Advertisement delivery method and advertisement delivery platform
The advertisement delivery platform enhances targeting accuracy by analyzing user data to deliver ads to intended travelers, reducing costs and fraud, and increasing revenue through improved click-through rates.
Patent Information
- Application Number
- JP2023223231
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-12-28
- Publication Date
- 2025-07-10
- Estimated Expiration
- 2043-12-28
AI Technical Summary
Existing advertisement delivery systems struggle to accurately target users, leading to wasted advertising costs when ads are displayed to unintended user groups, such as foreign residents instead of intended travelers.
An advertisement delivery platform that collects and analyzes user identifiers, geographical information, and time data to infer user movement and stay patterns, enabling targeted advertisement delivery to intended user groups, such as travelers, by compressing data to reduce storage and processing costs.
Improves the accuracy of advertisement targeting, enhances click-through rates, reduces costs per click, and minimizes ad fraud by ensuring ads are displayed to the intended audience, contributing to increased revenue from inbound tourism.
Smart Images

Figure 2025104989000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a method for delivering advertisements to be displayed on a website to a user by an advertisement delivery platform, and an advertisement delivery platform.
Background Art
[0002] In recent years, for advertisements displayed on websites, some are transacted by RTB (Real-Time Bidding) using an SSP (Supply-Side Platform) and a DSP (Demand-Side Platform) for the advertisement frames of the website, and as a result, are delivered from the advertiser who won the bid for the advertisement frame via the DSP (see, for example, Patent Document 1).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] However, even when an advertisement frame is won by RTB and an advertisement is displayed as described above, if the advertisement is not displayed to the user layer targeted by the advertisement, it is difficult to actually lead to the profit of the advertiser. For example, when trying to display advertisements for hotels and tourist destinations to foreign visitors coming to Japan for tourism, if targeting is performed based on the language of the browser used by the user, etc., it often ends up being displayed to foreign residents staying in Japan for a long time, and in this case, the advertising cost will be wasted. The present invention has been made in view of the above problems, and an object thereof is to improve the accuracy of targeting advertisement delivery to an intended user layer.
Means for Solving the Problems
[0005] (Aspects of the Invention) The following aspects of the invention illustrate the configuration of the present invention and are described separately by item for easy understanding of various configurations of the present invention. Each item does not limit the technical scope of the present invention. Therefore, even if some of the components of each item are replaced, deleted, or other components are added while considering the best mode for carrying out the invention, they may be included in the technical scope of the present invention.
[0006] (1) A method for delivering an advertisement to be displayed on a website to a user by an advertisement delivery platform, comprising obtaining a user identifier, geographical information, and date and time included in an advertisement display request from a website visited by the user, and a user identifier, geographical information, and date and time provided from a linked service of the advertisement delivery platform used by the user, saving them in chronological order for each user, analyzing the saved data, grasping the movement information and stay information of each user from the relationship between the stay location and date and time of each user, and targeting a user to whom the advertisement is to be delivered based on the movement information and the stay information.
[0007] The advertisement delivery method described in this item is executed by an advertisement delivery platform, which collects geographical information indicating the area where the user is staying and performs advertisement delivery targeting based on it. Specifically, a user identifier, geographical information, and date and time included therein are obtained from an advertisement display request transmitted via an SSP or the like from a website visited by the user. Furthermore, a user identifier, geographical information, and date and time are also obtained from the information provided by the linked service used by the user. Then, the obtained data is saved in chronological order for each user identified by the user identifier. The acquisition and saving of these data shall be continuously performed. Here, the linked service refers to a website, application, information providing service, etc. that has a linked relationship with the advertisement delivery platform in use and the enterprise operating it.
