Information presentation system, information presentation method, and program

Abstract

To provide a system to present information about a customer or a product obtained from the purchase behavior of the customer at an actual store.SOLUTION: An information presentation system 10 comprises: a data acquisition part 220 that acquires time-series purchasing data of a customer purchasing in an actual store from multiple cameras installed in the store; an information generating part 230 that acquires a time interval between the keeping occurrence of a first product due to the customer and the return occurrence of a second product different from the first product and keeping product information indicating respectively the first and the second products, from the time-series purchasing data of the customer, determines a degree of competition between the first and the second products based on the time interval and the keeping product information, and generates analytical information based on the keeping product information and the determined result; and a data output part 250 that outputs the analytical information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique for presenting information about customers or products in a brick-and-mortar retail store. [Background technology]

[0002] A technique has been proposed that utilizes time-series information on the behavior of customers shopping at a retail store such as a supermarket, the time-series information being in accordance with order or time (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 4620807 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the information disclosed in Patent Document 1 does not allow for the creation of a store that is more likely to be chosen by customers, by improving the quality of the customer's shopping experience by reflecting the customer's behavior or psychological state in the sales floor.

[0005] Therefore, the present invention provides an information presentation system that presents to store managers information that can be used to create a sales floor, reflecting the behavior or psychological state of customers. [Means for solving the problem]

[0006] An information presentation system according to one embodiment of the present invention includes a data acquisition unit that acquires time-series shopping data of customers shopping in a physical store from a plurality of cameras installed in the store, an information generation unit that acquires from the time-series shopping data the time interval between the occurrence of the customer retaining a first product and the occurrence of the return of a second product different from the first product, and retained product information indicating the first product and the second product, determines the degree of competition between the first product and the second product based on the time interval and the retained product information, and generates analytical information based on the retained product information and the result of the determination, and a data output unit that outputs the analytical information.

[0007] In addition, an information presentation system according to one embodiment of the present invention includes a data acquisition unit that acquires time-series shopping data regarding the retention of products by customers over time while shopping at a physical store, an information generation unit that acquires shopping time spent by the customer at the physical store based on the time-series shopping data, acquires customer classification information indicating a classification of the customer regarding the degree of urgency based on a relationship between the shopping time and a first threshold, and generates store analysis information based on the acquired customer classification information and retained product information indicating products retained or returned by the customer in the time-series shopping data, and a data output unit that outputs the store analysis information.

[0008] These comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, or may be realized by any combination of a system, a method, an integrated circuit, a computer program, and a recording medium. Effect of the Invention

[0009] The information presentation system of the present invention can present information that enables the behavior or psychological state of a customer to be reflected in a sales area. [Brief description of the drawings]

[0010] [Figure 1]FIG. 1 is a block diagram showing a configuration of an information presentation system according to an embodiment. [Figure 2A] FIG. 2A is a diagram showing an example of a product holder equipped with a reader according to an embodiment. [Figure 2B] FIG. 2B is a diagram showing another example of a product holder equipped with a reader according to an embodiment. [Figure 2C] FIG. 2C is a diagram illustrating an example of a reader according to an embodiment. [Diagram 3] FIG. 3 is a diagram for explaining the concept of the process from reading of product-specific information to acquisition of time-series shopping data in the information presentation system. [Figure 4] FIG. 4 is a flowchart showing an example of a procedure of processing by the information generating unit included in the information presentation system. [Diagram 5] FIG. 5 is a diagram showing an example of data output by a data output unit included in the information presentation system. [Figure 6] FIG. 6 is a flowchart showing an example of a procedure of processing by the information generating unit included in the information presentation system. [Figure 7] FIG. 7 is a flowchart showing an example of a processing procedure performed by the information generating unit included in the information presentation system. [Figure 8] FIG. 8 is a flowchart showing an example of a procedure of processing by the information generating unit included in the information presentation system. [Figure 9A] FIG. 9A is a diagram for stating a conflict eligibility condition. [Figure 9B] FIG. 9B is a diagram for stating conflict ineligible conditions. [Figure 10A] FIG. 10A is a diagram showing the layout of products by department in a certain store. [Figure 10B] FIG. 10B is a diagram showing a part of the time-series shopping data, which shows the departments of held products and the time intervals at which the products were held. [Figure 11] FIG. 11 is a flowchart illustrating an example of a procedure of processing by the information generating unit included in the information presentation system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The present inventors have found that the above-mentioned problems occur with respect to the examples of using information described in the "Background Art" section.

