JP2020057322A - Information processor and information processing method - Google Patents

Abstract

To provide an information processor and a method, capable of performing proper information provision based on favorite information of a user.SOLUTION: An information providing device 7 includes an index management part 7a for managing, in each object, an index value for showing, in a plurality of stages, the degree of interest and concern relative to an object belonging to at least either of a commodity, a store or a genre, a cluster management part 7b for managing a user cluster formed by clustering users based on the index value, and a change tendency detection part 7c for detecting change tendency of the index value of a user belonging to one user cluster.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus and an information processing method, and more particularly, to a technique for managing products, stores, and the like that a user likes.

In order to stimulate the user's willingness to purchase, information such as recommended products and stores may be provided to the user. The optimal information to be provided to the user differs for each user, and it is important for the information provider to appropriately grasp the user's preferences.
Various techniques for estimating user preferences have been proposed. For example, Patent Literature 1 discloses a configuration in which information on a store designated as a favorite is stored, and the store provides a special service to a user registered as a favorite.

Japanese Patent No. 5363668

Incidentally, favorite registration is not always performed by the user's own hand, and unintended favorite registration may be performed depending on the action performed by the user.
If the special service as described above is performed based on unintended favorite registration, the user may not be interested in the service or may feel troublesome.
Therefore, an object of the present invention is to provide appropriate information based on user's favorite information.

An information processing apparatus according to the present invention, an index management unit that manages, for each of the objects, an index value indicating a degree of interest in an object belonging to at least one of a product, a store, and a genre in a plurality of stages; The system includes a cluster management unit that manages user clusters in which users are clustered based on an index value, and a change tendency detection unit that detects a change tendency of the index value of a user belonging to one user cluster.
An environment for providing appropriate information to the user according to the change tendency is formed by detecting the change tendency of the interest for each user cluster using the index value indicating the degree of the interest in a plurality of stages or more. You.

In the information processing device described above, when the detected change in the index value is a rising trend of the degree of interest, the user belongs to the one user cluster and the rising trend is not detected. A target user extracting unit that extracts a user as a target user, and an information providing unit that provides information on the target object in which the upward trend is detected to the target user may be provided.
As a result, the target user to whom the information to be provided is to be sent is determined based on the change in the interest of each user belonging to the user cluster.

The target user extraction unit of the information processing device described above, for a certain percentage of users belonging to the one user cluster, when the upward trend within a predetermined period for the same target object is detected, The target user may be extracted.
That is, when a phenomenon in which the evaluation of the target increases in the user cluster occurs on a certain scale, the target user is extracted.

As a result of providing the information, the cluster management unit of the information processing apparatus described above may divide the user who has not followed the change tendency and the user who has not followed the change tendency into different user clusters.
It is presumed that users who did not follow the change tendency as a result of providing information have different interests and interests. According to this configuration, such users are classified into different user clusters.

The index management unit of the information processing device described above may calculate the index value according to the number of purchases or the purchase frequency.
The act of purchasing a product is a daily act for the user. Calculating and updating an index value related to a product, a store, or a genre based on such daily activities not only reflects the user's interest and interest, but also quickly changes over time. It is possible to reflect.

In the information processing apparatus described above, the index value is an index that is set to be higher as the degree of interest is higher, and the index management unit is configured to operate the target object based on a user's active operation. When increasing the index value, the index value may be increased more than that based on the inactive operation of the user.
For example, a user's active operation for favorite registration is a self-declaration that the user likes an object, and such an object is automatically activated by an inactive operation. It is different from the favorite registered object. According to this configuration, the increase value (or increase rate) of the favorite index of the target object differs depending on whether the operation is active.

In the information processing device described above, the index value is an index that is set to be higher as the degree of interest is higher, and the index management unit determines that the number of the objects for which the index value is set to a maximum value is equal to or less than a predetermined number. You may manage so that it may become.
As a result, the index value is set to the maximum value, and the number of objects such as products that can be provided as information is suppressed to a certain number or less.

In the information processing apparatus described above, when presenting the correspondence information between the index value that is set to a predetermined value or more and the target object to the user, the information may be presented so that the magnitude of the index value is not known.
For example, when the index value is an index represented by 1 to 10, the indifferent object is represented by 5 and the object of high interest is represented by 6 to 10, the index value is 6 The object whose index value is set to 10 is regarded as an object having a higher degree of interest and interest of the user than the target object. At this time, the object having the index value of 6 and the object having the index value of 10 are presented to the user in a similar display manner so that the magnitude of the index value is not known. I can't tell the difference between the numbers. Therefore, the user cannot intentionally increase the object whose index value is the highest value (= 10).

In the information processing apparatus described above, the index value is an index represented by n or less and set as a higher value as the degree of interest is higher, and the first operation is an operation indicating that the degree of interest is higher. And a second operation are provided. When the first operation is an operation indicating that the degree of interest is higher than the second operation, the index management unit performs the second operation. If the index value of the object of the second operation is to be increased accordingly, a value smaller than n may be set.
For example, when a user purchases a product and the product to be purchased is registered as a favorite, the user may not intend to register the product as a favorite. In such a case, the index value of the product is set to a value lower than the highest value n.

The change tendency detection unit of the information processing device described above may detect an overall change tendency across the user cluster.
The user cluster is a group of users who have the same favorite tendency for each object, but it is possible to grasp the overall change tendency by analyzing the user cluster across the user cluster. .

An information processing method according to the present invention, wherein an index management step of managing, for each of the objects, an index value representing a degree of interest in the object belonging to at least one of a product, a store, and a genre in a plurality of stages; The information processing apparatus executes a cluster management step of managing a user cluster in which users are clustered based on an index value, and a change tendency detecting step of detecting a change tendency of the index value of a user belonging to one user cluster. Things.
With this information processing method, it is possible to generate an index for providing appropriate information based on the user's favorite information.

  According to the present invention, it is possible to generate an index for providing appropriate information based on user's favorite information.

FIG. 1 is an explanatory diagram of a network including an information providing device according to an embodiment of the present invention. It is a block diagram of a computer device of an embodiment. FIG. 2 is an explanatory diagram of a functional configuration of the information providing device according to the embodiment; FIG. 7 is a diagram for explaining similarity of a user's preference tendency. FIG. 9 is a diagram for describing an example of the entire process. It is a flowchart about an example of a favorite index change process. It is a flowchart about an example of a cluster information change process. It is a flowchart about an example of information provision processing. It is a flowchart about an example of the trend detection process in a cluster. It is a flowchart about an example of information provision effect check processing. It is a flowchart about an example of a general trend detection process. FIG. 9 is a diagram for explaining an example of a presentation mode when presenting favorite information to a user.

Hereinafter, embodiments will be described with reference to the accompanying drawings. In each of the following examples, electronic commerce will be described as an example of an environment in which appropriate information is provided to a user based on a product, a store, a genre, or the like registered as a favorite based on a user operation. That is, a product, a store, or the like is registered as a favorite based on various operations performed when the user uses the electronic commerce. Further, appropriate information is provided to the user based on the information registered as a favorite.

<1. System Configuration>
The configuration of the entire network system including the information providing device 7 according to the present embodiment will be described with reference to FIG.
In the network system 1, various terminal devices can communicate with each other via a communication network 2.
The network system 1 includes an electronic commerce system 3, a user terminal 4, and a store terminal 5.

The configuration of the communication network 2 shown in FIG. 1 is not particularly limited. In addition to the above-described Internet, for example, an intranet, an extranet, a LAN (Local Area Network), a CATV (Community Antenna TeleVision) communication network, A virtual private network, a telephone network, a mobile communication network, a satellite communication network, and the like are assumed.
Also, various examples of transmission media constituting all or a part of the communication network 2 are assumed. For example, even in the case of a wire such as IEEE (Institute of Electrical and Electronics Engineers) 1394, USB (Universal Serial Bus), power line carrier, telephone line, infrared rays such as IrDA (Infrared Data Association), Bluetooth (registered trademark), 802.11 wireless. It can also be used by wireless such as a mobile phone network, a satellite line, and a terrestrial digital network.

  The electronic commerce system 3 includes a shopping server 6 that provides various services used by a user to purchase a product, and an information providing device 7 that performs a process of providing appropriate information to the user. The electronic commerce system 3 manages and operates an EC site as a portal site for providing various services. The EC site has, for example, a hierarchical structure including a plurality of web pages with the top page at the top.