[0008] Subsequently, the data acquired and saved as described above is analyzed for each user, and based on the relationship between the staying locations grasped from each user's geographical information and the date and time at that time, the movement information and staying information of each user are grasped. That is, if the relationship between the staying location and the date and time is known for each user, staying information such as how long the user stayed in a certain area and movement information such as the user moving to another area at a certain point in time can be grasped. And from the grasped movement information and staying information, the purpose of the user staying in a certain area, the purpose of moving from a certain area to another area, etc. are inferred, and based on these information, the users to whom advertisements are to be delivered are targeted. As a result, the accuracy of targeting advertisement delivery to the intended user group is improved. For this reason, advertisements are accurately delivered to the intended user group, and an improvement in the click-through rate of the advertisements displayed on the website, a decrease in the cost per click, and the exclusion of ad fraud are expected.
[0009] (2) In the above item (1), based on the movement information and the staying information, a method for delivering advertisements that targets users during travel and delivers advertisements to users during travel. The advertisement delivery method described in this item targets users during travel and delivers advertisements to users during travel based on the movement information and staying information of each user grasped by analyzing the saved data as described in the above item (1). That is, if it is known how long the user stayed in each area, that the user moved from one area to another area, the user's movement frequency, etc., it can be determined whether the user is traveling, and users who are not traveling are excluded from the targeting candidates. As a result, advertisements for travelers are accurately displayed to users during travel. For example, when the travel destination is Japan, long-term staying foreign residents in Japan are excluded, and advertisements for hotels, tourist spots, etc. are displayed for foreign visitors coming to Japan for sightseeing, which contributes to an increase in inbound revenue.
[0010] (3) In the above (2), an advertisement distribution method for compressing data to be stored by extracting, from the stored data, data indicating that at least the staying area of each user has changed. The advertisement distribution method described in this item extracts, from the data for each user acquired and stored from an advertisement display request or a linked service, data indicating that the staying area of each user has changed. For example, taking as an example the case where for a certain period of a certain user, five pieces of data, namely, "data staying in area A", "data staying in area A", "data staying in area B", "data staying in area B", and "data staying in area A", are stored in chronological order in this description order.
[0011] In this case, the third "data staying in area B" indicating that the staying area has changed from area A to area B and the fifth "data staying in area A" indicating that the staying area has changed from area B to area A are extracted. In addition to this, the first "data staying in area A" indicating the initial staying area may be extracted. Then, only the extracted data is stored, and the data not extracted is deleted or the like to compress the data to be stored. As a result, the huge amount of data to be stored is compressed while leaving the data necessary to grasp the movement information and staying information of each user, which contributes to an improvement in processing speed and a reduction in costs.
[0012] (4) In the above (2), an advertisement distribution method for compressing data to be stored by extracting, for each user, a predetermined feature set in advance from the stored data and based on the extracted predetermined feature. The advertisement distribution method described in this item extracts, for each user, predetermined features related to, for example, the staying area, staying period, movement between areas, etc. from the data of each user acquired and stored from advertisement display requests and cooperation services. Then, based on the extracted predetermined features, it integrates and compresses a plurality of data into another valuable format, or deletes unnecessary data considered as noise, etc., to compress the data to be stored. Also by this, the data to be stored, which is an enormous amount, is compressed without damaging the valuable data of each user, thus contributing to the improvement of the processing speed and the reduction of costs.
[0013] (5) In the above item (4), as the predetermined feature, at least one of the number of stays in a specific area, the staying period of each area in the movement between two or more specific areas, the cumulative staying period in an arbitrary area, the number of movements between areas, the elapsed period since the previous movement between areas, and the elapsed period between data indicating the movement between areas is extracted for each user for a specific period. The advertisement distribution method. The advertisement distribution method described in this item specifically identifies the predetermined features extracted from the stored data of each user. That is, at least one of the number of stays in a specific area, the staying period of each area in the movement between two or more specific areas, the cumulative staying period in an arbitrary area, the number of movements between areas, the elapsed period since the previous movement between areas, and the elapsed period between data indicating the movement between areas is extracted for each user for a specific period as a predetermined feature. Then, based on each of the extracted features, data integration, deletion, etc. are performed to compress the data to be stored. As a result, while the data to be stored is compressed, a plurality of stored opaque data is converted into more valuable data, so that both the compression of the stored data and the improvement of the targeting accuracy can be achieved.
