JP2023153658A - Viewing information processing device, viewing information processing method, and program for viewing information processing - Google Patents

Abstract

To provide a viewing information processing device capable of selecting an investigation target viewer from viewing log information acquired from a plurality of television devices in an investigation target region, so that a television viewing situation in the investigation target region can be identified suitably.SOLUTION: A viewing information processing device 1 estimates on the basis of viewing log information acquired from television devices 20 in an investigation target region, estimates the attribute constitution of a viewer for each of the television devices 20 and a viewing time of each attribute, and estimates frequency distribution of the number of the viewers in the viewing time, for each attribute of the viewer. The viewing information processing device 1 selects an investigation target viewer based on comparison between the estimated frequency distribution and a reference frequency distribution for each attribute of the viewer.SELECTED DRAWING: Figure 1

Description

The present invention provides a viewing information processing device, a viewing information processing method, and a viewing information processing device having a function of selecting viewers for investigating the viewing status of television broadcasting from among viewers of television devices capable of outputting viewing log information. Regarding programs for

2. Description of the Related Art In recent years, television devices having a function of transmitting viewing data including viewing log information indicating which channel's television broadcast was viewed and when, to a television manufacturer or the like via an external network such as the Internet have become popular. Note that in this specification, a device that can receive and view television broadcasts and has a function of transmitting viewing log information as described above is referred to as a television device.

For example, as seen in Patent Document 1, from the viewing log information obtained from each television device, the viewer of the television device (specifically, one or more people who can watch the television broadcast received via the television device) The present application is a technology that uses a model (mathematical model) that has been subjected to machine learning processing in advance to estimate the attribute composition of viewers) and viewing information by attribute that indicates the viewing status of television broadcasts for each attribute of the viewer. Proposed by the applicant.

Here, the attribute composition of the viewers of a television device indicates which attributes the viewers are made up of among multiple types of attributes classified according to gender, age, etc. It is. In addition, viewing information by attribute of the viewer of a TV device is a TV broadcast broadcast on a certain channel (or broadcasting station series) on a certain date and time, for each attribute of the viewer. means something that indicates whether you have watched or not.

Patent No. 6433615

By the way, if viewing log information sent from television devices is collected in the survey target area where viewing status is to be investigated, the collected viewing log information will not be collected unless the television device that has the communication connection with the external network is used. This is viewing log information regarding viewers in households where the TV device is used, and viewing log information regarding viewers who do not own the television device or do not use an external network is not included. For this reason. When investigating viewing conditions such as audience ratings from all of the collected viewing log information, there is a risk that the results of the survey of estimated viewing conditions may deviate from the actual viewing conditions in the survey target area.

For example, viewers who view television broadcasts on television devices that have a communication connection with an external network so that viewing log information can be transmitted are often from a relatively young generation. This generation often spends a lot of time out of the day at work or school, or works or studies at home, so they tend to spend relatively little time watching TV broadcasts. It is often the case.

On the other hand, although viewers with attributes such as the elderly often spend a long time watching television broadcasts during the day, they may not have a television device that has the function of transmitting viewing log information. Alternatively, the communication connection between the television device and an external network is often not utilized.

In such a situation, when viewing log information sent from television devices is collected, the total viewing log information collected will be dominated by younger generations (generations with relatively short viewing times), and by older generations. Viewing log information of attributes such as people with relatively long viewing times tends to be smaller than viewing log information of attributes of younger generations. For this reason, there is a possibility that the survey results of the viewing situation estimated from the collected viewing log information may deviate from the actual viewing situation in the survey target area.

The present invention has been made in view of this background, and it is possible to appropriately identify the TV viewing situation in the survey target area from viewing log information obtained from multiple TV devices in the survey target area. It is an object of the present invention to provide a viewing information processing device and a viewing information processing method that are capable of selecting viewers to be surveyed. Another object of the present invention is to provide a viewing information processing program that allows a computer to select the viewer.

In order to achieve the above object, the viewing information processing device of the present invention includes a television broadcast receiver and a viewing log indicating which channel or broadcast station series' television broadcast was viewed and at what time via the receiver. Each of the attributes included in the viewer attribute configuration of each television device for each of the plurality of television devices that are each equipped with a viewing data output device capable of outputting information and that belong to a predetermined survey target area. a viewing time acquisition unit that acquires the viewing time of the television broadcast in a period of a predetermined unit time width,
a frequency distribution identifying unit that identifies a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time for each attribute estimated by the viewing time estimating unit;
Based on the comparison between the frequency distribution of the number of viewers for each attribute specified by the frequency distribution identification unit and the standard frequency distribution for each attribute predetermined in the survey target area, for each attribute, and a survey target audience selection unit that selects viewers to survey the viewing situation in the survey target area,
The survey target viewer selection unit selects the survey target viewers for each attribute so that the frequency distribution of the number of survey target viewers with respect to viewing time matches the frequency distribution of the standard. (first invention).

Supplementally, in the present invention, the attribute composition of viewers of each television device means what type of attributes the viewers of each television device are made up of.
Also. The fact that the frequency distribution of the number of surveyed viewers with respect to viewing time (hereinafter referred to simply as frequency distribution A in this column) matches the standard frequency distribution means that the frequency distribution according to viewing time in frequency distribution A This means that the pattern of change in (number of viewers) matches the pattern of change in the standard frequency distribution. In this case, "matching" is not limited to exactly matching, but also includes substantially matching (approximately matching). Further, as an index for determining the degree of coincidence of the above-mentioned "change patterns", for example, a mutual ratio of frequencies corresponding to each of a plurality of types of viewing times can be used.