The various functions provided by the shopping server 6 are, for example, when there are a plurality of stores participating in e-commerce operated by using the system, the manager of the store (hereinafter referred to as a seller) sells the stores. A function for registering product information (product information) to be performed, a function for changing registered product information, and the like. To this end, the shopping server 6 has a function of managing member store information, seller information, and product information.
Further, the shopping server 6 searches for and presents a product desired by the user from a group of products handled in e-commerce, or places an order for a product to a seller when the user performs a purchase operation of the product. Function, settlement processing function that mediates exchange of money when goods are sold, function to deliver goods to each user, notification function to users when product purchase is confirmed, and product Has a function of notifying the seller of the user information of the user who has purchased.
When a user purchases a product, information on the destination (address) of the product, credit card number and contact information (e-mail address, etc.) is required. The shopping server 6 has a function of managing user information in order to save the trouble of inputting such information every time a user purchases a product.

Then, the shopping server 6 generates web page data to display a web page as a user interface for realizing the above-described various functions on another information processing apparatus (the user terminal 4 or the shop terminal 5). Send.
The web page data is, for example, a structured document file such as HTML (Hyper Text Markup Language) or XHTML (Extensible HyperText Markup Language). In the structured document file, text data such as description of a product, image data such as a product image, and their arrangement and display mode (character color, font, size, decoration, etc.) are described.
Examples of the web page include a login page for allowing a user or a seller to input login information, a search result display page for displaying a result of a product search, and a product page on which product information is displayed.
The shopping server 6 has a user and seller authentication function, a function of registering information in various databases, a function of acquiring information from various databases, and the like.

The information providing device 7 is an information processing device that provides appropriate information to a user. Appropriate information is, for example, information on a product or a store that provokes a user's willingness to purchase.
For this purpose, the information providing device 7 quantifies and manages the degree of interest for each product, store, or genre based on various operations performed by the user. In each of the following examples, a description indicating a degree of interest in at least three levels will be described as a “favorite index”. In the following example, a description will be given using a favorite index indicating the degree of favorite in four stages of 0 to 3.

  The favorite index indicates that the higher the numerical value, the higher the degree of favorite. That is, a product, a store, or a genre for which the favorite index is set to “3” indicates that the degree of favorite is extremely high. A state in which the degree of favorite is neutral, that is, a state of indifference or ignorance with respect to the product, store, or genre is represented as “1”. A state in which the degree of favorite is negative, that is, a state in which a product, a store, or a genre is disliked, is represented as “0”. A plurality of stages may be provided for the degree of dislike. Further, it is not necessary to distinguish between a dislike state and an indifference state. For example, the degree of favorite is represented in three levels of 0 to 2, where "0" indicates a state of indifference or dislike, "1" indicates a state of being a favorite, and "2" is a fairly favorite. It may be configured to indicate a state.

  In the following description, items that belong to at least one of a product, a store, and a genre are described as “objects”. In other words, the object may indicate a certain product, may indicate a certain store, or may indicate a certain genre.

  Further, the information providing device 7 clusters each user into a user cluster UC based on the favorite information. Further, the information providing device 7 provides appropriate information based on the user cluster UC and the favorite information. The favorite information is information on the correspondence between the object and the favorite index.

In order to realize the various functions described so far, the electronic commerce system 3 sells a user DB (Database) 50 in which user information is stored, a product DB 51 in which information of products handled in electronic commerce is stored, and a product. A store DB 52 in which information on sellers (stores) is stored, a history DB 53 in which user operation histories are stored, an index DB 54 in which user favorite information is stored, and a cluster DB 55 in which information on user clusters UC is stored. Have.
In addition, it manages a web page DB (not shown) in which web page data of various web pages is stored.
These DBs are capable of communicating with the shopping server 6 and the information providing device 7 of the electronic commerce system 3 via a network such as a LAN, for example. is not.

  The user terminal 4 is an information processing device used by the user to receive various services provided by the electronic commerce system 3. Specifically, it is used when browsing product information, purchasing a product, or the like.

  The store terminal 5 is an information processing device used in a store that provides product information to a user by registering a product to be sold by the store terminal 5 in the electronic commerce system 3. The store terminal 5 performs transmission / reception processing for registering, deleting, or changing product information with respect to the electronic commerce system 3.

The user terminal 4 and the store terminal 5 are, for example, a PC (Personal Computer), a feature phone, a PDA (Personal Digital Assistants) having a communication function, or a smart device such as a smartphone or a tablet terminal.

<2. Hardware configuration of computer device>

Hardware configuration of computer devices constituting each device (shopping server 6, user terminal 4, store terminal 5, user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) including the information providing device 7 Is shown in FIG. A CPU (Central Processing Unit) 101 of each computer device executes various processes according to a program stored in a ROM (Read Only Memory) 102 or a program loaded from a storage unit 108 to a RAM (Random Access Memory) 103. I do. The RAM 103 also appropriately stores data necessary for the CPU 101 to execute various processes.
The CPU 101, the ROM 102, and the RAM 103 are mutually connected via a bus 104. An input / output interface 105 is also connected to the bus 104.
An input unit 106, an output unit 107, a storage unit 108, and a communication unit 109 are connected to the input / output interface 105.
The input unit 106 includes a keyboard, a mouse, a touch panel, and the like.
The output unit 107 includes a display including an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube), an organic EL (Electroluminescence) panel, a speaker, and the like.
The storage unit 108 includes a hard disk drive (HDD), a flash memory device, and the like.
The communication unit 109 performs communication processing and communication between devices via the network 2.
A media drive 110 is connected to the input / output interface 105 as necessary, and a removable medium 111 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory is appropriately mounted. Reading is performed.

In such a computer device, data and programs are uploaded and downloaded by communication through the communication unit 109. Also, data and programs can be transferred via the removable medium 111.
When the CPU 101 performs processing operations based on various programs, each device such as the information providing device 7 (shopping server 6, user terminal 4, store terminal 5, user DB 50, product DB 51, store DB 52, history DB 53, index DB 54 , The necessary information processing and communication as the cluster DB 55) are executed.
Note that the information processing apparatus that configures each device such as the information providing device 7 (shopping server 6, user terminal 4, store terminal 5, user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) is illustrated in FIG. 2 is not limited to a single computer device, and a plurality of computer devices may be systematized and configured. The plurality of computer devices may be systemized by a LAN or the like, or may be remotely located by a VPN or the like using the Internet or the like. The plurality of information processing devices may include an information processing device as a server group (cloud) that can be used by a cloud computing service.

Each function of the information processing apparatus is a function realized by processing executed by the CPU 101 in the information processing apparatus according to a program. However, the processing of all or some of the components described below may be realized by hardware.
When each function is realized by software, each function does not need to be realized by an independent program. Processing of a plurality of functions may be executed by one program, or one function may be realized by cooperation of a plurality of program modules.
Each function may be distributed to a plurality of information processing devices. Further, one of the functions may be realized by a plurality of information processing devices.

<3. Functional configuration of information providing device>

The specific configuration of the information providing device 7 will be described with reference to FIG.
The information providing device 7 includes an index managing unit 7a, a cluster managing unit 7b, a change tendency detecting unit 7c, a target user extracting unit 7d, and an information providing unit 7e.

  The index management unit 7a manages a favorite index for each user and object. That is, the favorite information is managed. Specifically, a favorite index for the object is calculated and stored according to a user operation. When the object is a product, the product A sold at the store A and the product A sold at the store B may be treated as different or the same.

  The cluster management unit 7b generates and manages a user cluster UC based on the user's favorite information. The management is performed so that the users having a similar preference tendency to the object belong to the same user cluster UC.

This will be specifically described with reference to an example shown in FIG.
FIG. 4 is a diagram for explaining how to determine whether or not the preference trends of the user U1 and the user U2 are similar. As the object, products S1 to S7 are illustrated.

For example, for the product S1, the favorite index of the user U1 is “1: indifferent”, and the favorite index of the user U2 is “3: very favorite”. Further, the distance of the preference tendency between the user U1 and the user U2 with respect to the product S1 is set to “-” indicating that the product S1 is not to be calculated.
The distance of the preference tendency is set to a smaller value as the user U1 and the user U2 are similar, and is set to a larger value as the user U1 and the user U2 are not similar.

  The product for which the index value of the favorite index is set to “1” is a product that the user does not know as described above, that is, a product that is indifferent. That is, it is unknown whether the user likes the product. In such a state, it is not appropriate to determine whether or not the preference tendency is similar to that of another user.

  Therefore, in the example of FIG. 4, since the index value of the favorite index of the user U1 or the user U2 is “1”, the products S1 and S2 are not calculated. Further, for the products S3 and S6, the user U1 and the user U2 have similar tastes (that is, the index values are the same), and thus the distance is “0”.

