JP7743662B1 - Viewing log information processing device and viewing log information processing method - Google Patents

Abstract

The present invention extracts viewing status information that reflects viewing trends using viewing log information.
[Solution] The viewing log information processing according to the present invention divides viewing status information into multiple PM group data, performs clustering processing, and applies the viewing log information to multiple cluster models obtained by the clustering processing, thereby bringing the viewing trends of the viewing log information closer to the viewing trends of the viewing status information.
[Selected Figure] Figure 3

Description

The present invention relates to a viewing log information processing device and a viewing log information processing method.

Program ratings are generally calculated by installing dedicated devices (such as people meter systems or online meter systems; hereafter referred to as people meters, etc.) to measure viewing status in a sampling of multiple households, and collecting and analyzing viewing status information for programs viewed on television sets, etc.

Furthermore, as shown in Patent Document 1, it is proposed to estimate attribute-specific viewing information by applying viewing log information to be analyzed obtained from each television device in the survey area to a prediction model obtained by learning from viewing log information in the survey area and viewing information obtained from people meters or the like installed in sample households in the survey area. Patent Document 1 also narrows down the target sample in the sample viewing log information, and matches the viewing minute distribution of the narrowed-down viewing log information with the data obtained by a dedicated device such as a people meter (survey target viewer selection process), thereby aggregating the viewing log information (bringing the distribution of the viewing log information closer to the distribution of the data from the dedicated device), and calculating individual viewing ratings based on that.

Japanese Patent Application Laid-Open No. 2023-153658

However, because the aggregation of viewing log information in Patent Document 1 is based on absolute viewing volume, there is an issue of a large number of samples with low viewing volume and a small number of samples with high viewing volume. Furthermore, because the current system considers viewing trends for all broadcasting stations, rather than individual broadcasting stations, discrepancies can arise when comparing this with data from the dedicated device, whereby even though the data from the dedicated device shows that one broadcasting station has the most viewers, the viewing log information shows that a different broadcasting station has the most viewers.

In light of this situation, the present invention proposes a technology for aggregating viewing log information that can better reflect the viewing trends of viewing status information (technology that brings viewing log information closer to data generated by dedicated devices).

In order to solve the above problems, the present invention provides, as an example,
A viewing log information processing device that executes a viewing log information aggregation process to bring the viewing trends of viewing log information obtained from television devices installed in each household in a survey area closer to the viewing trends based on viewing situation information obtained from dedicated devices installed in a sample household in the survey area,
a storage device that stores a program for executing the viewing log information aggregation process;
a control device that reads the program from the storage device and executes it;
The control device proposes a viewing log information processing device that divides the viewing status information into multiple PM group data, performs clustering processing, and applies the viewing log information to multiple cluster models obtained by the clustering processing, thereby bringing the viewing trends of the viewing log information closer to the viewing trends of the viewing status information.

Further features related to the present invention will become apparent from the description and accompanying drawings of this specification, and the aspects of the present invention may be realized and realized by the elements and combinations of various elements and aspects set forth in the following detailed description and the appended claims.
The descriptions in this specification are exemplary and illustrative only and are not intended to limit the scope or application of the present invention in any way.

The technology of the present invention makes it possible to extract viewing log information that more closely reflects (closes to) the viewing trends of viewing status information.

1 is a diagram illustrating an example of a schematic configuration of a viewing log information aggregation processing system according to an embodiment of the present invention. 10 is a flowchart illustrating details of a viewing log information aggregation process according to an embodiment of the present invention. 3 is a schematic diagram showing an example of processing in each step of the flowchart of FIG. 2. FIG. 10 is a diagram illustrating an example of a block configuration for executing an attribute configuration estimation process. FIG. 10 is a diagram illustrating an example of a block configuration for executing an individual separation process.

Embodiments of the present invention will be described below with reference to the accompanying drawings. In the accompanying drawings, functionally identical elements may be designated by the same numerals. Note that the accompanying drawings show specific embodiments and implementation examples in accordance with the principles of the present invention, but these are intended to aid in understanding the present invention and should not be used to interpret the present invention in any way as limiting.

In this embodiment, the present invention is described in sufficient detail to enable those skilled in the art to practice the invention, but it should be understood that other implementations and forms are possible, and that changes to the configuration and structure and substitutions of various elements are possible without departing from the scope and spirit of the technical concept of the present invention. Therefore, the following description should not be interpreted as being limited to this.