According to the present invention, by including the viewing time acquisition section and the frequency distribution specifying section, the viewing time (the viewing time of a television broadcast in a period of a predetermined unit time width) of a viewer of each attribute for each television device can be determined. Based on this, it is possible to specify the frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area.

Then, the survey target viewer selection unit selects the survey target viewers for each attribute such that the frequency distribution of the number of survey target viewers with respect to viewing time matches the standard frequency distribution. In this case, by appropriately setting the standard frequency distribution for each attribute, it is possible to ensure that the frequency distribution of the number of viewers to be surveyed for each attribute matches the actual situation in the survey target area. Viewers can be selected.

Therefore, by conducting a survey of the viewing status of the viewers selected as described above, it is possible to obtain survey results that match the actual viewing status in the survey target area. Therefore, according to the present invention, the TV viewing situation in the survey target area can be appropriately identified from the viewing log information obtained from multiple TV devices in the survey target area. viewers can be selected

In the first invention, the reference frequency distribution is viewing data obtained from each of a plurality of sample households selected in advance in the survey target area, and viewing log information for each viewer of each sample household is used. It is possible to adopt an aspect in which the frequency distribution is set based on the included viewing data (second invention).

According to this, by appropriately selecting sample households, viewers can be selected for each attribute in such a way that the frequency distribution of the number of surveyed viewers matches the actual situation in the surveyed area. Above, a suitable reference frequency distribution can be set.

The first or second invention further includes a viewing status estimating unit that estimates the viewing status of a predetermined survey target television broadcast, and the viewing status estimating unit is selected by the survey target viewer selection unit. a function of estimating whether or not each survey target viewer viewed the survey target television broadcast from the viewing log information acquired by the viewing log information acquisition unit regarding the television device corresponding to the viewer; and is configured to estimate the viewing status of the surveyed television broadcast for each attribute of the surveyed viewers based on the estimation results regarding all surveyed viewers in the surveyed area. (Third invention).

According to this, based on the viewing log information obtained from the television device corresponding to the selected survey target viewers as described above, it is possible to determine whether each survey target viewer watched the survey target TV broadcast or not. is estimated, and based on the estimation results, it becomes possible to estimate with high reliability the viewing status of the TV broadcast to be investigated in the area to be investigated for each attribute of the viewer.

Furthermore, the viewing information processing method of the present invention provides a television broadcast receiver and viewing data capable of outputting viewing log information indicating which channel or broadcast station series television broadcast was viewed and when through the receiver. For each of a plurality of television devices each having an output device and belonging to a predetermined survey target area, a predetermined unit time is calculated for each attribute included in the viewer attribute configuration of each television device. a first step of obtaining the viewing time of the television broadcast in the period of time;
a second step of identifying a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time for each attribute obtained in the first step;
Based on the comparison between the frequency distribution of the number of viewers for each attribute identified in the second step and the standard frequency distribution for each attribute predetermined in the survey target area, the The third step is to select viewers to survey the viewing situation in the survey target area.
In the third step, for each attribute, the viewers to be surveyed are selected such that the frequency distribution of the number of viewers to be surveyed with respect to viewing time is a distribution that matches the frequency distribution of the standard. (4th invention).
According to the fourth invention, the same effects as the first invention can be achieved.

The viewing information processing program of the present invention also provides a viewing information processing program capable of outputting viewing log information indicating when and when television broadcasting of which channel or broadcasting station series was viewed through a television broadcasting receiver and the television broadcasting receiver. For each of a plurality of television devices each having a data output device and belonging to a predetermined survey target area, a predetermined unit is set for each attribute included in the viewer attribute configuration of each television device. A first process of specifying a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time when the viewing time of the television broadcast in a period of time width is given;
Based on the comparison between the frequency distribution of the number of viewers for each attribute identified by the first process and the standard frequency distribution for each attribute predetermined in the survey target area, the The computer is configured to cause the computer to execute a second process of selecting viewers to be surveyed regarding viewing conditions in the survey target area, and
The second process selects the survey target viewers for each attribute so that the frequency distribution of the survey target viewer number with respect to the viewing time is a distribution that matches the reference frequency distribution. The method is characterized in that it is configured to be executed by the computer (fifth invention).
According to the fifth invention, the same effects as the first invention can be achieved by causing a computer to execute the visual information processing program.

FIG. 1 is a diagram showing an overall system in an embodiment of the present invention. FIG. 2 is a block diagram for explaining processing of an attribute configuration estimating unit of the viewing information processing device shown in FIG. 1. FIG. FIG. 2 is a block diagram for explaining processing of a viewing time estimating unit of the viewing information processing device shown in FIG. 1. FIG. 2 is a graph for explaining the processing of the frequency distribution specifying unit and the survey target viewer selecting unit shown in FIG. 1;

One embodiment of the present invention will be described below with reference to FIGS. 1 to 4. Referring to FIG. 1, the system described in this embodiment includes a viewing information processing device 1 that executes processing related to, for example, investigating the viewing status of television broadcasts. The viewing information processing device 1 is composed of, for example, one or more computers. The computer includes a processor such as a CPU (not shown), a memory (storage device), an interface circuit, a communication device, and the like. The viewing information processing device 1 then manages a plurality of device-based households 20 belonging to the target area for surveying the viewing situation (for example, a prefecture-based area or a combined area of multiple prefectures such as the Kanto area and the Kinki area). Viewing data regarding viewing of television broadcasts in households 20 for each device can be obtained from the above. The viewing data is data that includes viewing log information and the like indicating what channel (or which broadcasting station series) television broadcasting was viewed and when.

