Analysis server, advertisement distribution system, terminal, analysis method and program

Abstract

To provide a technology for improving the accuracy of extracting users to which an advertisement is delivered.SOLUTION: An analysis server includes: means for calculating a degree of contribution which is given by a user's feature quantity to a magnitude of a difference, on the basis of the user's feature quantity and a difference between an index value indicating the user's level of interest in an object of an advertisement when the advertisement is delivered and an index value indicating the user's level of interest in the object of the advertisement when the advertisement is not delivered; and means for extracting a feature quantity for which the degree of contribution satisfies a predetermined condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an analysis server, an advertisement distribution system, a terminal device, an analysis method, and a program. [Background technology]

[0002] Advertising plays an important role in providing products and services to consumers. Patent Document 1 discloses an advertising effectiveness prediction system that builds a prediction model by learning training data that associates known advertisements with consumer response information to those advertisements, inputs unknown advertisements into this prediction model, and predicts consumer response information to the unknown advertisements. This system can be used to predict the effectiveness of an advertisement before it is distributed, and by making modifications to achieve the desired effect, it is possible to create an advertisement that increases consumer purchasing motivation. In order to increase advertising effectiveness, it is important not only to improve the content of the advertisement, but also to determine the target audience to which the advertisement is distributed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-144916 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present disclosure is to provide an analysis server, an advertisement delivery system, a terminal device, an analysis method, and a program that can improve the accuracy of extracting users who are the targets of advertisement delivery.

[0005] Therefore, an object of the present invention is to provide an analysis server, an advertisement distribution system, a terminal device, an analysis method, and a program that solve at least part of the above-mentioned problems. [Means for solving the problem]

[0006] According to one aspect of the present invention, the analysis server includes means for calculating, based on a user's feature value and a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, the degree of contribution that the user's feature value makes to the magnitude of the difference; and means for extracting the feature value whose degree of contribution satisfies a predetermined condition.

[0007] According to one aspect of the present invention, an advertising delivery system includes the above-described analysis server, a delivery server including means for receiving an advertising delivery request, means for identifying advertising targets that match at least one feature based on the feature extracted for each of the candidate targets of the advertising to be delivered in response to the delivery request, the feature having a contribution level that satisfies a predetermined condition, as the advertising targets to be delivered to the user, and means for delivering the advertising identified by the identification means.

[0008] According to one aspect of the present invention, a terminal device receives an advertisement transmitted by the above-described advertisement distribution system.

[0009] According to one aspect of the present invention, an analysis method is an analysis method executed by a computer, and includes the steps of: calculating a degree of contribution that the user's feature value makes to the magnitude of a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, based on the user's feature value; and extracting the feature value whose contribution degree satisfies a predetermined condition.

[0010] According to one aspect of the present invention, the program causes a computer to function as a means for calculating the degree of contribution that the user's feature values ​​make to the magnitude of the difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, based on the user's feature values, and a means for extracting the feature values ​​whose degree of contribution satisfies a predetermined condition. [Effects of the Invention]

[0011] According to the present invention, it is possible to improve the accuracy of extracting users who are the targets of advertisement distribution. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram illustrating an example of an advertisement distribution system according to an embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of a purchase record table according to the embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a purchase prediction model according to the embodiment. [Figure 4] FIG. 10 is a diagram illustrating an example of a calculation result of a purchase probability according to the embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of a difference in purchase probability between a case where advertisement delivery is performed and a case where advertisement delivery is not performed according to the embodiment. [Figure 6] FIG. 10 is a diagram illustrating an example of a contribution model according to the embodiment. [Figure 7] 10 is a flowchart illustrating an example of a process for analyzing a feature amount that contributes to an advertising effect according to the embodiment. [Figure 8A] 10 is a flowchart illustrating an example of an advertisement distribution process according to the embodiment. [Figure 8B] 10 is a flowchart illustrating an example of a process for delivering a point-added advertisement according to the embodiment. [Figure 9] FIG. 10 is a diagram illustrating an example of a purchase probability table according to the embodiment. [Figure 10]FIG. 1 is a diagram illustrating an example of a hardware configuration of an advertisement delivery system according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] <Embodiment> (System Configuration) FIG. 1 is a block diagram illustrating an example of an advertisement distribution system according to an embodiment. The advertisement distribution system 1 includes a user terminal 10, a DB server 20, an advertising medium server 30, a purchase management server 40, and an analysis server 50. The user terminal 10, the DB server 20, the advertising medium server 30, the purchase management server 40, and the analysis server 50 are communicatively connected via a network NW.

[0014] The user terminal 10 is a terminal device such as a smartphone or a PC (personal computer). The user terminal 10 is used by a user who can purchase products and services by using an online shopping mall provided by the purchase management server 40 or advertisements provided by the advertising medium server 30. For example, when a user operates the user terminal 10 and logs in to the advertising medium server 30 or the purchase management server 40 using their own account information, advertisements appropriate for the user are delivered to the user terminal 10. When a user views or clicks on an advertisement displayed on the user terminal 10, the history is recorded in the advertising medium server 30 in association with the user ID of the user. Furthermore, when a user operates the user terminal 10 to purchase a product at an online shopping mall, the purchase history is recorded in the purchase management server 40 in association with the user ID.

[0015] The DB server 20 (DB is an abbreviation for database) includes a user information management DB 21. The DB server 20 writes various information to the user information management DB 21 and reads various information from the user information management DB 21. The DB server 20 transmits the read information to the analysis server 50, etc. The user information management DB 21 stores personal information of users who use the advertising medium server 30 or the purchase management server 40, such as their names, ages, genders, addresses, email addresses, and telephone numbers, as well as various feature quantities that represent the characteristics of the users, in association with their user IDs. The user feature quantities include demographic information such as the age and gender of each user, and user attribute information such as hobbies, preferences, and tendencies. The user attribute information includes actual attributes and estimated attributes estimated from other user attribute information. The user information management DB 21 may also store, for each user ID and product, an ad delivery history, the number of times an ad is displayed, the number of times an ad is clicked, and a product purchase history. Furthermore, different user IDs may be assigned to the same user for each advertising medium server 30, purchase management server 40, and store in a shopping mall provided by purchase management server 40, and the association of these multiple user IDs may be set in user information management DB 21. In the following description, the term "user ID" is used to refer to the identification information of one user collectively, rather than to refer to each of these different IDs individually.

