JP2018041314A - Classification device, classification method, and classification program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To appropriately classify users.SOLUTION: A classification device includes an acquisition unit and a classification unit. The acquisition unit obtains information on purchase of articles or services which was made by a user. The classification unit classifies the user into a cluster on the basis of the distribution of information on purchase which is obtained by the acquisition unit. For example, the classification unit classifies the user into a cluster on the basis of the distribution of the number of articles or services purchased by the user.SELECTED DRAWING: Figure 3

Description

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

  Conventionally, techniques for classifying users based on various types of information about users have been proposed. For example, using the past action history of event ticket purchaser (user), event attribute information, etc., segment the user group, and what kind of purchasing behavior the segmented user group takes in a specific event Technology for predicting this is provided.

JP 2012-208573 A

  However, in the above-described conventional technology, even if segmentation (classification) for predicting purchase behavior at a specific event is possible, it is not always applicable to other purchase behavior, and the user is appropriately classified. It is not always possible.

  The present application has been made in view of the above, and an object thereof is to provide a classification device, a classification method, and a classification program for appropriately classifying users.

  The classification device according to the present application includes an acquisition unit that acquires information regarding purchases of goods or services performed by a user, and a classification that classifies the users into clusters based on a distribution of information regarding the purchase acquired by the acquisition unit. And a section.

  According to one aspect of the embodiment, there is an effect that users can be classified appropriately.

FIG. 1 is a diagram illustrating an example of a classification process according to the embodiment. FIG. 2 is a diagram illustrating an example of service provision using cluster information according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the classification device according to the embodiment. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the cluster information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the advertisement information storage unit according to the embodiment. FIG. 7 is a flowchart illustrating an example of the classification process according to the embodiment. FIG. 8 is a flowchart illustrating an example of provision of a service using cluster information according to the embodiment. FIG. 9 is a diagram illustrating an example of the classification process according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the classification device.

  Hereinafter, a classification apparatus, a classification method, and a mode for implementing a classification program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the classification device, the classification method, and the classification program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Classification process)
An example of the classification process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a classification process according to the embodiment. In the example of FIG. 1, the classification device 100 illustrates a case in which users are classified into clusters based on information on purchases of each user (hereinafter also referred to as “purchase information”). Hereinafter, a product or service to be purchased may be referred to as “product”.

  As shown in FIG. 1, the classification system 1 includes a terminal device 10 (see FIG. 2), a commercial transaction device 50, and a classification device 100. The terminal device 10 and the classification device 100 are connected to be communicable by wire or wireless via a predetermined communication network (not shown). In addition, the classification system 1 illustrated in FIG. 1 may include a plurality of terminal devices 10, a plurality of commercial transaction devices 50, and a plurality of classification devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example illustrated in FIG. 1, the terminal device 10 is a smartphone. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10.

  The commercial transaction apparatus 50 is an information processing apparatus used for providing an electronic commercial transaction service. For example, the commercial transaction device 50 provides an electronic commercial transaction service in response to a purchase request from a user. In addition, the commercial transaction device 50 provides user purchase information to the classification device 100. The service provided by the provider using the commercial transaction device 50 is not limited to the electronic commercial transaction service as long as it can provide the user with the products and services purchased by each user. . Further, the commercial transaction device 50 may be integrated with the classification device 100. For example, the classification device 100 may provide an electronic commerce service.

  The classification device 100 classifies users into clusters based on the distribution of information regarding purchases of each user. For example, the classification device 100 classifies users into clusters based on the distribution of the number of items purchased by the user. The classification device 100 is not limited to the purchase history as long as it is information related to the purchase by the user, and various information may be used. For example, the classification device 100 may use a browsing history, a search history, and the like related to user purchases. For example, the classification device 100 may classify users into clusters by using content browsing history on the Internet related to user purchases, content search history on the Internet, and the like.

  First, in the example of FIG. 1, the classification device 100 receives a purchase information history (hereinafter also referred to as “purchase history”) of each user from the commercial transaction device 50 (step S <b> 11). For example, the classification device 100 is provided with purchase histories of the users U1 to Un (n is an arbitrary numerical value). For example, “n” may be 1 million or the like. When “user U * (* is an arbitrary numerical value)” is described, this indicates that the user is a user identified by the user ID “U *”. For example, when “user U1” is described, the user is a user identified by the user ID “U1”.