<Configuration example of viewing log information correction processing system>
Fig. 1 is a diagram showing an example of the schematic configuration of a viewing log information aggregation processing system according to this embodiment. The viewing information processing system includes a viewing log information aggregation processing device 100, television manufacturer 1 server devices 300_1 to 300_N connected to the viewing log information aggregation processing device 100 via a network 1_400, and television devices 1 200_1 to 200_M of each household connected to the television manufacturer 1 server devices 300_1 to 300_N via a network 2_500. Note that although network 1_400 and network 2_500 are separate networks in Fig. 2, they may be the same network.

One device-specific household is associated with each of television devices 1 200_1 to M 200_M. Therefore, even if a dwelling unit is equipped with multiple television devices, one device-specific household is associated with each of the multiple television devices. In this case, each device-specific household corresponding to each of the multiple television devices may include the same members as viewers. In other words, one or more members of one device-specific household may also be members of another device-specific household.

Television device 1 200_1 to television device M 200_M of each device-specific household may be composed of a television, or may be composed of a television and a recording device connected to it. Each television device is capable of detecting the channel of the television broadcast viewed through it, as well as the date and time when the television broadcast on that channel was viewed (more specifically, the date and time when viewing of the television broadcast on that channel began and ended). From this detection information, viewing log information for the device-specific household (hereinafter referred to as device-specific viewing log information) is generated. In other words, device-specific viewing log information is the overall viewing log information of the members included in the device-specific household.

Each of the TV manufacturer 1 server devices 300_1 to TV manufacturer M server devices 300_M collects viewing log information from the corresponding TV device manufactured by that company among the TV devices 1 200_1 to M 200_M installed in each household.

The viewing log information aggregation processing device 100 comprises a control device 110 consisting of a processor (CPU, MPU, GPU, MCU, etc.) that executes various processes, a storage device 120 consisting of ROM, RAM, etc., an input device 130 consisting of a mouse, keyboard, microphone, etc., an output device 140 consisting of a display device, printer, speaker, etc., and a communication device 150.

The storage device 120 stores and retains programs and parameters for aggregating and processing viewing log information, viewing log information for the surveyed area obtained from each television manufacturer (hereinafter sometimes referred to as RL information), and viewing situation information (hereinafter sometimes referred to as PM information) obtained from dedicated devices such as people meters in the surveyed area.

The control device 110 loads various programs from the storage device 120 and stores them in internal memory (not shown), thereby constructing a survey area viewing log information acquisition unit 111, a survey area viewing situation information acquisition unit 112, and a viewing log information aggregation processing unit 113.

The survey area viewing log information acquisition unit 111 controls the communication device 150 to acquire survey area viewing log information from the desired television manufacturer's server device (at least one of the television manufacturer 1 server device 300_1 to television manufacturer N server device 300_N) via network 1_400, and stores it in the storage device 120. Note that the survey area viewing log information may also be input directly from the input device 130.

The survey area viewing situation information acquisition unit 112 controls the communication device 150, collects viewing situation information acquired by dedicated devices such as people meters in the survey area, and stores it in the storage device 120. Note that the viewing situation information acquired by dedicated devices such as people meters in the survey area may also be input directly from the input device 130.

The viewing log information aggregation processing unit 113 performs processing to bring the viewing trends of the viewing log information (RL information) for the survey target area closer to the viewing trends of the viewing situation information (PM information) for the same survey target area. Details of the processing performed by the viewing log information aggregation processing unit 113 (viewing log information aggregation processing) will be described later.

<Details of viewing log information aggregation process>
Fig. 2 is a flowchart for explaining the details of the viewing log information aggregation process according to an embodiment of the present invention. Fig. 3 is a conceptual diagram showing an example of processing at each step of the flowchart in Fig. 2. Note that in the explanation of Fig. 2, the viewing log information aggregation processing unit 113 is the entity that performs the operations at each step, but since the viewing log information aggregation processing unit 113 is realized by the control device (processor) 110 reading the target program from the storage device 120, the entity that performs the operations may be interpreted as the control device (processor) 110.

