JP2015014887A - Commodity information provision system, commodity information provision method, server and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a commodity information provision system capable of contributing to activation of a community by promoting a commodity purchase of a customer in an actual store.SOLUTION: The commodity information provision system supports, for example, a purchase of a commodity in an actual store. The commodity information provision system comprises: a history creation unit for creating purchase action history information on a customer; a preference profile creation unit for creating preference profile information on a customer on the basis of personal profile information and the purchase action history information on the customer; a recommendation creation unit for creating recommendation information to a customer on the basis of the preference profile information; and a notification unit for notifying a customer of the recommendation information.

Description

  Embodiments of the present invention relate to an information providing technique for allowing a consumer to purchase a necessary product at an actual store.

  Since online shopping management sites can centrally manage the purchasing behavior of consumers, the purchase histories and check histories of many people are analyzed to find specific purchase patterns. For example, a recommendation presentation such as “People who bought this product also bought such a product” uses this kind of technology and is known as collaborative filtering.

JP 2002-109382 A JP 2011-145803 A Japanese Patent No. 3484111 Japanese Patent No. 3458635 Japanese Patent No. 4911536

In contrast to online shopping, which means buying and selling products in the virtual world on the Internet, buying and selling at actual stores is called real shopping. Even in real shopping, by analyzing the preferences of each consumer and presenting information that seems to be suitable for each consumer, each consumer purchases appropriate products, which makes life more enjoyable and richer Is expected to be.
An object is to provide a product information providing system, a product information providing method, a server, and a program for supporting a customer's product purchase in an actual store.

  According to the embodiment, the product information providing system supports providing information related to the purchase of the product at the actual store. This product information providing system includes a history creation unit for creating consumer purchase history information, and a preference profile creation for creating consumer preference profile information based on consumer personal profile information and purchase behavior history information. A recommendation creating unit that creates recommendation information for the consumer based on the preference profile information, and a notification unit that notifies the consumer of the recommendation information.

FIG. 1 is a diagram illustrating an example of a product information providing system according to the embodiment. FIG. 2 is a diagram illustrating an example of a relationship between the personal profile 4a, the purchase behavior history 4b, and the preference profile 4c. FIG. 3 is a diagram illustrating an example of the shopping street sensor illustrated in FIG. 1. FIG. 4 is a diagram illustrating an example of the center server according to the embodiment. FIG. 5 is a flowchart showing an example of a processing procedure of the center server 20 shown in FIG. FIG. 6 is a flowchart showing an example of a processing procedure of the center server 20 related to recording of a purchase behavior history of a consumer who is provided with recommendation information.

  FIG. 1 is a diagram illustrating an example of a product information providing system according to the embodiment. This system includes a cloud environment 100 connected to a shopping street 200. The shopping street 200 is a shopping mall, for example, and is an example of a community having a plurality of actual stores.

  The cloud environment 100 includes an analysis engine 400. The analysis engine 400 includes a personal profile 4a, a purchase behavior history 4b, a preference profile creation unit 23d, and a preference profile 4c. Among them, the personal profile 4a is a set of personal profiles (information such as date of birth and address of residence) of each consumer, and is registered in advance in the database under the consumer's voluntary intention.

  The purchase behavior history 4b is a database showing a history of purchase behavior for each consumer. Purchasing behavior is created by analyzing various sensing data. Sensing data includes various sensors (POS cash register, camera (image sensor), store visit sensor, etc.) installed in each of the actual stores in the shopping street 200 or in common areas, and GPS (Global Positioning System) of the mobile terminal 300. Collected from functions or object recognition functions. A group of sensors installed in the shopping street 200 is collectively referred to as a shopping street sensor.

  For example, a point-of-sale system (POS) cash register acquires consumer purchase data. If the image data acquired by the camera (image sensor) is analyzed, people's in-store behavior can be grasped. By using the store visit sensor, it is possible to grasp the customer's store visit performance to each store. If the indoor position of the mobile terminal 300 is specified by using a position sensor such as a GPS or an acceleration sensor, it is possible to grasp the excursion behavior of the consumer. If the smartphone application is used, the operation history data of the product object recognition function can be acquired from the system side.