[0016] The advertising medium server 30 is, for example, a web server that provides a place where advertisements for various products and services are posted. The places where advertisements are posted include, for example, web pages such as news sites and blogs, which are called advertising media. The advertising medium server 30 logs in to the advertising medium server 30 and transmits the ID of a user who is viewing a medium and various advertisements contained therein to the analysis server 50 to request advertisement distribution. In response to this request, the analysis server 50 selects an advertisement to distribute to the user ID and distributes the selected advertisement. The advertising medium server 30 then displays the distributed advertisement in a predetermined position on the advertising medium. The advertising medium server 30 may also store log information (advertisement distribution history) for each user ID, such as when an advertisement was distributed, how many times it was distributed, and advertisement impression information, such as whether the user viewed or clicked on the advertisement. Note that some advertisements offer points, which give points to users who view the advertisement. The advertising medium server 30 can display point-off advertisements on advertising media. For example, when a user logs in to the advertising medium server 30, the analysis server 50 determines whether an advertisement with points is effective for the user, and if it is determined to be effective, delivers the advertisement with points. When the user views the advertisement with points, the advertising medium server 30 may perform point management, such as awarding points to the user.

[0017] The purchase management server 40 manages an online shopping mall. For example, in response to a request from the user terminal 10, the purchase management server 40 transmits web pages listing products and processes product purchases. The purchase management server 40 manages log information (purchase history) that records which product web pages users have accessed and the purchases they made. Based on this log information, the purchase management server 40 can analyze, for each user ID, the number of times a product web page has been accessed and the number of times the product was purchased. The purchase management server 40 also logs in to the purchase management server 40 and transmits the user ID of a user who is considering purchasing a product to the analysis server 50, requesting the delivery of an advertisement. In response to this request, the analysis server 50 selects an advertisement to deliver to the user ID and delivers the selected advertisement. The purchase management server 40 then displays the delivered advertisement in a predetermined position on the web page listing the product.

[0018] The analysis server 50 analyzes user features that contribute to the magnitude of advertising effectiveness. Advertising effectiveness refers to the degree to which an advertisement stimulates interest in a product, such as when a user who receives the advertisement purchases the advertised product or accesses the product's purchase page. The magnitude of advertising effectiveness refers to the degree to which interest increases in that case. In the following description, as an example, the difference between the purchase probability with and without advertisement delivery is used as an indicator of advertising effectiveness. For example, the analysis server 50 analyzes, for a certain product advertisement, what features a user possesses that will lead them to purchase or become interested in the product as a result of the advertisement. Furthermore, based on the analysis results of the user features that contribute to the magnitude of advertising effectiveness, the analysis server 50 determines (selects) a product that matches the features of the user who sent the advertisement distribution request by logging in to the advertisement management server 30, etc., and distributes the advertisement for that product. In other words, the analysis server 50 determines the users to whom the advertisement will be distributed based on the analysis results. The analysis server 50 includes an input receiving unit 51 , a control unit 52 , and a storage unit 53 .

[0019] The input accepting unit 51 accepts information entered into the analysis server 50 using an input device such as a keyboard or a mouse, or information transmitted from another device via the communication unit 54. The input accepting unit 51 outputs the accepted information to the control unit 52 or records it in the memory unit 53. For example, the input accepting unit 51 accepts the specification of a product or the like for which user features that contribute to the magnitude of advertising effectiveness are to be analyzed. The input accepting unit 51 also accepts an advertisement delivery request from the advertising medium server 30. The input accepting unit 51 also accepts the user IDs of users to whom advertisements are to be delivered from the advertising medium server 30 or the purchase management server 40.

[0020] The control unit 52 controls the analysis process of user features that contribute to the magnitude of advertising effectiveness and the distribution process of advertisements based on the analysis results. The control unit 52 includes a purchase probability prediction unit 521, a contribution analysis unit 522, a distribution determination unit 523, and an advertisement distribution unit 524.

[0021] The purchase probability prediction unit 521 predicts the probability that a user will purchase a product. The purchase probability prediction unit 521 predicts the probability that a user will purchase a product based on the past purchase records of multiple users for a product when an advertisement for the product was delivered and when an advertisement for the product was not delivered. FIG. 2 shows an example of a purchase record table for a product. As shown in the figure, the purchase record table 200 has items such as a user ID, multiple feature values ​​such as age, whether an advertisement was delivered, and whether a product was purchased. For example, a user with a user ID of 001 is 21 years old, has received an advertisement, and has purchased a product. The feature values ​​include age, gender, area of ​​residence, and what products the user has purchased in the past. The purchase record table 200 is stored in the storage unit 53. For example, the purchase probability prediction unit 521 may request the feature values, the number of times an advertisement for the target product was delivered, and the product purchase history for all users stored in the user information management DB 21 from the DB server 20, and store this information in the purchase record table 200 in the storage unit 53. Alternatively, the purchase probability prediction unit 521 may acquire information from the advertising media server 30 that can determine whether or not an advertisement for a target product has been delivered for each user ID (e.g., advertisement delivery history, number of deliveries, advertisement impression information, etc.), acquire information on the purchase history of the target product for each user ID from the purchase management server 40, determine whether or not an advertisement has been delivered and whether or not the user has a purchase history based on the acquired information, and store the determination result in the purchase history table 200. In this case, users without advertisement impression information, etc. may be classified as users without advertisement delivery. The purchase probability prediction unit 521 uses the information stored in the purchase history table 200 as training data to create a purchase prediction model in which the user's features and whether or not an advertisement has been delivered are explanatory variables and the product purchase probability is a target variable. An example of the purchase prediction model is shown in FIG. 3. The purchase probability prediction unit 521 constructs a purchase prediction model 531 by machine learning or the like, which receives the user's features and whether or not an advertisement has been delivered and outputs the probability of purchasing the product. For example, the purchase probability prediction unit 521 calculates the purchase probability with and without advertisement delivery for all users stored in the purchase history table 200 using the purchase prediction model 531. An example of the calculation result is shown in FIG.Figure 4(a) shows the purchase probability for a certain product with ad delivery, and Figure 4(b) shows the purchase probability without ad delivery. For example, for a user with user ID 101, the purchase probability with ad delivery is 0.81, and the purchase probability without ad delivery is 0.54.

