JP5289423B2 - Advertisement distribution destination extraction apparatus and method - Google Patents

Advertisement distribution destination extraction apparatus and method Download PDF

Info

Publication number
JP5289423B2
JP5289423B2 JP2010277369A JP2010277369A JP5289423B2 JP 5289423 B2 JP5289423 B2 JP 5289423B2 JP 2010277369 A JP2010277369 A JP 2010277369A JP 2010277369 A JP2010277369 A JP 2010277369A JP 5289423 B2 JP5289423 B2 JP 5289423B2
Authority
JP
Japan
Prior art keywords
advertisement
user terminal
number
candidate
action history
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
JP2010277369A
Other languages
Japanese (ja)
Other versions
JP2012128526A (en
Inventor
勉 真田
耕平 津留崎
俊介 河波
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 JP2010277369A priority Critical patent/JP5289423B2/en
Publication of JP2012128526A publication Critical patent/JP2012128526A/en
Application granted granted Critical
Publication of JP5289423B2 publication Critical patent/JP5289423B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to an advertisement distribution destination extracting apparatus and method for extracting an advertisement distribution destination.

  In recent years, behavioral targeting advertising has been performed as a form of advertising (see, for example, Patent Document 1). The behavioral targeting advertisement distributes advertisements based on the category to which the user belongs and the past behavior history of the user (browsing page, search input, advertisement browsing, advertisement click log, etc.). The provider may be guaranteed the number of times the user browses the advertisement within a predetermined period.

JP 2009-223423 A

  However, the number of distribution destinations extracted from users belonging to the category designated as the distribution destination may differ from the number of browsing times guaranteed by the administrator to the advertisement provider. In this case, the administrator must adjust the number of advertisements distributed within a predetermined period.

  An object of the present invention is to provide an advertisement distribution destination extraction apparatus and method capable of adjusting the number of advertisement distributions distributed within a predetermined period.

  The present invention provides the following solutions.

  (1) An advertisement distribution destination extraction device that extracts an advertisement distribution destination based on an action history for each user terminal, and for each user terminal, the user terminal belongs to an action history for an advertisement distributed to the user terminal. Action history storage means that is stored in association with a category having a hierarchical structure, and actions of user terminals belonging to a specified category designated as an advertisement distribution destination among action histories stored in the action history storage means Candidate extraction means for referring to the history and extracting user terminals having a predetermined action history as advertisement distribution destination candidates, and the required distribution in which the number of candidates extracted by the candidate extraction means needs to be distributed within a predetermined period If the number is smaller than the number, the behavior history of the user terminal belonging to a category higher in the hierarchy of the designated category is referred to and the predetermined behavior history is present. Additional candidate extracting means for further extracting the user terminal as a candidate for the advertisement distribution destination, and processing by the additional candidate extracting means, the number of candidates extracted by the candidate extracting means is extracted by the additional candidate extracting means An advertisement distribution destination extraction apparatus comprising: a repeating unit that repeatedly executes the number of candidates added until the required number of distributions is reached.

  According to the invention described in (1), the behavior history storage means, for each user terminal, displays the behavior history for the advertisement distributed to the user terminal as a category to which the user terminal belongs and having a hierarchical structure. The candidate extraction means refers to the action history of the user terminal belonging to the designated category designated as the advertisement distribution destination among the action histories stored in the action history storage means, and has a predetermined action history. The terminal is extracted as a candidate for the advertisement distribution destination. Further, the additional candidate extraction unit is configured to detect the user terminals belonging to the category higher in the hierarchy of the designated category when the number of candidates extracted by the candidate extraction unit is smaller than the required number of distributions that need to be distributed within a predetermined period. With reference to the action history, user terminals having the predetermined action history are further extracted as advertisement distribution destination candidates. Then, the repeating unit repeatedly executes the processing by the additional candidate extracting unit until the number of candidates extracted by the candidate extracting unit plus the number of candidates extracted by the additional candidate extracting unit reaches the required number of distributions. To do. By doing in this way, when the number of required distributions required to be delivered within a predetermined period is smaller, the advertisement distribution destination capable of adjusting the number of advertisement distributions delivered within the predetermined period until the required number of distributions is reached An extraction device can be provided.

  (2) The advertisement distribution destination extraction device according to (1), wherein when the number of candidates extracted by the candidate extraction unit is larger than the required number of distributions, a category in a lower hierarchy of the specified category hierarchy Reference is made to the action history of the user terminal to which the user terminal belongs, and a candidate narrowing means for narrowing down the advertisement delivery destination candidates by making the user terminal having the predetermined action history a candidate for the advertisement delivery destination, the repeating means includes the An advertisement distribution destination extraction device that repeatedly executes the processing by the candidate narrowing means until the number of candidates narrowed down by the candidate narrowing means is narrowed down to the required number of distributions.

  According to the invention described in (2), the number of advertisement distributions distributed within a predetermined period is adjusted until the required number of distributions is reached even when the number is greater than the number of necessary distributions required for distribution within a predetermined period. It is possible to provide an advertisement distribution destination extraction device that can handle this.