The viewing log information aggregation process according to this embodiment, like the conventional process, narrows the number of viewing log information samples to approximate PM information. However, rather than capturing viewing trends for all broadcast stations in PM information as in the past, this process performs "station ranking reproduction" to capture viewing trends for each broadcast station. Furthermore, this viewing log information aggregation process extracts and processes more viewing log information samples each month (e.g., 25%) than in the past (which fluctuate by less than 20% each month). While it is desirable to secure as many samples as possible for analytical or statistical reasons, there is a trade-off between "approximating RL information to PM information" and the number of samples. After careful consideration, the inventors and others found that approximately 25% was appropriate. For example, it was found that increasing this to 30% would increase the number of samples but reduce accuracy, while increasing the number of samples to 20% would result in a lower accuracy due to the small number of samples.

(i) Step S201
The viewing log information tallying processor 113 divides the viewing situation information (PM information) acquired by a dedicated device (such as a people meter) into n equal parts (for example, n=4).

For example, if the PM information viewing minutes are divided into four equal samples (the viewing minutes are divided equally: the quartiles of the viewing minutes are taken), the PM information is divided into PM groups G1 to G4 (divided sets), as shown in the top row of Figure 3(a).

(ii) Step S202
The viewing log information aggregation processing unit 113 divides the ID of the viewing log information at the same division point as the PM information in step S201. Here, the viewing log information is information obtained by separating the television viewing logs collected from each television manufacturer into individuals (the processing details will be described later). Therefore, the ID of the viewing log information is identification information that indicates the unit of an individual who has a television viewing log.

For example, if the viewing log information is divided at the same division point as in the upper part of Figure 3(a), the viewing log information will be divided into RL groups G1 to G4 (division sets), as shown in the lower part of Figure 3(a).

(iii) Step S203
The viewing log information aggregation processing unit 113 clusters the PM information by broadcast station share for each PM group (divided set). For example, when multiple samples included in PM group G1 of the PM information are clustered by share by broadcast station (stations A to D), the result is as shown in the upper part of Figure 3(b). In the clustering process, for example, the k-means method can be used, with the station-by-station viewing share as an explanatory variable.

(iv) Step S204
The viewing log information aggregation processing unit 113 applies the clustering model of the PM information acquired in step S203 to each divided set (RL group) of viewing log information. That is, if the viewing log information is divided into multiple RL groups in step S202, the clustering model of the PM information is applied to each group, and the viewing log information for each RL group is classified into shares by broadcast station. For example, as shown in the lower part of FIG. 3( b), if the viewing log information is divided into RL groups G1 to G4 in step S203, the clustering model of the PM group G1 is applied to the RL group G1, and the information of the RL group of the viewing log information is classified by broadcast station (station A to station D).

(v) Step S205
The viewing log information aggregation processing unit 113 calculates the appearance rate of each classification (cluster) for each region x gender x age group for one divided set of PM information. For example, the upper part of Figure 3(c) shows that when the appearance rate of clusters for the Kanto region x gender x age group for PM group G1 of the PM information is calculated, for children (children: 12 years old or younger), it is Station A = 35%, Station B = 30%, Station C = 15%, and Station D = 20%, and for teens (13 to 19 years old), it is Station A = 30%, Station B = 25%, Station C = 20%, and Station D = 25%.

(vi) Step S206
The viewing log information aggregation processing unit 113 samples the IDs of each divided set (each RL group) of viewing log information according to the appearance rate of PM information in each group calculated in step S205. Specifically, the viewing log information is extracted in descending order of distance from the center of each cluster until the data volume of the viewing log information reaches the above-mentioned appearance rate.

For example, the lower part of Figure 3(c) shows viewing log information for "children" included in RL group G1 extracted based on the occurrence rate of PM information (children) for each of stations A to D calculated in step S205. Furthermore, if the occurrence rate of station A (cluster A) in PM group G1 with viewing minutes of 0 to 30 minutes among males aged 20 to 34 in the Kanto region in the PM information is, for example, 6% (this situation is not shown in Figure 3), the viewing log information sample is narrowed down so that the occurrence rate of station A in RL group G1 with viewing minutes of 0 to 30 minutes among males aged 20 to 34 in the Kanto region in the viewing log information is 6%.

(vii) Processing Order of Each Step It is not necessary to process each step in the execution order shown in the flowchart of Figure 2. For example, the processing steps for PM information (step S201 → step S203 → step S205) may be executed first, followed by the processing steps for RL information (step S202 → step S204 → step S206). The order of the processing steps for PM information and the execution order of the processing steps for RL information must be maintained, and step S201 must be executed before step S202, step S203 must be executed before step S204, and step S205 must be executed before step S206, but there are no other restrictions (for example, step S201 → step S203 → step S202 → step S205 → step S204 → step S206 is allowed).

