JP6805340B2 - Information processing system, information processing method, and program - Google Patents

Description

The present invention relates to information processing systems, information processing methods, and programs.

Conventionally, a technique for analyzing an action history such as a user browsing a website or purchasing a product has been known. For example, in Patent Document 1, each user is assigned to a cluster which is a group of users having similar tastes based on the content history of each of a plurality of users, and the content history characteristics of the representative user of each cluster and the content history characteristics of the new user are described. A system that provides content that suits the tastes of new users by allocating new users to any cluster based on the content history characteristics is described.

Japanese Unexamined Patent Publication No. 2013-900162

However, the content history characteristics of Patent Document 1 are calculated from the behavior history in all of various fields having different characteristics from each other, and do not indicate detailed preferences for each field. For example, when calculating the content history characteristics, the preference in a certain field and the preference in another field are offset, and the information does not indicate the preference peculiar to the field. Therefore, in the technique of Patent Document 1, even if a new user is assigned to the cluster by utilizing the content history characteristic, the accuracy of the information presented to the user cannot be sufficiently improved.

The present invention has been made in view of the above problems, and an object of the present invention is to provide an information processing system, an information processing method, and a program capable of improving the accuracy of information presented to a user.

In order to solve the above problems, the information processing system according to the present invention has a first acquisition means for acquiring data item feature information relating to each feature of a plurality of data items, and an action history relating to a user's behavior history for each data item. Based on the second acquisition means for acquiring information, the clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information, and the processing result of the clustering means. It is characterized by including a presenting means for presenting data item information regarding at least one of the plurality of data items to the user.

The information processing method according to the present invention has a first acquisition step of acquiring data item feature information relating to each feature of a plurality of data items, and a second acquisition step of acquiring behavior history information relating to the user's behavior history for each data item. A clustering step for clustering each data item based on the data item feature information of each data item indicated by the action history information, and a plurality of data items based on the processing result of the clustering step. It is characterized by including a presentation step of presenting data item information regarding at least one to the user.

The program according to the present invention includes a first acquisition means for acquiring data item feature information relating to each feature of a plurality of data items, a second acquisition means for acquiring behavior history information relating to a user's behavior history for each data item, and the above-mentioned behavior. Data relating to at least one of the plurality of data items based on a clustering means for clustering each data item based on the data item feature information of each data item indicated by the history information and the processing result of the clustering means. The computer functions as a presentation means for presenting the item information to the user.

Further, the information storage medium according to the present invention is a computer-readable information storage medium in which the above program is stored.

Further, in one aspect of the present invention, the clustering means acquires user characteristic information for each cluster based on the data item feature information of each data item belonging to the cluster, and the presenting means of each cluster It is characterized in that the data item information is presented based on the user feature information and the data item feature information of each data item.

Further, in one aspect of the present invention, the user feature information of each cluster and the data item feature information of each data item are represented by vectors, respectively, and the presenting means is the user feature information of each cluster. The data item information is presented based on the comparison result of the vector indicated by and the vector indicated by the data item feature information of each data item.

Further, in one aspect of the present invention, the clustering means acquires the average value of the vectors indicated by the data item feature information of each data item belonging to each cluster as the user feature information of the cluster. To do.

Further, in one aspect of the present invention, the presenting means sets the data item feature information of the data item in each cluster among the plurality of data items as a comparison target with the user feature information of the cluster. It is characterized by that.

Further, in one aspect of the present invention, the first acquisition means acquires the data item feature information of each data item based on the action history information of each of a plurality of users.

Further, in one aspect of the present invention, the data item feature information of each data item includes preset classification information of the data item.

Further, in one aspect of the present invention, the clustering means changes the cluster size based on the action history information.

Further, in one aspect of the present invention, the action history information includes action type information regarding the type of action of the user for each data item, and the presenting means further based on the action type information, the data item information. It is characterized by presenting.

Further, in one aspect of the present invention, the action history information includes action time information regarding the action time of the user for each data item, and the presenting means further obtains the data item information based on the action time information. It is characterized by presenting.

Further, in one aspect of the present invention, the data item information is coupon information or recommendation information regarding at least one of the plurality of data items.

Further, in one aspect of the present invention, each data item is a data item related to a product, and the first acquisition means acquires the data item feature information regarding the characteristics of each of a plurality of products, and the second acquisition means. Acquires the behavior history information regarding the user's behavior history for each product, and the clustering means clusters each product based on the data item feature information of each product indicated by the behavior history information. The presenting means is characterized in that the data item information regarding at least one of the plurality of products is presented to the user.

According to the present invention, the accuracy of the information presented to the user can be improved.

It is a figure which shows the whole structure of an information processing system. It is a functional block diagram which shows an example of a function realized by an information processing system. It is a figure which shows an example of a product database. It is a figure which shows an example of a user database. It is a figure which shows an example of a coupon database. It is a figure which shows the processing content of a clustering part. It is a flow chart which shows the preparatory processing. It is a figure which shows the detail of the process of S2. It is a flow chart which shows the coupon presentation process. It is a figure which shows the screen example of a product page.

[1. Overall configuration of information processing system]
Hereinafter, examples of embodiments of the information processing system according to the present invention will be described. FIG. 1 is a diagram showing an overall configuration of an information processing system. As shown in FIG. 1, the information processing system 1 includes a server 10 and a user terminal 20, which are connected so as to be able to send and receive data via a network. Although FIG. 1 shows one server 10 and one user terminal 20, there may be a plurality of these. Further, the information processing system 1 may include a computer other than the server 10 and the user terminal 20.

The server 10 is a server computer, and includes, for example, a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 includes at least one processor. The control unit 11 executes processing according to the programs and data stored in the storage unit 12. The storage unit 12 includes a main storage unit and an auxiliary storage unit. For example, the main storage unit is a volatile memory such as RAM, and the auxiliary storage unit is a non-volatile memory such as a hard disk or flash memory. The communication unit 13 includes a communication interface for wired communication or wireless communication, and performs data communication via a network, for example.

The user terminal 20 is a computer operated by the user, and is, for example, a personal computer, a personal digital assistant (including a tablet computer), a mobile phone (including a smartphone), or the like. The user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25. The hardware configurations of the control unit 21, the storage unit 22, and the communication unit 23 may be the same as those of the control unit 11, the storage unit 12, and the communication unit 13, respectively. The operation unit 24 is an input device for the user to perform an operation, and is, for example, a pointing device such as a touch panel or a mouse, a keyboard, or the like. The operation unit 24 transmits the operation content of the user to the control unit 21. The display unit 25 is, for example, a liquid crystal display unit, an organic EL display unit, or the like.

