Various information for determining a recommended advertisement can be obtained every predetermined period (for example, five minutes).
Referring to FIG. 1, advertisement interest information is received from each of a plurality of user devices (step S100).
The advertisement service apparatus can collect advertisement interest information from each of the plurality of user apparatuses in order to group the user apparatuses according to the advertisement interest information and determine the recommended advertisement in the group of user apparatuses grouped.
The advertisement interest information may include information about an impression of an advertisement, clicks of an advertisement, a click through rate (CTR), a probability that a user clicks on the advertisement, and the like. The advertisement interest information may be acquired based on an app tracking function provided in the user device.
Table 1 below shows the advertisement interest information of the user device for each advertisement.
<Table 1>
Referring to Table 1, the advertisement id may be an identifier of an advertisement for identifying an advertisement, and the user device_id may indicate an identifier of a user apparatus.
Impression indicates the number of times the advertisement is transmitted to the user device, and the number of clicks indicates the number of times the advertisement device clicked on the advertisement. CTR indicates the number of clicks on an ad that has been exposed to a user device (number of clicks / number of impressions) x 100. The probability that the user will click on the ad (the number of clicks on the total ad impressions of the user / the total ad impressions of the user) x 100. For example, the probability that the user u1 clicks the advertisement A can be calculated as [1 / (100 + 100 + 200)] x100 = 0.25%.
The advertisement service apparatus can create a user device group by grouping the user apparatuses based on the collected advertisement interest information as shown in Table 1. [ The ad serving device may determine a referral ad within the user device group. The time at which the media is used by the user device or the number of impressions for a particular advertisement due to targeting may appear differently. However, since the average usage time of user devices is the same, inventory (user advertisement request) may appear to be similar. That is, the advertisement service apparatus can determine whether the latest user has the greatest interest in an advertisement through the probability that the user clicks the advertisement.
And classifies the user device group based on the advertisement interest information (step S110).
The user device group can be grouped by prioritizing the advertisement interest information collected in step S100. For example, you can set up four priorities in your ad interest information to filter out those users who are highly interested in each ad (e.g., the top 20-30% of users) .
Table 2 below shows the priorities of advertising interest information.
<Table 2>
Referring to Table 2, the first rank is the probability that a user will click on the advertisement, the second rank is CTR, the third rank is the number of clicks, and the fourth rank is the number of impressions. Based on the priorities posted in Table 2, it is possible to filter user devices with a high degree of interest per advertisement.
Table 3 below shows the filtering of user devices in descending order of interest, based on the information published in Table 1 above.
<Table 3>
Referring to Table 3, user devices whose user device_id is u4, u3, u2, u1 are sorted in decreasing order in descending order of probability (first priority) of clicking on the advertisement for advertisement A. [
User devices whose device_id is u6, u8, u2, u7, u5, and u1 are sorted in decreasing order in the descending order of probability of clicking on the advertisement for advertisement B, respectively.
For the advertisement C, the user devices having the user device_id of u7, u1, u5, u6, and u4 are sorted in descending order in the descending order of probability of clicking the advertisement.
In the advertisement C, when the user device_id is u1 and u5, since the probability of the user clicking on the advertisement is the same, the CTR, which is the second priority, is determined and u1 having the large CTR can be sorted with a high priority.
After performing the sorting as described above for each advertisement based on the advertisement interest information, a plurality of user devices having an interest for a specific advertisement can be grouped by filtering user devices corresponding to a predetermined priority for each advertisement have.
Table 4 below shows only the user devices corresponding to a certain upper threshold percentage (for example, 20%) for each advertisement.
<Table 4>
Referring to Table 4, the user equipment corresponding to the upper 20% of the advertisement A is u4, the user equipment corresponding to the upper 20% of the advertisement B is u6, u8, and the upper 20% The user device may be u7.
Based on the filtered results, a user device group for each advertisement can be formed. For example, the first user device group for ad A includes u4, the second user device group for ad B includes u6 and u8, and the third user device group for ad C includes u7 .
