JP6541521B2 - Generation device, generation method, generation program, determination device, determination method, and determination program - Google Patents

Generation device, generation method, generation program, determination device, determination method, and determination program Download PDF

Info

Publication number
JP6541521B2
JP6541521B2 JP2015176903A JP2015176903A JP6541521B2 JP 6541521 B2 JP6541521 B2 JP 6541521B2 JP 2015176903 A JP2015176903 A JP 2015176903A JP 2015176903 A JP2015176903 A JP 2015176903A JP 6541521 B2 JP6541521 B2 JP 6541521B2
Authority
JP
Japan
Prior art keywords
advertisement
information
user
format
type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2015176903A
Other languages
Japanese (ja)
Other versions
JP2017054261A (en
Inventor
修司 大矢
修司 大矢
直貴 伊藤
直貴 伊藤
勇樹 佐久間
勇樹 佐久間
Original Assignee
ヤフー株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ヤフー株式会社 filed Critical ヤフー株式会社
Priority to JP2015176903A priority Critical patent/JP6541521B2/en
Publication of JP2017054261A publication Critical patent/JP2017054261A/en
Application granted granted Critical
Publication of JP6541521B2 publication Critical patent/JP6541521B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Description

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

  Conventionally, there is provided a technology for delivering an advertisement whose design has been determined according to a delivery request source. For example, techniques have been provided for dynamically generating advertisements based on web page design.

Patent No. 5265659 gazette

  However, in the above-described conventional technology, when the evaluation value in the type of the advertising content to be distributed is predicted based on the distribution result for each type in the data format of the advertising content, the evaluation value may not be appropriately predicted. For example, in the case of collecting evaluation values of a type for each of a plurality of classifications, there are cases in which the evaluation values can not be predicted appropriately because the results of evaluation values of various types run short.

  The present application has been made in view of the above, and a generating device, a generating method, a generating program, a determining device, a determining method, and a method for appropriately using a model for predicting an evaluation value related to a type of advertising content to be delivered. The purpose is to provide a decision program.

  A generating device according to the present application generates a model that predicts an evaluation value related to a type of data format of advertisement information based on an acquisition unit that acquires user information on a user and the user information acquired by the acquisition unit. And.

  According to an aspect of the embodiment, it is possible to appropriately use a model that predicts an evaluation value regarding the type of advertising content to be distributed.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating an example of the distribution process according to the embodiment. FIG. 3 is a diagram illustrating an exemplary configuration of the advertisement distribution device according to the embodiment. FIG. 4 is a diagram illustrating an example of the user information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of a distribution log information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of the format information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the advertisement information storage unit according to the embodiment. FIG. 8 is a diagram showing an example of a template information storage unit according to the embodiment. FIG. 9 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 10 is a flowchart illustrating an example of the distribution process according to the embodiment. FIG. 11 is a diagram illustrating an example of a generation process of determining a plurality of formats according to the embodiment. FIG. 12 is a diagram illustrating an example of a generation process of determining a plurality of formats according to the embodiment. FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the function of the advertisement distribution device.

  Hereinafter, a generation apparatus, a generation method, a generation program, a determination apparatus, a determination method, and an embodiment (hereinafter, referred to as an “embodiment”) according to the present application will be described in detail with reference to the drawings. . Note that the generation device, the generation method, the generation program, the determination device, the determination method, and the determination program according to the present application are not limited by this embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

(Embodiment)
[1-1. Generation process]
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. The advertisement distribution device 100 shown in FIG. 1 generates a model that predicts a predetermined evaluation value regarding the format. Further, the advertisement distribution device 100 provides a distribution service for distributing advertisement content displayed on the content distributed by the content distribution device 50, which will be described with reference to FIG.

  Further, the design of the advertisement content is made up of two elements of the type of the data format of the advertisement information and the display style when the advertisement information is displayed as the advertisement content. The type in the data format of the advertisement information mentioned here indicates, for example, classification based on the data format of the advertisement information, such as text information, image information, and a combination of text information and image information. Below, the classification in the data format of advertisement information may be made into a "format." Further, for example, the advertisement information indicates specific contents of advertisements such as a text advertisement of car A, an image advertisement of car A, an advertisement in which a text of car A is combined with an image, and the like. Further, the display style of the advertisement information includes, for example, character font at the time of displaying the advertisement information as advertisement content, color of the character, number of lines on which the character information is displayed, and each component such as character information and image information. The classification of the display mode which combined various elements, such as arrangement of, is shown. Below, the display style of advertisement information may be made into a "template." Moreover, in the example shown below, for example, a plurality of templates applicable to each format is prepared for each format in the advertisement content. For example, in FIG. 2, the format identified by the format ID “FM11” is selected from a plurality of templates such as a template identified by the template ID “TP11” and a template identified by the template ID “TP12”. Any template is applicable.

  As shown in FIG. 1, the distribution system 1 includes a terminal device 10, a content distribution device 50 (see FIG. 2), and an advertisement distribution device 100. The terminal device 10, the content distribution device 50, and the advertisement distribution device 100 are communicably connected by wire or wireless via a predetermined communication network (not shown). The distribution system 1 illustrated in FIG. 1 may include a plurality of terminal devices 10, a plurality of content distribution devices 50, and a plurality of advertisement distribution devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. FIG. 1 shows the case where the terminal device 10 is a smartphone.

  The terminal device 10 also receives an operation by the user. In the example illustrated in FIG. 1, the terminal device 10 requests the content distribution device 50 for content to be displayed on a predetermined application (for example, a browser or the like). Further, when the content to be displayed includes an area for displaying an advertisement, the terminal device 10 requests the advertisement distribution device 100 for the advertisement. In the following, the terminal device 10 may be described as a user. That is, the user can be read as the terminal device 10 below.

  The advertisement distribution device 100 is a generation device that generates a model that predicts CTR, which is an evaluation value regarding the format of advertisement information, based on user information. Further, the advertisement distribution device 100 is an information processing device that provides an advertisement distribution service that distributes an advertisement in response to an advertisement distribution request. For example, the advertisement distribution device 100 is an information processing device that distributes an advertisement to the terminal device 10 according to the user who uses the terminal device 10 that has requested distribution of the advertisement.

  The content distribution device 50 is an information processing device that distributes content. In the example illustrated in FIG. 1, the content distribution device 50 distributes the content displayed on the application activated in the terminal device 10 in response to the content request from the terminal device 10.

  Hereinafter, an example of the generation process will be described with reference to FIG. FIG. 1 shows the case where the user is a user identified by the user ID "U1" (hereinafter sometimes referred to as "user U1"). Moreover, in FIG. 1, the case where the evaluation value regarding the format used as object of model generation is made into a click rate, ie, CTR (Click Through Rate), is demonstrated to an example.

  Further, in FIG. 1, the advertisement distribution device 100 generates a model that predicts CTR for each of a plurality of formats. Specifically, the advertisement distribution device 100 generates a model for predicting CTR for each of a plurality of formats identified by the format IDs “FM11” to “FM13” stored in the format information storage unit 123. Hereinafter, the format identified by the format ID “FM11” is assumed to be the format FM11, the format identified by the format ID “FM12” is assumed to be the format FM12, and the format identified by the format ID “FM13” is assumed to be the format FM13. . For example, in FIG. 1, the format FM11 is text (character information). Also, the format FM12 is an image. Also, the format FM13 is a combination of text and an image.

  First, as illustrated in FIG. 1, the advertisement distribution device 100 acquires user information such as the action history of the user U1 from the terminal device 10 (step S1). Then, the advertisement distribution device 100 stores the user information of the user U1 in the user information storage unit 121. For example, in FIG. 1, the advertisement distribution device 100 uses the user information storage unit 121 to indicate that the user U1 is a twentieth male, information indicating that a car has been searched for, a site A has been browsed, etc. Remember. Note that the advertisement distribution device 100 may acquire various information according to the purpose, such as the user's age and gender, as well as the user's action history, as long as the user information.

  Then, the advertisement distribution device 100 distributes the advertisement content to be displayed in the advertisement display area AR11 included in the content CT10 displayed on the terminal device 10 (step S2). Hereinafter, the advertisement display area may be simply referred to as "area" or "frame". For example, the advertisement display area AR11 may be simply described as "area AR11". In step S2 of FIG. 1, the advertisement distribution device 100 distributes the advertisement content AC11 of the text format FM11 to the terminal device 10 of the user U1.