[0014] An advertisement distribution platform that distributes advertisements for display on a website to a user, the data acquisition unit for acquiring a user identifier, geographical information, and date and time included in an advertisement display request from the website visited by the user, and user identifiers, geographical information, and date and time provided from a linked service of the advertisement distribution platform used by the user, a data storage unit for storing the data acquired by the data acquisition unit in a time series for each user, and a data analysis unit for analyzing the data stored by the data storage unit to grasp the movement information and stay information of each user from the relationship between the stay position and date and time of each user, and a targeting unit for targeting users to whom advertisements are to be distributed based on the movement information and the stay information. And the advertisement distribution platform according to item (6) is used in the advertisement distribution method of the above (1), and exhibits an equivalent effect corresponding to the advertisement distribution method of item (1) above.
Effect of the Invention
[0015] Since the present invention is configured in this way, it is possible to improve the accuracy of targeting advertisement distribution to the intended user layer.
Brief Description of the Drawings
[0016]
Figure 1
Figure 2
Mode for Carrying Out the Invention
[0017] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Here, throughout the drawings, the same parts or corresponding parts are denoted by the same reference numerals. In addition, detailed descriptions of the same parts or corresponding parts as the prior art will be omitted. Figure 1 shows an example of the configuration of the advertising distribution platform 10 according to an embodiment of the present invention. Here, the roles of the respective components of the advertising distribution platform 10 will be described, and the specific operations will be described with reference to the flowchart of FIG. 2 described later. Note that the configuration of the advertising distribution platform 10 according to the embodiment of the present invention is not limited to the block diagram of FIG. 1. For example, depending on the procedure and situation of the advertising distribution method, etc., a configuration in which some of the components shown in FIG. 1 are deleted, changed, or appropriately added may also be acceptable.
[0018] As shown in FIG. 1, the advertising distribution platform 10 includes a data acquisition unit 12, a data storage unit 14, a data extraction unit 16, a data analysis unit 18, a targeting unit 20, and an advertising distribution unit 22. The advertising distribution platform 10 of the embodiment in FIG. 1 is used in an RTB (Real-Time Bidding) environment and corresponds to a so-called DSP (Demand-Side Platform). Therefore, the advertising distribution platform 10 exchanges information with a plurality of websites 40 having advertising spaces for bidding and an SSP (Supply-Side Platform) 50. Each of the websites 40 has one or more advertising spaces where advertisements are distributed, and is browsed by a plurality of users U via terminals 30. Further, the advertising distribution platform 10 is also configured to receive information from a plurality of cooperation services 60 as described later.
[0019] The data acquisition unit 12 of the advertising distribution platform 10 acquires necessary data from the advertisement display request received from the website 40 via the SSP 50 and the information received from the cooperation service 60. For example, the data acquisition unit 12 acquires the IP address of the terminal 30 used by the user U browsing the website 40 and the transmission date and time (reception date and time) of the advertisement display request from the advertisement display request of the website 40, and further acquires a user identifier that can identify each user U, geographical information indicating the region where the user U is considered to be staying, etc. from there.
[0020] Here, the cooperation service 60 refers to various services that cooperate with the advertisement distribution platform 10 or the company operating the advertisement distribution platform 10. For example, it includes general websites, applications, information provision services using DMP (Data Management Platform), etc. From such cooperation services 60, the data acquisition unit 12 acquires, for example, the access log of user U, its date and time, IP address, user agent, the profile (age, gender, occupation, nationality, etc.) input by user U, the language information set by user U, and their date and time. Further, the data acquisition unit 12 acquires a user identifier that can identify each user U determined from them, and geographical information indicating the region where user U is considered to be staying. Note that examples of the user identifier acquired from the advertisement display request and the cooperation service 60 include cookies, advertisement IDs, common IDs, etc.
