JP2015153042A - Calculation device, calculation method and calculation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve revenue acquired by distribution of advertisement content.SOLUTION: A calculation device of the application comprises an acquisition unit and a calculation unit. The acquisition unit acquires time variation of a billing allowable amount which allows a cumulative value of a billing amount which is charged according to the number of times that advertisement content has been clicked. The calculation unit calculates distribution probability on the basis of the time variation of the billing allowable amount acquired by the acquisition unit.

Description

  The present invention relates to a calculation device, a calculation method, and a calculation program.

  In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has been actively performed. For example, an advertisement content such as a company or a product (for example, an icon such as an image) is displayed at a predetermined position on a web page, and when the advertisement content is clicked, there is a transition to an advertiser's web page.

  Such advertisement content is often distributed by an advertisement distribution device that holds advertisement content submitted by each advertiser. For example, as the advertisement distribution by the advertisement distribution apparatus, a technique for controlling the advertisement distribution so as not to exceed a budget allocation amount in which the advertisement budget is equally distributed in the advertisement insertion period is known. According to this technique, since the advertising budget is evenly consumed as time passes, it can be considered that the situation in which the advertising content is not distributed earlier than expected can be prevented from the expiration date of the advertising period.

JP2011-65201A

  However, with the above-described conventional technology, it is not always possible to improve the profits obtained by distributing the advertising content. Specifically, in the above-described conventional technology, the advertisement distribution device preferentially distributes advertisement content with a high bid price. Further, the advertisement distribution device stops the distribution of the advertisement content when the accumulated value of the billing amount of the advertisement content exceeds the budget allocation amount. For this reason, for example, the advertisement distribution apparatus has a low bid price during a time period when the distribution of the advertisement content with a high bid price is stopped by giving priority to the distribution of the advertising content with a high bid price. Deliver the set advertising content. For this reason, with the above-mentioned conventional technology, there is a possibility that even advertising content with a low bid price may be distributed, so advertisers can set a low bid price without competing to distribute the advertising content. There is a case. For this reason, in the above-described conventional technology, it is not always possible to improve the profits obtained by distributing the advertising content.

  The present application has been made in view of the above, and an object thereof is to provide a calculation device, a calculation method, and a calculation program capable of improving the profits obtained by distributing advertisement content.

  The distribution apparatus according to the present application includes an acquisition unit that acquires a time variation of an allowable charge amount that allows an accumulated value of an charged amount that is charged according to the number of times the advertisement content is clicked, and an allowable charging amount that is acquired by the acquiring unit. And calculating means for calculating a distribution probability of distributing the advertisement content based on a temporal variation of the forehead.

  According to one aspect of the embodiment, there is an effect that it is possible to improve profits obtained by distributing advertisement content.

FIG. 1 is a diagram illustrating an example of a calculation process according to the embodiment. FIG. 2 is a diagram showing a time transition of eCPM quality. FIG. 3 is a diagram illustrating a configuration example of the advertisement distribution system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the distribution apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of the advertising content storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the allowable information storage unit according to the embodiment. FIG. 7 is a flowchart illustrating a reception processing procedure by the distribution apparatus according to the embodiment. FIG. 8 is a flowchart illustrating a distribution processing procedure performed by the distribution apparatus according to the embodiment. FIG. 9 is an explanatory diagram for explaining the distribution probability calculation process. FIG. 10 is an explanatory diagram for explaining temporal transition of the click tendency. FIG. 11 is an explanatory diagram for explaining an allowable charge amount linked with a click tendency. FIG. 12 is an explanatory diagram for explaining temporal transition of the click tendency. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the distribution apparatus.

  Hereinafter, a mode for carrying out a calculation device, a calculation method, and a calculation program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the calculation device, the calculation method, and the calculation program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. (Calculation process)
First, an example of calculation processing according to the embodiment will be described with reference to FIG. FIG. 1 is an explanatory diagram illustrating an example of a calculation process according to the embodiment. In the example of FIG. 1, calculation processing is performed by the distribution apparatus 100 illustrated in FIG. The distribution apparatus 100 is configured such that the advertiser distributes an advertisement distributor (for example, a distribution apparatus) when the advertisement content is distributed together with the advertisement content from the advertiser (that is, the advertisement content posting period) or when the advertisement content is clicked once. (100 managers) are accepted, and an advertisement budget, which is the upper limit of the advertisement fee, is specified.

  Here, an example focusing on the predetermined advertisement content AD11 will be described. The vertical axis of the graph shown in FIG. 1 indicates the billing amount that the advertisement distributor charges the advertiser according to the number of times the advertisement content AD11 is clicked. The horizontal axis of the graph shown in FIG. In the example of FIG. 1, when the advertising budget of the advertising content AD11 is equally distributed over the distribution period, the advertising budget per day is assumed to be “M10”. For example, when the distribution period is “31 days” and the advertisement budget is “310,000 yen”, the advertisement budget “M10” per day is “10,000 yen” as shown in FIG.

  Under such a premise, the distribution device of the comparative example compared with the distribution device 100 has the advertising budget M10 per day consumed evenly every predetermined time (for example, 1 second, 1 minute, or 10 minutes). As shown, the allowable charging amount BL shown in FIG. 1 is calculated as the allowable value of the accumulated charging amount that varies with time. This chargeable amount BL is expressed by the expression “chargeable amount BL = A · x” when the elapsed time is “x”. In this formula, “A” indicates the digestion rate of the advertising budget. For example, when the unit of the elapsed time “x” is minutes and the advertising budget per day is “10,000 yen”, “10,000 yen” divided by “1440 minutes” is “6.944 yen / "Minute" becomes "A". Here, the fourth decimal place of the division result is rounded off.

  Then, the distribution device of the comparative example distributes the advertising content AD11, and counts the accumulated charge amount of the advertising content AD11 when the distributed advertising content AD11 is clicked. At this time, when the accumulated charge amount exceeds the chargeable amount BL corresponding to the current date and time, the distribution device of the comparative example restricts the advertisement content AD11 from being distributed until a predetermined time has elapsed. Thereafter, the distribution device of the comparative example resumes the distribution of the advertising content AD11 when the accumulated charging amount does not exceed the allowable charging amount BL as time elapses. In this way, the distribution device of the comparative example performs the distribution control based on the above-described allowable charging amount BL every day so that the advertising budget is consumed at a constant pace, thereby completing the expiration date of the distribution period of the advertising content AD11. This prevents the advertising budget from being consumed more quickly than expected, and as a result, prevents the advertising content AD11 from being delivered earlier than expected.

  However, the number of impressions indicating the number of times advertisement content has been distributed varies depending on the time of day. For this reason, in the above-described advertisement distribution, distribution of high-value advertising content is stopped in a time zone with a large number of impressions, and there is a possibility that low-value advertising content is distributed. This point will be described with reference to FIG.

  FIG. 2 is a diagram showing temporal transition of quality of eCPM (effective Cost Per Mill). Here, eCPM indicates the amount of revenue that the provider of the web page obtains when the advertising content is displayed 1000 times on the web page. For example, eCPM is calculated by multiplying the bid price of the advertising content by CTR (Click Through Rate) and 1000. It should be noted that advertising content with a high eCPM means high-quality advertising content.

  Further, FIG. 2 shows a total value of various values of all advertisement contents distributed by the distribution device of the comparative example. In FIG. 2, the vertical axis represents the ratio of various values to the daily average. The horizontal axis indicates the time of the day. In FIG. 2, “number of impressions” indicates a total value of the number of distributions of the advertisement content distributed by the distribution device of the comparative example. “Total eCPM” indicates the total eCPM of the advertisement content actually distributed. “Total amount of eCPM that can be distributed” indicates the sum of eCPMs of the advertisement content in the state of distribution. “Average eCPM” indicates an average of eCPMs of advertisement contents actually distributed. “Quality of eCPM” indicates the quality of advertisement content actually distributed. For example, the “eCPM quality” is calculated by dividing the “distributable eCPM total amount” by the “eCPM total amount”.

