JP2003067290A - Information delivery system and program therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information delivery system and a program therefor a allocate optimally the number of times of deliveries for advertisement information depending on fluctuations of the number of demands for the deliveries and manage the deliveries in case of delivering the advertisement information together with image content via the Internet. SOLUTION: In accordance with forecast information for the number of the deliveries and information for delivery conditions defined for each of the advertisements, a calculation processing part for the number of deliveries of the advertisements 20 calculates the number of the deliveries using a performance function with a variable consisting of the information for the delivery conditions and the number of the deliveries based on a value of the performance function to meet limiting conditions which are defined by the information for the delivery conditions and the forecast information for the deliveries forecasted. An advertisement list generation part 21 generates an advertisement list based on the number of the deliveries forecasted. An advertisement delivery processing part 23 identifies a subscriber category, refers to the advertisement list and delivers the advertisement information combined with the identified category to a subscriber terminal 10.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information distribution system and a program thereof for distributing information to be viewed such as video content to a viewer terminal capable of connecting to a network via a network.

[0002]

2. Description of the Related Art In recent years, services for distributing video contents via the Internet have been started with the increase in communication speed. Along with this, a service for delivering advertisement information including the advertisement information to the video content and a service for delivering advertisement information including the video image on the information screen (portal screen, search screen, etc.) have begun to be provided. This distribution of advertising information is expected to have the same effect as advertising for TV broadcasting,
One of the criteria for showing the effectiveness of an advertisement is how many people (reach) and how many times (frequency) the target audience views.

[0003] In addition, a television broadcast advertisement has a time frame for advertisement provided for each program (referred to as a program advertisement frame). Then, for each program advertisement frame, in consideration of the broadcast time zone, the program content, and the audience rating, what kind of audience (age, gender, etc.)
By estimating how many people are seeing, the advertising company has created an advertisement broadcasting plan (program advertisement frame purchasing plan) that can meet the needs of advertisers for reach and frequency for each target segment.

When the advertisement information is distributed together with the video content to the viewer terminal via the Internet or when the advertisement information including the video is distributed on the information screen, the same video content or information screen is distributed. Even if
Since the viewers can deliver different advertisement information, the concept of the time frame for advertisement is not set for each program but is set for each viewing timing of the viewer (referred to as a viewing timing advertisement frame). ). Compared with program advertisement frames in TV broadcasting, this viewing timing advertisement frame can identify viewers rather than estimate, so more accurate target advertisement can be performed, but the number of advertisement frames depends on the total viewing time of viewers. Because it will change
It is not possible to set a fixed number of ad slots.

[0005]

As described above, when the advertisement information is distributed together with the video content to the viewer terminal via the Internet, or when the advertisement information including the video on the information screen is distributed, the viewing timing. There is a demand for a system that predicts the number of distribution demands in each ad space and manages the best distribution distribution distribution so that each advertiser can meet the demand for reach and frequency for each target segment. For this reason, it is necessary to distribute the number of distributions in consideration of the distribution balance of the whole and fluctuations in the number of distribution demands, and there is a problem that distribution management is complicated.

[0006] In the distribution of advertising information via the Internet, the effects of reach and frequency are:
It can be grasped with a real number. However, since the number of advertisement distribution demands is limited, 100%
Can not meet. Therefore, this system has a problem that it is necessary to accurately estimate the future distribution demand number in order to efficiently distribute the advertisement information.

The present invention has been made in consideration of the above-mentioned circumstances, and when the advertisement information is distributed together with the video contents via the Internet, the number of times of distribution of the advertisement information is adjusted in response to the fluctuation of the distribution demand number. It is an object of the present invention to provide an information distribution system and its program for optimal distribution and management of distribution. It is another object of the present invention to provide an information distribution system and its program capable of accurately predicting the future distribution demand number in advertisement information distributed via the Internet.

[0008]

The present invention has been made to solve the above-mentioned problems, and in the information distribution system according to the present invention, a viewer terminal which can be connected to a network and which displays video contents is provided. An information distribution system for controlling distribution of advertisement information, which is distribution demand number prediction information that is information for predicting the distribution demand number within a predetermined period according to viewer classified categories, and at least the planned distribution number and distribution for each advertisement. Based on the distribution condition information that determines the evaluation value, which is a value arbitrarily weighted by the advertiser according to the period, category, and distribution date and time, using the evaluation function with the evaluation value and the distribution number as variables, the distribution condition information and the distribution demand Based on the advertisement distribution number calculation means for calculating the distribution number based on the value of the evaluation function satisfying the constraint condition defined by the prediction information, and the distribution number calculated by the advertisement distribution number calculation means. , A category and an advertisement list creating means for creating an advertisement list that is a list of combinations of advertisement information to be distributed to the category, and a viewer category is specified, and the advertisement list is referred to and combined with the specified category. And an advertisement delivery means for delivering the advertisement information to the viewer terminal.

Thus, when the advertisement information is distributed together with the video content via the Internet, the distribution of the advertisement information can be controlled according to the evaluation value set by the advertiser. Further, since the advertisement distribution number calculation means calculates the distribution number of the advertisement information using the distribution demand number, it is possible to optimally manage the distribution number of the advertisement information corresponding to the fluctuation of the distribution demand number. .

Further, in the information distribution system according to the present invention, the distribution history database storing the distribution history in which the category of the viewer and the distribution date and time are related to the advertisement information distributed to the viewer terminal, and the distribution history. A distribution demand number predicting unit that statistically processes the past distribution count in arbitrary date / time units by category with reference to the distribution history from the database and predicts the distribution demand count in a predetermined period in the date / time unit based on the statistical processing result. It is characterized by including.

Thus, the past distribution demand of viewers is statistically processed for each viewer category, so that the future distribution demand number of advertisement information can be accurately predicted.

Further, in the information distribution system according to the present invention, the advertisement distribution number calculating means calculates the distribution number on a date / time basis. As a result, the number of distributions can be calculated with higher accuracy by calculating the number of distributions on a date and time basis that matches the cycle of distribution demands of the viewer.

Further, in the information distribution system according to the present invention, the attribute information includes information about the video content being viewed on the viewer terminal, and the advertisement distribution number calculation means relates to the video content included in the attribute information. It is characterized in that the number of distributions is calculated using information as an evaluation value. Thus, the information distribution system can provide the viewer terminal with the advertisement information that reflects the content of the video content that the viewer is viewing.

Further, in the information distribution system according to the present invention, the advertisement list creating means is adapted to maintain the appearance probability according to the ratio of the distribution number of each advertisement to the total distribution number of advertisements of each category. It is characterized by creating an advertisement list that determines the order. As a result, it is possible to deliver advertisements according to the ratio of the number of deliveries of each advertisement assigned to each category.