  In the example of FIG. 1, the classification device 100 acquires purchase history of each user as shown in the user information storage unit 121 from the commercial transaction device 50 (step S11). The classification device 100 acquires the purchase history of each user for a predetermined period from the commercial transaction device 50. In the example of FIG. 1, it is assumed that the classification device 100 acquires the purchase history of each user from the commercial transaction device 50 for one month before acquiring the purchase history.

  For example, as shown in the user information storage unit 121 of FIG. 1, the classification device 100 purchases six water A, three wines A, and a washing machine A in one month for the user U1. Get a purchase history that indicates not. Further, for example, in the example illustrated in FIG. 1, the user U2 indicates that he / she has not purchased water A or wine A but purchased one washing machine A in one month. Further, for example, in the example illustrated in FIG. 1, the user U3 indicates that five waters A, four wines A, and no washing machine A are purchased in one month. Further, for example, in the example shown in FIG. 1, the user U4 indicates that he has not purchased water A or wine A and has purchased 100 washing machines A in one month.

  Moreover, the graph D1 in FIG. 1 shows the distribution of the number of products and the like that the user U1 purchased in one month. Moreover, the graph D2 in FIG. 1 shows distribution of the number of goods etc. which the user U2 purchased in one month. Moreover, the graph D3 in FIG. 1 shows distribution of the number of goods etc. which the user U3 purchased in one month. Further, a graph D4 in FIG. 1 shows the distribution of the number of products and the like purchased by the user U4 during one month.

  The classification device 100 that acquired the purchase history from the commercial transaction device 50 classifies each user based on the acquired purchase history (step S12). For example, the classification device 100 classifies users into clusters based on the distribution of the number of goods or services purchased by the users. In the example of FIG. 1, the classification device 100 classifies each user as shown in the cluster information storage unit 122 based on the purchase history of each user shown in the user information storage unit 121.

  For example, the classification apparatus 100 uses each user's purchase history and appropriately uses various conventional techniques such as K-means to assign each user according to the similarity in the distribution of the number of products purchased by each user. Classify into clusters. For example, the classification device 100 classifies users into clusters so that the number of clusters is a predetermined number (for example, 1000). The classification device 100 may use any clustering technique as long as the users can be classified into a plurality of clusters based on the similarity in the distribution of the number of products purchased by each user. For example, the classification device 100 may classify users into clusters based on the similarity between the vectors of each user, using the distribution of the number of products purchased by each user as a vector.

  In the example of FIG. 1, the cluster (cluster C11) identified by the cluster ID “C11” includes users such as “user U1”, “user U3”, “user U15”, and “user U40”. . Note that “cluster C * (* is an arbitrary numerical value)” indicates that the cluster is a user identified by the cluster ID “C *”. For example, when “cluster C11” is described, the cluster is a cluster identified by the cluster ID “C11”. In the example of FIG. 1, the cluster C12 indicates that users such as “user U2” and “user U500” are included. In the example of FIG. 1, the cluster C13 indicates that users such as “user U4” and “user U302” are included. In the example of FIG. 1, for example, the classification device 100 determines that the user U1 and the user U3 that are similar in the number of items purchased by each user are based on the distribution of the number of items purchased by each user in the same cluster. Classify as C11.

  As described above, the classification device 100 can appropriately classify users based on the distribution of the number of items purchased by each user. More specifically, the classification device 100 classifies the data into clusters that take into account information related to the purchase amount of each user, based on the distribution of the number of products purchased by each user. For example, the classification device 100 is based on the distribution of the number of products purchased by each user, and thus the similarity between the products purchased by each user and the similarity in the amount of products purchased by each user. Classify into clusters with similarities. Thereby, the classification apparatus 100 can classify a user appropriately.

  In the above-described example, the case where the classification device 100 aggregates the number of items purchased by each user for each product and classifies the users based on the information is shown. However, the classification device 100 is purchased by each user. As long as the information is based on the number of products or the like, any information may be used to classify the users. For example, the classification apparatus 100 may count the number of products purchased by each user for each category of products, and classify users based on the distribution of the number of products purchased by each user for each category. Good. For example, the classification device 100 uses water or tea as products belonging to the beverage category, wine, beer, sake, etc. as products belonging to the alcohol category, etc., and refrigerators or washing machines as products belonging to the home appliance category, Users may be classified. For example, the classification apparatus 100 sets the number of categories “beverages” as a total value of the number of purchased water, tea, etc., and sets the number of categories “alcohol” as the total value of the number of purchased wines, beer, sake, etc. The users may be classified by using the number of categories “home appliances” as the total value of the number of home appliances purchased for refrigerators and washing machines.

