JP2022166200A - Model generation system, model generation module and model generation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a system, a module and a method for generating a model as an index for appropriately and objectively evaluating effects of digital advertisements.

SOLUTION: In a model generation system 10, a data processing server storage comprises: a first database of an advertisement distribution server that stores advertisement distribution result data on a distribution results of digital advertisements for advertising advertisement objects; a second database of an aggregation server that stores questionnaire survey data for grasping attitude change contribution, which is a factor in a change in customer attitude, regarding the advertisement objects advertised by the digital advertisements on the advertisement distribution result data; and a correlation model generation module that generates a correlation model for correlating prospective customer number data on the number of customers who have an intention to purchase the advertisement objects calculated based on the data stored in the second database with the data stored in the first database, and calculating an amount of fluctuation in the prospective customer number data, which fluctuates based on the fluctuation of the advertisement distribution result data.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2023,JPO&INPIT

Description

The present invention relates to a model generation system, a model generation module and a model generation method, and more particularly to a model generation system, a model generation module and a model generation method for generating a correlation model for evaluating the effectiveness of digital advertisements.

In general, advertisements for goods, such as goods and services, serve as one of the major opportunities for customers who purchase the advertised object, which is a product, to come into contact with the advertised object. Since the marketing of goods can be affected, there are various methods of evaluating the effectiveness of advertising.

For example, there is a method of evaluating the effect of television commercials using television broadcasting as an advertising medium using GRP (Gross Rating Point), which is the total household audience rating of television commercials broadcast during a specific period.

On the other hand, in Patent Document 1, based on a first aggregated value obtained by aggregating questionnaire information on the purchasing consciousness of those who viewed the advertisement and a second aggregated value obtained by aggregating the questionnaire information on the viewers' evaluation of the expression elements of the advertisement. An advertisement rating system is disclosed that evaluates advertisements using a method.

Japanese Unexamined Patent Application Publication No. 2009-37484

By the way, with the development of digital technology and the Internet environment, so-called digital advertisements, in which various contents (for example, websites) on the Internet network are distributed as advertising media, are becoming mainstream for advertisements of advertisement targets.

However, an appropriate method for evaluating the effectiveness of such digital advertising has not yet been established, and the current situation is that it is not possible to sufficiently carry out marketing of products and the like based on the effectiveness of digital advertising.

Furthermore, from the viewpoint of precisely executing marketing of advertising objects based on the effects of digital advertising, it is preferable that the effects of digital advertising be objectively evaluated.

The present invention has been made in view of the above circumstances, and a model generation system, a model generation module, and a model generation method for generating a model that serves as an index for appropriately and objectively evaluating the effectiveness of digital advertising. The task is to provide

A model generation system according to the present invention for achieving the above object comprises: a first database storing advertisement delivery result data relating to the delivery result of a digital advertisement advertising an advertisement object; and an advertisement delivery stored in the first database. A second database storing questionnaire survey data for grasping a contribution to attitude change, which is a factor in changing a customer's attitude, regarding an advertisement object advertised in a digital advertisement relating to result data; and a questionnaire stored in the second database. Prospective customer number data relating to the number of customers who have an intention to purchase the advertised object calculated based on survey data is correlated with advertisement distribution result data stored in the first database, and based on fluctuations in the advertisement distribution result data and a model generation module for generating a correlation model for calculating the amount of variation in the data on the number of prospective customers that fluctuates.

According to this, by a correlation model generated by correlating the advertisement distribution result data and the prospective customer number data calculated based on the questionnaire survey data, the prospective customers who fluctuate based on the fluctuation of the advertisement distribution result data Since it is possible to calculate the amount of change in the number data, it is possible to quantitatively grasp the number of prospective customers of the advertising object that changes due to digital advertising.

Therefore, it is possible to generate a correlation model that can appropriately and objectively evaluate the effects of digital advertising based on the amount of change in the number of prospective customers that is quantitatively grasped.

This model generation system is provided with a variable information extraction module for extracting variable information from advertisement distribution result data to be correlated with prospective customer number data in the model generation module, and the variable information is distributed via the Internet network. It has information on the number of views of the content in which the advertising object is posted through the digital advertisement.

Furthermore, the model generation system may comprise a prospective customer number data calculation module for calculating prospective customer number data, or a trained model generation module for learning questionnaire survey data and generating a trained model. can be anything.