  For the product S4, the favorite index of the user U1 is set to "3: very favorite", whereas the favorite index of the user U2 is set to "2: rather favorite". In other words, the distance is set to "1" because the preference tendency is slightly different.

  For the product S5, the favorite index of the user U1 is set to "3: very favorite", whereas the favorite index of the user U2 is set to "0: dislike". That is, the distance is set to “2” because the preference tendency is exactly opposite.

  For the product S7, since the favorite index is set to "1: indifferent" for both the users U1 and U2, the distance is set to "-" indicating that the user is not calculated.

For the product S8, the favorite index of the user U1 is set to "0: dislike", and the favorite index of the user U2 is set to "2: rather favorite". That is, since the preference tendency is almost opposite, the distance is set to “2”. Note that the distance calculated below will not be a very large value, and the distance between "3: very favorite" and "0: dislike", and "2: rather favorite" and "0: dislike". Are both "2".
Of course, if the favorite index of one of the users is not “1: indifferent”, the difference between the index values may be used as the distance.

In accordance with the distance for each object shown in FIG. 4, the closeness of the preference tendency between the user U1 and the user U2 is determined. If the preference tendency is determined to be close, the user is classified into the same user cluster UC. .
When calculating the closeness of the preference tendency of the user U1 and the user U2 for the products S1 to S8 shown in FIG. 4 as the average distance, for example, the sum of the distances (5 = 0 + 1 + 2 + 0 + 2) is calculated as (5 pieces: products S3, S4, S5, S6, S8) may be obtained by dividing. In the example shown in FIG. 4, the average distance is calculated as “1 (= 5/5)”.

There are several examples of a method for determining whether or not a preference tendency is close.
For example, distances as shown in FIG. 4 are obtained for all the products handled by the electronic commerce system 3, and when the average value is less than a predetermined value (for example, 0.2), it is determined that the preference tendency of the two users is close. May be. When the target object is a product, the product may be classified into each genre, and the proximity of the user's preference tendency may be determined for each genre. For example, distances are calculated for products belonging to the “sports” genre, respectively, and if the average value is less than a predetermined value, the user U1 and the user U2 have similar preferences for products belonging to the sports genre. May be determined. Note that the “predetermined value” to be compared with the average value may be a threshold arbitrarily determined in advance.

  In addition, when the target object is a store, it may be possible to determine the closeness of the preference tendency between users with respect to a group of stores selling products belonging to the same genre. For example, with respect to a group of stores selling sporting goods, it is determined how close the user U1 and the user U2 are to preference.

  When the target object is a genre, a hierarchical structure in which a small genre such as "soccer", "baseball", "golf", and "swimming" is linked to a large genre of "sports" is provided. It may be determined whether or not the preferences of the large genre are similar according to the proximity of the preferences.

  For each of the user clusters UC, a reference model for characterizing the preference tendency of the user cluster UC may be set. The reference model is set, for example, as a collection of favorite indexes for each product.

The reference model may be a preference tendency of a representative user belonging to the user cluster UC. In that case, users having similar tastes to the representative user are classified into the same user cluster UC.
For example, when the user U1 of FIG. 4 is used as the reference model, the favorite index of the product S2 is set to “2”, the favorite indexes of the products S3, S4, and S5 are set to “3”, respectively, and the product S6 is set. The favorite index for S8 is set to “0”. Each product (products S1 and S7) for which the favorite index of the user U1 is set to “1” may be set based on a preference tendency of another user belonging to the same user cluster as the user U1.

  In addition, as described above, providing an index value indicating an indifferent state, and determining whether two users are similar in taste tendency, a product in which either user is indifferent, that is, an evaluation value Is not used for calculating the average value of the distance, it is possible to appropriately calculate the degree of similarity of the preference tendency between the users.

  The change tendency detection unit 7c performs a process of detecting a change tendency of a preference tendency of a user belonging to one user cluster UC.

  When the change tendency detection unit 7c detects a change tendency in a certain user cluster UC, the target user extraction unit 7d determines a user who has seen a change tendency and a user who does not. Further, a process of extracting a user who does not see a change tendency as a “target user” who is a target of information provision is performed.

This will be specifically described. For example, for a certain percentage of users belonging to a certain user cluster UC1, from a state in which the favorite index of the product S1 is "1: indifferent" for a predetermined period (for example, one week), "3: Consider a case where the status changes to a status of "very favorite".
The change tendency detection unit 7c detects such a change tendency. That is, it is detected that the popularity of the product S1 is rapidly increasing among the users belonging to the user cluster UC1. Further, the target user extraction unit 7d determines, for each user belonging to the user cluster UC1, a user whose favorite index of the product S1 is not “3”, in other words, a user whose “2” or less is a “target user” for information provision. Extract as

The information providing unit 7e performs various processes for providing information to the extracted user. Specifically, information to be provided is generated according to the information providing means, and transmitted to the user by an appropriate means.
For example, it is conceivable to use electronic mail as a means for providing information. When the above example is used, processing for generating e-mail data including information on the product S1 as the target is performed, and processing for transmitting the data to the user is performed. The transmission of the electronic mail may be delivered to the user at an appropriate time zone by setting a transmission reservation.

  As a means for providing information, it is conceivable to post advertisements related to various services provided by the electronic commerce system 3 on a web page viewed by a user. Using the above example, in a state where the target user among the users belonging to the user cluster UC1 is browsing a web page, a request for transmitting advertisement information is received from the user terminal 4 in use. In response to receiving the request, the information providing unit 7e performs a process of extracting the advertisement information including the information of the target product S1 and transmitting the advertisement information to the user terminal 4.

  Further, for example, when a display column for displaying recommended products is provided according to a user who has visited the top page of the portal site managed by the electronic commerce system 3, the provided information may be displayed in the display column. Good. In the above example, when the visiting user is a target user belonging to the user cluster UC1, information on the target product S1 is posted in the recommended product display column.

Also, consider a case where a user uses software (hereinafter referred to as a “terminal application”) installed in a user terminal 4 to use various services provided by the electronic commerce system 3. In such a case, the information of the product S1 as the target object is changed in response to the user operating an operator (for example, a “view recommended information” button) such as a predetermined button provided in the terminal application. It may be presented to the user.
In addition, another window is displayed when the user browses information on other products related to the target object (products belonging to the same genre, products having the same sales store, and products with high relevance). Thereby, information on the product S1 as the target object may be provided.

<4. DB>

Various DBs managed by the electronic commerce system 3 will be described.

[4-1. User DB]
The user DB 50 stores information of users who use various services provided by the electronic commerce system 3. For example, personal information such as a login password, name, age, gender, annual income, address, e-mail address, and hobby are stored in association with one user ID (Identification) that can identify one user. You. In addition, payment information, product purchase history, product favorite registration information, and the like may be stored. The details of the purchase history and the browsing history are separately stored in the history DB 53. The details of the favorite information are separately stored in the index DB 54.

[4-2. Product DB]
The product DB 51 stores information about each product that can be bought and sold using the electronic commerce system 3. For example, for a product ID capable of uniquely identifying a product, a product genre, a product image, manufacturer (manufacturer) information, a model number information provided by the manufacturer, a sales start date, a handled product provider information, stock information, and the like. Is linked and stored.
The product image information may be the image data itself, or URL (Uniform Resource Locator) information as link information of the stored image data.
In addition, the product DB 51 may store, in addition to the above, a production location, product specifications (color, size, performance information), and the like.

[4-3. Store DB]
The store DB 52 stores information on stores that sell products and stores that make purchases using the electronic commerce system 3.
For example, genre information, sales product information, representative information, contact information, and the like are stored for a store ID that can uniquely specify a store.

[4-4. History DB]
The history DB 53 stores various histories related to user operations (such as purchase histories and browsing histories).
Specifically, for each operation performed by the user, a history ID, an operation type, and an operation target (a target product ID for a “purchase operation” or a “browsing operation”, and a target user ID for a “user information change operation” Changed item name, etc., operation date and time, operation result ("Login operation" indicates whether login is possible, "User information change operation" indicates whether change is possible, and "Purchase operation" indicates whether the user has purchased or canceled. Is stored.

[4-5. Index DB]
The index DB 54 stores user favorite information. The favorite information is information of a favorite index for each object such as a product, a store, or a genre. Favorite information is stored for each user.
In the following example, as described above, a favorite index indicating the degree of favorite in four stages of 0 to 3 is used. The favorite index is set to a higher numerical value (index value) as the degree of favorite is higher. An object for which the favorite index is set to “1” indicates that the user is an indifferent object.