  Further, the classification device 100 may extract a special cluster to which a special user whose amount related to purchase exceeds a predetermined threshold among clusters generated by the above-described classification processing. For example, the classification device 100 extracts a special cluster to which a special user whose amount related to purchase exceeds a predetermined threshold belongs from the clusters based on the distribution of the number of products purchased by each user. For example, it is considered that few users purchase a plurality of identical products (for example, refrigerator A) in a predetermined period (for example, one month) within one year.

  Therefore, in the example of FIG. 1, the classification device 100 extracts a user who has purchased two or more refrigerators A during a predetermined period as a special user, and extracts a cluster including the user as a special cluster. In this case, the classification device 100 is based on the distribution of the number of items purchased by each user, and the cluster to which the user U4 who is a special user whose amount related to purchase exceeds a predetermined threshold among the clusters C11 to C14 belongs. C13 is extracted as a special cluster. For example, the classification device 100 extracts the cluster C13 to which the user U4 who has purchased two or more refrigerators A in a predetermined period from the clusters C11 to C14 and the like belongs as a special cluster.

  For example, the classification device 100 can classify the user U2 and the user U4, who are users who have purchased only the refrigerator, into different clusters based on the distribution of the number of items purchased by each user. A cluster can be generated that classifies users into regular users and merchant users. The normal user here means, for example, a general user who purchases a product or the like for personal consumption or the like. The trader user here means, for example, a user who purchases a product or the like for a commercial transaction such as resale, not a user who purchases the product for his own consumption.

  As described above, the classification device 100 can provide an appropriate service for each cluster by generating a cluster in which normal users and trader users are appropriately classified. For example, the classification device 100 may provide information that promotes purchase such as distribution of a predetermined campaign or coupon for a cluster to which a normal user belongs. Further, for example, the classification device 100 may limit the number of purchases to a trader user who normally inhibits the use of the user by an action such as purchasing the same product in large quantities. Note that the classification device 100 may provide the information specifying the normal user or the trader user described above to another information processing device.

[1-2. Service provision)
Next, an example of service provision using cluster information will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of service provision using cluster information according to the embodiment.

  First, in the example of FIG. 2, the terminal device 10 used by the user U15 requests an advertisement from the classification device 100 in accordance with an operation by the user U15 (step S21).

  The classification device 100 that acquired the advertisement request from the terminal device 10 extracts the cluster to which the user U15 belongs (step S22). For example, the classification device 100 extracts the cluster C11 to which the user U15 belongs from the clusters stored in the cluster information storage unit 122.

  Thereafter, the classification device 100 extracts, from the user information storage unit 121, products that have not been purchased by the user U15 and that have been purchased by other users belonging to the same cluster (step S23). In the example of FIG. 2, the classification device 100 extracts wine A that is a product not purchased by the user U15 and is a product purchased by another user U1 or user U3 belonging to the same cluster.

  Thereafter, the classification device 100 extracts an advertisement related to the extracted product or the like (step S24). In the example of FIG. 2, the classification device 100 extracts the advertisement A related to the wine A from the advertisement information storage unit 123. The classification device 100 may extract the advertisement A related to the product consumed with the wine A from the advertisement information storage unit 123. For example, the classification device 100 may extract an advertisement related to cheese as an advertisement of a product consumed with the wine A.

  Then, the classification device 100 provides the extracted advertisement to the terminal device 10 (step S25). In the example of FIG. 2, the classification device 100 provides an advertisement A related to wine A to the terminal device 10 used by the user U15. The classification device 100 may provide an advertisement about cheese together with an advertisement A about wine A to the terminal device 10 used by the user U15.

  As described above, the classification device 100 relates to one user belonging to one cluster with respect to a product or service that is not purchased by one user but purchased by another user belonging to one cluster. By providing information, it is possible to appropriately provide various services such as advertisement distribution to one user. The classification device 100 may extract a user who has not purchased a product purchased by many other users belonging to the same cluster, such as the user U15, as a target user. Then, the classification device 100 may provide the target user with an advertisement related to a product that is not purchased by the target user and purchased by many other users belonging to the same cluster. In the above-described example, an example in which the classification device 100 distributes an advertisement in response to a request from the user is shown. However, the classification device 100 can provide any service as long as it provides a service using the user cluster information. A service may be provided. For example, the classification device 100 may provide a recommendation service to the user based on the user cluster information. For example, the classification device 100 may provide information that prompts the target user to purchase a product at a predetermined timing based on the purchase history of other users of the cluster to which the target user of the recommendation belongs. For example, when browsing content related to products purchased by other users of the cluster to which the target user of the recommendation belongs, the classification device 100 may provide information regarding products purchased by other users to the target user at a predetermined timing. May be.