  Then, the terminal device 10 used by the user U1 displays the received advertisement content AC11 in the advertisement display area AR11 included in the content CT10. Further, in FIG. 1, it is assumed that the user U1 selects, ie, clicks on the advertising content AC11 displayed on the terminal device 10.

  Thereafter, the advertisement distribution device 100 acquires distribution log information regarding the advertisement distributed from the terminal device 10 used by the user U1 (step S3). For example, the advertisement distribution device 100 acquires information indicating that the user U1 has clicked on the advertisement content AC11 from the terminal device 10 used by the user U1.

  Further, the advertisement distribution device 100 distributes the advertisement content to be displayed in the advertisement display area AR11 included in the content CT10 displayed on the terminal device 10 (step S4). In step S4 of FIG. 1, the advertisement distribution device 100 distributes the advertisement content AC21 of the image format FM12 to the terminal device 10 of the user U1.

  Then, the terminal device 10 used by the user U1 displays the received advertisement content AC21 in the advertisement display area AR11 included in the content CT10. Further, in FIG. 1, it is assumed that the user U1 has selected, ie, did not click on the advertising content AC21 displayed on the terminal device 10.

  Thereafter, the advertisement distribution device 100 acquires distribution log information on the advertisement distributed from the terminal device 10 used by the user U1 (step S5). For example, the advertisement distribution device 100 acquires, from the terminal device 10 used by the user U1, information indicating that the user U1 has not clicked on the advertisement content AC21. Then, the advertisement distribution device 100 stores the distribution log information acquired in step S3 or step S5 in the distribution log information storage unit 122. For example, in FIG. 1, the advertisement distribution device 100 stores, in the distribution log information storage unit 122, information indicating that the user U1 has clicked on the advertisement content AC11, that the user U1 has not clicked on the advertisement content AC21, and the like.

  Note that steps S1 and S2 and step S4 may be performed in any order as long as they are before model generation in step S6. Further, acquisition of distribution log information in step S3 and step S5 may be performed as one step. Further, FIG. 1 shows a case of distributing the advertisement content to be displayed in the advertisement display area AR11 included in the content CT10 for the purpose of explanation, but the distribution log information is displayed in other contents and other advertisement display areas. It may also include information on advertising content. Although FIG. 1 illustrates the case of acquiring user information and delivery log information regarding the user U1, the advertisement delivery apparatus 100 is assumed to acquire user information and delivery log information from a plurality of users including the user U1. It will be described below.

  Next, the advertisement distribution device 100 predicts a CTR for each of the formats FM11 to FM13 using the user information stored in the user information storage unit 121 and the distribution log information stored in the distribution log information storage unit 122. Are generated (step S6). For example, the advertisement distribution apparatus 100 predicts the CTR of the format FM11 using the user information stored in the user information storage unit 121 and the distribution log information on the advertisement content of the format FM11 stored in the distribution log information storage unit 122. Generate a model to

  Also, for example, the advertisement distribution device 100 derives a weight corresponding to each feature as a model for predicting the CTR for each format. The weight of the model generated by the advertisement distribution device 100 may be 0 or a negative value. In addition, the advertisement distribution device 100 may generate a model using various conventional techniques as appropriate. For example, the advertisement distribution device 100 may generate a model by deriving the weight of the extracted feature by learning, or may generate the model using a feature specified in advance. For example, the advertisement distribution device 100 generates a model in which the feature 1 shown in FIG. 1 is “male” and the feature 2 is “visiting site B” or the like. The feature may include information related to the advertisement display area (for example, a frame type to be described later).

  Also, the advertisement distribution device 100 stores the model of each format generated in step S6 in the format information storage unit 123. In FIG. 1, the advertisement distribution device 100 stores information indicating that the weight of feature 1 is “0.6” and the weight of feature 2 is “0.1” in the model of the format FM11. The CTR prediction using the model stored in the format information storage unit 123 will be described with reference to FIG.

  As described above, the advertisement distribution device 100 can generate a model that appropriately predicts the CTR regarding the format of the advertisement information to be distributed. In addition, the advertisement distribution device 100 may appropriately predict the CTR of each format according to the user who uses the terminal device 10 that transmits the distribution request by using the model stored in the format information storage unit 123. it can. For example, the advertisement distribution device 100 can appropriately predict CTR of each format and distribute appropriate content, even when distributing advertisement content whose distribution record is not sufficient. Also, for example, the advertisement distribution device 100 can appropriately predict the CTR of each format and distribute appropriate content even when distributing to a user whose distribution record is not sufficient.

  In the example shown in FIG. 1, the case where the advertisement delivery apparatus 100 generates a model for predicting CTR for each format of advertisement information is shown, but the advertisement delivery apparatus 100 predicts CTR for each template of advertisement information. Models may be generated.

[1-2. Delivery process]
Next, an example of the distribution process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of the distribution process according to the embodiment. FIG. 2 shows the case where the user is a user identified by the user ID "U10" (hereinafter sometimes referred to as "user U10"). In addition, in FIG. 2, the case where the advertisement delivery apparatus 100 has already acquired user information such as the action history of the user U10 will be described as an example.

  Moreover, in FIG. 2, the case where the evaluation value at the time of determining a format, advertisement information, and a template is made into an expected return value, ie, eCPM (effective Cost Per Mille) is demonstrated to an example. Note that eCPM is an example, and various evaluation values may be used depending on the purpose, such as a click rate, that is, a CTR, as an evaluation value when determining a format, advertisement information, or a template.

  As shown in FIG. 2, the content distribution device 50 distributes the content CT10 to the terminal device 10 (step S10). For example, the content distribution device 50 that has received the content request from the terminal device 10 distributes the content CT10 to the terminal device 10.

  The terminal device 10 having received the content CT10 transmits the distribution request of the advertisement content to the advertisement distribution device 100 because the content display region AR11 is included in the content CT10 (step S11). In FIG. 2, in step S11, the terminal device 10 transmits, to the advertisement distribution device 100, user information on the user U10 using the terminal device 10 and information on the area AR11 as a distribution request.

  In step S11, for example, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating the size of the area AR11 or the position where the area AR11 is arranged, as the information related to the area AR11. The terminal device 10 may transmit various types of information to the advertisement distribution device 100 as long as the information is related to the area. In FIG. 2, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating that the area AR11 is frame type A as the information related to the area AR11. In addition, when the advertisement delivery device 100 acquires the information on the area AR11, the terminal device 10 may not transmit the information on the region AR11 to the advertisement delivery device 100 in step S11.

  The advertisement distribution device 100 that has acquired the distribution request of the advertisement from the terminal device 10 determines the format of the advertisement content to be distributed to the terminal device 10 (step S12). Here, in order to determine the format of the advertisement content, the advertisement distribution apparatus 100 determines the format of the advertisement content based on the user information stored in the user information storage unit 121 and the model stored in the format information storage unit 123. Predict CTR. In FIG. 2, the advertisement distribution device 100 predicts the CTR for each of the formats FM11 to FM13 based on the user information of the user U10 and the model of each of the formats FM11 to FM13. Hereinafter, the predicted CTR may be referred to as a predicted CTR.

  In FIG. 2, the advertisement delivery apparatus 100 sets the predicted CTR of the format FM11 to “0.2”, the predicted CTR of the format FM12 to “0.1”, and the predicted CTR of the format FM13 as shown in the prediction list PR11. It is predicted to be 0.2 ".

  Then, the advertisement distribution device 100 estimates the eCPM of the advertisement content of each of the formats FM11 to FM13 based on the predicted CTR of each of the formats FM11 to FM13. In FIG. 2, the advertisement delivery apparatus 100 sets the eCPM of the format FM11 to "30 (yen)", the eCPM of the format FM12 to "10 (yen)", and the eCPM of the format FM13 to "20", as shown in the prediction list PR11. (Yen) ”.

  Then, the advertisement distribution device 100 determines the format with the highest eCPM among the plurality of formats FM11 to FM13 as the format of the advertisement content to be distributed. In FIG. 2, the advertisement distribution device 100 determines the format of the advertisement content to be distributed, which is the format FM11 having the highest eCPM when distributing the advertisement content to the user U10, as shown in the prediction list PR11. Thereby, the advertisement distribution device 100 can suppress an increase in the number of pieces of advertisement information extracted from the advertisement information storage unit 124 in the advertisement determination also in step S13 described below. For example, assuming that the number of pieces of advertisement information corresponding to each of the formats FM11 to FM13 is equal, the advertisement distribution device 100 compares the case where the advertisement information corresponding to all the formats FM11 to FM13 is extracted from the advertisement information storage unit 124. It is possible to suppress the number of advertisement information extracted to 1/3. Thus, the advertisement distribution device 100 can suppress the processing load for determining the advertisement to be distributed.