[0012] In order to solve such problems, an information presentation system according to one embodiment of the present invention includes a data acquisition unit that acquires time-series shopping data, which is data regarding the retention of products by customers over time while shopping in a physical store, an information generation unit that acquires classification information indicating classifications of customers or products based on the time-series shopping data and generates store analysis information based on the acquired classification information and retained product information indicating products retained or returned by customers in the time-series shopping data, and a data output unit that outputs the store analysis information as data that can be used by operators of the physical store.

[0013] This makes it possible to use, as information about each product, information indicating classification of customers or products based on an analysis of the behavior of customers who have purchased or considered purchasing the product.

[0014] Such classification reflects the state of mind of the customer, etc., that can be read from their behavior. Therefore, for example, a store manager can obtain information to better understand the state of the customers in his store, which he wants to reflect in the sales floor. A sales floor created using such information can provide, for example, a highly convenient shopping experience for customers, and can bring about increased sales for the store manager.

[0015] For example, the store analysis information may include classification information indicating a classification of the customer with respect to the degree of urgency of the customer. Such classification may be a quantitative classification for each time span, or a qualitative classification based on statistically obtained knowledge, such as a classification with respect to the degree of urgency such as "customers in a hurry," "customers with plenty of time," and "intermediate customers."

[0016] For example, the information generating unit may obtain shopping time, which is the time that a customer spends shopping at a physical store, from the time-series shopping data, and obtain classification information based on the shopping time.

[0017] For example, the information generating unit may acquire the classification information by determining a classification for the customer based on the magnitude relationship between the shopping time and a first threshold value.

[0018] For example, the information generating unit may obtain the retention start intervals at which a customer starts retaining each of a plurality of items of merchandise from the time-series shopping data, and obtain the classification information based on the retention start intervals.

[0019] For example, the information generating unit may acquire the classification information by determining a classification for the customer based on the magnitude relationship between the retention start interval and the second threshold value.

[0020] The time a customer spends shopping or the interval between picking up products varies depending on whether the customer is in a hurry or not. By understanding the product trends for each of these customer categories and reflecting this in product placement or guide displays, the store manager can create a sales floor that allows customers in a hurry to shop smoothly, for example.

[0021] Also for example, the store analysis information may include classification information indicating classifications of products that customers were unsure about whether to keep or not, or classifications of products that customers had difficulty locating.

[0022] For example, the information generation unit may obtain from the time-series shopping data the elapsed time before holding, which is the time from a specified action by a customer to the start of holding the product, obtain sales of the held product, and obtain the classification information indicating the classification of the product based on the elapsed time before holding and the obtained sales.

[0023] For example, when the pre-holding elapsed time exceeds a third threshold, the information generating unit may acquire the classification information by determining a classification for the product based on whether the sale is greater than or smaller than a fourth threshold.

[0024] For example, when the sales exceed a fourth threshold, the information generating unit may acquire classification information by determining that the product is classified as a product that the customer is unsure whether to keep or not.

[0025] For example, when the sales are equal to or less than the fourth threshold, the information generating unit may acquire the classification information by determining that the classification of the product is a product whose location took a long time to identify.

[0026] The time it takes a customer to put a certain product in the shopping cart can vary depending on the customer's state. For example, if the customer is hesitant before deciding to purchase the product, the time will be longer. The same is true if the customer has the intention to buy the product but has difficulty finding it on the sales floor. In such cases, each product is classified based on the customer's state and presented to the store manager, who then reflects this in the product layout or POP (Point Of Purchase), etc., allowing customers to obtain the information they need to select a product or creating a sales floor that makes it easy to find products. Furthermore, for the store, this reduces missed sales opportunities.

[0027] Also, for example, the store analysis information may include the classification information indicating the classification of a product that the customer is unsure whether to purchase or return after starting to hold the product.

[0028] For example, the information generating unit may obtain, from the time-series shopping data, retained product information indicating the occurrence of product returns by customers and the products, and obtain classification information indicating the classification of the products based on the retained product information.

[0029] For example, the information generation unit may obtain classification information by calculating a return rate for a product based on the retained product information, and determining a classification for the product regarding the degree to which a customer is unsure about whether or not to purchase the product based on the return rate.

[0030] In the past, store managers were not aware of the occurrence of customers releasing their hold on products while shopping (returning the products to the sales floor). The information presentation system in the present disclosure is capable of presenting such information to store managers, who can then use this information to plan sales strategies, including product lineups and pricing, and increase sales. At the same time, for customers, the store is able to offer products that are more attractive in terms of product lineup or price.

[0031] Furthermore, for example, the store analysis information may include classification information indicating classification of two or more products with respect to the degree of competition between the products.

