WO2019182068A1

WO2019182068A1 - Information processing device, information processing method, and recording medium

Info

Publication number: WO2019182068A1
Application number: PCT/JP2019/011899
Authority: WO
Inventors: 隆義大山
Original assignee: 日本電気株式会社
Priority date: 2018-03-22
Filing date: 2019-03-20
Publication date: 2019-09-26
Also published as: JP2019168817A; JP7054444B2

Abstract

An information processing device according to the present invention is characterized by being provided with: an image capture means for capturing an image of an object being held by a customer in a shop; an extraction means for extracting from the image object information about the object; an estimation means for estimating an attribute of the customer from the object information; and a selection means for selecting an advertisement to be output to an advertisement medium on the basis of the attribute.

Description

Information processing apparatus, information processing method, and recording medium

The present invention relates to an information processing apparatus, an information processing method, and a recording medium.

Patent Document 1 discloses an advertisement distribution support system that improves the rate at which a customer is interested in advertisement information based on the customer's hobbies / preferences and the position / weather / time surrounding the customer.

Japanese Patent Application Laid-Open No. 2005-078497

In the apparatus described in Patent Document 1, it is necessary to store image data on the server in advance from the customer side in order to estimate the customer characteristics. For this reason, it has been impossible to display an appropriate advertisement on the advertising medium for customers who have not yet registered customer information such as customers who have visited the store for the first time.

The present invention has been made in view of the above-described problems, and is an information processing apparatus, an information processing method, and a recording that can output an appropriate advertisement according to the attribute to a customer existing in the vicinity of an advertisement medium The purpose is to provide a medium.

According to one aspect of the present invention, an imaging unit that captures an image of an object owned by a customer at a store, an extraction unit that extracts object information of the object from the image, and an attribute of the customer from the object information. There is provided an information processing apparatus comprising estimation means for estimation and selection means for selecting an advertisement to be output to an advertisement medium based on the attribute.

According to the present invention, it is possible to provide an information processing apparatus, an information processing method, and a recording medium that can output an appropriate advertisement according to the attribute to a customer in the vicinity of the advertising medium.

1 is a schematic diagram illustrating an example of the overall configuration of a POS system to which an information processing apparatus according to a first embodiment of the present invention is applied. It is a block diagram which shows the hardware constitutions of the information processing apparatus which concerns on 1st Embodiment of this invention. It is a flowchart which shows an example of the advertisement output method of the information processing apparatus which concerns on 1st Embodiment of this invention. It is a figure which shows an example of the relationship between the image of the goods imaged in 1st Embodiment of this invention, and the attribute estimated from an image. It is a figure which shows an example of the relationship between the image of the goods imaged in 1st Embodiment of this invention, and the attribute estimated from an image. It is a figure which shows an example of the relationship between the image of the goods imaged in 1st Embodiment of this invention, and the attribute estimated from an image. It is a figure which shows an example of the advertisement output based on the customer's attribute in 1st Embodiment of this invention. It is a figure which shows an example of the advertisement output based on the customer's attribute in 1st Embodiment of this invention. It is a figure which shows an example of the advertisement output based on the customer's attribute in 1st Embodiment of this invention. It is a flowchart which shows an example of the advertisement output method of the information processing apparatus which concerns on 1st Embodiment of this invention. It is a flowchart which shows an example of the advertisement output method of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a figure which shows an example of the image of the goods imaged in 2nd Embodiment of this invention, the purchase tendency of a customer estimated from the image, and an attribute. It is a figure which shows an example of the advertisement output based on the customer's attribute in 2nd Embodiment of this invention. It is the schematic which shows the example of whole structure of the advertisement delivery system with which the information processing apparatus which concerns on 3rd Embodiment of this invention is applied. It is a flowchart which shows an example of the advertisement output method of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure which shows an example of the image of the object imaged in 3rd Embodiment of this invention. It is a figure which shows an example of the advertisement output based on the customer's attribute in 3rd Embodiment of this invention. It is a figure which shows an example of the relationship between the advertisement outside based on the weather outside a store in 4th Embodiment of this invention, and the weather. It is a block diagram which shows the structure of the information processing apparatus in other embodiment of this invention.

[First Embodiment]
FIG. 1 is a schematic diagram showing an example of the overall configuration of a POS system to which an information processing apparatus 10 according to the first embodiment of the present invention is applied. The POS (Point of Sale) system is a computer system installed in a store that sells products. As shown in FIG. 1, the POS system includes an information processing apparatus 10 and a store server 12. The information processing apparatus 10 and the store server 12 are connected to a network 14 that is, for example, a LAN (Local Area Network). Note that the connection method is not limited to wired, and may be connected wirelessly.