The programs and data described as being stored in the storage units 12 and 22 may be supplied to them via a network. Further, the hardware configuration of the server 10 and the user terminal 20 is not limited to the above example, and various hardware can be applied. For example, the server 10 and the user terminal 20 are read / output units (for example, USB) for directly connecting to a reading unit (for example, an optical disk drive or a memory card slot) for reading a computer-readable information storage medium or an external device, respectively. Terminal) may be included. In this case, the program or data stored in the information storage medium may be supplied to the server 10 or the user terminal 20 via the reading unit or the input / output unit.

[2. Information processing system overview]
In the information processing system 1, a plurality of data items are stored in the server 10, and arbitrary data items are provided to the user. The data item is data for providing predetermined information to the user. The content of the data item may be arbitrary and may be, for example, content relating to a product, service, or content.

The goods may be tangible items such as foodstuffs, clothing, furniture, home appliances, or electronic devices, as long as they are objects to be traded, or intangible items such as contents described later. May be good. For example, the data item is data for displaying the product page on the user terminal 20. The data item may be HTML of the product page, or may be an image or text to be inserted in the frame of the product page. The frame is data that defines the screen layout when the screen is displayed in the application.

The service may be any service of content, such as travel reservations, insurance applications, restaurant reservations, lottery purchases, or financial services. For example, the data item is data for displaying the service usage application page on the user terminal 20. The data item may be HTML of the usage application page, or may be an image or text to be inserted in the frame of the usage application page.

The content may be content of any content, such as websites, coupons, advertisements, e-books, videos, images, songs, or applications. For example, the product page and the service usage application page can be said to be examples of contents. For example, the data item may be the content data itself, or may be data for displaying the content download page on the user terminal 20. The data item may be HTML of the download page, or may be an image or text to be inserted in the frame of the download page.

In the present embodiment, the case where each data item is a data item related to a product will be described as an example. In the following description, the "data item" is simply referred to as a "product" for the sake of brevity. Therefore, the part described as "product" in this embodiment can be read as "data item".

In the present embodiment, the user operates the user terminal 20 to access the server 10 to browse or purchase products handled by a virtual store on the Internet. The user's browsing history and purchase history are recorded as an action history. The information processing system 1 analyzes the user's behavior history for each product and executes product clustering for each user.

Clustering is a process for grouping (classifying) observation data. In this embodiment, each product corresponds to observation data. A cluster is an individual group and a unit of classification. Clusters are conceptually a bit like categories in terms of product classification. However, while the categories are information common to all users, the clusters are different for each user and reflect the user's unique preferences.

The information processing system 1 of the present embodiment calculates the user characteristic information regarding the user's preference for each cluster based on the product characteristic information of the products belonging to the cluster. Then, the information processing system 1 analyzes the user-specific preferences for each cluster by presenting the coupon information of the product based on the user characteristic information of each cluster, and improves the accuracy of the coupon information presented to the user. I have to. Hereinafter, the details of the configuration will be described.

[3. Functions realized in this embodiment]
FIG. 2 is a functional block diagram showing an example of the functions realized by the information processing system 1. As shown in FIG. 2, in the present embodiment, the data storage unit 100, the first acquisition unit 101, the second acquisition unit 102, the clustering unit 103, and the presentation unit 104 are realized by the server 10. The data storage unit 100 is mainly realized by the storage unit 12, and each of the first acquisition unit 101, the second acquisition unit 102, the clustering unit 103, and the presentation unit 104 is mainly realized by the control unit 11.

[3-1. Data storage]
The data storage unit 100 stores data necessary for executing the process according to the present embodiment. Here, as an example of the data stored in the data storage unit 100, the product database DB1, the user database DB2, and the coupon database DB3 will be described.

FIG. 3 is a diagram showing an example of the product database DB1. As shown in FIG. 3, the product database DB1 is a database in which various information about products is stored. For example, the product database DB1 stores a store ID, a product ID, basic product information, and product feature information. The store ID is information that uniquely identifies a store on the Internet. The product ID is information that uniquely identifies the product handled by the store.

The basic information of a product is basic information about the content of the product, and includes, for example, a product name (product title), a category (genre), an attribute, a unit price, an inventory quantity, a keyword, and a product description. The attribute is the property of the product, for example, information such as the color, size, material, condition, place of origin, or manufacturer of the product. The keyword is a word for searching a product, and may be, for example, a word extracted from a product name or a product description, or a word input as a keyword by a store clerk. The item description is a detailed description of the item, indicated by, for example, at least one of text, table, and image.

For example, the basic information of the product is input by the person in charge of the store. The basic information of the product may include other information, and may include various information such as the URL of the product page, the HTML data of the product page, the frame, or the image data. The product page may be a screen for purchasing a product, for example, basic information of the product such as a product name, a product image, a product description, and a unit price, and a button for putting the product in the shopping cart. Including. The product page may be displayed in the web browser of the user terminal 20 or may be displayed in the application installed in the user terminal 20.

The product feature information is information about the feature of the product, and includes, for example, the feature amount of each of the plurality of items. The item may be any item for evaluating the characteristics of the product, for example, it may be an item related to the basic information of the product, or an item related to the basic information of the user who browsed or purchased the product. There may be. For example, the feature quantity is information that quantifies the features of the product of each item. The feature amount may be indicated by characters instead of numerical values, or may be indicated by a combination of numerical values and characters.

For example, in the product feature information, words included in the product name, keywords, and product description may be items, or categories, attributes, or price ranges may be items. When a word is an item of product feature information, the feature amount of the item may be a feature vector of the word. As a method for acquiring a word feature vector, various known methods can be applied, and for example, a neural network such as Word2vec may be used. Further, for example, the product feature information may include the age, gender, or region of the user who browsed or purchased the product.

In the present embodiment, the case where the product feature information is represented by an n (n is a natural number) -dimensional vector will be described as an example. That is, the product feature information includes the feature amounts of n items, and the feature amounts of each item are shown as the values of each element of the vector. The product feature information may be in a format other than a vector, and can be expressed in any format. For example, the product feature information may be information in any format such as an array format, an image format, a text format, or a table format.