[0032] For example, the information generation unit may obtain from the time-series shopping data the time interval between the occurrence of a customer retaining a first product and the occurrence of the return of a second product different from the retained product, as well as retained product information indicating the first product and the second product, and obtain classification information based on the retained product information.

[0033] For example, the information generation unit may obtain the classification information by determining a classification regarding the degree of mutual competition between the first product and the second product based on the relationship between the time interval and the sixth threshold and the held product information.

[0034] For example, the information generation unit may obtain the department of the first product and the department of the second product using product identification information indicating the first product and the second product, respectively, and information indicating the department of products handled in a physical store, and determine a classification regarding the degree of mutual competition between the first product and the second product based on the relationship between the time interval and the sixth threshold value, and the similarity relationship between the department of the first product and the department of the second product.

[0035] Until now, it has been difficult for store managers to understand how customers consider competing products on the sales floor, even when the products are known to be in a competitive relationship. The information presentation system disclosed herein can obtain such information from the turnover of products held by customers and present it to store managers. Store managers can use such information to discover unknown competitive relationships between products and competitive relationships between products that are not one-to-one. Store managers can use such information on product competitive relationships in product lineups, product placement, or presenting advertisements customized for each customer. Customers can have more opportunities to learn about new products in stores, expanding the range of product choices.

[0036] Also, for example, the store analysis information may include classification information indicating a classification of customers as to whether or not they are group customers.

[0037] For example, the information generation unit may obtain from the time-series shopping data the time interval between the occurrence of a customer holding a first product and the occurrence of the occurrence of holding a second product different from the first product, and held product information indicating the first product and the second product, respectively, calculate the held product information indicating the first product and the second product, respectively, and the travel time required between the sales floor of the first product and the sales floor of the second product in a physical store, and if the time interval is less than or equal to the travel time, classify the customer as a group customer, thereby obtaining the classification information.

[0038] This allows stores to obtain information that identifies products that are frequently purchased by groups of customers, which was previously difficult to grasp. Store managers can use this product information to improve their product lineup, product placement, or to present advertisements in stores that are customized for each customer.

[0039] The information provided by the information presentation system of the present disclosure may be used not only by store managers but also by product manufacturers. For example, for products that are often difficult to choose, such information can be used to renew the packaging to differentiate them from competing products, to develop sales promotion methods, or to develop new products.

[0040] In addition, these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, or may be realized by any combination of the system, method, integrated circuit, computer program, or recording medium.

[0041] Hereinafter, the embodiments will be described in detail with reference to the drawings. The following embodiments are all comprehensive or specific examples. The numerical values, shapes, materials, components, arrangement and connection forms of the components, steps, and order of steps shown below are merely examples and are not intended to limit the present invention. In addition, among the components in the following embodiments, components that are not described in the independent claims showing the highest concept are described as optional components.

[0042] (Embodiment) [1. Configuration example] An information presentation system according to an embodiment will be described with reference to FIG. 1 to FIG. 2C.

[0043] FIG. 1 is a block diagram showing a configuration of an information presentation system according to an embodiment.

[0044] The information presentation system 10 in the embodiment is a brick-and-mortar self-service store (hereinafter simply referred to as a store) in the retail industry, such as a supermarket or convenience store, and based on information about a customer's behavior while shopping, presents information that can be used to create a sales floor that reflects the customer's behavior or psychological state, for example, to the manager of the store.

[0045] The self-service method here is one that is widely adopted in retail stores such as those mentioned above, and should be understood to basically satisfy the following conditions. First, the customer can know the price of each product through a price tag or a predetermined price setting such as a uniform price for all products. Second, the customer can freely select the product he or she wishes to purchase from the products on display, and can keep the selected product by placing it in a basket, cart, tray, or the like provided by the store, or can return the selected product to the sales floor and cancel the selection. Third, the customer can pay for the product he or she wishes to purchase by taking the product he or she has kept to a cash register located near the exit or the like.

[0046] However, the concept 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 a specific example of a situation in which the information presentation system of the present invention is used, and are not intended to limit the present invention. For example, the product to be purchased may be held in a bag or the like brought by the customer, or may simply be held by hand. Furthermore, payment may be made by a method that does not use a checkout station equipped with a cash register. Furthermore, for any of the above conditions, cases in which assistance or management by a store clerk is involved are also included in the concept of the self-service method in this disclosure.

[0047] The information presentation system 10 includes a reader 100 and a store analysis server 200 .

[0048] The reader 100 obtains product identification information indicating products held by a customer during shopping.

[0049] The reader 100 includes a sensor 110 and a transmitter unit 120 .

[0050] The sensor 110 acquires product identification information indicating a product held by a customer while shopping in a store.