  Next, the advertisement distribution device 100 extracts advertisement information corresponding to the format FM11 determined in step S12 from the advertisement information storage unit 124. In FIG. 2, the advertisement distribution device 100 extracts, from the advertisement information storage unit 124, advertisement information identified by the advertisement ID “A11” and advertisement information identified by the advertisement ID “A12”. Hereinafter, the advertisement information identified by the advertisement ID "A11" is referred to as advertisement information A11, and the advertisement information identified by the advertisement ID "A12" is referred to as advertisement information A12.

  Here, in FIG. 2, the delivery target of the advertising content is male of twenties with user information, and the area AR11 is frame type A. Therefore, the advertisement distribution apparatus 100 is the eCPM in the case where a twenties male and frame type A are to be distributed among the advertisement information A11 and the advertisement information A12 corresponding to the format FM11 stored in the advertisement information storage unit 124. High advertisement information is determined as advertisement information of advertisement content to be distributed (step S13).

  Specifically, in FIG. 2, when advertising content is displayed in the area of frame type A for the user U10 of the twenties male, in the case of the advertising information A11, the eCPM is 40 (yen), and in the advertising information A12 If there is, eCPM is 10 (yen). Therefore, as shown in the advertisement information storage unit 124-1, the advertisement distribution apparatus 100 uses advertisement information A11 for distributing the advertisement information A11 having the highest eCPM when the frame type A is targeted for distribution as the advertisement information of the advertisement content. decide. That is, the advertisement distribution device 100 determines the advertisement information A11 regarding job change A as the advertisement information of the advertisement content to be distributed.

  The eCPM stored in the advertisement information storage unit 124 may be the entire average of advertisement content in which the same advertisement information is distributed to the same distribution target. Further, the eCPM based on the distribution target may be calculated after the format is determined in step S12.

  Thereafter, the advertisement distribution device 100 extracts a template corresponding to the advertisement information A11 determined in step S13 from the template information storage unit 125. In FIG. 2, the advertisement distribution device 100 extracts, from the template information storage unit 125, a template identified by the template ID “TP11”, a template identified by the template ID “TP12”, and the like. Hereinafter, the template identified by the template ID “TP11” is referred to as a template TP11, and the template identified by the template ID “TP12” is referred to as a template TP12.

  Here, in FIG. 2, the delivery target of the advertising content is male twenties with user information, the area AR 11 is frame type A, and the advertising information of the advertising content to be delivered is the advertising information A 11. Therefore, the advertisement distribution device 100 distributes the advertisement information A11, with the frame type A as the distribution target, of the template TP11 and the template TP12 corresponding to the format FM11 stored in the template information storage unit 125, etc. The template with the highest eCPM in is determined as a template for advertisement content to be delivered (step S14).

  Specifically, in FIG. 2, when the advertisement content is displayed in the frame type A area for the user U10 of the twenties male, in the case of the template TP11, the eCPM is 35 (yen) and in the case of the template TP12 eCPM is 20 (yen). Therefore, as shown in the template information storage unit 125-1, the advertisement distribution apparatus 100 distributes the template TP11 having the highest eCPM when distributing the advertisement information A11, with the frame type A as the distribution target, as a 20-year-old male. Determined as a template for advertising content. That is, the advertisement distribution device 100 determines the template used when the advertisement information A11 is displayed as the template TP11. The eCPM based on the distribution target may be calculated after the advertisement information is determined in step S13.

  Thereafter, the advertisement distribution device 100 distributes the advertisement content AC11 displaying the advertisement information A11 with the template TP11 to the terminal device 10 (step S15). Then, the terminal device 10 having received the advertisement content AC11 displays the advertisement content AC11 in the advertisement display area AR11 in the content CT10 (step S16).

  As described above, the advertisement distribution device 100 can suppress the processing load for determining the advertisement to be distributed by extracting only the advertisement information corresponding to the determined format after determining the format first. Specifically, the advertisement distribution device 100 can suppress an increase in the number of pieces of advertisement information to be extracted by reducing the number of formats targeted for extracting the advertisement information from the advertisement information storage unit 124. Thus, the advertisement distribution device 100 can suppress the processing load for determining the advertisement to be distributed. In addition, the advertisement distribution apparatus 100 can ensure profitability by distributing advertisement content with the highest possible eCPM based on the user information of the user using the terminal device 10 and the advertisement display area while suppressing the processing load. . In addition, although the case where a format was made into the classification in the data format of advertising information was shown in the example mentioned above, various classifications may be used for a format according to the object. For example, the advertisement distribution device 100 may format the type based on the management of the submitted advertisement information. For example, the advertisement distribution device 100 may format the type of the advertisement information submitted as a commercial item. Also, for example, the advertisement distribution device 100 may format the classification in management of the submitted advertisement information (for example, inventory management). In the above example, the advertisement distribution apparatus 100 generates a model. However, the advertisement distribution apparatus 100 is a model generated in advance, and is a model that predicts an evaluation value related to a type of data format of advertisement information. The type of advertisement content may be determined based on For example, the advertisement distribution device 100 may determine the type of the advertisement content based on a model that predicts an evaluation value regarding the type in the data format of the advertisement information acquired from the external device. That is, the advertisement distribution device 100 may be a determination device that determines the type of advertisement content based on a model that predicts an evaluation value regarding the type in the data format of the advertisement information.

[2. Configuration of Advertisement Distribution Device]
Next, the configuration of the advertisement distribution device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing an exemplary configuration of the advertisement distribution device 100 according to the embodiment. As shown in FIG. 3, the advertisement distribution device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the advertisement distribution apparatus 100 includes an input unit (for example, a keyboard or a mouse) that receives various operations from the administrator of the advertisement distribution apparatus 100 and a display unit (for example, a liquid crystal display or the like) for displaying various information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to the network by wire or wirelessly, and transmits and receives information to and from the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a user information storage unit 121, a distribution log information storage unit 122, a format information storage unit 123, an advertisement information storage unit 124, and a template information storage unit 125. And.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various types of information related to content. FIG. 4 shows an example of the user information storage unit 121 according to the embodiment. The user information storage unit 121 illustrated in FIG. 4 includes items such as “user ID”, “age”, “sex”, “click count”, and “action history”.

  "User ID" indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user illustrated in the example of FIG. "Age" indicates the age of the user identified by the user ID. The “age” may be a specific age of the user identified by the user ID, such as 35, for example. Also, “sex” indicates the gender of the user identified by the user ID.

  Also, “the number of clicks” indicates the average of the number of clicks in a predetermined period A. The “number of clicks” is not limited to the example illustrated in FIG. 4, and various information may be stored according to the purpose. For example, “the number of clicks” may be a ratio of the number of clicks to the number of times the advertisement content is displayed. The case of determining the format based on the “number of clicks” will be described later.

  Also, "action history" indicates the corresponding user's action history. The "action history" includes items such as "action content" and "date and time". "Action content" indicates the content of the user's action. "Date" indicates the date on which the corresponding action was taken.

  For example, in the example illustrated in FIG. 4, the age of the user identified by the user ID “U1” is “twenties”, and the gender indicates “male”. Also, for example, the user identified by the user ID “U1” indicates that the click count is “2.5”. Also, the user identified by the user ID “U1” indicates that the Internet search was performed using the search query “car” on August 23, 2015 at 12:34:26. Further, the user identified by the user ID “U1” indicates that the site A was browsed at 14:12:45 on August 23, 2015.

  The user information storage unit 121 is not limited to the above, and may store various information according to the purpose. For example, the user information storage unit 121 may store information such as name, family structure, income, and work place.

(Distribution log information storage unit 122)
The delivery log information storage unit 122 according to the embodiment stores various pieces of information regarding the delivery log. FIG. 5 shows an example of the delivery log information storage unit 122 according to the embodiment. In FIG. 5, the distribution log information acquired from each terminal device 10 is stored. The delivery log information storage unit 122 illustrated in FIG. 5 includes items such as “log ID”, “delivery destination (user)”, and “delivery content”.

  “Log ID” indicates identification information for identifying distribution log information. Also, “delivery destination (user)” indicates a delivery destination of advertisement content in the corresponding delivery log. The “delivery content” includes items such as “advertising content” and “click”. "Advertising content" indicates advertising content distributed in the corresponding distribution log. Also, "click" indicates whether the corresponding advertisement content is clicked by the user.