The information processing apparatus 10 of the present embodiment is installed with a POS application program having a product sales registration function, an accounting function, a product information registration function, an inventory management function, and the like, and functions as a POS device. The information processing apparatus 10 is used by a store clerk at a checkout counter and executes accounting processing. The number of information processing apparatuses 10 is not limited to one, and can be arbitrarily changed according to the scale of the store.

Also, the information processing apparatus 10 is connected to an advertisement distribution apparatus 16, an imaging apparatus 18, and a peripheral device 20, which are advertisement media. The advertisement distribution device 16 includes a display 16a such as a liquid crystal display, an OLED (Organic Light Emitting Diode) display, an LED (Light Emitting Diode) display, and a speaker 16b. As the advertisement distribution apparatus 16 of this embodiment, a customer display that displays various information such as accounting data on the screen under the control of the information processing apparatus 10 that is a POS apparatus is used. That is, the advertisement distribution device 16 displays data related to advertisements, advertisements, events, and the like (hereinafter referred to as “advertisement data”) on the screen in addition to the accounting data. The advertisement distribution device 16 may be installed separately from the customer display. Further, advertisement data is output from the speaker 16b as necessary.

The store server 12 is, for example, a POS server (store controller) that manages the operation of the POS system by managing information on products sold in stores, collecting sales data, managing sales, managing inventory, and the like. The store server 12 is installed, for example, in a store backyard.

The store server 12 includes a business database 12a and an advertisement database 12b. The business database 12a is a database that manages product information, sales data, sales data, inventory data, and the like. The advertisement database 12b is a database that manages advertisement data to be presented to the customer at the store. In the advertisement database 12b, it is assumed that the attribute of the customer that is the target of each advertisement is associated with the advertisement data.

The imaging device 18 is, for example, a camera or video camera installed on a cash register counter, ceiling, wall surface or the like of a store. The peripheral device 20 is various devices used at the time of accounting processing, and includes, for example, a display, a non-contact IC (Integrated Circuit) reader / writer, a printer, a cash drawer, a code scanner, and the like.

As shown in FIG. 1, the information processing apparatus 10 according to the present embodiment includes an imaging unit 10a, a product information extraction unit 10b, an attribute estimation unit 10c, an advertisement selection unit 10d, an advertisement output unit 10e, A product information registration unit 10f. The imaging unit 10a captures an image of an object owned by a customer at a store. The imaging unit 10a of the present embodiment acquires an image of a product (object) brought by the customer to the settlement area by controlling the imaging operation of the imaging device 18. The product information extraction unit 10b extracts product information (object information) of a product (object) from the image.

The attribute estimation unit 10c estimates customer attributes from the product information extracted by the product information extraction unit 10b. Specific examples of customer attributes include age (age), gender, height, body shape, clothing, family structure, occupation, customer hobbies, and preferences. Here, an example of a method for estimating the age and sex, which are customer attributes, from the product image will be described. First, a database is provided in a storage device (for example, HDD 104) or store server 12 described later, and the age group and sex of a customer who is the target of each product are registered in the database. The attribute estimation unit 10c estimates the age and sex of the customer who owns the product by referring to the database based on the product information extracted by the product information extraction unit 10b.

Further, the attribute estimation unit 10c estimates the customer's internal attributes such as the customer's hobbies and preferences by referring to a database in which the hobbies and preferences are previously associated with the single product and the combination of the products. Specifically, hobbies and preferences of people who buy sneakers are [Outdoor], and hobbies and preferences of people who purchase running shoes and sports towels are [Sports], [Running], [Runner-oriented], etc. Can be estimated as follows. Note that the method for estimating the customer attribute based on the product is not limited to the above-described method. In the present embodiment, a product information table (not shown) included in the business database 12a is used.

The advertisement selection unit 10d selects an advertisement to be output to the advertisement distribution device 16 that is an advertisement medium in the store, based on the attribute estimated by the attribute estimation unit 10c. Specifically, the advertisement selection unit 10d of the present embodiment refers to the advertisement database 12b of the store server 12 based on customer attributes. Then, the advertisement selection unit 10d selects advertisement data that matches the customer attribute estimated from the product image, and downloads it from the advertisement database 12b. The advertisement output unit 10e outputs the advertisement data selected by the advertisement selection unit 10d to the advertisement distribution device 16. In this way, by estimating an attribute such as the customer's age from the product owned by the customer and referring to the database based on the attribute, an advertisement can be selected and output based on the customer's attribute.

The product information registration unit 10f uses a barcode scanner (not shown) or a non-contact IC reader / writer (not shown), which is a peripheral device 20, to copy a barcode or IC tag attached to a product brought to the settlement area by the customer. The product information of the purchased product is acquired by reading and registered in a storage device to be described later. The product information extraction unit 10b described above acquires product information based on the product image before settlement. On the other hand, the merchandise information registration unit 10f acquires the merchandise information by reading the recording medium attached to the merchandise, and outputs the merchandise information to the attribute estimation unit 10c.

