JP7108910B2 - Information presentation system - Google Patents

Description

The present invention relates to technology for presenting information about customers in brick-and-mortar retail stores.

In physical retail stores such as supermarkets, there has been proposed a shopping cart or the like equipped with a display for presenting shoppers with bargain sale information at the store (see Patent Document 1).

JP 2004-106827 A

However, the information provided by the display of Patent Literature 1 may not be immediately useful to each shopper visiting the store for various purposes. In this case, shoppers do not pay attention to the information displayed on the display, and the system including the shopping cart that can provide such information is not effectively utilized.

Accordingly, the present invention provides an information presentation system that presents more useful information for each customer.

An information presentation system according to an aspect of the present invention includes a product identification information acquirer that acquires, from each of a plurality of products owned by a customer who is shopping in a physical store, identification information for identifying the product. , customer profile information that acquires results obtained by identifying each of a plurality of products using the identification information as purchase candidate information, and that indicates the customer's psychological state estimated based on at least part of the purchase candidate information; and a profiling server that identifies sales floor- related information of a physical store using customer profile information ; Among them, the customer profile information is obtained by giving higher weight to the purchase candidate information indicating the product whose order in which the customer started holding is later .

In addition, these general or specific aspects may be realized by a system, method, integrated circuit, computer program, or a recording medium such as a computer-readable CD-ROM. and any combination of recording media.

The information presentation system of the present invention can present more useful information for each customer.

FIG. 1 is a block diagram showing the configuration of an information presentation system according to an embodiment. FIG. 2A is a diagram showing an example of a product holder according to the embodiment; FIG. 2B is a diagram showing another example of the product holder in the embodiment. FIG. 2C is a diagram showing another example of the product holder in the embodiment; FIG. 2D is a diagram illustrating an example of an information presentation device according to the embodiment; FIG. 3A is a diagram illustrating the concept of the Evaluation Grid Method™. FIG. 3B is a diagram illustrating an example of a deep psychological model according to the embodiment; FIG. 3C is a diagram illustrating another example of a deep psychological model in the embodiment; FIG. 4 is a sequence diagram for explaining the procedure of an operation example of the information presentation system according to the embodiment. FIG. 5 is a diagram for explaining the concept of a procedure from transmission of product identification information to product identification in the embodiment. FIG. 6 is an example of a screen presented to the customer by the information presentation device in the embodiment. FIG. 7 is a sequence diagram for explaining another example of the procedure of the operation example of the information presentation system according to the embodiment. FIG. 8 is a sequence diagram for explaining still another example of the procedure of the operation example of the information presentation system according to the embodiment. FIG. 9 is a sequence diagram for explaining still another example of the procedure of the operation example of the information presentation system according to the embodiment.

(Circumstances leading to obtaining one aspect of the present invention)
The inventors of the present invention have found that the following problems arise in the shopping carts and the like provided with displays described in the "Background Art" section.

The information displayed on the shopping cart display is an electronic extension of the newspaper insert, with dynamic changes that change over time. However, the products that customers who visit the store want are not necessarily the products advertised. Therefore, the information displayed on such a display may be regarded by some customers as uninteresting information, and they may not pay attention to it or may have the impression that it is bothersome.

On the other hand, as a method of sales promotion that matches the purpose of each customer's visit to the store or the trend of store usage, it is possible that the customer will be interested based on the information on the purchased item read at the time of payment by the POS (point of sales) system. A method of issuing discount coupons for high-quality products has been proposed. However, there are customers who forget the existence of the discount coupon or lose it by the time they come to the store next time. Moreover, the customer may not necessarily want the target product during the validity period of the discount coupon. Because of this background, it is difficult for the rate of response to this discount coupon to increase beyond a certain level.

In this way, the provision of information to customers and the utilization of information about customers in physical retail stores have not produced sufficient beneficial effects for both customers and store operators.

In order to solve such a problem, an information presentation system according to an aspect of the present invention provides a system for identifying a product from each of a plurality of products sequentially held by a customer who is shopping in a physical store. a product identification information acquisition device for acquiring identification information; and, when the identification information is acquired from the product identification information acquisition device, acquiring results obtained by identifying each of a plurality of products using the identification information as purchase candidate information, a profiling server that acquires customer profile information indicating a customer's psychological state estimated based on at least part of purchase candidate information and specifies sales floor related information for reflecting the customer profile information on the sales floor of the actual store; and an information presentation device that acquires and presents related information.

As a result, it is possible to obtain a store configuration according to the customer's mental state in the store. In such stores, the quality of the customer's shopping experience tends to be improved, and an increase in store sales can be expected.

For example, the profiling server may acquire customer profile information using purchase candidate information indicating a predetermined number or types of products in descending order of the order in which the customer started holding the purchase candidate information. In addition, for example, the profiling server may acquire customer profile information using purchase candidate information that indicates products for which the customer started holding the product within a predetermined retroactive time, among the purchase candidate information.

This makes it possible to estimate a more accurate state of mind based on a product that is likely to have been selected in a state of mind close to the current state of mind from among the products held by the customer. In addition, it is possible to avoid using the information of the product held in a state of mind that is highly likely to be different from the current state of mind of the customer for estimating the current state of mind.

For example, the profiling server may acquire customer profile information by using, among purchase candidate information, purchase candidate information indicating a product whose order in which the customer started holding the product later is weighted higher.

As a result, among the products held by customers, products that are likely to better reflect the customer's current state of mind are more importantly used in estimating the state of mind of the customer. can be estimated.

For example, the profiling server stores a customer profile indicating the psychological state of other customers who have been at the sales floor within a predetermined time from the current time after the customer entered the physical store and before the customer started holding a plurality of products. Other sales floor-related information that has been specified in order to reflect the information on the sales floor may be transmitted to the information presentation device so as to be presented to the customer.