<Preprocessing of viewing log information>
Here, as a premise for executing the viewing log information aggregation process, a process is executed in which an attribute composition indicating which members of which attributes are included in a device-specific household from viewing log information by device (in other words, the attribute composition of viewers of television devices in a device-specific household) is estimated, and for each device-specific household, an individual separation process is executed in which, for each attribute included in the attribute composition estimated by the attribute composition estimation process, the viewing time of television broadcasts by viewers of each attribute over a predetermined unit time width (for example, viewing time per day or viewing time per month, etc.) is estimated. Below, a brief explanation of the attribute composition estimation process and the individual separation process is given.

(i) Attribute Composition Estimation Process The attribute composition estimation process estimates an attribute composition indicating which members of which attributes are included in a device-specific household (in other words, the attribute composition of viewers of television device k 200_k in the device-specific household) from device-specific viewing log information for a predetermined period (e.g., one month, several months, one year, etc.) output from television device k 200_k (k=1, 2, ..., M) in each device-specific household.

Here, the attributes of the members of each device-specific household (viewers of television device k 200_k) are classified into multiple types of attributes based on, for example, the age and gender of the members. For example, they are classified into multiple types of attributes such as children under y1, men aged y1 or older but under y2, women aged y1 or older but under y2, men aged y2 or older, and women aged y2 or older. Hereinafter, the number of types of attributes will be designated as N, and each of the N types of attributes will be appropriately represented as At(i) (i = 1, 2, ..., n). Note that the attributes of the members of each device-specific household can be classified not only by age and gender, but also by various other parameters such as occupation and educational background.

FIG. 4 is a diagram illustrating an example of a block configuration for executing an attribute composition estimation process. As shown in FIG. 4, the attribute composition estimation process estimates the attribute composition of members of each device-specific household using a first model that has been previously subjected to machine learning processing. Here, the first model is a model that has been previously subjected to machine learning processing so that the attribute composition of members of a device-specific household can be estimated from device-specific viewing log information for a predetermined period of any device-specific household belonging to a survey target area. In the machine learning process for the first model, viewing situation information for each sample household obtained from people meters or the like installed in each of multiple sample households (sample households in areas other than the survey target area) whose attribute composition is known and the attribute composition for each sample household are used as learning data. Furthermore, a publicly known algorithm can be used as the algorithm for the machine learning process.

In this case, in this embodiment, the first model is configured to be able to determine, for each of n types of attributes At(i) (i = 1, 2, ..., n), an attribute-specific presence probability, which is the probability that a member of each attribute At(i) is present in the device-specific household, from the device-specific viewing log information for a predetermined period of time for each device-specific household 20. Such a first model may be similar to the mathematical model for determining household composition in Patent Document 1, for example. However, the first model may be of another form, as long as it is able to determine an attribute-specific presence probability (or an index value similar thereto) from the device-specific viewing log information for a predetermined period of time for the device-specific household.

The attribute composition estimation process then estimates attributes whose attribute-specific presence probability identified by the first model is higher than a predetermined threshold (e.g., 0.5) (or attributes whose attribute-specific presence probability is higher than or matches the predetermined threshold) as attributes of the members of the device-specific household. As an example, Figure 4 shows the attribute composition estimation process for one device-specific household (in Figure 4, a device-specific household with identification information ID x1).

In the example shown in Figure 4, the attribute-specific presence probabilities of members of a device-specific household are identified by the first model as shown, based on device-specific viewing log information for a specified period of time for a device-specific household with identification information ID x1. In this example, of the n types of attributes At(i) (i = 1, 2, ..., n), the attribute-specific presence probabilities of each of attributes At(1), At(3), and At(n) are higher than a predetermined threshold (here, for example, 0.5), and the attribute-specific presence probabilities of each of the other attributes At(2), At(4) to At(n-1) are lower than the threshold.

In this case, the attribute composition estimation unit 113 estimates that attributes At(1), At(3), and At(n), whose attribute-specific existence probability is higher than the threshold, are attributes of the members of the device-specific household 20 (viewers of the television device 23), and estimates that attributes At(2), At(4) to At(n-1), whose attribute-specific existence probability is lower than the threshold, are not attributes of the members of the device-specific household. This allows the attribute composition of the members of the device-specific household to be estimated.

