KR102631654B1 - Advertisement effect analysis system - Google Patents

Abstract

Disclosed is an advertising effect analysis providing system including an advertising effect analysis device that analyzes the advertising effect of advertising content registered on SNS.

Description

Advertising effect analysis provision system {ADVERTISEMENT EFFECT ANALYSIS SYSTEM}

The present invention relates to a system for providing advertising effect analysis.

The mobile communication market is constantly being asked to produce new services through recombination or integration of existing technologies. Today, due to the development of communication and broadcasting technology, mobile phones and PDAs (Personal Digital Assistants) are being replaced in conventional broadcasting or mobile communication systems. We are currently in the process of providing broadcasting services through mobile terminals (hereinafter referred to as “mobile terminals”).

IT is strengthening its mobile communications business by accommodating these potential and actual market demands, rapidly increasing user demand for multimedia services, operators' strategies to provide new services such as broadcasting services in addition to existing voice services, and consumer demands. (Information Technology) With the interests of companies aligned, the convergence of mobile communication services and IP (Internet Protocol) networks is becoming a major trend in the development of next-generation mobile communication technology.

Among these, the mobile advertising service is a technology that transmits customized advertisements (personal advertisements) based on technologies such as music, graphics, voice, and text to users of mobile devices through mobile devices (mobile phones, PDAs, etc.).

The mainstream of these mobile advertising services is a provider-centered advertising method that inserts advertisements related to a specific service when a terminal user executes the service.

However, this provider-centered advertising method had the problem of delivering one-sided advertising that did not suit the user's tastes or personal interests, making users feel uncomfortable and significantly reducing advertising effectiveness.

Recently, attempts have been made to break away from provider-centered advertising methods and use user-centered advertising. Typically, using the subscriber information held by the mobile communication service provider, scores are assigned to each table to classify the tendencies of the subscribed members and send advertisements appropriate to them.

In other words, it is possible to build an information database about users and implement personalized advertisements tailored to individual characteristics. Since users always carry a mobile terminal with them, advertising content selected by the user can be transmitted to the user at a period determined by the business operator or at the user's request, and advertisements through mobile terminals have the advantage of being always exposed to the user. .

These digital advertising media (e.g. Internet, mobile) store log data in their own format in each service system, and the advertising platform collects log data from each service system using FTP, etc., parses the log data format, and produces the results. It is limited to generating analysis data.

One aspect of the present invention relates to an advertising effect analysis providing system that analyzes and provides advertisement effects for advertisement content registered on SNS.

The technical problem of the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

The advertising effect analysis providing system of the present invention includes an advertising effect analysis device that analyzes the advertising effect of advertising content registered on SNS.

On the other hand, it further includes a SNS server, which is an operation server of the SNS,

The advertising effect analysis device receives usage activity information from the SNS server, including page views indicating the number of times the advertising content has been opened, the number of followers of the SNS account, and the number of interaction activities with respect to the advertising content. collection department; and an advertising effect analysis unit that analyzes the usage activity information to analyze the advertising effect of the advertising content, generates a report including the advertising effect analysis results, and provides the report to advertisers for viewing.

In addition, the advertising effect analysis unit divides and stores the types of advertising content into customer participation-type advertising, homepage-based advertising, product highlighting-type advertising, and live broadcast-type advertising, and calculates the increase/decrease rate of the usage activity information for each type of advertising content. Calculate and generate the report by estimating the performance of the advertising effect according to the increase/decrease rate of the usage activity information for each type of advertising content,

It further includes; an output device connected to the advertising effect analysis device through a network and outputting advertising content provided by the advertising effect analysis device;

The advertising effect analysis unit may further include transmitting advertising content estimated to have the highest advertising effectiveness among the types of advertising content to the output device to be output.

According to one aspect of the present invention described above, advertising effectiveness can be increased by analyzing and providing advertising effectiveness performance for various types of advertising content using SNS.