[4-6. Cluster DB]
The cluster DB 55 stores information on the user cluster UC.
The user cluster information is stored in association with a user cluster ID capable of uniquely specifying one user cluster UC, belonging user information, information on a preference tendency, and the like.

As described above, the information on the preference tendency is information on the reference model. Specifically, one user having a standard preference tendency in the user cluster UC may be specified, and the user's preference tendency (favorite information) may be adopted as a reference model.

[4-7. DB Mode]
Each of these DBs (user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) can be accessed by each information processing apparatus constituting the electronic commerce system 3 as necessary. It may be realized in any form. For example, all the DBs (user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) may be formed in a storage unit in the same system as the electronic commerce system 3, or each DB (user DB 50) , A product DB 51, a store DB 52, a history DB 53, an index DB 54, a cluster DB 55) may be provided in a computer system such as a separate or remote location. Of course, each DB (user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) need not be formed in one device (for example, one HDD). Further, each of the DBs (the user DB 50, the product DB 51, the store DB 52, the history DB 53, the index DB 54, and the cluster DB 55) does not need to be configured as one DB. For example, the information stored in the user DB 50 may be stored and managed by a plurality of user DBs (for example, a user DB for log-in and a user DB for storing user attribute information). Each DB (user DB 50, product DB 51, store DB 52, history DB 53, index DB 54, cluster DB 55) described below exemplifies a storage unit of information related to the processing of the embodiment in a form of one DB. It's just

<5. First Embodiment>

[5-1. Overall flow]
A process executed by each information processing terminal of the electronic commerce system 3 based on an operation performed by the user will be described.
FIG. 5 illustrates an example of a flow of a series of processing.

First, the user performs an operation of displaying a login page using the user terminal 4. In response, the user terminal 4 executes a login page information request process in step S101. The login page information request process is a process for requesting web page information for executing login.
When the login page information request is transmitted from the user terminal 4 to the e-commerce system 3, the e-commerce system 3 executes a login page information transmission process in step S201.
Thereby, for example, a web page corresponding to the login page information (web page data) for the EC site received from the electronic commerce system 3 is displayed on the user terminal 4.

  Next, in step S102, the user terminal 4 executes a login information transmission process of transmitting the login information (user ID and password) input by the user to the electronic commerce system 3. When the login information is transmitted from the user terminal 4 to the electronic commerce system 3, the electronic commerce system 3 executes an authentication process in step S202, and performs a process of storing the login history in the DB in step S203. Further, in step S204, the electronic commerce system 3 executes an authentication result notification process.

Specifically, the e-commerce system 3 compares the user ID and the password input on the user terminal 4 with information stored in the user DB 50 to determine whether or not the user can log in. Notify to The authentication result may be returned to the user terminal 4 and the web page data of the top page of the EC site may be transmitted. Thereby, user authentication is performed, and the top page of the EC site is displayed on the user terminal 4.
Note that a series of flows shown in FIG. 5 show a case where it is determined that the login is permitted in the authentication processing in step S202. If it is determined in step S202 that the login is not possible, the user terminal 4 executes the processing of step S102 again, and in response thereto, the e-commerce system 3 executes the processing of step S202.

  A user who has successfully logged in to the EC site performs various operations for using the EC site. In response, the user terminal 4 receives various operations in step S103. In the process of step S103, various information is transmitted to the electronic commerce system 3 according to the type of operation performed by the user. For example, when a user searches for a product, information such as a search query is transmitted to the electronic commerce system 3. When an operation for browsing the product page is performed, information for specifying the product page desired by the user is transmitted to the electronic commerce system 3.

In the electronic commerce system 3, appropriate processing is performed according to the operation of the user in step S103. Specifically, a search process and a notification process according to a product search operation, a web page information acquisition process and a transmission process according to a product page browsing operation, and the like are performed. In FIG. 5, these processes are omitted.
In FIG. 5, each process executed by the information providing device 7 of the electronic commerce system 3 according to various operations of the user is shown in steps S205 to S207. This will be specifically described.

  In step S205, the favorite index is changed based on the user operation. In step S206, the user cluster information is changed. Further, in step S207, information is provided in accordance with the changed favorite index and user cluster information.

In step S104, the user terminal 4 performs a process for displaying the provided information. Thereby, the user can browse the information received from the information providing device 7 of the electronic commerce system 3.
Hereinafter, each process of steps S205 to S207 will be specifically described.

[5-2. Favorite index change processing]
The favorite index change process is a process for changing the index value of the favorite index according to a user operation.
This will be specifically described with reference to FIG. In the following description, the index value of the favorite index is simply described as “index value”.

In step S301, the information providing device 7 performs a process of specifying the type of operation performed by the user. The operation performed by the user is the user operation received by the user terminal 4 in step S103 of FIG. In the following description, the user who has performed the operation will be referred to as “operation user”.
As the operation type, for example, an operation of browsing a product page, a product purchase operation, an operation of adding a product to a shopping cart, an operation of searching for a product or a store, and registering a product, a store, or a genre (object) as a favorite. Operation is conceivable.

In step S302, the information providing device 7 performs a process of specifying the target. For example, when the operation performed by the operating user is a browsing operation of a product page, the product is specified as an object. Further, the genre to which the product belongs may be further set as the target object. That is, the number of objects is not limited to one.
The genre may be a large genre such as “sports equipment” or a fine genre such as “golf equipment”. Further, the genre may be a subdivided genre such as "golf iron set".
When the operation performed by the operating user is a browsing operation of a store page, the store may be specified as an object, and the product genre sold by the store may be further set as the object.

The information providing device 7 acquires the history information in step S303. In this process, information such as the browsing history and purchase history of the operating user is acquired from the history DB 53.
Subsequently, in step S304, the information providing device 7 calculates an index value of the operating user for the target object. At this time, the history information acquired in step S303 is referred to.

A specific example will be described. An example in which the index value of the operating user regarding the target object before the operation is “1” will be described.
For example, if the user has browsed the product pages of a plurality of products belonging to the same product genre within a predetermined period such as the latest 10 minutes, it is determined that interest in the product genre has significantly increased, and the index Reflect on the value. That is, the index value of the genre is changed from “1” indicating indifference to “3”.
Further, for example, if the user has not browsed a product page of another product belonging to the same product genre as the target object within a predetermined period such as the latest 10 minutes, the interest in the product genre has significantly increased. Therefore, the index value of the genre is changed from "1" indicating indifference to "2". In a single index value change process, the index value may be changed to “1”. That is, the index value may be changed from “1” to “2” when a product page of the same product genre has been browsed a predetermined number of times within a predetermined period.

It is also conceivable to calculate an index value based on a purchase history. For example, when a product belonging to a certain genre is purchased a plurality of times within a predetermined period, the index value of the genre is changed from “1” to “3”. In addition, when one product belonging to a certain genre is purchased within a predetermined period, the index value of the genre is changed from “1” to “2”.
Further, when there is a commodity that is regularly purchased, it is conceivable to increase the index value of the commodity. Further, when the commodity that has been regularly purchased is no longer purchased, the index value of the commodity may be reduced.

  In addition, when a certain product page is frequently viewed, it is conceivable to increase the index value of the product. However, it is also possible to increase the index value of another product similar to the product. Good. For example, the index value of the browsed product may be changed to “3”, and the index value of another similar product may be changed to “2”.

That is, in step S304, it is desirable to calculate the index value according to the number of purchases and the purchase frequency, or the number of times of browsing and the frequency of browsing.
By performing such a process in step S304, a process of estimating the preference of the target object according to the history and calculating an appropriate index value is performed.
When referring to the history information, weighting may be performed based on the time information at which the operation was performed, so that the more recently performed operation has a greater influence on the calculation of the index value.

Alternatively, the index value may be calculated based on whether the user operation is an operation for actively performing favorite registration or an operation for performing favorite registration inactively.
For example, an operation performed by a user with the intention of registering a certain product as a favorite is defined as an active operation. Conversely, if the purchased product is unintentionally registered as a favorite in response to the user performing a purchase operation for purchasing a product, the purchase operation is defined as an inactive operation.
In this case, when the favorite is registered by the active operation or when the favorite index is increased, the increment of the index value is increased as compared with the case where the favorite is registered or the favorite index is increased by the inactive operation. It is possible. Specifically, when a user whose index value of a certain product is set to “1” indicating indifference performs an active operation for favorite registration, the index value is changed to “3”. On the other hand, when the user has performed an inactive operation for favorite registration, the index value is changed to “2”, which is lower than the maximum value “3”.

