JP2016076047A - Merchandise recommendation system, merchandise recommendation method, and program for merchandise recommendation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To recommend merchandise from a purchase behavior including the actual moving route of a user.SOLUTION: The merchandise recommendation system includes a merchandise database 250 communicably connected to a user terminal 10 for allowing a storage part to store merchandise data. A merchandise recommendation server 200 for recommending the merchandise on the basis of the behavior history of the user terminal acquires the moving route of the user terminal 10, and specifies related merchandise related to the acquired moving route of the user terminal 10, and specifies recommendation merchandise to be recommended to the user terminal 10 from the merchandise database on the basis of the specified related merchandise, and transmits the information of the specified recommendation merchandise to the user terminal 10.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a product recommendation system, a product recommendation method, and a product recommendation system program for recommending a product based on an action history of a user terminal.

  In recent years, with the development of wireless technology, it has become possible to acquire terminal position information more precisely. In particular, a terminal capable of specifying a position in units of several meters of error while using a short-range wireless communication technique and devising power saving is generally popular.

  In such a terminal, for example, in a store displaying merchandise, by effectively arranging sensors, it is possible to accurately identify the position in units of shelves, that is, to accurately acquire the movement route and residence time. .

  Incidentally, in EC sites, it is widely practiced to recommend products based on user purchase behavior. As an example, collaborative filtering using information that you bought or not bought a product is well known as an algorithm, but based on the movement from the product page to the product page, the browsing time of a product page, etc. There was a demand to increase the information to be used and to make recommendations with higher accuracy.

  In response to such a problem, on the EC site, a product recommendation device that recommends to the user a product that the user wants to buy and that the service provider wants to show has been clarified.

JP 2012-150563 A

  According to Patent Literature 1, a user's interest in the product is calculated from purchase information, product information that the service provider wants to promote sales, setting parameters are acquired, and for all combinations of the product and the user, Whether the user has purchased the product, the degree of interest, the sales promotion product information, and the setting parameter are used to calculate a weight parameter, and given the user identifier, The purchase information is used to acquire only the items that have not been purchased by the user, and for the user's unpurchased products, the user's unpurchased items are obtained using the degree of interest, sales promotion product information, and weight parameters. A product recommendation device that calculates a recommendation score for each product and selects identifiers of the top N products in the recommendation score as a recommended product is disclosed.

  However, since the method disclosed in Patent Document 1 mainly uses web access history as an information source, there is a limitation that information that can be used for recommendation is limited to actions on the Internet.

  Therefore, the inventor of the present invention can also convert the purchase behavior in the real world into the same data as the purchase behavior on the Internet based on the movement route of the terminal. We focused on the fact that recommendations can be made with higher accuracy than when using only purchasing behavior.

  In view of these problems, the present invention specifies a related product related to the purchase behavior based on the purchase behavior composed of the movement route of the user terminal, the residence time, the purchase history of the product, etc. An object is to provide a product recommendation system, a product recommendation method, and a product recommendation system program for recommending a product to a user terminal from purchase behavior.

  The present invention provides the following solutions.

An invention according to a first feature is a product recommendation system that includes a product database that is communicably connected to a user terminal, stores product data in a storage unit, and recommends products based on an action history of the user terminal. And
A travel route acquisition means for acquiring a travel route of the user terminal;
Related product specifying means for specifying related products related to the travel route of the acquired user terminal;
Based on the identified related products, recommended product specifying means for specifying recommended products recommended for the user terminal from the product database;
Product information transmitting means for transmitting the specified recommended product information to the user terminal;
A product recommendation system is provided.

  According to the first aspect of the invention, a product recommendation system that includes a product database that is communicably connected to a user terminal, stores product data in a storage unit, and recommends a product based on an action history of the user terminal. Acquires the travel route of the user terminal, identifies related products related to the travel route of the acquired user terminal, and recommends the user terminal from the product database based on the identified related products. A recommended product is specified, and information on the specified recommended product is transmitted to the user terminal.

  The invention according to the first feature is the category of the product recommendation system, but the same action and effect are exhibited in the category of the product recommendation method and the product recommendation system program.

The invention according to the second feature comprises display goods displayed around the movement route of the user terminal and display goods acquisition means for acquiring the display position thereof,
In the related product specifying means, the display product located in a predetermined range calculated using at least one of the distance from the moving route or the moving direction is specified as the related product. Provided is a product recommendation system which is an invention relating to features.