Here, in this embodiment, each "household by device 20" includes a television device 23 including a television broadcast receiver 21 and a viewing data output device 22 capable of outputting viewing data regarding viewing of the television broadcast. , means a household whose members include one or more viewers of the television device 23 (more specifically, one or more viewers who can view the television broadcast received by the receiver 21 of the television device 23). In other words, the device-specific household 20 is configured as a set of a television device 23 and a viewer of the television device 23.

In this case, one device-specific household 20 is associated with each television device 23. Therefore, even if a certain dwelling unit is equipped with a plurality of television devices 23, one device-based household 20 is associated with each of the plurality of television devices 23. In this case, each device-specific household 20 corresponding to each of the plurality of television devices 23 may include the same members as viewers. In other words, one or more members of any device-based household 20 may be members of another device-based household 20.

The television device 23 of each device-based household 20 may be constituted by a television, or may be constituted by a television and a recording device connected thereto. The viewing data output device 22 of the television device 23 includes, for example, a processor such as a microcomputer (not shown), a memory, an interface circuit, a communication device, and the like. The viewing data output device 22 is capable of detecting the channel of the television broadcast viewed through the television device 23 including the device 22, and also detects the date and time when the television broadcast of the channel was viewed (in detail, the channel It is possible to detect the viewing start and viewing end date and time of the television broadcast of the TV broadcast, and to generate viewing log information for the device-specific households 20 (hereinafter referred to as device-specific viewing log information) from this detection information. is possible. In other words, the device-specific viewing log information is the viewing log information of all members included in the device-specific household 20.

Then, the viewing data output device 22 transmits the viewing data including the generated device-specific viewing log information to the television or recording device constituting the television device 23 via an external network NW constituted by the Internet, telephone line network, etc. It is possible to transmit the information periodically (or in response to a request from the server) to the manufacturer's server (not shown). In this case, the viewing data transmitted from the viewing data output device 22 includes, in addition to device-specific viewing log information, location information (for example, postal code, information indicating three digits) and identification information of the television device 23 are included. Note that the identification information of the television device 23 can also be used as identification information of the device-specific household 20 that includes the television device 23.

The viewing information processing device 1 includes a viewing data acquisition unit 11, an attribute configuration estimation unit 12, a viewing time acquisition unit 13, and a frequency distribution identification unit 14 as functions realized by the implemented hardware configuration and program (software configuration). , a survey target viewer selection section 15 , and a viewing status estimation section 16 . Hereinafter, the overall processing of the viewing information processing device 1 will be explained in conjunction with the details of each of these functional units.

The viewing data acquisition unit 11 can communicate with a server (not shown) of the manufacturer of each television device 23 in the device-based household 20, and by communicating with the server (not shown), the viewing data acquisition unit 11 can communicate with the server (not shown) of the manufacturer of each television device 23 of the device-based household 20. It is possible to obtain viewing data. The viewing data acquisition unit 11 has a function as a viewing log information acquisition unit in the present invention.

Note that when the viewing information processing device 1 can communicate with the viewing data output device 22 of the device-based household 20, the viewing data acquisition unit 11 transmits the viewing data of the television device 23 of the device-based household 20 to the television. The viewing data may be directly acquired from the viewing data output device 22 of the device 23. Additionally, the viewing information processing device 1 may acquire viewing data of the television device 23 from each manufacturer via an appropriate storage device.

In this embodiment, the viewing information processing device 1 uses the viewing data acquired by the viewing data acquisition unit 11 for each device-specific household 20 in the survey target area, and the attribute configuration estimation unit 12 and the viewing time information acquisition unit. Each of the 13 processes is executed sequentially.

The attribute configuration estimating unit 12 determines the device-specific household from the device-specific viewing log information for a predetermined period (for example, one month, several months, one year, etc.) output from the television device 23 of the device-specific household 20. This is a functional unit that estimates the attribute configuration indicating which attributes of members are included in the device 20 (in other words, the attribute configuration of the viewers of the television device 23 of the device-specific household 20).

Here, the attributes of the members (viewers of the television device 23) of each device-based household 20 are classified into multiple types of attributes depending on the age and gender of the members, for example. For example, multiple types of attributes such as children under y1 years old, men over y1 years old and under y2 years old, women over y1 years old and under y2 years old, men over y2 years old, and women over y2 years old. being classified. Hereinafter, the number of types of attributes will be N types, and each of the N types of attributes will be appropriately expressed as At(i) (i=1, 2, . . . , N). Note that the attributes of the members of each device-based household 20 can be classified not only according to age and gender, but also according to various parameters such as occupation and educational background.

As shown in FIG. 2, the attribute configuration estimating unit 12 estimates the attribute configuration of the members of each device-based household 20 using a first model that has been subjected to machine learning processing in advance. Here, the first model is constructed in advance so that the attribute structure of the members of the device-specific household 20 can be estimated from the device-specific viewing log for a predetermined period of any device-specific household 20 belonging to the survey target area. This is a model that has undergone learning processing. In the machine learning process for the first model, viewing log information for each sample household obtained from people meters installed in each of a plurality of sample households with known attribute configurations and the attribute configuration for each sample household are learned. Used as data. A known algorithm can be used as the algorithm for the machine learning process.

