KR-102962572-B1 - SYSTEM FOR AUTOMATICALLY OPTIMIZING PAID ADVERTISING CAMPAIGNS

Abstract

The present invention relates to an automatic optimization system for paid advertising campaigns. The objective of the invention is to maximize the effectiveness of keyword advertising by increasing the achievement rate of advertising goals through the use of an artificial intelligence algorithm to discover and propose various keywords based on keyword advertising setting information provided by an advertiser, to derive conditions optimized for advertising bidding by considering the conversion cost and click-through rate of the proposed keywords, to automatically bid on and execute keyword advertising, to monitor and provide the results of advertising execution, and to update the algorithm by retraining the advertising execution results as new training data for the artificial intelligence algorithm. For example, an automatic optimization system for paid advertising campaigns is disclosed, comprising: an advertiser terminal that receives keyword advertising setting information for each paid advertising channel from an advertiser; an artificial intelligence server that, based on a pre-established artificial intelligence algorithm, generates recommended advertising keywords necessary for advertising execution according to the keyword advertising setting information and derives optimal advertising bidding conditions for each paid advertising channel for the generated recommended advertising keywords; an advertising setting server that performs information settings for keyword advertising bidding for each paid advertising channel according to the recommended advertising keywords and the optimal advertising bidding conditions; and an advertising execution monitoring server that monitors keyword advertising execution results for each paid advertising channel.

Inventors

• 박무진
• 박창훈
• 박진아

Assignees

• 주식회사 쇼엠

Dates

Publication Date

20260508

Application Date

20240821

Claims (6)

1. Advertiser terminal receiving keyword advertising setting information for each paid advertising channel from the advertiser; An AI server that, based on a pre-established AI algorithm, generates recommended advertising keywords necessary for advertising execution according to the keyword advertising setting information, and derives optimal advertising bidding conditions for each paid advertising channel for the generated recommended advertising keywords; An ad setting server that performs information settings for keyword ad bidding for each paid ad channel according to the above recommended ad keywords and above optimal ad bidding conditions; and It includes an ad execution monitoring server that monitors keyword ad execution results by paid ad channel, and The above advertiser terminal is, A keyword ad setting information input unit that receives keyword ad setting information including paid ad channel information, ad type information, ad creative information, ad representative keyword, ad target exposure ranking, ad target conversion cost, ad target click conversion rate, and ad execution budget; and It includes a keyword advertising execution result display unit that receives and displays keyword advertising execution results, including representative advertising keywords, related keywords, autocomplete keywords, advertising target exposure rankings, advertising conversion costs, and advertising conversion rates, for each paid advertising channel from the above-mentioned advertising execution monitoring server. The above artificial intelligence server is, A recommended ad keyword generation unit that generates related keywords and autocomplete keywords for the above representative ad keyword, respectively, through a pre-established artificial intelligence-based keyword generation algorithm based on real-time keyword interest and competition intensity for each paid ad channel; An ad optimal bidding time prediction unit that predicts the optimal keyword ad bidding time, which is the time slot optimized for ad bidding for the above representative ad keyword, the above related keyword, and the above autocomplete keyword, using an AI-based ad execution optimization algorithm that has pre-learned the ad conversion cost and click conversion rate for keywords by time slot; A data collection and classification unit that collects data posted on at least one online platform among SNS, online communities, and portal sites, and classifies the collected data according to predefined keyword categories; A neologism detection unit that recognizes at least one of the body content, comments, hashtags, and text within a video of the data collected and classified by the above data collection and classification unit, detects a neologism among the keywords included in the recognized content, analyzes the meaning of the detected neologism, checks whether the meaning of the neologism corresponds to a predefined slang term, and if it corresponds to a slang term, deletes the neologism and stores the neologism that does not correspond to a slang term and the meaning of the corresponding neologism in a neologism database; A neologism generation pattern derivation unit that derives a neologism generation pattern based on the neologism and the meaning of the neologism stored in the neologism detection unit; and A paid advertising campaign automatic optimization system characterized by including a neologism keyword generation unit that trains an artificial intelligence-based neologism generation algorithm according to a neologism, the meaning of a neologism, and a neologism generation pattern, and generates a neologism keyword for at least one of the above representative advertising keyword, the above related keyword, and the above autocomplete keyword based on the trained neologism generation algorithm and provides it to the above recommended advertising keyword generation unit.
2. delete
3. delete
4. In Article 1, The above artificial intelligence server is, A paid advertising campaign automatic optimization system characterized by further including an algorithm update unit that receives keyword advertising execution results from the above-mentioned advertising execution monitoring server, checks whether the ad exposure ranking and ad conversion cost included in the received keyword advertising execution results have reached the above-mentioned ad target exposure ranking and the ad conversion cost at the predicted optimal time for keyword advertising bidding, and retrains the advertising execution optimization algorithm by reflecting the reached status and the corresponding keyword advertising execution results.
5. In Article 1, The above-mentioned ad setting server is, A paid advertising campaign automatic optimization system characterized by setting up the type, bidding, keywords, and creatives of keyword advertising based on the paid advertising channel information, the advertising type information, the advertising creative information, the representative advertising keyword, the related keywords, the autocomplete keywords, the advertising target conversion price, the advertising target click conversion rate, and the advertising execution budget according to the above advertising target exposure ranking, the above advertising execution budget, and the above keyword advertising bidding optimal time slot, and conducting bidding according to the setting information.
6. In Article 1, The above-mentioned ad execution monitoring server is, A paid advertising campaign automatic optimization system characterized by monitoring the ad conversion cost, ad conversion rate, and ad exposure ranking for each paid advertising channel, and providing the monitoring results to the advertiser's terminal as keyword advertising execution results, along with the aforementioned representative ad keyword, the aforementioned related keyword, the aforementioned autocomplete keyword, and the aforementioned ad target exposure ranking.