Further, in the present embodiment, the case where the product feature information of each product includes the preset classification information of the product will be described. For example, in the n-dimensional vector indicated by the product feature information, the kth element (k is an integer of 1 or more and n or less) is a value indicating the product classification information. The classification information is at least one preset from a plurality of classification information, and is, for example, information such as a category (genre), an attribute, or a price range. The price range is a price range to which the unit price belongs from among a plurality of price ranges.

In the present embodiment, as an example of the classification information, the category stored in the basic information of the product (that is, the category input by the person in charge of the store) will be described. Therefore, the part described as a category in this embodiment can be read as classification information. The kth element of the product feature information is a feature amount indicating a category. Which numerical value indicates which category may be determined in advance in the data storage unit 100.

In the present embodiment, the case where both the information input by the person in charge of the store and the information generated by the server 10 are included in the product feature information will be described, but the product feature information is in charge of the store. It may include only the information input by the person or only the information generated by the server 10. In addition, the items included in the product feature information are not limited to the above examples, and any item can be applied. For example, it may be an item related to the date and time when the product was browsed or purchased, or it may be an item related to the search formula used when the product was browsed or purchased. The search formula is a search condition, and is, for example, at least one of a keyword, a category, an attribute, a price range, and whether or not there is inventory.

FIG. 4 is a diagram showing an example of the user database DB2. As shown in FIG. 4, the user database DB2 is a database in which various information about the user is stored. For example, the user database DB2 stores a user ID, basic user information, action history information, and cluster information. The user ID is information that uniquely identifies the user.

The basic information of the user is the registered information of the user, and for example, information such as a user name, age, gender, and region is stored. The basic information of the user may include other information, for example, information such as a favorite category of the user may be included.

The action history information is information on the user's action history for each product, and for example, information such as identification information of the product to be acted (here, a combination of a store ID and a product ID), action type information, and action time information is provided. Stored in chronological order.

The action target is a target of action by the user, for example, a target of browsing, purchasing, or downloading. The action type information is information on the type of action, and is information indicating the type of action taken by the user among a plurality of types such as browsing, purchasing, and downloading. The action time information is information indicating the date and time when the user acted, and is, for example, information such as a browsing date and time, a purchase date and time, or a download date and time.

The server 10 updates the action history information based on the communication content with the user terminal 20. For example, when the server 10 receives a product page browsing request from the user, the server 10 transmits the display data of the product page to the user terminal 20. Then, the server 10 stores the store ID and product ID of the product indicated by the product page in the action history information of the record in which the user ID of the user is stored, sets "browsing" in the action type information, and acts. Set the current date and time in the time information.

Further, for example, when the server 10 receives a purchase request for a product from a user, the server 10 executes a purchase process for the product. Various known processes can be applied to the purchase process itself, and for example, a payment process using a credit card is executed. Then, the server 10 stores the store ID and product ID of the product indicated on the product page in the action history information of the record in which the user ID of the user is stored, sets "purchase" in the action type information, and acts. Set the current date and time in the time information.

The cluster information is information about the cluster specified by the clustering unit 103, and includes, for example, a cluster number, user characteristic information, weighting coefficient, action type information, and action time information. The cluster number is information that uniquely identifies the cluster. Since the cluster is acquired for each user, the cluster number can be said to be information that uniquely identifies the cluster among the plurality of clusters acquired for a certain user.

The user characteristic information is information that comprehensively indicates the characteristics of the products in the cluster. The user characteristic information is generated for each cluster, and is, for example, a value obtained by substituting the product characteristic information of the product to be acted belonging to the cluster into a predetermined mathematical formula. This formula may be any formula, for example, a formula for obtaining a simple average or a weighted average. In the present embodiment, since the product feature information is represented by a vector, a case where the user feature information is also represented by a vector will be described as an example.

The weighting factor is the importance (probability) of the cluster. For example, the higher the weighting factor, the more important the cluster, and the lower the weighting factor, the less important the cluster.

The action type information is information on the type of action for a product belonging to the cluster. Here, the action type information shall take either a value of "purchased" or "view only". If at least one product belonging to the cluster as an action target is purchased, the action type information of the cluster is "purchased", and if not, the action type information of the cluster is "view only". The type of action is not limited to purchase and browsing, and may be, for example, an action such as putting a product in a shopping cart.

The action time information is information on the action time for the products belonging to the cluster. Here, the action time information stores the action time for the "purchased" product.

The items included in the action history information are not limited to the above examples, and any item can be applied. For example, the behavior history information may include a search formula used when the product was browsed or purchased. In addition, the user database DB2 may include information such as coupon information acquired by the user.

FIG. 5 is a diagram showing an example of the coupon database DB3. As shown in FIG. 5, the coupon database DB3 is a database in which various information related to coupons is stored. For example, the coupon database DB3 stores a coupon ID, identification information of a store or product targeted for a coupon (here, a combination of a store ID and a product ID), coupon contents, and product feature information. The coupon ID is information that uniquely identifies the coupon.

The content of the coupon is an effect when the coupon is used, and information such as a discount amount, a discount percentage (percentage), and an extra product is stored. The product feature information is the product feature information of the product to which the coupon is applied. When the coupon target is a store, it may be the product feature information of a specific product handled by the store, or it may be calculated from the product feature information of each of a plurality of products of the store. Information such as the validity period of the coupon may be stored in the coupon database DB3.

For example, the coupon database DB3 is updated by the person in charge at each store. For example, the person in charge of the store that issues the coupon transmits to the server 10 the store ID of the store, the product ID of the product that is the target of the coupon, and the registration request of the contents of the coupon. When the server 10 receives the registration request from the person in charge of the store, the server 10 issues a coupon ID and stores the coupon ID in association with the store ID, the product ID, and the contents of the coupon in the coupon database DB3. Then, the server 10 refers to the product database DB 1, acquires the store ID and the product feature information associated with the product ID, and stores the product feature information associated with the product ID in the coupon database DB 3 in association with the issued coupon ID.

The data stored in the data storage unit 100 is not limited to the above example. The data storage unit 100 may store data necessary for the processing according to the embodiment. For example, the data storage unit 100 may store the relationship between the action history information and the product feature information (details will be described later).

[3-2. 1st acquisition department]
The first acquisition unit 101 acquires product feature information regarding the features of each of the plurality of products. In the present embodiment, since the product feature information is stored in the product database DB 1, the first acquisition unit 101 acquires the product feature information of each product stored in the data storage unit 100. When the product feature information is stored in a computer other than the server 10 (for example, an external database server), the first acquisition unit 101 may acquire the product feature information of each product from the computer.