In this case, in the present embodiment, the first model calculates N types of attributes At(i) (i=1, 2, ..., N) from the device-specific viewing log information for a predetermined period of each device-specific household 20. For each device, it is configured to be able to specify the attribute-specific existence probability, which is the probability that a member of each attribute At(i) exists in the device-specific household 20. As such a first model, for example, a model similar to the mathematical model for determining household composition in Patent Document 1 may be adopted. However, the first model may be any other form of model as long as it is possible to specify the existence probability by attribute (or an index value similar to this) from viewing log information by device for a predetermined period of time in households 20 by device. There may be.

Then, the attribute configuration estimating unit 12 determines which attributes (or whose existence probabilities by attribute are higher than a predetermined threshold) are identified by the first model and whose existence probabilities by attribute are higher than a predetermined threshold (for example, 0.5). (preferably, the attributes that match the threshold value) are estimated as the attributes of the members of the device-based household 20. As an example, FIG. 2 illustrates the processing of the attribute configuration estimation unit 12 for one device-based household 20 (in FIG. 2, the device-based household 20 whose identification information ID is x1). In the block diagrams shown in FIG. 2 and FIG. 3, which will be described later, a processing execution section is shown in a thick line frame, and a data output section or data is shown in a thin line frame.

In the example shown in FIG. 2, from the device-specific viewing log information for a predetermined period of device-specific household 20 whose identification information ID is It is specified as follows. In this example, among the N types of attributes At(i) (i=1, 2, ..., N), the existence probabilities for each attribute of At(1), At(3), and At(N) are given as follows. (here, for example, 0.5), and the existence probabilities of each of the other attributes At(2), At(4) to At(N-1) are lower than the threshold. It is a probability.

In this case, the attribute configuration estimating unit 12 determines that the attributes At(1), At(3), and At(N) whose existence probabilities by attribute are higher than the threshold are The attributes At(2), At(4) to At(N-1), which are estimated to be the attributes of the device-based household 20 and whose existence probabilities by attribute are lower than the threshold, must not be the attributes of the members of the device-based household 20. presume. As a result, the attribute structure of the members of the device-based household 20 is estimated.

In this way, the attribute composition estimating unit 12 determines whether the members (viewers) of each attribute are in the device-specific household 20 based on the level of the attribute-specific presence probability specified by the first model with respect to the predetermined threshold. By estimating whether the device exists in the household 20, the attribute structure of the members of the household 20 for each device is estimated.

After the viewing information processing device 1 executes the processing of the attribute configuration estimation section 12, the viewing information processing device 1 next executes the processing of the viewing time acquisition section 13. In this embodiment, the viewing time acquisition unit 13 acquires a predetermined unit time width by viewers of each attribute for each attribute included in the attribute configuration estimated by the attribute configuration estimation unit 12 for each device-based household 20. This is a functional unit that obtains the information by estimating the viewing time of television broadcasts in a period, for example, the viewing time per day. Note that the above unit time width is not limited to one day, but may be a time width of one week, one month, or the like.

In this case, the viewing time acquisition unit 13 determines, for each device-specific household 20, from the viewing log information of each device-specific household 20 that the viewers of each attribute included in the attribute configuration of the device-specific household 20 are connected to the channel (or Attributes for generating (estimating) attribute-specific viewing information indicating whether or not a television broadcast corresponding to an arbitrary set of a broadcasting station series (broadcasting station series) and date/time data indicating month, day of the week, time zone, etc. was viewed using a second model. The separate viewing information generation unit 13a aggregates the viewing time (total viewing time in a period of a predetermined unit time width) for each attribute included in the attribute configuration of the device-specific household 20 from the attribute-specific viewing information. The viewing time totaling unit 13b is included.

Furthermore, a television broadcast that corresponds to a set of a channel (or broadcasting station series) and date and time data indicating the month, day of the week, and time zone is a television broadcast that corresponds to a pair of channel (or broadcasting station series) and date and time data indicating the month, day of the week, and time zone. means a television broadcast that is broadcast. Further, the time zone in the date and time data is, for example, a time zone divided by a predetermined time width unit (10 minutes, 30 minutes, 1 hour, etc.).

Here, the second model used by the attribute-specific viewing information generating section 13a is a model created separately for each of the N types of attributes At(i) (i=1, 2, . . . , N). The second model corresponding to each attribute At(i) is a device to which a member (viewer) of the attribute At(i) belongs when a set of channel (or broadcasting station series) and date/time data is specified. From the device-specific viewing log for a predetermined period of time in another household 20, it is determined that the viewer with the attribute At(i) has received a TV broadcast (hereinafter, channel This is a model that has been subjected to machine learning processing in advance so that it can specify the probability of viewing a date and time specified broadcast (hereinafter referred to as attribute-specific viewing probability).

In addition, in FIG. 2, based on the viewing log information of a device-specific household 20 having members (viewers) with a certain attribute At(n), a channel/date/time specified broadcast is determined by the second model corresponding to the attribute At(n). It is shown that the viewing probability by attribute, which is the probability that a member of the attribute At(n) viewed the video, is specified. The same applies to second models corresponding to other attributes.

In the machine learning process for the second model as described above, viewing log information of each member of each sample household obtained from people meters installed in each of a plurality of sample households with known attribute configurations and each sample household are used. The attribute configuration for each is used as learning data. A known algorithm can be used as the algorithm for the machine learning process. Further, as the second model, for example, a model similar to the mathematical model for personal viewing determination in Patent Document 1 may be adopted. However, in the second model, the channel (or broadcasting station series) and date and time data are arbitrarily specified from the device-specific viewing log information for a predetermined period of the device-specific household 20 for each attribute of the members of the device-specific household 20. Any other type of model may be used as long as it can specify the viewing probability by attribute (or an index value similar to this) regarding the specified channel/date and time broadcast.