Description

SYSTEM FOR AUTOMATICALLY OPTIMIZING PAID ADVERTISING CAMPAIGNS An embodiment of the present invention relates to an automatic optimization system for paid advertising campaigns. Keyword advertising refers to an advertising technique that exposes an advertiser's website to people who have searched for specific keywords on internet search sites, and is also known as search advertising. Unlike TV, radio, or banner ads, where sellers seek out customers, this type of keyword advertising can be considered much more proactive and highly effective than previous forms of advertising in that it exposes ads to customers who come to them. Furthermore, since the search behavior of surfers itself is already subject to highly sophisticated targeting in keyword advertising, the efficiency in leading to conversions is relatively higher compared to other advertisements based on customer circumstances, demographic targeting, or visit history. While keyword advertising has a low barrier to entry because it is possible to advertise with just one keyword, places where keyword advertising can be executed efficiently are limited to famous portal sites that hold the majority of search market share, and popular keywords that guarantee a large number of impressions are mostly subject to competition among numerous advertisers, which can lead to an increase in the keyword purchase price (cost per click) and hinder profits. Accordingly, a proposed solution is detailed keywords, which tend to exhibit higher click-through and purchase rates than representative keywords, and have lower unit purchase costs due to the scarcity of competitors. However, detailed keywords have the disadvantage of requiring significant effort to discover and a lengthy verification period to determine their effectiveness. Furthermore, since the revenue increase generated through detailed keywords is limited, they cannot serve as an ultimate solution. Keyword research must be conducted beforehand to discover specific keywords. Keyword research refers to the process of finding related keywords associated with a company and products, and keyword research tools such as Google Keyword Planner and Twinword Ideas can be utilized. However, keyword research has the disadvantage of requiring a relatively large amount of time and cost compared to its effectiveness. Furthermore, even if related keywords are discovered through research, it is difficult to achieve optimized bidding for each keyword because real-time interest and competition intensity vary across paid advertising channels (Naver, Google, Daum, Facebook, Instagram, etc.). Additionally, there is a problem in that there is a lack of a solution capable of accurately verifying the results of ad execution—specifically, whether advertising goals (target ranking, cost per conversion, click-through rate) have been reached for each keyword. FIG. 1 is a schematic diagram showing the overall configuration of a paid advertising campaign automatic optimization system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the configuration of an advertiser terminal according to an embodiment of the present invention. FIGS. 3 to 6 are drawings illustrating exemplary information input through a keyword advertising setting information input unit according to an embodiment of the present invention. FIG. 7 is a block diagram showing the configuration of an artificial intelligence server according to an embodiment of the present invention. FIG. 8 is a diagram illustrating the overall operation of an algorithm configured in an artificial intelligence server according to an embodiment of the present invention. The terms used in this specification will be briefly explained, and the invention will be described in detail. The terms used in this invention have been selected based on currently widely used general terms, taking into account their functions within the invention; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this invention should be defined not merely by their names, but based on their meanings and the overall content of the invention. When a part of a specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part" or "module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software. Embodiments of the present invention are described below with reference to the attached drawings so that t