A model generation module according to the present invention for achieving the above object includes advertisement distribution result data regarding the distribution results of digital advertisements that advertise advertisement objects, and changes in customer attitudes regarding advertisement objects advertised by digital advertisements. By correlating the number of prospective customers data on the number of customers who have the intention to purchase the advertising object calculated based on questionnaire survey data that grasps the contribution to attitude change, which is the factor of It generates a correlation model for calculating the amount of fluctuation in the data on the number of prospective customers that fluctuates.

A model generation method according to the present invention for achieving the above object includes advertisement delivery result data relating to the delivery results of digital advertisements that advertise advertisement objects, and changes in customer attitudes regarding advertisement objects advertised by digital advertisements. By correlating the number of prospective customers data on the number of customers who have the intention to purchase the advertising object calculated based on questionnaire survey data that grasps the contribution to attitude change, which is the factor of It generates a correlation model for calculating the amount of fluctuation in the data on the number of prospective customers that fluctuates.

According to the present invention, it is possible to generate a correlation model that can appropriately and objectively evaluate the effectiveness of digital advertisements.

1 is a block diagram illustrating the outline of the configuration of a model generation system according to an embodiment of the present invention; FIG. Similarly, it is a block diagram for explaining an outline of a hardware configuration of a computer in which an advertisement distribution server, an aggregation server, and a data processing server of the model generation system according to the present embodiment are mounted. Similarly, it is a block diagram for explaining the outline of the configuration of the storage of the advertisement distribution server of the model generation system according to the present embodiment. Similarly, it is a block diagram for explaining the outline of the configuration of the advertisement distribution result data processed by the model generation system according to the present embodiment. Similarly, it is a block diagram for explaining the outline of the configuration of the storage of the aggregation server of the model generation system according to the present embodiment. Similarly, it is a figure explaining the outline of the structure of the questionnaire processed by the model generation system which concerns on this Embodiment. Similarly, it is a block diagram for explaining the outline of the configuration of the storage of the data processing server of the model generation system according to the present embodiment. Similarly, FIG. 10 is a diagram for explaining the outline of the processing of the data processing program of the data processing server of the model generation system according to the present embodiment. Similarly, FIG. 10 is a diagram for explaining the outline of the processing of the data processing program of the data processing server of the model generation system according to the present embodiment.

Next, a model generation system according to an embodiment of the present invention will be described with reference to FIGS. 1 to 9. FIG.

FIG. 1 is a block diagram for explaining the outline of the configuration of the model generating system according to this embodiment. As illustrated, the model generation system 10 includes an advertisement delivery server 20, an aggregation server 30, and a data processing server 40. The advertisement delivery server 20 and data processing server 40, and the aggregation server 30 and data processing server 40 are connected to the Internet. They are connected via a network such as a network.

In the present embodiment, the advertisement distribution server 20 is deployed in an EC site operator 1 that operates an EC site, which is a website where electronic commerce is conducted, and is used by customers who purchase products such as products and services. A digital advertisement, which will be described later, is distributed to the terminal T of the user U who can be the user U, and advertisement distribution result data, which will be described later, regarding the result of distributing the digital advertisement is acquired.

Aggregation server 30, in the present embodiment, is deployed in survey business operator 2 that engages in marketing-related questionnaire survey work, distributes questionnaires, which will be described later, to terminals T of users U, and aggregates the questionnaires answered by users U. Questionnaire survey data, which will be described later, is generated.

In this embodiment, the data processing server 40 is deployed in the operator 3 that conducts marketing operations using the correlation model generated by the model generation system 10 and described later.

The advertisement distribution server 20, totalization server 30, and data processing server 40 are implemented by a computer having substantially the same hardware configuration, such as a desktop or notebook computer, in this embodiment.

FIG. 2 is a block diagram outlining the hardware configuration of a computer in which the advertisement delivery server 20, totalization server 30 and data processing server 40 are implemented.

As shown, the computer has a processor 101 , a memory 102 , a storage 103 , a transmitter/receiver 104 and an input/output unit 105 as main components, which are electrically connected to each other via a bus 106 .

The processor 101 is an arithmetic unit that controls the operation of the computer, controls transmission and reception of data between elements, and performs processes necessary for executing application programs.

The processor 101 is, for example, a CPU (Central Processing Unit) in this embodiment, and executes an application program stored in a storage 103 and developed in a memory 102 to perform various processes.

The memory 102 includes a main storage device composed of a volatile memory device such as a DRAM (Dynamic Random Access Memory), and an auxiliary storage device composed of a non-volatile memory device such as a flash memory or a HDD (Hard Disc Drive). .