In the information distribution system according to the present invention, the advertisement list creating means creates an advertisement list by extracting advertisement information matching the search condition based on the advertisement information assigned to the category according to the number of distributions. It is characterized by doing. As a result, it is possible to perform more targeted advertisement distribution in the allocated advertisement information.

Further, the information delivery system according to the present invention is characterized by further comprising an advertisement fee processing means for calculating an increase or decrease in the delivery fee of the advertisement for which the evaluation value is set according to the evaluation value. As a result, for advertisements with a high evaluation value (advertisements with higher priority than other advertisements), the distribution fee for the advertisement is increased, and the distribution fee is increased or decreased according to the evaluation value. be able to.

Further, the program according to the present invention is a program for an information distribution system which controls distribution of advertisement information to a viewer terminal which is connectable to a network and which displays video contents, and is a category of viewers. Separately, the distribution demand number prediction information that is information that predicts the distribution demand number within a predetermined period, and the evaluation value that is a value arbitrarily weighted by the advertiser according to at least the planned distribution number, distribution period, category and distribution date and time for each advertisement. Based on the delivery condition information that is defined,
Using an evaluation function with the evaluation value and the number of distributions as variables, calculating the number of distributions based on the value of the evaluation function that satisfies the constraint condition determined by the distribution condition information and the distribution demand forecast information, and calculating the number of distributions based on , A step of creating an advertisement list which is a list of combinations of categories and advertisement information to be distributed to the categories, an audience category is identified, an advertisement combined with the identified category is referred by referring to the advertisement list. A program for causing a computer to execute a step of distributing information to a viewer terminal of the viewer.

Further, the program according to the present invention, with respect to the advertisement information distributed to the viewer terminal, sets the category of the viewer,
From a distribution history database that stores distribution histories associated with distribution dates and times, the distribution history is referred to, statistical processing is performed on the number of past distributions in arbitrary date and time units for each category, and based on the statistical processing result, a predetermined number is calculated for each date and time unit. It is the above-mentioned program that causes a computer to further execute the step of predicting the number of demands for distribution during a period.

Further, the program according to the present invention is the above-mentioned program, wherein the step of calculating the number of distributions calculates the number of distributions on a date and time basis.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention described in the claims, and all of the combinations of features described in the embodiments are required for the solution means of the invention. Not necessarily. First, as an evaluation function used in the calculation processing of the information distribution system according to the first embodiment of the present invention, an objective function of a linear programming method that finds a combination of variables that maximizes the value of the objective function under given conditions. The case of using will be described below.

FIG. 1 is a block diagram showing the overall configuration of an information distribution system according to the first embodiment of the present invention. In this figure, reference numeral 10 is a viewer terminal that is connectable to the network 11 and that has software for reproducing the video content provided via the network 11.
Reference numeral 12 is a video information server that includes a video content database that stores video content to be distributed to the viewer terminal 10, and distributes the video content via the network 11. Reference numeral 13 is an advertisement server that includes an advertisement content database that stores the video content for advertisement created by the advertiser and distributes the advertisement content via the network 11.

For the video content distributed by the video information server 12, a request for the advertisement information is sent to the network 1 in order to reproduce the advertisement content during the reproduction of the video content.
1 contains the program to send to. Furthermore, when transmitting a request for advertisement content from the viewer terminal 10, the video content is combined with attribute information including information regarding the viewer of the viewer terminal 10 that transmits the request for advertisement content and information regarding the video content. Including programs to send.

Reference numeral 14 receives a request for advertisement information and attribute information from the viewer terminal 10 which is reproducing the above-mentioned video content via the network 11, and the advertisement information according to the category of the viewer determined by the attribute information. Is an information distribution system for distributing to the viewer terminal 10. Further, the information distribution system 14 accepts registration of advertisement information including advertisement content data and distribution condition information such as a distribution period of the advertisement content from the advertisement information server 13. Although not shown, each of the viewer terminal 10, the video information server 12, the advertisement server 13, and the information distribution system 14 described above may be plural.

Next, the internal structure of the information distribution system 14 will be described with reference to FIG. Reference numeral 15 is a control unit that controls data in the information distribution system 14. 16
Is a transmission / reception processing unit that transmits and receives various data via the network 11. Reference numeral 17 is a database that stores various information necessary for advertisement distribution. Here, the internal structure of the database will be described with reference to the drawings.

First, the advertisement information database 17a stores the advertisement information in association with the advertisement identifier unique to each advertisement. FIG. 2 is a diagram showing a schematic configuration of the advertisement information database 17a in the first embodiment of the present invention. As shown in the figure, the following information is stored as "advertising information" in association with the "advertising identifier". The “advertisement name” is a name arbitrarily given to the advertisement by the advertiser. If this "advertisement name" is unique, this may be used as the advertisement identifier. The “advertisement content data” is data of the video content for advertisement provided by the advertiser. The “advertiser information” is information about an advertiser who provides the advertisement, for example, information such as an advertiser name and affiliated company information.

"Distribution condition information" is information for determining an evaluation value which is a value arbitrarily weighted by the advertiser according to at least the planned number of distributions, distribution period, category and distribution date and time for each advertisement. including. The “delivery period” is information indicating a period during which the advertiser wants the advertisement to be delivered. The “evaluation value” is, for example, a category classified according to the age or sex of the viewer, and a value arbitrarily weighted by the advertiser according to the distribution date and time. The information that the advertiser refers to when setting the "evaluation value" includes information about the video content that the viewer is viewing, hobby information, and information about the type of advertisement that the viewer wants to see. Information that can identify the viewer who wants to present the advertisement may be referred to.

"Distribution budget" is information that defines the upper limit of the distribution fee added each time the advertiser distributes the advertisement. The details of the method of adding charges by distribution will be described later. The “total number of distributions” is the total number of distributions that the advertiser wants to distribute in the distribution period designated by the advertiser. The “cumulative number of distributions” is the cumulative number of distributions that the information distribution system 14 has distributed so far. The "delivery scheduled number" is the difference between the "delivery total number" and the "delivery cumulative number", and indicates the number of advertisements scheduled to be delivered. As described above, the advertisement information database 17a stores information registered by the advertiser and information regarding the number of distributions.

Next, the distribution history database 17b will be described. The distribution history database 17b stores a distribution history in which the category of the viewer and the distribution date and time are associated with the advertisement information distributed to the viewer terminal 10. Figure 3
(A) is a figure showing a schematic structure of distribution history database 17b in a first embodiment of the present invention. As shown in the figure, the “attribute information of the distribution destination” is the information received together with the program of the video content when the viewer terminal 10 receives the request for the advertisement information, so as to classify the viewers. , It consists of the following contents.

