JP2015133033A - Recommendation device, recommendation method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem in which conventionally appropriate products or services cannot be recommended.SOLUTION: An appropriate product or service can be recommended by a recommendation device 11 comprising: a user management information storage unit that can store one user management information or more including a user identifier, one purchase history information or more, and one browsing product information or more about a product viewed by a user; a product information storage unit that can store two product information or more including one attribute information or more; a reception unit that receives the user identifier from a terminal device; a product information acquisition unit that acquires all or one part of one product information or more from using one purchase history information or more making a pair with the user identifier received by the reception unit and one browsing product information or more from the product information storage unit; and a recommendation unit that transmits all or one part of one product information or more acquired by the product information acquisition unit to the terminal device.

Description

  The present invention relates to a recommendation device that recommends information on goods or services to a user.

  There have been many recommendation devices that determine recommended items for a target user based on historical data of a large number of users.

  In addition, there has been a recommendation system that enables an accurate recommendation regarding an item with little history information based on the history information of another item with a lot of history data (see Patent Document 1).

  Furthermore, there was a head-mounted display type augmented reality wearable computer (for example, see Non-Patent Document 1).

Japanese Unexamined Patent Publication No. 2007-102407 (first page, FIG. 1 etc.)

Wikipedia, "Google Glass", [searched on November 14, 2013], Internet [URL: http://en.wikipedia.org/wiki/Google_Glass]

  However, in the prior art, it was not possible to recommend an appropriate product or service.

  In particular, in the prior art, it is possible to recommend an appropriate product or service by using both the purchase history information, which is one of the results of the user's conscious behavior, and the browsing product information indicating the movement of unconscious feelings. There wasn't. The purchase history information is information related to the purchase history of the user's product, and the browse product information is information related to the product viewed by the user.

  The recommendation device according to the first aspect of the present invention includes a user identifier for identifying a user, one or more purchase history information that is information related to a user's product purchase history, and one or more browsing products that are information related to the product viewed by the user. A user management information storage unit that can store one or more user management information having information, and a product information storage unit that is information about the product and can store two or more product information having one or more attribute information of the product; , Using a receiving unit that receives a user identifier from the terminal device, one or more purchase history information that is paired with the user identifier received by the receiving unit, and one or more browsed product information from the product information storage unit A product information acquisition unit that acquires all or part of product information, and a recommendation unit that transmits all or a part of one or more product information acquired by the product information acquisition unit to the terminal device It is a Komendo apparatus.

  With this configuration, it is possible to make recommendations for appropriate products or services using purchase history information and browsed product information.

  Moreover, the recommendation apparatus of this 2nd invention is a recommendation apparatus in which browsing goods information contains the positional information which shows the position where the user looked at goods with respect to 1st invention.

  With this configuration, it is possible to recommend more appropriate products or services.

  Moreover, the recommendation apparatus of this 3rd invention is related with the goods which browsing goods information which is the information regarding the goods which the user stared and the goods which the user did not stare with respect to the 1st or 2nd invention. It is a recommendation device including non-gaze product information that is information.

  With this configuration, it is possible to recommend more appropriate products or services.

  Further, in the recommendation device according to the fourth aspect of the present invention, with respect to any one of the first to third aspects, the browsed product information includes user product related information that is information indicating a physical positional relationship between the user and the product. It is a recommendation device including.

  With this configuration, it is possible to recommend more appropriate products or services.

  The recommendation device according to the fifth aspect of the present invention is a recommendation device in which the browsed merchandise information includes the biological information of the user while the user is viewing the merchandise, as compared with any of the first to fourth inventions.

  With this configuration, it is possible to recommend more appropriate products or services.

  Further, in the recommendation device according to the sixth aspect of the invention, in contrast to any one of the first to fifth aspects, the browsed product information is facial expression information that is information related to the movement of the surface of the user while the user is viewing the product. It is a recommendation apparatus containing.

  With this configuration, it is possible to recommend more appropriate products or services.

  Further, in the recommendation device of the seventh aspect of the invention, in response to any one of the first to sixth aspects, the recommendation part is acquired by the product information acquisition part so as to be output on the web page of the online shopping site. This is a recommendation device that transmits all or part of the product information to the terminal device.

  With this configuration, it is possible to recommend an appropriate product or service on an online shopping site.

  Further, in the recommendation device according to the eighth aspect of the present invention, with respect to any one of the first to seventh aspects, the product information acquisition unit includes one or more purchase history information paired with the user identifier received by the reception unit, and 1 Using the above browsed product information, an advertisement of one or more products included in the one or more product information is acquired from the product information storage unit, and the recommendation unit is an advertisement of one or more products acquired by the product information acquisition unit. Is a recommendation device that transmits to the terminal device.

  With this configuration, it is possible to output an advertisement for a more appropriate product or service.

  Further, in the recommendation device according to the ninth aspect of the present invention, with respect to any one of the first to sixth aspects, the product information acquisition unit includes one or more purchase history information paired with the user identifier received by the reception unit, and 1 Using the browsing product information described above, the attribute value of the product included in the one or more product information is acquired from the product information storage unit, and the recommendation unit transmits the attribute value of the product acquired by the product information acquisition unit to the terminal device. It is a recommendation device to transmit.

  With this configuration, it is possible to recommend more appropriate products or services.

  The recommendation device according to the tenth aspect of the present invention is a recommendation device in which the purchase history information is information related to a product or service purchased by a user using a credit card, as compared with any of the first to ninth aspects. .

  With such a configuration, it is possible to recommend an appropriate product or service using purchase history information by credit card.

  According to the recommendation system according to the present invention, it is possible to recommend an appropriate product or service using purchase history information and browsed product information.

The figure which shows the conceptual diagram of the recommendation system 1 in Embodiment 1. FIG. Block diagram of the recommendation system 1 A flowchart for explaining the operation of the recommendation device 11 Flow chart explaining the product information acquisition process The figure which shows the same user purchase history information management table The figure which shows the same user inspection commodity information management table The figure which shows the same reading commodity information management table Figure showing the product information management table Figure showing the same output example Overview of the computer system Block diagram of the computer system

  Hereinafter, embodiments of a recommendation system and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment 1)
In this embodiment, a recommendation system that selects and outputs information on a product recommended for a user using the user's behavior history information including the user's purchase history information and browsing product information will be described. In the present specification, a product is an object to be bought and sold, and is usually used to include a service.