Then, the attribute-specific viewing information generation unit 13a generates the attribute-specific viewing information estimated by the second model for the channel/date/time specified broadcast for each attribute constituting the attribute configuration of the device-specific household 20, and the device-specific household 20. The system is configured to determine (estimate) whether or not members of each attribute have viewed the specified channel/date/time broadcast from the 20 device-specific viewing log information.

Specifically, the attribute-by-attribute viewing information generation unit 13a calculates, for each attribute of the members of the device-by-device household 20, the attribute-by-attribute viewing probability (probability value) specified by the second model for channel/date/time specified broadcasting. is higher than a predetermined threshold value (for example, 0.5 or higher), and at the broadcast date and time indicated by the date and time data of the channel/date and time specified broadcast, the actual broadcast time on the channel (or broadcast station series) of the channel/date and time specified broadcast. If the condition that viewing was confirmed from the viewing log information of the device-specific household 20 is met, it is determined that the channel/date/time specified broadcast was viewed by a member of the attribute, and the condition is met. If this is not satisfied, it is determined that there was no channel/date/time designated broadcast by the member with the relevant attribute.

The viewing time acquisition unit 13 sends the attribute-specific viewing information generation unit 13a configured as described above for each attribute included in the attribute configuration of each device-specific household 20 within a predetermined period (for example, for January). Specify all sets of channels (or broadcast station series) and date and time data in sequence (within the specified period), and check whether or not the channel/date and time specified broadcast corresponding to each of the sets has been viewed for each device. Estimation is made from the device-specific viewing log of household 20 for a predetermined period.

Next, the viewing time acquisition section 13 executes the processing of the viewing time aggregation section 13b. This viewing time aggregation unit 13b calculates the sum of the time widths of all channel/date and time specified broadcasts that are estimated to have been watched for each attribute of the members of the household 20 for each device, and calculates the total time The viewing time per day is estimated by dividing the width by the number of days within the predetermined period. As a result, the viewing time per day is acquired for each attribute of the members (viewers) of the household 20 for each device.
In this embodiment, the processing of the viewing time estimation unit 13 is executed as described above.

The viewing information processing device 1 executes the processing of the attribute composition estimation unit 12 and the viewing time acquisition unit 13 as described above for each device-based household 20 in the survey target area, and then executes the processing of the frequency distribution identification unit 14. do. This frequency distribution specifying unit 14 determines the frequency distribution (for details, , frequency distribution of the number of viewers with respect to viewing time). In this case, the viewing time is divided into m types of time ranges T(k) (k=1, 2, . . . , m). For example, T(1)=0, 0<T(2)≦Tx_2, Tx_2<T(3)≦Tx_3, ..., Tx_m-2<T(m-1)≦Tx_m-1, Tx_m-1<T It is divided into m types of time ranges, such as (m). Note that the boundary values Tx_2, Tx_3, ..., Tx_m-1 of adjacent time ranges are predetermined constant values.

Then, the frequency distribution specifying unit 14 determines the total number of viewers who have viewing time belonging to each time range T(k) for each of the N types of attributes At(i) (i=1, 2,...,N). (total number in the survey target area) is determined as the frequency corresponding to the time range T(k). For example, in the entire device-based households 20 estimated to have viewers (members) with a certain attribute At(n), the viewing time is T(1), T(2), ..., T(m). If the total number of viewers (members of attribute At(n)) belonging to each is X1, X2, ..., Xm, then X1, X2, ..., Xm are respectively for attribute At(n). is determined as the frequency corresponding to the viewing time of each time range T(1), T(2), . . . , T(m).

In this way, the frequency distribution specifying unit 14 specifies the frequency distribution regarding viewing time for each of the N types of attributes At(i) (i=1, 2, . . . , N). The solid line bar graph in FIG. 4 exemplifies the frequency distribution of viewing times specified as described above with respect to one of the attributes At(i). In this example, the number m of types of time range T(k) is, for example, 10 types. For other attributes, the frequency distribution of viewing times is similarly specified.

To supplement, the number m of types of time range T(k) or the boundary values Tx_2, Tx_3, ..., Tx_m-1 of adjacent time ranges are N types of attributes At(i) (i=1, 2, ... , N) need not be the same for all attributes At(i), and may be different depending on the type of attribute At(i). For example, the number m of types of time range T(k) corresponding to attributes whose viewing time tends to be dispersed over a wide range is determined from the number m of types of time range T(k) corresponding to attributes with relatively low variance of viewing time. You can also increase the number.

The viewing information processing device 1 then executes the processing of the survey target viewer selection unit 15. The survey target viewer selection unit 15 selects targets for surveying viewing conditions such as viewer ratings of television broadcasts for each of the N types of attributes At(i) (i=1, 2, ..., N). This is a functional unit that selects survey target viewers who are viewers who

In this case, the survey target audience selection unit 15 selects the frequency distribution specified by the frequency distribution identification unit 14 for each of the N types of attributes At(i) (i=1, 2,..., N), and the frequency distribution specified by the frequency distribution identification unit 14 and each Audiences to be surveyed are selected based on a comparison with a predetermined standard frequency distribution corresponding to the attribute At(i).