  In addition, it is necessary to specify an individual for the in-store behavior data acquired by the camera. In such a case, for example, it is possible to grasp personal in-store behavior data by comparing the excursion data tracked up to the cash register with the POS cash register data when the person makes the POS cash register settlement.

  As the store visit sensor, for example, the ultrasonic wave emitted from the speaker in the store is captured by the microphone of the mobile terminal 300, and the store information of the user who owns the mobile terminal 300 is grasped by reading the store information encoded in the ultrasonic wave. Such a technique is already known.

  The preference profile 4c is calculated by the preference profile creation unit 23d based on at least one of the personal profile 4a and the purchase behavior history 4b. The preference profile 4c is a database in which preference scores are associated with items such as individual products, genres, brands, etc., and personal preferences for each consumer are quantified. If there is a deficiency in the preference profile of a certain individual, it is possible to infer the deficiency in the preference profile of that person by using the data acquired from the big data (BigData) in a complementary manner.

  The actual store belonging to the shopping street 200 transmits the product information of the handling product, the recommended product, the special sale / event information, etc. to the cloud environment 100, respectively. These pieces of information (collectively referred to as product information) are stored in the database 600.

  Further, the cloud environment 100 includes a recommendation creation unit 23b. The recommendation creation unit 23 b acquires the preference profile 4 c from the analysis engine 400 and acquires product information from the database 600. The recommendation creating unit 23b further acquires various information such as trend information, trend data, ranking data, and likes from the Internet. Such information can be acquired from, for example, an SNS (Social Networking Service) server.

The recommendation creation unit 23b creates recommendation information based on the acquired information, for example, by analyzing consumer preferences. The recommendation information is information for providing information that seems to be suitable for each consumer in the shopping street 200.
The recommendation information is roughly classified into action-induced recommendation and buying recommendation. The behavior-induced recommendation is a recommendation information that attracts a consumer to the shopping street 200, and is so-called recommendation information that prompts the consumer to purchase a purpose. The buy-around recommendation is to notify the consumer in the shopping street 200 of the product information of the actual store, which is so-called recommendation information that prompts the consumer to make an impulse purchase.

  The recommended information is generated in the form of, for example, HTML (HyperText Markup Language) or XML (eXtended Markup Language) data, converted into IP (Internet Protocol) data, and sent to the mobile terminal 300 via an IP network or the like. The The mobile terminal 300 displays the received data on the browser screen, and thus the recommendation information is notified to the consumer.

  FIG. 2 is a diagram illustrating an example of a relationship between the personal profile 4a, the purchase behavior history 4b, and the preference profile 4c. The personal profile 4a is a personal profile registered by the subscriber to the service in the database, and is registered in the system in a form of answering a questionnaire, for example.

  The personal profile 4a includes questions that are not directly related to individual products, such as family composition and occupation, information about preferences, and the like. The amount of questions to be entered at a time may be within a psychologically acceptable range, and input may be prompted at intervals. Also, if the subscriber's permission is obtained, the registration information in the SNS service or the like may be referred.

  The purchase behavior history 4b is information obtained from a customer's excursion behavior, store visit performance, merchandise object recognition behavior, in-store behavior, or purchase performance collected through the POS cash register system. . These data are sensing data detected by a sensor, and are accumulated in the big data of the cloud environment 100. By analyzing the sensing data, not only product preferences but also shopping behavior patterns can be detected.

  The preference profile 4c can be estimated from each individual profile 4a and purchase behavior history 4b of the subscriber individual (preference profile estimation processing). For example, the cluster to which each person belongs is specified using big data from the subscriber's personal profile and purchase behavior history. The preferences that are not specified can be estimated or interpolated by applying the same preferences of the cluster members. The preference profile 4c shown in FIG. 2 is a product category / product preference score registered in, for example, a five-step evaluation. By scoring only items that have the potential to be purchased, it is possible to reduce the size of the database. The product service is recommended based on the score in the preference profile 4c.

  FIG. 3 is a diagram illustrating an example of the shopping street sensor illustrated in FIG. 1. In FIG. 3, sensors such as a store visit sensor, a POS register, and a security camera (CAM) are installed in each store partitioned by walls (hatched portions). The store visit sensor detects the visit of the person who has the mobile terminal 300 (understands store visit results) and notifies the cloud environment 100 of this.