  In the present embodiment, the browsing product information includes various types of information representing the movement of unconscious emotion, as will be described later.

  Further, in the present embodiment, the purchase history information includes, for example, purchase history information by credit card, and a recommendation for selecting and outputting information on products recommended to the user using a wide range of purchase history information. The system will be described.

  FIG. 1 is a conceptual diagram of a recommendation system 1 in the present embodiment. The recommendation system 1 includes a recommendation device 11, one or more terminal devices 12, a browsing product management server 13, and a purchase history management server 14. The recommendation device 11 is a device for implementing a recommendation. The terminal device 12 is a terminal that the user has, and is a terminal that outputs product information and the like, for example, a so-called personal computer, smartphone, tablet terminal, mobile phone, and the like. The browsed product management server 13 is a server device that manages information related to products and the like browsed by the user. The purchase history management server 14 is a server device that stores information on a user's purchase history with a credit card.

  FIG. 2 is a block diagram of the recommendation system 1 in the present embodiment.

  A recommendation device 11 constituting the recommendation system 1 includes a user management information storage unit 111, a product information storage unit 112, a reception unit 113, a product information acquisition unit 114, a recommendation unit 115, a purchase history information acquisition unit 116, and a purchase history information storage unit. 117, a browsing product information acquisition unit 118, and a browsing product information storage unit 119.

  The terminal device 12 includes a terminal reception unit 121, a terminal transmission unit 122, a terminal reception unit 123, and a terminal output unit 124.

  The browsing product management server 13 includes a browsing product information storage unit 131, a browsing product transmission instruction reception unit 132, and a browsing product information transmission unit 133.

  The purchase history management server 14 includes a purchase history information storage unit 141, a purchase history transmission instruction reception unit 142, and a purchase history information transmission unit 143.

  The user management information storage unit 111 constituting the recommendation device 11 can store one or more user management information. The user management information includes a user identifier for identifying a user, one or more purchase history information, and one or two or more browsed product information. The user management information is information about the user. The user management information may include, for example, user attributes that are user attributes. The user attribute may be called personal information. User attributes are, for example, sex, age, address, and the like. Further, the user management information may include notification destination information for notifying the user of information. The notification destination information is, for example, a mail address or an IP address.

  The user identifier is, for example, a user ID, a mail address, a mobile phone number, a credit card number, an IP address, or the like.

  The purchase history information is information related to the purchase history of the user's product. The purchase history information is information related to products purchased by the user using a credit card, for example. The purchase history information includes, for example, a credit card number, a product name, a price, a use store name, a use date, and the like. The purchase history information may be information on purchase history of products on the net. The purchase history information may be, for example, information related to a product purchased by a user using a credit card and information on a purchase history of a product on the net.

  The browsed product information is information related to the product viewed by the user. Here, the product viewed by the user may be a product that has been viewed well as the predetermined condition is satisfied (for example, the user has been in the field of view beyond the threshold), or the product that has entered the field of view is determined in advance. A product that has not been seen so much as to satisfy the condition, that is, a so-called product that has passed through may be used. The product viewed by the user is, for example, a product photographed by a camera worn by the user, a product corresponding to the user identified by the user ID received by the receiver associated with the product, or the like. The browsed product information may include position information indicating a position where the user has viewed the product. The browsed product information may include gaze product information that is information related to a product stared by the user and non-gaze product information that is information related to a product that the user has not stared at. The stared product is, for example, a product that has been reflected on the camera for a time equal to or greater than a threshold value. Moreover, the goods which did not stare are goods which were reflected on the camera for less time than a threshold value, for example. The browsed product information may include user product related information that is information indicating a physical positional relationship between the user and the product. The user product related information is, for example, information indicating the distance between the user and the product, information indicating whether the user has touched the product, or the like. The user product related information may be, for example, the number of times and time when the distance between the user and the product is within a certain range, the number of times the user touched the product, time, and the like. Further, the browsed product information may include biometric information of the user while the user is viewing the product. The biological information is information such as blood pressure and pulse, for example. The biological information may be, for example, information such as the number of times that blood pressure, pulse, etc. have changed abruptly so as to satisfy a predetermined condition. The browsed product information may include facial expression information that is information related to the movement of the user's surface while the user is viewing the product. The facial expression information is, for example, information such as an eyebrow raised, a pupil opened, a saliva, a frown. The facial expression information may be, for example, the number of times that the eyebrows are raised, the pupil is opened, the saliva is swollen, the eyebrows are frowned, the number of times, the number of times per unit time, or the like.

  The product information storage unit 112 can store two or more product information. The product information is information related to the product, and has one or more attribute information of the product. Here, the attribute information is, for example, the type of product, the amount of money, and the seller. Note that the product information is information on a product to be recommended.

  The receiving unit 113 receives a user identifier from the terminal device 12. There is no limitation on the timing at which the receiving unit 113 receives the user identifier.

  The product information acquisition unit 114 uses the one or more purchase history information and the one or more browsed product information that are paired with the user identifier received by the reception unit 113 to store all of the one or more product information from the product information storage unit 112. Or get some. Here, a part of the product information may be an advertisement of a product included in the product information. Further, the part of the product information may be one or more attribute values of the product included in the product information.

  Further, the product information acquisition unit 114 acquires all or part of the one or more product information from the product information storage unit 112 using one or more browsed product information paired with the user identifier received by the reception unit 113. May be. That is, the product information acquisition unit 114 may acquire all or part of the one or more pieces of product information without using the one or more pieces of purchase history information.

  In addition, the product information acquisition unit 114 acquires, for example, one or more purchase history information and one or more browsed product information that are paired with the user identifier received by the reception unit 113, and the one or more purchase history information and 1 Using the above browsed product information, a product that the user likes or a product that the user does not like is determined from the product indicated by the product information in the product information storage unit 112. And the merchandise information acquisition part 114 acquires all or one part of the 1 or more merchandise information corresponding to the goods determined that the said user likes. Further, the product information acquisition unit 114 does not acquire all or a part of one or more product information corresponding to the product determined to be unfavorable by the user.