  (3) The advertisement distribution destination extracting device according to (1) or (2), wherein the advertisement distribution period is determined in response to reception of designation of an advertisement distribution period for distributing the advertisement from an administrator's terminal. The advertisement distribution period storage means for storing the advertisement in association with the advertisement identification information for identifying the advertisement and the passage of the advertisement distribution period stored for each advertisement by the advertisement distribution period storage means in association with the advertisement identification information. Accordingly, the action history of each user terminal stored in the action history storage means is read and the action history of the advertisement distribution within the elapsed period is read and subtracted from the number necessary for the distribution as the advertisement distribution result. An advertisement distribution destination extraction device comprising: a result recalculation unit that recalculates the number of advertisement distributions required during the period and extracts the advertisement distribution destination candidates.

  According to the invention described in (3), it is possible to provide an advertisement distribution destination extraction device capable of adjusting the number of advertisement distributions to be distributed within a predetermined period in the middle of an advertisement distribution period.

  (4) The advertisement distribution destination extracting apparatus according to (3), further including a frequency adjusting unit that executes the process by the result recalculating unit more frequently as the advertisement distribution period elapses. Extraction device.

  According to the invention described in (4), it is possible to provide an advertisement distribution destination extraction device capable of adjusting the number of advertisement distributions to be distributed within a predetermined period in the middle of an advertisement distribution period.

  (5) A method in which a computer including a control unit and a storage unit extracts an advertisement distribution destination based on an action history for each user terminal, and the control unit distributes an advertisement distributed to the user terminal for each user terminal. Action history storage step of storing the action history for the user in the category to which the user terminal belongs and having a hierarchical structure in the storage unit, and the action history stored in the storage unit in the action history storage step Among these, a candidate extraction step for extracting a user terminal having a predetermined behavior history as a candidate for an advertisement distribution destination with reference to an action history of a user terminal belonging to a designated category designated as an advertisement distribution destination, and extraction by the candidate extraction step If the number of selected candidates is less than the required number of distributions that need to be distributed within a predetermined period, it belongs to the category of the upper hierarchy of the specified category hierarchy A candidate extracted from the candidate extraction step by adding an additional candidate extracting step of referring to an action history of the user terminal and further extracting a user terminal having the predetermined behavior history as an advertisement delivery destination candidate And repeating the step of repeatedly executing the number of candidates extracted in the additional candidate extracting step until the required number of distributions is reached.

  According to the method described in (5), the same effect as in (1) can be expected by implementing the invention according to the method.

  ADVANTAGE OF THE INVENTION According to this invention, the advertisement delivery destination extraction apparatus which can adjust the delivery number of the advertisement delivered within a predetermined period, and its method can be provided.

It is a figure which shows the whole structure for demonstrating the advertisement delivery destination extraction apparatus 1 which concerns on embodiment of this invention. It is a figure which shows the attribute database 21 which concerns on embodiment of this invention. It is a figure which shows the action history database 22 which concerns on embodiment of this invention. It is a figure which shows the advertisement database 23 which concerns on embodiment of this invention. It is a flowchart of the advertisement delivery destination extraction apparatus 1 which concerns on embodiment of this invention.

[overall structure]
Embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram illustrating an overall configuration for explaining an advertisement distribution destination extraction device 1 according to the present embodiment. The advertisement distribution destination extraction device 1 is connected to the user terminal 2 and the administrator terminal 3 via a network, and includes a control unit 10 and a storage unit 20.

  The control unit 10 is a part that comprehensively controls each function related to the advertisement distribution destination extraction device 1. For each user terminal 2, the user terminal 2 belongs to the action history for the advertisement distributed to the user terminal 2. An action history storage unit 11 is provided that stores a category in association with a category having a hierarchical structure. The storage unit 20 includes an attribute database 21 and an action history database 22. The category to which the user terminal 2 belongs is stored in the attribute database 21, and the action history in the user terminal 2 is stored in the action history database 22. The action history storage unit 11 and the action history database 22 function as action history storage means.