[0051] The transmission unit 120 transmits the product identification information acquired by the reader 100 to the store analysis server 200, which will be described later.

[0052] Such a reader 100 is carried or worn by a customer while shopping, and moves around the store with the customer. More specifically, it is realized as a device provided in an apparatus (hereinafter referred to as a product holder) on which a customer places and holds products, such as a shopping basket for use in a store as shown in FIG. 2A or a cart as shown in FIG. 2B, or on an information terminal such as a smartphone or tablet computer that is separate from the product holder and is held by the customer as shown in FIG. 2C. However, in FIG. 2B, a part of the frame below the cart and a part including the wheels are not shown. Another example of a product holder is a tray.

[0053] By providing the reader 100 on the product holder, it is possible for a customer shopping to obtain information for identifying a product more naturally and with higher certainty.

[0054] The reader 100 provided in the shopping basket shown in Fig. 2A includes a sensor 111 as an example of the sensor 110. The reader 100 provided in the cart shown in Fig. 2B includes a sensor 112 directed toward a location where an item is placed as an example of the sensor 110. The reader 100 realized on an information terminal shown in Fig. 2C includes a sensor (image sensor) 113 constituting a built-in camera as an example of the sensor 110.

[0055] The sensor 110 may be, for example, an optical sensor for reading a barcode attached to a product. Alternatively, the sensor 110 may be, for example, an RF reader for reading an RFID (Radio Frequency Identification) from an RF (Radio Frequency) tag attached to a product. The barcode or RFID indicates a product identification code such as a JAN (Japan Article Number) code. Alternatively, the sensor 110 may be an image sensor for acquiring an external image of the product. The information indicated by the barcode or RFID and the information indicated by the external image of the product are each an example of product identification information in this embodiment.

[0056] For example, every time a customer selects a product at a sales floor, the customer holds the barcode on the product at the sensor 110 so that the reader 100 can read it, and then places the product in the shopping basket (start of holding the product). In other words, the reader 100 sequentially reads product identification information indicating the product held by the customer in response to the customer's operation.

[0057] Furthermore, when a customer returns an item that was once placed in the shopping cart to the sales floor, the customer also has the barcode read by reader 100. In this case, the customer performs an operation to make reader 100 recognize that the barcode of the item to be returned is to be read, such as by pressing a button (not shown) on reader 100, and then has reader 100 read the barcode.

[0058] If the sensor 110 of the reader 100 is an RF reader, it may periodically scan items placed on the item holder and recognize retention and return of the item by comparing the results with those obtained by the previous scan.

[0059] The product identification information read by the reader 100 in this manner can also be used for settling the price of the products. For example, the product identification information is sent from the reader 100 to a cash register at a checkout counter in a store, and the cash register shows the total price of the products indicated by the product identification information to the customer. This eliminates the need for a store clerk to use a scanner to input the barcodes of each product into a POS (Point Of Sales) register, as seen in conventional checkout counters. Alternatively, the product identification information may be confirmed when the customer leaves the store and sent to the store's sales management system, and the payment may then be made by credit card or other payment method.

[0060] Even in conventional POS systems, sales information obtained through the POS register for settlement allows store sales by time period, product trends, and associations between products and the gender and age of purchasers to be understood and used for store management. In the information presentation system of the present disclosure, product identification information is also used for purposes other than settlement. Details will be described later.

[0061] The acquired product identification information is wirelessly transmitted to the store analysis server 200 by a transmitting unit 120 (not shown in FIGS. 2A to 2C) provided in a product holder such as a shopping basket.

[0062] A series of processes from reading to transmitting such product identification information is performed by a processor (not shown) included in the reader 100 reading and executing a predetermined program stored in a storage device (not shown). If the information terminal shown in Fig. 2C belongs to a user, the user may install a program (app) provided by the store in the information terminal to transmit the product identification information to the store analysis server 200, start it, and use it in the store.

[0063] The above-mentioned reader 100 is realized as a product holder or an information terminal that is used by each customer throughout their shopping experience, and the product-specific information transmitted by the reader 100 indicates chronological information regarding each customer's product holdings.

[0064] The store analysis server 200 acquires time-series data, which is data on the retention of products by customers over time, based on the product identification information acquired from the reader 100. The store analysis server 200 that processes such information is realized, for example, by a server computer installed in the store, a cloud server outside the store, or, if the store is one of a chain store, a host computer used by the headquarters of the chain store, or a combination of these (hereinafter referred to as a server computer, etc.).