[0022] By creating the purchase prediction model 531 illustrated in FIG. 3 , it is possible to predict the purchase probability of a user who has never purchased a product based on the user's features. For a user who has purchased a product, the purchase probability may be predicted as follows. For example, the purchase probability prediction unit 521 acquires information on the number of times a product advertisement was delivered to the user and the number of times the advertisement was delivered that the user purchased the product. The purchase probability prediction unit 521 acquires the number of advertisement deliveries from the advertising media server 30 and compares this with information on the purchase date and time of the product acquired from the purchase management server 40. For example, if the product was purchased within a predetermined time after the advertisement delivery and this advertisement delivery is the third advertisement delivery, the purchase probability prediction unit 521 determines that the user purchased the product at the third advertisement delivery. Alternatively, if there is log information indicating that the advertisement was clicked at the third advertisement delivery and a purchase was subsequently made, the purchase probability prediction unit 521 determines that the user purchased the product at the third advertisement delivery. In this case, the purchase probability prediction unit 521 predicts the purchase probability at the time of advertisement delivery to be 1 / 3. Furthermore, purchase probability prediction unit 521 acquires log information stored in purchase management server 40, and calculates the purchase probability in the absence of ad delivery based on information regarding the number of times a user has logged in to purchase management server 40 and accessed the product in question at the online shopping mall and the number of accesses required to purchase the product. For example, if a user purchases the product on their fifth access, purchase probability prediction unit 521 predicts that the purchase probability in the absence of ad delivery will be 1 / 5.

[0023] The contribution analysis unit 522 analyzes user features that contribute to the magnitude of the advertising effectiveness. The contribution analysis unit 522 analyzes user features that affect the magnitude of the difference in purchase probability between cases with and without ad delivery (difference = "purchase probability with ad delivery" - "purchase probability without ad delivery") and extracts features that contribute significantly to the difference. A large difference in purchase probability between cases with and without ad delivery can be considered to be due to the advertisement promoting the purchase. Therefore, user features that contribute to the large difference can be said to be user features that contribute to the magnitude of the advertising effectiveness. For example, the contribution analysis unit 522 calculates the data in the table illustrated in FIG. 5 and creates a learning model using machine learning, with the user features as explanatory variables and the difference in purchase probability between cases with and without ad delivery predicted by the purchase probability prediction unit 521 as the objective variable. By performing a SHAP analysis on the created trained model, the contribution (contribution rate) of each user feature to the magnitude of the difference is calculated. A model that indicates user features that contribute to the magnitude of the advertising effectiveness is called a contribution model. An example of a contribution model is shown in FIG. 6. The vertical axis of FIG. 6 represents the feature amount of a user, and the horizontal axis represents the absolute value of the SHAP value. The contribution analysis unit 522 extracts feature amounts whose contribution value is equal to or greater than a predetermined value, and registers the extracted feature amounts in the storage unit 53. Alternatively, the contribution analysis unit 522 may arrange the feature amounts in descending order of contribution, extract a predetermined number of feature amounts from the top, and register them in the storage unit 53. The feature amounts of a user that contribute to the magnitude of the advertising effectiveness, extracted by the contribution analysis unit 522, may be registered in the user information management DB 21 for each product. In the case of the contribution model 532 illustrated in FIG. 6, the contribution analysis unit 522 extracts feature amount 1 and feature amount 2 as feature amounts of a user that contribute to the magnitude of the advertising effectiveness.

[0024] The method for calculating the contribution is not limited to SHAP analysis. For example, the correlation coefficient between each user feature and the difference may be calculated, and feature values ​​with a correlation coefficient value equal to or greater than a threshold value may be extracted. Alternatively, data with a difference magnitude equal to or greater than a predetermined value may be extracted from the difference data for each user illustrated in FIG. 5, information on the user feature corresponding to the extracted data may be aggregated, and the frequency of appearance of the user feature may be counted as the contribution. For example, in a data group with a difference magnitude equal to or greater than a predetermined value for a certain product α, if the frequency of appearance of data with the feature "age in 20s" is equal to or greater than a predetermined number of times or if the frequency of appearance of data with the feature "has purchased related product β in the past" is equal to or greater than a predetermined number of times, the contribution analysis unit 522 may extract the feature "age in 20s" and the feature "has purchased related product A in the past" as feature values ​​with high contribution.

[0025] Here, we have calculated the difference in purchase probability between cases with and without ad delivery. However, instead of calculating the purchase probability, it is also possible to use other actions that can confirm that a user has become interested in a product due to an advertisement, such as the probability of accessing a web page on which the product is posted or the probability of downloading a catalogue about the product or requesting information or making an inquiry, as indicator values ​​to calculate the difference in the probability of accessing a web page for purchasing a product between cases with and without ad delivery, and analyze the feature quantities that have a strong influence on the magnitude of this difference.