[2. (Configuration of classification device)
Next, the configuration of the classification device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the classification device 100 according to the embodiment. As illustrated in FIG. 3, the classification device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The classification device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the classification device 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wirelessly, and transmits and receives information to and from the terminal device 10 included in the classification system 1, for example.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a user information storage unit 121, a cluster information storage unit 122, and an advertisement information storage unit 123.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various types of information regarding the user. For example, the user information storage unit 121 stores various types of information including purchase information related to products purchased by each user as information related to the user. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. The user information storage unit 121 illustrated in FIG. 4 includes items such as “user ID” and “purchase list”.

  “User ID” indicates identification information for identifying a user. The “purchase list (number)” indicates the number of items purchased by the user identified by the corresponding user ID. The “purchase list (number)” includes items such as “water A”, “wine A”, and “washing machine A”.

  For example, in the example illustrated in FIG. 4, the user identified by the user ID “U1” has purchased six water A, three wine A, and has not purchased the washing machine A. For example, in the example illustrated in FIG. 4, the user identified by the user ID “U2” indicates that he / she has not purchased water A or wine A but has purchased one washing machine A. The number of items purchased by each user in a predetermined period (for example, one month) may be used.

  The user information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the user information storage unit 121 may store information such as name, sex, age, place of residence, interest, family structure, income, lifestyle, and the like. For example, the user information storage unit 121 may store information for identifying the terminal device 10 used by each user. For example, the user information storage unit 121 may store information related to the amount of money related to each product purchased by each user. For example, the user information storage unit 121 may store information regarding the total amount used by each user for each product or the like, or may store a unit price (amount per item) of each product. For example, when the unit price of each product is stored in the user information storage unit 121, the classification device 100 uses the product purchased by each user for each product purchased based on the number of each product purchased by each user and the unit price. The total amount may be calculated.

(Cluster information storage unit 122)
The cluster information storage unit 122 according to the embodiment stores information about the cluster. FIG. 5 shows an example of information about users stored in the cluster information storage unit 122. As illustrated in FIG. 5, the cluster information storage unit 122 includes items such as “cluster ID” and “user list”. The user list includes items such as “user 1” to “user 4”.

  “Cluster ID” indicates identification information for identifying a cluster. “User 1” to “User 4” in the “user list” indicate users belonging to the corresponding cluster.

  In the example of FIG. 5, the cluster (cluster C11) identified by the cluster ID “C11” includes users such as “user U1”, “user U3”, “user U15”, and “user U40”. .

  Note that the cluster information storage unit 122 is not limited to the above, and may store various types of information according to the purpose. For example, the cluster information storage unit 122 may store information related to the date and time when a user is classified and a cluster is generated. Further, the cluster information storage unit 122 may store a flag indicating that it is a feature cluster. For example, since the cluster information storage unit 122 is a special cluster including the user U4 who is a special user in the cluster C13, a flag (for example, 1) indicating that it is a feature cluster is stored in the item “special cluster”. The

(Advertisement information storage unit 123)
The advertisement information storage unit 123 according to the embodiment stores various types of information related to advertisements. FIG. 6 shows an example of the advertisement information storage unit 123 according to the embodiment. The advertisement information storage unit 123 illustrated in FIG. 6 includes items such as “advertisement ID”, “advertisement content”, “target”, and “bid price”.

  “Advertisement ID” indicates identification information for identifying an advertisement. “Advertising content” indicates an advertisement submitted by an advertiser, an agency, or the like. FIG. 6 shows an example in which conceptual information such as “advertisement A” is stored in “advertising content”, but actually, still images, moving images, text data, URLs, or storage locations thereof are shown. File path name etc. are stored. Hereinafter, the notation “advertiser” is a concept including not only the advertiser but also the agency. “Bid price” indicates an advertising fee designated when an advertiser submits advertising content. For example, the “bid price” corresponds to the unit price paid from the advertiser to the advertisement distributor (for example, the administrator of the classification device 100) when the advertisement content is clicked once by the user. The unit of “bid price” may be various currency units such as “yen” and “dollar”. “Target” indicates, for example, a product or service to be advertised, that is, a product or the like. The information for identifying the product or service is not limited to the “target”, and information such as “product ID” for identifying the product or service may be stored.