  In addition, the product information acquisition unit 114 acquires, for example, one or more browsing product information that is paired with the user identifier received by the reception unit 113, and uses the one or more browsing product information, for example, one or more gazes. Product information or / and non-staring product information is acquired. And the merchandise information acquisition part 114 may acquire all or one part of one or more merchandise information, for example using the one or more gaze merchandise information or / and non-gaze merchandise information. For example, the product information acquisition unit 114 may acquire all or part of the product information of the product corresponding to the gaze product information. Further, for example, the product information acquisition unit 114 may acquire all or part of the product information including the attribute value of the product corresponding to the gaze product information.

  Further, for example, the product information acquisition unit 114 determines a product that includes a product attribute value corresponding to the gaze product information and that is not a product corresponding to the non-gaze product information as a recommended product. Then, the product information acquisition unit 114 may acquire all or part of the product information of the determined product.

  Further, for example, the product information acquisition unit 114 determines a product that includes a product attribute value corresponding to the gaze product information and does not include a product attribute value corresponding to the non-gaze product information as a recommended product. Then, the product information acquisition unit 114 may acquire all or part of the product information of the determined product.

  In addition, the product information acquisition unit 114 acquires, for example, one or more purchase history information and one or more browsed product information that are paired with the user identifier received by the reception unit 113, and the one or more purchase history information and 1 One or more gaze product information and / or non-gaze product information is acquired using the browsed product information. The product information acquisition unit 114 is, for example, a product corresponding to the staring product information, and may acquire all or part of the product information of the product corresponding to the unpurchased product from the purchase history information.

  In addition, the product information acquisition unit 114 has, for example, the type of the product that has been viewed acquired from the one or more gaze product information and the type of the purchased product acquired from the one or more purchase history information, If the attributes of other products are different (the product you were viewing is expensive, etc.), select an attribute value that is highly similar to the attribute value of the product corresponding to the gaze product information or the product corresponding to the gaze product information. You may select the goods to have and acquire all or one part of the merchandise information of the said goods.

  In addition, as shown below, when acquiring all or a part of product information, the product information acquisition unit 114 obtains one or more types of information among gaze product information, non-gaze product information, and purchase history information. Any method may be used.

  The product information acquisition unit 114 determines, for example, one or more attribute values of the product that the user would like from the attribute value of the product corresponding to the gaze product information and / or one or more purchase history information. All or part of the product information of the product including the attribute value may be acquired. In addition, it can be said that one or more attribute values of a product that the user would like is a kind of preference information. The preference information is information related to the object preferred by the user, such as an attribute value of a product preferred by the user or a product preferred by the user.

  In addition, the product information acquisition unit 114 uses, for example, a product attribute value corresponding to the gaze product information and / or a product attribute value acquired from one or more purchase history information, and a product that the user may not like. One or more attribute values may be determined, and all or part of the product information of a product that does not include the one or more attribute values may be acquired. It should be noted that one or more attribute values of a product that the user may not like are a kind of exclusion information. Exclusion information is information about objects that the user does not like, such as attribute values of products that the user does not like or products that the user does not like.

  Further, the product information acquisition unit 114 determines one or more attribute values of the product that the user would like from the product attribute value corresponding to the gaze product information and / or one or more purchase history information. And the merchandise information acquisition part 114 may acquire all or one part of the merchandise information of the goods which are the goods containing the said 1 or more attribute value and do not respond | correspond to non-staring merchandise information, for example.

  Further, the product information acquisition unit 114 determines one or more attribute values of the product that the user would like from the product attribute value corresponding to the gaze product information and / or one or more purchase history information. And the merchandise information acquisition part 114 determines the 1 or more attribute value of the goods which a user would not like from the attribute value of the goods corresponding to non-staring merchandise information or / and one or more purchase history information, for example. . And the merchandise information acquisition part 114 may acquire all or one part of the merchandise information of the goods which do not contain the said 1 or more attribute value, for example. Furthermore, the product information acquisition unit 114 includes, for example, all of the product information of products including one or more attribute values of products that the user would like and not including one or more attribute values of products that the user would not like. Or you may acquire a part.

  In addition, the product information acquisition unit 114 determines, for example, the product preferred by the user using one or more browsed product information as follows, and the product information of the determined product or the attribute value of the determined product You may acquire all or some of merchandise information containing.

  When the browsed product information includes the position information, the product information acquisition unit 114 determines that the product prefers the product being browsed at a point that is greater than or equal to the threshold or greater than the threshold, for example. Further, when the browsed product information includes user product related information, the product information acquisition unit 114, for example, a product in which the number of times the user touched the product is greater than or equal to a threshold, and the time when the distance between the user and the product is within the threshold A product that is equal to or greater than the threshold is determined as a product that the user likes. In addition, when the browsed product information includes biological information, the product information acquisition unit 114 determines, for example, the product that was browsed when the blood pressure or the pulse rate was higher than the threshold as the product preferred by the user. Is preferred. For example, it is preferable that the product information acquisition unit 114 determines a product having a threshold value or more when the blood pressure or pulse is higher than the threshold value as a product that the user likes.

  The recommendation unit 115 transmits all or part of the one or more pieces of product information acquired by the product information acquisition unit 114 to the terminal device 12. It is preferable that the recommendation unit 115 transmits all or a part of one or more pieces of product information acquired by the product information acquisition unit 114 to the terminal device 12 so as to be output on the web page of the online shopping site. Further, the recommendation unit 115 may transmit an advertisement for one or more products acquired by the product information acquisition unit 114 to the terminal device 12. The recommendation unit 115 may transmit the attribute value of the product acquired by the product information acquisition unit 114 to the terminal device 12.

  The purchase history information acquisition unit 116 acquires one or more purchase history information from the purchase history management server 14. Here, “acquisition” is usually reception. It should be noted that the timing and method by which the purchase history information acquisition unit 116 acquires purchase history information does not matter. The purchase history information acquisition unit 116 may acquire purchase history information every time the receiving unit 113 receives a user identifier, or may periodically acquire purchase history information from the purchase history management server 14. .

  The purchase history information accumulation unit 117 accumulates the purchase history information acquired by the purchase history information acquisition unit 116 in the user management information storage unit 111. This purchase history information is information constituting user management information.