[0026] The distribution determination unit 523 determines products for which advertisements are to be distributed. For example, upon receiving an advertisement distribution request from the advertising medium server 30 or the like, the distribution determination unit 523 compares the user feature associated with the user ID with the user feature that contributes to the magnitude of the advertisement effect extracted by the contribution analysis unit 522, selects one or more products for which the feature associated with the user ID matches the feature extracted by the contribution analysis unit 522, and determines to distribute an advertisement for a specific product from among the selected products. In the above example, if user A is in his twenties and has previously purchased product β, the distribution determination unit 523 determines to distribute an advertisement for product α to user A. If user A is in his thirties and has not previously purchased product β, the distribution determination unit 523 determines not to distribute an advertisement for product α to user A. Note that, when there are multiple contributions extracted by the contribution analysis unit 522, for example, the decision on whether to distribute an advertisement can be arbitrarily set according to the magnitude of the contribution of each feature. For example, if the contribution of "has purchased related product A in the past" is particularly high (large SHAP value, large correlation coefficient, frequent appearance) among the features "age is in their 20s" and "has purchased related product A in the past" and the contribution of "has purchased related product A in the past" is not so high in comparison, the system may be configured to deliver an advertisement for product α to users who have the feature "has purchased related product A in the past" even if they are not in their 20s, or to users who are in their 20s and do not have the feature "has purchased related product A in the past," an advertisement for product α may be delivered, for example, once in three times. Also, if there are multiple candidate products to be delivered in response to a request for advertisement delivery received from the advertising medium server 30, etc., and there are user features that match the multiple products, the delivery determination unit 523 determines to deliver an advertisement for the product from which the user feature with the highest or highest contribution has been extracted.For example, suppose that feature 1 is registered in the storage unit 53 as a feature with a high degree of contribution for product α1, feature 2 is registered as a feature with a high degree of contribution for product α2, and feature 3 is registered as a feature with a high degree of contribution for product α3, and the relationship of the magnitudes of the respective contributions (e.g., SHAP values) is such that the contribution of feature 1 > the contribution of feature 2 > the contribution of feature 3. When products α1 to α3 are targets for advertisement distribution and user A1 has all of features 1 to 3, the distribution determination unit 523 decides to distribute an advertisement for product α1 corresponding to feature 1, which has the highest degree of contribution. When user A2 has features 2 to 3, the distribution determination unit 523 decides to distribute an advertisement for product α2 corresponding to feature 2 to user A2.

[0027] The advertisement distribution unit 524 distributes to the user terminal 10 the advertisement for the product that the distribution determination unit 523 has determined to be distributed.

[0028] The storage unit 53 stores various types of information. For example, the storage unit 53 stores a purchase prediction model 531 and a contribution model 532.

[0029] (operation) (1) Feature analysis that contributes to advertising effectiveness Next, the operation of the advertisement distribution system 1 will be described. FIG. 7 is a flowchart illustrating an example of a process for analyzing a feature amount that contributes to an advertising effect according to the embodiment.

[0030] The input receiving unit 51 receives the designation of a product (step S1). The entity that inputs the designation information of the product to be analyzed to the analysis server 50 may be an advertiser, a product provider, a person requesting product analysis, an analyst of advertising effectiveness, an administrator of the analysis server, etc. Furthermore, multiple products may be designated. When multiple products are designated, the processes of steps S2 to S5 are executed for each product.

[0031] Next, the purchase probability prediction unit 521 creates a purchase prediction model (step S2). The purchase probability prediction unit 521 creates a purchase prediction model 531 (FIG. 3) that predicts the purchase probability for the product specified in step S1 based on the user's feature amount and whether or not an advertisement is distributed.

[0032] Next, the purchase probability prediction unit 521 makes a purchase prediction (step S3). The purchase probability prediction unit 521 inputs the feature quantities of many users and the presence or absence of advertisement delivery into the purchase prediction model 531 created in step S2, and predicts the purchase probability with advertisement delivery and the purchase probability without advertisement delivery for each user (FIG. 4).

[0033] Next, the contribution analysis unit 522 creates a contribution model (step S4). From the prediction results of step S3, the contribution analysis unit 522 calculates the difference between the purchase probability for each user when advertisements are delivered and when advertisements are not delivered, and calculates the data shown in Fig. 5. The contribution analysis unit 522 analyzes the feature amounts that contribute to the magnitude of the calculated difference using SHAP analysis or the like, and creates a contribution model 532 (Fig. 6).

[0034] Next, the contribution analysis unit 522 extracts and registers feature quantities that contribute highly to the advertising effectiveness (step S5). For example, the contribution analysis unit 522 refers to the contribution model 532 to extract feature quantities whose contribution levels (e.g., absolute values ​​of SHAP values) are equal to or greater than a predetermined threshold, and registers the extracted feature quantities in the storage unit 53, the user information management DB 21, or the like, in association with the products specified in step S1. Note that information on the user feature quantities that contribute highly to the advertising effectiveness extracted for each product may be provided to advertisers, product providers, product analysis clients, etc. For example, the contribution analysis unit 522 may output the extraction results of step S5 to an electronic file, etc., and transmit this electronic file to advertisers, product providers, product analysis clients, etc.

