JP7510025B1 - DATA PROCESSING APPARATUS, DATA PROCESSING METHOD, AND PROGRAM - Google Patents

Abstract

The present invention makes it possible to acquire pseudo-sample data that is useful for analyzing exposure to target content via multiple media.
[Solution] The system includes an actual data acquisition unit that acquires single-source data for multiple users, the single-source data including a first value indicating the usage status of a first medium and a second value indicating the usage status of a second medium of a single user; a pseudo data generation unit that generates a pseudo sample of the single-source data so that the correlation coefficient between the first value and the second value is the same as that of the single-source data for the multiple users; and a contact frequency allocation unit that calculates a first contact frequency to the target content via the first medium for each of the generated pseudo samples, where the contact frequency allocation unit uses data indicating the contact status to the target content in the first medium and calculates the first contact frequency based on the first value in each pseudo sample.
[Selected figure] Figure 3

Description

The present invention relates to a data processing device, a data processing method, and a program that analyzes content exposure using data amplified with pseudo samples.

In recent years, research has been conducted into the scale of exposure to a certain product through multiple media, such as television commercials and video site advertisements.

For example, Patent Document 1 discloses a method for calculating the number of people exposed to at least one of a television commercial and a digital advertisement, using data on the number of people exposed to a television commercial, data on the number of people exposed to a digital advertisement, and data (single-source data) indicating, for each of a number of targets, whether or not the target person viewed the television commercial and the number of times the site on which the digital advertisement was posted was viewed.

In addition, as described in Patent Document 2, for example, it is known that in a survey of content exposure, pseudo sample data created based on actual sample data is used to increase the amount of data.

JP 2020-160657 A JP 2022-028370 A

Single-source data generally contains information indicating the same individual's exposure to multiple media, but does not necessarily contain information indicating the frequency of exposure to targeted advertising via multiple media. However, in order to analyze exposure to targeted advertising via multiple media, data containing information indicating exposure that reflects the actual situation for each medium was required.

The present invention aims to make it possible to obtain pseudo-sample data that is useful for analyzing exposure to target content via multiple media.

The data processing device according to the present invention includes an actual data acquisition unit that acquires single-source data for a plurality of users, including a first value indicating the usage status of a first medium and a second value indicating the usage status of a second medium for a single user; a pseudo data generation unit that generates pseudo samples such that the correlation coefficient between the first value and the second value is not different from that of the single-source data for the plurality of users; and a contact frequency allocation unit that calculates a first contact frequency to a target content via the first medium for each of the generated pseudo samples, the contact frequency allocation unit using data indicating the contact status to the target content in the first medium and calculating the first contact frequency based on the first value in each pseudo sample.

The data processing method according to the present invention includes a step of acquiring single-source data for a plurality of users, the single-source data including a first value indicating the usage status of a first medium and a second value indicating the usage status of a second medium by a single user, a step of generating pseudo samples of the single-source data such that the correlation coefficient between the first value and the second value is the same as that of the single-source data for the plurality of users, and a step of calculating a first contact frequency of contact with the target content via the first medium for each of the generated pseudo samples, in which the step of calculating the first contact frequency uses data indicating the contact status of the target content in the first medium and calculates the first contact frequency based on the first value in each pseudo sample.

The program of the present invention causes a computer to function as an actual data acquisition unit that acquires single-source data for multiple users, including a first value indicating the usage status of a first medium and a second value indicating the usage status of a second medium for a single user; a pseudo data generation unit that generates a pseudo sample of the single-source data such that the correlation coefficient between the first value and the second value is not different from that of the single-source data for the multiple users; and a contact frequency allocation unit that calculates a first contact frequency to a target content via the first medium for each of the generated pseudo samples, the contact frequency allocation unit using data indicating the contact status to the target content in the first medium and calculating the first contact frequency based on the first value in each pseudo sample.

The present invention makes it possible to obtain pseudo-sample data that is useful for analyzing exposure to target content via multiple media.