  For example, in the example illustrated in FIG. 5, in the distribution identified by the log ID “LG11”, it indicates that the advertisement content AC11 distributed to the terminal device 10 of the user U1 is clicked. Further, in the distribution identified by the log ID “LG12”, it indicates that the advertisement content AC21 distributed to the terminal device 10 of the user U1 is not clicked.

  The distribution log information storage unit 122 is not limited to the above, and may store various information according to the purpose. For example, the delivery log information storage unit 122 may store information on the time when the advertisement content is delivered or information on the time when the advertisement content is displayed.

(Format information storage unit 123)
The format information storage unit 123 according to the embodiment stores various information on a model for calculating an evaluation value of the format (for example, CTR). FIG. 6 shows an example of the format information storage unit 123 according to the embodiment. The format information storage unit 123 illustrated in FIG. 6 includes items such as “format ID”, “format”, and “model”.

  “Format ID” indicates identification information for identifying a format. "Format" indicates the type of information included in the format. Also, “model” indicates a model for calculating CTR of the corresponding format.

  In the example shown in FIG. 6, the format information storage unit 123 stores information on a plurality of formats identified by the format IDs “FM11” to “FM13”. For example, in FIG. 6, the format identified by the format ID "FM11" is text (character information). Also, the format identified by the format ID “FM12” is an image. Also, the format identified by the format ID "FM13" is a combination of text and image.

  For example, the format identified by the format ID “FM11” indicates that the weight of feature 1 is “0.6” and the weight of feature 2 is “0.1”. Also, for example, the format identified by the format ID “FM12” indicates that the weight of feature 1 is “0.2” and the weight of feature 2 is “0.5”. Also, for example, the format identified by the format ID “FM 13” indicates that the weight of feature 1 is “0.3” and the weight of feature 2 is “0.3”. The weight of each feature may be a negative number.

  The format information storage unit 123 is not limited to the above, and may store various information according to the purpose.

(Advertising information storage unit 124)
The advertisement information storage unit 124 according to the embodiment stores various types of information regarding advertisement information of advertisement content. FIG. 7 shows an example of the advertisement information storage unit 124 according to the embodiment. The advertisement information storage unit 124 illustrated in FIG. 7 includes items such as “format ID”, “advertisement ID”, “advertisement information”, and “eCPM”.

  “Format ID” indicates identification information for identifying a format. "Advertisement ID" indicates identification information for identifying advertisement information. "Advertising information" indicates information about an advertisement submitted by an advertiser. For example, in the “advertising information”, text information, image information, a combination of text information and image information, etc. submitted from an advertiser are stored. Also, “eCPM” indicates eCPM for each distribution target based on the combination of user information and frame type.

  In the example illustrated in FIG. 7, each advertisement information is stored in the advertisement information storage unit 124 in association with the format IDs “FM11” to “FM13” and the like. For example, in FIG. 7, the advertisement information identified by the advertisement ID “A11” is stored in association with the format ID “FM11”. That is, the advertisement information identified by the advertisement ID "A11" indicates that it is text (character information). The advertisement information identified by the advertisement ID "A11" indicates that the information contains information such as a sentence "job change A if job change" and a URL (Uniform Resource Locator) "www.tensyoku ..".

  For example, the advertisement information identified by the advertisement ID "A11" indicates that the eCPM is "20 yen" when the user to be distributed is a 20's female and the advertisement display area is frame type A. Further, for example, in the advertisement information identified by the advertisement ID "A11", when the user to be delivered is a male in his twenties and the advertisement display area is a frame type A, it indicates that the eCPM is "40" yen. .

  The advertisement information storage unit 124 may store various information according to the purpose, not limited to the above. For example, the advertisement information storage unit 124 may store identification information for identifying an advertiser, information indicating the classification of a product or service to be advertised, or identification information for identifying a product or service. Good. In addition, for example, the advertisement information storage unit 124 may store information on a bid price.

(Template information storage unit 125)
The template information storage unit 125 according to the embodiment stores various types of information regarding a template of advertisement content. FIG. 8 shows an example of the template information storage unit 125 according to the embodiment. The template information storage unit 125 illustrated in FIG. 8 includes items such as “format ID”, “template ID”, “template”, and “eCPM”.

  “Format ID” indicates identification information for identifying a format. “Template ID” indicates identification information for identifying a template. "Template" indicates information on the display style of advertisement content. Also, “eCPM” indicates eCPM for each delivery target based on a combination of user information and frame type corresponding to each piece of advertisement information.

  In the example illustrated in FIG. 8, each template is stored in the template information storage unit 125 in association with the format IDs “FM11” to “FM13” and the like. For example, in FIG. 8, the template identified by the template ID “TP31” is stored in association with the format ID “FM13”. That is, the template identified by the template ID “TP31” indicates that the image information is displayed on the left side and the text (character information) is displayed on the right side. The template may include any information as long as it relates to display of advertising content, such as the size, color, and number of lines of character information.

  For example, the template identified by the template ID “TP31” indicates that the eCPM is “30” yen when the user to be distributed is a 20's female and the advertisement display area is frame type A. Further, for example, the template identified by the template ID “TP31” indicates that the eCPM is “15” yen when the user to be distributed is a twenties male and the advertisement display area is a frame type A.

  The template information storage unit 125 is not limited to the above, and may store various information according to the purpose. For example, the template information storage unit 125 may store the eCPM of the entire advertising content distributed by the template for each distribution target based on the combination of the user information and the frame type.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 may execute various programs (such as distribution programs) stored in a storage device inside the advertisement distribution device 100 by, for example, a central processing unit (CPU) or a micro processing unit (MPU). (Corresponding to an example) is realized by executing the RAM as a work area. Further, the control unit 130 is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a generation unit 132, a reception unit 133, a first determination unit 134, a second determination unit 135, a third determination unit 136, and a distribution unit. And implements or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as it performs the information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3, and may be another connection relationship.

(Acquisition unit 131)
The acquisition unit 131 acquires user information on the user. For example, the acquisition unit 131 acquires user information such as the action history of the user U1 from the terminal device 10. In FIG. 1, the acquisition unit 131 acquires information indicating that the user U1 is a 20-year-old male in the user information storage unit 121, and information indicating that a search has been performed on a car, that a site A has been browsed, and the like. . Note that the acquiring unit 131 may acquire various information according to the purpose, such as the user's age and gender, as well as the user's action history, as long as the information is user information. In addition, the acquisition unit 131 stores the acquired user information in the user information storage unit 121.

  In addition, the acquisition unit 131 acquires distribution log information on an advertisement distributed from the terminal device 10 used by the user U1. In FIG. 1, the acquisition unit 131 acquires information indicating that the user U1 has clicked on the advertising content AC11 from the terminal device 10 used by the user U1. Further, in FIG. 1, the acquisition unit 131 acquires, from the terminal device 10 used by the user U1, information indicating that the user U1 has not clicked the advertising content AC21.

(Generation 132)
Based on the user information acquired by the acquisition unit 131, the generation unit 132 generates a model that predicts the evaluation value regarding the type in the data format of the advertisement information. For example, based on the user information acquired by the acquisition unit 131, the generation unit 132 generates a model for predicting CTR related to the format of the advertisement information. For example, based on the user information acquired by the acquisition unit 131, the generation unit 132 generates a model that predicts the click rate related to the format.

  In FIG. 1, the generation unit 132 is a model that predicts the CTR for each of the formats FM11 to FM13 using the user information stored in the user information storage unit 121 and the distribution log information stored in the distribution log information storage unit 122. Generate For example, the generation unit 132 predicts the CTR of the format FM11 using the user information stored in the user information storage unit 121, and the distribution log information on the advertisement content of the format FM11 stored in the distribution log information storage unit 122. Generate a model.