[0035] (2) Ad delivery operations FIG. 8A is a flowchart illustrating an example of an advertisement distribution process according to the embodiment. It is assumed that a user to whom an advertisement is to be delivered is logged in to the advertising medium server 30 or the purchase management server 40. Furthermore, it is assumed that for the advertisement to be delivered, user features that contribute highly to the effectiveness of the advertisement are analyzed in advance by the process illustrated in FIG. 7, and the results are registered in the storage unit 53. The input receiving unit 51 receives a request for advertisement delivery from the advertising medium server 30 or the like (step S11). The request for advertisement delivery may be transmitted, for example, when a user logs in to the advertising medium server 30 or the purchase management server 40, or when an advertisement space is displayed on a web page accessed by the user operating the user terminal 10. The request for advertisement delivery includes a user ID and a type of advertisement medium. The input receiving unit 51 outputs a notification that the advertisement delivery request has been received to the control unit 52. In the control unit 52, the delivery determination unit 523 determines a product to be advertisement-delivered (step S12). The delivery determination unit 523 refers to the user information management DB 21 using the user ID included in the advertisement delivery request and acquires various features registered in association with the user ID. The delivery determination unit 523 also reads from the storage unit 53 user features that have a high contribution to advertising effectiveness and are registered in association with the product to be advertisement-delivered. Each product registered in the storage unit 53 in association with a user feature that has a high contribution to advertising effectiveness is a candidate for advertisement delivery. The distribution decision unit 523 compares the feature acquired from the user information management DB21 with the feature read from the storage unit 53, and if there is a feature that matches the two, decides to distribute an advertisement for the product. If there is no advertisement for the product with a matching feature, the distribution decision unit 523 decides not to distribute the advertisement. If it is decided not to distribute the advertisement (there is no product to be advertised) (step S13; No), the processing of FIG. 8A is terminated. If it is decided to distribute the advertisement (step S13; Yes), the distribution decision unit 523 instructs the advertisement distribution unit 524 to distribute an advertisement for the determined product. If there is one product whose feature matches the user's feature and the feature extracted for the product to be advertised, the distribution decision unit 523 instructs the advertisement distribution unit 524 to distribute an advertisement for that product. If there are multiple products whose features match the user's features and the extracted features for the products, the distribution decision unit 523 identifies a product for which an advertisement should be distributed from among the multiple products, and instructs the advertisement distribution unit 524 to distribute an advertisement for the identified product.For example, the distribution determination unit 523 may specify a product corresponding to the feature with the highest contribution as the product to be advertised, or may specify a product having the largest number of feature quantities matching the user's feature quantities (a product having the largest number of feature quantities matching when a plurality of feature quantities with high advertising effectiveness associated with the product are compared with a plurality of feature quantities possessed by the logged-in user) as the product to be advertised. The advertisement distribution unit 524 distributes the advertisement (step S14). The advertisement distribution unit 524 distributes the advertisement for the product specified by the distribution determination unit 523. The user terminal 10 receives the transmitted advertisement and outputs it to the display unit.

[0036] (2´) Point-based advertisement distribution process 8A, only a determination is made as to whether to send an advertisement, but if it is determined that an advertisement should be delivered, a further determination may be made as to whether an advertisement with points should be delivered or an advertisement without points. The processing in this case will be described with reference to FIG. 8B. It is assumed that users to whom advertisements are to be delivered are logged in to the advertising medium server 30 or the purchase management server 40. Furthermore, for the advertisements to be delivered, user features that contribute highly to advertising effectiveness are analyzed in advance by the process illustrated in FIG. 7, and the results are registered in the storage unit 53. Furthermore, it is assumed that a purchase probability table 201 (FIG. 9), which will be described later, is registered in the storage unit 53. Note that steps S11 to S13 are similar to the processes described in FIG. 8A, and will be explained briefly.

[0037] The input receiving unit 51 receives a request for advertisement distribution from the advertising medium server 30 (step S11). Next, the distribution determining unit 523 determines a product for which advertisement distribution is to be performed (step S12). If it is determined that an advertisement will not be distributed (there is no product for which advertisement distribution is to be performed) (step S13; No), the processing of FIG. 8B is terminated. If it is determined that an advertisement will be distributed (step S13; Yes), the distribution determining unit 523 determines whether to distribute an advertisement with points or an advertisement without points (step S141). For example, the memory unit 53 stores a purchase probability table 201 illustrated in FIG. 9. As illustrated, the purchase probability table 201 registers, for a certain product, the purchase probability in the case where no advertisement distribution is performed, the purchase probability in the case where an advertisement distribution with points is performed, and the purchase probability in the case where an advertisement distribution without points is performed, for each user ID. For example, instead of the purchase history table 200 illustrated in FIG. 2, in the column for whether or not an advertisement is delivered in the purchase history table 200, an option of "2: With point-bearing advertisement delivery" is added in addition to "0: No advertisement delivery" and "1: With advertisement delivery", and a table is prepared that records for each user whether the product was purchased in the case of "0: No advertisement delivery", "1: With advertisement delivery" (equivalent to "without point-bearing advertisement delivery"), or "2: With point-bearing advertisement delivery", and the purchase probability prediction unit 521 creates a purchase prediction model 531' with the user's features and whether or not advertisement delivery was delivered (the above flags 0 to 2) as explanatory variables and the purchase probability as a target variable. The purchase probability prediction unit 521 inputs the characteristics of the user with user ID=101 and the above flag "0" into this purchase prediction model 531', calculates the purchase probability (1.0%) when no advertisements are delivered, inputs the characteristics of the user with user ID=101 and the above flag "1" to calculate the purchase probability (1.5%) when advertisements without points are delivered, inputs the characteristics of the user with user ID=101 and the above flag "2" to calculate the purchase probability (2.5%) when advertisements with points are delivered, and registers these values ​​in the purchase probability table 201.Similarly, for other users such as user ID=102, 103, the purchase probability prediction unit 521 uses the purchase prediction model 531′ to predict the purchase probability in the cases where no advertisement is delivered, where no advertisement without points is delivered, and where an advertisement with points is delivered, and registers the predicted purchase rates in the purchase probability table 201. The purchase probability table 201 illustrated in Fig. 9 is a table created in advance in this manner.

[0038] The distribution determination unit 523 refers to the purchase probability table 201 and determines whether to distribute an advertisement with points or an advertisement without points (step S141). For example, if the purchase probability when an advertisement with points is distributed is greater than the purchase probability when an advertisement without points is distributed by a predetermined value or more, the distribution determination unit 523 determines to distribute an advertisement with points; otherwise, the distribution determination unit 523 determines to distribute an advertisement without points. For example, in the example of FIG. 9, if the user to whom the advertisement is distributed is a user with user ID = 101, the distribution determination unit 523 determines to distribute an advertisement with points, and if the user to whom the advertisement is distributed is a user with user ID = 102, the distribution determination unit 523 determines to distribute an advertisement without points. If it is determined to distribute an advertisement with points (step S141; Yes), the distribution determination unit 523 instructs the advertisement distribution unit 524 to distribute an advertisement with points for the product determined in step S13. The advertisement distribution unit 524 distributes an advertisement with points for the instructed product (step S15). If it is determined that an advertisement without points is to be distributed (step S141; No), the distribution determination unit 523 instructs the advertisement distribution unit 524 to distribute an advertisement without points for the product determined in step S13. The advertisement distribution unit 524 distributes the advertisement without points for the instructed product (step S16). The user terminal 10 receives the transmitted advertisement and outputs it on the display unit.