  The browsing product information acquisition unit 118 acquires one or more browsing product information from the browsing product management server 13. Here, “acquisition” is usually reception. There is no limitation on the timing and method by which the browsed product information acquisition unit 118 acquires the browsed product information. The browsed product information acquisition unit 118 may acquire the browsed product information every time the receiving unit 113 receives the user identifier, or may periodically acquire the browsed product information from the browsed product management server 13. .

  The browsing product information storage unit 119 stores the browsing product information acquired by the browsing product information acquisition unit 118 in the user management information storage unit 111. This browsed merchandise information is information constituting user management information.

  The terminal reception unit 121 configuring the terminal device 12 receives instructions, information, and the like from the user. Here, the information or the like is, for example, a user identifier. The terminal reception unit 121 may receive an instruction to access a web page including a user identifier. The user identifier input means may be anything such as a keyboard, mouse, touch panel, or menu screen. The terminal reception unit 121 can be realized by a device driver of an input unit such as a keyboard, menu screen control software, or the like.

  The terminal transmission unit 122 transmits instructions, information, and the like received by the terminal reception unit 121 to the recommendation device 11.

  The terminal reception unit 123 receives information from the recommendation device 11. Here, the information is, for example, all or part of the product information. The terminal receiving unit 123 may receive a web page including all or part of the product information.

  The terminal output unit 124 outputs information received by the terminal receiving unit 123.

  The browsing product information storage unit 131 constituting the browsing product management server 13 stores browsing product information for each user. The browsed merchandise information includes, for example, information of a result obtained by analyzing a video acquired by the wearable computer described in Non-Patent Document 1. Moreover, browsing product information contains the information of the result of having analyzed the image | video which image | photographed the user who browses goods, for example. The video shot of the user browsing the product is, for example, a video shot by a camera installed near the displayed product.

  Since the technology for recognizing each still image constituting a video and identifying a product included in the still image is a known image recognition technology, detailed description thereof is omitted. Also, if the image of the product included in each still image constituting the video is known, the time when the user views the product is expressed as “the number of still images in which the product is shown × 1 unit of still image (1 field)”. Needless to say, the calculation can be made according to “time (for example, 1/30 second)”.

  Further, the position information included in the browsed product information may be acquired by a GPS function or the like provided in the wearable computer, or may be held by a camera that captures the user.

  Further, the gaze product information included in the browse product information is acquired as follows, for example. A staring product information acquisition unit (not shown) recognizes each still image constituting a video by using a product image database having a product image and a product identifier as a pair, and acquires a product identifier. Then, the staring product information acquisition unit acquires the product identifier as staring product information when a still image including the product identified by the same product identifier continues for a predetermined time or more. Here, the staring product information acquisition unit may acquire one or more attribute values of the product as the staring product information when a still image including the product identified by the same product identifier continues for a certain period of time.

  In addition, the non-fixed product information included in the browsed product information is acquired as follows, for example. A non-fixed product information acquisition unit (not shown) recognizes each still image constituting a video by using a product image database having a product image and a product identifier as a pair, and acquires a product identifier. Then, when the still image including the product identified by the same product identifier continues for a time shorter than the threshold, the non-fixed product information acquisition unit acquires the product identifier as the non-fixed product information. Here, when the still image including the product identified by the same product identifier continues for a time shorter than the threshold, the non-staring product information acquisition unit acquires one or more attribute values of the product as non-staring product information. May be.

  Moreover, it acquires by the apparatus which acquires the biometric information contained in browsing merchandise information, for example, biometric information. Since such an apparatus is a known technique, its description is omitted.

  The facial expression information included in the browsed product information is acquired by, for example, a known facial image analysis technique (see, for example, the URL “http://www.kaga-create.co.jp/fas/”).

  The browsing product transmission instruction receiving unit 132 receives a browsing product information transmission instruction from the recommendation device 11 or the user. The reception here is reception or reception from the user.

  When the browsing product transmission instruction receiving unit 132 receives a browsing product information transmission instruction, the browsing product information transmission unit 133 transmits browsing product information corresponding to the transmission instruction to the recommendation device 11.

  The purchase history information storage unit 141 constituting the purchase history management server 14 can store one or more purchase history information.

  The purchase history transmission instruction receiving unit 142 receives a purchase history information transmission instruction from the recommendation device 11 or the user. The reception here is reception or reception from the user.

  When the purchase history transmission instruction reception unit 142 receives a purchase history information transmission instruction, the purchase history information transmission unit 143 transmits purchase history information corresponding to the transmission instruction to the recommendation device 11.

  The user management information storage unit 111, the product information storage unit 112, the browsing product information storage unit 131, and the purchase history information storage unit 141 are preferably non-volatile recording media, but can also be realized by volatile recording media.

  The process in which user management information etc. are memorize | stored in the user management information storage part 111 grade | etc., Is not ask | required. For example, user management information or the like may be stored in the user management information storage unit 111 or the like via a recording medium, and user management information or the like transmitted via a communication line or the like may be stored in the user management information storage unit 111. Or the user management information input via the input device may be stored in the user management information storage unit 111 or the like.

  The receiving unit 113, the purchase history information acquiring unit 116, the browsed product information acquiring unit 118, the terminal receiving unit 123, the browsed product transmission instruction receiving unit 132, and the purchase history transmission instruction receiving unit 142 are usually wireless or wired communication means. Although realized, it may be realized by means of receiving a broadcast.

  The product information acquisition unit 114, the purchase history information storage unit 117, and the browsed product information storage unit 119 can be usually realized by an MPU, a memory, or the like. The processing procedure of the merchandise information acquisition unit 114 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The recommendation unit 115, the terminal transmission unit 122, the browsing product information transmission unit 133, and the purchase history information transmission unit 143 are usually realized by wireless or wired communication means, but may be realized by broadcasting means.

  The terminal output unit 124 may be considered as including or not including an output device such as a display or a speaker. The terminal output unit 124 may be realized by output device driver software, or output device driver software and an output device.

  Next, the operation of the recommendation system 1 will be described. First, operation | movement of the recommendation apparatus 11 is demonstrated using the flowchart of FIG.