Specifically, in this embodiment, the composition of each sample household is obtained through a people meter etc. from each of a plurality of sample households (households in which the attributes of each member are known) selected in advance in the survey target area. The frequency distribution of viewing time for each attribute At(i) in the entire sample household is specified in advance from the viewing log information of each member, and this frequency distribution is used as the frequency distribution of the above-mentioned standard. Here, the sample households are selected as households that represent the viewing status of television broadcasting in the survey target area, so the frequency distribution of viewing time for each attribute At(i) in the sample households as a whole is based on the survey target area. It can be considered that it corresponds to the frequency distribution of actual viewing times for each attribute At(i) in the region.

Then, for each attribute At(i), the research target viewer selection unit 15 sets the frequency distribution of the viewing time of the selected research target viewers to match (including the case where it almost matches) the frequency distribution of the standard. , select the audience for the survey. Such selection can be performed for each attribute At(i), for example, as follows.

Hereinafter, any one of the N types of attributes At(i) (i = 1, 2, ..., N) will be referred to as a focused attribute At(x), and this focused attribute At(x) will be the subject of investigation. The process for selecting viewers will be described below. In the following explanation, the frequency distribution of the viewing time specified for each attribute At(i) by the frequency distribution specifying unit 14 will be defined as a pre-selection frequency distribution, and each time range T(k ) (k = 1, 2, ..., m) is the frequency before selection Xa_k, the frequency distribution of the viewing time of the survey target viewers selected for each attribute At(i) is the frequency distribution after selection, and after the selection Of the frequency distribution, the frequency in each time range T(k) (k=1, 2, . . . , m) is referred to as the selected frequency Xb_k. Further, in the standard frequency distribution, the frequency (normalized frequency) corresponding to each time range T(k) (k=1, 2, . . . , m) is referred to as the standard frequency Xs_k. The frequency distribution shown by the solid bar graph in FIG. 4 is used as an example of the pre-selection frequency distribution regarding the attribute of interest At(x), and as an example of the frequency distribution of the standard corresponding to the attribute of interest At(x), The frequency distribution shown by the dashed-dotted line with the open circles in FIG. 4 as the breaking points is used.

(Step 1)
The survey target viewer selection unit 15 selects m (here, 10) time ranges T(1) to T(10), respectively, in the pre-selection frequency distribution of viewers of the attribute of interest At(x). The value obtained by dividing the pre-selection degree Xa_k by the standard frequency Xs_k corresponding to each of the m time ranges T(1) to T(10) in the standard frequency distribution (hereinafter referred to as the standard frequency The ratio Xa_k/Xs_k) is calculated. Then, from the m (10) time ranges T(1) to T(10), the time range corresponding to the smallest standard frequency ratio Xa_k/Xs_k (excluding zero) (hereinafter, this time range is The minimum time range (referred to as T(min)) is specified. For example, in the example of the pre-selection frequency distribution (the frequency distribution shown by the solid bar graph) shown in FIG. Among the frequencies Xa_1 to Xa_10, the reference frequency ratio Xa_9/Xs_9 (>0) corresponding to the time range T(9) is the smallest, so T(9) is specified as the frequency ratio minimum time range T(min).

(Step 2)
The survey target viewer selection unit 15 calculates the ratio of the frequency in each of the other time ranges to the frequency in the minimum frequency ratio time range T (min) in the standard frequency distribution corresponding to the attribute of interest At(x). Calculated as For example, in the standard frequency distribution illustrated in FIG. 4, each time range T(1), T(2), . The reference ratios corresponding to .

(Step 3)
The survey target viewer selection unit 15 calculates the pre-selection frequency Xa_9 in the minimum frequency time range T(min) (=T(9)) in the pre-selection frequency distribution of the viewer of the focused attribute At(x) to the minimum frequency ratio. It is set as the temporary target value of the selected frequency Xb_9 in the time range T(min), and also in other time ranges T(1), T(2). As the tentative target values of the post-selection frequencies Xb_1, Xb_2, . The tentative target value of the post-selection frequency Xb_9 (=pre-selection frequency Xa_9) in other time ranges T(1), T(2). ..., T(8), and T(10) each by the corresponding standard ratio.

Therefore, time ranges T(1), T(2) other than the frequency ratio minimum time range T(min) (=T(9)). ..., T(8), T(10) is expressed as T(y) (y is 1, 2,..., 8, 10), then the time range T As the tentative target value of the post-selection frequency Xb_y corresponding to (y), the tentative target value of the post-selection frequency Xb_9 (=pre-selection frequency Xa_9) in the frequency ratio minimum time range T(min) (=T(9)), An integer portion of the value obtained by multiplying the time range T(y) by the corresponding reference ratio (=Xs_y/Xs_9) is set.

(Step 4)
The survey target viewer selection unit 15 determines that the tentative target value of the post-selection frequency Xb_k set in step 3 is set for each time range T(k) (k=1, 2, ..., 10). It is determined whether the value is less than or equal to the pre-selection frequency Xa_k corresponding to k) (temporary target value of the post-selection frequency Xb_k≦pre-selection frequency Xa_k). Note that regarding the frequency ratio minimum time range T(min) (=T(9)), the result of the judgment process is inevitably positive, so the judgment process regarding the frequency ratio minimum time range T(min) is May be omitted.