  In the case of the example shown in FIG. 2, the number of impressions is the lowest value in the time zone T1 around 4 o'clock. On the other hand, the quality of eCPM becomes the highest value in the time zone T1. Further, the number of impressions is the highest in the time zone T2 around 12:00. On the other hand, the quality of eCPM becomes the lowest value in the time zone T2.

  Here, the distribution device of the comparative example preferentially distributes the advertising content having a high eCPM. Therefore, as shown in FIG. 2, the distribution device of the comparative example distributes advertising content with high eCPM quality in a time zone with a small number of impressions. This is because the ratio of the total amount of eCPM that can be distributed to the total amount of eCPM necessary for distribution is large, so that there is a wide range of selection of the advertising content to be distributed, and the advertising content with high eCPM quality is distributed preferentially. For this reason, in the time zone with a large number of impressions, the distribution device of the comparative example has already distributed the advertising content with a high eCPM quality, and stops the distribution of the advertising content with a high eCPM quality. In addition, since average eCPM advertising content with high quality is distributed, the average CTR also increases.

  Further, the distribution device of the comparative example distributes advertising content with low eCPM quality because it cannot distribute advertising content with high eCPM quality in a time zone with a large number of impressions. This is because the ratio of the total amount of eCPM that can be distributed to the total amount of eCPM necessary for distribution is small, so there is little room for selection of the advertising content to be distributed, and there are few advertising content that can be distributed with high eCPM quality. In addition, since average eCPM advertising content with low quality is distributed, the average CTR is also low.

  In general, the number of impressions tends to have such a tendency. Therefore, in the distribution device of the comparative example, there is a possibility that even advertising content with low eCPM quality is distributed. For this reason, the advertiser may set a low bid price without competing to distribute the advertising content. As a result, the advertisement distributor may miss the profit obtained by setting a high bid price.

  Therefore, the distribution apparatus 100 according to the embodiment controls the distribution of the advertising content so as not to reach the chargeable amount. Specifically, the distribution apparatus 100 calculates a distribution probability of distributing the advertising content based on the time variation of the chargeable amount. For example, the distribution apparatus 100 calculates the distribution probability that is the probability that the advertising content will be distributed and that is linked to the difference between the chargeable amount corresponding to the current date and time and the accumulated value of the charge amount. Then, the distribution device 100 distributes the advertising content based on the calculated distribution probability. This point will be described with reference to FIG. In the example of FIG. 1, the distribution apparatus 100 shows an example of calculating the distribution probability for each advertising content.

  First, when the distribution apparatus 100 receives an advertisement content acquisition request, the distribution apparatus 100 acquires a time variation of a chargeable amount that allows a cumulative value of a charge amount charged according to the number of times the advertisement content is clicked. In the example of FIG. 1, the distribution apparatus 100 acquires the chargeable amount BL shown in FIG. The chargeable amount BL is not limited to a straight line as shown in FIG. 1, but may be a curve calculated by a method described later. In addition, the distribution apparatus 100 acquires the accumulated value RL of the billing amount from the start of the distribution of the advertising content to the current date and time.

  Subsequently, the distribution device 100 is a probability that the advertisement content is distributed, and is distributed in conjunction with the difference between the chargeable amount corresponding to the current date and time of the acquired chargeable amount and the accumulated value of the charge amount. Probability is calculated. Specifically, the distribution device 100 calculates a distribution probability high at a time when the difference is large, and calculates a distribution probability low at a time when the difference is small. For example, the distribution apparatus 100 calculates the distribution probability by dividing the difference by the chargeable amount.

  In the example of FIG. 1, at the time “10 o'clock”, the distribution apparatus 100 sets the difference L1 “1116” between the chargeable amount “4166” and the accumulated value “3000” of the chargeable amount to the chargeable amount B1 “4166”. The distribution probability P1 “28%” is calculated. On the other hand, at time “20:00”, the distribution apparatus 100 divides the difference L2 “332” between the chargeable amount “8332” and the accumulated value of the charge amount “8000” by the chargeable amount B2 “8332”. Thus, the distribution probability P2 “4%” is calculated.

  The distribution apparatus 100 according to the embodiment calculates an advertisement budget per day, and performs the above-described distribution control for each day in the advertisement content distribution period. Here, the distribution device 100 according to the embodiment has a high probability of advertising content when there is a sufficient difference between the chargeable amount and the accumulated value of the charge amount (for example, time “10” in FIG. 1). Therefore, the advertisement content can be distributed so as to approach the upper limit of the allowable charge amount. Thereby, the distribution apparatus 100 can increase the possibility of using the advertising budget. Further, when the difference between the chargeable amount and the accumulated value of the charge amount is tight (for example, time “20” in FIG. 1), the distribution device 100 distributes the advertising content with a low probability. The advertising content can be distributed so as not to exceed the chargeable amount. As a result, the distribution apparatus 100 can reduce the possibility that the advertising content will be stopped.

  As described above, the distribution apparatus 100 according to the embodiment acquires the time variation of the chargeable amount that allows the accumulated value of the chargeable amount charged according to the number of times the advertisement content is clicked, and acquires the acquired chargeable amount. The distribution probability of distributing the advertisement content is calculated based on the time variation of the.

  Thereby, since the distribution apparatus 100 can prevent the distribution of the advertising content from being stopped, the range of selection of the advertising content can be widened regardless of the time zone during the distribution period. For this reason, the distribution apparatus 100 may average the quality of the advertisement content distributed during the distribution period as compared to the case where the difference in the quality of the advertisement content distributed in the time period as shown in FIG. 2 is large. it can. Further, since the distribution apparatus 100 can prevent the high bid price advertisement content from being stopped from being distributed, the distribution device 100 can prevent the low bid price advertisement content from being distributed. Thereby, since the distribution apparatus 100 can compete with the advertiser in order to distribute the advertising content, the advertiser can set a high bid price. For this reason, the distribution apparatus 100 can improve the profits obtained by distributing the advertising content.

[2. Configuration of advertisement distribution system)
Next, the configuration of the advertisement distribution system according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the advertisement distribution system 1 according to the embodiment. As illustrated in FIG. 3, the advertisement distribution system 1 includes a terminal device 10, advertiser apparatuses 20 _{1 to} 20 _n , an information providing apparatus 30, and a distribution apparatus 100. The terminal device 10, the advertiser devices 20 _{1 to} 20 _n , the information providing device 30, and the distribution device 100 are connected via a network N so that they can communicate with each other by wire or wirelessly. 3 may include a plurality of terminal devices 10, a plurality of information providing devices 30, and a plurality of distribution devices 100.

  The terminal device 10 is an information processing device such as a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, or a PDA (Personal Digital Assistant). For example, the terminal device 10 obtains a web page from the information providing device 30 by accessing the information providing device 30 and displays the obtained web page on a display device (for example, a liquid crystal display). Further, when the web page includes an advertising space, the terminal device 10 accesses the distribution device 100 to acquire the advertisement content from the distribution device 100 and displays the acquired advertisement content on the web page. However, the present invention is not limited to this example, and the terminal device 10 may acquire a web page including advertisement content from the information providing device 30. In this case, the information providing apparatus 30 distributes the web page in which the advertisement content distributed by the distribution apparatus 100 is incorporated to the terminal apparatus 10.

The advertiser apparatuses 20 _{1 to} 20 _n are information processing apparatuses that are used by advertisers who request the distribution apparatus 100 to distribute advertisements. The advertiser apparatuses 20 _{1 to} 20 _n submit the advertising content to the distribution apparatus 100 in accordance with an operation by the advertiser. The advertiser apparatuses 20 _{1 to} 20 _{n according to the} embodiments include a still image, a moving image, text data, and a URL (Uniform Resource Locator) for accessing a web page provided by an advertiser server managed by the advertiser. ) And the like are submitted to the distribution apparatus 100.