A recommended advertisement is determined within the classified user device group (step S120).
In step S110, a user device group for a specific advertisement may be determined through filtering only the user apparatuses corresponding to the upper threshold percentage for each advertisement. The conditional probability that the user device included in the user device group for a specific advertisement clicks on another advertisement can be calculated. For example, a conditional probability that a user device included in a first user device group for an A advertisement clicks on a B advertisement or a C advertisement can be calculated. The conditional probability can be a criterion for the user device to select advertisements preferred by subordination.
The following equation represents the probability that user device u4 included in the first user device group for advertisement A clicks the B advertisement and the C advertisement.
≪ Equation &
Conditional probability formula
P (X | Y) = P (X? Y) / P (Y)
Conditional probability calculation
For example, the conditional probability of C advertisement of advertisement A of user u4
A Chance to click on ads: 2.5%
B likelihood of clicking on ads: 0% -> (0% x2.5%) / 2.5% = 0%
C chance to click on ads: 2.5% -> (2.5% x2.5%) / 2.5% = 2.5%
Table 5 below shows the value of conditional probability calculated by the above method.
<Table 5>
Referring to Table 5, it is possible to select advertisements within the top 20 to 30% of the calculated conditional probability, and to determine the advertisements as recommended advertisements of other user devices in the same user device group.
In the case of u4, u6, and u7, there are no users who have ads with conditional probability, and there is no advertisement to recommend. In case of u8, the probability that u6 clicks on this relatively high C advertisement is referred to as u8 .
Table 6 below shows a list of recommended advertisements based on conditional probability.
<Table 6>
In the case of using the advertisement targeting method according to the embodiment of the present invention, advertisement can be more effectively transmitted to the user device by applying an automated and real-time analyzed result.
In the case of using the advertisement recommendation method based on the user device group according to the embodiment of the present invention, the CTR can be improved through recommendation of the next advertisement in the same group having high advertisement interest. Because the algorithm is constructed based on the probability of click and advertisement selection, users of the interest group can be automatically changed if the probability of click and advertisement selection changes in real time.
2 is a conceptual diagram illustrating an advertisement service apparatus according to an embodiment of the present invention.
2, the advertisement service apparatus may include an advertisement interest
The advertisement interest
The advertisement service apparatus may be configured to group the user apparatuses according to advertisement interest information and to determine a recommended advertisement in the grouped user apparatuses. The advertisement interest information may include information about at least one of an impression, a click, a CTR, and a probability that a user clicks on the advertisement. The advertisement interest information may be acquired based on an app tracking function provided in the user device.
The user device
The recommended advertisement determination unit 220 may calculate a probability that a specific user device in the user device group generated by the user device
The
The operations of the user device
3 is a conceptual diagram illustrating a user device group generation unit according to an embodiment of the present invention.
Referring to FIG. 3, the user device group generating unit may include an advertisement interest
The advertisement interest
The
The user
4 is a conceptual diagram illustrating a recommended advertisement determination unit according to an embodiment of the present invention.
Referring to FIG. 4, the recommended advertisement determination unit may include a conditional
The conditional
The recommended
5 is a conceptual diagram illustrating a recommended advertisement targeting method according to an embodiment of the present invention.
In FIG. 5, when a recommendation advertisement is already present in the recommendation target user apparatus, a method of determining advertisement is posted. The recommendation target user device may be a user device that includes a recommendation advertisement in the advertisement list.
The advertisement service apparatus can determine whether the recommended advertisement is already in the recommended advertisement list. If the determined recommendation advertisement is already included in the advertisement list, the advertisement service apparatus can transmit another advertisement to the recommendation target user apparatus. The other advertisement may be an item classified in the same category as the recommended advertisement and similar to the article advertised in the referenced advertisement.
Alternatively, if the determined recommendation advertisement is already included in the advertisement list, the advertisement service apparatus may increase the frequency of sending the recommended advertisement to the recommendation target user apparatus.