  For example, in the example illustrated in FIG. 6, the advertisement A identified by the advertisement ID “AC1” is an advertisement for the product “wine A”, and indicates that the bid price is “80”. Further, for example, in the example illustrated in FIG. 6, the advertisement B identified by the advertisement ID “AC2” is an advertisement for the product “beer A”, and indicates that the bid price is “80”. In addition, for example, in the example illustrated in FIG. 6, the advertisement C identified by the advertisement ID “AC3” is an advertisement for the product “Sake A” and indicates that the bid price is “100”.

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

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller and is stored in a storage device inside the classification apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a classification program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, a classification unit 132, an extraction unit 133, and a provision unit 134, and implements or executes information processing functions and operations described below. .

(Acquisition part 131)
For example, the acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires information related to purchase of products or services performed by the user. In FIG. 1, the acquisition unit 131 acquires purchase information for each user from the commercial transaction device 50. For example, the acquisition unit 131 stores the purchase history of each user acquired from the commercial transaction device 50 in the user information storage unit 121.

  The acquisition unit 131 acquires an advertisement request. In FIG. 2, the acquisition unit 131 acquires an advertisement request from the terminal device 10 used by the user U15.

(Classification part 132)
The classification unit 132 classifies various information. For example, the classification unit 132 classifies users into clusters based on the distribution of information regarding purchases acquired by the acquisition unit 131. For example, the classification unit 132 classifies the user into clusters based on the distribution of the number of products or services purchased by the user. For example, the classification unit 132 classifies the user into clusters based on the distribution of the amount of goods or services purchased by the user.

  In the example of FIG. 1, the classification unit 132 classifies the cluster into a cluster that includes information on the purchase amount of each user based on the distribution of the number of products purchased by each user. For example, the classification unit 132 is based on the distribution of the number of products purchased by each user, so that the similarity between the products purchased by each user and the similarity in the amount of products purchased by each user are two. Classify into clusters with similarities.

  In the example of FIG. 1, the classification unit 132 classifies each user based on the purchase history. For example, the classification unit 132 classifies each user as shown in the cluster information storage unit 122 (see FIG. 5) based on the purchase history of each user shown in the user information storage unit 121 (see FIG. 4). For example, the classification unit 132 classifies the user U1 and the user U3 that are similar in the number purchased for each product into the same cluster C11 based on the distribution of the number of products purchased by each user. For example, the classification unit 132 classifies the users U2 and U4, who are users who have purchased only the refrigerator, into different clusters based on the distribution of the number of items purchased by each user. Further, for example, the classification unit 132 classifies the user into a normal cluster and a trader user into different clusters.

  For example, the classification unit 132 uses each user's purchase history and appropriately uses various conventional techniques such as K-means to assign each user according to the similarity in the distribution of the number of products purchased by each user. Classify into clusters. For example, the classification device 100 classifies users into clusters so that the number of clusters is a predetermined number (for example, 1000). The classification device 100 may use any clustering technique as long as the users can be classified into a plurality of clusters based on the similarity in the distribution of the number of products purchased by each user. For example, the classification unit 132 may classify users into clusters based on the similarity between the vectors of each user, with the distribution of the number of products purchased by each user as a vector.

  Further, the classification unit 132 sets water or tea as a product belonging to the beverage category, wine, beer, sake, etc. as a product belonging to the alcohol category, etc., and sets the refrigerator or washing machine as a product belonging to the home appliance category, Users may be classified. For example, the classification unit 132 sets the number of categories “beverages” as the total number of purchased water, tea, etc., and sets the number of categories “alcohol” as the total number of purchased wines, beer, sake, etc. The users may be classified by using the number of categories “home appliances” as the total value of the number of home appliances purchased for refrigerators and washing machines.

(Extractor 133)
The extraction unit 133 estimates various information. For example, the extraction unit 133 extracts a special cluster to which a special user whose purchase amount exceeds a predetermined threshold among clusters based on the user classification by the classification unit 132.