The attribute database 21 is illustrated in FIG. The attribute database 21 includes a “terminal ID” field for specifying the user terminal 2 connected to the advertisement distribution destination extracting device 1 via the network, and an “attribute” field indicating an attribute of the user who uses the user terminal 2. And have. In the “attribute” field, a plurality of hierarchies are provided, and user attributes are specified by categories having a hierarchical structure.
For a user who uses the user terminal 2 with the terminal ID “1”, the address is Tokyo 23 wards, the age is in his 30s, the gender is male, and the interested advertising field is 40 million yen level. The case of a 2000cc white new car minivan or the like will be described. In this case, “1” is stored in the “terminal ID” field. In the “attribute” field, as an address, “East Japan” indicating a rough region is stored in the “first hierarchy” field, and the “second hierarchy” field is a Kanto region in the eastern Japan. “Kanto” is stored, the “third layer” field stores “South Kanto” indicating the southern Kanto region in the Kanto region, and the “fourth layer” field stores south. “Tokyo” indicating that it is Tokyo in the Kanto region is stored, and “23 wards” indicating that it is 23 wards in Tokyo are stored in the “fifth hierarchy” field. As the age, “adult” indicating an adult is stored in the “first hierarchy” field, and “30s” indicating that the adult is in his 30s in the “second hierarchy” field. Is memorized. In addition, as a gender, “male” indicating a male is stored in the “first hierarchy” field. In addition, regarding the fact that the advertising field of interest is a newly built apartment of 40 million yen level, “real estate” indicating that it is a real estate advertisement is stored in the “first tier” field, and “second tier” field is stored. Stores “owned house” indicating that it is an advertisement of a house in a real estate advertisement, and stores “condominium” indicating that it is an advertisement of a condominium in the advertisement of a house in the “third layer” field. In the “fourth hierarchy” field, “new construction” indicating that it is an advertisement for a new apartment building in the apartment advertisement is stored. In the “fifth hierarchy” field, 4000 in the advertisement for a new apartment building is stored. “40 million yen” indicating that it is an advertisement for a newly built apartment of 10 million yen is stored. In addition, regarding the advertising field of interest being a 2000cc white new car minivan, the “first layer” field stores “car” indicating that it is an automobile advertisement, and the “second layer” field stores “New car” indicating that it is an advertisement for a new car in an automobile advertisement is stored, and “Minivan” indicating that it is an advertisement for a minivan in an advertisement for a new car is stored in the “third hierarchy” field. In the “fourth layer” field, “2000cc” indicating that the advertisement is a 2000 cc minivan in the minivan advertisement is stored, and in the “fifth layer” field, the 2000 cc minivan advertisement is stored. “White” indicating that the advertisement is a white minivan is stored.

The action history database 22 is illustrated in FIG. The action history database 22 includes a “terminal ID” field for identifying the distributed user terminal 2, a “distribution time” field indicating the time when the advertisement is distributed to the user terminal 2, and an advertisement clicked on the user terminal 2. The “action history (distributed advertisement ID)” field for specifying the URL and the “category” field indicating the category related to the advertisement.
For example, a real estate advertisement corresponding to the advertisement code (advertisement identification number) “AD-CX001” is distributed to the user terminal 2 with the terminal ID “1” at 13:44 on November 25, and clicked by the user terminal 2. In this case, “1” is stored in the “terminal ID” field, “11/25 13:44” is stored in the “delivery time” field, and “AD” is stored in the “behavior history (distribution advertisement ID)” field. -CX001 "is stored, and" real estate advertisement "is stored in the" category "field.

  Returning to FIG. 1, the control unit 10 includes an advertisement distribution condition storage unit 12 that stores conditions for distributing advertisements designated by the administrator terminal 3. The storage unit 20 includes an advertisement database 23, and the conditions are stored in the advertisement database 23. The advertisement distribution condition storage unit 12 and the advertisement database 23 function as an advertisement distribution condition storage unit.

The advertisement database 23 is illustrated in FIG. The advertisement database 23 has an “advertising code (advertising identification information)” field indicating an advertising code (advertising identification information), a “content” field indicating the contents of the advertisement, and a category designated as a distribution destination of the advertisement. "Specified category" field, "Contract period" field indicating the contract period with the advertisement provider, and "Required distribution number" indicating that the number of distributions guaranteed by the administrator to the advertisement provider within this contract period A field, a “guaranteed number” field that indicates the number of times the administrator has guaranteed the advertisement provider within the contract period, a “review period” field that is provided to review the distribution target, And a “target number” field indicating a target number of browsing times within the review period. The “specified category” field is the target of the “address” field indicating the address of the person to be distributed, the “age” field indicating the age of the person, the “gender” field indicating the gender of the person, and the like. It includes a “browsing frequency” field indicating the browsing frequency of advertisements.
For example, with regard to the advertisement of advertisement code (advertising identification information) “AD-CX101” related to the advertisement of real estate in Tokyo's 23 wards, a real estate advertisement is made once in the past month by a male in his 30s living in Tokyo's 23 wards. A case will be described in which the person who clicked above is provisionally distributed. The contract period with the advertisement provider is from November 1 to December 31, and the number of distributions guaranteed by the administrator to the advertisement provider during that period is 30,000 times. The number of browsing guaranteed to 20,000 is 20,000, the review period provisionally set by the administrator is from November 1 to November 25, and the target number of browsing within that period is 8 In the case of 1,000 times, “AD-CX101” is first stored in the “advertising code (advertisement identification information)” field, and “real estate” is stored in the “content” field. In the “designated category” field, “Tokyo 23 wards” is stored in the “address” field, “30s” is stored in the “age” field, and “male” is stored in the “gender” field. "Is stored, and" at least once a month "is stored in the" browsing frequency "field. In addition, “11/1 to 12/31” is stored in the “contract period” field, “30,000” is stored in the “necessary delivery number” field, and “20,000” is stored in the “guarantee count” field. Is stored, “11/1 to 11/25” is stored in the “review period” field, and “8,000” is stored in the “target number” field.

