A new media advertising delivery method and system

Abstract

This invention discloses a new media advertising placement method and system. The method includes: acquiring known media; performing a first tagging on each known media to generate an industry tag for the known media; determining the industry to which a target media belongs and performing a second tagging on the target media to obtain a target media industry tag; filtering out media with the same or similar industries as the target media from the known media based on the target media industry tag; calculating the advertising effect of all advertising industries of the known media with the same or similar industries as the target media, and filtering out advertising industries that meet the conditions based on the advertising effect; and recommending or publishing advertisements based on the filtered advertising industries.

Description

Technical Field

[0001] This invention relates to the field of internet advertising technology, and in particular to a new media advertising delivery method and system. Background Technology

[0002] Currently in the mobile internet advertising industry, when a brand-new media outlet joins an advertising platform, the conversion rate is completely unknown due to the lack of prior data accumulation. Advertising operators often rely on their experience to select and target media with known good performance. Therefore, for a new media outlet to run ads, it must communicate offline with the advertising operations team to configure CPC (cost-per-click) billing (cost per click) and add the new media outlet to the targeted media list. However, ad placement is limited by conversion cost, requiring individual bidding trials on each new media outlet, which is inefficient and risky. Another advertising billing model is OCPC (Optimal Cost-Per-Click). Under OCPC, without data on the media outlet, the model cannot be trained, bids cannot be estimated, and suitable ads cannot be recommended to users on the new media outlet. Furthermore, regardless of the billing model, existing models often lead to low customer retention rates in the initial days of ad campaigns due to poor performance. Summary of the Invention

[0003] One of the objectives of this invention is to provide a new media advertising placement method and system. The method and system utilize similar media to the target media to place advertisements in different industries, analyze the relevant data of different industry advertisements on the similar media, and apply the analysis results to the corresponding similar industry advertisements of the target media for placement. This eliminates the cold start process of the target media as a new media in advertising placement and improves the retention rate of the new media.

[0004] Another objective of this invention is to provide a new media advertising delivery method and system. When the method and system utilize industry advertising delivery performance data of similar media and corresponding similar media of the target media, they directly adjust the price and deliver the advertisement in the OCPC mode based on the performance data when migrating to the target media. Therefore, this invention can avoid the problem that new media cannot be delivered due to the lack of relevant advertising traffic data during the advertising delivery recall process.

[0005] Another objective of this invention is to provide a new media advertising placement method and system. The method and system mark each media outlet that joins the platform according to its own attributes, filter out similar media through the marking, and statistically analyze and sort the conversion rates and conversion bids of different industry advertisements in similar media to obtain the optimal industry advertisement recommendation for advertisers to place their advertisements.

[0006] To achieve at least one of the above-mentioned objectives, the present invention further provides a method for new media advertising delivery, the method comprising:

[0007] Obtain known media, assign a first tag to each known media, and generate an industry tag to which the known media belongs;

[0008] Determine the industry to which the target media belongs, and perform a second tagging on the target media to obtain the target media industry label;

[0009] Based on the target media industry tags, filter out media from known media that have the same or similar industries as the target media;

[0010] Calculate the advertising performance of all advertising industries in known media that are the same as or similar to the target media, and filter out the advertising industries that meet the criteria based on the advertising performance;

[0011] Ad recommendations or publications are made based on the selected advertising industries.

[0012] According to a preferred embodiment of the present invention, the known media are media in the system that have advertising placements. Historical advertising placement effect data of known media that are the same as or similar to the target media are obtained, and the historical advertising placement effect data are sorted. The sorting results are then filtered to obtain historical advertisements that meet the filtering conditions.

[0013] According to another preferred embodiment of the present invention, after obtaining historical advertising performance data of known media that are the same as or similar to the target media, the historical advertisements are tagged a third time to generate an industry tag for each historical advertisement, thereby obtaining the historical advertisements tagged with the industry.

[0014] According to another preferred embodiment of the present invention, the advertising industry corresponding to the historical advertisements that meet the filtering conditions is obtained according to the filtering conditions, and the corresponding industry advertisements that meet the filtering conditions are then tagged a fourth time.

[0015] According to another preferred embodiment of the present invention, the historical advertising performance data includes: the click-through rate and conversion rate of all historical advertisements of known media that are the same as or similar to the current target media; the conversion bid of the historical advertisements; the estimated bid of the corresponding historical advertisements; the sorting of all advertisements from high to low according to the estimated bids; and the fourth tagging of the industry advertisements ranked in the top specified position according to the filtering conditions.

[0016] According to another preferred embodiment of the present invention, when there is an ad slot access in the target media as new media, the advertisements in the same or similar industries as the fourth tag are first retrieved and recalled. The recalled advertisements are then calculated by pre-estimated bid simulation according to the advertising industries corresponding to the known media that are the same or similar to the current target media, and the pre-estimated bids of the advertisements in different industries are ranked from high to low. The advertisement in the industry with the highest ranking is then promoted as the target advertisement.