  In the example of FIG. 1, the extraction unit 133 extracts a user who has purchased two or more refrigerators A during a predetermined period as a special user, and extracts a cluster including the user as a special cluster. For example, the extraction unit 133 extracts, as a special cluster, the cluster C13 to which the user U4, which is a special user whose purchase amount exceeds a predetermined threshold, from among the clusters C11 to C14 and the like. For example, the extraction unit 133 extracts, as a special cluster, the cluster C13 to which the user U4 who has purchased two or more refrigerators A in a predetermined period out of the clusters C11 to C14 and the like belongs.

  For example, the extraction unit 133 extracts products or the like that have not been purchased by the user who uses the terminal device 10 and that have been purchased by other users belonging to the same cluster. In FIG. 2, the extraction unit 133 extracts wine A, which is a product not purchased by the user U15 and is a product purchased by another user U1 or user U3 belonging to the same cluster.

(Providing unit 134)
The providing unit 134 provides various types of information to an external information processing apparatus. For example, the providing unit 134 provides a service to the user according to the cluster based on the classification of the user by the classification unit 132. For example, the providing unit 134 provides, to one user belonging to one cluster, information related to a product or service that is not purchased by one user but purchased by another user belonging to one cluster. To do. In FIG. 2, the providing unit 134 provides the advertisement A related to the wine A to the terminal device 10 used by the user U15.

[3. (Classification process flow)
Here, the procedure of the classification process performed by the classification apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 7 is a flowchart illustrating an example of the classification process according to the embodiment.

  As shown in FIG. 7, the classification device 100 acquires purchase information of each user (step S101). In FIG. 1, the classification device 100 acquires purchase information of each user from the commercial transaction device 50.

  Thereafter, the classification device 100 classifies the users based on the distribution of information regarding purchases of the users (step S102). In FIG. 1, the classification device 100 classifies users into clusters based on the distribution of information regarding purchases of each user.

[4. (Service provision flow)
Next, a service provision procedure by the classification device 100 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of provision of a service using cluster information according to the embodiment.

  As shown in FIG. 8, the classification device 100 acquires an advertisement request from the terminal device 10 (step S201). In FIG. 2, the classification device 100 acquires an advertisement request from the terminal device 10 used by the user U15.

  Thereafter, the classification device 100 extracts a cluster to which a user who uses the terminal device 10 belongs (step S202). In FIG. 2, the classification device 100 extracts the cluster C11 to which the user U15 who uses the terminal device 10 belongs.

  Thereafter, the classification device 100 extracts products and the like that have not been purchased by the user who uses the terminal device 10 and that have been purchased by other users belonging to the same cluster (step S203). In FIG. 2, the classification device 100 extracts wine A, which is a product not purchased by the user U15 and is a product purchased by another user U1 or user U3 belonging to the same cluster.

  Thereafter, the classification device 100 provides the terminal device 10 with an advertisement related to the extracted product (step S204). In FIG. 2, the classification device 100 provides an advertisement A related to wine A to the terminal device 10 used by the user U15.

[5. Classification processing (amount)
In the above-described example, the case where the classification device 100 classifies users based on the distribution of the number of each product has been described. However, the classification device 100 may classify users based on other information. For example, the classification device 100 may classify users into clusters based on the distribution of amounts of goods purchased by the user. This point will be described with reference to FIG. FIG. 9 is a diagram illustrating an example of the classification process according to the embodiment.

  In the example of FIG. 9, the classification device 100 acquires the purchase history of each user as shown in the user information storage unit 121A from the commercial transaction device 50 (step S31). In the example of FIG. 9, the classification device 100 differs from the processing in FIG. 1 in that the amount used by each user for each product is acquired as the purchase history, as shown in the user information storage unit 121A. . In the example of FIG. 9, the classification device 100 acquires the purchase history of each user from the commercial transaction device 50 for two months before acquiring the purchase history. For example, the classification device 100 acquires, as a purchase history, an amount used by each user for each product in a predetermined period (for example, two months).

  For example, as shown in the user information storage unit 121A in FIG. 9, the classification device 100 is configured such that the amount used by the user U1 for water A is 6000 (yen) and the amount used for wine A is 3000 for two months. (Yen) and a purchase history indicating that the amount used for the washing machine A is 0 (yen) is acquired. Further, for example, in the example shown in FIG. 9, the user U2 spends 2 months on water A and wine A for 0 (yen), and spends 5000 (yen) on the washing machine A. Indicates that there is. Also, for example, in the example shown in FIG. 9, the user U3 spends two months with the amount used for water A of 5000 (yen) and the amount used for wine A of 4000 (yen), and the washing machine Indicates that the amount used for A is 0 (yen). Further, for example, in the example shown in FIG. 9, the user U4 spends 2 months for water A and wine A at 0 (yen) and spends 5 million (yen) on the washing machine A. Indicates that there is.