  Returning to FIG. 1, the control unit 10 refers to the action history of the user terminal 2 belonging to the designated category designated as the advertisement distribution destination among the action histories stored in the action history database 22, and has a predetermined action history. A candidate extraction unit 13 that extracts the user terminal 2 as a candidate for an advertisement distribution destination is provided. The candidate extraction unit 13 functions as a candidate extraction unit.

  The case where an advertisement corresponding to the advertisement code (advertisement identification information) “AD-CX101” in FIG. 4 is distributed will be described as an example. The content of the advertisement is a real estate advertisement, and the designated category is “Tokyo 23 wards / 30's / male / at least once a month”. Therefore, the candidate extraction unit 13 has an action history of the user terminal 2 whose address is “23 wards” among the attributes stored in the attribute database 21, whose age is “30s”, and whose gender is “male”. Refer to Taking the attribute database 21 of FIG. 2 as an example, the candidate extraction unit 13 refers to the action history of the user terminal 2 whose terminal IDs are “1”, “3”, and “5”. Then, the candidate extraction unit 13 refers to the behavior history of these user terminals 2 and extracts the user terminal 2 that has clicked on the real estate advertisement at least once within the past month as an advertisement distribution destination candidate. Taking the behavior history database 22 of FIG. 3 as an example, among the user terminals 2 with terminal IDs “1”, “3”, and “5”, the user terminal that has clicked on a real estate advertisement one or more times within the past month , The user terminal 2 whose terminal IDs are “1” and “3”. Therefore, the candidate extraction unit 13 extracts the user terminals 2 whose terminal IDs are “1” and “3” as advertisement distribution destination candidates.

The “predetermined action history” is sufficient if it is the user terminal 2 having an action history that matches the specified category, but it is preferable to perform weighting according to the newness of the distribution time. For example, only the user terminal 2 having an action history that matches a specified category within a certain period (for example, 28 days) may be extracted as an advertisement distribution destination candidate, and the contribution rate to the number of occurrences of the action history α n-1 (α is an arbitrary constant satisfying 0 <α <1, and n indicates that the distribution time is n days before the extraction time by the candidate extraction unit 13), and obtained there Only the user terminals 2 whose numerical values exceed a certain threshold may be extracted as advertisement distribution destination candidates.

  In addition, when the number of candidates extracted by the candidate extraction unit 13 is smaller than the necessary number of distributions that need to be distributed within a predetermined period, the control unit 10 can also manage the user terminals 2 that belong to a category higher in the hierarchy of the designated category. The additional candidate extracting unit 14 is further provided for further extracting the user terminal 2 having a predetermined behavior history as a candidate for the advertisement distribution destination. The additional candidate extraction unit 14 functions as additional candidate extraction means.

  In the case of distributing the above advertisement, that is, the advertisement corresponding to the advertisement code (advertisement identification information) “AD-CX101” of FIG. 4, the number of candidates extracted by the candidate extraction unit 13 was 15,321. A case will be described as an example. The number of candidates extracted by the candidate extraction unit 13 is 15,321, which is less than the required number of distributions 30,000 that are required to be distributed from November 1 to December 31 as the contract period. . Therefore, the additional candidate extraction unit 14 refers to the action history of the user terminal 2 belonging to the category of the fourth hierarchy “Tokyo” corresponding to the upper hierarchy of the fifth hierarchy “23 wards” that is the designated category, and performs a predetermined action history. Are further extracted as advertisement distribution destination candidates. Since the designated hierarchy has shifted from the fifth hierarchy to the fourth hierarchy, not only those who live in Tokyo's 23 wards but also those who live in Tokyo. Therefore, the additional candidate extraction unit 14 has the action history of the user terminal 2 having the address “Tokyo”, the age “30”, and the gender “male” among the attributes stored in the attribute database 21. Refer to Taking the attribute database 21 of FIG. 2 as an example, the additional candidate extracting unit 14 has already selected the candidate extracting unit 13 among the user terminals 2 whose terminal IDs are “1”, “3”, “4”, and “5”. The action history of the user terminal 2 excluding the user terminal 2 that has executed the process, that is, the user terminal 2 whose terminal IDs are “1”, “3”, and “5” is referred to. Then, the additional candidate extraction unit 14 refers to the action history of the user terminal 2, that is, the user terminal 2 whose terminal ID is “4”, and selects the user terminal 2 that clicked the real estate advertisement at least once within the past month. Extracted as candidates for advertisement distribution destinations. Taking the behavior history database 22 of FIG. 3 as an example, the user terminal 2 whose terminal ID is “4” corresponds to the user terminal 2 who clicked on a real estate advertisement at least once within the past month. Therefore, the additional candidate extraction unit 14 further extracts the user terminal 2 having the terminal ID “4” as an advertisement distribution destination candidate.