  (Step S301) The receiving unit 113 determines whether a user identifier or the like has been received from the terminal device 12. If a user identifier or the like is received, the process proceeds to step S302. If a user identifier or the like is not received, the process returns to step S301.

  (Step S302) The merchandise information acquisition unit 114 acquires a user identifier from the information received in Step S301.

  (Step S303) The browsed product information acquisition unit 118 acquires, from the browsed product management server 13, one or more browsed product information of the user identified by the user identifier using the user identifier acquired in Step S302. Here, the browsing product information storage unit 119 may store the acquired one or more browsing product information in the user management information storage unit 111 in association with the user identifier.

  (Step S304) The product information acquisition unit 114 acquires one or more purchase history information of the user identified by the user identifier from the purchase history management server 14 using the user identifier acquired in Step S302. Here, the purchase history information accumulation unit 117 may accumulate the acquired one or more purchase history information in the user management information storage unit 111 in association with the user identifier.

  (Step S305) The product information acquisition unit 114 uses one or more pieces of browsing product information acquired in step S303 and one or more purchase history information acquired in step S304. Get a department. Such merchandise information acquisition processing will be described with reference to the flowchart of FIG.

  (Step S306) The recommendation unit 115 transmits all or part of the one or more pieces of product information acquired in step S305 to the terminal device 12. The process returns to step S301.

  In the flowchart of FIG. 3, the process ends when the power is turned off or the process is terminated.

  Next, the product information acquisition process in step S305 will be described using the flowchart in FIG.

  (Step S401) The product information acquisition unit 114 acquires the personal information of the user included in the user management information corresponding to the user identifier acquired in Step S302 from the user management information storage unit 111. The personal information includes, for example, the user's sex, age group, address, and the like.

  (Step S402) The product information acquisition unit 114 receives one or more types of information among the personal information of the user acquired in Step S401, the acquired one or more browsed product information, and the one or more purchase history information. To obtain preference information.

  (Step S403) The product information acquisition unit 114 receives one or more types of information among the personal information of the user acquired in step S401, the acquired one or more browsed product information, and the one or more purchase history information. To obtain exclusion information.

  (Step S404) The merchandise information acquisition unit 114 uses one or more pieces of information among the personal information acquired in step S401, the preference information acquired in step S402, or the exclusion information acquired in step S403. Configure a search expression to search. The product information acquisition unit 114, for example, “(the product attribute value matches the personal information) AND (the product attribute value matches the preference information) AND (the product attribute value does not match the exclusion information)”. Construct a search expression. Further, the product information acquisition unit 114 may, for example, “(the attribute value of the product matches the personal information) AND (the attribute value of the product matches the attribute information of the product indicated by the preference information) AND (the product has the exclusion information. The search expression is not matched with the indicated product).

  (Step S405) The product information acquisition unit 114 executes the search formula configured in step S404, and selects one or more products from two or more products indicated by the two or more product information included in the product information storage unit 112.

  (Step S406) The product information acquisition unit 114 determines a product to be recommended from one or more products selected in step S405. The product information acquisition unit 114 normally determines a part of the products selected in step S405 as recommended products, but may determine all the products selected in step S405 as recommended products. In addition, when determining some products as recommended products, the product information acquisition unit 114 may randomly select N (N is a natural number of 1 or more) products, or calculate a score for each product. N products (N is a natural number of 1 or more) having a high score may be selected, or products having a score higher than a threshold value may be selected. The score may be, for example, a degree of preference described later, or a numerical value calculated using the degree of preference and an attribute value of purchase history information.

  (Step S407) The product information acquisition unit 114 acquires all or part of one or more product information of the one or more products selected in step S406 from the product information storage unit 112. Return to upper process.

  Next, the operation of the terminal device 12 will be described. The terminal reception unit 121 of the terminal device 12 receives a user identifier. Then, the terminal transmission unit 122 transmits the user identifier received by the terminal reception unit 121 to the recommendation device 11. Further, the terminal receiving unit 123 receives all or part of the product information from the recommendation device 11. And the terminal output part 124 outputs all or one part of the merchandise information which the terminal receiver 123 received.

  Next, the operation of the browsed product management server 13 will be described. The browsing product transmission instruction receiving unit 132 configuring the browsing product management server 13 receives a browsing product information transmission instruction from the recommendation device 11 or the user. Then, the browse product information transmission unit 133 reads the browse product information corresponding to the transmission instruction from the browse product information storage unit 131 and transmits the read product information to the recommendation device 11.

  Next, the operation of the purchase history management server 14 will be described. The purchase history transmission instruction reception unit 142 constituting the purchase history management server 14 receives an instruction to transmit purchase history information from the recommendation device 11 or the user. Then, the purchase history information transmission unit 143 reads the purchase history information corresponding to the transmission instruction from the purchase history information storage unit 141 and transmits it to the recommendation device 11.

  Hereinafter, a specific operation of the recommendation system 1 in the present embodiment will be described. A conceptual diagram of the recommendation system 1 is shown in FIG.

  Now, the user management information storage unit 111 holds the user purchase history information management table shown in FIG. The user purchase history information management table stores one or more records having “user ID”, “user attribute”, and “purchase history information”. Here, “user ID” is a user identifier. The “user attribute” is so-called personal information, and includes “name”, “age”, “sex”, “address”, and the like. The “address” may be a complete address, only a prefecture, or only a prefecture and a municipality. The “purchase history information” includes “card number”, “amount”, “color”, “product name”, “product code”, “product type”, and “use date”. “Product name” is the name of a product or service. “Product type” is the type of product or service. “Use date” is the date when the credit card is used. Furthermore, at the initial stage, the user purchase history information management table may not include “purchase history information” of each user.

  Further, the user management information storage unit 111 holds a user browsing product information management table shown in FIGS. 6 and 7. The user browsing product information management table stores one or more records having “user ID”, “user attribute”, and “browsing product information”. The “user attribute” is so-called personal information. Further, “browsing product information” in FIG. 6 is omitted, and a specific example of data is the table in FIG.