For example, the first acquisition unit 101 may acquire the product feature information of each product based on the behavior history information of each of the plurality of users. In this case, the first acquisition unit 101 may acquire the product feature information of each product based on the behavior history information of all the users of the information processing system 1, or the behavior of some users of the information processing system 1. Product feature information of each product may be acquired based on the history information. Further, for example, the first acquisition unit may acquire the feature amounts of all the items of the product feature information based on the behavior history information of each user, or acquire the feature amounts of some items of the product feature information. You may.

It is assumed that the relationship between the behavior history information of each user and the product feature information of each product is stored in advance in the data storage unit 100. This relationship may be defined in mathematical or tabular form, or as part of the program code. The first acquisition unit 101 acquires the product feature information of each product associated with the behavior history information of each user. That is, the first acquisition unit 101 uses the action history information of each user as the input of the above relationship, and acquires the product feature information of each product as the output of the above relationship.

For example, the first acquisition unit 101 acquires the product feature information of each product so that the product feature information of the products browsed or purchased from the search result obtained by a certain search formula is similar. Further, for example, the first acquisition unit 101 may refer to the keyword used when the product is browsed or purchased, and acquire the product feature information of the product based on the word included in the keyword. In this case, the first acquisition unit 101 may use the feature vector of the word included in the keyword as the feature amount of some items of the product feature information.

Further, for example, when the product feature information includes information about the user, the first acquisition unit 101 may acquire the product feature information of each product based on the basic information of each user. For example, when the item of the product feature information includes at least one of the age, gender, and region of the user who browses or purchases the product, the first acquisition unit 101 refers to the user database DB2 and of each product. The feature amount of the item of the product feature information may be acquired based on the age, gender, and region of the user who targeted the product.

The product feature information of each product is not acquired based on the behavior history information, but the information input by the store manager may be used as the product feature information as it is, or may be entered by the store manager. Information generated based on the information may be used as product feature information.

[3-3. 2nd acquisition department]
The second acquisition unit 102 acquires the behavior history information regarding the behavior history of the user for each product. In the present embodiment, since the action history information is stored in the user database DB 2, the second acquisition unit 102 acquires the action history information stored in the data storage unit 100. For example, the second acquisition unit 102 acquires the action history information of each user stored in the user database DB2. When the action history information is stored in a computer other than the server 10 (for example, an external database server), the second acquisition unit 102 may acquire the action history information of each user from the computer.

[3-4. Clustering section]
The clustering unit 103 clusters each product based on the product feature information of each product indicated by the action history information. In the present embodiment, clustering is a process for grouping products having similar product feature information. Clustering is sometimes referred to as data clustering, unsupervised learning, or data mining.

The clustering unit 103 performs clustering for each user based on the behavior history information of the user. In other words, the clustering unit 103 performs clustering for the user based on the behavior history information of each user. For example, the clustering unit 103 identifies a product to be acted by the user based on the behavior history information of each user, and executes clustering for the user based on the product feature information of each identified product. Therefore, when the clustering unit 103 executes clustering of a certain user, the clustering unit 103 refers to the behavior history information of the user, but does not refer to the behavior history information of another user.

As the clustering algorithm itself, various known methods can be applied, and for example, an algorithm using a hierarchical method such as the shortest distance method, the longest distance method, the group average method, and the Ward method may be used. , K-means method or other non-hierarchical method may be used. For example, DBSCAN (Density-based spatial clustering of applications with noise) may be used.

FIG. 6 is a diagram showing the processing contents of the clustering unit 103. As shown in FIG. 6, in the present embodiment, the product feature information is represented by an n-dimensional vector, so that the clustering unit 103 converts the n-dimensional vector indicated by the product feature information of the product to be acted into the n-dimensional space SP. Map and perform clustering of each product based on a hierarchical or non-hierarchical algorithm.

In the example of FIG. 6, the clustering unit 103 maps the vectors V1 to V40 indicated by the product feature information of 40 products to the n-dimensional space SP, and sets three clusters CL1 to CL3. Products corresponding to the vectors V1 to V13 belong to the cluster CL1. Products corresponding to the vectors V14 to V26 belong to the cluster CL2. Products corresponding to the vectors V27 to V39 belong to the cluster CL3.

For example, the clustering unit 103 issues a cluster number of each cluster CL1 to CL3 based on a predetermined rule, and associates the cluster number with the product based on the product feature information of each product to be acted. Update the information. Note that the clustering unit 103 may remove products that are far from any of the clusters CL1 to CL3 (in the example of FIG. 6, the product corresponding to the vector V40) as noise. In the following description, the reference numerals of the cluster and the vector are omitted when it is not necessary to refer to FIG.

For example, the clustering unit 103 may acquire user characteristic information for each cluster based on the product characteristic information of each product belonging to the cluster. The clustering unit 103 acquires the user characteristic information by substituting the product characteristic information of each product belonging to the cluster into a predetermined mathematical formula for each cluster. As described above, this formula may have arbitrary contents, and may be, for example, a formula for obtaining a simple average or a weighted average.

In the present embodiment, the product feature information is indicated by a vector. Therefore, for example, the clustering unit 103 acquires the average value of the vectors indicated by the product feature information of each product belonging to each cluster as the user feature information of the cluster. May be good. In other words, the average value is a joint vector of vectors indicated by product feature information of each product belonging to the cluster.

In the example of FIG. 6, the clustering unit 103 acquires the joint vector, which is the average value of the vectors V1 to V13, as the user characteristic information of the cluster CL1 and stores it in the cluster information. The clustering unit 103 acquires the joint vector, which is the average value of the vectors V14 to V26, as the user characteristic information of the cluster CL2 and stores it in the cluster information. The clustering unit 103 acquires the joint vector, which is the average value of the vectors V27 to V39, as the user characteristic information of the cluster CL3 and stores it in the cluster information.

In the present embodiment, the cluster information includes not only the user characteristic information but also the weighting coefficient. Therefore, the clustering unit 103 sets the weighting coefficient stored in the cluster information of the user based on the behavior history information of each user. You may decide.

Further, for example, in the clustering unit 103, the larger the number of products included in the cluster, the stronger the user may be interested in the products in the cluster. Therefore, the weighting coefficient is increased and the products included in the cluster are included in the cluster. The smaller the number of, the less the user may be interested in the products in the cluster, so the weighting factor may be reduced.