6 is a conceptual diagram illustrating reclassification of a user device group according to an embodiment of the present invention.
In FIG. 6, a method of reclassifying a user device group in a plurality of user apparatuses of a user apparatus group provided with a recommendation advertisement is posted.
Referring to FIG. 6, a user device included in the first
Using this method, a plurality of user devices having similar product preferences in the first
Specifically, publishing the method of regrouping a group of user devices, a recommendation advertisement determined based on the
If at least one of the
In this manner, a method of reclassifying user device groups can regroup user devices having similar taste preferences and perform product advertisements that match the user device groups. For example, the advertisements provided to the first
The reclassification method disclosed in FIG. 6 uses various methods such as a method of reclassifying a recommendation advertisement to a second
7 is a conceptual diagram illustrating a click rate analysis according to an embodiment of the present invention.
In FIG. 7, a method of additionally analyzing the click rate as an actual effective click rate is posted.
When calculating the click rate for the exposed advertisement, the click rate can be calculated by judging whether or not the advertisement is actually viewed, not the simple click rate.
In many cases, users access websites that advertise by clicking on ads with a high percentage of users using the website. It is possible to calculate a more accurate click-through rate by further analyzing the connection of the advertised website due to such a miss click. In order to determine whether a click is a miss click, the user device may analyze the time at which the user has stayed at the connected advertisement site. In the case of an access to a advertised web site due to a miss click, most user devices will be able to disconnect from the site without much time left. Accordingly, when the user clicks on a web site to be advertised for a predetermined time (for example, five seconds) after accessing the advertised website, the click can be analyzed with a valid click. On the contrary, if the user remains at the advertisement site for less than the threshold time (for example, 5 seconds) after accessing the advertised website, the click can be analyzed as an invalid click.
It is possible to judge whether or not the user clicks the additional information on the web site to be advertised by accessing the web site to be advertised according to another judgment as to whether or not the user clicks the miss. If additional information is clicked on the advertised website, the validity of the click is analyzed and if the additional information is not clicked on the advertised website, the click can be analyzed as an invalid click.
That is, in the embodiment of the present invention, a miss click is determined (step S700), the effective click rate is calculated, and the advertisement interest is calculated based on the effective click rate (step S720).
A method for targeting a recommendation advertisement based on real-time advertisement analysis based on real-time advertisement analysis according to an embodiment of the present invention, a user device for receiving a recommendation advertisement based on real-time advertisement analysis, The code and code segments constituting the computer program can be easily deduced by a computer programmer in the field. In addition, the computer program may be stored in a computer-readable medium and readable by a computer, an advertisement service apparatus, a user apparatus, etc. according to an embodiment of the present invention to implement a synchronization method .
The information storage medium includes a magnetic recording medium, an optical recording medium, and a carrier wave medium. An advertisement service device that targets a recommended advertisement based on real-time advertisement analysis according to an embodiment of the present invention, a user device that receives a recommended advertisement based on real-time advertisement analysis, and a method of targeting a recommended advertisement based on real- An implementing computer program may be stored and installed in a built-in memory such as a user's device. Alternatively, an advertisement service device that targets a recommended advertisement based on real-time advertisement analysis according to an embodiment of the present invention, a user device that receives a recommended advertisement based on real-time advertisement analysis, An external memory such as a smart card storing and installing a computer program implementing the method may be mounted on a user device or the like through an interface.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or essential characteristics thereof. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.
It is possible to provide a continuous computing environment to a user by performing synchronization among a plurality of user devices owned by the user of the present invention, and to provide a continuous computing environment to the user even if data stored in the user device is lost, The loss can be prevented.
In addition, a service based on a plurality of user equipments can be provided based on synchronization between user equipments.
By using this method, a user can effectively use a plurality of user apparatuses interlocked with each other.