1 is a block diagram showing a configuration of a data processing device 1 according to a first embodiment of the present invention. 1 is a block diagram showing functional modules of a program executed by a processor 11 of a data processing device 1 according to a first embodiment of the present invention. 3 is a flowchart of the operation of the data processing device 1 according to the first embodiment of the present invention. 3A and 3B are diagrams showing specific examples of single-source data and pseudo samples according to the first embodiment of the present invention. FIG. 2 is a diagram illustrating statistical data on the gender/age structure of the television owner population used to determine the pseudo sample size according to the first embodiment of the present invention. 5 is a diagram for explaining a method for calculating the number of exposures to advertisement C on a video site according to the first embodiment of the present invention. FIG. FIG. 4 is a diagram for explaining a method for calculating the number of exposures to advertisement C on television according to the first embodiment of the present invention. FIG. 11 is a diagram for explaining a method for calculating the number of exposures to advertisement C on a video site according to the second embodiment of the present invention. FIG. 11 is a diagram for explaining a method for calculating the number of exposures to advertisement C on a video site according to the second embodiment of the present invention.

Next, an embodiment of the present invention will be described in detail with reference to the drawings.
(Embodiment 1)
1 is a block diagram showing the configuration of a data processing device 1 according to a first embodiment of the present invention. The data processing device 1 is composed of one computer or a plurality of computers connected by a communication line. The data processing device 1 includes a processor 11, a main memory 12, an input/output interface 13, a communication interface 14, and a storage device 15. The storage device 15 is a computer-readable recording medium such as a semiconductor memory (e.g., a volatile memory or a non-volatile memory) or a disk medium (e.g., a magnetic recording medium or a magneto-optical recording medium). The storage device 15 stores programs to be executed by the processor 11, various data, and the like. The programs are read from the storage device 15 into the main memory 12, and are interpreted and executed by the processor 11 to perform various functions.

Figure 2 is a block diagram showing the functional modules of a program executed by the processor 11 of the data processing device 1. As shown in Figure 2, the functional modules executed by the processor 11 of the data processing device 1 include an actual data acquisition unit 101, a pseudo data generation unit 102, a contact frequency allocation unit 103, and a counting unit 104.

The storage device 15 stores actual single-source data (actual data) and pseudo-sample data generated based on the actual data. Single-source data is data that includes the results of measuring the exposure of a single user (the same individual) to multiple media. In this embodiment, as an example, data that includes the results of measuring the amount of time a single individual spends watching television, the number of times they have been exposed to advertisements on television, and the amount of time they spend watching video sites (such as YouTube (registered trademark))) is used as single-source data.

Next, the flow of data processing by the data processing device 1 will be described with reference to the flowchart of FIG. 3. For a certain advertisement C (target content), the data processing device 1 generates data for analyzing the exposure to advertisement C on television (second medium) and the exposure to advertisement C on a web video site (first medium). Note that, although an example of analyzing the exposure to a target advertisement in multiple media is given here, the target content for which the exposure is analyzed is not limited to advertisements and may be, for example, a specific program or video.

First, the actual data acquisition unit 101 acquires single source data (actual data) related to the usage history of television (second medium) and the usage history of a web video site (first medium) (step S101). FIG. 4 (A) is a diagram showing a specific example of single source data. As shown in FIG. 4 (A), the single source data includes the television usage time (minutes) (second value indicating usage status) for each survey target user (Sno001, 002, ...) in a specified survey period (e.g., one week), the number of times (times) that the user came into contact with advertisement C on television, and the usage time (minutes) (first value indicating usage status) of a video site (YouTube, etc.). Note that the single source data does not include the number of times that the user came into contact with advertisement C on the video site.

The single-source data may also include user attribute information (gender, age, etc.). In the example of FIG. 4(A), attribute information includes gender and age category, and as shown in the figure, single-source data is obtained for male users aged 18-24 (M18-24).