  In addition, when the number of candidates extracted by the candidate extraction unit 13 is larger than the above-described required number of distributions, the control unit 10 refers to the action history of the user terminal 2 belonging to the category in the lower hierarchy of the specified category hierarchy. And a candidate narrowing-down unit 15 that narrows down advertisement distribution destination candidates by making the user terminal 2 having a predetermined action history a candidate for the advertisement distribution destination. The candidate narrowing unit 15 functions as candidate narrowing means.

  In the case of distributing the above advertisement, that is, the advertisement corresponding to the advertisement code (advertisement identification information) “AD-CX102” in FIG. 4, the number of candidates extracted by the candidate extraction unit 13 was 87,925. A case will be described as an example. The number of candidates extracted by the candidate extraction unit 13 is 87,925, which is larger than the necessary number of distributions required for distribution from November 20th to December 19th, which is the contract period, 70,000. . Therefore, the candidate narrowing unit 15 refers to the action history of the user terminal 2 belonging to the category of the second hierarchy “20's” corresponding to the lower hierarchy of the first hierarchy “adult” that is the designated category, and the predetermined action history The advertisement distribution destination candidates are narrowed down by making the user terminal 2 having the advertisement distribution destination candidates. Since the designated hierarchy has shifted from the first hierarchy to the second hierarchy, only users in their 20s are targeted. Therefore, the candidate narrowing-down part 15 refers to the action history of the user terminal 2 used by the user whose age is in his 20s among the attributes stored in the attribute database 21. Taking the attribute database 21 of FIG. 2 as an example, the candidate narrowing-down unit 15 originally referred to the action history of the user terminal 2 with the terminal IDs “2” and “6”. ”And refer to the action history. Then, the candidate narrowing unit 15 refers to the action history of the user terminal 2 whose terminal ID is “2”, and sets the user terminal 2 that clicked the cosmetic advertisement three or more times within the past week as the advertisement distribution destination candidate. To narrow down the ad delivery destination candidates. Taking the behavior history database 22 of FIG. 3 as an example, the user terminal 2 whose terminal ID is “2” has clicked on a cosmetic advertisement three or more times within the past week. For this reason, the candidate narrowing unit 15 narrows down advertisement distribution destination candidates by setting the user terminal 2 having the terminal ID “2” as the advertisement distribution destination candidate.

  Further, the control unit 10 includes a repeating unit 16. The repeating unit 16 functions as a repeating unit. The repetition unit 16 performs the processing by the additional candidate extraction unit 14 until the number of candidates extracted by the candidate extraction unit 13 plus the number of candidates extracted by the additional candidate extraction unit 14 reaches the required number of distributions. Run repeatedly. On the other hand, the repetition unit 16 repeatedly executes the processing by the candidate narrowing unit 15 until the number of candidates narrowed down by the candidate narrowing unit 15 is narrowed down to the required number of distributions.

  In the middle of the contract period, the control unit 10 stores the advertisement database 23 in association with the advertisement code (advertisement identification information) for each advertisement so that the number of advertisement distributions distributed within the contract period can be adjusted again. In accordance with the progress of the review period, out of the action history for each user terminal 2 stored in the action history database 22, the action history within the elapsed period is read out and deducted from the number that needs to be distributed as the advertisement distribution result. Therefore, it is preferable to include a performance recalculation unit 17 that recalculates the number of advertisements that need to be distributed in a period that has not yet elapsed, and extracts advertisement distribution destination candidates. The result recalculation unit 17 functions as a result recalculation means.

  Moreover, if it is the advertisement delivery destination extraction apparatus 1 provided with the results recalculation part 17, the frequency adjustment part 18 which performs the process by the results recalculation part 17 more frequently according to progress of a contract period may be provided. preferable. The frequency adjusting unit 18 functions as a frequency adjusting unit. In the case where an advertisement corresponding to the advertisement code (advertisement identification information) “AD-CX101” in FIG. 4 is distributed as an example, the frequency adjustment unit 18 is provided to review the advertisement database 23 according to the progress of the contract period. The period is shortened. In other words, the review period was initially 25 days from November 1st to 25th, but the next was 15 days from November 26th to December 10th, followed by 10th of December 11th to 20th. The day can be a review period. As a result, it is possible to frequently adjust the number of advertisements distributed within the contract period as the contract period approaches expiration.

[Hardware and Software Configuration of this Embodiment]
The hardware and software configurations of this embodiment will be described. The hardware of the advertisement distribution destination extraction device 1 includes a CPU as a control device (control unit), a storage device (storage unit), a communication device (communication unit), a display device (display unit), and an input device (input unit). ) Is included. Examples of the storage device (storage unit) include a memory (RAM, ROM, etc.), a hard disk drive (HDD), an optical disk (CD, DVD, etc.) drive, and the like. Examples of the communication device (communication unit) include various wired or wireless interface devices. Examples of the display device (display unit) include various displays such as a liquid crystal display or a plasma display. Examples of the input device (input unit) include a keyboard, a pointing device (such as a mouse), a remote control device, and the like.