[0021] The data storage unit 14 stores the data acquired by the data acquisition unit 12 as described above and the data extracted by the data extraction unit 16 as described later. When storing the data acquired by the data acquisition unit 12, it is stored in a time series based on the date and time of each data for each user U based on the user identifier. Here, although the user identifier acquired from the advertisement display request by the data acquisition unit 12 and the user identifier acquired from the cooperation service 60 may have different structures, if it is found that they are user identifiers indicating the same user U, they are stored together as the data of that user U. The determination of whether user identifiers with different structures belong to the same user U can be made by using the common part between those user identifiers. As the storage destination of the data by the data storage unit 14, an arbitrary database or the like may be used, and different storage destinations may be used for the data acquired by the data acquisition unit 12 and the data extracted by the data extraction unit 16.
[0022] The data extraction unit 16 extracts data that meets specific conditions or preset features for each user U from the data acquired by the data acquisition unit 12 and stored by the data storage unit 14 for the purpose of compressing the stored data and the like. Such specific conditions and preset features will be described in detail later. The data extracted by the data extraction unit 16 and the data derived from the features extracted by the data extraction unit 16, as will be described later, are stored by the data storage unit 14 as described above. The data analysis unit 18 analyzes the data stored by the data storage unit 14, and grasps the movement information and stay information of each user U from the relationship between the stay location of the user U determined from the geographical information and the date and time of the data indicating the same.
[0023] The targeting unit 20 targets the user U to whom the advertisement is to be distributed based on the movement information and stay information of each user U grasped by the data analysis unit 18. Since the user layer to be targeted varies depending on the content of the advertisement, the targeting unit 20 performs advertisement delivery targeting according to the characteristics of the user U grasped from the movement information and stay information of the user U and the content of the advertisement to be distributed. Here, the targeting also includes the meaning of excluding the user U who has not been targeted for a certain advertisement from the distribution candidates of that advertisement. The advertisement delivery unit 22 delivers the advertisement to the user U targeted by the targeting unit 20 for a certain advertisement, and in response to an advertisement display request from the website 40 being viewed by the targeted user U, delivers the advertisement to the advertisement frame of the website 40.
[0024] Here, each component of the advertising distribution platform 10 as described above is divided by functional unit, and not by software or hardware units that actually construct the advertising distribution platform 10. Further, any software and hardware can be used for the software and hardware that construct the advertising distribution platform 10. Also, the terminal 30 used by the user U can be any terminal as long as it can access the website 40 via the network, for example, a personal computer, a tablet computer, a smartphone, a mobile phone, or the like. Although not shown in FIG. 1, various settings and inputs are made to the advertising distribution platform 10 by an administrator terminal used by an administrator of the advertising distribution platform 10 or the like.
[0025] Next, along the flow of the flowchart shown in FIG. 2, taking as an example the case of targeting and distributing advertisements to the user U, a foreigner traveling in Japan, for the advertising distribution method according to an embodiment of the present invention that utilizes the advertising distribution platform 10 shown in FIG. 1. Regarding the configuration of the advertising distribution platform 10, refer to FIG. 1 as appropriate. Note that the flowchart shown in FIG. 2 shows an example of the procedure flow for explaining the advertising distribution method according to an embodiment of the present invention. Therefore, the advertising distribution method is not limited to these flowcharts, and for example, depending on the configuration and situation of the advertising distribution platform 10 or the like, a flowchart in which some of the steps shown in FIG. 2 are deleted, changed, or appropriately added may be used.
[0026] S10 (Data acquisition): The data acquisition unit 12 acquires data including a user identifier, geographical information, and date and time from an advertisement display request transmitted from the website 40 via the SSP. Further, the data acquisition unit 12 also acquires data including a user identifier, geographical information, and date and time from the cooperation service 60. The acquisition of these data is to be continuously performed, and data is acquired each time an advertisement display request is received and each time data is provided from the cooperation service 60.
[0027] S20 (Data Saving): The data saving unit 14 saves the data acquired by the data acquisition unit 12 in S10 above. That is, it saves the data including the user identifier, geographical information, and date and time acquired from the advertisement display request, and the data including the user identifier, geographical information, and date and time acquired from the cooperation service 60. At this time, each user U is identified using the user identifier, and the data is saved in chronological order for each user U using the date and time data. Also, similar to S10 above, the data saving in this step is also continuously performed, and it is saved each time data is acquired in S10, accumulating the data of each user U.