In addition, advertisers, using an advertiser devices 20 ₁ ~20 _n, without traffic your ad content to the distribution apparatus 100, there is also a case to ask the agency trafficking of advertising content. In this case, it is the agency that submits the advertising content to the distribution apparatus 100. In the following, the term “advertiser” is a concept that includes not only the advertiser but also the agency, and the term “advertiser device” includes the agency device used by the agency as well as the advertiser device. It is assumed to be a concept. In addition, since the advertiser apparatuses 20 _{1 to} 20 _n have the same functions, in the following, when it is not necessary to distinguish the advertiser apparatuses 20 _{1 to} 20 _n , they are collectively referred to as “advertiser apparatus”. 20 ”.

  The information providing device 30 is a web server or the like that provides a web page to the terminal device 10. The information providing apparatus 30 is, for example, various websites related to news sites, auction sites, weather forecast sites, shopping sites, finance (stock price) sites, route search sites, map providing sites, travel sites, restaurant introduction sites, web blogs, and the like. Provide a page.

  The distribution apparatus 100 is a server apparatus that distributes advertising content submitted from the advertiser apparatus 20. As described above, the distribution device 100 distributes the advertising content to the terminal device 10 when accessed from the terminal device 10. Further, when accessed from the information providing apparatus 30, the distribution apparatus 100 distributes the advertising content to the information providing apparatus 30.

[3. Configuration of distribution device]
Next, the configuration of the distribution apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the distribution apparatus 100 according to the embodiment. As illustrated in FIG. 4, the distribution apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The distribution apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the distribution apparatus 100, and a display unit (for example, a liquid crystal display) that displays various types of information. You may have.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the terminal device 10, the advertiser device 20, and the information providing device 30 via the network N.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes an advertisement content storage unit 121 and an allowable information storage unit 122.

(Advertising content storage unit 121)
The advertising content storage unit 121 stores the advertising content submitted from the advertiser device 20. Here, FIG. 5 illustrates an example of the advertisement content storage unit 121 according to the embodiment. In the example illustrated in FIG. 5, the advertisement content storage unit 121 includes items such as “advertiser ID”, “advertisement content”, “bid price”, “distribution period”, “advertisement budget”, and “cumulative billing amount”. .

  The “advertiser ID” indicates identification information for identifying the advertiser or the advertiser device 20. “Advertising content” indicates the advertising content submitted from the advertiser apparatus 20. In the example shown in FIG. 5, an example in which conceptual information such as “AD11” and “AD21” is stored in “advertising content”. However, in practice, still images, moving images, text data, URLs, and the like are stored. (Uniform Resource Locator) or a file path name indicating the storage location thereof is stored.

  “Bid price” indicates an advertising fee designated when an advertiser submits advertising content. In the present embodiment, the “bid price” is a unit price (for example, unit) of an amount charged to the advertiser by the advertisement distributor (for example, the administrator of the distribution apparatus 100) when the advertisement content is clicked once by the user. Corresponds to “yen”). “Delivery period” is information specified when an advertiser submits advertisement content, and indicates a period during which the advertisement content is posted on a web page. “Advertising budget” is information specified when an advertiser submits advertising content, and indicates an upper limit value of an advertising fee (that is, a cumulative billing amount) paid by an advertiser to an advertisement distributor. In addition, GSP (Generalize Second Price) that adopts the second highest bid price as the unit price of the amount charged to the advertiser may be applied to the “bid price”.

  The “cumulative charge amount” indicates an advertisement charge charged to the advertiser at the present time. Specifically, the “cumulative billing amount” corresponds to a value obtained by multiplying the number of times the advertisement content is clicked by the bid price. The “cumulative billing amount” is updated by the distribution unit 136 described later.

  That is, in FIG. 5, the advertiser identified by the advertiser ID “AP10” has the bid price “10 yen”, the distribution period “January 1, 2013 to January 31, 2013”, and the advertising budget “310,000”. In this example, “Yen” is designated and the advertisement content “AD11” is submitted. FIG. 5 shows an example in which the accumulated charge amount due to the advertisement distribution of the advertisement content “AD11” is “100,000 yen” at the present time.

  Although not shown in FIG. 5, the advertisement content storage unit 121 may store “CTR” or the like. “CTR” indicates an advertising effect when advertising content is distributed to the terminal device 10. For example, “CTR” corresponds to a value obtained by dividing the number of times the advertising content is clicked by the user by the number of times the advertising content is displayed.

(Allowable information storage unit 122)
The permissible information storage unit 122 stores information related to a permissible charge amount that is a permissible value of the accumulated charge amount. Note that the allowable information storage unit 122 according to the embodiment stores an allowable charging amount for each advertising content. Here, FIG. 6 illustrates an example of the allowable information storage unit 122 according to the embodiment. In the example illustrated in FIG. 6, the allowable information storage unit 122 includes items such as “advertisement content”, “target period”, “digestion reference amount”, and “accumulated charge amount within the control period”.

  “Advertising content” corresponds to the advertising content shown in FIG. 5 and indicates advertising content that can be distributed by the distribution apparatus 100. The “target period” indicates the date and time when the advertising content can be distributed. FIG. 6 shows an example in which only the time zone in which the date is not specified is stored in the “target period”. “Digestion standard amount” indicates the digestion rate of the advertising budget. Specifically, the “digestion reference amount” corresponds to “A” in the expression “B = A · x” representing the “acceptable charge amount B”. As described above, “x” indicates an elapsed time (in this example, the unit is “minute”) since the delivery of the advertising content is started.

  “Accumulated charge amount within the control period” indicates the accumulated charge amount during the control period corresponding to the current date and time when the distribution of the advertisement content is performed by the distribution apparatus 100 in units of a predetermined period. For example, in the case of the example illustrated in FIG. 1, the distribution apparatus 100 performs distribution control based on the chargeable amount BL every day. In this example, the accumulated charge amount up to the current date on the current date is stored in the “accumulated charge amount within the control period” of the allowable information storage unit 122. This “accumulated charge amount within the control period” is cleared to “0” every day, and the accumulated charge amount per day is stored as needed.

  That is, FIG. 6 shows an example in which, when the advertising content “AD11” is distributed between “0:00 and 24:00”, it is allowed to charge at a pace of “6.944 yen” per minute. Yes. FIG. 6 shows an example in which the accumulated charge amount at the current date and time is “3000 yen” among the accumulated charge amounts of the advertisement content “AD11”.

  In the example of FIG. 6, an example in which the time zone in which the date is not specified is stored in the “target period”, but the date, day, and day of the week may be stored in the “target period”. In the example of FIG. 6, an example in which the digestion pace per minute is stored in the “digestion reference amount” is shown. However, the “digestion reference amount” includes the digestion pace per second and the digestion rate per 10 minutes. The digestion pace, the digestion pace per hour, and the like may be stored.

(About the control unit 130)
The control unit 130 is configured such that, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like stores various programs (corresponding to an example of a distribution program) stored in a storage device inside the distribution apparatus 100 in the RAM. This is realized by being executed as The control unit 130 is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 4, the control unit 130 includes a reception unit 131, a calculation unit 132, a reception unit 133, an acquisition unit 134, a calculation unit 135, and a distribution unit 136, which will be described below. Implement or execute information processing functions and actions. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as the information processing described below is performed. In addition, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 4, and may be another connection relationship.

(About the reception unit 131)
The accepting unit 131 accepts submission of advertising content from the advertiser device 20 and stores the accepted advertising content in the advertising content storage unit 121. Specifically, the accepting unit 131 accepts the submission of the advertisement content together with the designation of the bid price, the delivery period, and the advertisement budget, and advertises the bid price, the delivery period, and the advertisement budget in association with the submitted advertisement content. It is stored in the content storage unit 121. At this time, the reception unit 131 also stores the advertiser ID corresponding to the advertiser who is the source of the advertisement content in the advertisement content storage unit 121.

(About the calculation unit 132)
The calculation unit 132 calculates a chargeable amount for each advertisement content. Specifically, the calculation unit 132 calculates the time variation of the chargeable amount based on the distribution period and the advertisement budget received by the reception unit 131. Here, the calculation unit 132 calculates the time variation of the chargeable amount B by obtaining “digestion reference amount A” in the expression “B = A · x” representing the chargeable amount B.