The "information about the viewer" is information for specifying the viewer such as the viewer name and the viewer identifier. For example, it may be an IP address that identifies the viewer terminal 10 in the network 11 or information regarding a provider used by the viewer. In addition, information such as the hobby and age / sex of the viewer may be used. The “category” is information about a category to which the viewer of the viewer terminal 10 who has delivered the advertisement belongs.

The "video content information being watched" is information relating to the movie content being watched by the viewer. Accordingly, the advertiser can set the evaluation value so that the advertisement is distributed according to the content of the video content. For example, when a viewer is watching the video content of a sports program, an advertiser who provides an advertisement for sports equipment sets an evaluation value that most weights the video content of the sports program so that the viewer can The probability of viewing the advertisement can be increased.

The "delivery date and time" is information indicating the date and time when the advertisement is delivered. The "delivery advertisement information" stores information that can identify the delivered advertisement, such as "the advertisement name of the delivered advertisement" and "the advertisement identifier of the delivered advertisement". As described above, the distribution history database 17b stores the history of distributed advertisements.

Next, the viewer information database 17c will be described. The viewer information database 17c stores "viewer information" that is information about the viewer in association with the viewer identifier. FIG. 3B is a diagram showing a schematic configuration of the viewer information database 17c in the first embodiment of the present invention. As shown in the figure, the following information is stored as the "viewer information". The “viewer name, address, contact information” is information such as the viewer's name, address, telephone number, and e-mail address. Thus, for example, when there is an advertisement to be distributed by region, it is possible to deal with the information on the address of the viewer.

"Gender, age, birthplace" is information on the sex, age, and birthplace of the viewer. As a result, by determining the categories of viewers according to age and sex and giving weighted evaluation values, it is possible to deliver more advertisements to men or women of the desired age group. “Information about hobbies and interests” is information about the hobbies and interests of the viewer. As a result, it is possible to deliver advertisements that take into account the hobbies and interests of the viewer.

The "viewing history information of video contents" is information on the video contents that the viewer has viewed in the past. As a result, it is possible to extract information such as the type of video content preferred by the viewer and whether or not the viewing time period is determined depending on the day of the week, and can be used for category classification, evaluation value calculation, and distribution demand calculation. The “viewing history information of advertisement” is history information regarding an advertisement that the viewer viewed in the past. As a result, it is known that, when the same advertisement is viewed by the same viewer a plurality of times, it becomes counterproductive when the number exceeds a predetermined number, but this can be prevented. Further, in the case of a story-like advertisement, it is possible to deliver an advertisement that is a continuation of the story.

"Categorized categories" stores all applicable categories among a plurality of categories used in the processing of the information distribution system 14 based on the various kinds of information of the viewers shown above. For example, when a category AAA of “male in twenties” and a category BBB of “living in Kanagawa prefecture and playing baseball” are applicable, the categories AAA and BBB are stored. Thereby, in the processing in the information distribution system 14, the viewers can be grouped into a predetermined category and processed. As described above, the viewer information database 17c stores information about viewers.

Next, the information distribution system 14 in FIG.
Return to the description of the reference numerals inside. A registration processing unit 18 generates registration screen information that causes the advertisement server 13 to display a registration screen that prompts the advertisement server 13 to register advertisement information in the information distribution system 14. The transmission / reception processing unit 16 transmits the registration screen information generated by the registration processing unit 18 to the advertisement server 13. Here, an example of a case where a plurality of advertisers set an evaluation value for each viewer for advertisement 1, advertisement 2, advertisement 3, ... Advertisement i will be illustrated. FIG. 4 is a diagram showing an example of setting the evaluation value of each advertisement for each viewer according to the first embodiment of the present invention. As shown in the figure, each unit time (t ₁ , t ₂ , ...
each viewer (U1, U2, U3, ... U at t _k ).
The advertiser sets the evaluation values a _ij of j) advertisements 1 to i.

The above-mentioned setting of the evaluation value a _ij is performed for each viewer, but the present invention is not limited to this. For each advertisement, a group of a plurality of viewers is created and the evaluation value is set. Alternatively, the viewers may be classified into various categories and the evaluation value may be set for each category. Here, a case of creating a group in which a plurality of viewers are collected for each advertisement will be described with reference to the drawings. FIG. 5 is a diagram showing an example of setting the evaluation value of each advertisement for each group according to the first embodiment of the present invention. As shown, each unit of time (t _1, t _2, ... t _k) in each ad (1, ad 2, ad 3, ...) to the viewer (U1, U2, ... U
Create group j). The advertiser sets the evaluation value g _ij for each group. In addition, the creation of the group,
It may be created by referring to the viewer information database 17c.

Numeral 19 refers to the distribution history from the distribution history database 17b to statistically process the past distribution number in arbitrary date and time units for each category, and based on the statistical processing result, the distribution demand number in a predetermined period in the date and time unit. It is a delivery demand number prediction processing unit that predicts. Here, each viewer (U1, U
2, U3, ... Uj), future unit time (t ₁ ,
An example of the distribution demand number predicted by the distribution demand number prediction processing unit 10 at t ₂ , ... T _k ) is shown. FIG. 6 is a diagram showing an example of the distribution demand number predicted by the distribution demand number prediction processing unit 10 according to the first embodiment of the present invention. As shown in the figure,
The distribution demand number prediction processing unit 10 includes a distribution history database 1
7b, the distribution demand number m _jk of each viewer (U1, U2, U3, ... Uj) at each unit time (t ₁ , t ₂ , ... T _k ) is predicted.

Numeral 20 is an optimum distribution number of advertisements using the evaluation function of the following (Equation 1) with the evaluation value and the distribution number as variables based on the distribution demand number prediction information and the distribution condition information. It is an advertisement distribution number calculation processing unit for calculating.

[Equation 1] Note that t = 1, 2, 3, ... Q in (Equation 1) corresponds to the unit time (t ₁ , t ₂ , ... T _k ) in FIG. Further, the variable N ′ _it is the scheduled delivery number of the advertisement i at the time t, and is a term for making the cumulative delivery number approach the total delivery number. In addition, the variable x _ij indicates the number of distributions, which is the number of distributions of the advertisement i to the viewer Uj.

In (Equation 1), the first term is a term for obtaining the distribution number x _ij satisfying the evaluation value a _ij , and the second term is the distribution number x satisfying the scheduled distribution number N ′ _{it. This} is a term for finding _ij . Further, α for accumulating in the first term and (1-α) for accumulating in the second term are for adjusting the weighting of whether to give priority to satisfying the evaluation value or giving priority to satisfying the planned number of distributions. It is a coefficient that takes an arbitrary value.