[0028] S30 (Data Acquisition of the Target User): The data extraction unit 16 acquires data for an arbitrary specific period including the latest data of the target user U (hereinafter referred to as "target user U1" for convenience of explanation) whose trend is to be grasped, from the data of each user U that is accumulated by being saved in S20 above. At this time, the data of the target user U1 saved in S70 and S90 described later may also be acquired together. The acquisition of these data may be executed at an arbitrary timing in addition to the timing when new data is saved in S20 above.
[0029] S40 (Judgment of Change in Staying Area): The data extraction unit 16 determines whether or not the staying area (staying country in this embodiment) of the target user U1 has changed based on the data of the target user U1 acquired in S30 above. That is, it determines whether or not the staying country determined from the geographical information of the latest data of the target user U1 has changed from the staying country determined from the geographical information of the previous data of the target user U1. As a result, if it is determined that the staying country has changed (YES), it proceeds to S50, and if it is determined that the staying country has not changed (NO), it returns to S10 to continue the acquisition and saving of data.
[0030] S50 (Judgment of the number of changes in the staying area): The data extraction unit 16 determines whether there are changes in the staying area (the staying country in this embodiment) of the corresponding user U1 that are equal to or more than a preset fixed number. That is, as will be described in S60 and S70 below, since the data indicating that the staying country of the corresponding user U1 has changed is extracted and saved, the number of changes is determined based on that data. As a result, if it is determined that the number of changes in the staying country is equal to or more than the fixed number (YES), the process proceeds to S80, and if it is determined that the number of changes in the staying country is less than the fixed number (NO), the process proceeds to S60.
[0031] S60 (Data extraction): The data extraction unit 16 extracts the original data when it is determined in S40 above that the staying country of the corresponding user U1 has changed. That is, since the latest data of the corresponding user U1 obtained in S30 above is data indicating a change in the staying country, that data is extracted. S70 (Data compression and storage): The data storage unit 14 stores the data extracted in S60 above separately from the data stored in S20 above. At this time, among the data of the corresponding user U1 stored in S20 above, data that is considered unnecessary, such as data that does not indicate a change in the staying country and is older than the data stored in this step, may be deleted.
[0032] S80 (Feature extraction): The data extraction unit 16 extracts the characteristic trends of the corresponding user U1 from the data of the staying country changes of the corresponding user U1 that are equal to or more than a fixed number. In this embodiment, "the number of stays in a specific country", "the staying periods of each country in the movement between two or more specific countries", "the cumulative staying period in an arbitrary country", "the number of movements between countries", "the elapsed period since the previous movement between countries", and "the elapsed period between the data indicating the movement between countries" are extracted, etc. Here, taking as an example the case where data such as "2023-12-01@Japan", "2023-12-02@China", "2023-12-03@Japan", "2023-12-04@China", and "2023-12-07@Japan" is stored as data indicating the changes in the staying country of the corresponding user U1 during a specific period, each feature will be explained.
[0033] "The number of stays in a specific country" refers to the number of stays in each country that the corresponding user U1 has traveled to and from. In the case of the above example, it can be confirmed that the user stayed in Japan 3 times and in China 2 times. Therefore, while retaining the information that the user stayed in Japan 3 times and in China 2 times, since the number of stays in Japan is more, the data is compressed with Japan as the country of stay during those periods. "The length of stay in each country during the movement between two or more specific countries" refers to the length of stay in each country during the period when the corresponding user U1 travels to and from between countries. In the case of the above example, it is 1 day in Japan from "2023-12-01@Japan" to "2023-12-02@China", 1 day in China from "2023-12-02@China" to "2023-12-03@Japan", 1 day in Japan from "2023-12-03@Japan" to "2023-12-04@China", and 3 days in China from "2023-12-04@China" to "2023-12-07@Japan". Therefore, while retaining that information, the data is compressed with China, where the longest stay is 3 days, as the country of stay during those periods.