[0017] According to another preferred embodiment of the present invention, the historical advertising performance data includes: log data of coupons issued and conversions made by the same or similar known media as the target media, and the log data is stored in a designated storage area.

[0018] According to another preferred embodiment of the present invention, the advertising delivery method further includes: configuring an advertising delivery strategy, the strategy including configuring OCPC billing rules, obtaining historical advertising industries corresponding to the same or similar media with the same fourth tag as the target media, and billing the historical advertising industries corresponding to the fourth tag retrieved from the target media access according to the OCPC billing rules.

[0019] To achieve at least one of the above-mentioned objectives, the present invention further provides a new media advertising delivery system, wherein the system executes the above-mentioned new media advertising delivery method.

[0020] The present invention further provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the above-described new media advertising delivery method. Attached Figure Description

[0021] Figure 1 The diagram shown is a flowchart illustrating a new media advertising delivery method according to the present invention.

[0022] Figure 2 The diagram shown is a preferred embodiment of a new media advertising delivery method of the present invention. Detailed Implementation

[0023] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0024] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0025] Please combine Figures 1-2 This invention discloses a method and system for new media advertising placement. The method mainly includes: firstly, collecting relevant data from known media outlets registered in the system; secondly, labeling the industry attributes of the known media with a first annotation to obtain industry tags; thirdly, labeling the new media according to its industry with a second annotation to obtain industry tags; fourthly, searching for identical or similar industry tags from the known media based on the industry tags obtained from the second annotation, using the corresponding known media with identical or similar industry tags as reference media; fifthly, acquiring historical data for the corresponding known media, constructing a calculation model based on the historical data, wherein the historical data includes relevant log data and contains historical advertising performance data; and finally, analyzing the historical advertising performance data to determine the optimal advertising industry, thereby prioritizing advertising promotion and OCPC billing for the optimal advertising industry.

[0026] It is worth mentioning that this invention requires the use of known media that have already published advertisements to carry out advertising promotion on new media, thereby directly skipping the cold start stage of the new media itself, enabling the new media to have faster and more effective advertising promotion revenue on the advertising promotion platform, and increasing the retention rate of the new media on the advertising platform.

[0027] For example, the industry attributes of the known media include, but are not limited to, news media, video media, browser media, and television media. Known media are labeled with corresponding industry tags after a first annotation. For example, Tencent News can be labeled as news media, Youku Video as video media, Baidu Browser as browser media, and various satellite TV channels as television media. Since all the above-mentioned known media have advertising promotion processes in the system of this invention, historical data of all the example media can be obtained, and the industry attributes of the corresponding media's historical advertisements can be tagged a third time. For example, Meituan advertisements can be tagged as e-commerce advertisements, Nongfu Spring advertisements can be tagged as drinking water advertisements or physical industry advertisements, and financial securities-related advertisements can be tagged as financial advertisements. The tagged industry types can be further subdivided according to actual needs, which will not be described in detail in this invention. Relevant log data is obtained from the historical data, and the log data is further analyzed. The log data includes coupon issuance, click-through rate (CRT), conversion rate (CRT), and investment conversion rate (ROI) from the corresponding media's historical data as historical advertising performance data. The historical advertising investment performance data is stored in the HBase storage area. Further, the estimated bid is calculated based on the click-through rate (CTR), conversion rate (CTR), and conversion bid, where the estimated bid is conversion rate * conversion bid. The estimated bids of all ads under the corresponding known media are sorted from highest to lowest. An appropriate range for ad bids is set, such as by setting a filtering procedure to select the top 10 ads with the highest estimated bids as the dataset for fourth tagging. The fourth tagging refers to high-yield historical ads that meet the filtering criteria, and the corresponding industry attributes of the ads are obtained. The industry attributes of the ads are then further sorted according to the estimated bids.

[0028] After completing the above processing of the historical advertising data of known media, the target media as new media is further processed based on the processed historical advertising data. The target media obtains the industry tag to which the new media belongs after the second tagging. Based on the industry tag of the new media, the same or similar known media are obtained. For example, if the newly joined media includes iQiyi, then iQiyi is tagged a second time to obtain the corresponding video industry media tag. Finding the same video industry media tag from the known media can be Tencent Video. When the new media iQiyi is registered on the platform of this invention, multiple ad slots can be configured. The ad slots are preferably the fourth-tagged ad industry in the same video industry media. When a user visits the ad slot corresponding to the new media, the ad visited and the ad industry tagged by the fourth tag are recalled first. For example, in this invention, the user visits the Meituan e-commerce ad, and the Meituan e-commerce ad has been tagged by Tencent Video as the fourth tag of the known media. Therefore, when the user visits the Meituan ad slot under the new media iQiyi, the visited Meituan ad is immediately recalled. After recall, the estimated bid is calculated immediately based on the relevant conversion effect data of the known media. That is, the estimated bid conversion rate (crt) * conversion bid is calculated based on the click-through rate (crt), conversion rate (crt), and conversion bid of the same industry ad (Meituan ad) on Tencent Video media of the same industry as iQiyi video media. The estimated bid for the Meituan ad slot on the new media iQiyi is obtained. Simultaneously, calculate the estimated bids for other accessed and labeled ads of the same type, sort the estimated bids of different advertising industries in new media from high to low according to the estimated bids, and promote the ads of the advertising industry with the highest ranking to users.