  Here, an example of processing for calculating the allowable charge amount by the calculation unit 132 will be described with reference to FIG. In this example, it is assumed that the unit of the period during which the distribution control of the advertising content is performed by the distribution apparatus 100 is “1 day”. In other words, the distribution apparatus 100 performs distribution control that uses the advertising budget per day every day. Here, as in the example of FIG. 1, an example in which attention is paid to a predetermined advertisement content AD11 will be described.

  First, the calculation unit 132 calculates an advertisement budget per control period in which the distribution control of the advertisement content AD11 is performed by the distribution apparatus 100. Specifically, since the unit of the control period is “1 day” in this example, the calculation unit 132 acquires the distribution period and the advertising budget of the advertising content AD11 from the advertising content storage unit 121, and acquires the acquired advertising budget. Is divided by the number of days in the distribution period to calculate the advertising budget per day. Here, it is assumed that the daily advertising budget “M10” is “10,000 yen”.

  Subsequently, the calculation unit 132 calculates the digestion reference amount A “6.944 yen / minute” by dividing the advertising budget “10,000 yen” per day by “1440 minutes” that is the daily unit. To do. Such an inclination in the time variation of the chargeable amount corresponds to the “digestion reference amount A” described above. That is, the calculation unit 132 stores the calculated inclination in the digestion reference amount of the allowable information storage unit 122.

  Note that the calculation unit 132 performs such calculation processing for each advertising content received by the reception unit 131. In the above example, the calculation unit 132 shows an example of calculating the advertising budget per control period (in the above example, the advertising budget per day). However, the present invention is not limited to this example, and the reception unit 131 calculates an advertising budget per control period at the time of receiving the submission of the advertising content, and the calculated advertising budget per control period is used as the advertising content storage unit 121. Alternatively, it may be stored in the allowable information storage unit 122.

(Receiver 133)
The receiving unit 133 receives an advertisement content acquisition request from the terminal device 10 or the information providing device 30. For example, the receiving unit 133 receives an advertisement content acquisition request by an HTTP (Hypertext Transfer Protocol) request or the like.

  Note that an apparatus that transmits an advertisement content acquisition request to the reception unit 133 differs depending on a web page distributed by the information providing apparatus 30. For example, when a web page in which a URL for accessing the distribution device 100 is embedded is distributed to the terminal device 10, the reception unit 133 receives an advertisement content acquisition request from the terminal device 10. Further, when a web page in which advertisement content is already embedded is distributed to the terminal device 10, the reception unit 133 receives an advertisement content acquisition request from the information providing device 30. In the present embodiment, it is assumed that the receiving unit 133 receives an advertisement content acquisition request from the terminal device 10.

(About the acquisition unit 134)
The acquisition unit 134 acquires the accumulated charging amount and the charging allowable amount corresponding to the current date and time. Specifically, when the receiving unit 133 receives the advertisement content acquisition request, the acquiring unit 134 multiplies the elapsed reference time amount stored in the allowable information storage unit 122 by the elapsed time at the current date and time. By doing so, the allowable charge amount at the present time is calculated. For example, the acquisition unit 134 substitutes the calculated digestion reference amount A and the elapsed time (minutes) of the day into an expression “B = A · x” representing the chargeable amount B, thereby calculating the chargeable amount B. Calculate time variation. As an example, when the current time is 10:00, the acquisition unit 134 multiplies the digestion reference amount A “6.944 yen / min” by the elapsed time “10 × 60 minutes” per day. Thus, the allowable charge amount “4166 yen” is calculated. Thereby, the acquisition unit 134 acquires the accumulated charge amount corresponding to the current date and time and the allowable charge amount corresponding to the current date and time.

(About the calculation unit 135)
The calculation unit 135 calculates the distribution probability of distributing the advertisement content based on the time variation of the chargeable amount acquired by the acquisition unit 134. Specifically, the calculation unit 135 is the probability that the advertising content will be distributed, and includes the chargeable amount corresponding to the current date and time of the chargeable amount acquired by the acquisition unit 132 and the accumulated value of the charge amount. The distribution probability linked to the difference between the two is calculated. For example, the calculation unit 135 calculates a distribution probability that is linked to the ratio of the difference between the chargeable amount with respect to the chargeable amount corresponding to the current date and time and the cumulative value of the charge amount.

This point will be described in detail using equations (1) to (4). First, the calculation unit 135 calculates the difference between the chargeable amount corresponding to the current date and time acquired by the acquisition unit 134 and the accumulated value of the charge amount. Subsequently, the calculation unit 135 calculates the distribution probability using the difference between the chargeable amount corresponding to the current date and time and the accumulated value of the charge amount. The distribution probability P _{it at} the time t of the advertisement content i is expressed by the following equation (1).

Here, “B _it ” indicates the chargeable amount at the time t of the advertisement content i. “L _it ” indicates the difference between the chargeable amount at the time t of the advertisement content i and the accumulated value of the charge amount. “K” indicates a correction coefficient that corrects the distribution probability so that the difference between the allowable charge amount and the accumulated value of the charge amount in all advertisement contents is minimized. The calculation unit 135 multiplies the ratio of the difference between the chargeable amount with respect to the chargeable amount corresponding to the current date and time and the accumulated value of the charge amount by a correction coefficient, thereby allowing the charge allowance while digesting the advertising budget as much as possible. Since it is possible to calculate the distribution probability that the difference between the amount and the accumulated value of the billing amount is the smallest, the correction coefficient is calculated.

  For example, the calculation unit 135 calculates a correction coefficient that corrects the sum of the differences between the submitted advertisement contents to the minimum. The difference between the chargeable amount Q (t), which is the sum of the chargeable amounts of all advertisement contents, and the accumulated value of the charge amounts of all advertisement contents is expressed by the following equation (2).

Expression (2) is converted into the following Expression (3) by substituting Expression (1) into the distribution probability _Pit .

  Here, the correction coefficient “k” is set to a value that minimizes the squared difference of the difference expressed by the equation (3) as the following equation (4).

Then, the calculation unit 135 calculates the distribution probability P _it by substituting the calculated correction coefficient “k” into Expression (1). The correction coefficient “k” is not limited to the calculation method described above, and may be an optimal value obtained from a history of past charge amounts, for example.

  In this way, the calculation unit 135 calculates a correction coefficient for correcting the distribution probability so that the difference between the allowable charge amount and the accumulated value of the charge amount in all advertisement contents is minimized. As a result, the distribution device 100 can calculate the distribution probability that it is difficult for all advertisement contents to stop being distributed while using the advertising budget as much as possible, so the distribution is possible regardless of the time period during the distribution period. As a result, it is possible to widen the range of selection of advertisement content to be performed and to prevent unsettled advertising budget.

(About distribution unit 136)
When the receiving unit 133 receives an advertisement content acquisition request, the distributing unit 136 distributes any of the advertising content stored in the advertising content storage unit 121. Specifically, the distribution unit 136 extracts the advertisement content to be distributed from the advertisement content storage unit 121 based on the distribution probability calculated by the calculation unit 135, and the extracted advertisement content is extracted from the terminal device 10 or the information providing device. 30. For example, the distribution unit 136 controls the distribution of the advertising content by extracting the advertising content with a higher probability as the advertising content has a higher distribution probability. In this way, the distribution unit 136 controls the distribution of the advertising content so as not to exceed the chargeable amount calculated by the calculation unit 132.

  In the above, an example in which the advertisement content to be distributed is determined based on the distribution probability has been described. However, the distribution unit 136 determines the advertisement content to be distributed by combining advertisement content extraction processing by various methods. May be. For example, the distribution unit 136 first extracts a predetermined number of advertisement contents matching the keyword included in the web page on which the advertisement content is displayed (that is, the web page browsed by the user) from the advertisement content storage unit 121. Later, from the predetermined number of extracted advertisement contents, the advertisement contents to be distributed may be determined based on the distribution probability. Further, for example, the distribution unit 136 first selects a predetermined number of advertising contents that match user attributes (for example, psychographic attributes and demographic attributes) and a predetermined number of advertising contents that match the search keyword input by the user. After extraction, the advertisement content to be distributed may be determined based on the distribution probability from the predetermined number of extracted advertisement contents. Further, for example, the distribution unit 136 first extracts the distribution candidate advertisement content based on the distribution probability, and then, from the extracted distribution candidate advertisement content, the keyword included in the web page, the user attribute, The advertisement content to be distributed may be determined based on a search keyword or the like. Further, the present invention is not limited to this example, and the distribution unit 136 first extracts the advertisement content as the distribution candidate based on the distribution probability, and then determines the advertisement content to be distributed based on the CTR and the bid price of the advertisement content. Also good. Note that the CTR here may be an actual CTR or a predicted CTR predicted from a CTR prediction model or the like.