[0065] The store analysis server 200 includes a receiving unit 210, a data acquisition unit 220, an information generation unit 230, a store master 240, and a data output unit 250 as functional components that are realized by a processor in the above-mentioned server computer or the like reading and executing a program from a storage device.

[0066] The store analysis server 200 acquires the product identification information transmitted from the reader 100 via the receiving unit 210.

[0067] The data acquiring unit 220 acquires data on product holdings based on the product identification information acquired by the receiving unit 210. As described above, the product identification information indicates information on product holdings of each customer in chronological order, and the data on product holdings is data on product holdings of each customer in chronological order. Fig. 3 is a diagram for explaining the concept from reading the product identification information to acquiring the chronological shopping data in the information presentation system 10.

[0068] The product identification information acquired by the reader 100 is transmitted to the store analysis server 200. The character string in the speech bubble on the left in Fig. 3 indicates log data including a series of product identification information acquired and transmitted by the reader 100. The data acquisition unit 220 acquires time-series shopping data such as that illustrated in the speech bubble on the right in Fig. 3, which indicates in chronological order the products that the customer has started to keep or returned, as indicated in the acquired product identification information.

[0069] The time-series shopping data in this example includes, as records associated with each other, the product identification code of each product included in the product identification information, the product name acquired by the data acquisition unit 220 by checking the product identification code against a database (the product master included in the store master 240), the state of each product, and the time difference of the occurrence of the state. The product identification code or product name is an example of the retained product information in this embodiment.

[0070] In addition, when the product identification information is an external appearance image of the product, for example, the data acquisition unit 220 may acquire the product name by performing character recognition on this image, or by performing image recognition using a model obtained by machine learning.

[0071] The status of each product in the time-series shopping data indicates whether the customer has started to hold the product in each record or released it. In this example, "hold" indicates the start of holding, and "return" indicates the release of holding.

[0072] The time difference indicates, for example, the amount of time that has elapsed from the time a customer first starts holding any one of the products on the sales floor until the customer subsequently starts holding or releases the product. This time is calculated, for example, based on the product identification information. For example, the reader 100 attaches a timestamp of the time when the product identification information is read to the product identification information that is sent to the store analysis server 200. The data acquisition unit 220, which receives the product identification information via the receiving unit 210, acquires this time difference based on the timestamp. This time difference is included in the "time series" item of the time series shopping data as chronological information on the data regarding the holding of products.

[0073] The format of the time-series information is not limited to the time difference as shown in the figure. For example, the starting point of the time difference may be the time difference from the start or release time of the product holding indicated in the immediately preceding record, or the actual time when the product holding started or released. In addition, in the case of a time difference, the starting point may be a time earlier than the customer first picking up any product, for example, the time when the product holder starts holding the product or the time when the reader 100 is started. In this case, the reader 100 is provided with a switch or a sensor for using such a time as the starting point of the time difference. In addition, in the case where an information terminal separate from the product holder is used as the reader 100, the starting point of the time difference may be the time when an app that causes the information terminal to function as the reader 100 is started, or the timing of the user checking in to the store using this app.

[0074] The time-series shopping data thus acquired is then subjected to processing by the information generating unit 230 .

[0075] The information generation unit 230 acquires classification information indicating classification of customers or products based on the time-series shopping data, and generates store analysis information based on the acquired classification information and retained product information indicating products retained or returned by customers in the time-series shopping data.

[0076] The classification of customers or products based on time-series shopping data is a classification of the behavior of customers while shopping in a physical store, or the psychological state reflected in the behavior. Such classification cannot be obtained by a POS system that relies on the information at the time of registering sales results in a cash register. In addition, it goes further than the time-series information shown in Patent Document 1, and is useful for stores to further improve sales, efficiency, etc. of the store through improvement of customer satisfaction, convenience, etc. Details of the processing procedure for such classification and generation of store analysis information will be exemplified in the explanation of the operation of the information presentation system 10 described later.

[0077] The store analysis information generated by the information generating unit 230 is output by the data output unit 250 as data usable by the store manager. The data usable by the store manager is, for example, data showing the correlation between the above-mentioned classifications and products, which the store manager can use to change and measure the effectiveness of the product lineup, product arrangement and display, display guidance, or sales promotion measures.

[0078] The representation format of the output data is not limited, and various formats such as data tables, lists, graphs, maps, etc. can be used, and the data is output as a data file that can be displayed on a monitor or mobile terminal connected to the information presentation system 10, and can be printed as necessary. This data file is stored in a storage device provided in, for example, a server computer that realizes the information presentation system 10. The store manager can access and use the data file at any time.