[0039] In the processing of step S141 in FIG. 8B, a determination is made as to whether to deliver an advertisement with points or an advertisement without points based on the purchase probability table 201 illustrated in FIG. 9. However, for example, difference 1 (1.5%) obtained by subtracting the purchase probability when an advertisement with points is delivered in the purchase probability table 201 (2.5% for user ID=101) from the purchase probability when no advertisement is delivered (1.0% for user ID=101), and difference 2 (0.5%) obtained by subtracting the purchase probability when an advertisement without points is delivered (1.5% for user ID=101) from the purchase probability when no advertisement is delivered (1.0% for user ID=101), may be calculated for all users, and the contribution analysis unit 522 may analyze the user features that contribute to the magnitude of difference 1 and the user features that contribute to the magnitude of difference 2 using SHAP analysis or the like, and determine whether to deliver an advertisement with points or an advertisement without points based on the analysis results. For example, if the analysis by the contribution analysis unit 522 reveals that the features that contribute to the magnitude of difference 1 (advertising effectiveness of the advertisement with points) for the product are feature 1 and feature 2, and the features that contribute to the magnitude of difference 2 (advertising effectiveness of the advertisement without points) are feature 1 and feature 3, and if a user to whom the advertisement is to be delivered has feature 1 and feature 2, the delivery decision unit 523 decides to deliver the advertisement with points.

[0040] (effect) As described above, according to this embodiment, it is possible to calculate the feature amounts of users that contribute to the magnitude of advertising effectiveness. This makes it possible to improve the accuracy of extracting users to whom advertisements are to be delivered when delivering advertisements. Specifically, users having feature amounts of users that contribute to the magnitude of advertising effectiveness are extracted as users to whom advertisements are to be delivered. This makes it possible to deliver advertisements to users for whom the advertising effect is high. Since advertisements and users are matched based on the feature amounts of the users, it is possible to provide advertisements that are suitable for new users even for whom there is no data, such as past product purchase history.

[0041] In the above embodiment, the user features that contribute to the magnitude of advertising effectiveness for each product or service are analyzed. However, the user features that contribute to the magnitude of advertising effectiveness for each product or service category may also be calculated. For example, the user features that contribute to the magnitude of advertising effectiveness when a food advertisement is delivered may be analyzed based on purchase history data when an advertisement for a food product is delivered and purchase history data when an advertisement for a food product is delivered without delivery of the advertisement. Alternatively, the user features that contribute to the magnitude of advertising effectiveness may be analyzed for each store or manufacturer that provides the product or service. In the above embodiment, when an advertisement delivery request is received from the advertising medium server 30 or the like, the analysis server 50 determines a specific product from at least one or more candidate products to be delivered to the medium based on the received medium and user information, and delivers an advertisement for the product. However, the advertising medium server 30 may specify a product and request the analysis server 50 to deliver an advertisement for the product, and the analysis server 50 may determine whether to deliver an advertisement for the product. More specifically, the delivery determination unit 523 refers to the user information management DB21 using the user ID included in the request for advertisement delivery, acquires various feature amounts registered in association with the user ID, reads from the storage unit 53 user feature amounts that have a high contribution to the advertising effect and are registered in association with the product to be advertised, compares the feature amounts acquired from the user information management DB21 with the feature amounts read from the storage unit 53, and if the two match (for example, if at least one feature amount matches, or if a predetermined number or more of the feature amounts match), decides to deliver the advertisement, and if the feature amounts do not match, may decide not to deliver the advertisement for the requested product. If it is decided to deliver the advertisement, the delivery determination unit 523 instructs the advertisement delivery unit 524 to deliver the advertisement for the requested product.

[0042] In the above embodiment, the user feature that contributes to the magnitude of advertising effectiveness for each product or service is analyzed. However, if there are multiple types of advertisements for one product, the user feature that contributes to the magnitude of advertising effectiveness for each advertisement may be analyzed, and an advertisement whose feature of the advertisement delivery target user matches the feature of the advertisement with a high advertising effectiveness may be delivered. For example, suppose there are three types of advertisements γ1 to γ3 for product α, and the feature with a high advertising effectiveness for advertisement γ1 is feature 1, the feature with a high advertising effectiveness for advertisement γ2 is feature 2, and the feature with a high advertising effectiveness for advertisement γ3 is feature 3. Furthermore, if the feature possessed by user A1, who is the advertisement delivery target, is feature 1, and the feature possessed by user A2 is feature 2, the delivery determination unit 523 determines to deliver advertisement γ1 to user A1 and advertisement γ2 to user A2.

[0043] 1, the analysis server 50 is provided with the advertisement distribution unit 524, but the advertisement distribution server may be provided as a server device separate from the analysis server 50. In this configuration, the function of the distribution determination unit 523 may be implemented in the advertisement distribution server, and the user features with a high degree of contribution to advertising effectiveness extracted for each product by the contribution analysis unit 522 may be registered in the advertisement distribution server.

[0044] FIG. 10 is a diagram illustrating an example of the hardware configuration of an advertisement delivery system according to an embodiment. The computer 900 includes a CPU 901, a main storage device 902, an auxiliary storage device 903, an input / output interface 904, and a communication interface 905. The above-described user terminal 10, DB server 20, advertising medium server 30, purchase management server 40, and analysis server 50 are implemented in the computer 900. The above-described processes are stored in the auxiliary storage device 903 in the form of a program. The CPU 901 reads the program from the auxiliary storage device 903, loads it into the main storage device 902, and executes the above-described processes in accordance with the program. The CPU 901 also allocates a memory area in the main storage device 902 in accordance with the program. The CPU 901 also allocates a memory area in the auxiliary storage device 903 for storing data being processed in accordance with the program.