As a result, customers who have just entered each store can be presented with recommended products that reflect the psychological state of the customer base during that time period at the store. If this customer matches this customer class, it is possible to present sales floor-related information in accordance with the customer's psychological state from an early stage of shopping behavior.

For example, the sales floor-related information may indicate products that have been purchased in the above psychological state, and the information presentation device may present the sales floor-related information to the customer at the sales floor of the actual store.

As a result, it is possible to present information for proposing combined purchases according to the customer's mental state to the customer who is shopping at the sales floor. In other words, it is possible to select on the spot information about products that the customer is likely to be interested in and provide the information to the customer. Therefore, the quality of the customer's shopping experience at this store can be further improved. Further increases in store sales can also be expected.

For example, the sales floor-related information is information indicated by at least one of an image and a sound associated with the psychological state, and the information presentation device presents at least one of the image and the sound to the customer at the sales floor of the actual store. Relevant information may be presented.

As a result, it is possible to provide a customer who is shopping at the sales floor with video or audio for an effect corresponding to the customer's state of mind. And the quality of the customer's shopping experience at this store can be further improved.

For example, the product identification information acquirer further detects the cancellation of retention of the product by the customer and recognizes the product, and the profiling server acquires the return information regarding the released product from the product identification information acquirer. After that, customer profile information may be obtained based on at least a part of the purchase candidate information and return information regarding the product that the customer has started to hold.

As a result, it is possible to more easily and accurately estimate the reason why the customer changed the product to be purchased. The reason estimated in this way can be used as a material for improvement or development of the product lineup of the store or the product of the manufacturer, and can lead to an increase in the sales of the store or the manufacturer.

For example, the profiling server may acquire customer profile information using a deep psychological model created in advance by the evaluation grid method (registered trademark) for each product sold at a physical store.

This makes it possible to estimate the psychological state of the customer when purchasing each product, for example, the purpose of purchasing the product, based on the evaluation of each product actually made by the consumer. Therefore, it is easier to obtain a higher accuracy than the conventional estimation using POS data or store member registration information.

For example, the deep psychological model includes a deep psychological model individually corresponding to the sex and age of the customer sample, the profiling server acquires personal attribute information indicating at least one of the customer's sex and age, and the personal attribute information is Customer profile information may be obtained that indicates a psychological state estimated using a deep psychological model that corresponds to at least one of gender and age.

As a result, it is possible to easily obtain a higher degree of accuracy in estimating the psychological state according to the customer's attributes such as gender or generation.

For example, the product identification information acquisition device may be provided in a product holder for holding products by placing the products by the customer.

In this way, by equipping the product identification information acquisition device to the tool on which the product selected and held by the customer in the physical store is placed, the customer can purchase the product more naturally and with a higher degree of certainty during shopping. information for identifying the

For example, the information presentation device may include at least one of an information terminal carried or worn by the customer in the physical store and a digital signage installed in the physical store.

As a result, it is possible to more reliably receive information corresponding to the customer's psychological state while shopping in the actual store.

In addition, these general or specific aspects may be realized by a system, method, integrated circuit, computer program, or a recording medium such as a computer-readable CD-ROM. Or it may be realized by any combination of recording media.

Hereinafter, embodiments will be specifically described with reference to the drawings. All of the following embodiments show comprehensive or specific examples. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown below are examples and are not intended to limit the present invention. In addition, among the constituent elements in the following embodiments, constituent elements that are not described in independent claims representing the highest concept will be described as arbitrary constituent elements.

(Embodiment 1)
[1. Configuration example]
An information presentation system according to an embodiment will be described with reference to FIGS. 1 to 2D.

FIG. 1 is a block diagram showing the configuration of an information presentation system according to an embodiment.

The information presentation system 10 according to the embodiment is a self-service type physical store (hereinafter also simply referred to as a store) in the retail industry such as a supermarket or a convenience store, based on information on the behavior of a certain customer during shopping, for example, the Make purchase suggestions to customers.

The self-service system here is widely used in retail stores as described above, and should be understood to basically satisfy the following conditions. One is that the customer can know the price of each product through a predetermined price setting such as a price tag or a uniform price for all products. On the other hand, the customer can freely select the products to be purchased from the displayed products, and the selected products can be placed in a basket, cart, tray, etc. to cancel the selection. Furthermore, the settlement of the purchases is made by the customer bringing the held commodities to a settlement office equipped with a register near the exit or the like.

However, the idea of the present invention can be applied even to stores that do not strictly meet these conditions. These conditions are shown for the purpose of presenting specific examples of situations in which the information presentation system of the present invention is used, and are not meant to limit the present invention. For example, the product to be purchased may be held using a bag or the like brought by the customer, or simply held by hand. Also, the settlement may be carried out by a method that does not use a settlement office with a register. In addition, the concept of self-service method in the present disclosure also includes the case where any of the above conditions is assisted or managed by a store clerk.

The information presentation system 10 includes a product identification information acquisition device 100 , a profiling server 200 and an information presentation device 300 .

The product identification information acquirer 100 acquires by reading identification information for identifying each product from each of a plurality of products that a customer who is shopping sequentially starts holding.

The product identification information acquisition device 100 includes a sensor 110 and a transmitter 120 .

The sensor 110 acquires identification information for identifying each product from each product that a customer who is shopping in the store starts holding.

The transmission unit 120 transmits the identification information acquired by the product identification information acquisition device 100 to the profiling server 200, which will be described later.