  In addition, when the distributed advertisement content is clicked by the user, the distribution unit 136 receives a click notification that the click has been made from the terminal device 10. In this case, the distribution unit 136 adds the bid price to the “cumulative billing amount” of the advertisement content storage unit 121 corresponding to the clicked advertisement content based on the click notification, and the “control period” of the allowable information storage unit 122. The bid price is added to the cumulative charge amount.

  Further, the distribution unit 136 updates “accumulated charge amount within the control period” of the allowable information storage unit 122 to “0” when the control period during which distribution control is performed by the distribution apparatus 100 is switched. For example, when the control period is “1 day” and the start time of the control period is “0 o'clock”, the distribution unit 136 sets “within the control period” in the allowable information storage unit 122 every time it becomes “0 o'clock”. Is updated to “0”. The distribution unit 136 may store “accumulated charge amount within the control period” in the allowable information storage unit 122 as a history.

[4. (Reception processing procedure)
Next, with reference to FIG. 7, a procedure of reception processing by the distribution apparatus 100 according to the embodiment will be described. FIG. 7 is a flowchart illustrating a reception processing procedure by the distribution apparatus 100 according to the embodiment.

  As illustrated in FIG. 7, the receiving unit 131 of the distribution apparatus 100 determines whether or not the advertisement content submission has been received from the advertiser apparatus 20 (step S <b> 101). And when the reception part 131 has not received the submission (step S101; No), it waits until it accepts the submission. On the other hand, when accepting the submission (step S101; Yes), the accepting unit 131 advertises the submitted advertisement content and the bid price, distribution period, and advertisement budget specified by the advertiser at the time of submission. The content is stored in the content storage unit 121 (step S102).

  Subsequently, the calculation unit 132 calculates the time variation of the chargeable amount based on the advertisement content distribution period and the advertisement budget received by the reception unit 131 (step S103). For example, the calculation unit 132 calculates the digestion reference amount by dividing the advertising budget per day by the minute, and multiplies the calculated digestion reference amount by the elapsed time at the current date and time. Thus, the chargeable amount at the present time is calculated.

  Then, the calculation unit 132 updates the allowable information storage unit 122 based on the calculated time variation of the allowable charge amount (step S104). For example, the calculation unit 132 stores, in the allowable information storage unit 122, the inclination of the charging allowable amount over time as the digestion reference amount.

[5. (Ad delivery procedure)
Next, the procedure of distribution processing by the distribution apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating a distribution processing procedure performed by the distribution apparatus 100 according to the embodiment.

  As illustrated in FIG. 8, the receiving unit 133 of the distribution apparatus 100 determines whether or not an advertisement content acquisition request has been received (step S201). And the receiving part 133 waits until an acquisition request is received, when the acquisition request is not received (step S201; No).

  On the other hand, when the acquisition request is received by the reception unit 133 (step S201; Yes), the acquisition unit 134 acquires the current allowable charge amount stored in the allowable information storage unit 122 (step S202).

  Subsequently, the calculation unit 135 calculates the difference between the current chargeable amount acquired by the acquisition unit 134 and the accumulated charge amount (step S203). Then, the calculation unit 135 calculates a correction coefficient using the calculated difference and the chargeable amount (step S204).

  Subsequently, the calculation unit 135 calculates the distribution probability of the advertising content using the calculated correction coefficient (step S205). Then, the distribution unit 136 distributes the advertising content based on the distribution probability calculated by the calculation unit 135 (step S206).

[6. (Modification)
The distribution apparatus 100 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, in the following, another embodiment of the distribution device 100 will be described.

[6-1. Correction coefficient
In the above-described embodiment, an example is shown in which the calculation unit 135 calculates a correction coefficient that corrects the total sum of differences in the submitted advertisement content to the minimum, as in the example shown in Expression (4). However, the present invention is not limited to this example, and the calculation unit 135 may calculate a correction coefficient for each group of advertising content belonging to the same classification with the targeting condition, and calculate the distribution probability using the calculated correction coefficient.

  This point will be described using the following formula (5).

Expression (5) is an expression for calculating a correction coefficient for each group of advertising content belonging to the same classification with the targeting condition. Here, the calculation unit 135 calculates a correction coefficient for each of various targeting conditions such as sex, age, region, and time. For example, the calculation unit 135 calculates a correction coefficient “k _mn ” that minimizes the expression (5) for each age m and gender n. Note that the calculation unit 135 may calculate the correction coefficient for each product handled by the advertising content, for example, not only for each targeting condition.

  Further, the calculation unit 135 may calculate a correction coefficient for each group of advertising content belonging to the same category of the advertising content, and calculate the distribution probability of the advertising content using the calculated correction coefficient. For example, the calculation unit 135 calculates a correction coefficient for each group of advertising content whose advertising content type is a retargeting advertisement.

  As described above, the distribution apparatus 100 calculates the correction coefficient for each group of advertising content belonging to the same classification with the targeting condition, and calculates the distribution probability using the calculated correction coefficient. Further, the distribution apparatus 100 calculates a correction coefficient for each group of advertising content belonging to the same category of the advertising content, and calculates the distribution probability of the advertising content using the calculated correction coefficient.

  Thereby, since the distribution apparatus 100 can calculate the correction coefficient with high accuracy, the distribution probability can be calculated with high accuracy. For this reason, since the delivery apparatus 100 can prevent the delivery stop of advertisement content, it can improve the profit obtained by delivery of advertisement content.

[6-2. (Probability of delivery according to bid price)
Moreover, in the said embodiment, the delivery apparatus 100 may calculate a delivery probability according to the bid price of advertising content. Specifically, the calculation unit 135 calculates the distribution probability lower as the bid price of the advertising content is higher. This point will be described with reference to FIG. FIG. 9 is an explanatory diagram for explaining the distribution probability calculation process.

  As shown in FIG. 9, it is assumed that the advertiser AP 10 has submitted the advertising content AD3 and the advertising content AD4 to the distribution apparatus 100. Further, it is assumed that the chargeable amount at the present time for the advertisement content AD3 and the advertisement content AD4 is “10000 yen”. Further, the advertisement content AD3 and the advertisement content AD4 are assumed to have an accumulated charge amount of “4000 yen” at the present time.

  First, the calculation unit 135 calculates a difference “6000 yen” between the current chargeable amount and the accumulated charge amount. Subsequently, the calculation unit 135 calculates a ratio “60%” of the difference with respect to the chargeable amount. Here, the calculation unit 135 calculates the distribution probability lower as the bid price of the advertising content is higher. For example, as shown in FIG. 9, in the case of the advertisement content AD3, the calculation unit 135 subtracts the ratio “1%” of the bid price with respect to the difference from the ratio “60%” of the difference, thereby distributing probability P3 “59% Is calculated. On the other hand, in the case of the advertisement content AD4, the calculating unit 135 calculates the distribution probability P4 “55%” by subtracting the bid price ratio “5%” from the difference ratio “60%”.

  Thus, the distribution apparatus 100 calculates the distribution probability lower as the bid price of the advertising content is higher.

  Thereby, since the distribution apparatus 100 reduces the distribution of the advertising content with a high bid price, it is possible to prevent the distribution of the advertising content from being stopped. For this reason, the distribution apparatus 100 can improve the profits obtained by distributing the advertising content.