Further, the advertisement distribution number calculation processing section 20 uses the following four formulas (Formula 2), (Formula 3), (Formula 4) and (Formula 5) which are determined by the distribution condition information and the distribution demand forecast information. Use the constraints shown.

[Equation 2] That is, the advertisement distribution number calculation processing unit 20 calculates the distribution number such that the evaluation function (Equation 1) satisfies the above constraint condition and becomes the maximum value. The detailed operation of the advertisement distribution number calculation processing unit 20 will be described later.

Reference numeral 21 is an advertisement list creation processing unit that creates an advertisement list, which is a list of combinations of categories and advertisement information to be distributed to the categories, based on the distribution numbers calculated by the advertisement distribution number calculation processing unit 20. . The advertisement list creation processing unit 21 creates an advertisement list that determines the order of advertisement distribution so as to maintain the appearance probability according to the ratio of the number of distributions of each advertisement to the total number of distributions of advertisements for each category. 22 is
The viewer of the viewer terminal 10 is classified into a predetermined category based on the advertisement request information requesting the advertisement information received from the viewer terminal 10 and the attribute information for classifying the viewer of the viewer terminal 10 into the category. This is a classification processing unit. 23
Is an advertisement distribution processing unit that refers to the viewer category classified by the classification processing unit 22 and the advertisement list, and distributes the advertisement information combined with the category to the viewer terminal 10 of the viewer.

Here, the above-mentioned advertisement list creation processing unit 2
1 shows some other examples of how to create an advertisement listing. As a first example, the advertisement list creation processing unit 2
1 creates an advertisement list that defines a distribution order in which advertisements assigned to each category are included a predetermined number of times (create one for each category). As a result, the advertisement distribution processing unit 2
When there is an advertisement distribution request from the viewer terminal 10, 3 distributes advertisement information in order from the advertisement list of the category to which the viewer belongs. Also, when the advertisement list reaches the end, it returns to the beginning and delivers.

As a second example, the advertisement list creation processing unit 2
1 creates an advertisement list that is a “basic set” of advertisements arranged in the distribution order at the ratio of the number of distributions of each advertisement distributed to the category (create one for each category). Next, the advertisement list creation processing unit 21 has a file size that allows the same advertisement from the advertisement list of the “basic set” to be distributed to the viewer terminal 10 at one time without lining up twice in succession, “secondary set”. Create an ad listing for. As a result, the advertisement distribution processing unit 23 selects an arbitrary “secondary set” of the advertisement list when the viewer terminal 10 makes an advertisement distribution request, and distributes the advertisement information according to the advertisement list. Also,
When the advertisement list reaches the end, another "secondary set" advertisement list is selected and advertisement distribution is performed in the same manner.

As a third example, the advertisement list creation processing unit 2
First, the number of viewers for each viewing count is grasped based on the past viewing record, and an advertisement list that determines the distribution order in consideration of the number of viewers is created (for example, once a month, one is created for each category). Accordingly, when the viewer terminal 10 requests an advertisement distribution, the advertisement distribution processing unit 23 distributes the advertisement information according to the advertisement list created for the category to which the viewer belongs.

As a fourth example, the advertisement list creation processing unit 2
1 creates an advertisement list that determines the distribution order of advertisements distributed to categories by monthly processing according to the value of "remaining number / total number" at the stage of daily processing (create one for each category). It should be noted that the advertisement list creation processing unit 21 determines that "the remaining number of times /
When there are two or more advertisements having the same value of "total number of times", an advertisement list is created in the order of distribution from the advertisement having the largest total number (or small). When the total number of times is also the same value, an advertisement list in a distribution order randomly selected from the advertisement is created.

As a result, the advertisement distribution processing section 23 distributes the advertisement information according to the advertisement list of the category to which the viewer belongs when the viewer terminal 10 requests the advertisement distribution. (All the viewers who belong to the same category follow the same advertisement list.) Also, the advertisement list creation processing unit 2
When the distribution of 1 day is over, 1 updates the advertisement list by reflecting the distribution record up to that point.

As a fifth example, the advertisement list creation processing unit 2
1 creates an advertisement list that determines the distribution order in consideration of the evaluation value for the time zone, in addition to the value of "remaining number / total number" (one for each category). That is, the distribution order is determined based on the value of “remaining number / total number” and the value of the evaluation function in a predetermined time zone for each category, and an advertisement list is created. As a result, the advertisement distribution processing unit 23
When there is an advertisement distribution request from the viewer terminal 10,
Advertisement information is distributed based on the advertisement list of the category to which the viewer belongs.

As a sixth example, the advertisement list creation processing unit 2
1 creates the advertisement list by extracting the advertisement information that matches the search condition based on the advertisement information assigned to each category by the distribution number calculated by the advertisement distribution number calculation processing unit 20. The information that can be specified as the search condition includes the distribution history of advertisement information, the type of video that the viewer is viewing, the type of Web page that the viewer is viewing, the age, sex, hobbies, etc. of the viewer. Information such as the type of personal computer (hereinafter referred to as a PC) used, the type of browser used in the PC, the communication capability (communication speed, communication mode) of the PC, and the like. In addition, the advertisement information is also associated with information regarding a prohibited distribution time period determined by the advertiser, the law, or the like, and an individual (specified by age, etc.). This allows
The advertisement list creation processing unit 21 refers to the distribution prohibited time zone and the information of the viewer to identify the advertisement information that should not be distributed, and the past advertisement history or the current viewer views the advertisement information that can be distributed. It is possible to search and provide the advertisement information that reflects the information of the image inside or the Web page being browsed.

When the advertisement distribution processing unit 23 distributes the advertisement information to the viewer terminal 10 based on the advertisement list, the advertisement information whose distribution is prohibited due to a time slot, a request from the advertiser, or the like is the advertisement. If it is included in the list, it is dealt with by skipping the advertisement information. In addition, the advertisement list creation processing unit 21 sets some rules at the time of creating the advertisement list, such as avoiding delivering the same advertisement to the same viewer two or more times in succession. It is also possible to create an advertisement list in the order of distribution.

Each processing unit shown in FIG. 1 described above may be realized by dedicated hardware,
Each processing unit has a memory and a CPU (central processing unit).
Alternatively, the program may be realized by loading a program for realizing the function of each processing unit into a memory and executing the program. The memory is a non-volatile memory such as a hard disk device, a magneto-optical disk device, a flash memory, a read-only recording medium such as a CD-ROM, or a RAM (Random).
A volatile memory such as an access memory or a computer-readable / writable recording medium using a combination thereof.