Such a product identification information acquisition device 100 is carried or worn by a customer who is shopping, for example, and moves in the store with the customer. More specifically, it is provided in a merchandise holder for holding merchandise by placing it on a customer, such as an in-store shopping basket as shown in FIG. 2A or a cart as shown in FIG. 2B. , or an information terminal such as a smart phone or tablet computer held in the customer's hand as shown in FIG. 2C. Note that in FIG. 2B, illustration of a portion of the frame below the cart and a portion including the wheels is omitted. A shopping basket and a cart are examples of product holders in this embodiment. Another example of a product holder is a tray. The product identification information acquisition device 100 is provided in the product holder, so that it is possible to acquire information for identifying products more naturally and with higher certainty in the customer's behavior during shopping.

The shopping basket shown in FIG. 2A includes sensor 111 as an example of sensor 110 . The cart shown in FIG. 2B includes, as an example of sensor 110, sensor 112 directed at the location where the product is to be placed. The information terminal shown in FIG. 2C includes, as an example of the sensor 110, a sensor (image sensor) 113 that constitutes a built-in camera.

The sensor 110 is, for example, an optical sensor for reading barcodes attached to products. Alternatively, sensor 110 may be, for example, an RF reader for reading radio frequency identification (RFID) from radio frequency (RF) tags attached to merchandise. A barcode or RFID indicates a product identification code such as a JAN (Japanese article number) code. Alternatively, the sensor 110 may be an image sensor for acquiring an appearance image of a product. The information indicated by the barcode or RFID and the appearance image of the product are examples of identification information for identifying the product in the present embodiment.

For example, every time a customer picks up an item at a sales floor, the barcode attached to the item is read by the sensor 110, and then placed in the shopping basket (start of holding the item). The acquired identification information is wirelessly transmitted to the profiling server 200 by the transmitting unit 120 (not shown in FIG. 2A) included in the shopping cart. A series of processing from reading to transmission of such identification information is performed by a microcontroller or processor (not shown) provided in the product identification information acquisition device 100 reading out a predetermined program stored in a storage device (not shown). This is done by running When the information terminal shown in FIG. 2C is owned by the user, the user installs a program (application) provided by the store on the information terminal to transmit the identification information to the profiling server 200, and activates it in the store. can be used.

The profiling server 200 identifies each product that the customer has started to hold using the identification information acquired from the product identification information acquisition device 100, and acquires the result obtained by this identification as purchase candidate information. Further, the profiling server 200 acquires customer profile information indicating the customer's state of mind estimated based on the purchase candidate information. In addition, the profiling server 200 further specifies sales floor-related information for reflecting this customer profile information on the sales floor of the actual store. The profiling server 200 that processes information in this way can be implemented using, for example, a server computer installed in the store or a cloud server outside the store.

The profiling server 200 includes a receiving unit 210, an identifying unit 220, an estimating unit 230, a deep psychological model 240, and a transmitting unit 250 as functional components.

The profiling server 200 acquires the product identification information transmitted from the product identification information acquisition device 100 via the receiving unit 210 .

The identification unit 220 identifies each product that the customer has started to hold using the product identification information acquired from the product identification information acquisition device 100 . For example, if the product identification information is a product identification code, the identification unit 220 searches the product identification code database (not shown) for the product identification code to identify the product. When the product identification information is an external image of the product, for example, the identification unit 220 may perform character recognition on this image to identify the product, or may perform image recognition using a model obtained by machine learning. may be run to identify the item. The result obtained by executing the identification is passed to the estimation unit 230 as information indicating the product that the customer has started to hold (hereinafter referred to as purchase candidate information).

The estimation unit 230 acquires customer profile information indicating the customer's state of mind estimated based on the purchase candidate information. The estimator 230 uses a deep psychological model 240 to obtain customer profile information.

The deep psychological model 240 is created in advance by, for example, the evaluation grid method (registered trademark) targeting each product sold at a physical store. FIG. 3A is a diagram showing the concept of the evaluation grid method.

The evaluation grid method is a research method that uses interviews to clarify the hierarchy (cognitive structure) of the evaluation concept that consumers have regarding a product, and obtains the consumer's purpose (psychological state) for choosing this product. The example in Figure 3A shows the cognitive structure that one consumer in the sample of this study has regarding a brand of chocolate. The cognitive structure is represented in a hierarchical structure from subordinate concept to superordinate concept from left to right, and the rightmost column indicates the consumer's reason for choosing this chocolate or the consumer's purpose when choosing this chocolate. Such surveys are conducted with a sample of multiple consumers. In addition, by aggregating samples for each category of attributes such as gender and age, the psychological state of consumers choosing each product for each attribute can be obtained as a result of the survey. If it is possible to acquire information indicating the attributes of customers who start holding products on the sales floor of a store (hereinafter also referred to as personal attribute information), by using a deep psychological model according to the attributes of this customer, It is possible to estimate the state of mind of the customer in the sales floor with higher accuracy.

The deep psychological model 240 according to the present embodiment associates, for example, each product with the psychological state of choosing each product among the results of the evaluation grid method implemented for each product.

FIG. 3B shows an example of the data configuration of the deep psychological model obtained in the example of FIG. 3A. Here, the example of FIG. 3B is a deep psychological model for the category of women in their thirties. Note that the cognitive structure that can be included in the deep psychological model is not limited to the psychological state of choosing a product as in this example. For example, the hierarchical content of the leftmost column seen in FIG. 3A may also be included.

Further, according to this example, the estimation unit 230 obtains the brand of chocolate as the identification information of the product that a certain customer has started holding, and obtains the information that the customer is a woman in her 30s. By referring to the psychological model, the information in the "mental state" column is obtained as customer profile information.

FIG. 3C shows another example of the data structure of the deep psychological model. In the example of FIG. 3C, a score regarding the state of mind is assigned to each product. Such scores are based, for example, on the results of questionnaires or interviews with consumers. The estimation unit 230 acquires customer profile information indicating the customer's psychological state as follows, using the deep psychological model illustrated in FIG. 3C.