In this way, the attribute composition estimation process estimates the attribute composition of the members of a device-specific household by estimating whether or not members (viewers) of each attribute are present in the device-specific household based on whether the attribute-specific presence probability identified by the first model is high or low relative to a predetermined threshold.

(ii) Person Separation Processing Fig. 5 is a diagram showing an example of a block configuration for executing the person separation processing. The person separation processing estimates, for each device-specific household, the television broadcast viewing time by viewers of each attribute included in the attribute configuration estimated by the attribute configuration estimation processing over a predetermined unit time span, for example, the viewing time per day. Note that the unit time span is not limited to one day, but may be one week, one month, or the like.

In this case, the individual separation process includes an attribute-specific viewing information generation unit 50a that uses a second model to generate (estimate) attribute-specific viewing information for each device-specific household from the viewing log information of each device-specific household, indicating whether a viewer with each attribute included in the attribute configuration of the device-specific household watched a television broadcast corresponding to any combination of channel (or broadcast station network) and date and time data indicating the month, day of the week, time slot, etc., and a viewing time aggregation unit 50b that aggregates, from the attribute-specific viewing information, the viewing time (total viewing time over a specified unit time period) for each attribute included in the attribute configuration of the device-specific household.

Note that a television broadcast corresponding to a combination of a channel (or broadcasting station network) and date and time data indicating the month, day of the week, and time slot refers to a television broadcast that is broadcast on that channel (or broadcasting station network) at the date and time indicated by the date and time data. Furthermore, the time slot in the date and time data is, for example, a time slot divided into predetermined time intervals (10 minutes, 30 minutes, 1 hour, etc.).

The second model used by the attribute-specific viewing information generation unit 50a 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 model that has been subjected to machine learning processing in advance so that, when a set of channel (or broadcasting station) and date/time data is specified, the probability (hereinafter referred to as attribute-specific viewing probability) that a viewer with attribute At(i) watched a television broadcast (hereinafter referred to as channel/date/time specified broadcast) corresponding to the specified set of channel (or broadcasting station) and date/time data can be determined from device-specific viewing log information for a specified period of the device-specific household 20 to which the members (viewers) of attribute At(i) belong.

Note that Figure 5 shows that the attribute-specific viewing probability, which is the probability that a member (viewer) with attribute At(n) watched a channel/date/time specified broadcast, is determined using the second model corresponding to attribute At(n) from the viewing log information by device for a household with members (viewers) with a certain attribute At(n). The same applies to second models corresponding to other attributes.

In the machine learning process for the second model, the learning data includes viewing status information for each member of each sample household, obtained from people meters or the like installed in each of multiple sample households (sample households in areas other than the survey area) with known attribute configurations, and the attribute configuration of each sample household. A known algorithm may be used as the algorithm for the machine learning process. Furthermore, the second model may be similar to the mathematical model for determining individual viewing behavior described in JP 2019-220825 A, for example. However, the second model may be of another form, as long as it can identify attribute-specific viewing probabilities (or similar index values) for channel/date/time-specified broadcasts for which channel (or broadcast station affiliate) and date/time data are arbitrarily specified, for each attribute of the members of the device-specific household, from device-specific viewing log information for the device-specific household over a predetermined period.

The attribute-specific viewing information generation unit 50a is configured to determine (estimate) for each attribute constituting the attribute configuration of a device-specific household whether or not members of each attribute watched the channel/date/time specified broadcast, based on the attribute-specific viewing information estimated by the second model and the device-specific viewing log information of the device-specific household.

Specifically, the attribute-specific viewing information generation unit 50a determines that a member of a device-specific household has viewed a channel/date/time specified broadcast if the attribute-specific viewing probability value (probability value) identified by the second model for each attribute of the member of the device-specific household for a channel/date/time specified broadcast is equal to or greater than a predetermined threshold (e.g., 0.5 or greater), and the viewing log information for the device-specific household confirms that actual viewing occurred on the channel (or broadcast station affiliate) of the channel/date/time specified broadcast at the broadcast date and time indicated by the date and time data for the channel/date/time specified broadcast; if the condition is not met, it determines that a member of the device-specific household has not viewed a channel/date/time specified broadcast.