FIG. 2 is a block diagram illustrating a hardware configuration example of the information processing apparatus 10 according to the present embodiment. As shown in FIG. 2, the information processing apparatus 10 includes a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, an HDD (Hard Disk Drive) 104, a communication interface (I / I). F (Interface)) 105, an input device 106, an output device 107, and a display device 108. Each device is connected to a common bus line 109.

The CPU 101 controls the overall operation of the information processing apparatus 10. Further, the CPU 101 loads a program stored in the HDD 104 or the like into the RAM 103 and executes it. Thereby, CPU101 implement | achieves the function as the above-mentioned imaging part 10a, the product information extraction part 10b, the attribute estimation part 10c, the advertisement selection part 10d, the advertisement output part 10e, and the product information registration part 10f.

The ROM 102 stores a program such as a boot program. The RAM 103 is used as a working area when the CPU 101 executes a program.

The HDD 104 is a storage device that stores the processing results in the information processing apparatus 10 and various programs executed by the CPU 101. The storage device is not limited to the HDD 104 as long as it is nonvolatile. The storage device may be a flash memory, for example.

The communication I / F 105 controls data communication with a device connected to the network 14. The communication I / F 105, together with the CPU 101, realizes functions as an imaging unit 10a, a product information extraction unit 10b, an attribute estimation unit 10c, an advertisement selection unit 10d, an advertisement output unit 10e, and a product information registration unit 10f.

The input device 106 is a human interface such as a keyboard and a mouse. Further, the input device 106 may be a touch panel incorporated in the display device 108. A user of the information processing apparatus 10 can input settings of the information processing apparatus 10, input a process execution instruction, and the like via the input device 106.

The output device 107 is a device that outputs predetermined information in accordance with a control signal from the CPU 101. The output device 107 is, for example, a speaker or a printer.

The display device 108 is a device that displays predetermined information in accordance with a control signal from the CPU 101. As the display device 108, a liquid crystal display or the like can be used in the same manner as the advertisement distribution device 16 described above.

Note that the information processing apparatus 10 is not limited to the hardware configuration illustrated in FIG. 2 and may further include other devices. The information processing device 10 may be composed of one or a plurality of devices, or may be configured integrally with other devices. Further, the information processing apparatus 10 may be connected to another apparatus, and at least a part of the processing performed by the information processing apparatus 10 in the present embodiment may be performed by the apparatus.

Hereinafter, the operation of the information processing apparatus 10 configured as described above will be described with reference to FIGS. 3 to 5C. FIG. 3 is a flowchart illustrating an example of the advertisement output method of the information processing apparatus 10 according to the present embodiment. 4A to 4C are diagrams illustrating an example of a relationship between an image of a product imaged in the present embodiment and an attribute estimated from the image. 5A to 5C are diagrams showing examples of advertisements output based on customer attributes in the present embodiment.

First, the image capturing unit 10a captures an image of a pre-payment product that a customer has with a shopping basket (step S101). The imaging unit 10a outputs the captured image to the attribute estimation unit 10c.

Next, the product information extraction unit 10b analyzes the product image and extracts product information (step S102). The merchandise information extraction unit 10b stores the merchandise information in a storage device (for example, the HDD 104 or the RAM 103) and outputs the merchandise information to the attribute estimation unit 10c.

Next, the attribute estimation unit 10c refers to the business database 12a of the store server 12 based on the product information input from the product information extraction unit 10b, and determines the customer's age, gender, and height based on the single product and the combination of products. , Attributes such as body type, hobbies, and preferences are estimated (step S103). The attribute estimation unit 10c outputs the estimated customer attribute to the advertisement selection unit 10d.

In FIGS. 4A to 4C, images IMG_1 to IMG_3 respectively showing products brought by the customer with shopping basket B, product information of each product extracted from each image, and customer attributes estimated from each image are shown. ing. In FIG. 4A, [G1: Running shoes] and [G2: Sports towel] are extracted as product information. The customer attributes are estimated to be [sex: male], [age group: 20-30s], and [hobby: running].

In FIG. 4B, [G3: Cosmetics] and [G4: Fashion magazine] are extracted as the product information. The customer attributes are estimated to be [sex: female], [age group: 20-30s], and [hobby: fashion]. Gender and age groups are estimated from fashion magazine subscribers.

Similarly, in FIG. 4C, [G5: Shaving], [G6: Golf magazine], and [G7: Paper diaper] are extracted as product information. The customer attributes are estimated to be [sex: male], [hobby: golf], and [family composition: infants]. That is, the gender is estimated from the shaving (G5) and the golf magazine (G6), and the family structure is estimated based on the fact that the paper diaper (G7) is included.