[6-3. (Probability of delivery after a predetermined period of time)
In the above embodiment, if the cumulative value of the charge amount does not exceed the chargeable amount after a predetermined period, the distribution probability may be calculated as 100%.

  For example, the calculation unit 135 calculates the distribution probability by the above-described distribution probability calculation process until a predetermined period elapses. And the calculation part 135 stops the calculation process of the delivery probability mentioned above after progress for a predetermined period. For example, the calculation unit 135 stops the above-described distribution probability calculation processing when the time close to the end time of the distribution period comes. Then, the calculation unit 135 calculates the distribution probability as 100% when the cumulative value of the charge amount does not exceed the charge allowable amount. On the other hand, the calculation unit 135 calculates the distribution probability as 0%, for example, when the accumulated value of the charge amount exceeds the chargeable amount after a predetermined period.

  As described above, the distribution apparatus 100 calculates the distribution probability as 100% when the accumulated value of the charge amount does not exceed the charge allowable amount after a predetermined period has elapsed.

  As a result, the distribution apparatus 100 distributes the advertising content whose accumulated amount of charge does not exceed the chargeable amount just before the end of the distribution period, thereby preventing the advertisement budget from being used up.

[6-4. (Calculation of billing allowance linked to ad click tendency)
Moreover, in the said embodiment, the calculation part 132 showed the example which calculates a digestion reference amount by dividing | segmenting the advertising budget per day by 1440 minutes like the example shown in FIG. However, the present invention is not limited to this example, and the calculation unit 132 may calculate the time variation of the chargeable amount that allows the accumulated value of the charge amount in conjunction with the advertisement click tendency that the advertisement content is clicked.

  This point will be described with reference to FIGS. FIG. 10 is an explanatory diagram for explaining temporal transition of the click tendency. In FIG. 10, the vertical axis represents CTR, which is an index representing the ratio of the number of clicks out of the number of times advertisement content has been displayed. The horizontal axis indicates time. As shown in FIG. 10, the CTR of the advertising content varies depending on the advertising content in a time zone during which it is easily clicked. In FIG. 10, the advertising content AD1 is an example in which the CTR is high in the time zone from 18:00 to 24:00. On the other hand, the advertising content AD2 is an example in which the CTR is high in the time zone from 0:00 to 6:00. As described above, the time period during which the advertisement content is easily clicked varies.

  Here, if the advertising content is distributed in a time zone where it is difficult to click, the CTR is lowered, and there is a problem that the sales of the advertising distributor is also reduced. Therefore, the calculation unit 132 of the distribution apparatus 100 calculates the time variation of the chargeable amount that allows the accumulated value of the charge amount in conjunction with the advertisement click tendency.

  FIG. 11 is an explanatory diagram for explaining the chargeable amount linked with the click tendency. As shown in FIG. 11, the calculation unit 132 calculates the allowable charging amount OL1 of the advertising content AD1 so that the allowable charging amount approaches the upper limit during the time period from 18:00 to 24:00. On the other hand, the calculating unit 132 calculates the allowable charging amount OL2 of the advertising content AD2 so that the allowable charging amount approaches the upper limit in the time zone from 0:00 to 6:00.

  In this way, the distribution apparatus 100 calculates the time variation of the chargeable amount that allows the accumulated value of the charge amount in conjunction with the advertisement click tendency that the advertisement content is clicked. Then, the distribution device 100 controls the distribution of the advertising content in conjunction with the difference between the chargeable amount corresponding to the current date and time of the chargeable amount calculated by the calculation unit 132 and the accumulated value of the charge amount. Calculate delivery probability.

  Thereby, since the distribution apparatus 100 can perform distribution control based on the chargeable amount according to the click tendency of each advertisement content, it is possible to further reduce the unsettled advertisement budget. For this reason, the distribution apparatus 100 can improve the profits obtained by distributing the advertising content.

  The distribution apparatus 100 may calculate an advertisement click tendency for each campaign, not limited to each advertisement content. Here, the campaign means, for example, a group of a plurality of advertisement contents prepared for promoting a specific product or service. Further, the distribution apparatus 100 may calculate an advertisement click tendency for each advertiser who has submitted the advertisement content. Specifically, the distribution apparatus 100 calculates an advertisement click tendency for each day of the week or time period using the actual data of the number of clicks and the number of impressions of the advertisement content.

For example, the distribution apparatus 100 is linked to an advertisement click tendency that is calculated by maximizing the number of advertisement clicks that the advertisement content is clicked on or the revenue that is obtained from the distribution of the advertisement content, and allows the accumulated value of the charge amount. Calculate the allowable fluctuation over time. This point will be described with reference to FIG. FIG. 12 is an explanatory diagram for explaining temporal transition of the click tendency. In FIG. 12, for example, Click ₁ (0) indicates the number of clicks of the advertisement content AD _{1 in} the 0 o'clock range. Click _MAX1 indicates the total value of the number of clicks of the advertising content AD _{1 from} the 0 o'clock to the T o'clock. In addition, Imps (0) indicates the total value of the number of impressions at 0 o'clock of advertising content _AD 1 _{~AD M.} In the example of FIG. 12, M × T number of clicks trend the Click ₁ at each time period of the advertisement content _{AD 1 ~AD M (0) ~Click} M (T) is a parameter. Further, the total value Click _{MAXm of the} number of clicks of the advertisement content AD _m in the time from 0 o'clock to T o'clock is determined from the budget constraint.

  Here, the constraint conditions are expressed by the following equations (6) and (7).

  Then, the distribution device 100 calculates the maximum number of clicks of the advertising content or the maximum profit obtained by the distribution of the advertising content by linear programming. Specifically, the distribution apparatus 100 calculates a tendency of the optimal number of clicks by maximizing the number of clicks or revenue under the constraint conditions of Expression (6) and Expression (7). Here, the formula for maximizing the number of clicks is represented by the following formula (8).

Then, the distribution apparatus 100 calculates the number of clicks that maximizes the following equation (8). The distribution apparatus 100 may calculate the maximum profit, not limited to the maximum number of clicks. Revenue is calculated by multiplying the number of clicks on the advertising content by the bid price. For this reason, the formula which maximizes profit is represented by the following formula (9). Here, Bid _m indicates a bid price of the advertisement content AD _m . Thereby, the distribution apparatus 100 calculates the profit that maximizes the following equation (9).

  As described above, the distribution apparatus 100 allows the accumulated value of the billing amount in conjunction with the advertisement click tendency calculated by maximizing the number of advertisement clicks for which the advertisement content is clicked or the revenue obtained by the distribution of the advertisement content. Calculate the time variation of the allowable charge amount.

  Thereby, since the distribution apparatus 100 can calculate the click tendency of the advertising content with high accuracy, it can calculate the distribution probability that improves the profit obtained by the distribution of the advertising content.

Note that the distribution apparatus 100 may perform optimization for each time without considering budget constraints. Specifically, the distribution apparatus 100 calculates the number of times of display proportional to the number of clicks or the click rate of the advertisement content for each predetermined time period, and multiplies the calculated number of display times by the click rate. In conjunction with the advertising click tendency, the time variation of the chargeable amount that allows the accumulated value of the chargeable amount is calculated. For example, the distribution apparatus 100 distributes the number of impressions in proportion to the number of actual clicks of each advertisement content for each hourly time zone. Here, the number of impressions Imps _m (t) of the advertisement content AD _m at time t is expressed by the following equation (10). As a result, the distribution apparatus 100 calculates the number of impressions.

In addition, the delivery apparatus 100 may distribute the number of impressions in proportion to the actual CTR of each advertisement content for each hourly time zone. In this case, the number of impressions Imps _m (t) is expressed by the following formula (11).

Then, the distribution device 100 multiplies the number of impressions Imps _m (t) calculated by the formula (10) or the formula (11) by the actual CTR _m (t) indicating the actually observed CTR, thereby clicking the optimum click. The number trend Click _m (t) is calculated. The distribution apparatus 100 calculates an optimal distribution plan curve by calculating a time-series cumulative curve of the calculated Click _m (t). Thereby, the distribution apparatus 100 calculates the time variation of the chargeable amount that allows the accumulated value of the charge amount in conjunction with the advertisement click tendency.