  In step S305, the information providing device 7 determines whether the index value calculated in step S304 is the highest value (= 3). If the calculated index value is the highest value, the information providing apparatus 7 determines in step S306 whether there is a predetermined number (for example, 10) of objects having the highest index value in the favorite information of the operating user. Is determined. In this determination processing, it may be determined whether there are 10 or more objects having the highest index value other than the product being processed this time, or if the predetermined number is 11 and the current processing is performed. It may be determined whether or not there are 11 or more objects having the highest index values, including the target product.

  When it is determined that the number of objects whose index values are set to the maximum value is equal to or more than the predetermined number, the information providing device 7 performs a replacement process in step S307. In the replacement process, one of the objects for which the highest index value is set is selected, and the index value is lowered by one level (that is, changed from “3” to “2”). As a result, the index value of the current object is set to the highest value, and the total number of objects whose index values are set to the highest value is suppressed to a predetermined number or less.

If the number of objects having the highest index value increases too much, the processing load for determining which object to provide information to when providing appropriate information to the user increases. There is a possibility that it will end up. If information is provided by the number of objects having the highest index value, information provision to the user will increase too much, and the user may feel troublesome. It is also conceivable that the user does not really know the product he liked.
By performing the processes of steps S305 to S307 shown in FIG. 6, the number of objects whose index values are set to the maximum value is equal to or less than a predetermined number, so that appropriate information can be easily provided.

It should be noted that in the replacement process in step S307, various methods for selecting an object to lower the index value from “3” to “2” are conceivable.
For example, the operation of the user includes an operation of increasing the favorite index of the target object, such as a product purchase operation. Such an operation includes an object to be operated. It can be inferred that the closer to the last time the operation was performed, the higher the current favorite level of the target object of the operation is. In other words, there is a possibility that the older the time at which the operation was performed, the lower the current favorite level of the object. Therefore, it is conceivable to select the target object in step S307 that has the oldest time when the operation of raising the favorite index for the target object is last performed.

  In addition, it is conceivable that the operation for increasing the favorite index is ranked, and the object that is the target of the operation with a high degree of increasing the favorite index is excluded from the selection targets in step S307. In other words, an object that is only an operation target with a small degree of increasing the favorite index is selected as the selection target in step S307.

In step S308, the information providing device 7 stores the correspondence between the target object and the newly set index value in the index DB 54.
If it is determined in step S305 that the index value is not the highest value, or if it is determined in step S306 that the number of objects having the highest index value is less than the predetermined number, the process proceeds to step S307 without performing the replacement process. The storage processing of S308 is performed. That is, the index value related to the target object of the current operation is updated.

[5-3. Cluster information change processing]
After performing the favorite index changing process in step S205 in FIG. 5, the information providing device 7 performs the cluster information changing process in step S206.
The cluster information change process performs a process of determining whether or not the user cluster UC to which the operating user belongs has been changed due to the change of the favorite information of the operating user. If the operating user does not belong to any user cluster UC, a process of specifying an appropriate user cluster UC to which the operating user belongs in this cluster information change process is performed.

An example of each process executed in the cluster information change process will be described with reference to FIG.
In step S401, the information providing device 7 specifies an operation user. The operation user is a user who has performed the operation in step S103 in FIG.
Next, the information providing apparatus 7 specifies an object in step S402. The target object is a product, a store, a genre, or the like that has been operated by the operation user in step S103.

In step S403, the information providing device 7 determines whether or not to change the belonging cluster. In this process, the cluster to which the operating user belongs is specified, and it is determined whether it is appropriate to belong to the belonging cluster.
For example, the information of the reference model of the belonging cluster is acquired from the cluster DB 55, and it is determined whether or not the preference tendency of the operating user and the reference model deviate by a predetermined amount or more. As a method for determining whether or not the preference trend is different from the reference model, for example, as described with reference to FIG. 4, the distance for each object is calculated, and the average value is set to a predetermined value (for example, 0). .2) It may be determined according to whether it is less than.

  If the operating user does not belong to any of the user clusters UC, it is determined that the change of the belonging cluster is “necessary”.

In step S404, the information providing device 7 performs a branch process based on the determination result. Specifically, when the change of the belonging cluster is “necessary”, that is, when the determination result of step S404 is “Y”, the information providing apparatus 7 performs a process of identifying the optimum user cluster UC in step S405. Do.
In this process, for example, in each user cluster UC, the average value of the index value for each object of the operating user and the distance of the reference model is calculated, and the user cluster UC with the smallest average value of the distance is determined as the optimal user cluster UC. Identify. However, even if the average value of the distance is the smallest user cluster UC, if the average value is equal to or more than the predetermined value, it is inappropriate to assign the operating user to the user cluster UC. The optimal user cluster UC may be determined as “not applicable”. In other words, it is determined that the optimal user cluster UC has not been specified.

The information providing device 7 performs a branching process according to whether or not the optimum user cluster UC has been specified in step S406.
When the optimum user cluster UC has not been specified, the information providing apparatus 7 generates a new user cluster UC in step S407. At this time, each index value of the operating user may be set as a reference model of the new user cluster UC.

In step S408, the information providing device 7 changes the belonging cluster. If the optimum user cluster UC has been identified in step S406, the operating user is assigned to the identified user cluster UC to change the assigned cluster.
When a new user cluster UC is generated in step S407, the belonging cluster is changed by causing the operating user to belong to the new user cluster UC.

If it is determined in step S404 that the change of the belonging cluster is unnecessary, the information providing device 7 ends the series of processes illustrated in FIG.

[5-4. Information provision processing]
After changing the favorite index in step S205 in FIG. 5 and changing the cluster information in subsequent step S206, it is necessary to newly provide information in step S207 in accordance with the change in the favorite index and the user cluster UC. This is to detect the target object and provide information.
This information providing process may be realized by providing information immediately after step S206. However, at the time of executing step S206, a process of selecting information to be provided and determining a timing of providing is performed. The provision may be performed according to the determined timing (for example, several hours or several days later, or the timing at which a specific operation is performed by the user).

An example of the information providing process will be described with reference to FIG.
First, the information providing apparatus 7 acquires favorite information from the index DB 54 in step S501. Subsequently, in step S502, the information providing apparatus 7 executes a process of detecting an object whose preference has changed.
Next, in step S503, the information providing device 7 performs a branching process according to the presence or absence of the target object.

  Here, as a specific example of steps S502 and S503, an example will be described in which information is provided when a change in the preference tendency within a predetermined period is detected for 30% or more of the users belonging to a certain user cluster UC.

For example, a user cluster UC1 to which ten users U1 to U10 belong will be described as an example.
At a certain point in time, it is assumed that the index value for the product S1 of the users U1 to U10 is “1”. Thereafter, it is assumed that, for the users U1 and U2, the index value for the product S1 has increased to “3” within a predetermined period. At this time, the ratio of the users who have detected a change in the preference tendency for the product S1 is 2 out of 10 users, and thus is calculated as 20%.
Next, it is assumed that the index value of the favorite index of the product S1 of the user U3 has increased to “3” in step S205 of FIG. 5 in response to the operation of the user U3 purchasing the product S1. At this time, 30% of the users U1 to U10 belonging to the user cluster UC1 have the index value of the product S1 increased to “3” within the predetermined period. That is, it means that the increasing tendency of the index value of the product S1 has been detected in the user cluster UC1.

In such a case, the information providing apparatus 7 determines in step S503 that there is an object (that is, the product S1) for which information needs to be provided based on the operation of the user U3.
If it is determined that there is an object whose preference tendency has changed, the information providing apparatus 7 specifies the target user in step S504. Specifically, if the purpose is to induce the user to purchase by providing information on the product S1, the target user is a user whose index value of the product S1 has not risen to “3”. That is, in this example, seven users U4 to U10 are specified as target users.

Next, in step S505, the information providing device 7 executes an information providing process. In this process, information provision to each user may be performed immediately, or information provision reservation may be performed by setting a transmission trigger of information provision.
Various means for providing information can be considered as described above.
On the other hand, when it is determined that there is no object whose preference tendency has changed, the information providing apparatus 7 ends the series of processes illustrated in FIG. That is, no information is provided.

Each time the user performs an operation, a series of processes illustrated in FIG. 8 is executed, so that it is appropriate to execute information provision every time a change in the favorite index or a change in the user cluster UC occurs. Is performed, the timing of information provision is not missed, and effective information provision can be performed.