The individual separation process sequentially specifies all combinations of channel (or broadcast station network) and date/time data for a specified period (e.g., within a one-month period) for each attribute included in the attribute configuration of each device-specific household to the attribute-specific viewing information generation unit 50a configured as described above, and estimates whether the channel/date/time-specific broadcast corresponding to each of these combinations was viewed from the device-specific viewing log for that device-specific household for the specified period.

Next, in the individual separation process, the viewing time aggregation unit 50b executes its processing. The viewing time aggregation unit 50b calculates the sum of the time durations of all channel/date/time specified broadcasts that are estimated to have been viewed for each attribute of the members of each device-specific household, and estimates the viewing time per day by dividing this sum by the number of days in the specified period. This allows the viewing time per day to be obtained for each attribute of the members (viewers) of each device-specific household.

(iii) Others In this embodiment, the attribute configuration and attribute-specific viewing information of each device-specific household are estimated from device-specific viewing log information, and the viewing time for each attribute of viewers in each device-specific household (viewing time for a predetermined unit time period) is estimated from the estimated attribute-specific viewing information. However, in the present invention, the method for acquiring the viewing time for each attribute of viewers in each device-specific household is not limited to the above method. For example, each device-specific household may be equipped with an appropriate device capable of measuring or estimating the viewing time for each attribute of viewers in each device-specific household, and the viewing time for each attribute of viewers in each device-specific household may be acquired from that device. Alternatively, for example, each device-specific household may be equipped with an appropriate device capable of generating and outputting viewing log information for each attribute of viewers in each device-specific household, and the viewing time for each attribute of viewers in each device-specific household may be estimated from the viewing log information output from that device.

<Calculation of individual audience ratings>
Although the above-described viewing log information compilation processing device 100 does not include the individual audience rating estimation process, the viewing log information compilation processing device 100 may be configured to execute the individual audience rating estimation process.

After the viewing log information aggregation processing unit 113 extracts the viewers (viewing log information) to be surveyed, the individual viewing rate estimation process is executed. The individual viewing rate estimation process uses the extracted viewers (viewing log information) to estimate viewing rates (equivalent to individual viewing rates) for each of n types of attributes At(i) for the television broadcasts (hereafter referred to as survey target broadcasts) that are the subject of a survey of viewing conditions in the survey target area.

In this case, the individual audience rating estimation process estimates whether or not the target surveyed viewer watched the surveyed broadcast by performing the same process as the attribute-specific viewing information generation unit 50a in the individual separation process (processing that uses a second model corresponding to the attributes of the surveyed viewer) using viewing log information for a specified period of time for the device-specific households to which each surveyed viewer belongs, and the channel (or broadcast station network) and date and time data for the surveyed broadcast.

The individual audience rating estimation process then estimates whether or not all surveyed viewers in the surveyed area have watched the surveyed broadcast, and then, based on the estimation results, calculates viewing status data for the surveyed broadcast for each attribute At(i), for example, using equation (1).
Individual audience rating for 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 total number of surveyed viewers with attribute At(i) who are estimated to have watched the surveyed broadcast.

This makes it possible to obtain individual viewer ratings as data equivalent to the viewer ratings for each attribute At(i) in the survey area. In this case, the survey target viewers are selected so that the post-selection frequency distribution of viewing time matches the standard frequency distribution based on viewing status information for sample households in the survey area, making it possible to obtain highly reliable individual viewer ratings.

<Summary>
(i) The viewing log information processing device 100 according to this embodiment executes a viewing log information aggregation process to approximate the viewing trends of viewing log information obtained from television devices installed in each household in a survey area to viewing trends based on viewing status information obtained from dedicated equipment (such as a people meter) installed in a sample of households in the survey area. The viewing log information aggregation process is executed by the control device (processor) 110 according to a corresponding program. The control device 110 is configured to divide the viewing status information into multiple PM group data (see the upper part of FIG. 3(a)), perform a clustering process (see the upper part of FIG. 3(b)), and apply the viewing log information to multiple cluster models obtained by the clustering process (see the lower part of FIG. 3(b)), thereby approximating the viewing trends of the viewing log information to the viewing trends of the viewing status information. This makes it possible to extract viewing log information from all viewing log information that is similar to the viewing trends of the corresponding program acquired by the people meter, thereby enabling accurate audience ratings to be calculated using the viewing log information.