  The software of the advertisement distribution destination extracting device 1 includes a program and data for controlling the hardware. Programs and data are stored in a storage device (storage unit), and are appropriately executed and referenced by a control device (control unit). Further, the computer program and data can be distributed by an electromagnetic method, or can be recorded and distributed on a computer-readable medium such as a CD-ROM.

[flowchart]
FIG. 5 is a flowchart of the advertisement distribution destination extraction device 1 according to the present embodiment.

  First, the action history storage unit 11 executes an action history storage process (S1). In this process, the action history storage unit 11 associates, for each user terminal 2, the click action history for the advertisement distributed to the user terminal 2 with the category to which the user terminal 2 belongs and having a hierarchical structure. The process to memorize is executed.

  Next, the advertisement distribution condition storage unit 12 executes an advertisement distribution condition storage process (S2). In this process, the advertisement distribution condition storage unit 12 executes a process of storing, in the advertisement database 23, the condition for distributing the advertisement specified by the administrator terminal 3.

  Next, the candidate extraction unit 13 executes candidate extraction processing (S3). In this process, the candidate extraction unit 13 refers to the action history of the user terminal 2 belonging to the designated category designated as the advertisement distribution destination among the action histories stored in the action history database 22 and has a predetermined action history. A process of extracting the user terminal 2 as an advertisement distribution destination candidate is executed.

  Next, the additional candidate extraction unit 14 determines whether or not the number of candidates extracted by the candidate extraction unit 13 is smaller than the required number of distributions that need to be distributed within the contract period (S4). When this determination is YES, the additional candidate extraction unit 14 moves the process to step S5, and when this determination is NO, the additional candidate extraction unit 14 moves the process to step S6.

  Next, the additional candidate extraction unit 14 performs an additional candidate extraction process (S5). In this process, the additional candidate extraction unit 14 refers to the action history of the user terminal 2 belonging to the category of the upper hierarchy of the designated category hierarchy, and further extracts the user terminal 2 having a predetermined action history as an advertisement distribution destination candidate. Execute the process. When the additional candidate extraction process is completed, the additional candidate extraction unit 14 moves the process to step S8.

  Next, the candidate narrowing-down unit 15 determines whether or not the number of candidates extracted by the candidate extracting unit 13 is larger than the necessary number of distributions (S6). If this determination is YES, the candidate narrowing unit 15 moves the process to step S7, and if this determination is NO, the candidate narrowing unit 15 ends the series of processes.

  Next, the candidate narrowing down part 15 performs a candidate narrowing-down process (S7). In this process, the candidate narrowing-down unit 15 refers to the action history of the user terminal 2 belonging to the lower-level category of the specified category hierarchy, and makes the user terminal 2 having the predetermined action history a candidate for the advertisement distribution destination. Execute the process of narrowing down advertisement distribution destination candidates.

  Next, the repeating unit 16 performs a repetition process (S8). When the process proceeds from the process of step S5 to the process of step S8, the repetition unit 16 extracts the process by the additional candidate extraction unit 14 to the number of candidates extracted by the candidate extraction unit 13 by the additional candidate extraction unit 14. Repeat until the number of candidates reaches the required number of distributions. On the other hand, when the process proceeds from the process of step S7 to the process of step S8, the repetition unit 16 performs the process by the candidate narrowing unit 15 until the number of candidates narrowed down by the candidate narrowing unit 15 is narrowed down to the required number of distributions. Run repeatedly. When this process ends, the control unit 10 ends the series of processes.

  When the advertisement distribution destination extraction device 1 includes the performance recalculation unit 17, the performance recalculation unit 17 records the results according to the progress of the review period stored in the advertisement database 23 in association with the advertisement code (advertisement identification information). Perform recalculation processing. In the results recalculation process, the results recalculation unit 17 reads out the behavior histories within the elapsed period from the behavior histories for each user terminal 2 stored in the behavior history database 22, and the number required to be distributed as the advertisement distribution results. By subtracting from the above, the number of advertisements that need to be distributed in a period that has not elapsed is recalculated, and a process of extracting advertisement distribution destination candidates is executed. When the advertisement distribution destination extraction device 1 includes the performance recalculation unit 17 and the frequency adjustment unit 18, the frequency adjustment unit 18 performs a frequency adjustment process. In this process, the frequency adjustment unit 18 executes the process by the result recalculation unit 17 at a higher frequency in accordance with the progress of the contract period.