Next, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the customer attribute estimated by the attribute estimation unit 10c. Then, the advertisement selection unit 10d selects advertisement data that matches the estimated attribute (step S104), and downloads it from the advertisement database 12b.

Then, the advertisement output unit 10e outputs the advertisement data selected by the advertisement selection unit 10d to the advertisement distribution device 16 (Step S105), and ends the process. In this way, by presenting the advertisement to the customer before the settlement process is completed, the customer's new demand can be stimulated.

5A to 5C, the advertisement data matching the customer attributes shown in FIGS. 4A to 4C is displayed on the advertisement distribution device 16. FIG. That is, in FIG. 5A, an advertisement targeting men in their 20s to 30s is displayed on the display 16a. Further, in FIG. 5B, an advertisement targeting women in their 20s to 30s is displayed on the display 16a. In FIG. 5C, an advertisement targeting a home with a small child is displayed on the display 16a.

Subsequently, the operation of the information processing apparatus 10 at the time of settlement will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of the advertisement output method of the information processing apparatus 10 according to the present embodiment. The process in FIG. 6 is executed for a purchased product.

First, the product information registration unit 10f acquires the product information of the purchased product by reading the record information of the recording medium attached to the purchased product brought to the cashier counter by the customer with the shopping cart (step S201). The merchandise information registration unit 10f outputs the acquired merchandise information to the attribute estimation unit 10c.

Next, the merchandise information registration unit 10f determines whether or not a customer's member card has been presented (step S202). Here, when the merchandise information registration unit 10f determines that the member's card is presented (step S202: YES), the process proceeds to step S203. On the other hand, when the merchandise information registration unit 10f determines that the member's card is not presented (step S202: NO), the process proceeds to step S206.

In step S203, the merchandise information registration unit 10f acquires the purchase history data of the customer from the business database 12a of the store server 12 based on the presented member card, and outputs the purchase history data to the advertisement selection unit 10d.

Next, the attribute estimation unit 10c refers to the business database 12a of the store server 12 based on the product information of the purchased product input from the product information registration unit 10f, and determines the customer's age based on the product alone and the product combination, Attributes such as gender, height, body type, hobbies, and preferences are estimated (step S204). The attribute estimation unit 10c outputs the estimated customer attribute to the advertisement selection unit 10d.

Next, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the customer attributes and purchase history data estimated by the attribute estimation unit 10c. Then, the advertisement selection unit 10d selects advertisement data that matches the estimated attribute (step S205), and downloads it from the advertisement database 12b.

In step S206, the attribute estimation unit 10c refers to the business database 12a of the store server 12 based on the product information of the purchased product input from the product information registration unit 10f, and determines the customer's age based on the product alone and the product combination. Estimate attributes such as sex, height, body type, hobbies, and preferences. The attribute estimation unit 10c outputs the estimated customer attribute to the advertisement selection unit 10d.

Next, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the customer attribute estimated by the attribute estimation unit 10c. Then, the advertisement selection unit 10d selects advertisement data that matches the estimated attribute (step S207), and downloads it from the advertisement database 12b.

In step S208, the advertisement output unit 10e outputs the advertisement data selected by the advertisement selection unit 10d to the advertisement distribution device 16, and ends the process.

As described above, according to the information processing apparatus 10 according to the present embodiment, product information can be acquired from an image of a product held by a customer before settlement, and customer attributes can be estimated based on the product information. Then, the information processing apparatus 10 can select an appropriate advertisement according to the estimated customer attribute and output it to the advertisement medium. Since it is not necessary to register data such as hobbies and preferences of customers who have visited the store in advance, for example, appropriate advertisements can be output even for customers who have visited the store for the first time. Further, the customer attributes are estimated again based on the product information acquired from the purchased product at the time of checkout. Customer attributes can be estimated with higher accuracy than before payment, and new advertisements can be presented to customers.

[Second Embodiment]
The information processing apparatus according to the second embodiment will be described below. In addition, the code | symbol common with the code | symbol provided in the figure of 1st Embodiment shows the same object. For this reason, the description of the part common to 1st Embodiment is abbreviate | omitted, and a different part is demonstrated in detail.

The information processing apparatus according to the present embodiment further includes a function in which the attribute estimation unit 10c further estimates a purchase tendency based on a comparison result between the price of a product and the price of another product that belongs to the same category as the product. This is different from the first embodiment. Here, examples of purchase tendencies include luxury-oriented, cost-oriented, brand-oriented, and functionality-oriented.

As a method of estimating purchase tendency, first, a category to which a customer's purchase item belongs is specified. Next, the rank of the price range where the price of the purchased product is located in the same category (hereinafter referred to as “purchased product rank”) is determined in 100 steps, for example. When the purchase item rank is higher than a predetermined threshold, it is determined as [purchasing tendency: high-end orientation], and when it is low, it is determined as [purchasing tendency: cost-oriented]. Furthermore, when a product of a predetermined luxury brand is included in the purchased product at a high ratio, it is determined that [purchasing tendency: brand-oriented].