Next, the pseudo data generating unit 102 generates pseudo sample data having the same data items and the same distribution as the acquired single source data (step S102). FIG. 4B is a diagram illustrating pseudo sample data generated based on the single source data of FIG. 4A. The pseudo data generating unit 102 obtains a three-dimensional normal distribution for the three items constituting the data (television usage time, number of exposures to television advertisements, and usage time of video sites) based on the single source data acquired in step S101. Furthermore, the pseudo sample data is generated randomly according to the obtained three-dimensional normal distribution. The pseudo data generating unit 102 generates pseudo sample data so that the average and correlation coefficient between the items (television usage time, number of exposures to television advertisements, and usage time of video sites) in the generated pseudo sample data are the same as the average and correlation coefficient in the original single source data. Note that in the example of FIG. 4B, a normal distribution random number is assigned to the numerical value of each item of the pseudo sample, so that, for example, the number of exposures to television advertisements is not a natural number but a numerical value including a decimal point.

The number of pseudo samples generated by the pseudo data generating unit 102 can be set according to the purpose of the survey. In the example of FIG. 4(B), the number of pseudo samples is determined based on the statistical data of the gender/age composition of the television owner population shown in FIG. 5. FIG. 5 shows the television owner population in each gender/age category when the number of pseudo samples is 100,000, where MF, M, and F represent male and female, male, and female, respectively, and the numbers next to them represent the age group. FIG. 4(B) shows a pseudo sample generated based on actual data of men aged 18 to 24 (M18-24). According to FIG. 5, when the total TV owner population is 100,000, the number of men aged 18 to 24 is 3346, so in the example of FIG. 4(B), 3346 pseudo samples are generated. Note that here, data assuming the television owner population for each gender/age category is used, but it is also possible to assume not only the television owner population, but also the total population for each gender/age category, for example.

Next, the contact frequency allocation unit 103 calculates the number of times advertisement C was contacted via the video site (first contact frequency) for each of the generated pseudo samples (step S103).

Using FIG. 6, a method for calculating the number of contacts to advertisement C on a video site by the contact frequency allocation unit 103 will be described. The distribution data of the number of contacts to advertisement C on a video site provided as official data is used to calculate the number of contacts. The second column of the table in FIG. 6(A) illustrates the distribution (official data) of the number of contacts to advertisement C in a given population (0 to 10 or more), and the third column shows the number of samples (number of data) allocated to each number of contacts (0 to 10 or more) from the pseudo sample generated in step S102 (data for 3,346 people in the example of FIG. 4(B)) in accordance with the distribution in the second column. The fourth column shows the result of rounding off the decimal point of the numbers in the third column and adjusting the number of people with 10 or more contacts so that the total is 3,346 people.

Figure 6 (B) shows an example in which the pseudo samples generated in step S102 are ranked by the number of exposures to TV commercials (third column of the table) and the time spent on video sites (sixth column of the table). The ranking of the number of exposures to TV commercials (third column of the table) is based on the number of exposures to advertisement C on TV in the fourth column of the table, in ascending order. On the other hand, the ranking of the time spent on video sites (sixth column of the table) is based on the time spent on video sites, in descending order.

The contact frequency allocation unit 103 calculates the number of contacts to advertisement C on the video site for each pseudo sample in FIG. 6(B) based on the distribution of the number of contacts to advertisement C on the video site shown in FIG. 6(A). Referring to the fourth column in FIG. 6(A), for 1255 of the 3346 pseudo samples, the number of contacts to advertisement C on the video site is "0". Therefore, the contact frequency allocation unit 103 sets the number of contacts to advertisement C to "0" for the pseudo samples up to the 1255th pseudo sample in the order of the shortest usage time of the video site among the pseudo samples in FIG. 6(B). Similarly, for the 1256th to 1690th samples, the number of contacts to advertisement C is "1", for the 1691st to 2008th samples, "2", for the 2009th to 2319th samples, "3", and for the 2320th to 2677th samples, "4". In the example of FIG. 6(B), samples Sno 001 and 002 are included up to the 1255th, so the number of exposures to advertisement C is 0. On the other hand, sample Sno 003 is included in the range from the 2320th to the 2677th, so the number of exposures to advertisement C is 4. In this way, the number of exposures to advertisement C on the video site in the pseudo sample data can be set.