<6. Second Embodiment>

In the second embodiment, as in the first embodiment, the favorite index changing process in step S205 and the cluster information changing process in step S206 in FIG. 5 are executed in response to a user operation. However, the information providing process in step S207 is not performed at a timing according to a user operation, but is performed at another timing.
For example, by performing the intra-cluster trend detection processing illustrated in FIG. 9 periodically by batch processing or the like, appropriate information provision is realized. As in the first embodiment, if the process of step S207 is performed every time various operations are performed by the user, the processing load on the information providing device 7 may be excessively increased. In this example, information is provided without excessively increasing the processing load.

  In step S601, the information providing device 7 executes a process of specifying the target user cluster UC. This process is a process for selecting one user cluster UC. When the series of processes shown in FIG. 9 is performed on all the user clusters UC, an unprocessed user cluster UC is selected in step S601.

In step S602, the information providing device 7 specifies the target whose index value has increased within a predetermined period. For example, when each process shown in FIG. 9 is executed once a day as a batch process, the period from when the previous batch process was executed to the present is set as a “predetermined period”, so that the processing load of the batch process is increased. While the index value is increasing, it is possible to detect the target object.
In the process of step S602, all the objects such as products whose favorite index of each user belonging to the target user cluster UC has risen within a predetermined period are specified.

  Subsequently, in step S603, the information providing apparatus 7 narrows down, among all the specified objects, those objects in which a similar upward trend is seen in belonging users of a predetermined ratio or more in the target user cluster UC. By performing the processes of steps S602 and S603, an object such as a product that is popular within a predetermined period in the target user cluster UC is specified.

In step S604, the information providing apparatus 7 performs a process of generating provided information on the narrowed target object.
Various methods for providing information to the user can be considered as described above, but appropriate information generation according to the method is performed.

  The information providing device 7 provides information to the user in step S605. In this process, a process of transmitting the information provision to the user may be performed, or a reservation process of the information provision may be performed so that the information provision is performed at a timing appropriate for the user. Further, as described above, a flag may be set so that the information is provided according to the action of the user. For example, the information may be provided on the web page the next time the user browses the top page of the EC site.

It should be noted that the execution interval of the batch process and the predetermined period for detecting the increasing tendency of the index value may be different periods. For example, consider a case where an object whose index value has increased in the last week is specified. At this time, the batch processing may be executed once a day. By executing the batch processing at intervals (for example, one-day intervals) shorter than a predetermined period (for example, one week) for detecting the rising tendency, omission of detection of the rising tendency of the index value can be prevented.

<7. Other processing examples>

[7-1. Information provision effect check processing]
In the first embodiment and the second embodiment, the processing for providing appropriate information to the user has been described.
Here, an example of a process executed by the information providing device 7 after each information provision will be described.

Specifically, the effect of the information provision is confirmed, and processing according to the confirmation result is performed. This will be described with reference to FIG.
In step S701, the information providing device 7 specifies the user cluster UC that has provided the information. In the process of step S701, a user cluster UC that has passed a predetermined period (for example, one week) from information provision may be specified. This is because there is a time lag between the timing of providing information and the timing at which the effect begins to appear.

  Subsequently, in step S702, the information providing apparatus 7 specifies the affiliated user whose index value of the information providing target has not increased due to the information providing.

  Next, the information providing device 7 determines whether to change the user cluster UC to which the specified belonging user belongs. Specifically, in step S703, the information providing device 7 determines whether or not another user cluster UC suitable for the affiliation exists.

  If it is determined that another user cluster UC suitable for the affiliation exists, the information providing apparatus 7 changes the affiliation user cluster in step S704. Thus, for a user who belongs to the user cluster UC that has provided information and whose index value has not changed by providing information, if there is another user cluster UC to which the user belongs, the belonging cluster Is changed, and the uniformity of the preference tendency of the user cluster UC is maintained.

  On the other hand, when there is no other user cluster suitable for the affiliation, the series of processing illustrated in FIG. 10 ends. However, if “N” is determined in step S703, a new user cluster UC for newly belonging the user specified in step S702 may be generated.

Further, before executing the processing of step S703, the average value of the distance from the reference model is calculated for each identified user, and the user who moves the user whose average value is equal to or more than the predetermined value to another user cluster May be executed. According to this, even if the user does not change the index value due to the information provision, if the user is a user close to the reference model of the user cluster UC to which the user currently belongs, the affiliation is changed. Absent. On the other hand, if the user whose index value has not changed due to the provision of the information and the distance of the currently belonging user cluster UC from the reference model has become long, the user cluster to which the user cluster belongs belongs A change in UC is made.
This also makes it possible to maintain the uniformity of the preference tendency of the user cluster UC.

[7-2. General trend detection processing]
In the various examples described above, an example has been described in which information is provided to the user based on the preference tendency of each user cluster UC. Here, an example will be described in which a change in preference tendency is detected across the user cluster UC and information is provided to the user.

  In step S801, the information providing apparatus 7 identifies a target whose index value has increased within a predetermined period. For example, for any of the users (ie, all users) belonging to each user cluster UC, the target object whose index value has increased in the last week is specified.

In step S802, the information providing apparatus 7 narrows down, from the specified objects, those objects in which the index value of the user has increased by a certain percentage or more of all the users.
It is guessed that the target object in which the index value of a certain percentage of users among all the users has risen is a product or the like that is popular or popular in the world regardless of the index tendency for each user cluster UC. You.

In step S803, the information providing device 7 performs a process of generating provided information on the target object. This process is to generate appropriate information according to the means for providing information.
The information providing device 7 performs an information providing process in step S804. This process may be a process of transmitting the provided information or a process of setting the timing of transmitting the provided information.

[7-3. Presentation process of favorite information]
The process of presenting the user's favorite information to the user will be described.
The process of presenting the favorite information to the user is performed, for example, when the user browses the favorite management page.
At this time, it is conceivable to present the favorite information to the user so that the index value of the favorite index is known, or to present the favorite information so that the index value of the favorite index is not known.

FIG. 12 shows an example of the favorite management page presented to the user. FIG. 12 shows an example of a favorite management page for managing favorite information about a product.
On the favorite management page, information on a plurality of favorite products is arranged vertically. The information of one favorite product includes a product image area 8 in which an image of the favorite product is displayed, a product name display column 9 in which a product name is displayed, a store name display column 10 in which a store name is displayed, and price information. Price information display field 11 and a delete icon 12 for removing the product from favorite products.

In FIG. 12, the favorite information is presented so that the index value is not known to the user. When the index value is presented so as to be understood by the user, the user can intentionally perform an operation for changing the index value. That is, it is possible to perform a browsing operation for uselessly browsing another product in order to lower the index value of a specific product.
As a result, there is a possibility that the index value capable of appropriately expressing the user's preference tendency may be distorted by the user's intentional operation. In other words, there is a possibility that appropriate information cannot be provided to the user.

In this example, in order to prevent this, favorite information is provided so that the user cannot know the index value.

<8. Modification>

In the above description, as an example of decreasing the index value, a case in which regular purchase of a product is canceled has been described. In addition, the index value may be reduced. For example, it is conceivable that information is provided to the user by raising the index value of a product that the user is interested in checking. However, when the user actually purchases the product, it may be difficult for the user to maintain the same level of interest in the purchased product. In such a case, it is conceivable to decrease the index value for the product. Such a tendency is strongly observed when the purchased product is not a consumable but is a product that can be used for a long time and is sufficient for one user to have.
Therefore, it is desirable to reduce the index value for a product in consideration of the nature of the product and the purchase information of the user.

If the product is a consumable item, the index value of the product may be kept high. As another method, immediately after purchase, unnecessary information provision is suppressed by temporarily lowering the index value of the product, and the time when repurchase is likely to be performed in consideration of the purchase interval and consumption feeling of the product It is also effective to improve the index value of the product again immediately before the arrival of the product.
According to this, it is possible to suppress improper information provision according to the user's purchase, not to make the user feel troublesome, and to provoke the user's willingness to purchase by providing information on alternative products and the like. be able to.

Further, for example, when a product having a high favorite index (hereinafter, product S1) is not purchased but a similar product (hereinafter, product S1 ′) is purchased, the index value of the product S1 may be reduced. . That is, despite the fact that interest in the product S1 has dropped due to the purchase of the product S1 'which is a substitute for the product S1 having a high index value, the interest in the product S1 has not been made because the purchase of the product S1 has not been made. There is a risk that an erroneous determination that the information has not been lowered and unnecessary information provision may be performed.
By appropriately resetting the index value of the original product S1 by purchasing the substitute product S1 ', it is possible to prevent unnecessary or unfavorable information provision for the user.