  FIG. 7 is a table storing browsing product information, and can be said to be a browsing product information management table. The browsed product information management table includes “user ID”, “viewed product information”, and “purchase flag”. The “browsing product information” includes “date”, “time”, “product code”, “product attribute”, and “looked information”. “Date” is the date when a product, a brochure of the product, etc. were viewed. “Time” is the time when a product, a pamphlet of the product, etc. are viewed. “Product code” is a product identifier for identifying a product. The “product attribute” includes “price”, “brand”, “genre”, “item”, “color”, “material”, and “gender”. “Genre” or “item” or “genre” and “item” may be considered to be the same as the product type indicating the type of product. “Gender” is an example of the subject. Further, “looked information” is an example of action history information, and is information related to a user that can be acquired when browsing a product or a poster of the product. The “looked information” includes “gaze product information”, “user product related information”, “biological information”, and “facial expression information”. “Gaze product information” is information indicating a user's recognition or interest in a product or the like, and has a cumulative time and number of times that the user has looked at the product or the like. The “user product related information” is information indicating the user's interest in the product and the like. Here, the user product related information includes information indicating the degree to which the user has brought the product close and information indicating the degree to which the user has picked up the product. . Here, the information indicating the degree of closeness of the product has an accumulated time and the number of times that the user has brought the product close to a distance within a threshold. Here, the information indicating the degree of picking up the product has the cumulative time and number of times that the user picked up the product. “Biometric information” is information indicating the degree of surprise or excitement of the user, and here, has accumulated time and number of times when blood pressure or pulse is detected to rise above a threshold value. In addition, “facial expression information” here means “information about eyebrows being raised”, “information about opening of pupils”, “information about directing eyes to specific areas of products” "Information about things" and "information about frowning". “Information about eyebrows being raised” is information indicating the degree of surprise or excitement of the user, and here, the information includes the cumulative time and number of times that the eyebrows have been raised. “Information relating to the opening of the pupil” is information indicating the user's interest or degree of interest, and here, it includes the accumulated time and the number of times that the pupil has detected an opening movement that exceeds a threshold value. “Information about directing line of sight to a specific area of the product” is information indicating the degree of recognition or interest in the product, etc. Here, the accumulated time and number of times that the line of sight was directed to the specific area of the product Have. The “information about having spited” is information indicating the degree of surprise or excitement of the user, and here, has accumulated time and number of times of spitting. Further, “information regarding frowning” is information indicating the degree of disappointment of the user, and here, has accumulated time and number of times of frowning.

  The “preference level” included in the “browsing product information” is information indicating the degree of preference of the user with respect to the product or the like, and is a score calculated using “looking information”. The “preference level” is a value calculated by an arithmetic expression using the accumulated time or / and the number of times that the gaze product information, the user product related information, the biological information, and the facial expression information have as parameters. The larger the “preference level”, the more the product is preferred by the user. Further, the arithmetic expression is a decreasing function having the accumulated time and the number of times corresponding to “information concerning frowning” as parameters. In addition, the arithmetic expressions are “staring product information”, “user product related information”, “biological information”, “information about eyebrows being raised”, “information about opening of pupils”, “line of sight to specific areas of products” It is an increasing function using the accumulated time and the number of times corresponding to “information about having been directed” and “information about having saliva” as parameters.

  Then, it is assumed that a calculation means (not shown) calculates the preference degree in FIG. 7 using a previously stored calculation expression.

  Further, the “purchased flag” in FIG. 7 is information acquired from the purchase history information described in the first embodiment. That is, the product with “purchased flag = 1” has already been purchased by the user, and the product with “purchased flag = 0” has not been purchased by the user. A technique for determining whether one product has been purchased from the purchase history information is a known technique.

  The product information storage unit 112 holds a product information management table shown in FIG. The product information management table holds one or more records having “ID”, “product code”, “attribute information”, “photograph”, and the like. The “attribute information” includes “brand”, “item”, “amount”, “target person”, “color”, and the like. Here, the ID is a user identifier.

  In this situation, for example, it is assumed that the user “Taro Yamada” is an instruction having an ID “30001” and has input an access instruction to access a certain website to his / her terminal device 12.

  Then, the terminal reception unit 121 of the terminal device 12 receives an access command having the ID “30001”. Then, the terminal transmission unit 122 transmits an access command having the ID “30001” to the recommendation device 11.

  Next, the receiving unit 113 of the recommendation device 11 receives an access command having the ID “30001” from the terminal device 12.

  Next, the product information acquisition unit 114 acquires the ID “30001” from the received access command.

  Next, using the ID “30001”, the browsed product information acquisition unit 118 receives one or more browsed product information of the user identified by the ID “30001” from the browsed product management server 13. The received one or more browsed product information is the browsed product information of FIG.

  Next, the product information acquisition unit 114 uses the ID “30001” to receive one or more purchase history information of the user identified by the ID “30001” from the purchase history management server 14. The received one or more purchase history information is purchase history information paired with the ID “30001” in FIG.

  Next, the merchandise information acquisition unit 114 acquires personal information paired with the ID “30001” from the user purchase history information management table of FIG.

  Next, the product information acquisition unit 114 uses the acquired one or more browsed product information, the one or more purchase history information, and the personal information, for example, as described below, for all or one of the one or more product information. Get a department.

  That is, first, the product information acquisition unit 114 acquires preference information using, for example, the acquired one or more browsed product information and the one or more purchase history information. Here, the product information acquisition unit 114 has one or more attribute values (here, “genre”, “here”) of products whose “preference level” included in one or more browsed product information is greater than or equal to a threshold value (here, “100” or more). Item ”) and a product code for identifying a product whose“ preference level ”is equal to or greater than a threshold value (here,“ 40 ”or greater) are acquired as preference information. Further, the product information acquisition unit 114 appears as an attribute value of “color” included in one or more purchase history information, and the “preference level” included in one or more browsed product information is equal to or greater than a threshold (here, “100”). The attribute value “apricot” that appears as the “color” attribute value of the product is acquired.

  That is, the merchandise information acquisition unit 114 has preference information “((genre = sports) AND (item = parker)), ((genre = sports) AND (item = polo shirt)), merchandise code = 100001 and product code = 100005, product code = 100009, product code = 100012, color = apricot ”.