In addition, although the pseudo sample already contains values for the number of exposures to TV commercials, it may be set again based on the ranking of the number of exposures to TV commercials. Specifically, similar to the number of exposures to advertisement C on a video site, the distribution data of the number of exposures to advertisement C on television provided as official data (second column of FIG. 7) is used, and data for 3346 people is assigned to each number of exposures (for example, 0 to 10 or more) (third column of FIG. 7), the number of assigned data for each number of exposures is found (fourth column of FIG. 7), and the number of exposures to advertisement C on television may be assigned according to the ranking in the third column of FIG. 6(B). This makes it possible to create a pseudo sample with a distribution of the number of exposures that matches the distribution of the official data for television advertisements as well. For example, in the example of FIG. 6(B), Sno001 has a number of exposures to TV commercials originally shown in the pseudo sample of 5.6, but since the rank of the TV commercial is 2253rd, the number of exposures according to the distribution of FIG. 7 is 2. In addition, for Sno002, the number of exposures to the TV commercial originally shown in the pseudo sample is 3.3 times, but because the TV commercial is ranked 1521st, the number of exposures is 0 according to the distribution in Figure 7.

By performing the above steps S101 to S103, a desired number of pseudo samples including the number of exposures to advertisement C on television and the number of exposures to advertisement C on the video site can be obtained from a limited number of single-source data (actual data) including television usage time, the number of exposures to advertisement C on television, and usage time on the video site.

(Analysis of combined reach and overlapping reach)
The aggregation unit 104 estimates the integrated reach and overlapping reach using the generated pseudo sample. The integrated reach is the rate at which at least one of a plurality of events occurs, and in the above embodiment, it indicates the rate of users who are exposed to at least one of the television advertisement and the video site advertisement. The overlapping reach is the rate at which all of a plurality of events occur, and in the above embodiment, it indicates the rate of users who are exposed to both the television advertisement and the video site advertisement. That is, in the above embodiment, the integrated reach and overlapping reach can be calculated, for example, by the following formulas (1) and (2). Note that in the following formulas (1) and (2), the integrated reach and overlapping reach are calculated on the premise that a user who has been exposed even once is considered to have been reached. The definition of the reach is not limited to this, and for example, if it is determined that a user has been exposed two or more times, or three or more times, it can be calculated by replacing "number of exposures ≧ 2" and "number of exposures ≧ 3" in the following formulas.

Integrated reach = ([number of users with TV ad exposure count ≥ 1] + [number of users with video site ad exposure count ≥ 1] - [number of users with both TV ad exposure count and video site ad exposure count ≥ 1]) / 3346 ... (1)
Overlap reach = [number of users who have been exposed to both television ads and video site ads ≥ 1]
/3346 … (2)

By calculating the integrated reach using the generated pseudo-samples, the relationship between the contact rate for television ads and video site ads and the integrated reach can be analyzed, and this can be used to implement efficient advertising.

In the above embodiment, a single-source pseudo sample is obtained that includes the number of exposures to television advertisements and video site advertisements, but the items included in the pseudo sample can be adjusted depending on the purpose of the analysis. For example, it is possible to distinguish between exposure to advertisement C on a video site on a television screen and exposure to it on a smartphone. In addition, the number of exposures to advertisement C on television may be included by station. The number of exposures during a specific time period or on a specific site can also be calculated using a similar procedure.