  The camera acquires image data, and can grasp the in-store behavior of the store visitor by flow line analysis using the image data. For example, if it takes a long time to stay at a specific position, it is understood that the store visitor is interested in the product placed on the shelf at that position. The flow line of the visitor can also be grasped by the GPS / indoor location specifying system (explanation of excursion behavior). By linking store arrangements and excursion behavior histories, it is possible to grasp the state of interest in a specific store. This information is reflected in the purchase behavior history 4b.

  A visitor can be specified based on personal identification information such as a point card, credit information, or the like acquired by a POS register installed in each store. By combining this information with the flow line data, it is possible to grasp the purchased product of the store visitor (purchase record grasp). Knowing the purchase merchandise history using the POS cash register makes it possible to determine a recommendation hit and lead to point processing. The purchase merchandise history is reflected in the purchase behavior history 4b. Depending on the product genre, preference for other products can be obtained from the purchase record.

  Furthermore, if the visitor's mobile terminal 300 has an object recognition function, it is possible to grasp the visitor's product preference based on the history of the focused product (object recognition machine history). The fact that they visited the store is a sign of high interest in the store. Therefore, if this fact can be grasped, this is reflected in the purchase behavior history 4b as high interest.

  In this embodiment, according to the recommendation information, a purchase behavior history of a visitor who has come to the shopping street 200 is grasped by a shopping street sensor, and is recorded in a database as a purchase behavior history 4b. Of course, the purchase behavior history 4b created in this way is also reflected in the preference profile 4c.

  FIG. 4 is a diagram illustrating an example of the center server according to the embodiment. The center server (denoted by reference numeral 20) is provided, for example, in the shopping street 200 and can be managed by the system operator. The center server 20 shown in FIG. 4 includes an interface unit 21, a program memory 22, and a CPU (Central Processing Unit) 23. That is, the center server 20 is a computer that functions when the CPU 23 executes a program stored in the program memory 22.

The interface unit 21 is connected to the cloud environment 100 and is an interface for exchanging various data with the analysis engine 400 (preference profile creation unit 23d, personal profile 4a, purchase behavior history 4b, and preference profile 4c).
The program memory 22 includes a history creation program 22a, a recommendation creation program 22b, a notification program 22c, a preference profile creation program 22d, a calculation program 22e, and an incentive processing program as programs including instructions necessary for the processing functions according to this embodiment. 22f is stored. The history creation program 22a, the recommendation creation program 22b, the notification program 22c, the preference profile creation program 22d, the calculation program 22e, and the incentive processing program 22f can be recorded on a removable medium (recording medium) such as a CD-ROM, It is also possible to download via a communication network such as a network.

  The CPU 23 reads each program from the program memory 22 and performs arithmetic processing by hardware. As its processing functions, a history creation unit 23a, a recommendation creation unit 23b, a notification unit 23c, a preference profile creation unit 23d, a calculation unit 23e, An incentive processing unit 23f is provided.

  The history creation unit 23a creates consumer purchase history information. In particular, the history creation unit 23a creates the purchase behavior history 4b based on at least one of purchase record data, image data, store visit record data, flow line data, and operation history data acquired by a shopping street sensor. .

  The recommendation creation unit 23b creates recommendation information based on the purchase behavior history 4b, the preference profile 4c, and the like. The notification unit 23c transmits the created recommendation information to the consumer's mobile terminal 300, displays the recommendation information on the screen, and notifies the consumer. The preference profile creation unit 23d creates the consumer's preference profile 4c based on at least one of the consumer's personal profile 4a and the purchase behavior history 4b.

  The calculation unit 23e calculates the correlation between the recommendation information notified to the consumer and the purchase behavior history 4b of the consumer. The incentive processing unit 23f gives an incentive according to the calculated correlation to, for example, an administrator of the shopping street 200.

  FIG. 5 is a flowchart showing an example of a processing procedure of the center server 20 shown in FIG. In FIG. 5, the shopping mall sensor transmits sensing data to the cloud environment 100 (step S1). On the other hand, the consumer's mobile terminal 300 transmits application information to the cloud environment 100 as needed (step S2). The application information is, for example, data such as GPS data or operation history data of the object recognition function.