[0034] "The total length of stay in any country" refers to the total length of stay in each country where the corresponding user U1 stayed during a specific period. In the case of the above example, in Japan, it is a total of 2 days from "2023-12-01@Japan" to "2023-12-02@China" and from "2023-12-03@Japan" to "2023-12-04@China", and in China, it is a total of 4 days from "2023-12-02@China" to "2023-12-03@Japan" and from "2023-12-04@China" to "2023-12-07@Japan". Therefore, while retaining that information, the data is compressed with China, where the total length of stay is longer, as the country of stay during those periods. "The number of international trips" refers to the trend of the number of international trips during a certain period. For example, in the above example, if the period is divided into four-day intervals of "2023-12-01~04" and "2023-12-04~07", it can be confirmed that the number of trips is 3 in the former period and 1 in the latter period. Therefore, while retaining this information, considering the former period as noise, the data is compressed as "2023-12-01~03@Japan", "2023-12-04@China", and "2023-12-07@Japan".
[0035] "The elapsed time since the previous international trip" refers to the elapsed time between trips and is used, for example, to determine whether data indicating a certain international trip is a valid trip when compressing data. For example, in the above example, when determining whether the trip from "2023-12-02@China" to "2023-12-03@Japan" is valid, if the elapsed time since the previous trip before this trip is more than a predetermined number of days, it is determined to be valid, and it is used in this way. "The elapsed time between data indicating international trips" is for observing the frequency of trips and is used, for example, to exclude user U for whom high-frequency travel information has been observed for the purpose of excluding bots such as noise and crawlers. For example, in the above example, the elapsed time between trips is at least 1 day and at most 3 days, and by comparing this with the overall trend, user U who is noise is excluded. In addition to the features described above, any features such as having moved from a specific country to another specific country, the cumulative stay period in a specific country exceeding a predetermined period, the number of international trips between specific countries exceeding a predetermined number during a specific period, and having no travel information to countries other than a specific country may be extracted.
[0036] S90 (Data Compression and Storage): The data storage unit 14 stores the data compressed based on the features extracted in S80 separately from the data stored in S20. At this time, in anticipation of various future uses, the data may be stored permanently. S100 (Data Analysis): The data analysis unit 18 analyzes the data saved in S20, S70, and S90 above to grasp the movement information and stay information of the corresponding user U1. The movement information is information indicating movement from one country to another country and related information, and the stay information is information indicating staying in a certain country and related information. In this embodiment, since some data has already been analyzed by the data extraction unit 16 through S60 or S80, this data will be utilized.
[0037] S110 (Information Quantity Judgment): Based on the movement information and stay information of the corresponding user U1 grasped in S100 above, the targeting unit 20 determines whether sufficient information has been collected to perform targeting for the advertisements to be delivered to the corresponding user U1. The advertisements to be delivered in this embodiment are advertisements targeted at foreign tourists visiting Japan. As a result, if it is determined that sufficient information has been collected (YES), the process proceeds to S120; if it is determined that sufficient information has not been collected (NO), the process returns to S10 to continue data acquisition and storage.
[0038] S120 (Targeting): The targeting unit 20 determines whether to perform targeting for the advertisements to be delivered to the corresponding user U1, in other words, determines whether the corresponding user U1 is a foreign tourist visiting Japan. As a result, if it is determined that targeting is to be performed because the corresponding user U1 is a foreign tourist visiting Japan (YES), the process proceeds to S130; if it is determined that targeting is not to be performed because the corresponding user U1 is not a foreign tourist visiting Japan (NO), the process proceeds to S140.
[0039] S130 (Advertisement Delivery): The advertisement delivery unit 22 delivers the advertisements to be delivered, which are advertisements for foreign tourists visiting Japan in this embodiment, to the corresponding user U1 targeted in S120 above. The advertisement delivery destination is the advertisement frame of the website 40 visited by the corresponding user U1 that sent the advertisement display request. S140 (Excluding the applicable user): Since the applicable user U1 is considered not to be a foreign tourist visiting Japan but a foreign national staying in Japan for a long term etc. by the targeting unit 20, the applicable user U1 is excluded from the targeting candidates (distribution candidates) of the advertisement to be distributed.