Hereinafter, the operation of the information processing apparatus according to the present embodiment will be described with reference to FIGS. FIG. 7 is a flowchart illustrating an example of an advertisement output method of the information processing apparatus according to the present embodiment. FIG. 8 is a diagram illustrating an example of the relationship between the product image captured in the present embodiment and the customer's purchase tendency and attributes estimated from the image. FIG. 9 is a diagram illustrating an example of an advertisement output based on customer attributes in the present embodiment.

First, the image capturing unit 10a captures an image of a pre-settlement product that the customer has with a shopping cart or the like (step S301). The imaging unit 10a outputs the captured image to the attribute estimation unit 10c.

Next, the product information extraction unit 10b analyzes the product image and extracts product information (step S302). The merchandise information extraction unit 10b stores the merchandise information in a storage device (for example, the HDD 104 or the RAM 103) and outputs the merchandise information to the attribute estimation unit 10c.

Next, the attribute estimation unit 10c analyzes the product information input from the product information extraction unit 10b, and determines a purchase tendency based on a comparison result between the price of the product and the price of another product belonging to the same category as the product. Estimate (step S303).

In the example of FIG. 8, an image IMG_4 showing each product brought by the customer with the shopping basket B, product information of each product extracted from the image, customer attributes and purchase trends estimated from the image are shown. Yes. Specifically, [G8: Y-shirt], [Purchase rank: 36/100], [G9: Sneaker], [Purchase rank: 30/100], [Purchase rank (average): 33 / 100] is estimated. That is, assuming that the score of the highest price range is 100 and the average price range is 50, the customer who wants to purchase the product in FIG. 8 selects the relatively cheap price range. Therefore, the customer attributes are [sex: male] and [age group: 20-30s], and the purchase tendency is estimated to be [cost-oriented].

Next, the attribute estimation unit 10c refers to the business database 12a of the store server 12 based on the product information input from the product information extraction unit 10b, and determines the customer's age, gender, and height based on the single product and the combination of products. , Attributes such as body shape, hobbies, and preferences are estimated (step S304). The attribute estimation unit 10c outputs the estimated customer attribute to the advertisement selection unit 10d.

Next, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the customer attribute and the customer purchase tendency estimated by the attribute estimation unit 10c. Then, the advertisement selection unit 10d selects advertisement data that meets the conditions (step S305), and downloads it from the advertisement database 12b.

Then, the advertisement output unit 10e outputs the advertisement data selected by the advertisement selection unit 10d to the advertisement distribution device 16 (Step S306), and ends the process. In the example of FIG. 9, since the purchase tendency of the customer shown in FIG. 8 is cost-oriented, an advertisement for proposing another Y-shirt whose price is lower than the purchased product in the Y-shirt category is displayed on the display 16a. Has been.

Thus, according to the information processing apparatus according to the present embodiment, it is possible to select an advertisement based on the customer attribute and purchase tendency estimated from the product image. That is, an advertisement selected from a viewpoint different from that in the first embodiment can be presented to the customer.

[Third Embodiment]
Hereinafter, the information processing apparatus 30 according to the third embodiment will be described. In addition, the code | symbol common with the code | symbol provided in the figure of the above-mentioned embodiment shows the same object. For this reason, the description of the part common to the above-mentioned embodiment is abbreviate | omitted, and a different part is demonstrated in detail.

FIG. 10 is a schematic diagram illustrating an example of the overall configuration of an advertisement distribution system to which the information processing apparatus 30 according to the present embodiment is applied. As illustrated in FIG. 10, the information processing apparatus 30 according to the present embodiment includes an object specifying unit 10 g instead of the product information extraction unit 10 b and the product information registration unit 10 f illustrated in FIG. 1. The object specifying unit 10g specifies the type of the object by analyzing the image when an object other than the customer is included in the image. The object whose type is specified by the object specifying unit 10g is not limited to a product.

Then, the advertisement selection unit 10d selects an advertisement based on the combination of the customer attribute and the object type. For example, in the case of an image including a car, an advertisement for a driver is selected in consideration of the age of the customer. Similarly, in the case of an image including a golf bag, an advertisement for a golfer is selected. In other words, since there is a high possibility that the customer's hobbies and preferences are reflected in the object owned by the customer, the customer's attributes can be estimated in detail by specifying the type of the object.

Furthermore, the attribute estimation unit 10c of the present embodiment acquires the accessory information of the object from the image. Then, the advertisement selection unit 10d selects an advertisement based on a combination of attributes, object types, and accessory information. For example, vehicle accessory information includes information obtained from accessories on the outside of the vehicle such as emblems, license plates, vehicle inspection seals, and various stickers attached to the vehicle body, and information on the inside of the vehicle such as the presence or absence of a child seat. Information obtained from the product.