[0079] The store master 240 is a collection of basic information about the brick-and-mortar store that uses the information presentation system 10, and is stored in a storage device provided in a server computer or the like that realizes the information presentation system 10. The store master 240 also includes a product master and a sales floor master.

[0080] The product master is a collection of information on products handled in a physical store, including, for example, the product code, product name, department (category), etc. The sales floor master includes, for example, information on product placement and shelf allocation in a physical store.

[0081] The store master 240 is referenced by the data acquisition unit 220 and the information generation unit 230, which are realized by a processor executing a predetermined program in the information presentation system 10, and is used to acquire and generate information. Details will be exemplified in the explanation of the operation of the information presentation system 10 described later. Note that the store master 240 may also be used in other systems introduced in retail stores, such as an ordering system, an inventory management system, and a sales management system.

[0082] The configuration of the information presentation system 10 described above is an example of the row configuration of the information presentation system according to the present disclosure, and is not limited to this.

[0083] For example, the reader 100 does not have to be provided as part of an information presentation system.

[0084] Furthermore, the reader 100 does not have to be a device carried by each customer as described above, but may be a group of devices that are installed on the walls, ceilings, or fixtures in the store and can detect a series of shopping actions of the customer. Specifically, the reader 100 may be cameras installed in multiple locations in the store.

[0085] In this case, the customer's behavior regarding holding the product is recognized by image recognition of the images of the product and the customer captured by these cameras.

[0086] Alternatively, the group of devices may further include sensors other than the image sensor of the camera, such as an RF reader for acquiring information for identifying products or customers. In other words, the reader 100 acquires further information for identifying each customer so that the shopping behavior of each customer can be handled individually and captured in time series. The store analysis server 200 that receives this information further includes a customer identification unit for identifying each customer using this information.

[0087] The store analysis server 200 obtains time-series shopping data such as that shown in FIG. 3 by associating each identified customer, each customer's behavior of retaining or returning products, and the products that each customer has started to retain or released.

[0088] [2. Operation] The operation of the information presentation system 10 will be described below with a number of examples according to the type of data to be presented.

[0089] The procedure up to the point where the data acquisition unit 220 acquires time-series shopping data based on the product identification information acquired from the reader 100 is basically the same regardless of the type of data presented. Furthermore, regardless of the type of data, the output format can be determined by the user of the data, such as a store manager, depending on the purpose. The following explanation will focus on the operation of the information generation unit 230, which differs depending on the type of data.

[0090] [2-1. Classification based on shopping time, etc.] It is known from past experiments that there is a difference in the types of items purchased at a store between people who are in a hurry and those who are not. Therefore, if each store knows the types of items that are characteristic of customers who are in a hurry (hereinafter also referred to as customers in a hurry), it can create a sales floor that is highly convenient for customers in a hurry, for example by placing such items on the shortest route connecting the store entrance and the cash register.

[0091] FIG. 4 is a flowchart showing an example of a procedure of processing by the information generating unit 230 for the information presentation system 10 to output store analysis information using classification related to the degree of urgency for each customer.

[0092] In this example, the degree of urgency of the customer is determined using the time spent on one shopping trip at a store (shopping time) and the interval between the start of holding each of different items (holding start interval). The information generating unit 230 can obtain the shopping time and the holding start interval from the time-series shopping data as shown in FIG.

[0093] The information generating unit 230, which has acquired the shopping time and the retention start interval of a certain customer, determines whether the shopping time is equal to or less than a first threshold value (step S41). If the shopping time is equal to or less than the first threshold value (Yes in step S41), the information generating unit 230 classifies the customer as a rush customer (step S45).

[0094] The first threshold is a time length that is set based on, for example, the average shopping time of all customers of the store. This average shopping time is also calculated and acquired from the time-series shopping data in the information presentation system 10. The first threshold is set to a time length that is shorter than this average shopping time, for example, a quarter of the average shopping time.

[0095] The reason why a customer is classified as a customer in a hurry using step S41 is that, for example, the customer is likely to be in a behavioral or psychological state in which the customer is in a hurry and will put only predetermined items in the shopping cart and move quickly in order to complete the payment quickly.

[0096] If the shopping time exceeds the first threshold (No in step S41), the information generating unit 230 determines whether the retention start interval of this customer is equal to or less than the second threshold (step S42). If the shopping time is equal to or less than the second threshold (Yes in step S42), the information generating unit 230 classifies this customer as a rush customer (step S45).

[0097] The second threshold is a time length that is set based on, for example, the average retention start interval of all customers of the store. This average retention start interval is also calculated and acquired from the time-series shopping data in the information presentation system 10. The second threshold is set to a time length that is shorter than this average retention start interval, for example, a half of the average retention start interval.