  According to the second aspect of the invention, the product recommendation system according to the first aspect of the invention acquires the displayed product displayed around the movement route of the user terminal and the display position thereof, and specifies the related product identification In the means, the displayed product located in a predetermined range calculated using at least one of the distance from the moving route or the moving direction is specified as the related product.

According to a third aspect of the invention, in the travel route acquisition unit, the travel route of the user terminal is acquired including the time spent at each point,
Product recommendation according to the first or second aspect of the invention characterized in that, in the recommended product specifying means, the weight of the related product related to each point is calculated based on the time spent at each point. Provide a system.

  According to the third aspect of the invention, the product recommendation system according to the first or second aspect of the invention is characterized in that, in the movement route acquisition unit, the time spent at each point on the movement route of the user terminal is The recommended product specifying means calculates the weight of related products related to each point based on the time spent at each point.

The invention according to a fourth aspect includes a coupon transmission means for transmitting a coupon to the user terminal;
Coupon use history acquisition means for acquiring whether or not the user terminal has used the transmitted coupon as purchase behavior;
A product recommendation system according to any one of the first to third aspects, wherein the recommended product specifying means uses a product related to the acquired coupon usage history as the related product. provide.

  According to the fourth aspect of the invention, the product recommendation system according to any one of the first to third aspects of the invention transmits a coupon to the user terminal, and the user terminal receives the transmitted coupon. Whether or not it has been used is acquired as purchase behavior, and the recommended product specifying means uses a product related to the product related to the acquired coupon usage history as the related product.

  The invention according to a fifth feature is that, when the coupon usage history acquisition means transmits a coupon to the user terminal, the coupon usage history acquisition means acquires whether or not the user terminal has received the coupon as a part of the coupon usage history. A product recommendation system according to a fourth feature is provided.

  According to the invention relating to the fifth feature, in the product recommendation system according to the fourth feature, whether or not the user terminal has received the coupon when the coupon usage history acquisition means transmits the coupon to the user terminal. Is acquired as a part of the coupon use history.

The invention according to a sixth aspect is implemented by a product recommendation system that includes a product database that is communicably connected to a user terminal, stores product data in a storage unit, and recommends products based on an action history of the user terminal. Product recommendation method,
Obtaining a movement route of the user terminal;
Identifying related products related to the travel route of the acquired user terminal;
Identifying recommended products to be recommended to the user terminal from the product database based on the identified related products;
Transmitting the specified recommended product information to the user terminal;
A product recommendation method characterized by comprising:

An invention according to a seventh feature includes a product database that is communicably connected to a user terminal, stores a product data in a storage unit, and recommends a product based on an action history of the user terminal.
Obtaining a movement route of the user terminal;
Identifying a related product related to the travel route of the acquired user terminal;
Identifying recommended products to be recommended to the user terminal from the product database based on the identified related products;
Transmitting the specified recommended product information to the user terminal;
A product recommendation system program characterized in that is executed.

  According to the present invention, on the basis of the purchase behavior composed of the movement route of the user terminal, the residence time, the purchase history of the product, etc., the related product related to the purchase behavior is specified, and the user is determined from the related product and the purchase behavior. It is possible to provide a product recommendation system for recommending products to a terminal, a product recommendation method, and a product recommendation system program.

FIG. 1 is a diagram for explaining an outline of the product recommendation system 1. FIG. 2 is an overall configuration diagram of the product recommendation system 1. FIG. 3 is a functional block diagram of the user terminal 10 and the product recommendation server 200. FIG. 4 is a flowchart showing a product recommendation process executed by the user terminal 10 and the product recommendation server 200. FIG. 5 is a flowchart showing recommended product specifying processing executed by the product recommendation server 200. FIG. 6 is an example of a user's travel route represented on a store diagram. FIG. 7 is an example of the movement path of the user represented on the store diagram in a state where the residence time is visualized.

  Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings. This is merely an example, and the technical scope of the present invention is not limited to this.

[Outline of Product Recommendation System 1]
FIG. 1 is a diagram for explaining an outline of a product recommendation system 1 which is a preferred embodiment of the present invention. Based on this FIG. 1, the outline | summary of the goods recommendation system 1 is demonstrated.