Suppose a customer starts keeping one each of AAA vegetable juice, BBB coffee, and CCC blended tea. The estimating unit 230 that has acquired the purchase candidate information indicating these products refers to the deep psychological model of FIG. 3C, acquires the scores of these three points, and calculates the average value of the scores for each psychological state. Specifically, it is as follows.

I want to feel happy: (0.0+0.8+0.6)/3=0.466
I want to cheer up: (0.7 + 0.0 + 0.0) / 3 = 0.233
I want to relax: (0.4+0.9+0.9)/3=0.733
I want to refresh: (0.6+0.8+0.7)/3=0.700

Next, the estimating unit 230 acquires customer profile information such that the mental state of "I want to relax", which shows the highest value among the calculated average values, is treated as the estimated current mental state of this customer. .

In this way, the customer's state of mind may be estimated based on the multiple products that the customer has started to hold. The method of estimating the customer's mental state based on a plurality of products is not limited to the above example, and various modifications conceived by those skilled in the art are possible.

The estimation unit 230 further identifies sales floor related information for reflecting the acquired customer profile information on the sales floor of the store. The specified sales floor-related information is transmitted to the information presentation device 300 via the transmission unit 250 .

An example of the sales floor-related information is information indicating recommended products to be purchased by a customer who has started holding the product indicated by the identification information at the sales floor. In other words, in response to the acquisition of customer profile information indicating the current psychological state of a customer who has started holding a certain product, it is possible to purchase a product that has a track record of being purchased in this psychological state as a product that matches the customer's current mood. Information for recommendation.

To find products that have been purchased from the psychological state, for example, the deep psychological model shown in FIG. 3B may be traced from right to left. Alternatively, a database may be used in which products can be searched for from combinations of phrases that indicate psychological states, or from customer categories. A recommended product is a product that satisfies more conditions such as a combination of phrases indicating a psychological state and customer classification. After specifying such a recommended product, the estimation unit 230 further specifies sales floor related information. Note that the number of recommended products is not limited to one. Multiple products may be identified as recommended products.

The identification of the sales floor-related information according to this example by the estimation unit 230 is, for example, the identification of the information shown using the advertisement video or audio used in various media for this product, or the video or audio that is appropriately edited. is. Alternatively, it may be information presented using video or audio prepared separately for these media. For example, it may be information related to the recommended product, such as the location or price of the product at the store, and may be information that is highly useful for the customer at the actual store.

The estimation unit 230 identifies sales floor-related information by identifying data such as advertisement images of recommended products in a storage device inside the profiling server 200 or an external server, for example, acquires the data, and displays the information presentation device. 300 (transmission of counter-related information). Alternatively, the estimating unit 230 may process such data or generate such data from information on which the data is based (display location or price at the same store). In the present embodiment, the acquisition of data generated by the estimation unit 230 in this way is also referred to as identification of sales floor related information.

Other examples of sales floor related information will be described later.

The information presentation device 300 acquires the counter-related information specified by the estimation unit 230 from the profiling server 200 . The information presentation device 300 then presents the acquired sales floor-related information to the customer. In the above example, the customer is presented with an advertisement video or the like of a recommended product that the customer is recommended to purchase.

The information presentation device 300 includes a receiving section 310 and an output section 320 .

The information presentation device 300 receives the sales floor-related information transmitted from the profiling server 200 , in the above example, a signal indicating at least one of video and audio indicating recommended products via the receiving unit 310 .

Based on the signal received via the receiving unit 310, the output unit 320 outputs at least one of video and audio indicating the recommended product and presents it to the customer.

Such an information presentation device 300 is carried or worn by a customer who is shopping, for example, and moves in the store with the customer. More specifically, it is provided in a product holder for holding products by customers placing them, such as an in-store shopping basket as shown in FIG. 2A or an in-store cart as shown in FIG. 2B. or in an information terminal such as a smart phone or tablet computer held by the customer as shown in FIG. 2C. Alternatively, the information presentation device 300 may be realized by a digital signage installed in a sales floor of a store as shown in FIG. 2D.

If the information presentation device 300 is a digital signage, the product recommendation information is selectively transmitted from the profiling server 200 to the information presentation device 300 located near the customer to receive information presentation. In this case, the profiling server 200 grasps the position of the customer, for example, by using the information indicating the position in the store further transmitted from the product identification information acquisition device 100, or by estimating from the product information based on the identification information and the time. be done.

The shopping basket shown in FIG. 2A includes a liquid crystal or EL (electroluminescence) display 321 as an example of the output unit 320 . The cart shown in FIG. 2B includes a liquid crystal or EL display 322a and a speaker 322b as an example of the output unit 320. FIG. The information terminal shown in FIG. 2C includes a display 323a and a speaker 323b as an example of the output unit 320. FIG. The digital signage shown in FIG. 2D includes a liquid crystal or EL display 324a and a speaker 324b as an example of the output unit 320. FIG.

Via these output units 320, the customer is presented with information indicating recommended products using at least one of video and audio.

[2. Procedure up to presentation of sales floor-related information to customers]
Next, the procedure of an example of the operation of the information presentation system 10 configured as described above, which operates in an actual store, from when a customer selects a product until the customer is presented with sales floor-related information will be described as an example. will be used to explain. FIG. 4 is a sequence diagram for explaining this procedure. The procedure shown in this sequence diagram starts when the sensor 110 becomes ready to acquire product identification information from the product, such as when the customer holds the barcode of the product picked up by the customer over the sensor 110 to start holding the product. do.

In the explanation of the procedure below, the operation by the function of each component of the product identification information acquisition device 100 will be shown as the operation of the product identification information acquisition device 100 . Similarly, the operation by the function of each component of the profiling server 200 is shown as the operation of the profiling server 200 , and the operation by the function of each component of the information presentation device 300 is shown as the operation of the information presentation device 300 .