[0045] In at least one embodiment, the auxiliary storage device 903 is an example of a non-transitory tangible medium. Other examples of non-transitory tangible media include a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, and a semiconductor memory connected via the input / output interface 904. Furthermore, when this program is distributed to the computer 900 via a communication line, the computer 900 that receives the program may load the program into the main storage device 902 and execute the above-described processing. The program may also be for realizing part of the above-described functions. Furthermore, the program may be a so-called differential file (differential program) that realizes the above-described functions in combination with another program already stored in the auxiliary storage device 903.

[0046] In addition, the components in the above-described embodiments can be replaced with well-known components as appropriate without departing from the spirit of the present invention. Furthermore, the technical scope of the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention.

[0047] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0048] (Appendix 1) The analysis server includes: a means (contribution analysis unit 522) for calculating the degree of contribution that the user's feature value makes to the magnitude of the difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, based on the user's feature value; and a means (contribution analysis unit 522) for extracting the feature value whose contribution satisfies a predetermined condition.

[0049] (Appendix 2) The analysis server described in Appendix (1) further comprises: means for receiving an advertisement delivery request (input receiving unit 51); means for identifying a target of the advertisement to be delivered to the user based on the characteristics of the user to whom the advertisement will be delivered based on the delivery request and the characteristics extracted for each of the candidate targets of the advertisement to be delivered in response to the delivery request, the contribution level of which satisfies a predetermined condition (delivery determination unit 523); and means for delivering the advertisement identified by the identification means (advertisement delivery unit 524). The means for specifying the advertisement target may specify the advertisement target having at least one matching feature amount as the advertisement target to be delivered to the user.

[0050] (Appendix 3) When the identifying means identifies a plurality of targets of the advertisement having at least one feature that matches the feature of the user, the means for delivering the advertisement (advertising delivery unit 524) delivers an advertisement related to the target of the advertisement from which the feature with the greatest contribution degree was extracted among the matching features, which is the analysis server described in Appendix (2).

[0051] (Appendix 4) The analysis server according to Supplementary Notes (2) to (3) further comprises a means (purchase probability prediction unit 521) for acquiring, in the case where the advertisements include a point-bearing advertisement that awards points to the user to whom the advertisement is delivered, and a non-points advertisement, a first index value indicating the level of interest in the target of the advertisement held by the user to whom the advertisement is delivered when the point-bearing advertisement is delivered, and a second index value indicating the level of interest in the target of the advertisement held by the user to whom the advertisement is delivered when the non-points advertisement is delivered, and when the target of the advertisement to be delivered to the user is identified by the identifying means, the delivering means (advertising delivery unit 524) delivers the point-bearing advertisement if the first index value is greater than the second index value, and delivers the non-points advertisement if the second index value is greater than the first index value.

[0052] (Appendix 5) The analysis server according to Supplementary Notes (1) to (4) further comprises: means for accepting designation of a target of the advertisement (input accepting unit 51); means for acquiring purchase history information of the target for each user as an index value indicating the level of interest in the target (purchase probability prediction unit 521); means for acquiring information on whether an advertisement for the target has been delivered for each user (purchase probability prediction unit 521); and means for calculating, based on the purchase history information and the delivery information, the purchase probability of the target for each user when the advertisement is delivered as the index value when the advertisement is delivered, and calculating the purchase probability of the target when the advertisement is not delivered as the index value when the advertisement is not delivered (purchase probability prediction unit 521).

[0053] (Appendix 6) The analysis server described in Supplementary Notes (1) to (5) further includes a means (purchase probability prediction unit 521) for calculating an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered, and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, based on a prediction model using the user's features and whether the advertisement is delivered as explanatory variables and the index value as a target variable.

[0054] (Appendix 7) The means for calculating the contribution (contribution analysis unit 522) is an analysis server described in Supplementary Notes (1) to (6), which calculates the contribution by performing SHAP analysis on a machine learning model that uses the user's features as explanatory variables and the difference as a target variable.

[0055] (Appendix 8) The means for calculating the degree of contribution (contribution analysis unit 522) is an analysis server described in Supplementary Notes (1) to (7), which extracts the users whose difference is equal to or greater than a predetermined value, aggregates the extracted features of the users, and determines the degree of contribution as the frequency of appearance of the features of the users in the aggregated results.

[0056] (Appendix 9) The means for calculating the degree of contribution (contribution analysis unit 522) is an analysis server described in Supplementary Notes (1) to (8), which extracts features whose degree of contribution is equal to or greater than a predetermined value, or arranges the features in order of the greatest degree of contribution, extracts a predetermined number of the features from the top, and regards the extracted features as the features of the user that contribute to the magnitude of the advertising effect.

[0057] (Appendix 10) The means for calculating the contribution (contribution analysis unit 522) is the analysis server described in Supplementary Notes (1) to (9), which calculates the feature amount for each product, service, product or service category, and company that provides the product or service.

[0058] (Appendix 11) The analysis server described in appendix (1) to appendix (10) is one of the following: the probability of delivering the target of the advertisement; the probability of accessing a web page that describes the target of the advertisement; and the probability of requesting information or making an inquiry about the target of the advertisement.

[0059] (Appendix 12) An advertisement distribution system comprising: an analysis server according to Supplementary Notes (1) to (11); a distribution server comprising: means for receiving an advertisement distribution request; means for identifying a target of the advertisement to be distributed to the user based on the feature of a user to whom the advertisement will be distributed based on the distribution request and the feature extracted for each of the candidate targets of the advertisement to be distributed in response to the distribution request, the feature having a contribution degree that satisfies a predetermined condition; and means for delivering the advertisement identified by the identification means.

[0060] (Appendix 13) A terminal device that receives advertisements transmitted by the analysis server citing supplementary note (2) or the advertisement distribution system described in supplementary note 12.