Further, for example, the clustering unit 103 increases the weighting coefficient and clusters the cluster because the larger the cluster size of the cluster, the more products are included in the cluster and the user may be strongly interested in it. The smaller the size, the less the cluster contains products and the less interested the user may be, so the weighting factor may be reduced.

Further, in the present embodiment, since the cluster information includes not only the user characteristic information but also the action type information, the clustering unit 103 is stored in the cluster information of the user based on the action history information of each user. The action type information may be determined.

For example, the clustering unit 103 may determine the behavior type information of the cluster based on the behavior type information of the products included in the cluster. For example, if the behavior type information of the products included in the cluster is only browsing, the clustering unit 103 only browses the behavior type information of the cluster, and purchases a predetermined number of purchased products (for example, one or two or more). (Any number of) may be included, and the behavior type information of the cluster may be purchased.

For example, the clustering unit 103 refers to the behavior type information of the products included in the cluster, and if the cluster includes only the browsed products, the products may not have been purchased yet and the user's interest may be high. If the weight coefficient is increased and the cluster includes the purchased products, the products may have already been purchased and the user's interest may be low, so the weighting coefficient may be decreased.

Further, for example, even if the clustering unit 103 is a cluster including purchased products, if the products in the same cluster are browsed again after the products in the cluster are purchased, the user is interested again. Since it may have been shown, the weighting coefficient may be increased.

Further, in the present embodiment, since the cluster information includes not only the user characteristic information but also the action time information, the clustering unit 103 is stored in the cluster information of the user based on the action history information of each user. Action time information may be determined.

For example, the clustering unit 103 may determine the action time information of the cluster based on the action time information of the products included in the cluster. For example, the clustering unit 103 may use the average value of the action time information of the products included in the cluster as the action time information of the cluster, or may use the action time information of the purchased products among the products included in the cluster as the action time information of the cluster. It may be used as the action time information of.

Further, for example, the clustering unit 103 refers to the action time information of the products included in the cluster, and the shorter the elapsed time from the date and time when the user browses, the more the user's interest may not be diminished. Therefore, the weighting coefficient The weight coefficient may be reduced because the user's interest may have diminished as the elapsed time from the date and time when the user browsed is increased.

Further, for example, the clustering unit 103 refers to the action time information of the products included in the cluster, and the longer the elapsed time from the date and time when the user purchased the product, the more likely the user may purchase the product again. The weighting coefficient may be reduced because the larger the value and the shorter the elapsed time from the date and time of the purchase by the user, the more likely the user has not yet purchased the product.

Further, for example, the clustering unit 103 may change the cluster size based on the action history information. The cluster size is the size (wide range) of the cluster, and is also called the particle size. For example, the clustering unit 103 may reduce the cluster size as the number of products belonging to the cluster increases, and may increase the cluster size as the number of products belonging to the cluster decreases. Further, for example, the clustering unit 103 may refer to the mapping result of the product feature information of each product to be acted on, and may decrease the cluster size as the product density increases and increase the cluster size as the product density decreases. ..

[3-5. Presentation section]
The presenting unit 104 presents the product information regarding at least one of the plurality of products to the user based on the processing result of the clustering unit 103. The presenting unit 104 selects at least one product from a plurality of products based on the processing result of the clustering unit 103, and presents the product information regarding the at least one product to the user.

The product information may be information about the product, for example, coupon information or recommendation information about at least one of a plurality of products, the product page itself, or contents different from the product page. It may be a description or a product image.

The coupon information may be information for giving a predetermined privilege to the user, for example, information for purchasing a product at a discounted price, or information for obtaining a bonus other than the product. You may. The recommendation information may be any information for proposing a product to the user, and may be, for example, a link to a product page or an image in which the link is embedded. In this embodiment, coupon information will be described as an example of product information. Therefore, the portion described as coupon information in this embodiment can be read as product information.

The presentation is a visual presentation and is a process for displaying product information. Any method can be applied to the presentation method by the presentation unit 104, and may be, for example, display of an image in a page, transmission of an e-mail, transmission of a message using a message application, or push notification. In the present embodiment, a case where the presentation unit 104 displays coupon information on an arbitrary page such as a top page of a virtual market, a top page of a store, or a product page will be described as an example.

For example, the presenting unit 104 presents coupon information based on the user characteristic information of each cluster and the product characteristic information of each product. In the present embodiment, the user characteristic information of each cluster is information obtained by averaging the characteristics of the products belonging to the cluster, so that the presentation unit 104 can use the user of each cluster from among the plurality of products registered in the coupon database DB3. A product having product characteristic information similar to the characteristic information is specified, and coupon information of the specified product is presented.

Further, in the present embodiment, the user feature information of each cluster and the product feature information of each product are shown as vectors, so that the presentation unit 104 includes the vector indicated by the user feature information of each cluster and each of them. Coupon information is presented based on the comparison result with the vector indicated by the product feature information of the product. For example, the presenting unit 104 presents coupon information based on the distance between the vector indicated by the user characteristic information of each cluster and the vector indicated by the product characteristic information of each product.

For example, the presentation unit 104 identifies a predetermined number of products in ascending order of distance, and presents coupon information for the product. This number may be a fixed value regardless of the clusters, but in the present embodiment, it is assumed that the number varies depending on the weighting coefficient of each cluster. For example, the larger the weighting coefficient, the larger the number, and the smaller the weighting coefficient, the smaller the number. The relationship between the weighting coefficient and the number of weights may be stored in the data storage unit 100 in advance. This relationship may be defined in mathematical or tabular form, or as part of the program code. For example, the presenting unit 104 acquires and presents coupon information for each cluster in the order in which the distances are shorter by the number determined by the weighting coefficient of the cluster.

For example, in the case of the data storage example as shown in FIG. 4, the cluster information of "user X" has a weight coefficient of "2" for the cluster whose cluster number is "1" and a weight for the cluster whose cluster number is "2". The coefficient is "5", and the weighting coefficient of the cluster whose cluster number is "3" is "3". Therefore, assuming that the total number of coupon information presented to the user is 10, the presenting unit 104 acquires two coupon information in the order of closest distance to the user feature information having the cluster number "1", and the cluster number is "2". 5 coupon information is acquired in the order of proximity to the user feature information of "3", and 3 coupon information is acquired in order of proximity to the user feature information of cluster number "3". The presentation unit 104 presents the acquired 10 cupoin information by including it in the product page or the like.