  According to the advertisement distribution destination extraction device 1 described in the present embodiment, the behavior history storage unit 11 displays, for each user terminal 2, the behavior history for the advertisement distributed to the user terminal 2 in the category to which the user terminal 2 belongs. The candidate extraction unit 13 stores the action history of the user terminal 2 belonging to the designated category designated as the advertisement distribution destination among the action histories stored in the action history database 22. The user terminal having a predetermined action history is extracted as a candidate for the advertisement distribution destination. Further, the additional candidate extraction unit 14 is a user who belongs to a category in a higher hierarchy of the designated category when the number of candidates extracted by the candidate extraction unit 13 is smaller than the required number of distributions that need to be distributed within a predetermined period. The user terminal having the predetermined action history is further extracted as an advertisement distribution destination candidate by referring to the action history of the terminal 2. Then, the repetition unit 16 adds the number of candidates extracted by the additional candidate extraction unit 14 to the number of candidates extracted by the candidate extraction unit 13 by adding the number of candidates extracted by the candidate extraction unit 13 to the required number of distributions. Repeat until it reaches. By doing in this way, when the number of required distributions required to be delivered within a predetermined period is smaller, the advertisement distribution destination capable of adjusting the number of advertisement distributions delivered within the predetermined period until the required number of distributions is reached The extraction device 1 can be provided.

  Further, in addition to the above configuration, the advertisement distribution destination extraction device 1 has a user terminal 2 belonging to a category in a lower hierarchy of the hierarchy of the designated category when the number of candidates extracted by the candidate extraction unit 13 is larger than the required distribution number. , The candidate narrowing unit 15 for narrowing down the advertisement distribution destination candidates by making the user terminal 2 having the predetermined behavior history a candidate for the advertisement distribution destination, and the repetition unit 16 The processing by the unit 15 is repeatedly executed until the number of candidates narrowed down by the candidate narrowing unit 15 is narrowed down to the required number of distributions. By doing in this way, even when the number of required distributions required for distribution within a predetermined period is larger, the number of advertisement distributions distributed within the predetermined period can be adjusted until the required number of distributions is reached. The advertisement distribution destination extraction device 1 can be provided.

  Further, the advertisement distribution destination extracting device 1 reads out the action history within the elapsed period from the action history for each user terminal 2 stored in the action history database 22 and distributes it as the advertisement distribution result according to the progress of the review period. Is preferably subtracted from the required number to recalculate the number of advertisements that need to be distributed in the period that has not yet elapsed, and includes a performance recalculation unit 17 that extracts advertisement distribution destination candidates. It is even more preferable to provide a frequency adjusting unit 18 that executes the process by the actual result recalculating unit 17 at a higher frequency as time passes. In this way, it is possible to provide the advertisement distribution destination extraction device 1 that can adjust the number of advertisement distributions to be distributed within a predetermined period in the middle of the period for distributing advertisements.

  The effects described in the present embodiment are only the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the present embodiment. Absent.

DESCRIPTION OF SYMBOLS 1 Advertisement delivery destination extraction apparatus 2 User terminal 3 Administrator terminal 10 Control part 11 Action history memory | storage part 12 Advertisement delivery condition delivery part 13 Candidate extraction part 14 Additional candidate extraction part 16 Repeat part 20 Storage part 21 Attribute database 22 Advertisement history database 23 Advertising database

Claims (4)

  1. An advertisement distribution destination extraction device that extracts an advertisement distribution destination based on an action history for each user terminal,
    Action history storage means for storing an action history for an advertisement distributed to the user terminal for each user terminal in association with a category to which the user terminal belongs and having a hierarchical structure;
    For each advertisement provided by the advertisement provider, the behavior history stored in the behavior history storage means is referred to the behavior history of the user terminal belonging to the designated category designated as the advertisement distribution destination, and the predetermined behavior history is obtained. Candidate extraction means for extracting a user terminal having a candidate for an advertisement distribution destination as a target for distributing the advertisement;
    When the number of candidates extracted by the candidate extraction means is less than the required number of distributions that need to be distributed within a predetermined period, refer to the action history of the user terminal belonging to the category of the upper hierarchy of the specified category hierarchy, an additional candidate extracting means further extracts for each of the advertisement user terminals having the predetermined action history as a candidate of the Placement,
    The process by the addition candidate extracting means, the number of candidates extracted by the candidate extracting means, repeatedly performing up plus the number of candidate extracted by the addition candidate extracting unit reaches the number of the required distribution An advertisement distribution destination extraction apparatus comprising: a repeating unit that extracts, for each advertisement, the number of advertisement distribution destination candidates that has reached the required distribution number .
  2. The advertisement distribution destination extraction device according to claim 1,
    An advertisement delivery period storage means for storing the advertisement delivery period in association with the advertisement identification information for identifying the advertisement in response to the designation of the advertisement delivery period for delivering the advertisement from the administrator's terminal;
    For each advertisement, in accordance with the passage of the advertisement delivery period stored in association with the advertisement identification information by the advertisement delivery period storage means, the action history for each user terminal stored by the action history storage means has elapsed. By reading out the action history of advertisement distribution within the period and subtracting it as the advertisement distribution result from the number necessary for distribution, the number necessary for distribution of the advertisement in the period not yet elapsed is recalculated, and the candidate of the advertisement distribution destination An advertisement distribution destination extracting device comprising a result recalculation means for extracting the results.
  3. The advertisement distribution destination extraction device according to claim 2,
    An advertisement distribution destination extracting device comprising frequency adjusting means for executing processing by the result recalculating means at a higher frequency as the advertisement distribution period elapses.
  4. A computer including a control unit and a storage unit is a method for extracting an advertisement distribution destination based on an action history for each user terminal,
    The controller is
    For each user terminal, an action history storage step of storing an action history for an advertisement distributed to the user terminal in the storage unit in association with a category to which the user terminal belongs and having a hierarchical structure;
    For each advertisement provided by the advertisement provider, the action history stored in the storage unit in the action history storage step is referred to the action history of the user terminal belonging to the specified category designated as the advertisement distribution destination, and predetermined A candidate extraction step of extracting a user terminal having an action history as a candidate of an advertisement distribution destination which is a target for distributing the advertisement;
    When the number of candidates extracted in the candidate extraction step is less than the required number of distributions that need to be distributed within a predetermined period, refer to the action history of the user terminal belonging to the category of the upper hierarchy of the specified category hierarchy, the additional candidate extracting step further extracts the user terminal having a predetermined action history for each of the advertisement candidates of the advertisement delivery destination,
    The additional candidate extraction process, that plus the number of candidate extracted by the addition candidate extraction step the number of candidate extracted by the candidate extraction process is repeated until reaching the number of the required distribution, the necessary delivery And a repeating step of extracting, for each advertisement, the number of advertisement delivery destination candidates that has reached the number .
JP2010277369A 2010-12-13 2010-12-13 Advertisement distribution destination extraction apparatus and method Active JP5289423B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2010277369A JP5289423B2 (en) 2010-12-13 2010-12-13 Advertisement distribution destination extraction apparatus and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2010277369A JP5289423B2 (en) 2010-12-13 2010-12-13 Advertisement distribution destination extraction apparatus and method