  In addition, the generation unit 132 derives a weight corresponding to each feature as a model for predicting the CTR for each format. The weight of the model generated by the generation unit 132 may be 0 or a negative value. The generation unit 132 may also generate a model using various conventional techniques as appropriate. For example, the generation unit 132 may generate a model by deriving the weight of the extracted feature by learning, or may generate the model using a feature designated in advance. For example, the generation unit 132 generates a model in which the feature 1 shown in FIG. 1 is “male” and the feature 2 is “visiting site B” or the like. The feature may include information related to the advertisement display area (for example, a frame type to be described later). Further, the generation unit 132 stores the generated model of each format in the format information storage unit 123. When the advertisement distribution apparatus 100 is a model generated in advance and the type of advertisement content is determined based on a model that predicts an evaluation value regarding a type in a data format of advertisement information, the generation unit 132 is not included. May be For example, when the advertisement distribution apparatus 100 determines the type of the advertisement content based on a model that predicts an evaluation value regarding the type in the data format of the advertisement information acquired from the external device, the generation unit 132 may not be included. That is, the advertisement distribution device 100 may be a determination device that does not have the generation unit 132 and determines the type of advertisement content based on a model that predicts an evaluation value regarding the type in the data format of the advertisement information.

(Reception unit 133)
The receiving unit 133 receives an advertisement distribution request from the terminal device 10. For example, the reception unit 133 receives user information on the user U10 using the terminal device 10 and information on the area AR11. In FIG. 2, the receiving unit 133 receives, from the terminal device 10, information indicating that the user U10 is in his twenties and is a male as user information of the user U10. The receiving unit 133 may receive various types of information from the terminal device 10 as well as the age and the gender as long as the information is user information. Further, in FIG. 2, the receiving unit 133 receives, from the terminal device 10, information indicating the size of the area AR11, the position where the area AR11 is disposed, and the like as the information related to the area AR11. The receiving unit 133 may receive various types of information from the terminal device 10 as well as the age and the gender as long as the information is on the area. In FIG. 1, the receiving unit 133 may receive, from the terminal device 10, information indicating that the area AR11 is frame type A as the information related to the area AR11.

  Also, the reception unit 133 may receive a draft of an advertisement from the advertiser. Note that the receiving unit 133 may receive an advertisement submission from an agency requested by the advertiser to submit an advertisement. In this case, for example, the reception unit 133 receives an advertisement submission from an information processing apparatus used by the advertiser or the agency. Also, for example, the reception unit 133 stores the advertisement information for which the submission has been received in the advertisement information storage unit 124.

(First determination unit 134)
The first determination unit 134 determines the type in the data format of the advertisement information. For example, the first determination unit 134 determines the format among the format of the advertisement information in the advertisement content and the template for displaying the advertisement information as the advertisement content.

  The first determination unit 134 determines the format of the advertising content to be distributed to the user based on the evaluation predicted (estimated) by the information on the user using the terminal device 10 and the model. In FIG. 2, in order to determine the format of the advertising content, the first determination unit 134 determines the format based on the user information stored in the user information storage unit 121 and the model stored in the format information storage unit 123. Predict each CTR. Specifically, the first determination unit 134 predicts the CTR for each of the formats FM11 to FM13 based on the user information of the user U10 and the model of each of the formats FM11 to FM13. In FIG. 2, as shown in the prediction list PR11, the first determination unit 134 sets “0.2” for the prediction CTR of the format FM11, “0.1” for the prediction CTR of the format FM12, and the prediction CTR of the format FM13. It is predicted to be "0.2".

  Then, the first determination unit 134 estimates the eCPM of the advertising content of each of the formats FM11 to FM13 based on the predicted CTR of each of the formats FM11 to FM13. In FIG. 2, as shown in the prediction list PR11, the first determination unit 134 sets the eCPM of the format FM11 to "30 (yen)", the eCPM of the format FM12 to "10 (yen)", and the eCPM of the format FM13 to "10". It is estimated that “20 (yen)”.

  Then, the first determination unit 134 determines the format with the highest eCPM among the plurality of formats FM11 to FM13 as the format of the advertising content to be distributed. In FIG. 2, as shown in the prediction list PR11, the first determination unit 134 determines the format FM11 having the highest eCPM in the case of distributing the advertisement content to the user U10 as the format of the advertisement content to be distributed.

  In addition, when the user satisfies the predetermined condition, the first determination unit 134 determines a plurality of formats as candidates for the format of the advertising content to be distributed to the terminal device 10. For example, when the click rate of the advertisement of the user within a predetermined period is equal to or higher than a predetermined threshold, the first determination unit 134 determines a plurality of formats as candidates for the format of the advertising content to be distributed to the terminal device 10. The details of the determination of the plurality of formats based on the user will be described later.

  In addition, the first determination unit 134 determines a predetermined evaluation value corresponding to each format among the formats as a candidate of the format of the advertising content to which the upper format is distributed. For example, the first determination unit 134 determines, as a format candidate of the advertising content to which a click rate (CTR) as a predetermined evaluation value among the formats distributes the upper format. In addition, for example, the first determination unit 134 determines, among the formats, an expected revenue value (eCPM) as a predetermined evaluation value as a candidate for the format of the advertising content to which the upper format is distributed. For example, the first determination unit 134 determines a format having the highest predetermined evaluation value and a format of a predetermined evaluation value within a predetermined range from a predetermined evaluation value of the format as a candidate format of the advertising content to be delivered Do. In addition, the detail about determination of the several format based on a predetermined evaluation value is mentioned later.

(Second determination unit 135)
Further, the second determination unit 135 determines, among the advertisement information corresponding to the type determined by the first determination unit 134, the advertisement information to be distributed. For example, the second determination unit 135 determines, among the advertisement information corresponding to the format determined by the first determination unit 134, the advertisement information to be distributed to the terminal device 10.

  Specifically, the second determination unit 135 extracts advertisement information corresponding to the format determined by the first determination unit 134 from the advertisement information storage unit 124. Then, the second determination unit 135 determines the advertisement information of the advertisement content to be distributed to the terminal device 10 from the extracted advertisement information. In FIG. 2, as shown in the advertisement information storage unit 124-1, the second determination unit 135 uses the advertisement content A11 for delivering the advertisement information A11 with the highest eCPM when the frame type A is targeted for delivery to a male in twenties. Determined as advertising information.

(Third determination unit 136)
The third determination unit 136 determines the display style of the advertisement information determined by the second determination unit 135. For example, the third determination unit 136 determines the template of the advertisement information determined by the second determination unit 135. For example, the third determination unit 136 determines a template for displaying advertisement information as advertisement content. In FIG. 2, as shown in the template information storage unit 125-1, the third determination unit 136 targets the frame type A as a delivery target for the twenties male, and delivers the template TP 11 with the highest eCPM when the advertisement information A 11 is delivered. , Decide as a template for advertising content to deliver. For example, the third determination unit 136 determines the template used when displaying the advertisement information A11 as the template TP11.

(Distribution unit 137)
The distribution unit 137 distributes the advertising content for which the template has been determined by the third determination unit 136. In FIG. 2, the distribution unit 137 distributes to the terminal device 10 the advertisement content AC11 in which the advertisement information A11 is displayed by the template TP11.

[3. Flow of generation process]
Next, a procedure of generation processing by the distribution system 1 according to the embodiment will be described using FIG. FIG. 9 is a flowchart illustrating an example of the generation process according to the embodiment.

  As illustrated in FIG. 9, the acquisition unit 131 of the advertisement distribution device 100 receives user information (step S101). For example, the acquisition unit 131 receives, from the terminal device 10, user information such as an action history of a user who uses the terminal device 10. The acquisition unit 131 also acquires distribution log information (step S102). For example, the reception unit 133 acquires information on the presence or absence of click of the advertising content distributed to the terminal device 10. Note that step S101 and step S102 may be performed a plurality of times separately, and step S102 may be performed before step S101.

  Thereafter, the generation unit 132 of the advertisement distribution device 100 generates a model based on the user information acquired in step S101 and the distribution log information acquired in step S102 (step S103). For example, the generation unit 132 generates a model for predicting the CTR of each of the formats FM11 to FM13 based on the user information stored in the user information storage unit 121 and the distribution log information stored in the distribution log information storage unit 122. .

[4. Flow of distribution process]
Next, a procedure of distribution processing by the distribution system 1 according to the embodiment will be described using FIG. FIG. 10 is a flowchart illustrating an example of the distribution process according to the embodiment.

  As shown in FIG. 10, the receiving unit 133 of the advertisement distribution device 100 receives an advertisement distribution request (step S201). For example, the receiving unit 133 receives an advertisement distribution request from the terminal device 10. Further, the receiving unit 133 receives information on the area for displaying an advertisement (step S202). For example, the reception unit 133 receives information on the advertisement display area AR11 from the terminal device 10. Step S202 may be performed in step S201, or may be performed before step S201.