  Next, the product information acquisition unit 114 acquires exclusion information using, for example, the acquired one or more browsed product information and the one or more purchase history information. Here, the product information acquisition unit 114 has one or more attribute values (in this case, “genre”, “here”) of “product” whose “preference level” included in one or more browsed product information is less than a threshold (here, less than “0”). Item "" color ") and" preference "are items of products less than a threshold (here, less than" -10 ") and have been purchased within the last year from one or more purchase history information The product type (= item) is acquired as exclusion information. Furthermore, it is assumed that the product information acquisition unit 114 acquires, as exclusion information, products that have been purchased within the last month from one or more purchase history information.

  In other words, the merchandise information acquisition unit 114 excludes the exclusion information “((genre = crime system) AND (item = jacket) AND (color = olive green)), ((genre = high-end brand system) AND (item = jacket) AND ( Color = blue purple)), item = jacket, product code = 10052 ”.

  Next, the product information acquisition unit 114 forms a search formula for searching for product information using one or more types of information among the acquired personal information, the acquired preference information, and the acquired exclusion information. Here, the product information acquisition unit 114 is, for example, a product having an attribute value that matches the acquired personal information, a product having an attribute value that matches the acquired preference information, and an attribute that matches the acquired exclusion information. Construct a search expression that acquires products that do not have a value. In addition, the product information acquisition unit 114 is, for example, a product that has an attribute value that matches the acquired personal information, a product that has an attribute value that matches the acquired preference information, and a product that does not match the acquired exclusion information. Configure the search expression to be acquired. In addition, the product information acquisition unit 114 is, for example, a product having an attribute value that matches the acquired personal information, a product that matches the acquired preference information, and a product that does not have an attribute value that matches the acquired exclusion information Construct a search expression that retrieves The product information acquisition unit 114 is, for example, a product having an attribute value that matches the acquired personal information, a product that matches the acquired preference information, and a search expression that acquires a product that does not match the acquired exclusion information. Configure.

  For example, the merchandise information acquisition unit 114 searches the search expression ““ (subject = men's) AND (genre = sports) AND (item = parker) AND (gender = men's) ”OR“ (subject = men's) AND (genre = (Sports) AND (Item = Polo shirt)] OR "(Target = Men's) AND (Color = Apricot)" OR "(Product code = 100001)" OR "(Product code = 100005)" OR "(Product code = 100009) "OR" (product code = 100012) "NOT" (genre = Kirikaji system) AND (item = jacket) AND (color = olive green) "NOT" (genre = luxury brand system) AND (item = jacket) AND (Color = blue purple) "NOT" item = jacket "NOT “(Product code = 10052)” is configured.

  Next, the product information acquisition unit 114 executes the above-described retrieval formula, and selects one or more products from two or more products indicated by the two or more product information included in the product information management table.

  Next, the product information acquisition unit 114 determines a product to be recommended from one or more selected products. Here, the merchandise information acquisition unit 114 executes the above search formula, and determines the merchandise first hit (the merchandise in the record of “ID = 1” in the merchandise information management table of FIG. 8) as the recommended merchandise.

  Next, the product information acquisition unit 114 acquires the product information of the product of the selected record of “ID = 1” from the product information management table of FIG.

  Next, the recommendation unit 115 reads a web page corresponding to the access command from a web page storage unit (not shown). And the recommendation part 115 adds the acquired merchandise information to the predetermined advertisement area | region of the read web page, and comprises the web page output. It is needless to say that the recommendation unit 115 may constitute a web page including information other than the acquired product information. For example, the recommendation unit 115 may configure a web page that also includes information included in the browsed product information (for example, information such as position information and the number of times the user has viewed the product). For example, the recommendation unit 115 may configure a web page including information indicating whether or not the product corresponding to the product information is a product stared by the user. In addition, for example, the recommendation unit 115 includes a product page of product information that the user actually viewed in a real store in a format that contrasts or competes with product information on the net, and configures the web page. Also good.

  Next, the recommendation unit 115 transmits a web page including product information of the acquired record of “ID = 1” to the terminal device 12.

  Next, the terminal receiving unit 123 of the terminal device 12 receives a web page including product information from the recommendation device 11. And the terminal output part 124 outputs the web page which the terminal receiving part 123 received. An example of such output is shown in FIG.

  Here, in addition to the product information, the terminal output unit 124 may output position information, the number of times the user viewed the product, and the like included in the browsed product information. The terminal output unit 124 may also output information indicating whether the product is a product stared by the user. Further, the terminal output unit 124 may output a product that the user actually viewed at a real store in a format that is compared with or opposed to product information on the network. By outputting in this way, it is expected that the purchase opportunity of the product viewed in a real store can be enhanced while browsing the product information on the net.

  As described above, according to the present embodiment, it is possible to recommend an appropriate product or service using the purchase history information and the browsed product information. More specifically, an appropriate product or service can be recommended by using information indicating the result of conscious behavior of the user and information indicating unconscious emotional movement. Note that the information indicating the result of the user's conscious behavior is purchase history information, and the information indicating the unconscious emotional movement is browsing product information.

  Note that the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. In addition, the software which implement | achieves the recommendation apparatus 11 in this Embodiment is the following programs. That is, in this program, the computer-accessible recording medium is a user identifier for identifying the user, one or more purchase history information that is information related to the purchase history of the user's product, and information related to the product viewed by the user. A user management information storage unit that can store one or more user management information having one or more browsed product information, and information related to a product, and can store two or more product information having one or more attribute information of the product. A product information storage unit, a computer receiving a user identifier from a terminal device, one or more purchase history information paired with the user identifier received by the receiver, and one or more browsed product information And a product information acquisition unit that acquires all or part of one or more product information from the product information storage unit, and one or more items acquired by the product information acquisition unit All or part of the goods information, a program for functioning as a recommendation unit that transmits to the terminal device.

  In the above program, it is preferable that the browsed product information includes position information indicating a position where the user views the product.

  In the above program, it is preferable that the browsed product information includes gaze product information that is information related to a product stared by the user and non-gaze product information that is information related to a product that the user has not stared at.

  In the above program, it is preferable that the browsed product information includes user product related information which is information indicating a physical positional relationship between the user and the product.

  In the above program, it is preferable that the browsed product information includes biometric information of the user while the user is viewing the product.

  In the above program, it is preferable that the browsed product information includes facial expression information that is information related to the movement of the surface of the user while the user is viewing the product.