Next, the operation of the above-mentioned information distribution system 14 will be described with reference to the drawings. First, the operation of the distribution demand number prediction processing unit 19 in the information distribution system 14 will be described. FIG. 7 shows a distribution demand number prediction processing unit 19 in the information distribution system 14 according to the first embodiment of the present invention.
It is a flowchart which shows operation | movement of. First, the distribution demand number prediction processing unit 19 refers to the distribution history from the distribution history database 17b and obtains the average viewing time of advertisements in the past, the temporal distribution of the distribution number, and the probability distribution by day of the week for each category (step. S10).

Next, the distribution demand number prediction processing unit 19 determines whether or not the processing is completed for all days of the week by the expression t ≧ t.
Judgment is made by _MAX (step S11). Since the unit of t is a day of the week, t _MAX is 7 for one week. Here, if t ≧ t _MAX is not satisfied (NO in step S11),
The distribution demand number prediction processing unit 19 generates a random number to predict the distribution demand number at t = i from the probability distribution (step S12). Next, the distribution demand number prediction processing unit 19 increases the value of t by 1 (step S13). Next, the process returns to step S11. Here, when t ≧ t _MAX (YES in step S11), the distribution demand number prediction processing unit 19 ends the process.

As described above, the distribution demand number prediction processing unit 19 can predict the distribution demand number in arbitrary date units. The distribution demand number prediction processing unit 19 can predict the distribution demand number in consideration of the distribution of demand by generating a random number in step S12.
Further, in the above-described embodiment, the processing is performed on a day-of-week basis, but the processing is not limited to this, and processing may be performed on an arbitrary date-time basis.

Next, the operation of the advertisement distribution number calculation processing section 20 in the information distribution system 14 will be described. Figure 8
Is an information distribution system 1 according to the first embodiment of the present invention.
6 is a flowchart showing the operation of the advertisement distribution number calculation processing section 20 in FIG. First, the control unit 15 refers to the distribution history from the distribution history database 17b to update the current planned distribution number of each advertisement. Also, the distribution demand number prediction processing unit 1
9 predicts the number of distribution demands at present (step S2)
0). Next, the advertisement distribution number calculation processing unit 20 initializes the value of t _k to 1 (step S21).

Next, the advertisement distribution number calculation processing section 20 determines whether or not the processing has been completed for all days of the week by the formula t ≧ t.
Judgment is made by _MAX (step S22). Where t
If ≧ t _MAX is not satisfied (NO in step S22), the advertisement distribution number calculation processing unit 20 sets the initial value of the variable of the evaluation function (equation 1) at time t _k (step S23). Next, the advertisement distribution number calculation processing unit 20 calculates the value of the variable that maximizes the evaluation function (Equation 1) at time t _k (step S24). At this time, the advertisement distribution number calculation processing unit 20
The evaluation function (Equation 1) satisfies the constraint conditions (Equation 2), (Equation 3), (Equation 4), (Equation 5).

Next, the control unit 15 calculates the following formula and stores the expected distribution number as the calculation result in the advertisement information database 17a. (Step S25). Scheduled number of distribution = total number of distribution-cumulative number of distribution Next, the advertisement distribution number calculation processing unit 20 increments the value of t by 1 (step S26). Next, the process returns to step S22. Here, if t ≧ t _MAX (YES in step S22), the advertisement distribution number calculation processing unit 20 ends the process.

As described above, the advertisement distribution number calculation processing section 20 calculates the optimum distribution number using the evaluation function.
Here, an example of the distribution number calculated by the advertisement distribution number calculation processing unit 20 will be described with reference to the drawings. FIG. 9 shows an advertisement distribution number calculation processing unit 20 for each advertisement according to the first embodiment of the present invention.
It is a figure which shows the example which allocates the distribution number which is calculated to each viewer. As shown in the figure, the advertisement distribution number calculation processing unit 20
At each unit time (t ₁ , t ₂ , ... T _k ), each advertisement (advertisement 1, Ad 1) assigned to each viewer (U 1, U 2, ... Uj)
The distribution number x _ij of advertisement 2, advertisement 3, ... Advertisement i) is calculated.

Further, another example of the distribution number calculated by the advertisement distribution number calculation processing section 20 will be described with reference to the drawings. Figure 10
FIG. 6 is a diagram showing an example in which a distribution number calculated by the advertisement distribution number calculation processing unit 20 is assigned to each advertisement according to the first embodiment of the present invention. As shown in the figure, the advertisement distribution number calculation processing unit 20 allocates each advertisement (advertisement 1, advertisement 1) to each category (F1, F2, ... Fj) in each unit time (t ₁ , t ₂ , ... T _k ). 2, advertisement 3, ... number of advertisements i) delivered n
Calculate _j * x _ij . Note that n _j is the number of viewers belonging to each category Fj.

Next, the information distribution system 14, the viewer terminal 10, the video information server 12, and the advertisement server 1 described above.
The operation of the entire system including 3 will be described with reference to the drawings. FIG. 11: is a figure which shows operation | movement of the whole system containing the information delivery system 14 in 1st embodiment of this invention. First, the advertisement server 1 is processed by the registration processing unit 18.
3 receives registration of advertisement information including distribution conditions (t
1). Next, the distribution demand prediction processing unit 19 predicts the number of distribution demands by referring to the distribution history database 17b (t
2). Next, the advertisement distribution number calculation processing unit 20 calculates the distribution number for each category using the evaluation function (Equation 1) based on the distribution condition and the distribution demand number (t3).

Next, the advertisement list creation processing unit 21 creates an advertisement list which is a list of combinations of categories and advertisement information to be distributed to the categories, based on the distribution numbers calculated by the advertisement distribution number calculation processing unit 20. (T4). At this point, the information distribution system 14 receives the distribution request of the advertisement information from the viewer terminal 10, and becomes in a state in which the advertisement can be distributed according to the distribution condition of the advertiser.

Next, the viewer terminal 10 requests the video information server 12 to deliver the desired video content (t).
5). In response to this, the video information server 12 delivers the video content desired by the viewer to the viewer terminal 10 (t.
6). At this time, the advertisement distribution information inserted in the video content during the reproduction of the video content is transmitted to the information distribution system 1
4 includes the requested program. Next, the video content is reproduced on the viewer terminal 10 (t
7). Here, the program requesting the advertisement information is activated, and the viewer terminal 10 transmits the request for the advertisement information to the information distribution system 14 (t8). The information transmitted by the viewer terminal 10 includes attribute information for classifying the viewer into categories together with the advertisement information.