    In addition, a graph D1 in FIG. 9 shows the distribution of the amount of money used by the user U1 for purchasing each product in two months. In addition, a graph D2 in FIG. 9 shows the distribution of the amount of money used by the user U2 for purchasing each product or the like in two months. In addition, a graph D3 in FIG. 9 shows the distribution of the amount of money used by the user U3 for purchasing each product or the like in two months. In addition, a graph D4 in FIG. 9 shows the distribution of the amount of money used by the user U4 for purchasing each product or the like in two months.

  The classification device 100 that acquired the purchase history from the commercial transaction device 50 classifies each user based on the acquired purchase history (step S32). For example, the classification device 100 classifies the user into clusters based on the distribution of the amount of goods or services purchased by the user. In the example of FIG. 9, the classification device 100 classifies each user as shown in the cluster information storage unit 122A based on the purchase history of each user shown in the user information storage unit 121A. The cluster information storage unit 122A illustrated in FIG. 9 is the same as the cluster information storage unit 122, except that the cluster information storage unit 122A is information related to the cluster based on the usage amount of each user.

  For example, the classification apparatus 100 uses each user's purchase history and appropriately uses various conventional techniques such as K-means to assign each user according to the similarity in the distribution of the number of products purchased by each user. Classify into clusters. For example, the classification device 100 classifies users into clusters so that the number of clusters is a predetermined number (for example, 1000). The classification device 100 may use any clustering technique as long as the users can be classified into a plurality of clusters based on the similarity in the distribution of the number of products purchased by each user. For example, the classification apparatus 100 may classify users into clusters based on the similarity between the vectors of each user, with the distribution of the amount of money used by each user for purchasing each product as a vector.

  In the example of FIG. 9, the cluster (cluster C11) identified by the cluster ID “C11” includes users such as “user U1”, “user U3”, “user U15”, and “user U40”. . Note that “cluster C * (* is an arbitrary numerical value)” indicates that the cluster is a user identified by the cluster ID “C *”. For example, when “cluster C11” is described, the cluster is a cluster identified by the cluster ID “C11”. In the example of FIG. 9, the cluster C12 indicates that users such as “user U2” and “user U500” are included. In the example of FIG. 9, the cluster C13 indicates that users such as “user U4” and “user U302” are included. In the example of FIG. 9, for example, the classification device 100 determines a user U1 and a user U3 that have similar amounts of money used for purchase for each product, etc., based on the distribution of the amount of the product purchased by each user. Classify into the same cluster C11.

  As described above, the classification device 100 can appropriately classify users based on the distribution of the amount of goods purchased by each user. Specifically, the classification device 100 classifies the cluster into a cluster that includes information related to the amount of purchase cost of each user, based on the distribution of the amount of goods purchased by each user. For example, the classification device 100 is based on the distribution of the amount of goods purchased by each user, so that the similarity between the products purchased by each user and the similarity of the amounts used by each user for purchase are similar. Classify the cluster into consideration. Thereby, the classification apparatus 100 can classify a user appropriately.

[6. effect〕
As described above, the classification device 100 according to the embodiment includes the acquisition unit 131 and the classification unit 132. The acquisition unit 131 acquires information related to purchase of goods or services performed by the user. The classification unit 132 classifies users into clusters based on the distribution of information regarding purchase acquired by the acquisition unit 131.

  Thereby, the classification device 100 according to the embodiment can appropriately classify the user based on the information related to the purchase of the product or service performed by the user.

  In the classification device 100 according to the embodiment, the classification unit 132 classifies users into clusters based on the distribution of the number of products or services purchased by the user.

  Accordingly, the classification device 100 according to the embodiment is based on the distribution of the number of products purchased by each user, and the similarity between the products purchased by each user and the amount of products purchased by each user is similar. It classify | categorizes into the cluster which considered two similarities with sex. Thereby, the classification apparatus 100 can classify a user appropriately.

  In the classification device 100 according to the embodiment, the classification unit 132 classifies users into clusters based on the distribution of the amount of goods or services purchased by the user.