200: advertisement interest information acquisition unit 210: user device group creation unit
220: recommended advertisement determination unit 230: processor
300: Advertisement interest information receiving unit 310: Priority determining unit
320: User device grouping unit 400: Conditional probability calculation unit
410: recommended advertisement determination unit 600: first user device group
610: first user device 620: second user device
630: third user device 640: fourth user device
650: fifth user device 670: second user device group
Claims (13)
A user device group generation unit for generating a user device group for the first advertisement based on the advertisement interest information; And
A recommended advertisement determination unit that calculates a probability that a first user equipment in the user equipment group clicks on a second advertisement and determines the second advertisement as a recommended advertisement of the second user equipment in the user equipment group when the probability is equal to or greater than a threshold value Includes an advertising service device.
Wherein the advertisement interest information includes at least one of an impression, a click, a click through rate (CTR), and a probability that a user clicks the advertisement.
The user device group generation unit may determine a filtering priority of the advertisement interest information to determine the user device group, filter the plurality of user devices for the first advertisement according to the filtering priority, Is configured to generate at least one user device among the plurality of user devices corresponding to the schedule priority as a user device group for the first advertisement.
Wherein the filtering priority is a sequence of the probability that the user clicks the advertisement, the CTR, the number of clicks, and the number of impressions.
The number of clicks is counted only for a click corresponding to a valid click by distinguishing a valid click and a miss click,
Wherein the valid click is determined based on a time at which the first user device stays on the advertised web site or whether the first user device requests additional information from the advertised web site.
The probability that the first user equipment in the user equipment group clicks the second advertisement is calculated by the following equation
≪ Equation &
P (probability of clicking second advertisement | probability of clicking first advertisement)
= P (probability of clicking second advertisement ∩ probability of clicking first advertisement) / P (probability of clicking first advertisement)
Advertising services equipment.
And reclassifies the user device group based on a click rate of the recommended advertisement to generate a reclassified user device group.
And a communication unit for transmitting the advertisement interest information to the advertisement service apparatus and receiving a recommendation advertisement based on the advertisement interest information.
Wherein the recommendation advertisement is determined by another user device included in the user device group grouped by the user device,
Wherein the app tracking unit re-collects the advertisement interest information for the recommended advertisement,
Wherein the user device group is reclassified based on the advertisement interest information for the recommendation advertisement.
Generating a user device group for a first advertisement based on the advertisement interest information; And
Calculating a probability that a first user device in the user device group will click on a second advertisement and determining the second advertisement as a recommended advertisement in a second user device in the user device group if the probability is greater than or equal to a threshold value Advertising service method.
Wherein generating the user device group for the first advertisement based on the advertisement interest information comprises:
Determining a filtering priority of the advertisement interest information;
Filtering the plurality of user devices for the first advertisement according to the filtering priority; And
And generating at least one user device among the plurality of user devices corresponding to a predetermined priority based on the filtering result as a user device group for the first advertisement.