Next, the transmission / reception processing unit 16 determines the viewer terminal 1
From 0, the advertisement request information requesting the advertisement information and the attribute information for classifying the viewers of the viewer terminal 10 into categories are received. Next, the classification processing unit 22 classifies the viewers of the viewer terminal 10 into categories based on the attribute information (t
9). Next, the advertisement distribution processing unit 23 refers to the viewer categories classified by the classification processing unit 22 and the advertisement list,
The advertisement information combined with the category is distributed to the viewer terminal 10 of the viewer (t10).

Next, the viewer terminal 10 receives the advertisement information and reproduces the advertisement information at the timing defined by the video content (t11). Next, the information distribution system 1
4 stores the history of distributing the advertisement information in the distribution history database 17b (t12). As shown above,
The information distribution system 14 can control distribution of advertisement information according to the evaluation value set by the advertiser.

Next, as an information distribution system according to the second embodiment of the present invention, an embodiment of the information distribution system which differs from the above-described first embodiment in the following two points will be described.
An information distribution system that distributes advertisement information for displaying an advertisement in a part of a Web page or another small window instead of distributing the advertisement information at the time of distributing the video content described above. An information distribution system that calculates an advertisement fee corresponding to the evaluation value set for each advertisement by the advertiser. FIG. 12 is a block diagram showing the overall configuration of the information distribution system in the second embodiment of the present invention.

As shown in FIG. 12, the Web server 100 replaces the video information server 12 of FIG.
0 to provide Web contents. Viewer terminal 10 is W
When requesting and displaying the Web content to the eb server 100, a distribution request for the advertisement information is transmitted to the information distribution system 14. As a result, the information distribution system 14 becomes
Advertisement information for displaying an advertisement on a part of the eb page or another small window is transmitted to the viewer terminal 10.

Further, in the configuration of the information distribution system 14, a unit price calculation processing section 24 and an advertisement fee processing section 25 are added. The unit price calculation processing unit 24 calculates the advertisement unit price, which is the distribution cost of each advertisement, based on the number of distributed advertisements calculated by the number of distributed advertisement calculation processing unit 20. The advertisement fee processing unit 25 increases or reduces the advertisement unit price of the advertisement according to the evaluation value set for each advertisement by the advertiser.

Next, the information delivery system 14, the viewer terminal 10, the Web server 100, and the advertisement server 1 described above.
The operation of the entire system including 3 will be described with reference to the drawings. FIG. 13 is a diagram showing the operation of the entire system including the information distribution system 14 according to the second embodiment of the present invention. Here, from the process of receiving the registration of the advertisement information including the distribution condition from the advertisement server 13, the advertisement list creation processing unit 2
The process from t21 to t23 in which 1 creates the advertisement list is similar to the process from t1 to t4 in FIG.

Next, the unit price calculation processing section 24 charges a fee when one advertisement is distributed to the viewers of each category based on the information such as the predicted distribution demand number and the calculated distribution number of each advertisement. Calculate the advertisement unit price, which is the fee that is paid. The unit price calculation processing unit 24 may calculate the distribution charge by referring to the distribution charge information in which a predetermined charge is determined according to each category and the time zone for distribution. Next, the advertisement fee processing unit 25 increases or discounts the advertisement unit price calculated by the unit price calculation processing unit 24 according to the evaluation value set by the advertiser for each advertisement.
The final advertisement unit price is calculated (t24). at this point,
The information distribution system 14 receives the distribution request of the advertisement information from the viewer terminal 10, and becomes in a state in which the advertisement can be distributed according to the distribution conditions of the advertiser.

Next, the viewer terminal 10 is the Web server 1
00 to request delivery of desired Web content (t2
5). In response to this, the web server 100 delivers the web content desired by the viewer to the viewer terminal 10 (t26). In response to this, the web server 100 delivers the web content desired by the viewer to the viewer terminal 10 (t26). At this time, the W
A program for requesting the information distribution system 14 for advertisement information to be inserted into a part of the eb contents is included. Next, the web content is displayed on the viewer terminal 10 (t27). Here, the program for requesting advertisement information is activated, and the viewer terminal 10 transmits a request for advertisement information to the information distribution system 14 (t28). The information transmitted by the viewer terminal 10 includes attribute information for classifying the viewer into categories together with the advertisement information.

Next, the transmission / reception processing section 16 determines the viewer terminal 1
From 0, the advertisement request information requesting the advertisement information and the attribute information for classifying the viewers of the viewer terminal 10 into categories are received. Next, the classification processing unit 22 classifies the viewers of the viewer terminal 10 into categories based on the attribute information (t2).
9). Next, the advertisement distribution processing unit 23 refers to the viewer categories classified by the classification processing unit 22 and the advertisement list,
The advertisement information combined with the category is distributed to the viewer terminal 10 of the viewer (t30).

Next, the viewer terminal 10 receives the advertisement information and reproduces the advertisement information as a part of the Web content (t31). Next, the information distribution system 14 stores the history of distributing the advertisement information in the distribution history database 17b (t32). Further, the advertisement fee processing unit 25 calculates the advertisement fee associated with the record of delivering each advertisement based on the delivery history (t33). Next, the transmission / reception processing unit 16 determines the advertisement fee for each advertisement calculated by the advertisement fee processing unit 25.
3 is notified (t34). As described above, the information distribution system 14 can perform distribution of advertisement information according to the evaluation value set by the advertiser and control of the advertisement fee according to the evaluation value.

In the above-described embodiment, the fee charged to the advertiser is determined based on the number of delivery records for each advertisement, but the advertiser in each advertisement is determined according to the evaluation value set for each advertisement by the advertiser. You may decide the fee to be charged to. As a result, the basis for calculating the advertisement fee is not the actual delivery number of each advertisement that fluctuates greatly, and the advertisement fee calculation process is simplified.
Further, in the above-described embodiment, the advertisement list creation processing unit 2
The timing at which 1 creates the advertisement list is after the advertisement distribution number calculation processing unit 20 has calculated the distribution number. However, this is not limited to this, and after the advertisement information distribution request is received from the viewer terminal 10, or The advertisement list may be created at predetermined time intervals. At this time, the number of pieces of advertisement information included in the advertisement list may be any number.

Further, in the above-described embodiment, the evaluation value set by the advertiser and used by the advertisement distribution number calculation processing section 20 is a weighted value, but the present invention is not limited to this, and the ratio is based on the ratio of normalized numbers. It may be a value or a percentage value. Here, an example of an evaluation function in which a ratio is an evaluation value is shown in (Equation 6) below.

[Equation 3] Note that in (Equation 6), x _ijt indicates the number of deliveries at the advertisement i, the viewer j, and the time t. Further, x ′ _i (t) indicates the number of delivery records of the advertisement i at the time t. Also, p _ijt
Is a value in which the advertiser sets the priority at which the advertisement i is to be distributed to the viewer j at a time t.