First, the product identification information acquisition device 100 acquires product identification information from a product that a customer starts holding (step S401). The acquired product identification information is transmitted to the profiling server 200 (step S402). FIG. 5 is a diagram for explaining the concept of the procedure from step S402 to step S403.

The product identification information acquired by the product identification information acquisition device 100 is transmitted to the profiling server 200 . The character string in the left balloon in FIG. 5 is an example of log data containing a series of product identification information acquired and transmitted by the product identification information acquisition device 100 . The profiling server 200 processes the acquired product identification information to identify the product indicated by the product identification information and which the customer has started holding (step S403), get the data. Purchase candidate information is indicated by the data thus obtained.

The purchase candidate information includes a record in which the product identification code of each product, the product name obtained by collating the product identification code in the database, and the state and time difference of each product are associated with each other.

The state of each product indicates whether the holding of the product of each record has been started or released by the customer. In this example, "hold" indicates the start of holding, and "return" indicates release of holding. For example, if the sensor 110 of the product identification information acquisition device 100 is an RF reader, such product status recognition may be performed by periodically scanning the product placed on the product holder. Alternatively, if the sensor 110 is a barcode reader, the customer may perform an explicit operation such as pressing a predetermined button immediately before reading the barcode of the product to be returned to the shelf. Such once-stored information on "returns" of products is used, for example, to exclude information on products returned by customers from information used as materials for selecting recommended products.

The time difference indicates the elapsed time from the time when the customer first started holding one of the products to the time when the customer subsequently started holding another product or released the held product. This time calculation is performed based on, for example, product identification information. More specifically, for example, it is performed based on the time when the product identification information is acquired by the product identification information acquisition device 100 or transmitted.

Such time difference information has various uses. For example, it may be used to narrow down purchase candidate information used to acquire customer profile information indicating the psychological state of each customer. This application is described below with an example. In addition, it may be used to grasp the outline of the moving route of each customer in the store. In addition, if a certain amount of information is collected from the shopping behavior of multiple customers, it can be statistically grasped, the tendency of the order of product selection in shopping behavior, or the time elapsed after the start of shopping behavior It can be used to estimate recommended products based on changing tendencies of products that are likely to be purchased.

Note that the time difference information is not limited to the illustrated example, and may be, for example, the time difference from the start or release of holding of the product indicated in the previous record.

Further, the purchase candidate information may not include the time difference information. However, even if the time difference information is not included, the purchase candidate information data indicates the time order of identification of each product by the product identification information acquisition device 100, that is, the order of occurrence of the start or cancellation of holding of the product by the customer. may be Such an order is indicated, for example, by the order in which records are arranged or the number assigned to each record.

After acquiring the purchase candidate information, the profiling server 200 acquires customer profile information indicating the customer's psychological state estimated using the deep psychological model 240 based on the purchase candidate information (step S404).

Next, the profiling server 200 identifies sales floor-related information for reflecting the acquired customer profile information on the sales floor of the actual store, and transmits the information to the information presentation device 300 (steps S405 and S406).

The information presentation device 300 presents the received counter-related information to the customer (step S407). In the above example, at least one of video and audio including recommended product information indicated by the received sales floor related information is output.

FIG. 6 is an example of a screen presented to the customer by the information presentation device 300 in step S407. In this example, an image of a certain drip type coffee product is shown as a recommended product. Such recommended products are displayed on the information presentation device 300 in the following flow, for example.

First, a customer who is shopping in a store picks up a certain chocolate product and causes the sensor 110 to read it (step S401). The identification information read by the sensor 110 is transmitted to the profiling server 200 (step S402).

In the profiling server 200, this product is identified using this identification information (step S403), and purchase candidate information is obtained. Next, using the deep psychological model 240, customer profile information indicating the current psychological state estimated for the customer purchasing the chocolate indicated by the purchase candidate information is obtained (step S404).

Further, in the profiling server 200, sales floor-related information for reflecting the customer profile information on the sales floor of the store is specified (step S405). In the above example, the drip coffee product that has been purchased in the psychological state of the customer who purchases this chocolate is specified as the recommended product, and the sales floor related information indicating this product is transmitted to the information presentation device 300 (step S406).

The information presentation device 300 presents the sales floor-related information to the customer holding the chocolate.

In this way, the information presentation system 10 can provide information for recommending the purchase of a product according to the customer's psychological state by using information on the customer's current shopping behavior in the store. .

The products recommended for purchase as described above may be selected from all products handled in the store, or may be selected from some products such as advertised products.

Another example of specifying the sales floor-related information to be presented to the customer is specifying the information indicated by an image and/or voice in accordance with the estimated psychological state of the customer. The sales floor-related information in this case does not have to particularly indicate specific products. For example, when it is estimated that the customer is in a psychological state of "wanting to relax" using the deep psychological model 240 based on the product identification information, the estimation unit 230 determines the possibility that the person in this psychological state is interested. The sales floor related information is specified by specifying data such as an image with a high value in a storage device inside the profiling server 200 or an external server. Then, this data is transmitted from the profiling server 200 to the information presentation device 300 (transmission of sales floor-related information), and the information presentation device 300 outputs images and the like to present the sales floor-related information to customers in the sales floor.

Each mental state and the video or audio presented to the person in each mental state are, for example, pre-associated and managed in a database. This association may be made, for example, based on the results of a rating grid method performed on video or audio.

Also, the sales floor related information may be information indicating both the above-mentioned recommended products and items other than specific products. That is, the information presentation device 300 may simultaneously present to the customer both the image of the product and the image of the product other than the product according to the psychological state of the customer estimated by holding the product.

The above is the basic operation of the information presentation system 10 for recommending products to the customer based on the customer's current shopping history in the actual store. For example, the series of steps in FIG. 4 may be performed each time the customer picks up a product and causes the sensor 110 of the product identification information acquisition device 100 to read it.