1 is a conceptual diagram of a system for providing advertising effect analysis according to an embodiment of the present invention.
FIG. 2 is a conceptual diagram of the advertising effect analysis device shown in FIG. 1.
Figure 3 is a conceptual diagram of a system for providing advertising effect analysis according to another embodiment of the present invention.
FIG. 4 is a diagram showing an example of the output device shown in FIG. 3.
Figure 5 is a conceptual diagram of an advertising effect analysis device according to another embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. The present embodiments only serve to ensure that the disclosure of the present invention is complete and that common knowledge in the technical field to which the present invention pertains is not limited. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components, steps and operations.

1 is a conceptual diagram of a system for providing advertising effect analysis according to an embodiment of the present invention.

Referring to FIG. 1, the advertising effect analysis providing system 1 according to an embodiment of the present invention can analyze the advertising effect of advertising content registered on the Internet and provide it to advertisers.

The advertising effect analysis providing system 1 according to an embodiment of the present invention collects user activity information about advertising content from the SNS server 20 and the SNS server 20 where advertising content is registered, and advertises the advertising content. It may include an advertising effect analysis device 10 that analyzes the effect.

Here, the SNS server 20 may be an SNS operating server such as Facebook, Instagram, Kakao Story, Twitter, or YouTube. Advertising content may include posts, videos, live broadcasts, etc. registered on SNS. Usage activity information includes page views, which indicates the number of times a user has opened advertising content, the number of followers on SNS accounts, and interaction activities such as likes, comments, sympathy, sharing, and viewing of advertising content. It may include the number of cases, comment text on advertising content, etc.

The SNS server 20 and the advertising effect analysis device 10 have the same hardware configuration as a typical web server or web application server. However, in terms of software, it includes program modules that are implemented in various languages such as C, C++, Java, PHP, .Net, Python, and Ruby and perform various functions.

The SNS server 20 and the advertising effect analysis device 10 may generally be interconnected through a network such as an open computer network such as the Internet. The network is a transmission path for web pages and may be a closed network such as a LAN (Local Area Network) or WAN (Wide Area Network), but an open network such as the Internet is preferable. The Internet uses the TCP/IP protocol and several services existing at its upper layer, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), and SNMP ( It refers to a worldwide open computer network structure that provides Simple Network Management Protocol (NFS), Network File Service (NFS), and Network Information Service (NIS).

FIG. 2 is a conceptual diagram of the advertising effect analysis device shown in FIG. 1.

Referring to FIG. 2, the advertising effect analysis device 10 may include a usage activity information collection unit 11 and an advertising effect analysis unit 12.

The usage activity information collection unit 11 may collect usage activity information from the SNS server 20. Usage activity information relates to activity information about advertising content registered on SNS, including page views indicating the number of times advertising content has been opened, number of followers of SNS accounts, likes and comments on advertising content, It may include the number of interaction activities such as liking, sharing, and watching, and comment text on advertising content.

The advertising effect analysis unit 12 may analyze the advertising effect of advertising content by analyzing usage activity information, generate a report containing the advertising effect analysis results, and provide it to advertisers for viewing.

For example, the advertising effect analysis unit 12 may store the type of advertising content in advance. Types of advertising content can be divided into customer participation-type advertising, homepage-based advertising, product-emphasizing advertising, and live broadcast-type advertising.

The advertising effect analysis unit 12 can calculate the increase or decrease in page views, increase or decrease in the number of followers, increase or decrease in the number of interaction activities according to the type of advertising content, and calculate the advertising effectiveness performance according to the increase or decrease rate of usage activity information for each type of advertising content. can be estimated.

The advertising effect analysis unit 12 may generate a report containing advertising effectiveness performance for each type of advertising content and provide it to advertisers for viewing.

The advertising effect analysis providing system 1 according to an embodiment of the present invention can increase advertising effectiveness by analyzing and providing advertising effectiveness performance for various types of advertising content using SNS.

Figure 3 is a conceptual diagram of a system for providing advertising effect analysis according to another embodiment of the present invention.

Referring to FIG. 3, the advertising effect analysis providing system 1' according to another embodiment of the present invention includes an output device 30 in addition to the SNS server 20 and the advertising effect analysis device 10 shown in FIG. More may be included.

The output device 30 may be connected to the advertising effect analysis device 10 through a network and may output advertising content provided by the advertising effect analysis device 10.

For example, the output device 30 may receive and output advertising content estimated to have the highest advertising effectiveness among types of advertising content from the advertising effect analysis device 10 .

The output device 30 may be installed in a predetermined location, for example, in a place with a large floating population, and may be installed offline by outputting advertising content estimated to have the highest advertising effectiveness from the advertising effectiveness analysis device 10. Advertising effectiveness can be increased even in space.

FIG. 4 is a diagram showing an example of the output device shown in FIG. 3.

Referring to FIG. 4, the output device 30 can be applied as a typical kiosk device including a display unit 31 that outputs advertising content.

The output device 30 may further include an injection unit installed on the lower frame 30a. The lower frame 30a may be formed in the shape of a plate with a predetermined thickness.

The injection unit may include an injection groove 321 and an injection nozzle 322.

A plurality of injection grooves 321 may be formed at equal intervals along the outer peripheral surface of the lower frame 30a. The injection nozzle 322 may be installed in the injection groove 321, and is connected to the air injection module built into the output device 30 to spray air 323 to the outside of the lower frame 30a according to the operation of the air injection module. can be sprayed.

The spray unit can remove foreign substances by spraying high-pressure air 323 to the outside of the output device 30 installed in a place with a large floating population.

Figure 5 is a conceptual diagram of an advertising effect analysis device according to another embodiment of the present invention.

Referring to FIG. 5 , the advertisement effect analysis device 10 may include a usage activity information collection unit 11, an advertisement effect analysis unit 12, and an advertisement content analysis unit 13.

The usage activity information collection unit 11 may collect usage activity information from the SNS server 20. Usage activity information relates to activity information about advertising content registered on SNS, including page views indicating the number of times advertising content has been opened, number of followers of SNS accounts, likes and comments on advertising content, It may include the number of interaction activities such as liking, sharing, and watching, and comment text on advertising content.

The advertising effect analysis unit 12 may analyze the advertising effect of advertising content by analyzing usage activity information, generate a report containing the advertising effect analysis results, and provide it to advertisers for viewing.

For example, the advertising effect analysis unit 12 may store the type of advertising content in advance. Types of advertising content can be divided into customer participation-type advertising, homepage-based advertising, product-emphasizing advertising, and live broadcast-type advertising.

The advertising effect analysis unit 12 can calculate the increase or decrease in page views, increase or decrease in the number of followers, increase or decrease in the number of interaction activities according to the type of advertising content, and calculate the advertising effectiveness performance according to the increase or decrease rate of usage activity information for each type of advertising content. can be estimated.

The advertising effect analysis unit 12 may generate a report containing advertising effectiveness performance for each type of advertising content and provide it to advertisers for viewing.

The advertising effectiveness analysis unit 12 may calculate an advertising effectiveness score and provide a report containing the advertising effectiveness score so that advertisers can view it.

For example, the advertising effect analysis unit 12 may calculate the advertising effectiveness score based on Equation 1 below.

[Equation 1]

In Equation 1, p is the period during which advertising content was launched on the SNS account, A and B are arbitrary constants, n _f1 is the number of followers before launching advertising content, n _f2 is the number of followers after launching advertising content, and n _k is The number of interaction activities after launching the advertising content, n _p means page views during the advertising content launching period.

The advertising effect analysis unit 12 may include an artificial neural network.

An artificial neural network may refer to hardware, software, or a combination thereof to provide a generalized output for input.

For example, an artificial neural network is an application for simulating a convolutional neural network (CNN), a Markov chain, or a binarized neural network (BNN), and an application for executing the application. It can operate based on the processor.

A neural network learning device is a device that can perform machine learning through training, and may include a device that learns using a model composed of an artificial neural network. For example, a neural network device may be configured to input, output, build a database, and store information used for data mining, data analysis, and machine learning algorithms (e.g., deep learning algorithms).

The neural network device can transmit and receive data with an external electronic device (not shown) through a communication unit (not shown), and can derive a result by analyzing or learning data received from the external electronic device. A neural network device can process the calculations of external electronic devices by distributing them.

Neural network devices can be implemented as servers. Additionally, a plurality of neural network devices can be configured to form a neural network device set. Each neural network device can process operations by distributing them, and derive results through data analysis and learning based on distributedly processed data. The neural network device can transmit the results obtained using a machine learning algorithm, etc. to an external electronic device or another neural network device.

According to various embodiments, a neural network training device may include an input unit, a processor, a memory, and a learning processor.

According to various embodiments, the input unit may acquire input data to derive an output value through artificial neural network model learning. The input unit may obtain unprocessed input data. A processor or learning processor can preprocess raw input data to generate training data that can be input to artificial neural network model learning. The preprocessing may be extracting feature points from input data. As described above, the input unit may receive data through a communication unit (not shown) to obtain input data or preprocess the data.

According to various embodiments, the processor may collect usage history information from a neural network learning device and store it in memory. The processor can determine the best combination to execute a specific function through stored usage history information and predictive modeling. The processor may receive image information, audio information, data, or user input information from the input unit.

According to various embodiments, the processor may collect information in real time, process or classify the information, and store the processed information in memory, a database of the memory, or a learning processor.

According to various embodiments, when the operation of the neural network learning device is determined based on data analysis and machine learning algorithms, the processor may control components of the neural network learning device to execute the determined operation.

Additionally, the processor may control the neural network learning device according to the control command to perform the determined operation.

When a specific operation is performed, the processor may analyze history information indicating the execution of the specific operation through data analysis and machine learning algorithms and techniques, and update previously learned information based on the analyzed information. The processor, together with the learning processor, can improve the accuracy of data analysis and machine learning algorithms and performance based on updated information.

According to various embodiments, the memory may store input data obtained from the input unit, learned data, or learning history. The memory can store artificial neural network models.

According to various embodiments, the artificial neural network model may be stored in a space allocated to memory. The space allocated to the memory stores an artificial neural network model that is being trained or has been learned through a learning processor, and when the artificial neural network model is updated through learning, the updated artificial neural network model can be stored. The space allocated to the memory can be used to store the learned model by dividing it into a plurality of versions depending on the learning time or learning progress.

According to various embodiments, the memory may include a database capable of storing and classifying input data obtained from an input unit and learned data.

According to various embodiments, the learning processor learns an artificial neural network model by directly acquiring preprocessed input data obtained by the processor through an input unit, or acquires preprocessed input data stored in a database of the memory to model an artificial neural network model. You can learn. For example, a learning processor can acquire optimized artificial neural network model parameters by repeatedly training an artificial neural network model using various learning techniques.

According to various embodiments, the learned model may update the artificial neural network model in the database. The learning processor may be integrated into a neural network training device or implemented in memory. Specifically, a learning processor may be implemented using memory.

According to various embodiments, a learning processor generally processes data to identify, index, categorize, manipulate, store, retrieve, and output data for use in supervised or unsupervised learning, data mining, predictive analytics, or other devices. It can be configured to store in one or more databases. Here, the database may be implemented using memory, memory maintained in a cloud computing environment, or other remote memory locations accessible by the terminal through a communication method such as a network. Information stored in the learning processor may be stored in a variety of different types of memory. It may be utilized by the processor using any of data analysis algorithms and machine learning algorithms. Examples of such algorithms include k-nearest neighbor systems, fuzzy logic (e.g. possibility theory), neural networks, Boltzmann machines, vector quantization, pulsed neural networks, support vector machines, maximum margin classifier, hill climbing, induction. Logical systems Bayesian networks, Ferritnets (e.g. finite state machines, Millie machines, Moore finite state machines), classifier trees (e.g. perceptron trees, support vector trees, Markov trees, decision tree forests, random forests), reading models and systems, including artificial fusion, sensor fusion, image fusion, reinforcement learning, augmented reality, pattern recognition, automated planning, etc.

The advertising effectiveness analysis unit 12 may input the advertising effectiveness score into the artificial neural network and calculate the advertising cost according to the advertising effectiveness score. The artificial neural network can calculate and output the appropriate advertising cost according to the advertising effectiveness score.

The advertising content analysis unit 13 can calculate the advertising content launch period according to the advertising effectiveness score. The advertising content analysis unit 13 may calculate the advertising content start period according to the advertising effectiveness score and provide the advertising content for the advertiser to view. Advertisers can refer to this and set the advertisement content launch period in the future.

For example, the advertising content analysis unit 13 can calculate the advertising content start period according to Equation 2 below.

[Equation 2]

In Equation 2, manage is the average operating period of multiple SNSs that launched advertising content, score _ad is the total sum of advertising effect scores calculated on multiple SNSs that launched specific advertising content, and score _in is the average operating period of multiple SNS that launched specific advertising content. The advertising effectiveness score calculated on a specific SNS, score _av , means the average of the advertising effectiveness scores calculated on multiple SNSs that launched specific advertising content.

The advertising content analysis unit 13 can increase advertising effectiveness by calculating an appropriate advertising content start period according to the advertising effectiveness score and presenting it to the advertiser.

Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention can be implemented in other specific forms without changing the technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

1: Advertising effect analysis provision system
10: Advertising effect analysis device
20: SNS server

Claims (2)

It includes an advertising effect analysis device that analyzes the advertising effect of advertising content registered on SNS,
It further includes a SNS server, which is an operation server of the SNS,
The advertising effect analysis device,
a usage activity information collection unit that receives usage activity information from the SNS server, including page views indicating the number of times the advertising content has been opened, the number of followers of the SNS account, and the number of interaction activities with respect to the advertising content; and
An advertising effect analysis unit that analyzes the usage activity information to analyze the advertising effect of the advertising content, generates a report containing the advertising effect analysis results, and provides the report for advertisers to view,
The advertising effect analysis department,
The types of advertising content are divided and stored into customer participation-type advertising, homepage-type advertising, product highlighting-type advertising, and live broadcast-type advertising, the increase/decrease rate of the usage activity information is calculated for each type of advertising content, and the advertising content Generate the above report by estimating the performance of advertising effectiveness according to the increase/decrease rate of the above usage activity information by type,
It further includes; an output device connected to the advertising effect analysis device through a network and outputting advertising content provided by the advertising effect analysis device;
The advertising effect analysis department,
It further includes transmitting advertising content estimated to have the highest advertising effectiveness among the types of advertising content to the output device to be output,
The advertising effect analysis department,
Advertising effectiveness score using the period during which advertising content was launched on the SNS account, the number of followers before launching advertising content, the number of followers after launching advertising content, the number of interaction activities after launching advertising content, and page views during the period of launching advertising content. It further includes calculating,
The advertising effect analysis device,
It further includes an advertising content analysis unit that calculates the advertising content launch period according to the advertising effectiveness score and provides it for advertisers to view,
The advertising content analysis unit,
The average operation period of multiple SNSs that launched advertising content, the total sum of advertising effect scores calculated for multiple SNS accounts that launched specific advertising content, and the advertising effect score calculated for a specific SNS account that launched specific advertising content and an advertising effect analysis providing system that calculates the advertising content launch period using the average of advertising effect scores calculated for a plurality of SNS accounts that launched specific advertising content.
delete