Thus, by considering the accessory information of the object, it is possible to estimate the customer attributes in more detail. For example, when the vehicle is specified as a luxury vehicle from the emblem, it can be estimated that the customer's monetary allowance or purchase tendency is high-end-oriented. Moreover, when the child seat is attached in the vehicle, it can be estimated that there are small children in the family and the number of children. As described above, the information processing apparatus 30 according to the present embodiment is different from the above-described embodiment in that an advertisement is selected using information obtained from an object held by a customer.

Hereinafter, the operation of the information processing apparatus according to the present embodiment will be described with reference to FIGS. 11 to 13. FIG. 11 is a flowchart illustrating an example of the advertisement output method of the information processing apparatus according to the present embodiment. FIG. 12 is a diagram illustrating an example of an image of an object captured in the present embodiment. FIG. 13 is a diagram illustrating an example of an advertisement output according to a customer attribute estimated from an object image in the present embodiment. In the following description, a case where an advertisement is distributed in a gas station store will be described as an example.

First, the imaging unit 10a images an object existing in a predetermined imaging area in the store (step S401). The imaging unit 10a outputs the captured image to the attribute estimation unit 10c.

Next, the object specifying unit 10g analyzes the input image and specifies the type of the object (step S402). Here, an example of the specifying method will be described. Learning data in which feature quantities of a plurality of objects and object types are associated with each other is created in advance, and stored in a storage device (for example, the HDD 104) or the store server 12 as a database. Next, an object is extracted from the image captured by the imaging device 18, and a feature amount of the extracted object is calculated. Then, the attribute estimation unit 10c identifies the type of the imaged object by comparing the calculated feature quantity of the object with the feature quantity of the database. In the case of a gas station, the type of vehicle is specified such as a passenger car, a motorcycle, a truck, and a special vehicle.

Next, the attribute estimation unit 10c estimates a customer attribute based on the type of object (step S403). The attribute estimation unit 10c outputs the estimated customer attribute to the advertisement selection unit 10d.

Next, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the estimated customer attribute and object type. Then, the advertisement selection unit 10d selects advertisement data that matches the estimated attribute (step S404), and downloads it from the advertisement database 12b.

In step S405, the attribute estimation unit 10c analyzes the object portion included in the image and determines whether or not a predetermined accessory exists on the object. If the attribute estimation unit 10c determines that a predetermined accessory is present on the object (step S405: YES), the process proceeds to step S406. On the other hand, when the attribute estimation unit 10c determines that the predetermined accessory does not exist in the object (step S405: NO), the process proceeds to step S408.

In step S406, the attribute estimation unit 10c acquires the accessory information of the object from the image. In the example of FIG. 12, an image IMG_5 including the object X, customer attributes estimated from the image, object information of the object X, and accessory information of the object X are illustrated. Since the type of the object X is “automobile”, “hobby: drive” is included as a customer attribute. A plurality of accessory information is acquired by extracting / analyzing information on predetermined areas A1, A2, and A3 of the object X included in the image IMG_5. For example, accessory information of [maker: AAA], [maker category: domestic manufacturer], and [price range: high] is acquired from the emblem included in the area A1. The accessory information of [Registered place: Shinagawa] is acquired from the license plate included in the area A2. From the vehicle inspection seal included in the area A3, accessory information of [vehicle inspection expiration date: March 2018] is acquired. Then, accessory information [presence / absence of child seat: present] is acquired from the inside of the vehicle (not shown). Accordingly, [Family structure: With children] is added to the customer attribute.

In step S407, the advertisement selection unit 10d refers to the advertisement database 12b of the store server 12 based on the accessory information. Then, the advertisement selection unit 10d selects advertisement data that matches the estimated attribute, and downloads it from the advertisement database 12b. That is, advertisement data selected based on customer attributes and object accessory information is output.

In step S408, the advertisement output unit 10e outputs the advertisement data selected by the advertisement selection unit 10d to the advertisement distribution device 16 by the selected output method, and ends the process. FIG. 13 shows an example of an advertisement displayed for the customer of FIG. Here, two advertisements are displayed in the upper and lower columns of the display 16a. The advertisement in the upper column is an advertisement related to vehicle inspection, and is selected based on the fact that the vehicle inspection expiration date is approaching from the accessory information. The advertisement in the lower column is an advertisement that introduces a tourist destination for families with children, and is selected based on the presence of a child seat in the vehicle.

As described above, according to the information processing apparatus according to the present embodiment, when an object is included in an image, an appropriate advertisement is based on a combination of the type of the object, information on the accessory of the object, and the customer attribute. Can be output to the advertising medium. That is, by using information obtained from an object owned by a customer for selection of an advertisement, it is possible to provide an advertisement that further matches the hobby / preference of the customer.