  In the product recommendation system 1, first, the user moves in a specific area such as a store while holding the user terminal 10, and communicates with the beacon 4 installed in the area (step S01). A plurality of beacons 4 are installed in the area, and each measures the distance from the user terminal 10. The user terminal 10 can identify the position of the user terminal 10 in the two-dimensional space by communicating with two or more beacons 4, and can further improve the accuracy by increasing the number of beacons 4. It is.

  By specifying the position in the time series as described above, the user terminal 10 can acquire the relationship between the position and time, that is, the movement route as data (step S02). FIG. 1 shows a schematic diagram in which a movement route is overlapped with a dotted line on a schematic diagram of an actual store. Further, since the position information is time-series data, the residence time at each point can be taken at the same time.

  By the way, the product recommendation server 200 can transmit a coupon that can be used when purchasing a product to the user terminal 10 (step S03). Here, the coupon not only promotes the purchase behavior of the user, but also has an advantage that the purchase behavior of the user terminal 10 can be referred to by referring to the use history. In addition, depending on circumstances, not only the determination of whether or not to use a coupon, but also the behavior of receiving or not receiving a coupon can be used as an index for measuring the degree of interest.

  After performing the action as described above, the user terminal 10 transmits the movement route and the purchase action to the product recommendation server 200 (step S04). Although it is assumed that the purchase behavior is mainly acquired as a coupon usage history, it does not prevent the purchase behavior from being acquired by another method. Note that the purchasing behavior here refers to information such as whether or not a product has been purchased, but depending on the context, it may include all of a series of purchasing-related behaviors, including travel routes and residence times at the sales floor.

  When the product recommendation server 200 acquires the travel route and the purchase behavior, the product recommendation server 200 acquires the displayed product information displayed on the travel route from the product database 250 (step S05). Here, the display merchandise information includes the merchandise information of each merchandise and the position information of the display place. The display product information acquisition source is not limited to the product database 250.

  The product recommendation server 200 specifies related products based on the movement route and the display product information, and specifies recommended products from the related products. Examples of recommendations include products similar to related products, recommendations, recommendations by collaborative filtering, continuous recommendations of related products based on product characteristics, and the like. Here, an existing recommendation algorithm may be used for this recommendation, and the gist of the present invention is to use actual purchase behavior for recommendation.

  When the product recommendation server 200 specifies the recommended product, the product information of the recommended product is read from the product database 250 (step S06) and transmitted to the user terminal 10 (step S07). Here, the product information to be transmitted may have a purchase link that can be directly made online, and the product recommendation server 200 itself may be a part of the EC site. The above is the outline of the product recommendation system 1.

[System configuration of product recommendation system 1]
FIG. 2 is a system configuration diagram of the product recommendation system 1 which is a preferred embodiment of the present invention. The product recommendation system 1 includes a public line network 3 (such as the Internet network and a mobile communication network), a user terminal 10, a product recommendation server 200, and a product database 250.

  The user terminal 10 is communicably connected to the product recommendation server 200 via the public line network 3. The communication in the product recommendation system 1 may be wireless communication or wired communication. In order for the user terminal 10 to connect to the public line network 3, communication may be possible via a network device such as a router.

  The user terminal 10 may be a general information terminal used by a user, and is an information device or an electrical appliance having functions to be described later. The user terminal 10 may be, for example, a white appliance such as a refrigerator, a washing machine, a network device such as a mobile phone, a smartphone, a composite printer, a television, a router or a gateway, a computer, a telephone, a network It may be a general information appliance such as a book terminal, a slate terminal, an electronic book terminal, an electronic dictionary terminal, a portable music player, and a portable content playback / recording player.

  The product recommendation server 200 may be a general server having a product database 250 in a storage unit and performing a product recommendation process on the user terminal 10 and having a function to be described later.

[Description of each function]
FIG. 3 is a diagram illustrating the functional blocks of the user terminal 10 and the product recommendation server 200 and the relationship between the functions.

  The user terminal 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like as the control unit 11, and the communication unit 12 is, for example, WiFi (Wireless) compliant with IEEE 802.11. A device compatible with Fidelity or a wireless device that can communicate via a mobile communication network is included (may be a wired LAN connection).

  In the user terminal 10, when the control unit 11 reads a predetermined program, the coupon reception module 13, the movement route acquisition / transmission module 14, the coupon usage history transmission module 15, and the product information reception module cooperate with the communication unit 12. 16 is realized.