N _i is the total number of advertisements set by the advertiser and delivered. N ′ _i (t) indicates the total number of record distributions of advertisement i distributed by time t. M _jt is
Indicates the expected number of advertisement delivery demands. T _i indicates the number of unit hours when the period in which the advertisement i is delivered is changed from T _si (delivery start) to T _ei (delivery end). As described above, the advertisement distribution number calculation processing unit 20 causes the evaluation function (Expression 6) and (Expression 6).
By using (Equation 7) and (Equation 8) that define the variable of, the constraint function (Equation 9), (Equation 10), (Equation 11), (Equation 12) is satisfied, and the evaluation function (Equation 6) is The distribution number x _ijt having the minimum value is calculated.

Further, as a method of classifying the viewer category, in addition to the classification according to age and sex described above, MCR for estimating the viewer's viewing time zone in the future from the viewer's past viewing time zone pattern. (Media
It is preferable to use a Contact Report method or a collaborative filtering method for grouping viewers who have similar tastes based on the viewing history of the video content.

Further, a program for realizing the function of a processing unit for performing various processes in FIG. 1 is recorded in a computer-readable recording medium, and the program recorded in this recording medium is read into a computer system and executed. You may perform each process by doing. The “computer system” mentioned here includes an OS and hardware such as peripheral devices. Also, "computer system" means a home page providing environment (or display environment) if a WWW system is used.
Shall also be included.

The "computer-readable recording medium" means a flexible disk, a magneto-optical disk,
A portable medium such as a ROM or a CD-ROM, or a storage device such as a hard disk built in a computer system. Furthermore, "computer-readable recording medium"
Is a volatile memory (RAM) inside a computer system that serves as a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, and holds the program for a certain period of time. It also includes things.

Further, the above program may be transmitted from a computer system in which the program is stored in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. Further, the program may be for realizing a part of the functions described above. Further, it may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system. Although the embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and includes a design and the like within a range not departing from the gist of the present invention.

[0080]

As described above, in the information distribution system according to the present invention, the evaluation value and the distribution function are used as variables based on the distribution demand number prediction information and the distribution condition information defined for each advertisement. Based on the distribution number calculated by the advertisement distribution number calculation means for calculating the distribution number based on the value of the evaluation function satisfying the constraint condition defined by the distribution condition information and the distribution demand prediction information, and the distribution number calculated by the advertisement distribution number calculation means, It is provided with an advertisement list creating means for creating an advertisement list, and an advertisement delivery means for identifying a category of a viewer, referring to the advertisement list, and delivering advertisement information combined with the identified category to a viewer terminal. Therefore, when distributing the advertisement information, it is possible to control the distribution of the advertisement information according to the evaluation value set by the advertiser. Further, since the advertisement distribution number calculation means calculates the distribution number of the advertisement information using the distribution demand number, it is possible to optimally manage the distribution number of the advertisement information corresponding to the fluctuation of the distribution demand number. . As a result, the advertiser can narrow down the target for delivering the advertisement more accurately, and can perform efficient advertising activities.

In the information distribution system according to the present invention, the distribution history database storing the distribution history in which the category of the viewer and the distribution date and time are associated with the advertisement information distributed to the viewer terminal, and the distribution history. A distribution demand number predicting unit that statistically processes the past distribution count in arbitrary date / time units by category with reference to the distribution history from the database and predicts the distribution demand count in a predetermined period in the date / time unit based on the statistical processing result. Since the distribution demand of past viewers is statistically processed for each viewer category, it is possible to accurately predict the future distribution demand number of advertisement information. As a result, it is possible to efficiently place and receive advertisements even in an advertisement distribution service via a network in which demand changes drastically.

Further, in the information distribution system according to the present invention, the advertisement distribution number calculation means calculates the distribution number on a date / time basis, and therefore calculates the distribution number on a date / time basis combined with the viewer's distribution demand cycle. As a result, it is possible to calculate the number of distributions with higher accuracy.

Further, in the information distribution system according to the present invention, the attribute information includes information on the video content being viewed on the viewer terminal, and the advertisement distribution number calculation means relates to the video content included in the attribute information. Since the number of distributions is calculated by further using the information as an evaluation value, the information distribution system can provide the viewer terminal with advertisement information that reflects the content of the video content that the viewer is viewing. As a result, it is possible to distribute the advertisement information in consideration of the viewer's preference.

Further, in the information distribution system according to the present invention, the advertisement list creating means is adapted to maintain the appearance probability according to the ratio of the distribution number of each advertisement to the total distribution number of advertisements of each category. Since the advertisement list that determines the order is created, the advertisement can be distributed according to the ratio of the distribution number of each advertisement assigned to each category.
As a result, of each advertisement assigned to each category,
It is possible to prevent distribution that is biased toward a specific advertisement.

In the information distribution system according to the present invention, the advertisement list creating means creates an advertisement list by extracting advertisement information matching the search condition based on the advertisement information assigned to the category according to the number of distributions. Therefore, it is possible to perform more targeted advertisement delivery in the assigned advertisement information. This allows you to refer to the time zone and viewer information to identify advertisements that should not be delivered, and to reflect past advertisement history, information that the viewer is currently watching, and information about the web page that you are viewing. The advertisement information can be searched and provided.

Further, the information distribution system according to the present invention further comprises an advertisement charge processing means for calculating the increase or decrease of the distribution charge of the advertisement for which the evaluation value is set according to the evaluation value, and therefore the evaluation value is high. It is possible to increase or decrease the distribution charge according to the evaluation value, for example, by increasing the distribution charge of the advertisement for the set advertisement (the advertisement having higher priority than other advertisements). As a result, by increasing the delivery charge to the popular time zone or category, it is possible to prevent the evaluation value from being set high by concentrating on the time zone or category. Also, in the contract between the advertisement distributor and the advertiser, if the advertisement fee is charged by guaranteeing that the advertisement is prioritized by setting the evaluation value instead of guaranteeing the number of distribution, It becomes unnecessary for the advertiser to make a budget because it is not necessary to predict or correct the deviation with respect to the prediction, and the advertisement distributor can easily calculate the advertisement fee with the advertiser.

[Brief description of drawings]

FIG. 1 is a block diagram showing an overall configuration of an information distribution system according to a first embodiment of the present invention.

FIG. 2 is a diagram showing a schematic configuration of an advertisement information database 17a in the first embodiment of the present invention.

FIG. 3 is a distribution history database 17b and a viewer information database 17c according to the first embodiment of the present invention.
It is a figure which shows schematic structure of.