[Fourth Embodiment]
Hereinafter, the information processing apparatus 40 according to the fourth embodiment will be described. In addition, the code | symbol common with the code | symbol provided in the figure of the above-mentioned embodiment shows the same object. For this reason, the description of the part common to the above-mentioned embodiment is abbreviate | omitted, and a different part is demonstrated in detail.

The information processing apparatus 40 according to the present embodiment is different from the above-described embodiment in that an advertisement based on the situation outside the store can be output to an advertising medium. Here, specific examples of the situation outside the store include the situation such as weather, traffic, presence / absence of alarm, and the like.

FIG. 14 is a diagram illustrating an example of the relationship between the weather outside the store and an advertisement output based on the weather in the present embodiment. Here, when the customer Y shop in the store P, the imaging device 18 images outside the store P. The management server 22 is a server provided in common among a plurality of affiliated stores, and is assumed to hold advertisement data in the same manner as the store server 12 described above. The information processing device 40 of the store P controls the advertisement in the advertisement distribution device 16 according to the weather by determining the weather outside the store based on the analysis result of the captured image. For example, when it starts to rain outside the store P, an advertisement that prompts the purchase of an umbrella in real time can be presented to the customer Y.

Further, the example of FIG. 14 shows a case where the member card C presented by the customer Y is read by the peripheral device 20 and reflected in the advertisement content. Specifically, the return route from the store P is searched based on the customer's address acquired from the member's card C, and the affiliated store (store Q) existing near the customer's address is searched for. Weather information is acquired from the information processing apparatus 40 of Q). In addition, you may acquire weather information collectively by searching WEB information. If it is determined that the weather outside the store P is “cloudy” but the weather outside the store Q is “heavy rain”, the information processing apparatus 40 of the store P will be as shown in FIG. Can be advertised to encourage the purchase of umbrellas. Note that the same method can be used for cases other than weather information based on the situation outside the store.

Thus, according to the information processing apparatus 40 according to the present embodiment, in addition to the advertisement according to the customer's attribute, the advertisement selected based on the situation outside the store such as the weather and traffic situation can be presented to the customer. Further, by using the registered customer information, an advertisement useful for the customer can be presented.

[Other Embodiments]
According to still another embodiment, the information processing apparatus described in the above embodiment can be configured as shown in FIG. FIG. 15 is a block diagram illustrating a configuration of the information processing apparatus 50 according to another embodiment.

As illustrated in FIG. 15, the information processing apparatus 50 according to another embodiment includes an imaging unit 50 a that captures an image of an object owned by a customer in a store, an extraction unit 50 b that extracts object information of the object from the image, Estimating means 50c for estimating customer attributes from information, and selecting means 50d for selecting advertisements to be output to the advertising medium based on the attributes. According to the information processing apparatus 50 in another embodiment, an appropriate advertisement according to the attribute can be output to a customer existing in the vicinity of the advertisement medium.

[Modified Embodiment]
Although the present invention has been described with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention without departing from the gist of the present invention. For example, an embodiment in which a part of the configuration of any of the embodiments is added to another embodiment, or an embodiment in which a part of the configuration of another embodiment is replaced is also an embodiment to which the present invention can be applied. .

In the above-described embodiment, the method for estimating the customer attribute based on the result of the image analysis of the product that the customer owns (bring) is described. However, the attribute estimation method is not limited to this. The attribute estimation unit 10c may estimate the attribute based on the combination of the total weight of the product and the transport method. For example, when the total weight of purchased products exceeds 20 kg and the method of transport does not use a product cart, it can be estimated that the customer attribute is a relatively young man. About a conveyance method, it can determine by whether an instrument, such as a goods cart, is reflected in an image like goods.

Similarly, the attribute estimation unit 10c may estimate the attribute based on the total purchase amount of the product. For example, when the total purchase amount exceeds a predetermined threshold, it can be estimated that the customer has a financial margin. Further, the advertisement may be selected based on the number of purchased products and the past purchase history. That is, when the customer repeats bulk purchases over a long period of time, it is considered that the degree of product demand is high. Therefore, an advertisement that prompts repurchase may be presented at a predetermined timing.

Furthermore, when the purchased product includes a product having a different property from other products, the output of the advertisement based on the product may be restricted. For example, there may be variations such as not estimating customer attributes from products purchased for gifts. In this way, by combining several attribute estimation methods, customer attributes can be estimated with higher accuracy.

Also, there is a processing method in which a program for operating the configuration of the embodiment is recorded on a recording medium so as to realize the functions of the above-described embodiments, the program recorded on the recording medium is read as a code, and executed by a computer. It is included in the category of each embodiment. That is, a computer-readable recording medium is also included in the scope of each embodiment. In addition to the recording medium on which the above-described computer program is recorded, the computer program itself is included in each embodiment.