  Thereafter, the first determination unit 134 of the advertisement distribution device 100 determines the format of the advertisement information to be distributed based on the user information and the model (step S203). For example, the first determination unit 134 selects the format of the advertising content from the plurality of formats stored in the format information storage unit 123 by comparing the eCPM based on the predicted CTR by the model.

  Thereafter, the second determination unit 135 of the advertisement distribution device 100 extracts the advertisement information corresponding to the format determined in step S203 (step S204). For example, the second determination unit 135 extracts the advertisement information corresponding to the format from the advertisement information storage unit 124. Then, the second determination unit 135 determines advertisement information to be distributed from the advertisement information extracted in step S204 (step S205).

  Thereafter, the third determination unit 136 of the advertisement distribution device 100 determines the template of the advertisement information determined in step S205 (step S206). After that, the distribution unit 137 of the advertisement distribution device 100 distributes the advertisement content for displaying the advertisement information by the template determined in step S206 (step S207).

[5. Multiple Format Determination Based on User]
As described above, the first determining unit 134 of the advertisement distribution device 100 determines a plurality of formats as candidates for the format of the advertising content to be distributed to the terminal device 10 when the user distributing the advertising content satisfies the predetermined condition. May be This point will be described with reference to FIG. In addition, in FIG. 11, the case where the advertisement delivery apparatus 100 has already acquired user information such as the action history of the user U2 will be described as an example. Further, FIG. 11 shows only the configuration of the distribution system 1 required to explain determination of a plurality of formats. The description of the same points as FIG. 1 will be omitted as appropriate.

  FIG. 11 is a diagram illustrating an example of a generation process of determining a plurality of formats according to the embodiment. Specifically, FIG. 11 shows advertisement content for distributing a plurality of formats to the terminal device 10 when the click rate of the user's advertisement within a predetermined period (for example, one week, one month, etc.) is equal to or higher than a predetermined threshold. The case of determining as a candidate of the format of. That is, the example shown in FIG. 11 shows the case where the user U2 is a user whose click rate in a predetermined period is equal to or higher than a predetermined threshold (hereinafter, may be referred to as a "clicker"). For example, in the case where the number of clicks in the predetermined period A is “5 (times)” and it is assumed that the clicker, as shown in FIG. 4, the average number of clicks in the predetermined period A is “8 ( Times) and is a clicker.

  In the example illustrated in FIG. 11, the terminal device 10 that has received the content CT10 transmits a distribution request for advertisement content to the advertisement distribution device 100 because the content CT10 includes the advertisement display area AR11 (step S21). In FIG. 11, in step S21, the terminal device 10 transmits information on the area AR11 to the advertisement distribution device 100 as a distribution request.

  In step S21, for example, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating the size of the area AR11 or the position where the area AR11 is arranged, as the information on the area AR11. In FIG. 11, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating that the area AR11 is the frame type A as the information related to the area AR11. In addition, when the advertisement delivery device 100 acquires information on the area AR11, the terminal device 10 may not transmit the information on the region AR11 to the advertisement delivery device 100 in step S21.

  Then, the advertisement distribution apparatus 100 performs CTR for each format based on the user information stored in the user information storage unit 121 and the model stored in the format information storage unit 123 in order to determine the format of the advertisement content. Predict. In FIG. 11, the advertisement delivery apparatus 100 predicts the CTR for each of the formats FM11 to FM13 based on the user information of the user U2 and the model of each of the formats FM11 to FM13.

  In FIG. 11, as shown in the prediction list PR21, the advertisement distribution device 100 sets the prediction CTR of the format FM11 to "0.2", the prediction CTR of the format FM12 to "0.1", and the prediction CTR of the format FM13. It is predicted to be 0.2 ".

  Then, the advertisement distribution device 100 estimates the eCPM of the advertisement content of each of the formats FM11 to FM13 based on the predicted CTR of each of the formats FM11 to FM13. In FIG. 11, the advertisement delivery apparatus 100 sets the eCPM of the format FM11 to "30 (yen)", the eCPM of the format FM12 to "10 (yen)", and the eCPM of the format FM13 to "20" as shown in the prediction list PR21. (Yen) ”.

  Here, since the user U2 who uses the terminal device 10 is the clicker, the advertisement distribution device 100 determines a plurality of formats (step S22). That is, the advertisement distribution device 100 determines a plurality of formats as candidates for the format of the advertisement content to be distributed to the terminal device 10. Specifically, the advertisement distribution device 100 determines two formats out of a plurality of formats shown in the prediction list PR21 as candidates for the format of the advertisement content to be distributed to the terminal device 10.

  Specifically, the advertisement distribution device 100 determines, among the plurality of formats FM11 to FM13, as a format content candidate for distributing the format with the highest eCPM and the second format with the highest eCPM. In FIG. 11, the advertisement distribution device 100 determines the format FM11 having the highest eCPM and the format FM13 having the second highest eCPM in the case of distributing the advertisement content to the user U1 as candidates for the format of the advertisement content to be distributed.

  The processing after step S22 is the same as steps S13 to S16 shown in FIG. For example, the advertisement distribution device 100 extracts the advertisement information corresponding to each of the format FM11 and the format FM13 from the advertisement information storage unit 124, and determines the advertisement information of the highest eCPM as the advertisement information of the advertisement content to be distributed. Further, the advertisement distribution device 100 sets a frame type A as a distribution target for a twenties male, and determines a template with the highest eCPM in the case of distributing the determined advertisement information as a template of advertisement content to be distributed. Then, the advertisement distribution device 100 distributes, to the terminal device 10, advertisement content for displaying the determined advertisement information using the determined template.

  In this way, the advertisement distribution device 100 can distribute advertisement content as high as possible for high-click users, that is, good users, while suppressing an increase in the number of advertisement information extracted from the advertisement information storage unit 124. it can.

[6. Determination of multiple formats based on evaluation values]
As described above, the first determination unit 134 of the advertisement distribution device 100 may determine the predetermined evaluation value corresponding to each format among the types as a candidate of the format of the advertisement content to which the upper format is distributed. This point will be described with reference to FIG. Moreover, in FIG. 12, the case where a predetermined evaluation value is set to eCPM is demonstrated to an example. In addition, eCPM is an example and various evaluation values may be used as the predetermined evaluation value according to the purpose such as CTR. Moreover, in FIG. 12, the case where the advertisement delivery apparatus 100 has already acquired user information such as the action history of the user U3 will be described as an example. Further, FIG. 12 shows only the configuration of the distribution system 1 required to explain determination of a plurality of formats. The description of the same points as FIG. 1 will be omitted as appropriate.

  FIG. 12 is a diagram illustrating an example of a generation process of determining a plurality of formats according to the embodiment. Specifically, FIG. 12 shows a format in which eCPM is the highest among eCPM high-order formats and an eCPM format within a predetermined range (within 5 (yen) in FIG. 12) from the eCPM of the format. The case where it determines as a candidate of the format of advertising content to deliver is shown.

  In the example illustrated in FIG. 12, the terminal device 10 that has received the content CT10 transmits a distribution request for the advertisement content to the advertisement distribution device 100 because the content display region AR11 is included in the content CT10 (step S31). In FIG. 12, in step S31, the terminal device 10 transmits information on the area AR11 to the advertisement distribution device 100 as a distribution request.

  In step S31, for example, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating the size of the area AR11 or the position where the area AR11 is arranged, as the information related to the area AR11. In FIG. 12, the terminal device 10 transmits, to the advertisement distribution device 100, information indicating that the area AR11 is frame type A as the information related to the area AR11. In addition, when the advertisement delivery device 100 acquires information on the area AR11, the terminal device 10 may not transmit the information on the region AR11 to the advertisement delivery device 100 in step S31.

  Then, the advertisement distribution apparatus 100 performs CTR for each format based on the user information stored in the user information storage unit 121 and the model stored in the format information storage unit 123 in order to determine the format of the advertisement content. Predict. In FIG. 12, the advertisement delivery apparatus 100 predicts the CTR for each of the formats FM11 to FM13 based on the user information of the user U3 and the model of each of the formats FM11 to FM13.

  In FIG. 12, the advertisement delivery apparatus 100 sets the prediction CTR of the format FM11 to "0.2", the prediction CTR of the format FM12 to "0.3", and the prediction CTR of the format FM13 as shown in the prediction list PR31. It is predicted to be "0.25".