(ii) More specifically, the control device 110 calculates the occurrence rate based on predetermined conditions (survey area, gender, and age group) for multiple cluster models (the cluster model for PM group G1 is shown in the upper part of Figure 3(b)) for each of multiple PM group data (for example, PM groups G1 to G4 shown in the upper part of Figure 3(a)) (see the upper part of Figure 3(c)), and samples the viewing log information according to the occurrence rate (see the lower part of Figure 3(c)). By doing this, it is possible to align the viewing trends of the viewing log information with the viewing trends of the corresponding program obtained by the people meter in accordance with specific conditions.

It is preferable to adjust the viewing log information so that 25% of the total is extracted. For analytical or statistical reasons, it is desirable to secure as many samples as possible, but there is a trade-off between approximating the viewing log information to the PM information and the number of samples. For this reason, after extensive testing, the inventors have concluded that around 25% is optimal. For example, if the number of samples is increased beyond 25% (for example, to around 30%), the number of samples increases but the accuracy of the approximation decreases; even at around 20%, the accuracy of the approximation decreases.

(iii) The clustering process is performed on the four PM group data (PM groups G1 to G4) obtained by dividing the viewing situation information into four equal parts, with the station viewing share set as the explanatory variable. This generates a cluster model for each of the four PM group data. The viewing log information is then divided into four equal parts at the same division point as the viewing situation information (the division point for PM groups G1 to G4) to generate four RL group data (see the lower part of Figure 3(a)), and a cluster model for each of the PM group data is applied to each of the four RL group data. In this way, in this embodiment, the broadcast station viewing ratio (relative amount: whereas, in the past, the absolute amount of viewing was used as the standard, resulting in a large number of samples with low viewing amounts and a small number of samples with high viewing amounts) is incorporated, and clustering is performed on the two axes of relative viewing amount x broadcast station viewing ratio. This makes it possible to divide the viewing situation information into groups with similar viewing trends, allowing the viewing trends of the PM data to be more accurately reflected in the RL data.

(iv) The functions of this embodiment can also be realized by software program code. In this case, a storage medium on which the program code is recorded is provided to a system or device, and the computer (or CPU or MPU) of that system or device reads the program code stored on the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the above-mentioned embodiment, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

Furthermore, based on the instructions of the program code, an operating system (OS) running on a computer may perform some or all of the actual processing, thereby realizing the functions of the above-mentioned embodiments. Furthermore, after the program code is read from a storage medium and written to memory on a computer, a CPU or the like of the computer may perform some or all of the actual processing based on the instructions of the program code, thereby realizing the functions of the above-mentioned embodiments.

Furthermore, the software program code that realizes the functions of the embodiments and examples may be distributed over a network and stored in a storage means such as a hard disk or memory of a system or device, or on a storage medium such as a CD-RW or CD-R, so that when in use, the computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage means or storage medium.

The processes and techniques described herein are not inherently related to any specific device and can be implemented by combining components. Various types of general-purpose devices can also be added. A dedicated device may be constructed to perform the functions of this embodiment and each example. Various functions can also be formed by appropriately combining multiple components disclosed in this embodiment and each example. For example, some components may be omitted from all of the components shown in the embodiment and each example, or components from different examples may be appropriately combined.

While specific embodiments are described in the present invention, these are in all respects illustrative (for understanding the technology of the present invention) and not limiting. Those skilled in the art will recognize that there are numerous combinations of hardware, software, and firmware suitable for implementing the technology of the present invention. For example, the software described can be implemented in a wide variety of programming or scripting languages, such as Assembler, C/C++, Perl, Shell, PHP, Java (registered trademark), etc.

Furthermore, in the above-described embodiments, the control lines and information lines shown are those considered necessary for explanation, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

In addition, other implementations of the present invention will become apparent to those skilled in the art from consideration of the present embodiments and examples. The specification and examples are exemplary only, with the scope and spirit of the present invention being indicated by the following claims.