[0061] (Appendix 14) An analysis method executed by a computer, the analysis method comprising the steps of: calculating, based on a user's feature value and a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and the index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, the degree of contribution that the user's feature value makes to the magnitude of the difference; and extracting the feature value whose degree of contribution satisfies a predetermined condition.

[0062] (Appendix 15) This program causes a computer to function as a means for calculating the degree of contribution that a user's feature value makes to the magnitude of the difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, based on the user's feature value, and a means for extracting the feature value whose degree of contribution satisfies a predetermined condition. [Explanation of symbols]

[0063] 1. Advertising distribution system 10. User terminal 20. Database Server 21. User information management database 30. Advertising media server 40. Purchasing management server 50...Analysis Server 51 Input reception section 52 Control section 521 Purchase probability prediction section 522···Contribution Analysis Department 523···Distribution Decision Department 524···Advertising Distribution Department 53...Storage section 531···Purchase prediction model 532···Contribution Model 900···Computer 901 CPU 902...Main memory 903...Auxiliary storage device 904 Input / Output Interface 905···Communication Interface

Claims

1. a means for calculating, based on a feature amount of a user and a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, a degree of contribution of the feature amount of the user to the magnitude of the difference; means for extracting the feature amount whose contribution degree satisfies a predetermined condition; An analysis server comprising:

2. a means for accepting requests to deliver advertisements; means for identifying, as the advertisement target to be delivered to the user, advertisement targets having at least one feature that matches the user's feature, based on the feature of the user to be delivered the advertisement related to the delivery request and the feature extracted for each candidate advertisement target to be delivered in response to the delivery request, the feature having the degree of contribution that satisfies a predetermined condition; means for delivering the advertisement identified by the identifying means; The analysis server of claim 1 further comprising:

3. When the specifying means specifies a plurality of advertisement targets having at least one feature value that matches the feature value of the user, the means for delivering the advertisement delivers an advertisement related to the target of the advertisement from which the feature quantity having the greatest degree of contribution among the matching feature quantities has been extracted. The analysis server according to claim 2 .

4. The advertisement further comprises a means for acquiring, when there is a point-bearing advertisement that awards points to a user to whom the advertisement is distributed and a non-point-bearing advertisement, a first index value indicating the level of interest in the target of the advertisement held by users to whom the advertisement is distributed when the point-bearing advertisement is distributed, and a second index value indicating the level of interest in the target of the advertisement held by users to whom the advertisement is distributed when the non-point-bearing advertisement is distributed, When the target of the advertisement to be delivered to the user is identified by the identifying means, the distribution means distributes the point-added advertisement when the first index value is greater than the second index value; If the second index value is greater than the first index value, the no-point advertisement is delivered. The analysis server according to claim 2 .

5. means for accepting designation of a target of the advertisement; means for acquiring purchase history information of the target of the advertisement for each user; means for acquiring information on whether or not an advertisement related to the advertisement target for each user is delivered; means for calculating, for each user, a purchase probability of the target of the advertisement when the advertisement is delivered as the index value when the advertisement is delivered, based on the purchase record information and the delivery / non-delivery information, and calculating, for each user, a purchase probability of the target of the advertisement when the advertisement is not delivered as the index value when the advertisement is not delivered; The analysis server according to claim 1 or claim 2, further comprising:

6. a means for calculating the index value that the user will have when the advertisement is delivered and the index value that the user will have when the advertisement is not delivered, based on a prediction model that uses the feature amount of the user and whether or not the advertisement is delivered as explanatory variables and the index value as a target variable; The analysis server according to claim 1 or claim 2, further comprising:

7. the means for calculating the degree of contribution calculates the degree of contribution by performing a SHAP analysis on a machine learning model that uses the feature amount of the user as an explanatory variable and the difference as a target variable. The analysis server according to claim 1 or 2.

8. the means for calculating the degree of contribution extracts the users whose difference is equal to or greater than a predetermined value, aggregates the extracted feature quantities of the users, and determines the frequency of appearance of the feature quantities of the users in the aggregated result as the degree of contribution. The analysis server according to claim 1 or 2.

9. the means for calculating the degree of contribution extracts a feature quantity whose degree of contribution is equal to or greater than a predetermined value, or arranges the feature quantities in order of decreasing degree of contribution, extracts a predetermined number of feature quantities from the top, and sets the extracted feature quantities as the feature quantities of the user that contribute to the magnitude of the advertising effect. The analysis server according to claim 1 or 2.

10. the means for calculating the degree of contribution calculates the feature amount for each product, service, product or service category, and company providing the product or service. The analysis server according to claim 1 or 2.

11. The index value is any one of the following: a probability of delivering the target of the advertisement, a probability of accessing a web page on which the target of the advertisement is posted, and a probability of requesting information or making an inquiry about the target of the advertisement. The analysis server according to claim 1 or 2.

12. The analysis server according to claim 1; means for receiving an advertisement distribution request; means for identifying advertisement targets to be distributed to the user, based on feature amounts of a user to be a distribution target of the advertisement related to the distribution request and the feature amounts extracted for each candidate target of the advertisement to be distributed in response to the distribution request, the feature amounts having a degree of contribution that satisfies a predetermined condition; and means for distributing the advertisement identified by the identifying means; a distribution server comprising: An advertisement distribution system comprising:

13. receiving an advertisement transmitted by the analysis server according to claim 2 or the advertisement distribution system according to claim 12; Terminal device.

14. 1. A computer-implemented analysis method comprising: calculating, based on a feature amount of a user and a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, a degree of contribution of the feature amount of the user to the magnitude of the difference; extracting the feature amount whose contribution degree satisfies a predetermined condition; An analytical method having the following.

15. Computer, a means for calculating, based on a feature amount of a user and a difference between an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is delivered and an index value indicating the level of interest the user has in the target of the advertisement when the advertisement is not delivered, a degree of contribution of the feature amount of the user to the magnitude of the difference; means for extracting the feature quantity whose contribution degree satisfies a predetermined condition; A program to function as a

Images