  In addition, it is preferable to lower the index value for an object such as a product for which the user has canceled the favorite registration.

  In the example described with reference to FIG. 5 and the like, an example has been described in which after performing the cluster information changing process in step S206 based on the operation of the operating user, the information providing process is performed in step S207. According to this processing order, if the divergence from the reference model of the user cluster UC to which the operating user belongs at the time becomes greater than or equal to a certain value due to the change of the user's favorite index, the affiliation is determined in step S206. The cluster changes. Here, the user cluster UC to which the operating user belonged before the belonging cluster was changed is referred to as “user cluster UC before change”, and the user cluster UC to which the operating user belongs after changing the belonging cluster is referred to as “post-change user cluster UC”. .

In this case, in the example of the information providing process in step S207 (FIG. 8), when it is determined whether there is an object to provide information, in the user cluster UC before change, the operating user is not a belonging user. Therefore, there is a possibility that it is determined that the change in the preference tendency for the target object has not occurred.
Therefore, it is conceivable to perform the information providing process in step S207 before performing the cluster information changing process in step S206. Specifically, after performing the favorite index changing process, the information providing process is performed by detecting a change in the preference tendency in the user cluster UC based on the change of the favorite index. After the information is provided, some users follow the change in the preference tendency and some users do not, and the user waits for a certain period of time (a certain period) until the number of users following the change in the preference tendency has settled down. After the change in the preference tendency has calmed down, the cluster information changing process in step S206 is performed.
Further, for example, after performing the processing in step S205 in FIG. 5, the processing in step S207 may be performed, and the information providing effect check processing illustrated in FIG. 10 may be performed after a certain period of time.

Thereby, it is possible to appropriately detect the preference tendency in the user cluster UC in accordance with the operation performed by the user, and to appropriately change the user cluster information in accordance with the change in the preference tendency in the user cluster UC. Can be.

<9. Summary>

As described in the above-described various examples, the index management unit 7a that manages, for each object, a favorite index that indicates the degree of favorite of the object belonging to at least one of the product, the store, and the genre in three or more stages. A cluster management unit 7b that manages user clusters UC in which users are clustered based on the index, a change tendency detection unit 7c that detects a change tendency of a favorite index of a user belonging to one user cluster UC, and a detected favorite index If the change tendency is a rising tendency of the favorite degree, a target user extracting unit 7d that extracts, as a target user, a user belonging to one user cluster UC and for which no rising tendency is detected, Provide information to the target user on the target for which the upward trend was detected Includes a broadcast provider 7e, the.
By managing the favorite index indicating the degree of favorite in three or more levels, the preference information of the user is more finely managed than using the index indicating whether the user is simply a favorite or not in binary.
For example, a product that is determined to have a high favorite degree contrary to the user's intention and a product that the user intentionally specifies to have a high favorite degree can be managed as different favorite degrees.
As a result, a product or the like that is really favorite for the user can be managed separately from other products, and appropriate information can be provided to the user.
In addition, it is presumed that a product or the like for which the tendency of increasing the degree of favorite is detected in the user cluster UC is a product or the like that a user belonging to the user cluster UC is likely to like. Such a product is a user who belongs to the same user cluster UC, and is likely to be a favorite product even for a user who does not know the product or the like. It is possible to provide appropriate information in consideration of the similarity of the above. In particular, by setting the favorite index to three or more levels, clustering of users whose commonality of taste is emphasized is performed, so that a high effect of information provision can be obtained.

As described in the second embodiment, FIG. 9, and the like, the target user extracting unit 7d increases the percentage of users belonging to one user cluster UC within a predetermined period with respect to the same target object. When a tendency is detected, a target user may be extracted.
That is, when a phenomenon in which the evaluation of the target increases in the user cluster UC occurs to a certain extent, the target user is extracted.
This makes it possible to provide effective information to users belonging to the same user cluster UC and having a similar favorite tendency. In particular, by setting a rising trend within a predetermined period, a change in an instantaneous trend that occurred in a certain user cluster UC can be expanded to a user having the same favorite tendency, thereby changing the trend to a large trend. it can. Thereby, the effect of providing various information can be increased.

As described in the information provision effect check processing and FIG. 10 and the like, as a result of providing information, the cluster management unit 7b separates a user who did not follow the change tendency from a user who did not follow the change tendency into a different user cluster UC. Good.
It is presumed that users who did not follow the change tendency as a result of providing information have different favorite tendencies. According to this configuration, such users are classified into different user clusters UC.
Therefore, it is possible to suppress the variation in the favorite tendency of each user in the user cluster UC, and it is possible to increase the efficiency of providing useful information. In addition, appropriate clustering processing is performed in consideration of the change over time in the favorite tendency of each user in the user cluster UC, and the effect of providing information can be prevented from fading with time.

As described in the example of the favorite index change process, step S304 in FIG. 6, and the like, the index management unit 7a may calculate the favorite index according to the number of purchases and the purchase frequency.
The act of purchasing a product is a daily act for the user. Calculating and updating a favorite index for a product, store, or genre based on such routinely performed actions reflects not only the user's favorite tendency but also rapid changes over time. It is possible.
By appropriately providing information in accordance with the user cluster UC reflecting the latest favorite tendency of the user, it is possible to maximize the effect of information provision.

As described in the example of the favorite index change process, step S304 in FIG. 6, and the like, the favorite index is set to an index that is set higher as the degree of favorite is higher, and the index management unit 7a performs the operation based on the user's active operation. When raising the favorite index of the object set as the operation target, the favorite index may be increased more than that based on the inactive operation of the user.
An operation performed by the user for favorite registration actively declares that the user likes the object, and such an object is automatically registered as a favorite by an inactive operation. The object is different from the target object. According to this configuration, the increase value (or increase rate) of the favorite index of the target object differs depending on whether the operation is active.
Thereby, the management of the favorite index appropriate for the operation content of the user is performed, and the appropriate information provision based on the index can be performed.

As described in the example of the favorite index change process and steps S305 to S307 in FIG. 6, the favorite index is set as an index that is set higher as the degree of favorite is higher, and the index management unit 7a determines that the favorite index is the highest value. It may be managed so that the number of performed objects is equal to or less than a predetermined number.
As a result, the number of objects such as commodities that can be the target of providing information with the favorite index being the highest value is suppressed to a certain number or less.
Therefore, it is possible to prevent the user from being provided with excessive information. In particular, when information is provided by issuing an e-mail to a user, it is necessary to prevent a situation in which the user cannot view excessive e-mail and is left unread. Can be.

As described in the processing of presenting favorite information and FIG. 12 and the like, when presenting the user with the corresponding information of the favorite index and the target that is equal to or more than the predetermined value, the favorite index is presented so as not to be understood. May be.
For example, the favorite index is an index represented by 1 to 10, the indifferent object is represented by 5, and the favorite object is represented by 6 when the favorite object is represented by 6 to 10. An object whose favorite index is set to 10 is an object having a higher degree of user's favorite than an object. At this time, the object with the favorite index of 6 and the object with the favorite index of 10 are presented to the user in a similar display manner so that the magnitude of the index value is not known. I can't tell the difference between the numbers. Therefore, the user cannot intentionally increase the number of objects for which the favorite index has the highest value (= 10).
Thus, it is possible to prevent the number of objects having the favorite index having the highest value from being excessively increased, and to prevent the user from being provided with excessive information.

As described in the example of the favorite index change process and in step S304 in FIG. 6, the favorite index is an index that is represented by n or less (for example, 3 or less) and is set to a higher value as the degree of favorite is higher. The management unit 7a sets m (for example, 1) as a favorite index of an indifferent object for which the user has not performed a favorite registration operation, and sets m as a favorite index of an object for which the user has performed a favorite registration operation. Is set to a large value (for example, 3 which is the highest value), and the favorite index is increased for the target object of the favorite registration operation whose main purpose is other than the favorite registration. May be set to a value less than n (for example, 2).
For example, when a user purchases a product and the product to be purchased is registered as a favorite, the user may not intend to register the product as a favorite. In such a case, the favorite index of the product is set to a value lower than the highest value n.
As a result, it is possible to prevent information from being provided excessively for an object such as a product that has been unintentionally registered as a favorite.

As described in the example of the general trend detection process and FIG. 11, the change tendency detection unit 7c may detect the overall change tendency across the user cluster UC.
The user cluster UC is a group of users who have the same favorite tendency for each target object. By analyzing the user cluster UC cross-sectionally, it is possible to grasp the overall change tendency. It is.
That is, it is possible to extract a target object such as a product that shows signs of fashion without depending on the user cluster UC, and it is possible to provide effective information to each user.