(Step 5)
If the judgment result in step 4 is positive for all time ranges T(1) to T(10), the survey target viewer selection unit 15 selects the post-selection frequency Xb_k in each time range T(k). The tentative target value of is directly determined as the target value of the selected frequency Xb_k. For example, in FIG. 10, the determination result in step 4 is positive for all time ranges T(1) to T(10). In this case, the tentative target value of the post-selection frequency Xb_k in each of the time ranges T(k) (k=1, 2, . . . , 10) is determined as the target value of the post-selection frequency Xb_k.

(Step 6)
If the judgment result in step 4 is negative for any one or more of the time ranges T(1) to T(m), the survey target audience selection unit 15 selects the minimum frequency ratio. As a new temporary target value of the post-selection frequency Xb_9 in the time range T(min) (=T(9)), a value smaller than the pre-selection frequency Xa_9 in the frequency ratio minimum time range T(min) is set.

In this case, the new provisional target value of the post-selection frequency When setting the tentative target value of the frequency after selection in the time range of , it is set to satisfy the condition that the judgment result in step 4 is positive for all time ranges T(1) to T(10). Ru. In addition, the new tentative target value of the post-selection frequency Xb_9 in the frequency ratio minimum time range T(min) is as close as possible to the pre-selection frequency Xa_9 in the frequency ratio minimum time range T(min) within the range that satisfies the above conditions. is set to the value.

Setting a new temporary target value for the post-selection power Xa_9 in the minimum frequency ratio time range T(min) means, for example, that the provisional target value is changed to the pre-selection power Xa_9 until the above condition is satisfied. This can be achieved by repeating the process of decreasing the value by a predetermined amount.

Then, after setting the new provisional target value of the post-selection frequency Xb_k in each time range T(k) so as to satisfy the above conditions, the survey target viewer selection unit 15 performs the same steps as in step 5 above. The provisional target value of the post-selection frequency Xb_k in the time range T(k) is directly determined as the target value of the post-selection frequency Xb_k in each time range T(k).

(Step 7)
After determining the target value of the post-selection frequency Xb_k in each time range T(k) in step 5 or step 6, the survey target audience selection unit 15 selects the time range T(k) (k=1, 2,... . The number of viewers corresponding to the difference between the frequency Xa_k and the target value of the post-selection frequency Xb_k is deleted, and the viewers remaining after deletion are selected as viewers to be investigated for the focused attribute At(x). In this case, viewers to be deleted in each time range T(k) are selected at random, for example. As a result, the total number of survey target viewers for each time range T(k) (k = 1, 2, ..., m) (survey target viewers of the focused attribute At(y)) becomes the frequency Xb_k after selection. are selected to match the target value.

For example, in FIG. 4, in each of the time ranges T(k) (k = 1, 2, ..., 10) where the pre-selection frequency is larger than the target value of the post-selection frequency, the frequency of the gray part is A corresponding number of viewers will be removed. As a result, for the attribute of interest At(x), the survey target viewers are selected such that the post-selection frequency distribution regarding viewing time matches the standard frequency distribution. Then, for other attributes as well, viewers to be surveyed are selected in the same manner as above. Note that the selected survey target viewers are stored in association with the television device 23 of the device-specific household 20 to which each viewer belongs.
In this embodiment, the processing of the survey target viewer selection unit 15 is executed as described above.

The viewing information processing device 1 selects the survey target viewers for each attribute At(i) as described above, and then executes the processing of the viewing status estimating unit 16 using the survey target viewers. The viewing status estimating unit 16 calculates viewing status data (viewer ratings) for each of the N types of attributes At(i) regarding the television broadcasting to be investigated (hereinafter referred to as the surveyed broadcasting) of the viewing status in the surveyed area. This is a processing unit that estimates the corresponding data).

In this case, the viewing status estimating unit 16 calculates the viewing log information for a predetermined period of the device-specific household 20 to which each survey target viewer belongs, and the channel (or broadcast station series) and date and time data of the survey target broadcast. By executing the same process as the attribute-specific viewing information generation unit 13a of the time estimating unit 13 (processing using the second model corresponding to the attributes of the survey target viewer), the survey target viewer can Estimate whether or not you have watched the video.

Then, after estimating whether or not all survey target viewers in the survey target area watched the survey target broadcast, the viewing status estimating unit 16 conducts a survey for each attribute At(i) based on the estimation result. The viewing status data of the target broadcast is calculated using, for example, the following equation (1).

Viewing status data regarding attribute At(i)=m(i)/M(i)...(1)

Here, M(i) is the total number of surveyed viewers with attribute At(i), and m(i) is the number of surveyed viewers with attribute At(i) who are estimated to have watched the surveyed broadcast. This is the total number of surveyed viewers.

Thereby, it is possible to obtain viewing status data as data corresponding to the viewing rate for each attribute At(i) in the survey target area. In this case, the surveyed viewers are selected so that the frequency distribution after selection regarding viewing time matches the standard frequency distribution based on viewing data for sample households in the survey area, so highly reliable viewing data can be obtained. Obtainable.

In addition, in the embodiment described above, the provisional target value of the post-selection frequency Xb_k set as described above for each time range T(k) is the same as the temporary target value The provisional target value of the post-selection power Xb_k in each time range T(k) was determined as the target value of the post-selection power Xb_k, with the necessary condition that the provisional target value of the post-selection power Xb_k≦the pre-selection power Xa_k.