[0098] The reason why a customer is classified as a hurry customer using steps up to step S42 is that the customer is likely to be in a behavioral or psychological state in which, for example, they are quickly putting predetermined purchase items into a shopping cart, but because there are a large number of items, the shopping time is relatively long.

[0099] If the retention start interval exceeds the second threshold (No in step S42), the information generating unit 230 determines whether the shopping time of this customer exceeds the eighth threshold (step S43). If the shopping time exceeds the eighth threshold (Yes in step S43), the information generating unit 230 classifies this customer as a customer with plenty of time (step S47).

[0100] The eighth threshold is also a length of time that is set, for example, based on the average shopping time of all customers at the store, and is set to a length of time longer than the first threshold that is also set based on the average shopping time of all customers, for example, the same length of time as the average shopping time.

[0101] The reason why a customer is classified as a customer with plenty of time using steps up to S43 is that, for example, there is no particular reason for the customer to be in a hurry, so there is no need to quickly search for products to purchase and put them in a shopping cart, etc., and the customer is likely to be in a behavioral or psychological state in which they will spend a relatively long time in the store.

[0102] If the shopping time is equal to or less than the eighth threshold (No in step S43), the information generating unit 230 judges whether the retention start interval of this customer exceeds the ninth threshold (step S44). If the retention start interval exceeds the ninth threshold (Yes in step S44), the information generating unit 230 classifies this customer as a customer who has plenty of time (step S47).

[0103] The ninth threshold is also a length of time that is set, for example, based on the average hold start interval of all customers at the store, and is set to a longer length of time than the second threshold, which is also set based on the average hold start interval of all customers, for example, the same length of time as the average hold start interval.

[0104] The reason why a customer is classified as a customer with plenty of time using steps S44 is that, for example, since there is no particular reason for the customer to be in a hurry, there is no need to quickly search for products to purchase and put them in a shopping cart, etc., but since the number of items purchased is small, the customer is likely to be in a behavioral or psychological state in which he or she will not stay in the store for a particularly long time.

[0105] If the shopping time is equal to or less than the ninth threshold (No in step S44), the information generating unit 230 classifies the customer as an intermediate customer who is not in a hurry but does not have much time either (step S46).

[0106] The information generating unit 230, which has determined the classification of the customer in the steps up to this point, sets the determined classification as classification information. The information generating unit 230 further generates store analysis information based on this classification information and held product information indicating the products held by the customer (step S48). The store analysis information obtained in this way is, for example, information obtained by statistically processing the results of the process shown in FIG. 4 executed on a large number of customers, and more specifically, indicates products that tend to be purchased by customers in a hurry at the store. This store analysis information is output by the data output unit 250 as data that can be used by the store manager. FIG. 5 is a diagram showing an example of data output by the data output unit 250.

[0107] In this example, information on the top 10 departments of items purchased by customers in a hurry, customers with time to spare, and all customers is presented. Also, the same departments between customer classifications are connected with lines. Each department is the department to which the product indicated by the retained product information belongs, and was obtained by the information generating unit 230 by referring to the product master included in the store master 240.

[0108] Armed with this information, store operators can, for example, rearrange shelf allocations so that the top three department shelves are located along the route between the entrance and checkout, improving the quality of the shopping experience for rush customers and encouraging them to return, potentially increasing sales.

[0109] The above-described processing procedure and presented information are merely examples, and the following modifications are possible.

[0110] For example, the classification decision as described above may be based on only one of the shopping time and the holding start interval.

[0111] In addition, the determination regarding the hold start interval may be performed after normalization according to the distance of the path between the products. For example, the hold start interval may be corrected according to the distance in the physical space between the products. More specifically, L: the shortest path length between the product to be processed and the product that started being held immediately before that (this shortest path length may be included as information in, for example, the sales floor master of the store master 240, and may be acquired by the information generating unit 230 by referring to the sales floor master) V: Average walking speed (if information on time of day, store type, aisle width, and each customer is available, values ​​tailored to gender and age may be used) K: Correction coefficient (a value of 1.0 or more. A coefficient for taking into account time other than that required for movement, such as stopping in front of other products, and time spent other than considering purchasing the product being processed) As, Correction hold start interval = actual elapsed time - (L / V) x K This makes it possible to present more accurate information.

[0112] Also, the classification of customers may be not only three types, but also two or four or more types, and may be a quantitative classification by time range. Note that the qualitative classification as in the above example is a classification by dividing the time range based on, for example, statistically obtained knowledge. Alternatively, more detailed classification may be made based on a continuous value such as an index value (urgency index) indicating the degree of urgency calculated from the shopping time and the holding start interval.