  Thereby, the classification device 100 according to the embodiment is based on the distribution of the amount of the product purchased by each user, and the similarity between the product purchased by each user and the amount of money used by each user for purchase. Are classified into clusters taking into account the two similarities. Therefore, the classification device 100 can classify users appropriately.

  In addition, the classification device 100 according to the embodiment includes an extraction unit 133. The extraction unit 133 extracts a special cluster to which a special user whose purchase amount exceeds a predetermined threshold among clusters based on the user classification by the classification unit 132.

  Thereby, the classification apparatus 100 according to the embodiment can extract a special cluster to which a special user whose purchase amount exceeds a predetermined threshold value belongs. For example, the classification apparatus 100 can extract a special cluster to which a special user whose purchase amount exceeds a predetermined threshold from the clusters, based on the distribution of the number of products purchased by each user. For example, the classification device 100 can classify the user U2 and the user U4, who are users who have purchased only the refrigerator, into different clusters based on the distribution of the number of items purchased by each user. A cluster can be generated that classifies users into regular users and merchant users.

  Further, in the classification device 100 according to the embodiment, the classification unit 132 classifies users into clusters based on the distribution for each category of products or services purchased by the user.

  Thereby, the classification device 100 according to the embodiment can appropriately classify the user based on the distribution for each category of products or services purchased by the user.

  In addition, the classification device 100 according to the embodiment includes a providing unit 134. The providing unit 134 provides a service to the user according to the cluster based on the classification of the user by the classification unit 132.

  Thereby, the classification apparatus 100 according to the embodiment can appropriately provide a service related to the review based on the cluster based on the classification of the user.

  Further, in the classification device 100 according to the embodiment, the providing unit 134 allows one user belonging to one cluster to receive a product or service that one user has not purchased and another user belonging to one cluster. Provide information about purchased goods or services.

  As a result, the classification device 100 according to the embodiment allows a user belonging to one cluster to purchase a product or service that is not purchased by one user and purchased by another user belonging to the one cluster. By providing the information regarding the service, the service regarding the review can be appropriately provided.

[7. Hardware configuration)
The classification apparatus 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 10, for example. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the classification device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

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

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and provides the data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

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

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

  Although the embodiments of the present application have been described in detail with reference to the drawings, these are merely examples, and various modifications and improvements have been made based on the knowledge of those skilled in the art including the aspects described in the disclosure line of the invention. The present invention can be implemented in other forms.

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

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  Further, the above-described embodiments can be appropriately combined within a range in which processing contents are not contradictory.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Classification system 100 Classification apparatus 121 User information storage part 122 Cluster information storage part 123 Advertisement information storage part 130 Control part 131 Acquisition part 132 Classification part 133 Extraction part 134 Provision part 10 Terminal apparatus 50 Commercial transaction apparatus N Network

Claims (9)

An acquisition unit for acquiring information related to the purchase of goods or services made by the user;
A classification unit that classifies the users into clusters based on a distribution of information about the purchase acquired by the acquisition unit;
A classification apparatus comprising: The classification unit includes:
The classification device according to claim 1, wherein the users are classified into clusters based on a distribution of the number of the products or services purchased by the user. The classification unit includes:
The classification device according to claim 1 or 2, wherein the user is classified into a cluster based on a distribution of a price of the product or service purchased by the user. The extraction part which extracts the special cluster to which the special user in which the quantity regarding purchase exceeds a predetermined threshold among the clusters based on the said user's classification | category by the said classification | category part is further provided. Classification device according to. The classification unit includes:
The classification device according to any one of claims 1 to 4, wherein the user is classified into clusters based on a distribution for each category of the product or service purchased by the user. A providing unit that provides a service to a user according to a cluster based on the classification of the user by the classification unit;
The classification device according to claim 1, further comprising: The providing unit includes:
Providing to one user belonging to one cluster information related to a product or service not purchased by the one user but purchased by another user belonging to the one cluster The classification device according to claim 6. A classification method performed by a computer,
An acquisition process for acquiring information about the purchase of goods or services made by the user;
A classification step of classifying the users into clusters based on a distribution of information about the purchase acquired by the acquisition step;
Classification method characterized by including. An acquisition procedure to obtain information about the purchase of goods or services made by the user;
A classification procedure for classifying the users into clusters based on a distribution of information about the purchase acquired by the acquisition procedure;
A classification program characterized by causing a computer to execute.

Images