  Then, the advertisement distribution device 100 estimates the eCPM of the advertisement content of each of the formats FM11 to FM13 based on the predicted CTR of each of the formats FM11 to FM13. In FIG. 12, the advertisement delivery apparatus 100 sets the eCPM of the format FM11 to "20 (yen)", the eCPM of the format FM12 to "35 (yen)", and the eCPM of the format FM13 to "32" as shown in the prediction list PR31. (Yen) ”.

  Here, “32 (yen)” which is the eCPM of the format FM13 is within 5 (yen) from “35 (yen)” which is the eCPM of the format FM12 at which the eCPM is the highest. Therefore, as shown in the prediction list PR31, the advertisement distribution apparatus 100 has a format FM12 with the highest eCPM in the case of distributing the advertisement content to the user U3, and a format that is eCPM within 5 (yen) from the eCPM of the format FM12. The FM 13 is determined as a candidate of the format of the advertising content to be distributed (step S32).

  The process after step S32 is the same as steps S13 to S16 shown in FIG. For example, the advertisement distribution device 100 extracts the advertisement information corresponding to each of the format FM12 and the format FM13 from the advertisement information storage unit 124, and determines the advertisement information with the highest eCPM as the advertisement information of the advertisement content to be distributed. Further, the advertisement distribution device 100 targets the frame type A as a 20-year-old female distribution target, and determines a template with the highest eCPM in the case of distributing the determined advertisement information as a template of the advertisement content to be distributed. Then, the advertisement distribution device 100 distributes, to the terminal device 10, advertisement content for displaying the determined advertisement information using the determined template.

  Thereby, the advertisement distribution apparatus 100 suppresses the increase in the number of advertisement information extracted from the advertisement information storage unit 124, and when the evaluation values are in competition, that is, it is more appropriate to select a format other than the highest eCPM. As much as possible, it is possible to deliver advertisement content as appropriate as possible.

[7. effect〕
As described above, the advertisement distribution device 100 according to the embodiment includes the acquisition unit 131 and the generation unit 132. The acquisition unit 131 acquires user information on the user. In addition, based on the user information acquired by the acquisition unit 131, the generation unit 132 evaluates the evaluation value (CTR in the embodiment) on the type ("format" in the embodiment, the same applies hereinafter) in the data format of the advertisement information. Generate a model that predicts the same.

  Thereby, the advertisement distribution device 100 according to the embodiment can generate a model that appropriately predicts the evaluation value regarding the format of the advertisement information to be distributed. That is, the advertisement distribution device 100 can appropriately use a model that predicts the evaluation value regarding the format of the advertisement information to be distributed. For example, the advertisement distribution device 100 can appropriately predict the evaluation value of each format and distribute the appropriate content even when distributing the advertisement content whose distribution record is not sufficient. Also, for example, the advertisement distribution device 100 can appropriately predict the evaluation value of each format and distribute appropriate content even when distributing to a user whose distribution record is not sufficient.

  Further, in the advertisement distribution device 100 according to the embodiment, the generation unit 132 generates a model that predicts the click rate related to the type based on the user information acquired by the acquisition unit 131.

  Thereby, the advertisement distribution device 100 according to the embodiment can generate a model that appropriately predicts the CTR related to the format of the advertisement information to be distributed.

  In addition, the advertisement distribution device 100 according to the embodiment includes a determination unit (in the embodiment, the “first determination unit 134. The same applies to the following). The determination unit determines the type of the advertising content based on the model generated by the generation unit 132.

  Thereby, the advertisement distribution device 100 according to the embodiment can determine the format based on a model that appropriately predicts the evaluation value regarding the type of advertisement content to be distributed. That is, the advertisement distribution device 100 can appropriately use a model that predicts the evaluation value regarding the format of the advertisement information to be distributed.

  In addition, the advertisement distribution device 100 according to the embodiment includes the reception unit 133. The receiving unit 133 receives an advertisement distribution request from the terminal device 10. Further, the determination unit determines the type of the advertisement content to be distributed to the terminal device 10 based on the evaluation value predicted by the user information on the user using the terminal device 10 and the model.

  Thereby, the advertisement distribution device 100 according to the embodiment can suppress an increase in the number of pieces of advertisement information to be extracted. For example, in FIG. 2, when the number of pieces of advertisement information corresponding to each of the formats FM11 to FM13 is equal, the advertisement distribution device 100 extracts the advertisement information corresponding to all the formats FM11 to FM13 from the advertisement information storage unit 124. The number of pieces of advertisement information to be extracted to 1/3 can be reduced compared to the case of FIG. Thus, the advertisement distribution device 100 can suppress the processing load for determining the advertisement to be distributed.

  In addition, in the advertisement distribution device 100 according to the embodiment, when the user who uses the terminal device 10 satisfies the predetermined condition, the determination unit determines a plurality of types as candidates for the type of advertisement content to be distributed to the terminal device 10 .

  Thereby, the advertisement distribution device 100 according to the embodiment can distribute advertisement content as appropriate as possible to the user who satisfies the predetermined condition while suppressing an increase in the number of pieces of advertisement information to be extracted.

  In addition, in the advertisement distribution device 100 according to the embodiment, the determination unit distributes a plurality of types to the terminal device 10 when the click rate of the advertisement of the user using the terminal device 10 within the predetermined period is equal to or more than the predetermined threshold. It is determined as a candidate for the type of advertising content to be

  Thereby, the advertisement distribution device 100 according to the embodiment can distribute advertisement content as high as possible to a user with high click rate, that is, a good user while suppressing an increase in the number of advertisement information to be extracted.

  In addition, in the advertisement distribution device 100 according to the embodiment, the determination unit determines, as a candidate of the type of advertisement content to which a predetermined evaluation value corresponding to each type among the types is distributed.

  As a result, the advertisement distribution device 100 according to the embodiment can distribute advertisement content as appropriate as possible even when evaluation values are in competition, while suppressing an increase in the number of pieces of advertisement information to be extracted.

  In addition, in the advertisement distribution device 100 according to the embodiment, the determination unit determines, as a candidate for the type of advertisement content to which a higher click rate as a predetermined evaluation value is distributed among types.

  Thereby, the advertisement distribution apparatus 100 according to the embodiment suppresses an increase in the number of pieces of advertisement information to be extracted, and in the case where the evaluation values are antagonistic, that is, a method other than the format having the highest clickthrough rate (CTR) is selected. As much as possible, it is possible to deliver the ad content as much as possible when there is a high possibility that the ad can be delivered more appropriately.

  In addition, in the advertisement distribution device 100 according to the embodiment, the determination unit determines, as a candidate of the type of the advertisement content to which the expected earnings value as the predetermined evaluation value among the types is higher, is distributed.

  Thereby, the advertisement distribution apparatus 100 according to the embodiment selects a format other than the format with the highest expected profit value (eCPM) when the evaluation values are antagonistic while suppressing an increase in the number of advertisement information to be extracted. Ad content can be delivered as much as possible, where it is likely that the more appropriate ad can be delivered.

  In addition, in the advertisement distribution device 100 according to the embodiment, the determination unit distributes the type having the highest predetermined evaluation value and the type of the predetermined evaluation value within a predetermined range from the predetermined evaluation value of the type. Determined as a candidate for content type.

  In this way, the advertisement distribution apparatus 100 according to the embodiment is more appropriate to select a format other than the highest evaluation value when the evaluation values are antagonistic while suppressing an increase in the number of pieces of advertisement information to be extracted. As much as possible, it is possible to deliver ad content that is as appropriate as possible when the ad can be delivered.

[8. Hardware configuration]
The advertisement distribution device 100 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in FIG. FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the function of the advertisement distribution device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

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

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from another device via the network N, sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the network N.

  The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also 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 the CPU 1100 with the program 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 digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the advertisement distribution device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

  Although some of the embodiments and modifications of the present application have been described above in detail based on the drawings, these are merely examples, and various aspects can be obtained based on the knowledge of those skilled in the art, including the aspects described in the rows of the disclosure of the invention. It is possible to carry out the present invention in other forms that have been modified and improved.

[9. Other]
Further, among the processes described in the embodiment and the modification, all or part of the process described as being automatically performed can be manually performed, or it is described as manually performed. All or part of the treatment may be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  Moreover, it is possible to combine suitably the embodiment and modification which were mentioned above in the range which does not make process content contradictory.

  In addition, the "section (module, unit)" described above can be read as "means" or "circuit". For example, the reception unit can be read as reception means or a reception circuit.