For example, the product feature information of all products may be compared with the user feature information of each cluster, but the presenting unit 104 sets the product feature information of the products in each cluster among the plurality of products to the cluster. It may be compared with the user characteristic information of. For example, the presentation unit 104 identifies the products belonging to the cluster based on the product feature information of each product for each cluster. The presentation unit 104 makes the specified product a comparison target. In other words, the presenting unit 104 excludes the products in the cluster from the comparison target and the products outside the cluster from the comparison target among the plurality of products registered in the coupon database DB3.

In the present embodiment, since the action history information includes the action type information regarding the type of the user's action for each product, the presenting unit 104 may present the coupon information based on the action type information. For example, the presenting unit 104 may not present the coupon information for the product whose action type information indicates a predetermined type. A predetermined type is a behavior that is likely to cause the user to lose interest in the product, such as a purchase.

The presentation unit 104 may exclude the cluster including the product whose action type information indicates the purchase from the presentation target of the coupon information. Even if the action type information is a cluster including a product indicating a purchase, the presentation unit 104 may again use the cluster as a coupon information presentation target when the user browses the cluster after the purchase. Further, when the weighting coefficient of each cluster is determined based on the action type information, the presenting unit 104 determines the product to which the coupon information is presented based on the weighting coefficient, and thus is based on the action type information. You are presenting coupon information.

In the present embodiment, since the action history information includes the action time information regarding the action time of the user for each product, the presenting unit 104 presents the coupon information based on the action time information. For example, the presenting unit 104 does not present the coupon information if the elapsed time from the action time indicated by the action time information is less than the threshold value, and presents the coupon information if the elapsed time is equal to or more than the threshold value. You may. Further, when the weighting coefficient of each cluster is determined based on the action time information, the presenting unit 104 determines the product to which the coupon information is presented based on the weighting coefficient, and thus is based on the action time information. You are presenting coupon information.

[4. Process executed in this embodiment]
Next, the flow of processing executed by the information processing system 1 will be described. Here, a pre-preparation process for presenting a coupon and a coupon presenting process for presenting a coupon to a user will be described. The pre-preparation process and the coupon presentation process are examples of processes executed by the functional block shown in FIG.

[4-1. Preparatory processing]
FIG. 7 is a flow chart showing a preparatory process. The preparatory process is executed by the control unit 11 operating according to the program stored in the storage unit 12. The preparatory process may be executed at a predetermined timing, for example, may be executed according to an instruction of the system administrator, or may be executed at a predetermined date and time.

As shown in FIG. 7, first, the control unit 11 generates product feature information of each product based on the behavior history information of each of the plurality of users stored in the user database DB2 (S1). In S1, the control unit 11 refers to the action history information of all users or some users, and generates product feature information of the product based on the product that is the action target of each user. The process of generating product feature information from the action history information is as described above.

The control unit 11 generates user characteristic information of each cluster for each user (S2). FIG. 8 is a diagram showing details of the process of S2. As shown in FIG. 8, the control unit 11 determines the user to be processed based on the user database DB2 (S21). In S21, the control unit 11 may determine the user with the youngest user ID as the user to be processed, or may determine the user corresponding to the first record in the user database DB2 as the user to be processed. ..

The control unit 11 refers to the user database DB2 and acquires the action history information of the user to be processed determined in S21 (S22). In S22, the control unit 11 acquires the action history information of the record in which the user ID of the user to be processed is stored in the user database DB2. The control unit 11 may refer to all the action history information of the user to be processed, or may refer only to the action history information of the most recent predetermined number of days (for example, about 30 to 120 days). You may only refer to.

Based on the action history information acquired in S22, the control unit 11 maps the product feature information of each product that is the action target of the user to be processed into the n-dimensional space (S23). In S23, the control unit 11 refers to the product database DB1, acquires the product feature information of the product in which the store ID and the product ID are stored in the action history information, and sets it as the observation data of clustering.

The control unit 11 executes clustering of each product based on the mapping result in S23 (S24). In S24, the control unit 11 executes clustering of product feature information mapped in the n-dimensional space based on the clustering algorithm described above. The control unit 11 issues the cluster number of each cluster and stores the cluster number in the cluster information of the user to be processed. Then, the control unit 11 associates any cluster number with each product to which the product feature information is mapped in the n-dimensional space.

The control unit 11 determines the cluster to be processed based on the cluster information of the user to be processed (S25). In S25, the control unit 11 may determine the cluster with the lowest cluster number as the cluster to be processed, or may determine the cluster corresponding to the first record in the cluster information as the cluster to be processed.

The control unit 11 acquires the user characteristic information of the cluster to be processed based on the product characteristic information of each product belonging to the cluster to be processed (S26). In S26, the control unit 11 acquires the average value of the product feature information of each product belonging to the cluster to be processed as the user feature information of the cluster to be processed.

The control unit 11 determines whether or not the user characteristic information has been acquired for all the clusters (S27). In S27, the control unit 11 determines whether or not the process of S26 has been executed for all of the plurality of clusters whose cluster numbers have been generated by the clustering of S24.

When it is determined that there is a cluster for which the user characteristic information has not been acquired (S27; N), the process returns to the process of S26, and the user characteristic information of the next cluster is acquired. After that, the control unit 11 repeats the process of S26 until the user characteristic information of all the clusters acquired for the user to be processed is acquired.

On the other hand, when it is determined that the user feature information has been acquired for all the clusters (S27; Y), the control unit 11 determines whether or not the clustering has been executed for all the users (S28).

When it is determined that there is a user who has not executed clustering (S28; N), the process returns to the process of S21, and clustering is executed for the next user to be processed. After that, the control unit 11 acquires the user characteristic information of all the clusters acquired for the user to be processed next. On the other hand, when it is determined that clustering has been executed for all users (S28; Y), the processing of S2 ends and the process shifts to the processing of S3.

The control unit 11 associates the coupon with the product feature information based on the product database DB1 and the coupon database DB3 (S3), and the process ends. In S3, the control unit 11 refers to the coupon database DB3 and identifies the coupon currently registered. The control unit 11 refers to the store ID and the product ID of the specified coupon, acquires the product feature information stored in the product database DB1, and stores it in the coupon database DB3.

[4-2. Coupon presentation process]
FIG. 9 is a flow chart showing a coupon presentation process. The coupon presentation process is executed by the control unit 11 operating according to the program stored in the storage unit 12, and the control unit 21 operating according to the program stored in the storage unit 22.