As described above, according to this embodiment, single-source data including the usage time of multiple media is used to generate a pseudo sample so that the correlation coefficient between items does not change, and further, distribution data of the number of exposures to target advertisement C in each medium is used to assign the number of exposures to advertisement C based on the usage time of that medium in the pseudo sample. In this way, it is possible to estimate the number of exposures that is in line with the actual situation using single-source data that only includes information on the usage time of the media. This makes it possible to generate pseudo sample data that can be used to analyze the exposure situation to advertisement C via multiple media. Furthermore, even if an analysis is performed using the created pseudo sample, it is expected that results will be obtained that are not inconsistent with the results of an analysis using actual measured data.

In this embodiment, pseudo sample data is created that indicates exposure to television advertisements and video site advertisements, but the number and types of media are not limited to this, and the data can be used to create pseudo samples related to exposure to multiple media, such as newspapers and radio in addition to television and the web. In addition to integrated reach and overlapping reach, various indicators and statistical data can be created that can be analyzed and calculated based on single-source data. Furthermore, the data is not limited to the integrated reach and overlapping reach of two types of media, but can handle the integrated reach and overlapping reach of any number of media, as well as other analyses.

In addition, the pseudo-sample data that is created can be used not only for analyzing integrated reach and overlapping reach, but also for other purposes, such as the following:
(1) Use the demographic profile of those exposed to the ad to portray it.
(2) By combining it with other data sources, it can be used for a variety of purposes. Specific examples include the following:
(2)-1: By combining data from advertising distribution companies, we can achieve effective delivery to complement the reach.
(2)-2: Combine with brand evaluation data and use to analyze the effect of advertising on brand evaluation.
(2)-3: Combine with purchase history data and use to analyze the effectiveness of advertising on purchases.
(2)-4: Combine this with consumer attribute profile data to obtain detailed profiles of those who were exposed to the advertising.

(Embodiment 2)
The configuration of the data processing device 1 according to the second embodiment of the present invention and the functional modules of the program executed by the processor 11 of the data processing device 1 are the same as those of the first embodiment shown in Figures 1 and 2. Moreover, the flow of data processing by the data processing device 1 is the same as that shown in the flowchart of Figure 3. That is, based on single-source data as exemplified in Figure 4(A), pseudo sample data as exemplified in Figure 4(B) is generated as in the first embodiment. Furthermore, the contact frequency allocation unit 103 calculates the number of times advertisement C was contacted via the video site (first contact frequency) for each of the generated pseudo samples. In the second embodiment, the number of times advertisement C was contacted via the video site is calculated by a method different from that of the first embodiment.

In the first embodiment, distribution data of the number of times of contact with advertisement C on a video site as shown in FIG. 6(A) is provided as official data, and this is used to calculate the number of times each pseudo sample was contacted with advertisement C via the video site. On the other hand, many video sites do not provide distribution data of the number of times of contact with advertisement C as described above. Instead, data showing the ratio of whether or not there was contact with advertisement C on the video site may be provided. Specifically, values defined as follows are provided for a given population (for example, men aged 18 to 24 (M18-24)):
Percentage of people with exposure = number of people who were exposed to ad C on the video site / number of people in the population Percentage of people without exposure = 1 - (percentage of people with exposure)

In addition, the average number of contacts in the group that was exposed to advertisement C may also be provided. Specifically, values defined as follows are provided.
Average number of contacts = total number of times Ad C is displayed on the video site / number of people who came into contact with Ad C on the video site

In the second embodiment, the number of times each pseudo sample was exposed to advertisement C via a video site is calculated using data indicating the ratio of those who were exposed to advertisement C on a video site and the average number of times the sample was exposed to advertisement C in the group who were exposed to advertisement C.

First, the contact frequency allocation unit 103 allocates to each pseudo sample whether or not they have been exposed to advertisement C on the video site. The second column of the table in FIG. 8(A) is data obtained as official data, and illustrates the ratio of whether or not a specific population (for example, men aged 18 to 24 (M18-24)) has been exposed to advertisement C on a video site. The third column shows the number of people in the pseudo sample (17,964 people in this case) who have been allocated to no contact or contact according to the ratio in the second column. In addition, the fourth column shows the result of rounding off the decimal point of the numbers in the third column and adjusting the number of people with no contact so that the total is 17,964 people.