  Similarly, the product recommendation server 200 includes a CPU, a RAM, a ROM, and the like as the control unit 201, and a WiFi compatible device compliant with, for example, IEEE 802.11 (may be wired) as the communication unit 202. In addition, the product recommendation server 200 includes a data storage unit such as a hard disk or a semiconductor memory as the storage unit 203. The product recommendation server 200 includes a product database 250 in the storage unit 203.

  In the product recommendation server 200, the control unit 201 reads a predetermined program, so that the movement route acquisition module 204, the product information transmission module 205, the display product acquisition module 206, the coupon transmission module 207, in cooperation with the communication unit 202, A coupon usage history acquisition module 208 is realized. In the product recommendation server 200, the control unit 201 reads a predetermined program, thereby realizing the related product specifying module 209 and the recommended product specifying module 210 in cooperation with the storage unit 203.

[Product recommendation processing]
FIG. 4 is a flowchart of product recommendation processing executed by the user terminal 10 and the product recommendation server 200. The processing performed by the module of each device described above will be described together with this processing.

  First, the coupon transmission module 207 of the product recommendation server 200 transmits a coupon that can be used when purchasing a product to the user terminal 10 (step S11). The coupon reception module 13 of the user terminal 10 receives a coupon (step S12).

  Next, the user terminal 10 moves, and the movement route acquisition / transmission module 14 acquires the movement route (step S13). Here, although acquisition of a movement route can be substituted by GPS or the like, it is assumed that acquisition is performed with accuracy of several meters using a wireless beacon or the like as described above. In addition, the movement route may include a walking direction or a moving direction of the user terminal 10 at each timing at each point acquired by an electronic compass or an acceleration sensor.

  When the user terminal 10 acquires the travel route as time series data, the travel route acquisition / transmission module 14 transmits the travel route to the product recommendation server 200 (step S14). The travel route acquisition module 204 of the product recommendation server 200 receives this (step S15).

  The coupon usage history transmission module 15 of the user terminal 10 transmits the coupon usage history to the product recommendation server 200 (step S16), and the coupon usage history acquisition module 208 of the product recommendation server 200 receives this (step S17). ).

  Here, referring to the coupon usage history is nothing other than referring to the purchase behavior of the user terminal 10. The usage history is not only information that the coupon is used but also information that the coupon is not used.

  On the other hand, in a system that is configured to “receive” before using a coupon, an action of receiving or not receiving can also be used as a judgment material as a user action. This determination of receiving or not receiving may be included as part of the coupon usage history. Note that these usage histories may be acquired from a device other than the user terminal 10, for example, a dedicated server that accumulates the usage histories.

  As described above, after the travel route and purchase behavior are passed to the product recommendation server 200, the product recommendation server 200 executes the recommended product specifying process (step S18).

[Recommended product identification processing]
FIG. 5 is a flowchart of recommended product specifying processing executed by the product recommendation server 200. The processing performed by the module of each device described above will be described together with this processing.

  First, the display product acquisition module 206 of the product recommendation server 200 acquires display products related to the movement route of the user terminal 10 (step S31). Here, the display merchandise information is a combination of merchandise information and position information, and can be obtained from the merchandise database 250 or the service of each store. Further, the position information only needs to be grasped by the user's movement route and relative position, and may be coordinates in the store, an ID of the displayed shelf, or the like.

  Next, the related product specifying module 209 of the product recommendation server 200 specifies related products from the movement route and the displayed product information (step S32). Here, the specification of the related product is conceptually the specification of the product in which the user is interested in a series of purchase behaviors. As specific processing, a product in a certain range from the user's moving route is specified, and in particular, when the direction is available, the product in the direction in which the product is directed is specified. A threshold may be set for the staying time, and the related product may be specified using only a point where the staying time stays above a certain level.

  FIG. 6 is an example of a user's travel route represented on a store diagram. In FIG. 6, the movement route of the user is represented by a dotted line 61, and each shelf has a product name 62 that is easy to understand. In such a case, a point such as a point 63 approaching the shelf on which the product is displayed within a certain distance is searched for, and the product 64 within the range, that is, the product E is specified as the related product.

  Note that the recommended product specifying module 210 of the product recommendation server 200 may calculate a weight used in a recommendation process, which will be described later, from the residence time (step S33). For example, as an example of the weight, the dwell time at the reference position where each product is identified can be used as the weight. By doing so, it is possible to reflect the degree of interest of the user who has been processed in proportion to the residence time in the product.