1 Distribution system 100 Advertisement distribution device (generation device)
121 user information storage unit 122 distribution log information storage unit 123 format information storage unit 124 advertisement information storage unit 125 template information storage unit 130 control unit 131 acquisition unit 132 generation unit 133 reception unit 134 first determination unit (determination unit)
135 second determination unit 136 third determination unit 137 distribution unit 10 terminal device 50 content distribution device N network

Claims (15)

  1. The user information on the user is acquired , the acquired user information is stored in the user information storage unit, the distribution log information on the advertisement distributed to the user is acquired, and the acquired distribution log information is stored in the distribution log information storage unit Acquisition part,
    By based rather learning and the distribution log information stored in the distribution log information storage part with the stored user information in the user information storage unit, to generate a model that predicts an evaluation value related to the type of data format of the advertisement information A generation unit,
    A generator characterized by comprising.
  2. The generation unit is
    The generation device according to claim 1, wherein a model for predicting a click rate related to the type is generated based on the user information acquired by the acquisition unit.
  3. A determination unit that determines the type of advertising content based on the model generated by the generation unit;
    The generation apparatus according to claim 1, further comprising:
  4. A reception unit for receiving an advertisement distribution request from a terminal device;
    And further
    The determination unit is
    The type of advertisement content to be distributed to the terminal device is determined based on the evaluation value predicted by the user information of the user using the terminal device and the model. apparatus.
  5. The determination unit is
    The generation device according to claim 4, wherein when the user using the terminal device satisfies a predetermined condition, a plurality of types are determined as candidates for the type of advertising content to be distributed to the terminal device.
  6. The determination unit is
    When the click rate of the advertisement of the user using the terminal device within a predetermined period is equal to or higher than a predetermined threshold, a plurality of types are determined as candidates for the type of advertisement content to be delivered to the terminal device. The generator according to Item 5.
  7. The determination unit is
    The predetermined evaluation value corresponding to each of the types among the types is determined to be an upper type as a candidate of the type of the advertising content to be delivered to the terminal device. Generator of.
  8. The determination unit is
    The generation device according to claim 7, wherein among the types, a type having a higher click rate as the predetermined evaluation value is determined as a candidate of a type of advertisement content to be distributed.
  9. The determination unit is
    The generation apparatus according to claim 7, wherein among the types, an expected earnings value as the predetermined evaluation value is determined as a candidate of a type of advertisement content to which a higher type is distributed.
  10. The determination unit is
    It is characterized in that a type having the highest predetermined evaluation value and a type of the predetermined evaluation value within a predetermined range from the predetermined evaluation value of the type are determined as candidates for the type of advertisement content to be delivered. The production | generation apparatus of any one of Claims 7-9.
  11. A computer-implemented generation method,
    The control unit acquires user information on the user, stores the acquired user information in the user information storage unit, acquires distribution log information on the advertisement distributed to the user, and stores the acquired distribution log information on the distribution log information An acquisition process to be stored in the unit ;
    Wherein the control unit, the the user information the user information stored in the storage unit and based rather to said distribution log information distribution log information stored in the storage unit learning, predicting an evaluation value related to the type of data format of the advertisement information Generating a model to be
    A generation method characterized by including.
  12. The control unit acquires user information on the user, stores the acquired user information in the user information storage unit, acquires distribution log information on the advertisement distributed to the user, and stores the acquired distribution log information on the distribution log information Acquisition procedure to be stored in the
    Wherein the control unit, the the user information the user information stored in the storage unit and based rather to said distribution log information distribution log information stored in the storage unit learning, predicting an evaluation value related to the type of data format of the advertisement information Generation procedure for generating a model to be
    A generation program that causes a computer to execute.
  13. The advertisement content to be distributed to the user using the user information on the user stored in the user information storage unit and the model for predicting the evaluation value on the type in the data format of the advertisement information stored in the format information storage unit A determination unit that predicts a predicted evaluation value, which is a value used to determine the type, and determines the type of advertising content to be distributed to the user based on the predicted predicted evaluation value ;
    The determination apparatus characterized by having.
  14. A decision method that the computer executes,
    The control unit distributes to the user using user information on the user stored in the user information storage unit and a model for predicting an evaluation value on a type in a data format of the advertisement information stored on the format information storage unit A determination step of predicting a predicted evaluation value, which is a value used for determining the type of advertising content, and determining the type of advertising content to be delivered to the user based on the predicted predicted evaluation value ;
    A determination method comprising:
  15. The control unit distributes to the user using user information on the user stored in the user information storage unit and a model for predicting an evaluation value on a type in a data format of the advertisement information stored on the format information storage unit A determination procedure of predicting a predicted evaluation value, which is a value used for determining the type of advertising content, and determining the type of advertising content to be delivered to the user based on the predicted predicted evaluation value ;
    A decision program for causing a computer to execute.
JP2015176903A 2015-09-08 2015-09-08 Generation device, generation method, generation program, determination device, determination method, and determination program Active JP6541521B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2015176903A JP6541521B2 (en) 2015-09-08 2015-09-08 Generation device, generation method, generation program, determination device, determination method, and determination program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2015176903A JP6541521B2 (en) 2015-09-08 2015-09-08 Generation device, generation method, generation program, determination device, determination method, and determination program

Publications (2)

Publication Number Publication Date
JP2017054261A JP2017054261A (en) 2017-03-16
JP6541521B2 true JP6541521B2 (en) 2019-07-10

Family

ID=58320816

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2015176903A Active JP6541521B2 (en) 2015-09-08 2015-09-08 Generation device, generation method, generation program, determination device, determination method, and determination program

Country Status (1)

Country Link
JP (1) JP6541521B2 (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050251444A1 (en) * 2004-05-10 2005-11-10 Hal Varian Facilitating the serving of ads having different treatments and/or characteristics, such as text ads and image ads
US20080004954A1 (en) * 2006-06-30 2008-01-03 Microsoft Corporation Methods and architecture for performing client-side directed marketing with caching and local analytics for enhanced privacy and minimal disruption
US7806329B2 (en) * 2006-10-17 2010-10-05 Google Inc. Targeted video advertising
US20130346182A1 (en) * 2012-06-20 2013-12-26 Yahoo! Inc. Multimedia features for click prediction of new advertisements
JP6101577B2 (en) * 2013-06-19 2017-03-22 ヤフー株式会社 Advertisement generation apparatus, advertisement generation method, and advertisement generation program

Also Published As

Publication number Publication date
JP2017054261A (en) 2017-03-16

Similar Documents

Publication Publication Date Title
AU2010224228B2 (en) Generating user profiles
US8620718B2 (en) Industry specific brand benchmarking system based on social media strength of a brand
US10445840B2 (en) System and method for positioning sponsored content in a social network interface
JP5662446B2 (en) A learning system for using competitive evaluation models for real-time advertising bidding
US20160364767A1 (en) Method and system for influencing auction based advertising opportunities based on user characteristics
US8700543B2 (en) Web page analysis system for computerized derivation of webpage audience characteristics
US20130066711A1 (en) Understanding Effects of a Communication Propagated Through a Social Networking System
KR101947628B1 (en) Assisted adjustment of an advertising campaign
US20100088321A1 (en) Method and a system for advertising
US20140108130A1 (en) Calculating audience metrics for online campaigns
US20120059713A1 (en) Matching Advertisers and Users Based on Their Respective Intents
US20110010243A1 (en) User control of advertising content
US8458160B2 (en) Social network based user-initiated review and purchase related information and advertising
US20110208585A1 (en) Systems and Methods for Measurement of Engagement
EP2821950A1 (en) Quality scoring system for advertisements and content in an online system
EP2590128A1 (en) Information processing device, information processing method, information processing program, and recording medium in which information processing program is recorded
JP6117452B1 (en) System and method for optimizing content layout using behavioral metric
US20100228558A1 (en) Aggregate Content-Based Advertising
US20130226711A1 (en) Monetizing images in publishing networks
US20140032306A1 (en) System and method for real-time search re-targeting
US9183259B1 (en) Selecting content based on social significance
Datta et al. The challenge of retaining customers acquired with free trials
KR20120050593A (en) System and method for providing recommendation business keyword
US20080288347A1 (en) Advertising keyword selection based on real-time data
AU2013289036B2 (en) Modifying targeting criteria for an advertising campaign based on advertising campaign budget

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20180312

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20190215

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20190305

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20190426

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20190514

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20190611

R150 Certificate of patent or registration of utility model

Ref document number: 6541521

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

S533 Written request for registration of change of name

Free format text: JAPANESE INTERMEDIATE CODE: R313533