  In this way, the distribution device 100 calculates the number of displays proportional to the number of clicks or the click rate of the advertisement content for each predetermined time period, and calculates the advertisement calculated by multiplying the calculated number of displays by the click rate. In conjunction with the click tendency, the time variation of the chargeable amount that allows the accumulated value of the chargeable amount is calculated.

  Thereby, since the distribution apparatus 100 can calculate the click tendency of the advertising content with high accuracy, it can calculate the distribution probability that improves the profit obtained by the distribution of the advertising content.

  Further, the distribution apparatus 100 may calculate the time variation of the allowable charge amount that allows the accumulated value of the charge amount in conjunction with the CVR (Conversion Rate) without being limited to the advertisement click tendency. Here, the CVR indicates the ratio of the number of times of conversion (for example, the final result that can be acquired from the content such as product purchase or document request) to the number of times the advertisement is distributed. In addition, the distribution apparatus 100 may calculate the time variation of the chargeable amount in consideration of the user's margin. Here, the margin indicates a time allowance for the user to see the advertisement content. For example, the margin tends to be higher during night hours and weekends and holidays than during weekday daytime. Further, the distribution apparatus 100 may calculate the time variation of the chargeable amount in consideration of the time transition of the number of users having a high eCPM. Further, when the advertising content is a targeting advertisement, the distribution apparatus 100 may calculate the above-described change in the allowable charging amount for each demographic attribute that is a target of the targeting advertisement.

[6-5. (Control period unit)
In the above-described embodiment, an example in which the unit of the control period in which the distribution control of the advertisement content is performed by the distribution apparatus 100 is “1 day”, but the present invention is not limited to this example, and the unit of the control period is “1”. Other units than “day” may be used. For example, the unit of the control period may be “10 hours”, “3 days”, “1 week”, “1 month”, or the like.

[6-6. The granularity of the period during which the digestion amount (digestion pace) can be established)
Moreover, in the said embodiment, the calculation part 132 showed the example which calculates the digestion reference amount corresponding to one time slot | zone like the example shown in FIG. However, the present invention is not limited to this example, and the granularity of the period during which the digestion reference amount is calculated may be another example. Hereinafter, some examples will be described.

  Specifically, the calculation unit 132 may calculate a digestion reference amount corresponding to a plurality of time zones. For example, the calculation unit 132 calculates the digestion reference amount for each time zone for three time zones “0 to 6 o'clock”, “6 o'clock to 21:00” and “21:00 to 24:00”. In addition, the calculation unit 132 may calculate the digestion reference amount for each date range instead of the time zone. For example, when the click tendency fluctuates between the first half of the month (1st to 15th) and the second half of the month (16th to 31st), for example, the calculation unit 132 calculates the target period “2013 2 The digestion standard amount corresponding to “Month 1 to February 15, 2013”, the digestion standard amount corresponding to the target period “February 16, 2013 to March 15, 2013”, and the target period “20133 A digestion reference amount corresponding to “Monday 16 to March 31, 2013” may be calculated.

  Moreover, the calculation part 132 may change the time slot | zone which calculates a digestion reference amount for every range of dates. For example, the calculation unit 132 sets the three time zones “0 to 6 for“ February 1, 2013 to February 15, 2013 ”and“ March 16, 2013 to March 31, 2013 ”. The digestion standard amount is calculated for “hour”, “6 to 21:00” and “21:00 to 24:00”, and for “February 16, 2013 to March 15, 2013”, two time zones “0” The digestion standard amount is calculated for “time to 9:00” and “9 to 24:00”.

  For example, the calculation unit 132 may calculate a different digestion reference amount for each day of the week. Furthermore, the calculation unit 132 may change the time period for calculating the digestion reference amount for each day of the week. For example, for “Monday to Friday”, the calculation unit 132 calculates the digestion reference amount for the three time zones “0 to 6 o'clock”, “6 to 21:00” and “21:00 to 24:00” For “Saturday and Sunday”, a digestion standard amount is calculated for two time zones “0 to 9:00” and “9 to 24:00”. Further, the calculation unit 132 may calculate a digestion reference amount similar to “Saturday, Sunday” for holidays (flag days), or may calculate a digestion reference amount separately from each day of the week.

  Further, for example, the calculation unit 132 may calculate an expression indicating the time variation of the chargeable amount instead of providing the digestion reference amount for each predetermined period.

  First, the calculation unit 132 calculates the temporal fluctuation of the virtual charge amount of the advertisement content by assuming that the advertisement content is clicked according to the click tendency. Here, the calculation unit 132 calculates a virtual billing amount that fluctuates from the start date and time to the end date and time of the advertisement content distribution period. Subsequently, the calculation unit 132 corrects the time variation of the virtual billing amount so that the virtual billing amount corresponding to the end date and time of the distribution period matches the advertising budget set for the advertiser. That is, the calculation unit 132 calculates the time variation of the allowable charge amount by compressing the time variation of the virtual charge amount as a whole. Then, the calculation unit 132 obtains an approximate expression indicating the time variation of the chargeable amount by performing curve fitting, regression analysis, and the like, and the obtained approximate expression is used as the advertisement content (actually an advertisement for identifying the advertisement content). Stored in the allowable information storage unit 122 in association with the ID.

  As described above, the distribution apparatus 100 can perform distribution control based on the charge allowable amount in accordance with the click tendency analyzed in detail by calculating the charge allowable amount (that is, the digestion reference amount). The unsettled advertising budget can be further reduced.

[6-7. Device configuration〕
In the above embodiment, the advertisement distribution system 1 includes the information providing device 30 and the distribution device 100. However, the information providing device 30 and the distribution device 100 may be formed as a single device. Good. When receiving a web page acquisition request from the terminal device 10, the distribution device 100 distributes a web page that does not include an advertisement acquisition command to the terminal device 10 together with the advertisement content extracted from the advertisement content storage unit 121.

[6-8. Others]
Moreover, in the said embodiment, although user operation which selects the link area | region of advertisement content or a web page was described as "click", this user operation is not restricted to click operation using a mouse | mouth. For example, the “click” described above may be an operation of tapping advertisement content or the like with a finger or an operation of selecting advertisement content or the like with a line of sight.

  In the above embodiment, an example is shown in which the advertising content is displayed so as to overlap the web page. However, the content displayed so as to overlap the advertising content is not limited to the web page. For example, when an advertisement display area is included in a screen of a mobile phone game or the like, the advertisement content described above may be displayed so as to overlap with the game screen or the like.

  In the above embodiment, the advertisement content has been described as an example. However, the content displayed on the web page is not limited to the advertisement content for the advertisement purpose. For example, the advertisement content described above may be content for notifying weather information, earthquake information, and the like.

  In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the reception unit 131 and the reception unit 133 illustrated in FIG. 4 may be integrated.

[6-9. Hardware configuration)
Further, the distribution apparatus 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in FIG. 13, for example. Hereinafter, the distribution apparatus 100 will be described as an example. FIG. 13 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the distribution apparatus 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the communication network 50 (corresponding to the network N shown in FIG. 3), sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other devices via the communication network 50. Send to.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the distribution device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the communication network 50.

[7. effect〕
As described above, the distribution apparatus 100 according to the embodiment includes the acquisition unit 134 and the calculation unit 135. The acquisition unit 134 acquires a time variation of a chargeable amount that allows a cumulative value of a charge amount charged according to the number of times the advertisement content is clicked. The calculation unit 135 calculates the distribution probability of distributing the advertisement content based on the time variation of the chargeable amount acquired by the acquisition unit 134.

  Further, in the distribution device 100 according to the embodiment, the calculation unit 135 is a probability that the advertising content is distributed, and among the allowable charging amount acquired by the acquiring unit 134, the allowable charging amount corresponding to the current date and time, The distribution probability linked to the difference between the accumulated amount and the amount is calculated.