  The center server 20 in the cloud environment 100 receives application information (step S3) and collects sensing data (step S4). The center server 20 analyzes the received information and creates a purchase behavior history 4b (step S5), and creates recommendation information based on the purchase behavior history 4b and the preference profile 4c (step S6). Furthermore, the center server 20 transmits the recommendation information to the mobile terminal 300 (step S7).

The mobile terminal 300 receives the recommendation information (step S8) and displays it on the browser screen of the display (step S9).
FIG. 6 is a flowchart showing an example of a processing procedure of the center server 20 related to recording of a purchase behavior history of a consumer who is provided with recommendation information. After providing the recommendation information to the consumer's mobile terminal 300 by the notification unit 23c, the center server 20 traces the behavior of the consumer who has received the recommendation information (step S11).

  The center server 20 determines the correlation between the recommendation information and the purchase behavior (step S12). For example, after the recommendation information is received by the mobile terminal 300, the recommendation information and the purchase behavior are verified by, for example, verifying the fact that “the customer went to the store within 12 hours and the purchase procedure was performed at the cash register”. Can be determined.

  When it is determined that there is a correlation, the center server 20 transmits the information related to the recommendation information or the product information provider and the purchase behavior history of the consumer associated with the information to the cloud environment 100, and the big data The data, analysis engine 400, or database 600 is stored (step S13).

  As an example, the center server 20 sets a flag indicating that the purchase information sent from the POS cash register system is related to the provision of product information and stores it in the database. For example, the consumer ID acquired from the consumer's mobile terminal 300, the purchased product, and the store identification information are collected in the center server 20, and it is determined whether or not the center server 20 is a purchase within 12 hours. . Based on the result, the center server 20 records a flag indicating that the purchase is based on the product information together with the purchase behavior history.

  As described above, in the embodiment, the product information providing system that manages the purchase information by the consumer based on the consumer preference information (personal profile 4a) regarding the consumer's preference and the purchase behavior history 4b in the consumer's store. Is targeted.

  In the embodiment, by transmitting information (hereinafter collectively referred to as a recommendation) that suggests the purchase of a product in an actual store to the consumer's mobile terminal (smartphone, etc.) 300, the consumer's product purchase is promoted. It can be said that the system according to the embodiment is different from EC (Electric Commerce) targeting the net shop in that the target is not a net shop but a real shop (real shop).

  In the embodiment, purchase of a product has been described as an example. Not only this but the information provision system concerning embodiment also includes providing the service which a consumer desires by transmitting the proposal information for receiving provision of the service (service) in a real store to a consumer.

  In the embodiment, the consumer-induced behavior is also realized in real shopping by pushing the recommendation information to the mobile terminal 300. Specifically, in the real shopping for a plurality of actual stores in the community, a recommended product group or store group is recommended based on a personal preference profile obtained from a purchase history or a personal profile.

  Therefore, according to the embodiment, it is possible to provide a product information providing system that can promote the purchase of products by consumers in actual stores and thereby contribute to the activation of the community.

  Although an embodiment of the present invention has been described, this embodiment is presented as an example and is not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 100 ... Cloud environment, 200 ... Shopping street, 400 ... Analysis engine, 4a ... Personal profile, 4b ... Purchasing action history, 4c ... Preference profile, 300 ... Portable terminal, 600 ... Database, 20 ... Center server, 21 ... Interface part, 22 ... Program memory, 23 ... CPU, 22a ... History creation program, 22b ... Recommendation creation program, 22c ... Notification program, 22d ... Preference profile creation program, 22e ... Calculation program, 22f ... Incentive processing program, 23a ... History creation unit, 23b ... Recommendation creation unit, 23c ... Notification unit, 23d ... Preference profile creation unit, 23e ... Calculation unit, 23f ... Incentive processing unit

Claims (16)