[0040] Here, the advertisement distribution platform 10 according to the embodiment of the present invention and the advertisement distribution method according to the embodiment of the present invention are not limited to the above-described embodiment, and various changes can be made by those skilled in the art within the technical idea of the present invention. For example, the data acquired from the advertisement display request and the cooperation service 60 is not limited to the user identifier, geographical information, and date and time, and various other information may be acquired and used. Also, in the explanation using FIG. 2, geographical information was handled at the country level in order to target foreign tourists visiting Japan, but the granularity of the geographical information is not limited to the country and may be at the municipality level or the like. Furthermore, the content of the advertisement and its targeting candidates are not limited to foreign tourists visiting Japan, and may be various user groups that can be determined from geographical information of various granularities stored in time series. Also, the advertisement frame of the advertisement distribution destination is not limited to the advertisement frame won in the RTB environment, and may be an advertisement frame in which the advertiser has acquired the right to place an advertisement by any method.
[0041] Now, according to the embodiment of the present invention having the above configuration, the following operational effects can be obtained. That is, the advertising distribution method according to the embodiment of the present invention is executed by an advertising distribution platform 10 as shown in FIG. 1, for example, which collects geographical information indicating the area where the user U stays and performs targeting of advertising distribution based on it. Specifically, from an advertisement display request transmitted via an SSP 50 or the like from a website 40 visited by the user U, a user identifier, geographical information, and date and time included therein are acquired. Further, user identifier, geographical information, and date and time are also acquired from information provided by the linked service 60 used by the user U (see S10 in FIG. 2). Then, the acquired data is stored in chronological order for each user U specified by the user identifier (see S20 in FIG. 2). Acquisition and storage of these data shall be continuously performed.
[0042] Subsequently, the data acquired and stored as described above is analyzed for each user U, and from the relationship between the staying location grasped from the geographical information of each user U and the date and time at that time, the movement information and staying information of each user U are grasped (see S100 in FIG. 2). That is, if the relationship between the staying location and the date and time is known for each user U, staying information such as how long the user U has stayed in a certain area and movement information such as the user U has moved to another area at a certain point in time can be grasped. And from the grasped movement information and staying information, the purpose of the user U staying in a certain area or the purpose of moving from one area to another area can be inferred. Therefore, based on those information, the user U to whom the advertisement is to be distributed is targeted (see S120 in FIG. 2). As a result, it becomes possible to improve the accuracy of targeting of advertising distribution to the intended user group. For this reason, advertisements can be accurately distributed to the intended user group (see S130 in FIG. 2), and it is also possible to expect an improvement in the click-through rate of the advertisements displayed on the website 40, a decrease in the click cost, and the exclusion of ad fraud.
[0043] Furthermore, the advertisement distribution method according to the embodiment of the present invention may target users U during travel and distribute advertisements directed to users U during travel based on the movement information and stay information of each user U grasped by analyzing the stored data. That is, if it is known how long user U has stayed in each region, that user U has moved from one region to another, the frequency of movement of user U, etc., it is possible to determine whether that user U is on a trip, and users U who are not on a trip can be excluded from the targeting candidates. This makes it possible to accurately display advertisements for travelers to users U during travel. For example, when the travel destination is Japan, excluding foreign residents staying in Japan long-term (see S140 in FIG. 2), advertisements for hotels, tourist attractions, etc. can be displayed to foreign visitors coming to Japan for sightseeing, contributing to an increase in inbound revenue.
[0044] Furthermore, the advertisement distribution method according to the embodiment of the present invention extracts data indicating that the staying region of each user U has changed from the data of each user U obtained from advertisement display requests or the cooperation service 60 and stored (see S40 and S60 in FIG. 2). Then, only the extracted data is saved, and the data that was not extracted is deleted, etc., to compress the data to be saved (see S70 in FIG. 2). As a result, it is possible to compress the huge amount of data to be stored while leaving the data necessary to grasp the movement information and stay information of each user U, contributing to an improvement in processing speed and a reduction in costs.
[0045] In addition, the advertising distribution method according to an embodiment of the present invention extracts, for each user U, predetermined features related to, for example, the staying area, staying period, movement between areas, etc. from the data of each user U acquired and stored from an advertising display request or a cooperation service 60 (see S80 in FIG. 2). Then, based on the extracted predetermined features, a plurality of data are integrated and compressed into another valuable format, or unnecessary data considered as noise or the like are deleted, and the data to be stored are compressed (see S90 in FIG. 2). Also by this, since the data to be stored, which is an enormous amount, can be compressed without impairing the valuable data of each user U, it becomes possible to contribute to an improvement in processing speed and a reduction in cost.
[0046] In addition, the predetermined features extracted from the data of each stored user U in the advertising distribution method according to an embodiment of the present invention may be as follows. That is, at least one of the number of stays in a specific area, the staying period in each area in the movement between two or more specific areas, the cumulative staying period in an arbitrary area, the number of movements between areas, the elapsed period from the previous movement between areas, and the elapsed period between data indicating the movement between areas is extracted for each user U as a predetermined feature for a specific period. Then, based on each of the extracted features, data integration, deletion, etc. are performed, and the data to be stored are compressed. Thereby, while compressing the data to be stored, a plurality of stored opaque data can be converted into more valuable data, so that it becomes possible to achieve both compression of the stored data and improvement in targeting accuracy.
[0047] On the other hand, the advertising distribution platform according to an embodiment of the present invention can achieve equivalent operational effects corresponding to the advertising distribution method according to an embodiment of the present invention by being used in the advertising distribution method according to an embodiment of the present invention as described above.
Explanation of Signs
[0048] 10: Advertising delivery platform, 12: Data acquisition unit, 14: Data storage unit, 18: Data analysis unit, 20: Targeting unit, 40: Website, 60: Collaboration service, U (U1): User
Claims
1. A method for delivering an advertisement to be displayed on a website to a user by an advertisement delivery platform, comprising: obtaining a user identifier, geographical information, and date and time included in an advertisement display request from a website visited by the user, and a user identifier, geographical information, and date and time provided from a linked service of the advertisement delivery platform used by the user, and storing them in a time series for each user; analyzing the stored data to grasp movement information and stay information of each user from the relationship between the staying location and the date and time of each user; targeting a user to whom an advertisement is to be delivered based on the movement information and the staying information, wherein the advertisement delivery method is characterized in that.
2. The advertisement delivery method according to claim 1, characterized in that a user during a trip is targeted based on the movement information and the staying information, and an advertisement directed to the user during the trip is delivered.
3. The advertisement delivery method according to claim 2, characterized in that data indicating at least that the staying area of each user has changed is extracted from the stored data, and the stored data is compressed.
4. The advertisement delivery method according to claim 2, characterized in that predetermined features set in advance are extracted for each user from the stored data, and the stored data is compressed based on the extracted predetermined features.
5. As the predetermined features, at least one of the number of stays in a specific area, the staying period of each area in the movement between two or more specific areas, the cumulative staying period in an arbitrary area, the number of movements between areas, the elapsed period from the previous movement between areas, and the elapsed period between data indicating the movement between areas is extracted for each user for a specific period, wherein the advertisement delivery method according to claim 4 is characterized in that.
6. An advertisement delivery platform for delivering an advertisement to be displayed on a website to a user, comprising: a data acquisition unit that acquires a user identifier, geographical information, and date and time included in an advertisement display request from a website visited by the user, and a user identifier, geographical information, and date and time provided from a linked service of the advertisement delivery platform used by the user; a data storage unit that stores the data acquired by the data acquisition unit in a time series for each user; a data analysis unit that analyzes the data stored by the data storage unit to grasp movement information and staying information of each user from the relationship between the staying location and the date and time of each user; A targeting unit that targets users who deliver advertisements based on the movement information and the stay information, and an advertisement delivery platform characterized by including the same.
Citation Information
Patent Citations
Data analysis system and data analysis method
JP2019023851A
Method for providing advertisement for TV program
JP2020167645A
Point retargeting affiliate advertisement distribution method
JP2020197964A
System for user attribute estimation based on IP address
WO2019207771A1
On-line advertisement distribution system
JP2014102663A