  FIG. 10 shows the external appearance of a computer that executes the programs described in this specification to realize the recommendation systems of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 10 is an overview diagram of the computer system 300, and FIG. 11 is a block diagram of the system 300.

  In FIG. 10, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

  In FIG. 11, a computer 301 includes an MPU 3013, a bus 3014, a ROM 3015, a RAM 3016, and a hard disk 3017 in addition to the CD-ROM drive 3012. The bus 3014 is connected to the MPU 3013 and the CD-ROM drive 3012. The ROM 3015 stores a program such as a bootup program. The RAM 3016 is connected to the MPU 3013 and temporarily stores application program instructions and provides a temporary storage space. The hard disk 3017 is for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card that provides connection to a LAN.

  A program that causes the computer system 300 to execute the functions of the recommendation system according to the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 at the time of execution. The program may be loaded directly from the CD-ROM 3101 or the network.

  The program does not necessarily include an operating system or a third-party program that causes the computer 301 to execute the functions of the recommendation system according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 300 operates is well known and will not be described in detail.

  In the above program, in the step of transmitting information, the step of receiving information, etc., processing performed by hardware, for example, processing performed by a modem or an interface card in the transmitting step (only performed by hardware). Not included).

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, it goes without saying that two or more communication units existing in one apparatus may be physically realized by one medium.

  In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the recommendation system according to the present invention has an effect that the recommendation of an appropriate product or service can be performed using purchase history information and browsing product information, and is useful as a recommendation system or the like. .

DESCRIPTION OF SYMBOLS 1 Recommendation system 11 Recommendation apparatus 12 Terminal device 13 Browsing merchandise management server 14 Purchase history management server 111 User management information storage part 112 Merchandise information storage part 113 Receiving part 114 Commodity information acquisition part 115 Recommendation part 116 Purchase history information acquisition part 117 Purchase history Information storage unit 118 Browsing product information acquisition unit 119 Browsing product information storage unit 121 Terminal reception unit 122 Terminal transmission unit 123 Terminal reception unit 124 Terminal output unit 131 Browsing product information storage unit 132 Browsing product transmission instruction reception unit 133 Browsing product information transmission unit 141 Purchase history information storage unit 142 Purchase history transmission instruction reception unit 143 Purchase history information transmission unit

Claims (12)

One or more user management information having a user identifier for identifying a user, one or more purchase history information that is information related to a user's product purchase history, and one or more browsed product information that is information related to a product viewed by the user A user management information storage unit capable of storing
A product information storage unit that can store two or more pieces of product information that is information about the product and has one or more pieces of attribute information of the product;
A receiving unit for receiving a user identifier from a terminal device;
A product that acquires all or part of one or more pieces of product information from the product information storage unit using one or more purchase history information and one or more browsed product information paired with the user identifier received by the receiving unit An information acquisition unit;
A recommendation device comprising: a recommendation unit that transmits all or part of one or more pieces of product information acquired by the product information acquisition unit to the terminal device. The browsing product information is:
The recommendation device according to claim 1, wherein the recommendation device includes position information indicating a position where the user views the product. The browsing product information is:
The recommendation device according to claim 1, wherein the recommendation device includes gaze product information that is information related to a product stared by a user and non-gaze product information that is information related to a product that the user has not stared at. The browsing product information is:
The recommendation apparatus as described in any one of Claims 1-3 containing the user goods related information which is the information which shows the physical positional relationship of a user and goods. The browsing product information is:
The recommendation apparatus as described in any one of Claims 1-4 containing a user's biometric information while a user is looking at goods. The browsing product information is:
The recommendation apparatus as described in any one of Claims 1-5 including the facial expression information which is the information regarding the motion of the user's surface while a user is looking at goods. The recommendation part is:
The whole or part of one or more product information acquired by the product information acquisition unit is transmitted to the terminal device so as to be output on a web page of an online shopping site. The recommended device described. The product information acquisition unit
Advertisement of one or more products included in one or more product information from the product information storage unit using one or more purchase history information and one or more browsed product information paired with the user identifier received by the receiving unit Get
The recommendation part is:
The recommendation device according to any one of claims 1 to 7, wherein an advertisement for one or more products acquired by the product information acquisition unit is transmitted to the terminal device. The product information acquisition unit
Using one or more purchase history information paired with the user identifier received by the receiving unit and one or more browsed product information, an attribute value of a product included in the one or more product information is acquired from the product information storage unit. ,
The recommendation part is:
The recommendation apparatus as described in any one of Claims 1-6 which transmits the attribute value of the goods which the said goods information acquisition part acquired to the said terminal device. The purchase history information is
The recommendation device according to any one of claims 1 to 9, wherein the recommendation device is information related to a product or service purchased by a user using a credit card. The recording medium is
One or more user management information having a user identifier for identifying a user, one or more purchase history information that is information related to a user's product purchase history, and one or more browsed product information that is information related to a product viewed by the user A user management information storage unit capable of storing
A product information storage unit capable of storing two or more pieces of product information that is information about the product and has one or more attribute information of the product,
A recommendation method realized by a reception unit, a product information acquisition unit, and a recommendation unit,
The receiving unit receives a user identifier from a terminal device; and
The product information acquisition unit uses the one or more purchase history information and the one or more browsed product information to be paired with the user identifier received in the receiving step, and stores one or more product information from the product information storage unit. A product information acquisition step for acquiring all or part of the information;
A recommendation method comprising: a recommendation step in which the recommendation unit transmits all or part of one or more pieces of product information acquired in the product information acquisition step to the terminal device. Computer-accessible recording media
One or more user management information having a user identifier for identifying a user, one or more purchase history information that is information related to a user's product purchase history, and one or more browsed product information that is information related to a product viewed by the user A user management information storage unit capable of storing
A product information storage unit capable of storing two or more pieces of product information that is information about the product and has one or more attribute information of the product,
Computer
A receiving unit for receiving a user identifier from a terminal device;
A product that acquires all or part of one or more pieces of product information from the product information storage unit using one or more purchase history information and one or more browsed product information paired with the user identifier received by the receiving unit An information acquisition unit;
A program for causing all or part of one or more pieces of product information acquired by the product information acquisition unit to function as a recommendation unit that transmits to the terminal device.