As a result, it is possible to propose products that are likely to match the psychological state of the customer, or to provide images, etc., based on the products that the customer is likely to purchase while shopping at the sales floor. Therefore, it is possible to further improve the quality of the customer's shopping experience at the store, for example, to obtain a greater sense of accomplishment for the purpose of shopping. At the same time, further increases in store sales can be expected.

Also, in the above example, one recommended product is selected for the start of holding one product, but the operation of the information presentation system 10 is not limited to this example. As described above, the customer's state of mind may be estimated based on the number of items the customer has started to hold, and the sales floor related information may be sent once. FIG. 7 is a sequence diagram for explaining the procedure of such an operation example of the information presentation system 10. As shown in FIG.

In the sequence diagram of FIG. 7, steps S701 to 703 are added between steps S403 and S404 as compared with the sequence diagram of FIG. However, steps S701 to S703 are the same procedures as steps S401 to S403 in terms of content and subject of action. Therefore, description of steps S701 to S703 is omitted.

The profiling server 200 uses the deep psychological model 240 to estimate the customer's psychological state based on the information on the multiple products that the customer has started to hold. identified. Then, the profiling server 200 transmits sales floor-related information indicating this product. The information presentation device 300 receives this product recommendation information and presents it to the customer.

Further, the estimation of the customer's psychological state may be performed based on purchase candidate information indicating products that satisfy a predetermined condition among the products held by the customer. Predetermined condition here refers to the purchase condition used for the customer's psychological state based on the timing of the start of holding the product in order to accurately estimate the customer's psychological state, which may change with the passage of time or the progress of shopping behavior. It is a condition for selecting candidate information. Therefore, in estimating the customer's psychological state in the profiling server 200, all of the purchase candidate information that has already been acquired for one shopping behavior from the customer's entry to just before checkout may be used, or only part of it may be used. In some cases. The operation of the information presentation system 10 for estimating the psychological state in this way will be described below along with a specific example.

FIG. 8 is a sequence diagram for explaining the procedure of an example of the operation of the information presentation system 10 for estimating a customer's mental state based on purchase candidate information indicating products that satisfy predetermined conditions.

In the operation shown in the sequence diagram of FIG. 8, the product identification information acquirer 100 sequentially acquires four items of product identification information (steps S401A, S401B, S401C, and S401D) and transmits them to the profiling server 200 (step S402A). , S402B, S402C, S402D). Note that step S401C and step S402C are omitted in FIG.

Each time the profiling server 200 acquires product identification information, the profiling server 200 performs product identification and acquires purchase candidate information. The procedure up to this point corresponds to repeating the cycle from step S401 to step S403 in FIG. 4 or 7 four times. Details of each procedure are omitted.

Next, the profiling server 200 selects purchase candidate information indicating a predetermined number of products, in this example, three products, in descending order of the order in which the customer started holding the products, among the purchase candidate information already acquired (step S804). , the customer profile information is acquired using the selected purchase candidate information (step S805). The procedures after step S805 correspond to those after step 404 in FIG. 4 or FIG. 7, and the details of each procedure are omitted. Since the purchase candidate information indicates the order of starting to hold the products, the profiling server 200 can select such purchase candidate information.

In this operational example, customer profile information is obtained using candidate purchase information that indicates products with a later retention start, ie, the customer's current state of mind is estimated. This takes into consideration that the customer's state of mind changes during shopping. In other words, this makes it possible to estimate a more accurate state of mind based on a product that is likely to have been selected in a state of mind close to the current state of mind.

In the above example, purchase candidate information is selected based on the number of products, but purchase candidate information may be selected based on the number of types of products instead of the number. Alternatively, when the number exceeds a certain number, purchase candidate information may be selected based on the number of types. As a result, it is possible to more accurately estimate the state of mind of a customer who purchases a large number of items due to, for example, bulk purchases.

In addition, if the purchase candidate information indicates the time difference or the time when the holding of each item is started, the profiling server 200 can use this time difference or time to select the purchase candidate information. FIG. 9 is a sequence diagram for explaining the procedure of such an operation example of the information presentation system 10. As shown in FIG. Among the procedures of the operation example shown in FIG. 9, the procedures common to the procedures of the operation example shown in FIG. 8 are denoted by common reference numerals. That is, the operation example of FIG. 9 is different in step S904 performed by the profiling server 200, and is otherwise common, so detailed descriptions other than step S904 will be omitted here.

In step S904, the profiling server 200 selects, from among the purchase candidate information already acquired, the customer's holding start time within a predetermined retroactive time period, in this example, within five minutes retroactively from the current time. Select candidate information. As a result, it is possible to avoid using the information of the product whose holding is started in a state of mind that is highly likely to be different from the current state of mind of the customer for estimating the current state of mind.

Note that the starting point of retroactive time is not limited to the current time, and may be, for example, the time when holding of the last product was started. Alternatively, if the holding of the product has not started within a predetermined time from the current time, the start time of holding the last product may be used as the starting point of retroactive time.

Also, the conditions used in the operation examples described with reference to FIGS. 8 and 9 may be used in combination. For example, the profiling server 200 may select purchase candidate information indicating up to three products that have started to be held within five minutes to estimate the customer's state of mind.

Further, the profiling server 200 may use the purchase candidate information used for the customer's psychological state after weighting according to the order in which the products indicated by each purchase candidate information are started to be held. More specifically, the profiling server 200 obtains the customer profile information by using, among the purchase candidate information used for the customer's psychological state, the purchase candidate information indicating the product whose order in which the customer started holding later is weighted higher. may For example, the score of the depth psychology model in FIG. 3C may be used by multiplying a lower coefficient for a product that starts holding earlier. As a result, the state of mind associated with the product whose holding is started closer to the current time is more strongly reflected in the estimation of the current state of mind of the customer.

Alternatively, weighting may be performed according to the length of retroactive time. For example, the coefficient for multiplying the score of the deep psychology model in FIG. 0.6. As a result, the state of mind associated with the product whose holding is started closer to the current time is more strongly reflected in the estimation of the current state of mind of the customer.

Thus far, the information presentation system 10 has been described above using examples. Information presentation system 10 in the present embodiment is not limited to the above example.

For example, what the information presentation device 300 receives as the sales floor-related information may be information indicating the name of a data file such as an image or a location, instead of data such as an image indicating a recommended product. In this case, the information presentation device 300 acquires data such as video using such sales floor related information, and presents the sales floor related information to the customer by reproducing the acquired video or the like. Data such as images may be stored in a storage device included in the information presentation device 300, or may be stored in an external server or the like with which the information presentation device 300 can communicate.

In addition, the product identification information acquisition device 100 may be a group of devices that are installed on walls, ceilings, fixtures, or the like in a store and are capable of sensing a series of customer's shopping behaviors. Specifically, cameras (image sensors) installed at a plurality of locations in the store may be used.

In this case, the customer's behavior, including the start of holding the product, is captured by multiple cameras so that images for identifying the product and the customer are included, and sent to the profiling server 200 . Customers may use their own bags to hold merchandise. The devices may also include other types of sensors, such as RF readers, to obtain information for identifying merchandise or customers in place of or in combination with cameras. That is, in this case, the product identification information acquisition device 100 acquires information for identifying each customer in order to individually grasp the shopping behavior of each customer. This information serves as a substitute for information for identifying the individual product identification information acquisition device 100 . The profiling server 200 further comprises a customer identifier for performing identification of each customer using this information. The profiling server 200 also performs a series of processes while associating each identified customer with the retained or returned product. Also, when a product is purchased, the track record of this purchase may be associated with each customer.

Also, for example, at least one of the product identification information acquisition device 100 and the information presentation device 300 may be provided in a so-called wearable device such as smart glasses worn by the customer. For example, the product identification information acquisition device 100 may be a camera included in smart glasses, and the information presentation device 300 may be a display included in smart glasses.

In addition, the sales floor-related information may be presented to the customer as so-called augmented reality, which is superimposed on the scene inside the store. For example, it may be displayed so that an arrow pointing to the display place of the recommended product can be seen over the aisle. When the customer is within the range where the displayed product can be seen, a frame that seems to surround the product may be displayed.

The purchase candidate information shown in FIG. 5 includes only records of product identification information related to the holding of products during shopping by one customer, but the form of data accumulation is not limited to this. For example, a form in which a plurality of purchase candidate information tables shown in FIG. 5 are connected may be used. In this case, the row with "0s" in the time lag column is understood to be the beginning of the shopping behavior of one customer. Also, each record may contain information for identifying each customer. This information may be acquired, for example, from the customer himself/herself or from the customer's belongings such as a smartphone or membership card, or may be information stored or generated by the product identification information acquisition device 100 used by each customer. good.

(Embodiment 2)
In the information presentation system 10 described above, the product identification information acquisition device 100 is used to collect, in chronological order, information on the start or release of product retention from the shopping behavior of each customer in the store. Among such information, the information on releasing the holding of the product, that is, the information on the "return" of the product can also be used in the profiling server 200 to specify the sales floor related information to be presented to the customer.

First, as described above, it is used to exclude the information on the product returned by the customer from the information used for selecting the recommended product. This makes it possible to obtain customer profile information that more accurately estimates the customer's psychology. Also, customer profile information may be obtained, for example, based on the difference between the returned item and the item whose retention is started thereafter. A more specific example will be described with reference again to FIG. 3C showing an example of the data configuration of the deep psychological model.

Suppose a customer returns an AAA vegetable juice he or she has already kept and begins to keep CCC blended tea. The estimating unit 230 that has acquired the purchase candidate information and return information indicating each product refers to the deep psychological model of FIG. 3C, acquires the scores of these two products, and calculates the score difference for each psychological state. Specifically, it is as follows.

I want to feel happy: 0.6 - 0.0 = 0.6
I want to cheer up: 0.0-0.7=-0.7
I want to relax: 0.9-0.4=0.5
I want to refresh: 0.7-0.6=0.1

Next, the estimating unit 230 generates customer profile information such that the mental state of "I want to feel happy", which indicates the largest value among the calculated differences, is treated as the estimated current mental state of this customer. get.

Thereafter, the estimating unit 230 identifies and transmits to the information presenting unit 230 the sales floor-related information indicating the recommended product for the customer who is in the state of mind “I want to feel happy”.

The behavior of reselecting a product as described above may reflect, for example, the customer's reconfirmed intention to select a product that matches the current mood or physical condition. In this way, by using the return information generated by canceling the holding of the product, it is possible to estimate the psychological state that is the reason why the customer selected the product for which holding was started.

In the above example, the customer's state of mind for choosing the product was estimated based on the largest value among the differences, but a plurality of values, such as the largest value and the next largest value, may be used.

Also, the scores of multiple types of products that started to be held after the products were returned may be used. In addition, as described above, the product for which the score difference is calculated may be selected based on the category of the returned product and the product for which holding is newly started. In the above example, since all the categories are beverages, "CCC blended tea" is selected as a target for calculating the difference. However, in the case of detergents other than "CCC blended tea", the difference need not be taken. In addition, the products for which the score difference is calculated may be limited to products that have been returned and started to be held within a predetermined period of time.

In this way, the profiling server 200 acquires from the product identification information acquisition device 100 the return information about the product whose retention has been released, and at least the purchase candidate information about the product that the customer has started to hold after the return and the return information. Based in part, customer profile information may be obtained.