  FIG. 7 is an example of the movement path of the user represented on the store diagram in a state where the residence time is visualized. In FIG. 7, the movement path of the user is represented by a dotted line 71 as in FIG. 6, but the size of the circle 72 at each point represents the length of the staying time. For example, the largest circle 73 represents that the user has stayed in the store for the longest time. In such a case, the calculation is such that the product 74 that is the closest display product, that is, the product B, is given the greatest weight.

  Further, the related product specifying module 209 may specify a product related to the above-described coupon use history as the related product as the related product (step S34). If there are other products that are accounted for at the same time when the coupon is used, they may be similarly identified as related products.

  From the related products described above, the recommended product specifying module 210 recommends a product (step S35). This is because a recommendation algorithm widely used in EC sites may be applied, and the gist of the present invention is to use actual purchase behavior in a form that can be used for recommendation.

  The above is the procedure of the recommended product identification process. Returning to the product recommendation process, the recommended product specifying module 210 of the product recommendation server 200 reads the product information of the recommended product from the product database 250, and the product information transmission module 205 transmits the product information to the user terminal 10 (step S19).

  The product information receiving module 16 of the user terminal 10 receives product information (step S20). The product information may include a link for directly purchasing the product, and the user terminal 10 can purchase the recommended product as it is (step S21). In addition, the product recommendation server 200 itself may constitute a part of the EC site.

  The above is the procedure of the product recommendation process.

  The means and functions described above are realized by a computer (including a CPU, an information processing apparatus, and various terminals) reading and executing a predetermined program. The program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, CD (CD-ROM, etc.), DVD (DVD-ROM, DVD-RAM, etc.), for example. In this case, the computer reads the program from the recording medium, transfers it to the internal storage device or the external storage device, stores it, and executes it. The program may be recorded in advance in a storage device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and provided from the storage device to a computer via a communication line.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to these embodiment mentioned above. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

  1 product recommendation system, 3 public network, 4 beacons, 10 user terminals, 200 product recommendation server, 250 product database,

Claims (7)

A product recommendation system that is communicably connected to a user terminal, includes a product database that stores product data in a storage unit, and recommends a product based on an action history of the user terminal,
A travel route acquisition means for acquiring a travel route of the user terminal;
Related product specifying means for specifying related products related to the travel route of the acquired user terminal;
Based on the identified related products, recommended product specifying means for specifying recommended products recommended for the user terminal from the product database;
Product information transmitting means for transmitting the specified recommended product information to the user terminal;
A product recommendation system comprising: Display goods displayed around the movement route of the user terminal and display goods acquisition means for acquiring the display position,
The related product specifying means specifies the display product located in a predetermined range calculated using at least one of a distance from the moving route or a moving direction as the related product. Product recommendation system described in 1. In the travel route acquisition means, the travel route of the user terminal is acquired including the time spent at each point,
3. The product recommendation system according to claim 1, wherein the recommended product specifying unit calculates a weight of the related product related to each point based on a time spent at each point. Coupon transmission means for transmitting a coupon to the user terminal;
Coupon use history acquisition means for acquiring whether or not the user terminal has used the transmitted coupon as purchase behavior;
4. The product recommendation system according to claim 1, wherein the recommended product specifying unit uses a product related to the acquired use history of the coupon as the related product.   5. The coupon usage history acquisition unit acquires, as a part of the coupon usage history, whether or not the user terminal has received a coupon when the coupon is transmitted to the user terminal. Product recommendation system. A product recommendation method executed by a product recommendation system that is communicably connected to a user terminal, includes a product database in which product data is stored in a storage unit, and recommends products based on an action history of the user terminal,
Obtaining a movement route of the user terminal;
Identifying related products related to the travel route of the acquired user terminal;
Identifying recommended products to be recommended to the user terminal from the product database based on the identified related products;
Transmitting the specified recommended product information to the user terminal;
A method for recommending products. A product recommendation system that is communicably connected to a user terminal and includes a product database in which product data is stored in a storage unit, and recommends products based on an action history of the user terminal.
Obtaining a movement route of the user terminal;
Identifying a related product related to the travel route of the acquired user terminal;
Identifying recommended products to be recommended to the user terminal from the product database based on the identified related products;
Transmitting the specified recommended product information to the user terminal;
A product recommendation system program characterized in that