Figure 8 (B) is a diagram showing an example in which the pseudo samples are ranked by the time spent on the video site (column 8 of the table). The ranking of the time spent on the video site (column 7 of the table) is assigned in ascending order. The contact frequency allocation unit 103 assigns the presence or absence of contact with advertisement C on the video site to each pseudo sample in Figure 8 (B) based on the ratio of the presence or absence of contact with advertisement C on the video site shown in Figure 8 (A). With reference to the fourth column of Figure 8 (A), 15719 out of 17964 people in the pseudo sample have no contact with advertisement C on the video site. Therefore, the contact frequency allocation unit 103 assigns "no contact" with advertisement C to the 15719th pseudo sample in Figure 8 (B) in descending order of the time spent on the video site. Similarly, the 15720th to 17964th samples are assigned "yes" to contact with advertisement C.

Next, the contact frequency allocation unit 103 allocates an expected value of the number of advertisement contacts to the samples with “existence” of contact with advertisement C. The contact frequency allocation unit 103 allocates an expected value based on a relationship that satisfies the following three conditions.
Condition 1: The expected value is proportional to the amount of time spent on the video site.
Condition 2: The average expected value matches the average number of contacts among the group of people who have contact in the official data.
Condition 3: Among the pseudo-samples that are assigned "contact," the expected value of the sample with the shortest time spent on video sites is "1."

A specific procedure for calculating the expected value based on the relationship that satisfies conditions 1 to 3 will be described below. First, the contact frequency allocation unit 103 calculates the equation Y=c+bX for a straight line (condition 1) that passes through the following two points on a plane defined by (X, Y)=(usage time, expected value of number of contacts) as shown in FIG.
Point P1 (Condition 3): (Minimum usage time in contact “present” samples, 1)
Point P2 (Condition 2): (Average usage time At calculated from samples with contact, average expected value Ar (where average expected value Ar = "average number of advertising contacts" in official data))

The video site usage time (X) of each sample is substituted into the equation (1) for the obtained straight line to obtain an expected value Y of the number of advertisement exposures for each sample.
Expected number of ad exposures (Y) = c + b × video site usage time (X) (1)
(c and b are constants)

Furthermore, the contact frequency allocation unit 103 uses the expected value of each sample thus obtained to calculate the number of advertisement contacts for each sample. The contact frequency allocation unit 103 may, for example, generate a random number according to a truncated Poisson distribution whose expected value coincides with the expected value of each sample, and set it as the number of advertisement contacts for that sample. Since the number of advertisement contacts is an integer of 1 or more, a truncated Poisson distribution whose domain is 1 or more may be used. Note that, if the expected value (λ) of the Poisson distribution before truncation is required to generate random numbers of the truncated Poisson distribution, λ may be calculated individually according to the range of the expected value of each sample. The expected value E of the truncated Poisson distribution truncated at 1 or more and the expected value λ of the Poisson distribution before truncation have the following relationship:
E = λ/(1-exp(-λ))

According to the second embodiment, even if data on the distribution of ad exposures on video sites cannot be obtained, if data on the ratio of ad exposures and the average ad exposures can be obtained, the ad exposures can be estimated based on the actual situation of the pseudo sample. As a result, as in the first embodiment, pseudo sample data can be generated that can be used to analyze exposure to advertisement C via multiple media. Furthermore, even if an analysis is performed using the created pseudo sample, it is expected that results will be obtained that are consistent with the results of an analysis using actual data.

The probability distribution used to generate the number of ad exposures from the expected value is not limited to the truncated Poisson distribution. For example, binomial distribution, negative binomial distribution, geometric distribution, beta binomial distribution, etc. can also be used. As in the first embodiment, the number of exposures to television commercials may also be reset based on the ranking of the number of exposures to television commercials.