100 Viewing log information aggregation processing device 110 Control device (processor)
111 Survey target area viewing log information acquisition unit 112 Survey target area viewing situation information acquisition unit 113 Viewing log information aggregation processing unit 120 Storage device 130 Input device 140 Output device 150 Communication devices 200_1 to 200_M Television devices 1 to M
300_1 to 300_N: TV manufacturer 1 server device to TV manufacturer N server device 400, 500 network

Claims (10)

A viewing log information processing device that executes a viewing log information aggregation process to bring viewing trends of viewing log information, which is obtained from a television device installed in each household in a survey area and indicates history information of programs of each broadcasting station viewed by each television device, closer to viewing trends based on viewing situation information, which is obtained from dedicated equipment installed in sample households in the survey area and indicates history information of programs of each broadcasting station viewed by a television device connected to each dedicated equipment,
a storage device that stores a program for executing the viewing log information aggregation process;
a control device that reads the program from the storage device and executes it;
The viewing trends indicate characteristics of viewing content according to attributes including region, gender, and age;
The control device divides the viewing status information into multiple PM group data so that each group has an equal amount of information , performs clustering processing on the multiple PM group data using viewing shares by broadcast station as explanatory variables , and applies the viewing log information to multiple cluster models obtained by the clustering processing, thereby bringing the viewing trends of the viewing log information closer to the viewing trends of the viewing status information. In claim 1,
The control device calculates an appearance rate for the plurality of cluster models in each of the plurality of PM group data based on a predetermined condition, and samples the viewing log information in accordance with the appearance rate. In claim 2,
The control device calculates the appearance ratio based on information on the survey target area, gender, and age group. In claim 2,
The viewing log information processing device, wherein the control device samples the viewing log information to extract 25% of the viewing log information. In claim 1,
The control device performs the clustering process on the four PM group data obtained by dividing the viewing status information into four equal parts, setting the station viewing share as an explanatory variable, and generates the cluster model for each of the four PM group data. In claim 5,
The control device divides the viewing log information into four equal parts at the same division point as the viewing status information to generate four RL group data, and applies the cluster model to each of the four RL group data. A viewing log information processing device that executes a viewing log information aggregation process to make viewing trends of viewing log information, which is obtained from a television device installed in each household in a survey area and indicates history information of programs of each broadcasting station viewed by each television device, closer to viewing trends obtained from viewing situation information, which is obtained from dedicated equipment installed in sample households in the survey area and indicates history information of programs of each broadcasting station viewed by a television device connected to each dedicated equipment,
a storage device that stores a program for executing the viewing log information aggregation process;
a control device that reads the program from the storage device and executes it;
The viewing trends indicate characteristics of viewing content according to attributes including region, gender, and age;
The control device
a first process of generating a plurality of PM group data by dividing the viewing situation information into n equal parts so that the amount of information in each group is equal ;
a second process of dividing the viewing log information into n equal parts at the same division points as in the first process, and generating a plurality of RL group data;
a third process of clustering each of the plurality of PM group data using the viewer share by broadcast station as an explanatory variable, and generating a plurality of PM clusters for each of the PM group data;
a fourth process of applying the viewing log information to a plurality of cluster models for each of the plurality of RL group data;
a fifth process of calculating an appearance rate based on a predetermined condition for the plurality of cluster models in each of the plurality of PM group data;
a sixth process of sampling each of the plurality of RL group data in accordance with the appearance rate;
A viewing log information processing device that executes the above. In claim 7,
The control device calculates the appearance ratio based on information on the survey target area, gender, and age group in the fifth process. In claim 7 ,
The viewing log information processing device, wherein the control device, in the sixth process, extracts 25% of the viewing log information by sampling each of the plurality of RL group data. A viewing log information processing method and apparatus that performs a viewing log information aggregation process to approximate viewing trends of viewing log information, which is obtained from a television device installed in each household in a survey area and indicates history information of programs of each broadcasting station viewed by each television device, to viewing trends based on viewing situation information, which is obtained from dedicated equipment installed in sample households in the survey area and indicates history information of programs of each broadcasting station viewed by a television device connected to each dedicated equipment,
The viewing trends indicate characteristics of viewing content according to attributes including region, gender, and age;
a control device that executes the viewing log information aggregation process reading the program from a storage device that stores the program for executing the viewing log information aggregation process;
the control device divides the viewing situation information into a plurality of PM group data so that the amount of information in each group is equal , and executes a clustering process on the plurality of PM group data using the viewing share by broadcast station as an explanatory variable ;
the control device applies the viewing log information to a plurality of cluster models obtained by the clustering process, thereby bringing the viewing tendency of the viewing log information closer to the viewing tendency of the viewing situation information;
A viewing log information processing method, including: