JP7312680B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has been actively performed. For example, advertising content such as a company or product is displayed in an advertising space set in an advertising medium (web page), and when the advertising content is clicked, the advertisement is transferred to the advertiser's web page.

In such advertisement distribution, a bid unit price (CPC: Cost Per Click), which is a billing amount charged to the advertiser, may be used as a consideration for posting advertisement content. For example, eCPM (effective Cost Per Mille) is calculated by calculating a CPC and multiplying the calculated CPC by a click through rate (CTR).

Further, instead of a bid unit price (CPC), a technology (called conversion optimization) has been proposed in which an advertiser sets a target unit price per conversion (CPA), which is a target value of a conversion unit price (CPA), which is the cost associated with obtaining one profitable result such as product purchase or membership registration from predetermined advertisement content, and calculates a bid unit price to be set for the advertisement content based on the target conversion unit price.

Here, a technology has been proposed for correcting the click rate (CTR) of distribution information such as advertisement information according to the arrangement position in the display screen of the distribution destination (see Patent Document 1).

JP 2014-174805 A

However, in the conventional technology described above, the user's context (context, context, circumstance, background, situation, etc.) leading up to the click is not considered when correcting the click rate. In Internet advertisements, the user's context is expected to affect the success or failure of clicks. The user's context varies each time, but if a predictive model is uniformly generated based on the success or failure of a click, the user's context is not taken into account in the predictive model, so high accuracy in predicting the click rate cannot be obtained. Therefore, it is required to weight the action history such as clicks in consideration of the user's context.

The present application has been made in view of the above, and an object thereof is to provide an information processing device, an information processing method, and an information processing program capable of weighting an action history in consideration of a user's context.

An information processing apparatus according to the present application is characterized by comprising: an estimation unit that estimates a user's context up to an advertisement content selection operation; and a correction unit that corrects the number of selection operations by weighting the user's selection operation with a correction amount that differs according to the user's context for each advertisement content.

According to one aspect of the embodiments, the behavior history can be weighted considering the user's context.

FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to the embodiment; 3 is a diagram illustrating an example of a user information storage unit according to the embodiment; FIG. 4 is a diagram illustrating an example of an advertisement information storage unit according to the embodiment; FIG. FIG. 5 is a flowchart illustrating an information processing procedure performed by the information processing apparatus according to the embodiment; FIG. 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Hereinafter, modes for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Outline of information processing method]
First, an outline of an information processing method performed by an information processing apparatus according to an embodiment will be described with reference to FIG. FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. In the example of FIG. 1 , the information processing system 1 has an advertiser terminal 10 , a terminal device 20 , an information providing device 30 and an information processing device 100 . The advertiser terminal 10, the terminal device 20, the information providing device 30, and the information processing device 100 are communicably connected by wire or wirelessly via a network. The information processing system 1 shown in FIG. 1 may include multiple advertiser terminals 10 , multiple terminal devices 20 , multiple information providing devices 30 , and multiple information processing devices 100 . Further, in this embodiment, the information providing device 30 and the information processing device 100 are assumed to be managed by the business operator T1.

The advertiser terminal 10 is a terminal device used by advertisers. For example, the advertiser terminal 10 is a smart device such as a smart phone or a tablet terminal, a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), OA equipment (office automation equipment), or the like. In addition, the advertiser terminal 10 submits advertisement content to the information processing device 100 according to the advertiser's operation.

For example, the advertiser terminal 10 submits advertisement content corresponding to still images, moving images, text data, etc. to the information processing apparatus 100 . Also, for example, the advertiser terminal 10 submits to the information processing apparatus 100 advertising content corresponding to the URL (Uniform Resource Locator) of transition destination content to be transitioned when advertising content is selected (for example, clicked or tapped). Note that the selection operation will be described below as clicking.

Further, the advertiser terminal 10 instructs the information processing device 100 to set a target conversion unit price, which is a target value of a conversion unit price, which is a cost associated with obtaining one profitable result such as product purchase or membership registration from the advertisement content, in accordance with the operation of the advertiser. Here, the term "conversion" means that a user viewing advertisement content takes an action expected by an advertiser (implementation of a predetermined action). For example, conversions set for advertisements vary widely according to the settings of the advertiser, such as advertisement clicks, landing page visits, document requests, questionnaire responses, quote requests, sales requests, product purchases (contract conclusion).

Note that it is predetermined that the target unit price per conversion can be set only for advertising content that has obtained a predetermined number (for example, "10") or more of conversions. For this reason, for example, when the advertiser's own advertising content that has already been submitted has achieved a predetermined number of conversions or more, the advertiser sets a target unit price per conversion for the advertising content.

The terminal device 20 is a terminal device used by a user. For example, the terminal device 20 is a smart device such as a smart phone or a tablet terminal, a PC, a mobile phone, a PDA, or the like. For example, the terminal device 20 acquires a web page from the information providing device 30 by accessing the information providing device 30, and displays the acquired web page on the display screen.

Further, when the web page includes an advertising space, the terminal device 20 accesses the information processing device 100 to acquire advertising content from the information processing device 100, and displays the acquired advertising content in the advertising space.

The information providing device 30 is a content server that provides content such as web pages to the terminal device 20 . The information providing device 30 provides, for example, various web pages related to news sites, auction sites, weather forecast sites, shopping sites, finance (stock price) sites, route search sites, map providing sites, travel sites, gourmet sites, web blogs, and the like.

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

Further, as described above, the information processing apparatus 100 according to the embodiment automatically sets a bid unit price on behalf of the advertiser by receiving the setting of the target unit price per conversion from the advertiser. Specifically, the information processing apparatus 100 multiplies the conversion rate (CVR) of the advertisement content by a target unit price set for the advertisement content for each advertisement content, thereby calculating the bid unit price, which is the amount to be charged when the advertisement content is selected. Then, the information processing apparatus 100 distributes the advertisement based on the calculated bid unit price.

Here, the conversion rate (CVR) is a performance value calculated by dividing the number of conversions from advertising content (the number of conversions) by the number of clicks on the advertising content so far. Therefore, it can be said that the more conversions and clicks, the higher the accuracy of the conversion rate statistically. In other words, the less conversions and clicks, the less accurate your conversion rate is statistically. The precision of the conversion rate here corresponds to the degree of reliability, ie, whether or not the conversion rate is statistically reliable.

An example of a conversion rate calculation method will be described. For example, for advertisement content, when the number of clicks is "10" and the number of conversions is "1", the conversion rate of the advertisement content is "0.1". However, when the number of clicks is "1000", the conversion rate of "0.1" is not always calculated because the number of conversions is "100". For example, in reality, when the number of clicks is "1000", the number of conversions is "20", so the conversion rate may be calculated as "0.02".

Thus, it can be said that the conversion rate is an unstable value that changes according to the distribution information. In other words, the conversion rate once calculated is not necessarily a certain value. Originally, it is desirable to use a sufficient number of clicks to be reliable and a conversion rate calculated from the number of conversions. Therefore, it may be difficult to accurately predict what the conversion rate of all advertising content will be as a statistically reliable value.

Also, for example, when a bid unit price is calculated using a conversion rate with low accuracy, the calculated bid unit price can also be said to be a low-accuracy value. In addition, if an advertisement is distributed using an inaccurate bid unit price, the target conversion unit price may be greatly exceeded.

Therefore, the information processing apparatus 100 according to the embodiment performs processing for weighting clicks based on the circumstances surrounding the conversion rate as described above. Specifically, the information processing apparatus 100 corrects the number of clicks by weighting the user's clicks based on the score (index value) of the user's context when transitioning from the advertising content, which is an example of the first content, to the second content (transition destination content), which is the transition destination.

Transition destination content transitioned from advertising content is generally called a landing page (LP) or the like. Therefore, hereinafter, the transition destination content may be referred to as "LP". Further, hereinafter, the target unit price for conversion may be referred to as "target CPA", the conversion rate before correction calculated from performance information as "CVR", and the bid unit price as "CPC".

In this embodiment, a low score is set for a context that is easy for the user to click, and a high score is set for a context that is difficult for the user to click.

For example, when a user clicks on an advertisement content, the context score is set low because it is considered easy to click in the same environment as usual such as at home, and the context score is set high because it is considered difficult to click in an environment different from usual such as a travel destination.

In addition, since it is considered that a user (experienced person) who has purchased products from LP is easy to click, the context score is set low, and a user who has never purchased products from LP (inexperienced person) is considered difficult to click, so the context score is set high.

From the above, the lower the score of the user's context in the LP, the higher the possibility that the user will click, and the easier it is to click, that is, the higher the possibility that the click rate will improve. Conversely, the higher the user's context score in the LP, the less likely they are to click and the less likely they are to click, ie, improve their click-through rate. As such, there is a correlation between the user's context score and click-through rate on the LP.

However, clicks from users with high context scores are worth more per click than clicks from users with low context scores. Therefore, the information processing apparatus 100 according to the embodiment corrects the number of clicks by weighting the user's clicks using the score of the user's context. Then, the information processing apparatus 100 according to the embodiment calculates the click rate (CTR) and conversion rate (CVR) of the advertising content based on the corrected number of clicks.

That is, the information processing apparatus 100 weights the user's click (once) using the user's context score for each advertisement content, and corrects the number of clicks by the user. Then, the information processing apparatus 100 corrects the total number of clicks by adding the corrected number of clicks of the user to the total number of clicks, and uses the total number of clicks to calculate the click rate (CTR) and conversion rate (CVR) of the advertising content.

Correcting the number of clicks in this way corresponds to predicting what value the conversion rate based on the number of clicks will take as a statistically reliable value.

Information processing performed by the information processing apparatus 100 will be specifically described below with reference to FIG. It should be noted that the information processing apparatus 100 according to the embodiment employs a method of determining advertisement content to be distributed using a search query recently used by the user in content managed by the business operator T1. Such a technique is called search targeting or the like. Further, it is assumed that the advertising content provided by the information processing apparatus 100 is pay-per-click type advertising content.

First, the advertiser terminal 10 submits advertisement content to the information processing device 100 and instructs the information processing device 100 to set various information related to the advertisement content according to the operation of the advertiser (step S1). Accordingly, the information processing apparatus 100 receives advertisement content submission and various information settings from the advertiser. Then, the information processing apparatus 100 stores the received advertising content and various information.

In addition, the advertiser terminal 10 instructs the information processing device 100 to set a target CPA for advertising content submitted by the advertiser in accordance with the advertiser's operation (step S2). Thereby, the information processing apparatus 100 receives the setting of the target CPA from the advertiser. Then, the information processing apparatus 100 stores the received target CPA in association with the advertising content.

Here, it is assumed that the information processing apparatus 100 receives the submission of the advertising content AD11 from the advertiser C1, the LP11 transitioned from the advertising content AD11, and the setting of the target CPA for the advertising content AD11.

Here, it is assumed that the terminal device 20 transmits a request for acquiring the web page P1 to the information providing device 30 according to the operation of the user U1 (step S3). As a result, the information providing device 30 distributes the web page P1 to the terminal device 20 that has sent the acquisition request (step S4).

As shown in FIG. 1, a web page P1 includes an advertising space F1 in which advertising content is displayed. The terminal device 20 transmits an advertisement content acquisition request to the information processing device 100 (step S5).

When the information processing apparatus 100 receives the advertisement content acquisition request from the terminal device 20, the information processing apparatus 100 delivers the advertisement content AD11 as a delivery candidate to the terminal device 20 that has transmitted the acquisition request (step S6). Accordingly, the terminal device 20 displays the web page P1 in which the advertising content AD11 is displayed in the advertising space F1 on the display screen.

Next, when the terminal device 20 accesses the distributed advertising content AD11, the information processing device 100 estimates the context score of the access source user who clicked the advertising content AD11, i.e., the distribution target user U1 to whom the advertising content is distributed (step S7).

For example, the information processing apparatus 100 estimates the user's context score by machine-learning the relationship between the number of clicks and the context information such as the day of the week/time period/location for each advertisement content. Here, it is assumed that the information processing apparatus 100 estimates that the score of the context in the LP11 corresponding to the distribution candidate advertising content AD11 is "3".

At this time, the information processing apparatus 100 may estimate the score of the user's context using the user's attribute information together with the above context information. Arbitrary attributes, such as demographics (demographic attributes) and psychographics (psychological attributes), can be adopted as user attribute information.

Next, the information processing apparatus 100 corrects the number of clicks by weighting the clicks of the user U1 using the score of the context estimated in step S7 (step S8). Here, the information processing apparatus 100 corrects the number of clicks by the user U1 on the LP11 to "3" by multiplying one click by the user U1 on the LP11 by the context score "3". As a result, the total number of clicks including other users on the LP 11 also changes.

In this manner, the information processing apparatus 100 according to the embodiment performs correction so that the number of clicks increases as the score of the estimated context increases. The reason is that clicks by users with high context scores are considered to be more valuable per click than clicks by users with low context scores.

Next, the information processing apparatus 100 calculates a click rate (CTR) and a conversion rate (CVR) based on the number of clicks corrected in step S8 (step S9).

Next, the information processing apparatus 100 calculates the CPC by multiplying the calculated CVR by the target CPA set in step S2, and multiplies the calculated CPC by the click through rate (CTR) to calculate eCPM (effective cost per mille) (step S10).

In this manner, the information processing apparatus 100 according to the embodiment estimates the score of the context of the user to whom the advertisement content is distributed in the LP to which the advertisement content transitions. Then, the information processing apparatus 100 corrects the number of clicks based on the estimated score of the context, and calculates the click rate based on the corrected number of clicks.

As described above, the conversion rate (CVR) is an unstable value because it is calculated based on the number of conversions and the number of clicks for which it is difficult to obtain a statistically sufficient number of performance information. Therefore, by correcting the number of clicks using the score of the user's context that affects the number of clicks correlated with the conversion rate, it is possible to obtain a highly accurate conversion rate. In addition, the information processing apparatus 100 can improve the accuracy of the eCPM by using the conversion rate based on the corrected number of clicks, thereby making it easier to achieve the target CPA set by the advertiser.

[2. Configuration of Information Processing Device]
Next, the information processing apparatus 100 according to the embodiment will be described using FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 2, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section .

The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from the terminal device 20 and the information providing device 30, for example.

The storage unit 120 is realized by, for example, a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, or a storage device such as a hard disk or an optical disk. Storage unit 120 has user information storage unit 121 , advertisement content storage unit 122 , history information storage unit 123 , and prediction model storage unit 124 .

(Regarding the user information storage unit 121)
The user information storage unit 121 stores information related to actions performed by users on content. In this embodiment, the user information storage unit 121 stores, as a search history, search keywords and the like used by the user to search for information in predetermined content (for example, a search site). Here, FIG. 3 shows an example of the user information storage unit 121 according to the embodiment. In the example of FIG. 3, the user information storage unit 121 has items such as "user ID", "attribute information", "advertisement ID", "LP-ID", "click date and time", "click location", and "context".

“User ID” indicates identification information for identifying the user or the terminal device 20 used by the user. “Attribute information” indicates user attribute information such as demographics (demographic attributes) such as gender/age/address, and psychographics (psychological attributes). “Advertisement ID” indicates identification information for identifying advertisement content. “LP-ID” indicates identification information for identifying transition destination content (landing page) to be transitioned to when corresponding advertising content is selected. The “click date and time” indicates the date and time when the user clicked on the predetermined advertisement content. The "click date and time" may include the day of the week. "Clicked location" indicates the location where the user clicked on the predetermined advertisement content. The "click location" may be location information. "Context" indicates the score of the user's context.

That is, in the example of FIG. 3, the user identified by the user ID "U1" clicked "LP11" corresponding to the advertising content "AD11" at the click location "L11" at the click date and time "T11". Assume that the context at this time is "3". In FIG. 3, time is represented by concepts such as "T11" and position by "L11", but in actuality, specific information indicating the date, day of the week, time zone, etc. is stored in the item of position. Further, in the position item, specific information indicating the position of the terminal device 20 (for example, latitude and longitude, numerical values of a coordinate system, address, etc.) is stored.

User IDs may be used to distinguish between users. For example, a user identified by a user ID "U1" is referred to as user U1. Hereinafter, advertisers, advertisement contents, and LPs will also be described using identification information in the same manner.

(Regarding the advertisement content storage unit 122)
The advertising content storage unit 122 stores various information related to advertising content submitted from the advertiser terminal 10 and advertising content whose settings are received from the advertiser terminal 10 . In addition, the advertisement content storage unit 122 stores performance information regarding advertisement distribution. Here, FIG. 4 shows an example of the advertising content storage unit 122 according to the embodiment. In the example of FIG. 4, the advertising content storage unit 122 has items such as “advertiser ID”, “advertising ID”, “advertising content”, “LP-ID”, “LP-URL”, “target CPA”, “number of clicks”, “CTR”, and “number of conversions”.

"Advertiser ID" indicates identification information for identifying an advertiser or an advertiser terminal. “Advertisement ID” indicates identification information for identifying advertisement content. “Advertising content” indicates advertising content submitted from the advertiser terminal 10 . FIG. 4 shows an example in which conceptual information is stored in "advertisement content", but in reality still images, moving images, text data, or file path names indicating their storage locations are stored.

“LP-ID” indicates identification information for identifying transition destination content to be transitioned to when corresponding advertising content is selected. "LP-URL" indicates the URL of the transition destination content. The “LP-URL” is, for example, attached to advertising content and distributed together with the advertising content.

“Target CPA” indicates a target value of a conversion unit price, which is a cost associated with obtaining a profitable result such as product purchase or membership registration from the corresponding advertisement content, ie, one conversion. “Target CPA” can be set only for advertising content that has obtained a predetermined number (for example, “10”) or more of conversions. A "keyword" is information used for user targeting, and indicates what kind of content the advertisement content is. The “keyword” may be freely set by the advertiser, or may be selected by the advertiser by presenting candidate keywords from the information processing apparatus 100 .

"Number of clicks" indicates the number of times the advertising content has been clicked. "CTR" is a value obtained by dividing the "number of clicks" by the number of times the advertisement content is displayed. As the CTR of advertising content that has never been delivered to the terminal device 20, a predetermined fixed value, an average CTR value of all advertising content, an average CTR value of all advertising content belonging to the same advertising category (for example, "car", "travel"), etc. are stored. "Number of conversions" indicates the number of clicks on advertising content that have resulted in conversions.

That is, in the example of FIG. 4, the advertiser identified by the advertiser ID "C1" submits data "XX11" of the advertising content identified by the advertising ID "AD11". Further, an example is shown in which the advertiser C1 designates the URL "aa11.com" of the LP identified by the LP-ID "LP11" and sets the target CPA "15,000" for its advertisement content "AD11".

(Regarding the control unit 130)
Returning to FIG. 2, the control unit 130 is realized by executing various programs stored in a storage device inside the information processing apparatus 100 using a RAM as a work area by a CPU (Central Processing Unit), MPU (Micro Processing Unit), or the like. Also, the control unit 130 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130 includes a reception unit 131, a distribution unit 132, an estimation unit 133, and a correction unit 134, and realizes or executes information processing functions and actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it performs the information processing described later. Moreover, the connection relationship between the processing units of the control unit 130 is not limited to the connection relationship shown in FIG. 2, and may be another connection relationship.

(Regarding the reception unit 131)
The accepting unit 131 accepts submission of advertisement content and setting of various information about the advertisement content from the advertiser terminal 10 , and stores the accepted advertisement content and setting information in the advertisement content storage unit 122 . Specifically, the accepting unit 131 accepts submission of advertisement content corresponding to still images, moving images, text data, etc., and settings of LP-URL, target CPA, keywords, and the like.

Then, the receiving unit 131 issues the advertiser ID and the advertisement ID, and stores the received information in the advertisement content storage unit 122 in association with the issued advertiser ID and advertisement ID. Note that the target CPA can be set only for advertising content that has obtained a predetermined number (for example, "10") or more of conversions.

In addition, the receiving unit 131 receives a request to acquire advertising content from the terminal device 20 . For example, the reception unit 131 receives a request to acquire a web page using an HTTP (Hypertext Transfer Protocol) request or the like. For example, assume that the terminal device 20 transmits an advertisement content acquisition request to the information processing device 100 in accordance with the operation of the user U1. Then, when the reception unit 131 of the information processing apparatus 100 receives such an acquisition request, the reception unit 131 first identifies the advertisement content of the distribution candidate.

(Regarding the distribution unit 132)
The distribution unit 132 distributes the advertising content specified by the reception unit 131 to the terminal device 20 . For example, the distribution unit 132 distributes the advertisement content specified by the reception unit 131 to the terminal device 20 in association with predetermined information.

Here, the distribution unit 132 pastes the URL of LP11 to the advertising content AD11. In the example of the advertising content storage unit 122 shown in FIG. 4, the distribution unit 132 pastes the URL "bb11.com" of LP11 to the advertising content AD11. Then, the distribution unit 132 distributes the advertising content AD11 to the terminal device 20. FIG.

Further, the distribution unit 132 may receive information from the terminal device 20 indicating that the advertising content has been clicked. For example, every time the distribution unit 132 receives information indicating that the advertisement content has been clicked from the terminal device 20, the advertisement content storage unit 122 updates the corresponding number of clicks.

Also, the distribution unit 132 may receive information indicating that a conversion has been obtained from the terminal device 20 . For example, the distribution unit 132 updates the corresponding number of conversions stored in the advertisement content storage unit 122 every time it receives information on conversion acquisition from the terminal device 20 .

(Regarding the estimation unit 133)
The estimation unit 133 estimates the score of the context of the distribution target user to whom the advertising content is distributed for each distribution candidate advertising content. For example, when the terminal device 20 accesses LP11 corresponding to advertising content AD11 in response to a click operation of a distribution target user, the estimation unit 133 estimates the score of the user's context in LP11. Specifically, the score of the user's context in the LP is estimated by referring to past history information (log information) regarding advertisement distribution and performing machine learning for each advertisement content.

Note that if the advertising content is clicked even though the user's context score is high, it can be said that the user's degree of interest in the advertising content or the importance/effectiveness of the advertising content to the user is high. That is, if the advertising content is clicked on, the context score is the degree of user-indicated interest in the advertising content or the importance/effectiveness of the advertising content to the user. Therefore, the estimation unit 133 estimates the degree of interest shown by the user to the advertising content or the importance/effectiveness of the advertising content to the user, based on the score of the user's context.

Also, the estimation unit 133 may estimate the temporal situation when the user clicks on the advertisement content. For example, the estimating unit 133 depends on factors such as the time zone (early morning/morning/noon/night/evening/midnight/dawn/dawn/midday) and the day of the week (weekdays/Fridays/Saturdays, Sundays, and holidays) when the user clicks the advertising content. Estimates the context score.

Also, the estimation unit 133 may estimate the positional situation when the user clicks on the advertisement content. For example, the context score is estimated according to factors such as the location/facility/region where the user clicked on the advertising content.

In addition, the estimation unit 133 may estimate whether the user is traveling as the user's situation. For example, the estimating unit 133 estimates the context score according to factors such as whether the user clicked the advertisement content in a usual environment such as home or in an unusual environment such as traveling. Here, the estimation unit 133 estimates whether or not the user is traveling from the attribute information about the user's address and the position information of the terminal device 20, or from the user's schedule information or SNS (Social Networking Service). In addition, the estimation unit 133 may change the score of the context according to whether the trip is a day trip or an overnight stay, an urban area or a rural area, a domestic or overseas trip, a sightseeing trip or a business trip, or a homecoming trip. It should be noted that "during a trip" may be read as "out".

In addition, the estimation unit 133 may estimate whether the user is moving as the user's situation. For example, the estimation unit 133 estimates the score of the context according to factors such as whether the user is in a non-moving state (stationary/stopped) or in a moving state (moving). Here, the estimation unit 133 estimates whether or not the user is moving from the location information and time information of the terminal device 20, or from the user's schedule information or SNS. In addition, the estimation unit 133 may change the context score depending on whether the user is driving a car (including a motorcycle), riding a train/taxi/bus, or boarding an aircraft/ship.

(Regarding the correction unit 134)
The correcting unit 134 corrects the number of clicks on the advertisement content based on the score of the user's context estimated by the estimating unit 133, and calculates the click rate using the corrected number of clicks. Specifically, the correction unit 134 multiplies one click on the advertisement content of the distribution candidate by a correction amount (weight value) based on the score of the user's context in the LP corresponding to the advertisement content of the distribution candidate. Corrects the number of clicks. Here, the value of the context score is used as it is as the amount of correction based on the context score.

Note that the correction unit 134 may correct the number of clicks by a correction amount according to the relationship between the user's situation and the advertising content clicked by the user. For example, the correcting unit 134 corrects the number of clicks by multiplying the context score of the user by a correction amount based on the context score according to the relationship between the content of the advertising content (advertised product, design, etc.).

[3. Processing procedure]
Next, the procedure of information processing executed by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an information processing procedure by the information processing apparatus 100 according to the embodiment.

First, the receiving unit 131 of the information processing device 100 determines whether or not a request to acquire advertising content has been received (step S101). If the acquisition request has not been received (step S101; No), the reception unit 131 waits until the acquisition request is received.

On the other hand, when the acquisition request is accepted (Step S101; Yes), the accepting unit 131 identifies the advertisement content of the distribution candidate (Step S102). Next, the distribution unit 132 distributes the identified distribution candidate advertising content (step S103).

Next, the distribution unit 132 determines whether or not the terminal device 20 has accessed the advertising content distributed by the distribution unit 132 (step S104).

Next, when the terminal device 20 accesses the advertising content distributed by the distribution unit 132 (step S104; Yes), the estimating unit 133 estimates the context score of the access source user who clicked the advertising content, i.e., the user to whom the advertising content is distributed (the user who sent the acquisition request) (step S105).

Next, the correction unit 134 corrects the number of clicks using the score of the context estimated in step S105 (step S106). Then, the correction unit 134 calculates a click rate (CTR) and a conversion rate (CVR) using the corrected number of clicks (step S107).

Next, the correction unit 134 calculates the eCPM of the advertising content (step S108). Specifically, the correction unit 134 multiplies the calculated CVR by the target CPA of the advertising content to calculate the CPC, and multiplies the calculated CPV by the CTR of the advertising content to calculate the eCPM.

[4. Modification]
The information processing apparatus 100 according to the above embodiment may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the information processing apparatus 100 will be described below.

In the above-described embodiment, the information processing apparatus 100 estimates the score of the user's context in the LP each time.

Further, in the above-described embodiment, an example was shown in which the correction unit 134 uses the value of the score of the user's context as it is as the correction amount, but the present invention is not limited to this. For example, the correction unit 134 may use a predetermined correction amount according to the user's context score. As an example, the correction amount may be set in advance for each context score range, such as "context score range: ~1" (correction amount "1"), "context score range: 2 to 3" (correction amount "1.1"), "context score range: 4 to 5" (correction amount "1.2"). In such a case, the correcting unit 134 corrects the number of clicks using the correction amount associated with the context score range including the context score estimated by the estimating unit 133 .

Also, in the above embodiment, the score of the user's context in the LP is represented by one element (item), but in reality it may be represented by a plurality of elements. Further, the correction amount based on the score of the context may be the total value, the average value, or the median value of the correction amounts of a plurality of elements. For example, when the correction amount based on the context score of a certain user is represented by a plurality of elements such as "traveling" (correction amount "5"), "weekday" (correction amount "3"), and "stopping" (correction amount "1"), the correction amount based on the context score may be either a total value "9", an average value "3", or a median value "3".

Further, in the above embodiment, the information processing apparatus 100 may change the correction amount according to the difficulty based on the user's context. Furthermore, the information processing apparatus 100 may change the correction amount according to the combination of the degree of matching between the advertisement and the user and the difficulty based on the user's context. For example, the information processing apparatus 100 increases the correction amount in the following order: "advertisement that suits the user x not moving", "advertisement that suits the user x moving x traveling", "advertisement that does not suit the user x not moving", and "advertisement that does not suit the user x moving x traveling". Accordingly, the number of clicks after correction also increases. Here, an advertisement that does not target the user, such as when the advertised product is "for women" and the user is "male", or when the advertised product is "for the elderly" and the user is "young", can be said to be an advertisement that does not suit the user. The information processing apparatus 100 may also change the correction amount depending on how much the user and the advertisement match/are far apart (degree of divergence).

In the above embodiment, the information processing apparatus 100 corrects the number of clicks by multiplying one user click by a correction amount (weight value) based on the score of the user's context. That is, the information processing apparatus 100 may correct the number of conversions by multiplying one conversion of the user by a correction amount (weight value) based on the score of the user's context. Since conversions are also typically driven by clicks, it is expected that conversions, like clicks, are influenced by the user's context.

Further, in the above embodiment, the machine learning performed by the information processing apparatus 100 may be deep learning using a deep neural network, for example. The information processing device 100 may also use data mining or other machine learning algorithms.

[5. Hardware configuration]
The information processing apparatus 100 according to the embodiments described above is implemented by a computer 1000 configured as shown in FIG. 9, for example. The information processing apparatus 100 will be described below as an example. FIG. 9 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the information processing apparatus 100. As shown in FIG. Computer 1000 has CPU 1100 , RAM 1200 , ROM (Read Only Memory) 1300 , HDD (Hard Disk Drive) 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

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

HDD 1400 stores programs executed by CPU 1100 and data used by these programs. Communication interface 1500 receives data from other devices via communication network 50 (corresponding to network N shown in FIG. 2), sends the data to CPU 1100, and transmits data generated by CPU 1100 to other devices via communication network 50.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . Also, CPU 1100 outputs the generated data to an output device via input/output interface 1600 .

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

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the RAM 1200 . In addition, the data in storage unit 120 is stored in HDD 1400 . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via communication network 50 .

[6. effect〕
As described above, the information processing apparatus 100 according to the present application includes the estimation unit 133 that estimates the situation (context) of the user who clicked (selection operation) the advertisement content, and the correction unit 134 that corrects the number of clicks (the number of selection operations) with a different amount of correction depending on the situation of the user for each advertisement content. note that. Click may be read as tap. Thereby, the action history such as clicks can be weighted in consideration of the user's context.

The estimation unit 133 estimates the user's situation from the past history information of the user who clicked the advertisement content. Thereby, the user's context can be estimated from the past log.

The estimation unit 133 estimates the temporal situation when the user clicks on the advertisement content. As a result, factors such as the time zone and day of the week when the user clicked on the advertisement content can be considered and weighted.

The estimation unit 133 estimates the positional situation when the user clicks on the advertisement content. This allows weighting to take into account factors such as the location or region where the user clicked on the advertising content.

The estimation unit 133 estimates whether or not the user is traveling as the user's situation. As a result, weighting can be performed by taking into consideration factors such as whether the user clicked on the advertisement content in a normal environment such as at home or in an unusual environment such as while traveling.

The estimation unit 133 estimates whether or not the user is moving as the user's situation. As a result, weighting can be performed by taking into consideration factors such as whether the user is in a non-moving state (stationary/stopped) or in a moving state (moving). Also, factors such as whether the user is on a train/taxi/bus or the like can be taken into account for weighting.

The correction unit 134 corrects the number of clicks by a correction amount according to the relationship between the user's situation and the advertising content clicked by the user. Thereby, it is possible to weight according to the relationship between the user's context and the content of the advertising content (advertised product, design, etc.).

The correction unit 134 calculates a click rate (selection operation rate) based on the corrected number of clicks. Thereby, the click rate can be calculated based on the weighted number of clicks.

The correction unit 134 calculates a conversion rate (implementation rate of predetermined action) based on the corrected number of clicks. Thereby, the conversion rate can be calculated based on the weighted number of clicks.

[7. others〕
Although the embodiments of the present application have been described above, the present invention is not limited by the contents of these embodiments. In addition, the components described above include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those within the so-called equivalent range. Furthermore, the components described above can be combined as appropriate. Furthermore, various omissions, replacements, or modifications of components can be made without departing from the gist of the above-described embodiments.

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

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions.

For example, the information processing apparatus 100 described above may be implemented by a plurality of server computers, and depending on the function, the configuration may be flexibly changed, such as by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing content.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the reception unit can be read as reception means or a reception circuit.

1 information processing system 10 advertiser terminal 20 terminal device 30 information providing device 100 information processing device 121 user information storage unit 122 advertisement content storage unit 130 control unit 131 reception unit 132 distribution unit 133 estimation unit 134 correction unit

Claims (11)

an estimating unit that estimates the user's context up to the selection operation of the advertisement content;
An information processing apparatus, comprising: a correction unit that corrects the number of selection operations by weighting the selection operations of the user with a correction amount that differs depending on the context of the user for each advertisement content. 2. The information processing apparatus according to claim 1, wherein the estimation unit estimates the context of the user from past history information of the user who selected and operated the advertising content. 3. The information processing apparatus according to claim 1, wherein the estimation unit estimates a temporal context when the user selects the advertising content. 4. The information processing apparatus according to any one of claims 1 to 3, wherein the estimation unit estimates a positional context when the user selects the advertising content. 5. The information processing apparatus according to any one of claims 1 to 4, wherein the estimation unit estimates whether or not the user is traveling as the context of the user. 6. The information processing apparatus according to any one of claims 1 to 5, wherein the estimation unit estimates whether or not the user is moving as the context of the user. The correction unit weights the user's selection operation with a correction amount according to the relationship between the user's context and the advertising content selected by the user, thereby correcting the number of selection operations. The information processing apparatus according to any one of claims 1 to 6. The information processing apparatus according to any one of claims 1 to 7, wherein the correction unit calculates a selection operation rate based on the corrected number of selection operations. The information processing apparatus according to any one of claims 1 to 8, wherein the correction unit calculates an implementation rate of a predetermined action based on the corrected number of selection operations. An information providing method executed by an information providing device,
an estimation step of estimating the user's context up to the selection operation of the advertising content;
and a correction step of correcting the number of selection operations by weighting the selection operations of the user with a correction amount that differs depending on the context of the user for each advertisement content. an estimation procedure for estimating the user's context up to the selection operation of the advertising content;
an information processing program for causing a computer to execute a correction procedure for correcting the number of selection operations by weighting the user's selection operations with a correction amount that differs for each advertisement content according to the user's context .

Images