(Other embodiments)
In each of the above-described embodiments, the explanation is centered on the fact that the customer's mental state when selecting a product differs from product to product. There may also be trends of change during the time of day. For example, the psychological state of customers who buy a certain product in the morning or evening has a strong tendency to want to relax, while the psychological state of customers who buy a product in the afternoon has a strong tendency to want to be energetic. Ascertained by analysis.

In view of this point, among the sales floor-related information output by the profiling server 200 and presented to the customer by the information presentation device 300, the information indicating the recommended product, for example, even if it is an advertisement for the same product, There may be changes in the appeal to

In addition, in the above embodiment, the customer is not presented with the counter-related information until each customer starts holding the product.

However, it is known that each actual retail store has a sales trend of products different from that of other stores, and even a single store has a sales trend of products depending on the time of day. In consideration of this point, even if a customer who newly entered the store is presented with the sales floor related information presented to other customers who were in the sales floor of this store at that time or within a predetermined retroactive time good.

As a result, each customer can be presented with sales floor-related information in accordance with their psychological state from an early stage of their shopping behavior, thereby further improving the quality of their shopping experience. As a result, it leads to an increase in sales for the store.

In addition, when the purchase candidate information used for estimating the psychological state is selected in light of the conditions regarding the start of holding the product as described above, if there is no product that satisfies the condition, it is presented to other customers as described above. The displayed sales floor related information may be presented.

Further, in the above embodiments, each component may be implemented by dedicated hardware or by executing a software program suitable for each component. Each component may be implemented by a program execution unit such as a CPU (central processing unit) or processor reading and executing a software program recorded in a recording medium such as a hard disk or semiconductor memory. Here, the software program that implements the profiling server of the above embodiment is the following program.

That is, the program causes the computer to acquire the identification information from the product identification information acquisition device that acquires the identification information for identifying the product from the product that the customer starts to hold while shopping at the physical store, and Acquire the result obtained by identifying the product using the identification information as purchase candidate information, acquire customer profile information indicating the customer's psychological state estimated based on the purchase candidate information, and acquire the customer profile information at the actual store. to execute processing for acquiring sales floor-related information to be reflected in the sales floor.

Although the information presentation system according to one or more aspects has been described above based on the embodiment, the present invention is not limited to this embodiment. As long as they do not deviate from the gist of the present invention, various modifications conceived by those skilled in the art may be included in the scope of the present invention.

INDUSTRIAL APPLICABILITY The present invention can be used in a system that provides a customer or a store manager with information based on the behavior of a customer who is shopping in a store and holds products as purchase candidates.

10 information presentation system 100 product identification information acquisition device 110, 111, 112, 113 sensor 120 transmission unit 200 profiling server 210 reception unit 220 identification unit 230 estimation unit 240 deep psychological model 250 transmission unit 300 information presentation device 310 reception unit 320 output unit

Claims (11)

A product identification information acquisition device that acquires identification information for identifying a product from each of a plurality of products held by a customer who is shopping in a physical store;
A customer who obtains a result obtained by identifying each of the plurality of products using the identification information as purchase candidate information, and indicates the customer's psychological state estimated based on at least a part of the purchase candidate information. a profiling server that acquires profile information and uses the customer profile information to identify sales floor- related information of the physical store;
An information presentation device that acquires and presents the sales floor related information ,
The profiling server,
Among the purchase candidate information, the customer profile information is obtained by giving a higher weight to the purchase candidate information indicating the product whose order in which the customer started holding is later.
Information presentation system. The profiling server,
Acquiring the customer profile information using purchase candidate information indicating a predetermined number or types of products from the purchase candidate information in which the customer started to hold the product last.
The information presentation system according to claim 1. The profiling server,
Acquiring the customer profile information by using the purchase candidate information that indicates a product that the customer started holding within a predetermined retroactive time from the purchase candidate information;
The information presentation system according to claim 1 or 2. The profiling server,
After the customer enters the physical store and before starting to hold the plurality of products,
In order to present to the customer other sales floor-related information that has been specified in order to reflect in the sales floor customer profile information indicating the psychological state of other customers who have been in the sales floor within a predetermined time from the current time The information presentation system according to any one of claims 1 to 3 , wherein the information is transmitted to an information presentation device. The sales floor related information indicates products that have been purchased in the psychological state,
The information presentation system according to any one of claims 1 to 4 , wherein the information presentation device presents the sales floor-related information to the customer at the sales floor of the physical store. The sales floor-related information is information indicated by at least one of an image and a sound associated with the psychological state,
The information presentation system according to any one of claims 1 to 5 , wherein the information presentation device presents the sales floor-related information by presenting at least one of the image and sound to the customer at the sales floor of the physical store. . The product identification information acquisition device further detects release of holding of the product by the customer and recognizes the product,
The profiling server,
When the return information about the product whose retention has been released is obtained from the product identification information acquisition device, the customer profile information is based on at least a part of the purchase candidate information about the product that the customer has started to retain and the return information. The information presentation system according to any one of claims 1 to 6 . 8. The profiling server acquires the customer profile information using a deep psychological model created in advance by the evaluation grid method (registered trademark) targeting each product sold at the physical store. The information presentation system according to any one of the items. The deep psychological model includes a deep psychological model individually corresponding to the sex and age of the customer sample,
The profiling server,
Acquiring personal attribute information indicating at least one of the customer's sex and age,
9. The information presentation system according to claim 8 , wherein customer profile information indicating said psychological state estimated using said deep psychological model according to at least one of sex and age indicated by said personal attribute information is acquired. 10. The information presentation system according to any one of claims 1 to 9 , wherein the product identification information acquisition device is provided in a product holder for holding the product by placing the product by the customer. 11. The information presentation device according to any one of claims 1 to 10 , wherein the information presentation device includes at least one of an information terminal carried or worn by the customer in the physical store and a digital signage installed in the physical store. information presentation system.

Images