However, only the provisional target value of the post-selection frequency corresponding to each of the partial time ranges of the time ranges T(1) to T(10) is the pre-selection frequency corresponding to each of the partial time ranges. Even if it is larger than , if the difference between the provisional target value of the post-selection frequency and the pre-selection frequency corresponding to each of the partial time ranges is sufficiently small (if it is below a predetermined threshold) , the target value of the post-election frequency corresponding to each of the partial time ranges is set to match the pre-selection frequency, and the target value of the post-selection frequency corresponding to each of the partial time ranges is set to match the pre-selection frequency. Regarding the time range in which the provisional target value is equal to or less than the pre-selection power, the provisional target value of the post-selection power may be directly set as the target value.

Furthermore, in the embodiment described above, the viewing information processing device 1 includes the viewing status estimating section 16, but the viewing information processing device according to the present invention may not include the viewing status estimating section 16. In this case, the viewing status estimation unit 16 may be provided in a device different from the viewing information processing device.

Further, in the embodiment, the attribute configuration and attribute-specific viewing information of each device-specific household 20 are estimated from the device-specific viewing log information, and each attribute of the viewer of each device-specific household 20 is estimated from the estimated attribute-specific viewing information. The viewing time for each session (viewing time in a period of a predetermined unit time width) was estimated. However, in the present invention, the method of obtaining the viewing time for each attribute of the viewer in each device-based household 20 is not limited to the above method. For example, each device household 20 is equipped with an appropriate device capable of measuring or estimating viewing time for each attribute of viewers in each device household 20, and the device is used to Viewing time for each attribute may also be acquired. Alternatively, for example, each device-specific household 20 is equipped with an appropriate device that can generate and output viewing log information for each attribute of the viewer in each device-specific household 20, and the viewing log information output from that device is , the viewing time for each attribute of the viewer in the household 20 for each device may be estimated.

DESCRIPTION OF SYMBOLS 1... Viewing information processing device, 13... Viewing time acquisition part, 14... Frequency distribution identification part, 15... Survey target viewer selection part, 16... Viewing status estimation part.

Claims (5)

A plurality of television devices each comprising a television broadcast receiver and a viewing data output device capable of outputting viewing log information indicating which channel or broadcast station series television broadcast was viewed and when through the receiver. For each of a plurality of television devices belonging to a predetermined survey target area, the viewing time of television broadcasting during a period of a predetermined unit time width is obtained for each attribute included in the viewer attribute configuration of each television device. a viewing time acquisition unit,
a frequency distribution identification unit that identifies a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time for each attribute acquired by the viewing time acquisition unit;
Based on a comparison between the frequency distribution of the number of viewers for each attribute specified by the frequency distribution specifying unit and the standard frequency distribution for each attribute predetermined in the survey target area, for each attribute, and a survey target audience selection unit that selects viewers to survey the viewing situation in the survey target area,
The survey target viewer selection unit selects the survey target viewers for each attribute so that the frequency distribution of the number of survey target viewers with respect to viewing time matches the frequency distribution of the standard. A viewing information processing device characterized in that it is configured to. The viewing information processing device according to claim 1,
The standard frequency distribution is based on viewing data obtained from each of a plurality of sample households selected in advance in the survey target area, and including viewing log information for each viewer of each sample household. A viewing information processing device characterized by a set frequency distribution. The viewing information processing device according to claim 1 or 2,
It further includes a viewing status estimating unit that estimates the viewing status of a predetermined survey target television broadcast, and the viewing status estimating unit is configured to estimate whether each survey target viewer selected by the survey target viewer selection unit It has a function of estimating whether or not the viewer viewed the survey target TV broadcast from the viewing log information acquired by the viewing log information acquisition unit regarding the TV device corresponding to the viewer, and also The viewing information processing device is configured to estimate the viewing status of the television broadcast to be surveyed for each attribute of the viewer to be surveyed, based on the result of the estimation regarding the viewer to be surveyed. . A plurality of television devices each comprising a television broadcast receiver and a viewing data output device capable of outputting viewing log information indicating which channel or broadcast station series television broadcast was viewed and when through the receiver. For each of a plurality of television devices belonging to a predetermined survey target area, the viewing time of television broadcasting during a period of a predetermined unit time width is obtained for each attribute included in the viewer attribute configuration of each television device. The first step is to
a second step of identifying a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time for each attribute obtained in the first step;
Based on the comparison between the frequency distribution of the number of viewers for each attribute identified in the second step and the standard frequency distribution for each attribute predetermined in the survey target area, the The third step is to select viewers to survey the viewing situation in the survey target area.
In the third step, for each attribute, the viewers to be surveyed are selected such that the frequency distribution of the number of viewers to be surveyed with respect to viewing time is a distribution that matches the frequency distribution of the standard. Characteristic viewing information processing method. A plurality of television devices each comprising a television broadcast receiver and a viewing data output device capable of outputting viewing log information indicating which channel or broadcast station series television broadcast was viewed and when through the receiver. For each of a plurality of television devices belonging to a predetermined survey target area, the viewing time of television broadcasting in a period of a predetermined unit time width is given for each attribute included in the viewer attribute configuration of each television device. a first process of identifying a frequency distribution of the number of viewers with respect to viewing time for each attribute in the survey target area based on the viewing time;
Based on the comparison between the frequency distribution of the number of viewers for each attribute identified by the first process and the standard frequency distribution for each attribute predetermined in the survey target area, the The computer is configured to cause the computer to execute a second process of selecting viewers to be surveyed regarding viewing conditions in the survey target area, and
The second process selects the survey target viewers for each attribute so that the frequency distribution of the survey target viewer number with respect to the viewing time is a distribution that matches the reference frequency distribution. A program for processing viewing information, characterized in that the program is configured to be executed by the computer.

Images