As shown in FIG. 9, first, when the user performs a predetermined operation from the operation unit 24 in the user terminal 20, the control unit 21 transmits an access request to the server 10 together with the user ID (S31). The access request may be a request of a predetermined format, for example, a display request such as a top page or a product page of a virtual market. When displaying a page in a web browser, the access request may include the URL of the page, and when displaying the page in the application, the access request may include an ID that identifies the page. The user ID may be stored in the storage unit 22 in advance, or may be input from the operation unit 24.

When the server 10 receives the user ID and the access request, the control unit 11 refers to the user database DB2 and acquires the cluster information of the user who made the access request (S32). In S32, the control unit 11 acquires the cluster information of the record in which the user ID received together with the access request is stored.

The control unit 11 determines the coupon information to be presented to the user based on the cluster information acquired in S32 and the coupon database DB3 (S33). In S33, the control unit 11 determines the number of coupon information for each cluster based on the weighting coefficient, the action type information, and the action time information. Then, the control unit 11 acquires a predetermined number of coupons for each cluster in the order in which the distance between the user feature information and the product feature information of the cluster is short.

The control unit 11 generates page display data including the coupon information determined in S33 and transmits it to the user terminal 20 (S34). In S34, the control unit 11 embeds the coupon information determined in S33 in the top page, product page, or the like of the virtual market.

When the user terminal 20 receives the display data, the control unit 21 causes the display unit 25 to display a page including the coupon information based on the received display data (S35), and this process ends.

FIG. 10 is a diagram showing a screen example of a page including coupon information. In the example shown in FIG. 10, the case where the coupon information CP1 to CP2 is embedded in the top page P of the virtual market is shown. The coupon information CP1 to CP2 each include information such as an image of the product to be coupond, the application period of the coupon, the content of the coupon, and the store to be couponed. For example, coupon information selected by the user can be obtained from the top page P.

According to the information processing system 1 described above, the coupon information is presented after analyzing the user's preference in more detail based on the clustering result of each product targeted for the user's action. Therefore, the coupon information to be presented to the user. The accuracy of can be improved. For example, in the conventional technique, information indicating a user's preference is calculated regardless of the field. Therefore, when the preference in a certain field and the preference in another field are averaged, the characteristics of each other are canceled out. There was a possibility that the feature amount would indicate a completely unrelated product, but by setting a cluster for each user, it is possible to analyze the user's preferences in more detail and improve the accuracy of coupon information. .. Also, for example, a user's favorite product may exist across a plurality of categories, but clustering can be used to set up a cluster that straddles these multiple categories, and the cluster allows the user's preference to be fully understood. Can be identified. On the contrary, if the user does not like all the products in a certain category but only the products in a specific field in this category, the category is too broad to pinpoint the user's taste. However, the cluster can pinpoint the user's preference even in such a case. Therefore, since the cluster expresses the user's unique preference, the accuracy of the coupon information presented to the user can be improved.

Further, the information processing system 1 presents coupon information based on the user characteristic information acquired for each cluster, and the accuracy of the coupon information can be improved by simpler processing, thus reducing the processing load of the information processing system 1. can do.

In addition, the user feature information and the product feature information are shown as vectors, and the coupon information is presented based on the comparison result between the vector shown by the user feature information of each cluster and the vector shown by the product feature information of each product. Since the accuracy of the coupon information can be improved by simpler processing, the processing load of the information processing system 1 can be effectively reduced. Further, the memory consumption in the information processing system 1 can be suppressed by using a simple format called a vector for each of the user feature information and the product feature information.

Further, by setting the user characteristic information of each cluster as the average value of the product characteristic information of the products in the cluster, the accuracy of the user characteristic information is improved, so that the accuracy of the coupon information presented to the user is effectively improved. be able to. Further, since the user feature information can be acquired by a simpler process, the processing load of the information processing system 1 for acquiring the user feature information can be reduced.

Further, by using the product feature information of the products in the cluster as the comparison target with the user feature information of each cluster, the number of products to be compared is reduced, so that the processing load of the information processing system 1 can be reduced. it can. In addition, by reducing the number of products to be compared, it is possible to speed up the process of presenting coupon information.

In addition, by acquiring the product feature information of each product from the behavior history information of each user, the product feature information can be obtained based on the user's behavior, and the accuracy of the product feature information is improved, so that the product feature information is presented to the user. The accuracy of coupon information can be effectively improved.

Further, by including the product category in the product feature information, the accuracy of the product feature information is improved, so that the accuracy of the coupon information presented to the user can be effectively improved.

In addition, by changing the cluster size based on the behavior history information of each user, it is possible to set a finer cluster for the part where the product feature information is dense, and the accuracy of the cluster is improved. Therefore, the accuracy of the coupon information presented to the user can be effectively improved.

Further, by presenting the coupon information based on the type of the user's action, the accuracy of the coupon information presented to the user can be effectively improved.

Further, by presenting the coupon information based on the user's action time for each product, the accuracy of the coupon information presented to the user can be effectively improved.

Further, by presenting the coupon information of each product as the information to be presented to the user, it is possible to present useful information to the user.

Further, by setting the data item as a data item related to the product, useful information can be presented to the user who purchases the product.

[5. Modification example]
The present invention is not limited to the embodiments described above. It can be changed as appropriate without departing from the spirit of the present invention.

For example, the case where the user characteristic information is acquired for each cluster has been described, but the user characteristic information may not be acquired in particular. In this case, the presenting unit 104 may determine a product for which coupon information should be presented based on arbitrary product feature information among the products included in each cluster. Further, for example, the presenting unit 104 may set at least one product among the products included in each cluster as a target for presenting coupon information.

Further, for example, the product information may be recommendation information instead of coupon information. For example, the presentation unit 104 may display an image of the product to be recommended on the top page or the product page when the user accesses the server 10. Further, for example, the presentation unit 104 may send an e-mail containing the URL of the recommended product, or may display a message or push notification including the URL of the recommended product on the display unit 25.

Further, for example, the data item does not have to be a data item related to a product. For example, the process according to the present invention may be applied to data items related to services. In this case, the part described as "product" in the embodiment can be read as "service". For example, the data item feature information becomes service feature information related to service features and information related to the user's behavior history for each service. The clustering unit 103 clusters each service based on the service feature information of each service indicated by the action history information. The presenting unit 104 presents the user with service information regarding at least one of the plurality of services. For example, the presenting unit 104 embeds the coupon information or the recommendation information of the service in a predetermined page and presents it.