FIG. 4 is a diagram showing an example in which an evaluation value of each advertisement is set for each viewer according to the first embodiment of the present invention.

FIG. 5 is a diagram showing an example in which an evaluation value of each advertisement is set for each group according to the first embodiment of the present invention.

FIG. 6 is a diagram showing an example of a distribution demand number predicted by a distribution demand number prediction processing unit 10 according to the first embodiment of the present invention.

FIG. 7 is a flowchart showing the operation of the distribution demand number prediction processing unit 19 in the information distribution system 14 according to the first embodiment of the present invention.

FIG. 8 is a flowchart showing an operation of the advertisement distribution number calculation processing section 20 in the information distribution system 14 according to the first embodiment of the present invention.

FIG. 9 is a diagram showing an example in which a distribution number calculated by the advertisement distribution number calculation processing unit 20 is assigned to each viewer according to the first embodiment of the present invention.

FIG. 10 is a diagram showing an example in which a distribution number calculated by an advertisement distribution number calculation processing unit 20 is assigned to a category for each advertisement according to the first embodiment of the present invention.

FIG. 11 is a diagram showing an operation of the entire system including the information distribution system 14 according to the first embodiment of the present invention.

FIG. 12 is a block diagram showing an overall configuration of an information distribution system according to a second embodiment of the present invention.

FIG. 13 is a diagram showing an operation of the entire system including the information distribution system 14 according to the second embodiment of the present invention.

[Explanation of symbols]

10 Viewer terminal 11 network 12 Video information server 13 Advertising server 14 Information distribution system 15 Control unit 16 Transmission / reception processing unit 17 Database 17a Advertising information database 17b Delivery history database 17c Viewer information database 18 Registration Processing Department 19 Distribution demand number prediction processing unit 20 Advertising distribution number calculation processing unit 21 Advertising list creation processing unit 22 Classification processing unit 23 Advertising distribution processing unit 24 Unit price calculation processing unit 25 Advertising fee processing section

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) // H04N 7/173 610 H04N 7/173 610Z 17/00 17/00 Z (72) Inventor Koji Miyajima Tokyo 3-3 Toyosu 3-3 Toyosu, Koto-ku, Ltd. In NTT DATA (72) Inventor Nahoko Toda 3--3-3 Toyosu, Koto-ku, Tokyo In NTT DATA (72) Inventor Akio Iijima 1-11-10 Tsukiji, Chuo-ku, Tokyo Inside the Dentsu Stock Company (72) Inventor Tomohiko Yukawa 1-1-11 Tsukiji, Chuo-ku, Tokyo Inside the Dentsu Stock Company (72) Kyuya Suga 1-11-10 Tsukiji, Chuo-ku, Tokyo F-Term in Stock Company Dentsu (reference) 5C061 BB03 CC05 5C064 BA07 BB01 BB10 BC04 BC18 BC20 BD02 BD08

Claims (10)

[Claims] 1. An information distribution system for controlling distribution of advertisement information to a viewer terminal capable of being connected to a network and displaying video contents, wherein the distribution demand number within a predetermined period is classified according to viewer categories. Based on distribution demand number prediction information that is information to be predicted, and distribution condition information that defines an evaluation value that is an arbitrarily weighted value by the advertiser according to at least the planned distribution number, distribution period, category and distribution date and time for each advertisement , An advertisement distribution number that calculates the distribution number based on a value of the evaluation function that satisfies a constraint condition defined by the distribution condition information and the distribution demand forecast information, using an evaluation function having the evaluation value and the distribution number as variables Based on the distribution means calculated by the calculation means and the advertisement distribution number calculation means,
An advertisement list creating means for creating an advertisement list that is a list of a combination of the category and the advertisement information to be distributed to the category; the category of the viewer; An information delivery system, comprising: an advertisement delivery means for delivering the advertisement information combined with a category to the viewer terminal of the viewer. 2. A distribution history database storing a distribution history in which the category and distribution date and time of the viewer are associated with the advertisement information distributed to the viewer terminal; and the distribution history from the distribution history database. With reference to the category, a distribution demand number predicting unit that statistically processes the past distribution number in an arbitrary date and time unit and predicts the distribution demand number in the predetermined period in the date and time unit based on the statistical processing result. The information distribution system according to claim 1, wherein: 3. The information distribution system according to claim 1, wherein the advertisement distribution number calculation means calculates the distribution number in units of date and time. 4. The attribute information includes information about a video content being viewed on the viewer terminal, and the advertisement distribution number calculation means further distributes the information about the video content included in the attribute information as an evaluation value. The information distribution system according to claim 1, wherein the number is calculated. 5. The advertisement list creating means determines the advertisement distribution order so as to maintain an appearance probability according to a ratio of the distribution number of each advertisement to the total distribution number of the advertisement for each category. The information distribution system according to any one of claims 1 to 4, wherein 6. The advertisement list creating means creates the advertisement list by extracting advertisement information that matches a search condition based on the advertisement information assigned to the category according to the distribution number. Claims 1 to 5
The information distribution system described in any of. 7. The method according to claim 1, further comprising an advertisement fee processing means for calculating an increase or decrease in a delivery fee of an advertisement for which the evaluation value is set, according to the evaluation value.
The information distribution system described in any of. 8. A program for an information distribution system that controls distribution of advertisement information to a viewer terminal that is connectable to a network and that displays video content, and distributes within a predetermined period according to the categories of viewers. Distribution demand number prediction information that is information that predicts the demand number, and distribution condition information that determines an evaluation value that is an arbitrarily weighted value by the advertiser according to at least the planned distribution number, the distribution period, the category and the distribution date and time for each advertisement. On the basis of the above, by using an evaluation function having the evaluation value and the number of distributions as variables, the number of distributions is calculated based on the value of the evaluation function satisfying the constraint condition determined by the distribution condition information and the distribution demand prediction information. Step: Create an advertisement list that is a list of combinations of the category and the advertisement information to be distributed to the category, based on the calculated number of distributions And a step of identifying the category of the viewer, referring to the advertisement list, and delivering the advertisement information combined with the identified category to the viewer terminal of the viewer. A program to run to. 9. The distribution history database for storing the distribution history in which the category and distribution date and time of the viewer are associated with the advertisement information distributed to the viewer terminal, the distribution history is referred to, and 9. The computer according to claim 8, further comprising: statistically processing a past distribution number in an arbitrary date / time unit for each category and predicting the distribution demand number in the predetermined period in the date / time unit based on the statistical processing result. program. 10. The program according to claim 8, wherein the step of calculating the number of distributions calculates the number of distributions in units of date and time.