This memory 102 is used as a work area for the processor 101, and stores a BIOS (Basic Input/Output System) executed when the computer is started, various setting information, and the like.

The storage 103 stores application programs, data used for various processes, and the like.

The transmission/reception unit 104 connects the computer to the network. The transmitting/receiving unit 104 may include a short-range communication interface such as Bluetooth (registered trademark) or BLE (Bluetooth Low Energy).

Information input devices such as a keyboard and a mouse and output devices such as a display are connected to the input/output unit 105 as required. In this embodiment, a keyboard, mouse and display are connected.

The bus 106 transmits, for example, address signals, data signals and various control signals among the connected processor 101 , memory 102 , storage 103 , transmission/reception unit 104 and input/output unit 105 .

FIG. 3 is a block diagram outlining the configuration of the storage 103 of the advertisement distribution server 20. As shown in FIG. As illustrated, the storage 103 includes a first database 21 realized by a storage area of the storage 103 and an advertisement distribution program 22. FIG.

The first database 21 stores digital advertisements D1 and advertisement distribution result data D2 in this embodiment.

In the present embodiment, the digital advertisement D1 advertises an advertisement object such as a product, and is distributed using, for example, various contents on the Internet such as websites as advertisement media.

FIG. 4 is a block diagram outlining the configuration of the advertisement distribution result data D2. As illustrated, the advertisement distribution result data D2 includes various numerical information regarding the result of distributing the digital advertisement, such as the number of advertisement display times d1, the number of advertisement page accesses d2, and the advertisement page induction rate d3.

The advertisement display count d1 is numerical information about the number of times the digital advertisement D1 is displayed on the terminal T by the user U, and the advertisement page access count d2 is the number of times the advertisement object is posted via the digital advertisement D1 on a so-called view-through basis. The advertisement page induction rate d3 is numerical information calculated based on the advertisement page access count d2.

Even if the user U accesses the same digital advertisement D1 multiple times using a terminal (computer environment) different from the terminal T, these numerical information are acquired as accesses by the same user U.

The advertisement distribution program shown in FIG. 3 distributes the digital advertisement D1 stored in the first database 21 to the terminal T of the user U, and distributes the digital advertisement D1 based on access to the digital advertisement D1 via the terminal T. It is a program for acquiring advertisement distribution result data D2 related to the result of the advertisement distribution and storing it in the first database 21. FIG.

FIG. 5 is a block diagram illustrating the outline of the configuration of the storage 103 of the aggregation server 30. As shown in FIG. As illustrated, the storage 103 comprises a second database 31 implemented by a storage area of the storage 103 and a questionnaire tallying program 32 .

The second database 31 stores questionnaires D3 and questionnaire survey data D4 in this embodiment.

Questionnaire D3 is composed of questions about factors (attitude change contribution) of user U's attitude change toward the advertisement target when the user U changes from a potential customer to a prospective customer regarding the advertisement target.

Specifically, for example, as shown in FIG. 6, which outlines the configuration of the questionnaire D3, "Did you know the product?", "Where (what media) did you know about it?" or "What media did you purchase?" Configured.

In the present embodiment, a “potential customer” is defined as “a customer who has the possibility of purchasing an advertising object but does not know (not recognize) the advertising object, or who knows (is not aware of) the advertising object. It refers to a user U who has no intention of purchasing a product that has been purchased.

On the other hand, in the present embodiment, a "potential customer" refers to a user U who "knows (recognizes) and understands the advertised object and has an intention to purchase it."

Questionnaire survey data D4 shown in FIG. 5 is configured by aggregating questionnaires D3 answered by user U, and in the present embodiment, user U's attitude change contribution is grasped.

The questionnaire tallying program 32 distributes the questionnaire D3 stored in the second database 31 to the terminal T of the user U, tallies the responses to the questionnaire D3 via the terminal T, generates the questionnaire survey data D4, and collects the second data. It is a program stored in the database 31 .

FIG. 7 is a block diagram outlining the configuration of the storage 103 of the data processing server 40. As shown in FIG. As illustrated, the storage 103 comprises a third database 41 realized by a storage area of the storage 103 and a data processing program 42 .

In the third database 41, in this embodiment, prospective customer number data D5 and learned models D6 generated by a data processing program 42, which will be described later, are stored.

In this embodiment, the data processing program 42 includes an input module 42a, a variable information extraction module 42b, a prospective customer number data calculation module 42c, a correlation model generation module 42d and a learned model generation module 42e.

The input module 42a is a module to which the advertisement distribution result data D2 is input from the advertisement distribution server 20 and the questionnaire survey data D4 is input from the aggregation server 30. FIG.

The variable information extraction module 42b converts numerical information such as the advertisement display count d1, the advertisement page access count d2, and the advertisement page induction rate d3 included in the advertisement distribution result data D2 into the prospective customer number data D5 in the correlation model generation module 42d, which will be described later. It is a module that extracts as correlated variable information.

In the present embodiment, the prospective customer number data calculation module 42c, based on the questionnaire survey data D4, is a prospective customer who "knows (recognizes) and understands the advertised object and has an intention to purchase it." This is a module for calculating prospective customer number data D5 related to.

For example, as shown in FIG. 8 for explaining the outline of the processing of the prospective customer number data calculation module 42c, a coordinate plane in which the vertical axis indicates the degree of recognition of the advertising target and the horizontal axis indicates the purchase amount of the advertising target. , an area surrounded by the degree of recognition and the purchase amount corresponding to the coordinate position of the advertising object is calculated as the prospective customer number data D5.

In the present embodiment, for example, the advertisement target is a shampoo product a, and the area x surrounded by the degree of recognition and the purchase amount corresponding to the coordinate position of the product a is calculated as the prospective customer number data D5 of the product a. be done.

It should be noted that the "number of prospective customers" can be grasped as the "market size" of the advertising object.

FIG. 9 is a diagram for explaining the outline of the processing of the correlation model generation module 42d. As illustrated, the correlation model generation module 42d correlates the advertisement distribution result data D2 input from the advertisement distribution server 20 and the prospective customer number data D5 calculated by the prospective customer number data calculation module 42c, and It is a module that generates a model D7.

In the present embodiment, the variable information extraction module 42b extracts the advertisement page induction rate d3 as variable information from the advertisement distribution result data D2.

The generated correlation model D7 is a model for calculating the fluctuation amount of the prospective customer number data D5 that fluctuates based on the fluctuation of the advertisement distribution result data D2. As a result, the number of prospective customers (market size) of the advertised object, which fluctuates according to the digital advertisement D1, can be quantitatively grasped.

In this embodiment, the trained model generation module 42e shown in FIG. 7 is a module that generates a trained model D6 by performing machine learning on the questionnaire survey data D4 input from the collection server 30. FIG.

Various algorithms such as neural networks, random forests, and SVMs (support vector machines) are appropriately used as techniques for machine learning.

The generated trained model D6 is a model for calculating the prospective customer number data D5. As a result, the prospective customer number data D5 can be calculated without conducting the questionnaire D3 and generating the questionnaire survey data D4 each time the correlation model D7 is generated.

Next, operation of the model generation system 10 according to this embodiment will be described.

For example, when the advertisement target advertised by the digital advertisement D1 is the shampoo product a, the advertisement distribution result data D2 acquired by the advertisement distribution server 20 based on the access to the digital advertisement D1 via the terminal T is , is input to the data processing server 40 .

On the other hand, questionnaire survey data D4 generated by aggregating the questionnaire D3 regarding the product a via the terminal T is input to the data processing server 40 .

Subsequently, among the numerical information included in the advertisement distribution result data D2, arbitrary numerical information (for example, advertisement page induction rate d3) is extracted as variable information.

Furthermore, based on the questionnaire survey data D4, prospective customer number data D5 is calculated and stored in the third database 41. FIG.

As a result, the advertisement page induction rate d3 of the advertisement distribution result data D2 and the prospective customer number data D5 are correlated to generate the correlation model D7. The generated correlation model D7 is provided, for example, to an advertiser or the like who placed the digital advertisement D1 regarding the product a.

After generating the correlation model D7 for the product a, after generating the correlation model D7 for the products b and c, for example, when generating the correlation model D7 for the shampoo product d, a questionnaire D3 for the product d is conducted. Machine learning is performed on the questionnaire survey data D4 for the products a to c to generate a learned model D6.

When the trained model D6 is generated, the prospective customer number data D5 is calculated based on this, and the calculated prospective customer number data D5 and the advertisement distribution result data D2 regarding the product d are correlated to obtain a correlation model D7. is generated.

The generated correlation model D7 is provided, for example, to an advertiser or the like who placed the digital advertisement D1 regarding the product d.

In this way, the correlation model D7 generated by correlating the advertisement distribution result data D2 and the prospective customer number data D5 calculated based on the questionnaire survey data D4 changes based on the fluctuation of the advertisement distribution result data D2. Since it is possible to calculate the amount of change in the prospective customer number data D5, it is possible to quantitatively grasp the prospective customer number (market size) of the advertised object that fluctuates due to the digital advertisement D1.

Therefore, it is possible to generate a correlation model D7 that can appropriately and objectively evaluate the effect of the digital advertisement D1 based on the amount of change in the number of prospective customers that is quantitatively grasped.

Moreover, in the present embodiment, the learned model D6 is generated by performing machine learning on the questionnaire survey data in which the answers to the questionnaires that have already been conducted are aggregated, and the prospective customer number data D5 is calculated by the learned model D6. Therefore, when generating a new correlation model D7 after generating several correlation models D7, it is not necessary to conduct the questionnaire D3 and generate the questionnaire survey data D4 each time.

The present invention is not limited to the above-described embodiments, and various modifications are possible without departing from the scope of the invention.

In the above embodiment, the case where the digital advertisement D1 is distributed using a website on the Internet as an advertising medium has been described. good too.

In this case, the advertisement distribution result data D2 is generated, for example, based on an image or video of a viewer browsing the digital advertisement displayed on the digital signage detected by a camera or sensor placed near the digital signage. can be anything.

In the above embodiment, the case where the prospective customer number data calculation module 42c is a module that implements the data processing program 42 stored in the data processing server 40 has been described. It may be a module to be installed, or it may be the program itself stored in the aggregation server 30 .

In the above embodiment, the case where the questionnaire D3 is distributed to the terminal T of the user U via the Internet network has been described, but the questionnaire may be conducted on the street, for example.

In this case, the questionnaire survey data D<b>4 may be generated by the survey operator 2 inputting the aggregated results of street questionnaires to the aggregation server 30 .

1 EC site operator 2 Survey operator 3 Operator 10 Model generation system 20 Ad distribution server 21 First database 30 Aggregation server 31 Second database 40 Data processing server 42 Data processing program 42b Variable information extraction module 42c Number of prospective customers Data calculation module 42d Correlation model generation module (model generation module)
42e Learned model generation module D1 Digital advertisement D2 Ad distribution result data D3 Questionnaire D4 Questionnaire survey data D5 Prospective customer number data D6 Learned model D7 Correlation model d3 Advertisement page induction rate (variable information)

Claims (7)

a first database storing advertisement delivery result data relating to the delivery results of digital advertisements advertising advertising objects;
Questionnaire survey data for ascertaining attitude change contribution, which is a factor of change in attitude of customers regarding the advertisement object advertised by the digital advertisement, is stored in relation to the advertisement distribution result data stored in the first database. a second database;
prospective customer number data relating to the number of customers who have an intention to purchase the advertising object calculated based on the questionnaire survey data stored in the second database; and the advertisement distribution result data stored in the first database; and a model generation module for generating a correlation model for calculating the amount of variation in the number of prospective customers data that varies based on the variation in the advertisement delivery result data;
A model generation system with 2. The model generation system according to claim 1, further comprising a variable information extraction module for extracting from said advertisement distribution result data variable information to be correlated with said number of prospective customers data in said model generation module. The variable information is
3. The model generation system according to claim 2, comprising information on the number of views of the content in which the advertising object is posted via the digital advertisement distributed via the Internet network. 4. The model generation system according to any one of claims 1 to 3, comprising a prospective customer number data calculation module for calculating said prospective customer number data. The model generation system according to any one of claims 1 to 4, comprising a trained model generation module that learns the questionnaire survey data and generates a trained model. Advertisement delivery result data relating to delivery results of digital advertisements advertising an advertising object, and questionnaire survey data for grasping contribution to attitude change, which is a factor in changing customer attitudes regarding the advertising object advertised by the digital advertisement. Correlating with prospective customer number data regarding the number of customers who have an intention to purchase the advertised object calculated based on
generating a correlation model for calculating a variation amount of the prospective customer number data that varies based on a variation of the advertisement distribution result data;
Model generation module. Advertisement delivery result data relating to delivery results of digital advertisements advertising an advertising object, and questionnaire survey data for grasping contribution to attitude change, which is a factor in changing customer attitudes regarding the advertising object advertised by the digital advertisement. Correlating with prospective customer number data regarding the number of customers who have an intention to purchase the advertised object calculated based on
generating a correlation model for calculating a variation amount of the prospective customer number data that varies based on a variation of the advertisement distribution result data;
Model generation method.

Images