A product information providing system that supports the purchase of products in actual stores,
A history creation unit that creates consumer purchase history information,
A preference profile creating unit that creates the consumer's preference profile information based on the consumer's personal profile information and the purchase behavior history information;
Based on the preference profile information, a recommendation creating unit that creates recommendation information for the consumer;
A product information providing system comprising: a notification unit that notifies the consumer of the recommended information.   The product according to claim 1, wherein the history creation unit creates the purchase behavior history information based on purchase data of the consumer acquired by a POS register installed in the actual store. Information provision system. Further, an image sensor that acquires image data, a store sensor that detects the mobile terminal installed in the actual store and acquires store visitor data of the consumer, specifies the position of the mobile terminal, and moves the consumer A sensor unit including at least one of a position sensor for acquiring line data and an information reading unit for acquiring operation history data of an object recognition function provided in the mobile terminal from the mobile terminal;
The history creation unit creates the purchase behavior history information based on at least one of the image data, the store visit data, the flow line data, and the operation history data, and the purchase record data. The product information providing system according to claim 2, wherein: Furthermore, a calculation unit that calculates the correlation between the notified recommendation information and the purchase behavior history information;
The product information providing system according to claim 1, further comprising: an incentive processing unit that processes an incentive according to the correlation. A product information providing method that supports the purchase of products in a real store,
Create customer purchase history information,
Based on the consumer's personal profile information and the purchase behavior history information, create the consumer's preference profile information,
Based on the preference profile information, create recommendation information for the consumer,
A method for providing product information, wherein the recommendation information is notified to the consumer.   The creation of the purchase behavior history information is characterized in that the purchase behavior history information is created based on purchase data of the consumer acquired by a POS register installed in the actual store. 5. The method for providing product information according to 5.   Creating the purchase behavior history information includes image data acquired by an image sensor, store visit result data of the consumer acquired by a store sensor installed in the actual store and detecting the mobile terminal, Based on the flow line data of the consumer acquired by the position sensor for specifying the position, the operation history data of the object recognition function provided in the portable terminal, and the purchase record data The product information providing method according to claim 6, wherein purchase behavior history information is created. Further, the correlation between the notified recommendation information and the purchase behavior history information is calculated,
6. The product information providing method according to claim 5, wherein an incentive according to the correlation is processed. A server that supports the purchase of products in actual stores,
A history creation unit that creates consumer purchase history information,
A preference profile creating unit that creates the consumer's preference profile information based on the consumer's personal profile information and the purchase behavior history information;
Based on the preference profile information, a recommendation creating unit that creates recommendation information for the consumer;
And a notification unit that notifies the consumer of the recommended information.   The server according to claim 9, wherein the history creation unit creates the purchase behavior history information based on purchase data of the consumer acquired by a POS register installed in the actual store. .   The history creation unit includes image data acquired by an image sensor, store data of the customer acquired by a store sensor that is installed in the actual store and detects the mobile terminal, and a position that specifies the position of the mobile terminal The purchase behavior history information is obtained based on at least one of the flow line data of the consumer acquired by a sensor and the operation history data of the object recognition function provided in the mobile terminal, and the purchase record data. The server according to claim 10, wherein the server is created. Furthermore, a calculation unit that calculates the correlation between the notified recommendation information and the purchase behavior history information;
The server according to claim 9, further comprising an incentive processing unit that processes an incentive according to the correlation. A program executed by a computer for supporting the purchase of goods in a real store, the program
A history creation unit that creates consumer purchase history information,
A preference profile creating unit that creates the consumer's preference profile information based on the consumer's personal profile information and the purchase behavior history information;
Based on the preference profile information, a recommendation creating unit that creates recommendation information for the consumer;
A program that operates as a notification unit that notifies the consumer of the recommendation information.   The program according to claim 13, wherein the history creating unit creates the purchase behavior history information based on purchase data of the consumer acquired by a POS register installed in the actual store. .   The history creation unit includes image data acquired by an image sensor, store data of the customer acquired by a store sensor that is installed in the actual store and detects the mobile terminal, and a position that specifies the position of the mobile terminal The purchase behavior history information is obtained based on at least one of the flow line data of the consumer acquired by a sensor and the operation history data of the object recognition function provided in the mobile terminal, and the purchase record data. 15. The program according to claim 14, wherein the program is created. Further, the computer
A calculation unit for calculating a correlation between the notified recommendation information and the purchase behavior history information;
The program according to claim 13, wherein the program is operated as an incentive processing unit that processes incentives according to the correlation.

Images