As the recording medium, for example, a floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, CD-ROM (Compact Disc-Read Only Memory), magnetic tape, nonvolatile memory card, and ROM can be used. In addition, not only those that execute processing by a single program recorded on the recording medium, but also those that execute processing on an OS (Operating System) in cooperation with other software and expansion board functions Included in the category of form.

Some or all of the above-described embodiments can be described as in the following supplementary notes, but are not limited thereto.

(Appendix 1)
Image pickup means for picking up an image of an object owned by a customer at a store;
Extraction means for extracting object information of the object from the image;
Estimating means for estimating the attribute of the customer from the object information;
An information processing apparatus comprising: selection means for selecting an advertisement to be output to an advertisement medium based on the attribute.

(Appendix 2)
The information processing apparatus according to appendix 1, wherein the object is a product before settlement.

(Appendix 3)
A registration means for registering product information of the product;
The information processing apparatus according to appendix 2, wherein the estimation unit estimates an attribute of the customer from the registered product information.

(Appendix 4)
The estimation means estimates the purchase tendency of the customer from the product information,
The information processing apparatus according to appendix 3, wherein the selection unit selects the advertisement along the purchase tendency.

(Appendix 5)
The information processing apparatus according to appendix 4, wherein the estimation means estimates the purchase tendency based on a comparison result between a price of the product and a price of another product belonging to the same category as the product.

(Appendix 6)
The information processing apparatus according to any one of appendices 2 to 5, wherein the estimation unit estimates the attribute based on a combination of a total weight of the product and a transport method.

(Appendix 7)
The information processing apparatus according to any one of appendices 2 to 5, wherein the estimation unit estimates the attribute based on a total purchase amount of the product.

(Appendix 8)
The information processing apparatus according to any one of appendices 1 to 7, wherein the attribute includes at least one of the age, sex, hobbies, and preferences of the customer.

(Appendix 9)
Capturing an image of an object owned by the customer at the store;
Extracting object information of the object from the image;
Estimating customer attributes from the object information;
Selecting an advertisement to be output to an advertisement medium based on the attribute.

(Appendix 10)
On the computer,
Capturing an image of an object owned by the customer at the store;
Extracting object information of the object from the image;
Estimating customer attributes from the object information;
A recording medium on which is recorded a program that executes a step of selecting an advertisement to be output to an advertising medium based on the attribute.

This application claims priority based on Japanese Patent Application No. 2018-054809 filed on Mar. 22, 2018, the entire disclosure of which is incorporated herein.

10, 30, 40, 50 ... information processing apparatus 10a ... imaging unit (imaging means)
10b ... Product information extraction unit (extraction means)
10c ... attribute estimation unit (estimation means)
10d: Advertisement selection unit (selection means)
10e: Advertisement output unit 10f: Product information registration unit (registration means)
10g ... object identification part (extraction means)
12 ... Store server 14 ... Network 16 ... Advertisement distribution device 18 ... Imaging device 20 ... Peripheral device

Claims

Image pickup means for picking up an image of an object owned by a customer at a store;
Extraction means for extracting object information of the object from the image;
Estimating means for estimating the attribute of the customer from the object information;
An information processing apparatus comprising: selection means for selecting an advertisement to be output to an advertisement medium based on the attribute.
The information processing apparatus according to claim 1, wherein the object is a product before settlement.
A registration means for registering product information of the product;
The information processing apparatus according to claim 2, wherein the estimation unit estimates an attribute of the customer from the registered product information.
The estimation means estimates the purchase tendency of the customer from the product information,
The information processing apparatus according to claim 3, wherein the selection unit selects the advertisement along the purchase tendency.
The information processing apparatus according to claim 4, wherein the estimation unit estimates the purchase tendency based on a comparison result between a price of the product and a price of another product belonging to the same category as the product. .
The information processing apparatus according to any one of claims 2 to 5, wherein the estimation unit estimates the attribute based on a combination of a total weight of the product and a transport method.
The information processing apparatus according to any one of claims 2 to 5, wherein the estimation unit estimates the attribute based on a total purchase amount of the product.
The information processing apparatus according to any one of claims 1 to 7, wherein the attribute includes at least one of the age, sex, hobbies, and preferences of the customer.
Capturing an image of an object owned by the customer at the store;
Extracting object information of the object from the image;
Estimating customer attributes from the object information;
Selecting an advertisement to be output to an advertisement medium based on the attribute.
On the computer,
Capturing an image of an object owned by the customer at the store;
Extracting object information of the object from the image;
Estimating customer attributes from the object information;
A recording medium on which is recorded a program that executes a step of selecting an advertisement to be output to an advertising medium based on the attribute.