Publications (2)

Publication Number Publication Date
JP2012128526A JP2012128526A (en) 2012-07-05
JP5289423B2 true JP5289423B2 (en) 2013-09-11

Family

ID=46645502

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2010277369A Active JP5289423B2 (en) 2010-12-13 2010-12-13 Advertisement distribution destination extraction apparatus and method

Country Status (1)

Country Link
JP (1) JP5289423B2 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5235251B1 (en) * 2012-09-28 2013-07-10 楽天株式会社 Information processing apparatus, information processing method, and information processing program

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000122949A (en) * 1998-10-12 2000-04-28 Hitachi Ltd Content managing method
JP3825597B2 (en) * 1999-11-18 2006-09-27 日本電信電話株式会社 Content Impressions control method, apparatus and program storage medium
JP2001266257A (en) * 2000-03-21 2001-09-28 Casio Comput Co Ltd Advertisement data operation system and its program recording medium and transmission medium
WO2002061619A1 (en) * 2001-02-01 2002-08-08 Dentsu Inc. Advertisement distribution system
JP2007272814A (en) * 2006-03-31 2007-10-18 Cyber Wing Corp System, method and program for advertisement distribution

Also Published As

Publication number Publication date
JP2012128526A (en) 2012-07-05

Similar Documents

Publication Publication Date Title
US8355955B1 (en) Method, medium, and system for adjusting a selectable element based on social networking usage
US9208251B2 (en) Computer-based evaluation tool for selecting personalized content for users
US9002894B2 (en) Objective and subjective ranking of comments
US8972400B1 (en) Profile data management
US9704165B2 (en) Systems and methods for determining value of social media pages
US9165305B1 (en) Generating models based on user behavior
US20120310922A1 (en) Suggesting Search Results to Users Before Receiving Any Search Query From the Users
TWI424369B (en) Activity based users&#39; interests modeling for determining content relevance
US20150324868A1 (en) Query Categorizer
US9836545B2 (en) Systems and methods for personalized generalized content recommendations
US20100211464A1 (en) Targeted Online Advertising
CN103890710B (en) The method and apparatus for filtering Social search result
US20160364762A1 (en) Method and system for creating an audience list based on user behavior data
JP5612731B2 (en) Determining relevant information about the area of interest
US7853622B1 (en) Video-related recommendations using link structure
US20090248511A1 (en) Advertisements on demand
US20140280015A1 (en) Serving advertisements for search preview based on user intents
US20120078725A1 (en) Method and system for contextual advertisement recommendation across multiple devices of content delivery
KR20100051593A (en) Inferring user interests
KR20100027121A (en) Keyword and user association
US8555173B2 (en) Recommendation engine
US8478697B2 (en) Determining whether to provide an advertisement to a user of a social network
US20130290905A1 (en) Avatars for use with personalized generalized content recommendations
US9646055B2 (en) Blending search results on online social networks
US7707283B2 (en) Information processing apparatus, information processing method, program, and recording medium

Legal Events

Date Code Title Description
A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20120814

RD02 Notification of acceptance of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7422

Effective date: 20120904

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20121015

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20130129

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20130410

A911 Transfer of reconsideration by examiner before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20130417

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20130514

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20130604

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

S531 Written request for registration of change of domicile

Free format text: JAPANESE INTERMEDIATE CODE: R313531

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250