[0029] After completing the estimated bid test for new media, we will further conduct bidding for both ads that have not been tagged and those that have been tagged.

[0030] It is worth mentioning that this invention utilizes the historical advertising performance of known media to transfer to new media, thus significantly increasing advertising revenue after new media platforms are established and improving user retention rates.

[0031] This invention uses estimated bids as an example to illustrate advertising effectiveness. In other preferred embodiments of this invention, metrics such as ROI (Return on Investment), ARPU (Average Revenue Per User), and ARPU can be used as reference indicators for the fourth tagging mentioned above. Regarding CPC and OCP (Octoc / Cost Per Click) billing models, this invention provides the following explanation:

[0032] CPC: The system only charges when a user clicks on the ad link; there is no charge for the ad being displayed or viewed. CPC uses a bidding model for display, with the highest bidder getting priority for display. The final cost per click is calculated according to a certain coefficient, with a minimum bid starting at 0.2 yuan, and the actual transaction price is often higher than this price.

[0033] The advertising revenue per thousand impressions (eCPM) = Estimated click-through rate * Target click bid * 1000; Click billing = Next person's eCPM / (Your own estimated click-through rate * 1000) + 0.01.

[0034] OCPC stands for Optimized Cost per Click, which is essentially still based on CPC (cost-per-click). Employing a more accurate and scientific conversion rate prediction mechanism helps advertisers acquire more high-quality traffic while improving conversion rates. The system intelligently and dynamically adjusts bids based on multi-dimensional, real-time feedback, and massive amounts of historical data, taking into account the predicted conversion rate and the competitive environment. This optimizes ad ranking, helping advertisers win the most suitable traffic and reduce conversion costs.

[0035] Click-based billing = (next eCPM + 0.01) / (your estimated click-through rate * 1000).

[0036] In particular, according to embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0037] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0038] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the stated principles, the implementation of the present invention may have any variations or modifications.

Claims

1. A method for placing new media advertisements, characterized in that, The method comprises: acquiring known media, first labeling each known media, and generating industry labels to which the known media belong; judging the industry to which a target media belongs, and second labeling the target media to obtain a target media industry label; screening media with the same or similar industry as the target media from the known media according to the target media industry label; calculating the advertising effect of all advertising industries of the known media with the same or similar industry as the target media, and screening advertising industries that meet the conditions according to the advertising effect; advertising recommendation or publishing according to the screened advertising industries; wherein the known media are media in which advertising is placed in the system, historical advertising placement effect data of the known media with the same or similar industry as the target media is acquired, the historical advertising is sorted according to the historical advertising placement effect data, and the historical advertising that meets the screening condition is obtained by screening the sorting result; the historical advertising placement effect data comprises: the click rate and conversion rate of all historical advertisements of the known media with the same or similar industry as the target media, the conversion bid of the historical advertisement is calculated, the estimated bid of the corresponding historical advertisement is calculated, all advertisements are sorted from high to low according to the estimated bid, and the industry advertisements in the top specified number of ranks are fourth labeled according to the screening condition.

2. The method of claim 1, wherein, After acquiring the historical advertising placement effect data of the known media with the same or similar industry as the target media, the historical advertising is third labeled to generate the industry label to which each historical advertisement belongs, and the historical advertising of the labeled industry is obtained.

3. The method of claim 2, wherein, The advertising industry corresponding to the historical advertising that meets the screening condition is obtained according to the screening condition, and the corresponding industry advertisement that meets the screening condition is fourth labeled.

4. The method of claim 3, wherein, When an advertising position access exists in the target media as a new media, first recall the advertisements with the same or similar industry as the fourth label, simulate the estimated bid calculation of the recalled advertisements according to the corresponding advertising industry of the known media with the same or similar industry as the target media, obtain the estimated bid sorting of different industry advertisements from high to low, and the industry advertisement with the highest sorting is promoted as the target advertisement.

5. The method of claim 1, wherein, The historical advertising placement effect data comprises: log data of the target media with the same or similar known media that has already issued and converted, and the log data is stored in a specified storage area.

6. The method of claim 3, wherein, The advertising placement method further comprises: configuring an advertising placement strategy, the strategy comprises: configuring an OCPC billing rule, acquiring the historical advertising industry of the fourth label of the corresponding media of the target media, and charging the corresponding advertisements of the historical advertising industry that meets the fourth label according to the OCPC billing rule.

7. A new media advertisement delivery system, characterized by, The system executes any one of the new media advertising placement methods in claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the new media advertising placement method in any one of claims 1-6.

Images