Receives the advertisement interest information from the user apparatus, groups the user apparatus into a user apparatus group based on the advertisement interest information, calculates a probability that another user apparatus in the user apparatus group clicks a specific advertisement And to determine the specific advertisement as the recommendation advertisement of the user device when the probability is equal to or greater than a threshold value.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020140046855A KR20150121370A (en) | 2014-04-18 | 2014-04-18 | Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor |
| PCT/KR2014/012351 WO2015141932A1 (en) | 2014-03-21 | 2014-12-15 | Method for providing advertisements and apparatus therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020140046855A KR20150121370A (en) | 2014-04-18 | 2014-04-18 | Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20150121370A true KR20150121370A (en) | 2015-10-29 |
Family
ID=54430376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020140046855A KR20150121370A (en) | 2014-03-21 | 2014-04-18 | Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20150121370A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102145170B1 (en) * | 2020-03-04 | 2020-08-18 | 홍자민 | Method and apparatus for recommandating personalized goods based on peer group matching |
| US11086882B2 (en) | 2016-05-12 | 2021-08-10 | Advanced New Technologies Co., Ltd. | Method for determining user behavior preference, and method and device for presenting recommendation information |
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| KR20220150028A (en) | 2021-05-03 | 2022-11-10 | 주식회사 어웨이크스퀘어 | System and method for recommending advertising media |
| CN115907866A (en) * | 2022-11-19 | 2023-04-04 | 深圳有为通讯科技有限公司 | Data analysis push system based on mobile phone screen locking advertisement |
-
2014
- 2014-04-18 KR KR1020140046855A patent/KR20150121370A/en not_active Application Discontinuation
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11086882B2 (en) | 2016-05-12 | 2021-08-10 | Advanced New Technologies Co., Ltd. | Method for determining user behavior preference, and method and device for presenting recommendation information |
| US11281675B2 (en) | 2016-05-12 | 2022-03-22 | Advanced New Technologies Co., Ltd. | Method for determining user behavior preference, and method and device for presenting recommendation information |
| KR102145170B1 (en) * | 2020-03-04 | 2020-08-18 | 홍자민 | Method and apparatus for recommandating personalized goods based on peer group matching |
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| KR20220150028A (en) | 2021-05-03 | 2022-11-10 | 주식회사 어웨이크스퀘어 | System and method for recommending advertising media |
| CN115907866A (en) * | 2022-11-19 | 2023-04-04 | 深圳有为通讯科技有限公司 | Data analysis push system based on mobile phone screen locking advertisement |
| CN115907866B (en) * | 2022-11-19 | 2023-10-13 | 深圳有为通讯科技有限公司 | Data analysis pushing system based on mobile phone screen locking advertisement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105550903B (en) | Target user determination method and device | |
| US20160328748A1 (en) | User similarity groups for on-line marketing | |
| US20140122245A1 (en) | Method for audience profiling and audience analytics | |
| US20160117736A1 (en) | Methods and apparatus for identifying unique users for on-line advertising | |
| US10298705B2 (en) | Recommendation method and device | |
| CN1987916A (en) | Method and device for releasing network advertisements | |
| US20140280549A1 (en) | Method and System for Efficient Matching of User Profiles with Audience Segments | |
| JP5615857B2 (en) | Analysis apparatus, analysis method, and analysis program | |
| KR20150121370A (en) | Advertisement service device targeting recommended advertisement based on real-time advertisement analysis, user equipment receiving recommended advertisement based on real-time advertisement analysis, method for targeting recommended advertisement based on real-time advertisement analysis and computer readable medium having computer program recorded therefor | |
| AU2013222024A1 (en) | Multi-channel marketing attribution analytics | |
| KR20110032878A (en) | Keyword ad. method and system for social networking service | |
| KR101958577B1 (en) | Method for analyzing web page based on web page capture image and system using the same | |
| CN104217353A (en) | Webpage advertisement directional pushing system | |
| KR102328194B1 (en) | Advertisement service device targeting personalized advertisement to user equipment, user equipment receiving personalized advertisement, method for targeting personalized advertisement to user equipment and computer readable medium having computer program recorded therefor | |
| Yuan et al. | Internet advertising: An interplay among advertisers, online publishers, ad exchanges and web users | |
| US20130066708A1 (en) | Online advertising system and a method of operating the same | |
| CN108123972A (en) | The distribution method and device of multimedia file | |
| KR20070094264A (en) | Method for targeting web advertisement clickers based on click pattern by using a collaborative filtering system with neural networks and system thereof | |
| CN105183739A (en) | Image Processing Server | |
| CN100555283C (en) | A kind of directly at the dissemination method and the system of user's relevant information | |
| US20140101064A1 (en) | Systems and Methods for Automated Reprogramming of Displayed Content | |
| KR101613353B1 (en) | Method and apparatus for providing service for analysis of advertisement contents | |
| CN110309406B (en) | Click rate estimation method, device, equipment and storage medium | |
| CN111985955A (en) | Advertisement putting method and system based on reading behavior track | |
| US20140236929A1 (en) | Search method and search system in microblog and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WITN | Withdrawal due to no request for examination |