The examples described in the first embodiment, the second embodiment, the other processing examples, and the modified examples described above may be combined in any manner as long as the combination is not possible.

<10. Program and Storage Medium>

The program according to the embodiment is a program that causes an arithmetic processing device (CPU or the like) of the information providing device 7 to execute various processes.

The program according to the embodiment causes the arithmetic processing device to execute an index management function for managing, for each object, a favorite index indicating the degree of favorite of the object belonging to at least one of a product, a store, and a genre in three or more stages.
Further, the processor is caused to execute a cluster management function of managing a user cluster in which the users are clustered based on the favorite index.
Further, the processing unit is caused to execute a change tendency detecting function of detecting a change tendency of a favorite index of a user belonging to one user cluster.
Further, when the detected tendency of the favorite index is a rising tendency of the favorite degree, a target user extraction for extracting, as a target user, a user belonging to one user cluster and not detecting the rising tendency. Causes the processing unit to execute the function.
In addition, the information processing device is caused to execute an information providing function of providing the target user with information on the target object for which the increasing tendency of the favorite degree is detected.
That is, this program is a program for causing the arithmetic processing unit of the information processing apparatus to execute each processing of steps S205 to S207 in FIG. 5 and each processing shown in FIGS. 6 to 11.

With such a program, one or a plurality of information processing apparatuses as the information providing apparatus 7 described above can be realized.
Such a program can be stored in advance in an HDD as a storage medium built in a device such as a computer device, a ROM in a microcomputer having a CPU, or the like. Alternatively, it can be temporarily (permanently) stored in a removable storage medium such as a semiconductor memory, a memory card, an optical disk, a magneto-optical disk, or a magnetic disk. Further, such a removable storage medium can be provided as so-called package software.
Such a program can be installed on a personal computer or the like from a removable storage medium, or can be downloaded from a download site via a network such as a LAN or the Internet.

  Reference Signs List 1 network system, 2 communication network, 3 electronic commerce system, 4 user terminal, 5 store terminal, 6 shopping server, 7 information providing device, 7a index management unit, 7b cluster management unit, 7c change tendency detection unit, 7d target user extraction Department, 7e Information Provision Department, 50 User DB, 51 Product DB, 52 Store DB, 53 History DB, 54 Index DB, 55 Cluster DB

An information processing apparatus according to the present invention includes: an index management unit that manages, for each of the objects, an index value indicating a degree of interest and interest of the user in at least one of a product, a store, and a genre in a plurality of stages. comprises a cluster management section for managing user cluster said user is clustered based on the index value, the changing tendency detecting unit for detecting a changing trend of the index value of the user belonging to one of said user clusters, the ing.
An environment for providing appropriate information to the user according to the change tendency is formed by detecting the change tendency of the interest for each user cluster using the index value indicating the degree of the interest in a plurality of stages or more. You.

In the information processing apparatus described above, when presenting the object corresponding to the index value set to a predetermined value or more to the user, the target object may be presented such that the magnitude of the index value is not known.
For example, when the index value is an index represented by 1 to 10, the indifferent object is represented by 5 and the object of high interest is represented by 6 to 10, the index value is 6 The object whose index value is set to 10 is regarded as an object having a higher degree of interest and interest of the user than the target object. At this time, the object having the index value of 6 and the object having the index value of 10 are presented to the user in a similar display manner so that the magnitude of the index value is not known. I can't tell the difference between the numbers. Therefore, the user cannot intentionally increase the object whose index value is the highest value (= 10).

<9. Summary>

As described in the above-described various examples, an index management unit 7a that manages, for each target, a favorite index that indicates the user's favorite degree of the target belonging to at least one of a product, a store, and a genre in three or more levels. A cluster management unit 7b that manages a user cluster UC in which users are clustered based on a favorite index, a change tendency detection unit 7c that detects a change tendency of a favorite index of a user belonging to one user cluster UC, A target user extraction unit 7d for extracting, as a target user, a user who belongs to one user cluster UC and whose rising tendency is not detected when the change tendency of the favorite index is a rising tendency of the favorite degree; Provide information to the target user on the target for which the increasing tendency is detected. It includes an information providing portion 7e to provide the.
By managing the favorite index indicating the degree of favorite in three or more levels, the preference information of the user is more finely managed than using the index indicating whether the user is simply a favorite or not in binary.
For example, a product that is determined to have a high favorite degree contrary to the user's intention and a product that the user intentionally specifies to have a high favorite degree can be managed as different favorite degrees.
As a result, a product or the like that is really favorite for the user can be managed separately from other products, and appropriate information can be provided to the user.
In addition, it is presumed that a product or the like for which the tendency of increasing the degree of favorite is detected in the user cluster UC is a product or the like that a user belonging to the user cluster UC is likely to like. Such a product is a user who belongs to the same user cluster UC, and is likely to be a favorite product even for a user who does not know the product or the like. It is possible to provide appropriate information in consideration of the similarity of the above. In particular, by setting the favorite index to three or more levels, clustering of users whose commonality of taste is emphasized is performed, so that a high effect of information provision can be obtained.

As described in the processing of presenting favorite information and FIG. 12 and the like, when presenting an object corresponding to a favorite index set to a predetermined value or more to the user, the user is presented so that the number of favorite indexes is not known. You may.
For example, the favorite index is an index represented by 1 to 10, the indifferent object is represented by 5, and the favorite object is represented by 6 when the favorite object is represented by 6 to 10. An object whose favorite index is set to 10 is an object having a higher degree of user's favorite than an object. At this time, the object with the favorite index of 6 and the object with the favorite index of 10 are presented to the user in a similar display manner so that the magnitude of the index value is not known. I can't tell the difference between the numbers. Therefore, the user cannot intentionally increase the number of objects for which the favorite index has the highest value (= 10).
Thus, it is possible to prevent the number of objects having the favorite index having the highest value from being excessively increased, and to prevent the user from being provided with excessive information.

Claims (11)

An index management unit that manages, for each of the objects, an index value representing the degree of interest in the object belonging to at least one of the product, the store, and the genre in a plurality of stages;
A cluster management unit that manages a user cluster in which users are clustered based on the index value;
A change tendency detecting unit configured to detect a change tendency of the index value of a user belonging to one user cluster. When the detected change in the index value is a rising trend of the degree of interest, a user belonging to the one user cluster and a user for whom the rising trend is not detected is extracted as a target user. A user extraction unit;
The information processing device according to claim 1, further comprising: an information providing unit configured to provide information on the target in which the upward trend is detected to the target user. The target user extraction unit extracts the target user when a certain percentage of users belonging to the one user cluster detects the upward trend within a predetermined period of the same target object. The information processing apparatus according to claim 2. 4. The information processing apparatus according to claim 2, wherein, as a result of providing the information, the cluster management unit separates a user along the change tendency and a user not along the change tendency into different user clusters. 5. . The information processing apparatus according to any one of claims 1 to 4, wherein the index management unit calculates the index value according to the number of purchases and the purchase frequency. The index value is an index that is set higher as the degree of interest is higher,
The index management unit, when increasing the index value of the object set as the operation target based on the active operation of the user, increases the index value more than based on the inactive operation of the user. Item 6. An information processing device according to any one of Items 5. The index value is an index that is set higher as the degree of interest is higher,
The information processing apparatus according to claim 1, wherein the index management unit manages the number of the objects for which the index value is set to a maximum value to be equal to or less than a predetermined number. The information processing apparatus according to claim 7, wherein when presenting the correspondence information between the index value and the object that is equal to or more than a predetermined value to the user, the index value is presented so as to be unclear. The index value is an index represented by n or less and set as a higher value as the degree of interest is higher,
A first operation and a second operation are provided as operations indicating that the degree of interest is high,
When the first operation is an operation indicating that the degree of interest is higher than the second operation,
The index management unit,
The value smaller than n is set when raising the said index value of the said target object of this 2nd operation according to the said 2nd operation having been performed. Information processing device. The information processing apparatus according to any one of claims 1 to 9, wherein the change tendency detection unit detects an overall change tendency across the user cluster. An index management step of managing, for each object, an index value indicating a degree of interest in an object belonging to at least one of a product, a store, and a genre;
A cluster management step of managing a user cluster in which users are clustered based on the index value;
A change tendency detecting step of detecting a change tendency of the index value of a user belonging to one user cluster, the information processing method executed by the information processing apparatus.

Images