  Thereby, since the distribution apparatus 100 according to the embodiment can prevent the stop of the distribution of the advertisement content, the selection range of the advertisement content can be widened regardless of the time zone during the distribution period. In addition, the distribution apparatus 100 can average the quality of advertisement content distributed during the distribution period. Further, since the distribution apparatus 100 can prevent the high bid price advertisement content from being stopped from being distributed, the distribution device 100 can prevent the low bid price advertisement content from being distributed. Further, since the distribution apparatus 100 can compete with the advertiser to distribute the advertising content, the distribution apparatus 100 can cause the advertiser to set a high bid price. Further, the distribution apparatus 100 can improve the profits obtained by distributing the advertising content.

  In the distribution apparatus 100 according to the embodiment, the calculation unit 135 calculates a distribution probability that is linked to the ratio of the difference with respect to the chargeable amount corresponding to the current date and time.

  Thereby, the distribution apparatus 100 according to the embodiment can prevent the advertisement content from being stopped from being distributed.

  Further, in the distribution apparatus 100 according to the embodiment, the calculation unit 135 calculates a correction coefficient that corrects the sum of the differences between the submitted advertisement contents to the minimum, and calculates a distribution probability using the calculated correction coefficient. .

  Accordingly, the distribution apparatus 100 according to the embodiment can calculate a distribution probability that minimizes the difference between the chargeable amount and the accumulated value of the charge amount while digesting the advertisement budget as much as possible.

  Further, in the distribution device 100 according to the embodiment, the calculation unit 135 calculates a correction coefficient for each group of advertising content belonging to a category with the same targeting condition, and calculates a distribution probability using the calculated correction coefficient.

  Thereby, since the delivery apparatus 100 which concerns on embodiment can calculate a delivery probability with high precision, it can prevent the delivery stop of advertisement content.

  Further, in the distribution apparatus 100 according to the embodiment, the calculation unit 135 calculates a correction coefficient for each group of advertising content belonging to the same category of advertising content, and the distribution probability of the advertising content using the calculated correction coefficient. Is calculated.

  Thereby, since the delivery apparatus 100 which concerns on embodiment can calculate a delivery probability with high precision, it can prevent that advertising content stops a delivery.

  In the distribution apparatus 100 according to the embodiment, the calculation unit 135 calculates the distribution probability lower as the bid price of the advertising content is higher.

  Thereby, since the delivery apparatus 100 which concerns on embodiment reduces the delivery of advertising content with a high bid price, it can prevent that advertising content stops distribution.

  Further, in the distribution apparatus 100 according to the embodiment, the calculation unit 135 calculates the distribution probability as 100% when the accumulated value of the charge amount does not exceed the charge allowable amount after a predetermined period.

  As a result, the distribution apparatus 100 according to the embodiment distributes advertising content whose accumulated charge amount does not exceed the chargeable amount immediately before the end of the distribution period, so that the advertising budget can be prevented from being consumed.

  Further, in the distribution apparatus 100 according to the embodiment, the calculation unit 132 calculates time variation of the allowable charge amount that allows the accumulated value of the charge amount in conjunction with the advertisement click tendency that the advertisement content is clicked. The calculation unit 135 calculates a distribution probability that is linked to the difference between the chargeable amount corresponding to the current date and time of the chargeable amount calculated by the calculation unit 132 and the accumulated value of the charge amount.

  Thereby, since the distribution apparatus 100 according to the embodiment can perform distribution control based on the chargeable amount according to the click tendency of each advertisement content, it is possible to further reduce the unsettled advertisement budget.

  As described above, in the distribution device 100 according to the embodiment, the calculation unit 132 is linked to the advertisement click tendency calculated by maximizing the number of advertisement clicks for which the advertisement content is clicked or the profit obtained by the distribution of the advertisement content. Then, the time variation of the chargeable amount that allows the accumulated value of the chargeable amount is calculated.

  Thereby, since the distribution apparatus 100 can calculate the click tendency of the advertising content with high accuracy, it can calculate the distribution probability that improves the profit obtained by the distribution of the advertising content.

  As described above, in the distribution device 100 according to the embodiment, the calculation unit 132 calculates the number of times of display that is proportional to the number of clicks or the click rate of the advertisement content for each predetermined time period, In conjunction with the advertising click tendency calculated by multiplying by, the time fluctuation of the chargeable amount allowing the accumulated value of the chargeable amount is calculated.

  Thereby, since the distribution apparatus 100 can calculate the click tendency of the advertising content with high accuracy, it can calculate the distribution probability that improves the profit obtained by the distribution of the advertising content.

  As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to implement the present invention in other forms with improvements.

DESCRIPTION OF SYMBOLS 1 Advertisement distribution system 10 Terminal apparatus 20 Advertiser apparatus 30 Information provision apparatus 100 Distribution apparatus 121 Advertisement content storage part 122 Permissible information storage part 131 Reception part 132 Calculation part 133 Reception part 134 Acquisition part 135 Calculation part 136 Distribution part

Claims (13)

An acquisition means for acquiring a time variation of a chargeable amount that allows a cumulative value of a charge amount that is charged according to the number of times the advertisement content is clicked;
A calculation device comprising: a calculation unit that calculates a distribution probability of distributing the advertisement content based on a time variation of the chargeable amount acquired by the acquisition unit. The calculating means includes
2. The distribution probability linked to the difference between the chargeable amount corresponding to the current date and time of the chargeable amount acquired by the acquisition unit and the cumulative value of the charge amount is calculated. The calculation device described. The calculating means includes
The calculation device according to claim 2, wherein the distribution probability is calculated in conjunction with a ratio of the difference with respect to a chargeable amount corresponding to the current date and time. The calculating means includes
The calculation according to claim 2, wherein a correction coefficient that corrects the sum of the differences of the submitted advertisement content to a minimum is calculated, and the distribution probability is calculated using the calculated correction coefficient. apparatus. The calculating means includes
The calculation device according to claim 4, wherein the correction coefficient is calculated for each group of advertising content belonging to the same classification with the targeting condition, and the distribution probability is calculated using the calculated correction coefficient. The calculating means includes
5. The correction coefficient is calculated for each group of advertisement contents belonging to the same category of advertisement content, and the distribution probability of the advertisement content is calculated using the calculated correction coefficient. Calculation device. The calculating means includes
The calculation device according to claim 1, wherein the distribution probability is calculated to be lower as the bid price of the advertisement content is higher. The calculating means includes
8. The distribution probability is calculated as 100% when a cumulative value of the charge amount does not exceed the charge allowance amount after a predetermined period of time. The calculation device described. A calculation means for calculating a time variation of a chargeable amount that allows a cumulative value of the charge amount in conjunction with an advertisement click tendency in which the advertisement content is clicked;
Further comprising
The calculating means includes
2. The distribution probability linked to a difference between a chargeable amount corresponding to a current date and time among a chargeable amount calculated by the calculation means and a cumulative value of the chargeable amount is calculated. The calculation apparatus as described in any one of -8. The calculating means is
A chargeable amount of time that allows the cumulative value of the charge amount in conjunction with the number of ad clicks that the ad content is clicked on or the ad click tendency that is calculated by maximizing the revenue that is obtained from the distribution of the ad content The calculation device according to claim 9, wherein the fluctuation is calculated. The calculating means is
Calculate the number of impressions proportional to the number of clicks or click rate of the advertising content for each predetermined time period, and link the calculated number of impressions with the click rate to link the click rate of the advertisement. The calculation apparatus according to claim 9, wherein a time variation of a chargeable amount that allows a cumulative value of money is calculated. A calculation method executed by a calculation device,
An acquisition step for acquiring a time variation of a chargeable amount that allows a cumulative value of a chargeable amount that is charged according to the number of times the advertisement content is clicked;
And a calculation step of calculating a distribution probability of distributing the advertising content based on a time variation of the chargeable amount acquired by the acquisition step. An acquisition procedure to obtain the time variation of the chargeable amount that allows the cumulative amount of charge that is charged according to the number of times the advertising content is clicked,
A calculation program for causing a computer to execute a calculation procedure for calculating a distribution probability of distributing the advertisement content based on a time variation of the chargeable amount acquired in the acquisition step.

Images