The present invention is not limited to the above-described embodiment, and can be implemented in various other forms without departing from the spirit of the present invention. For this reason, the above-described embodiment is merely illustrative in every respect, and should not be interpreted in a restrictive manner. For example, the above-described processing steps can be arbitrarily changed in order or executed in parallel as long as no inconsistency occurs in the processing content. Other steps may be added between each processing step. A step described as one step may be divided into multiple steps and executed, and something described as being divided into multiple steps can be understood as one step.

1... data processing device 11... processor 12... main memory 13... input/output interface 14... communication interface 15... storage device 101... actual data acquisition unit 102... pseudo data generation unit 103... contact frequency allocation unit 104... counting unit

Claims (7)

an actual data acquisition unit that acquires single source data for a plurality of users, the single user including a first value indicating a usage status of a first medium and a second value indicating a usage status of a second medium;
a pseudo data generating unit configured to generate a pseudo sample of the single-source data such that a correlation coefficient between the first value and the second value is the same as that of the single-source data for the plurality of users;
a contact frequency allocation unit that calculates a first contact frequency of the target content via the first medium for each of the generated pseudo samples,
The contact frequency allocation unit
A data processing device that uses data indicating a contact state with the target content in the first medium and calculates the first contact frequency based on the first value in each pseudo sample. the data indicating the contact status with the target content is distribution data of contact frequency,
The contact frequency allocation unit
The data processing apparatus according to claim 1 , further comprising: ranking each pseudo sample according to a length of time spent using the first medium; and allocating the first exposure frequency based on distribution data of exposure frequency to the target content. The data indicating the contact status with the target content is data indicating a ratio of contact presence/absence,
The contact frequency allocation unit
2. The data processing device of claim 1, further comprising: ranking each pseudo sample according to the length of time the pseudo sample has spent using the first medium; assigning each pseudo sample a status of contact with the target content based on data indicating the ratio of contact with the target content to a status of contact; and assigning the first contact frequency to each pseudo sample that has been assigned a status of contact with the target content based on the length of time the pseudo sample has spent using the first medium. The contact frequency allocation unit
The data processing device according to claim 3 , wherein for a pseudo sample that is assigned a contact with the target content, a random number that follows a probability distribution having an expected value proportional to a length of time of using the first medium is assigned as the first contact frequency. the single-source data includes a second frequency of exposure to the target content via the second medium;
The contact frequency allocation unit
The data processing device according to claim 1 or 3, wherein each pseudo sample is ranked according to the second contact frequency, and the second contact frequency is reallocated based on data indicating a situation regarding the target content in the second medium. a processor obtaining single source data for a plurality of users, the single user including a first value indicative of a usage of a first medium and a second value indicative of a usage of a second medium;
a processor generating a pseudo-sample of the single-source data such that a correlation coefficient between the first values and the second values is invariant to single-source data for the plurality of users;
and calculating, by the processor, a first frequency of exposure to target content via the first medium for each of the generated pseudo samples;
In the step of calculating the first contact frequency,
A data processing method comprising: utilizing data indicating an exposure state to the target content in the first medium; and calculating the first exposure frequency based on the first value in each pseudo sample. Computer,
an actual data acquisition unit that acquires single source data for a plurality of users, the single user including a first value indicating a usage status of a first medium and a second value indicating a usage status of a second medium;
a pseudo data generating unit configured to generate a pseudo sample of the single-source data such that a correlation coefficient between the first value and the second value is the same as that of the single-source data for the plurality of users;
a contact frequency allocation unit that calculates a first contact frequency of the target content via the first medium for each of the generated pseudo samples;
The contact frequency allocation unit
a program for calculating the first exposure frequency based on the first value for each pseudo sample by using data indicating an exposure state to the target content in the first medium;

Images