Further, for example, the process according to the present invention may be applied to data items related to contents. In this case, the part described as "product" in the embodiment can be read as "content". For example, the data item feature information becomes service feature information related to the feature of the content, and becomes information related to the user's action history for each content. The clustering unit 103 clusters each content based on the content feature information of each content indicated by the action history information. The presenting unit 104 will present the service information regarding at least one of the plurality of contents to the user. For example, the presentation unit 104 embeds the coupon information or the recommendation information of the content in a predetermined page and presents it.

Further, for example, the first acquisition unit 101, the second acquisition unit 102, the clustering unit 103, and the presentation unit 104 may be realized by the user terminal 20, respectively. In this case, each of these functions is mainly realized by the control unit 11. For example, the first acquisition unit 101 may acquire product feature information from the server 10 via the network. Further, for example, the second acquisition unit 102 may acquire the action history information from the server 10 via the network. Further, for example, the clustering unit 103 may execute clustering based on the acquired product feature information and action history information. Further, for example, the presenting unit 104 may present the product information based on the information received from the server 10 via the network.

Claims (15)

A first acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means.
Including
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The action type information associated with each cluster indicates a purchase if the action type for a data item belonging to the cluster is a purchase .
When the data item belonging to the cluster is browsed again after the action type information associated with each cluster indicates a purchase , the presentation means increases the weighting coefficient of the cluster and increases the weighting coefficient of each cluster. The data item information is presented based on the weighting factor .
An information processing system characterized by this. A first acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means.
Including
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The presenting means does not present the data item information when the action type indicated by the action type information associated with each cluster is a purchase, and when the type is another type, the presenting means Present data item information,
An information processing system characterized by this. A first acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means.
Including
The action history information includes action time information regarding the action time of the user for each data item.
The action time information for the data item belonging to the cluster is associated with each cluster.
When the elapsed time from the action time indicated by the action time information associated with each cluster is less than the threshold value, the presenting means does not present the data item information, and the elapsed time is equal to or greater than the threshold value. If the data item information is presented,
An information processing system characterized by this. The clustering means acquires user feature information for each cluster based on the data item feature information of each data item belonging to the cluster.
The presenting means presents the data item information based on the user feature information of each cluster and the data item feature information of each data item.
The information processing system according to any one of claims 1 to 3. The user feature information of each cluster and the data item feature information of each data item are shown as vectors.
The presenting means presents the data item information based on the comparison result of the vector indicated by the user feature information of each cluster and the vector indicated by the data item feature information of each data item.
The information processing system according to claim 4, wherein the information processing system is characterized by the above. The clustering means acquires the average value of the vectors indicated by the data item feature information of each data item belonging to each cluster as the user feature information of the cluster.
The information processing system according to claim 5, wherein the information processing system is characterized by the above. The presenting means makes the data item feature information of the data item in each cluster among the plurality of data items a comparison target with the user feature information of the cluster.
The information processing system according to claim 5 or 6, wherein the information processing system is characterized by the above. The data item feature information of each data item includes preset classification information of the data item.
The information processing system according to any one of claims 1 to 7. The clustering means changes the cluster size based on the action history information.
The information processing system according to any one of claims 1 to 8. The computer
The first acquisition step of acquiring data item feature information for each feature of a plurality of data items, and
The second acquisition step of acquiring the behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering step for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation step that presents data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering step.
And run
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The action type information associated with each cluster indicates a purchase if the action type for a data item belonging to the cluster is a purchase .
In the presentation step, when the data item belonging to the cluster is browsed again after the action type information associated with each cluster indicates a purchase, the weighting coefficient of the cluster is increased to increase the weighting coefficient of each cluster. The data item information is presented based on the weighting factor .
An information processing method characterized by this. The computer
The first acquisition step of acquiring data item feature information for each feature of a plurality of data items, and
The second acquisition step of acquiring the behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering step for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation step that presents data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering step.
And run
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The presentation step does not present the data item information when the action type indicated by the action type information associated with each cluster is a purchase, and when the type is another type, the present step Present data item information,
An information processing method characterized by this. The computer
The first acquisition step of acquiring data item feature information for each feature of a plurality of data items, and
The second acquisition step of acquiring the behavior history information related to the user's behavior history for each data item associated with the user identification information, and
A clustering step for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
For each user identification information, a presentation step that presents data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering step.
And run
The action history information includes action time information regarding the action time of the user for each data item.
The action time information for the data item belonging to the cluster is associated with each cluster.
When the elapsed time from the action time indicated by the action time information associated with each cluster is less than the threshold value, the presentation step does not present the data item information and the elapsed time is equal to or greater than the threshold value. If the data item information is presented,
An information processing method characterized by this. First acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information,
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
A presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means for each user identification information.
It is a program to make a computer function as
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The action type information associated with each cluster indicates a purchase if the action type for a data item belonging to the cluster is a purchase .
When the data item belonging to the cluster is browsed again after the action type information associated with each cluster indicates a purchase , the presentation means increases the weighting coefficient of the cluster and increases the weighting coefficient of each cluster. The data item information is presented based on the weighting factor .
program. First acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information,
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
A presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means for each user identification information.
It is a program to make a computer function as
The action history information includes action type information regarding the type of action of the user for each data item.
The action type information for the data item belonging to the cluster is associated with each cluster.
The presenting means does not present the data item information when the action type indicated by the action type information associated with each cluster is a purchase, and when the type is another type, the presenting means Present data item information,
program. First acquisition means for acquiring data item feature information relating to each feature of a plurality of data items,
A second acquisition means for acquiring behavior history information related to the user's behavior history for each data item associated with the user identification information,
A clustering means for clustering each data item based on the data item feature information of each data item indicated by the action history information for each user identification information.
A presentation means for presenting data item information regarding at least one of the plurality of data items to the user based on the processing result of the clustering means for each user identification information.
It is a program to make a computer function as
The action history information includes action time information regarding the action time of the user for each data item.
The action time information for the data item belonging to the cluster is associated with each cluster.
When the elapsed time from the action time indicated by the action time information associated with each cluster is less than the threshold value, the presenting means does not present the data item information, and the elapsed time is equal to or greater than the threshold value. If the data item information is presented,
program.

Images