[0113] In the above example, the classification of customers is determined based on the magnitude relationship between the shopping time or the retention start interval and the threshold value, but the above-mentioned classification of customers may be determined using a method based on the shopping time or the retention start interval but without using a threshold value. For example, the classification may be determined using the percentile of the shopping time or the retention start interval of a certain customer among the shopping times or the retention start intervals of all customers.

[0114] Furthermore, the shopping time or retention start interval used to calculate the threshold or percentile does not have to be obtained from the time-series shopping data of all customers. For example, the shopping time or retention start interval may be obtained from the time-series shopping data of customers in a recent certain period, customers in the same time period, or customers who purchase the same or similar number of items.

[0115] Also, instead of percentiles, the above classification may be determined using ascending or descending ranks.

[0116] In addition, the products shown in the store analysis information do not have to be departments as in the above example, but may be individual products. In addition, by filtering, store analysis information limited to products in a specific department or a specific area of ​​the store may be presented. The example shown in FIG. 5 may be store analysis information limited to departments of food and beverages.

[0117] Furthermore, the manner in which the presented store analysis information is used is not limited to the above example. For example, the shelf allocation of the entire store may be determined based on the hurry index and the list of products held or purchased by each customer so that the shopping time at the store is optimized. This optimization does not only refer to shortening the shopping time of customers who are in a hurry, but also refers to changing the sales floor to one that provides more notices for customers who have time, makes shopping enjoyable, and encourages so-called "impulse buying."

[0118] In the above, customers are classified into categories according to the degree of "urgency" according to the shopping time or the retention start interval, but the method of classifying customers according to similar times is not limited to this. For example, it is also possible to classify customers into "purposeful purchases" who have decided the product they will purchase before coming to the store according to these times. This is because such customers often move around the store using a route that efficiently goes around the sales floor where the product they are looking for is located, and they also show similar tendencies to "hurry customers," such as a short retention start interval or shopping time.

[0119] Furthermore, in the above example, the store analysis information is used by the store manager as information on sales performance, but it may also be used to classify customers who are shopping.

[0120] For example, the information generating unit 230 may provisionally determine a classification of the customer's degree of urgency during shopping based on the combination of products held, the holding start interval, etc. The data output unit 250 outputs store analysis information indicating the customer, the classification determined for this customer, and products already held by this customer to a system that recommends products to the customer via digital signage or an information device held by the customer. This system may then introduce to the customer products that customers of this classification are likely to purchase later.

[0121] The store analysis information may also be provided to manufacturers of products sold in the store for use. To give a more specific example, information that a certain product of the manufacturer tends to be purchased by customers in a hurry is provided to the manufacturer based on the store analysis information. The manufacturer who receives this information can change the design of the package so that customers in a hurry can easily find it in the store, or create and distribute POP advertisements. For the manufacturer, information on the behavior or psychological state of consumers in the store, which could only be grasped by spending time and money by observing in the store, checking recordings, conducting questionnaires, etc., can now be obtained more easily, enabling product development that is more in line with that behavior or psychological state.

[0122] [2-2. Classification based on the time elapsed before the start of product retention] Next, the process of sorting based on the time spent before placing an item in the shopping cart will be described.

[0123] For example, if a customer is unsure about whether to purchase a certain product, it will take a long time from when they enter the store until they put the product in their shopping cart, or from when they put the product in their shopping cart just before (or when they return it to the sales floor) until they put the product in their shopping cart again. The same is true when a customer has the intention to buy a product but is unable to find it on the sales floor. If store managers can identify products that are likely to cause this kind of situation, they can reduce the loss of potential sales opportunities by providing information in-store that encourages the purchase of the product or by changing the product's location to make it easier to find.

[0124] FIG. 6 is a flowchart showing an example of a procedure of processing by the information generating unit 230 for the information presentation system 10 to output store analysis information in which each product is classified into the above-mentioned products.

[0125] In this example, whether or not a product is one for which a customer is unsure about purchasing or has difficulty identifying the location is determined using the time that has elapsed before each product was held on the sales floor (time before holding) and sales of each product. The information generating unit 230 can obtain this time before holding from time-series shopping data such as that shown in FIG. 3. In addition, information regarding sales can be obtained by referring to sales performance data obtained by the store using a POS system for each product shown in the time-series shopping data. Note that sales here refer to, for example, the number of items sold, but are not limited to this.

[0126] The information generating unit 230, which has acquired the pre-holding elapsed time of a certain customer, determines whether the pre-holding elapsed time is equal to or less than a third threshold (step S61). If the pre-holding elapsed time is equal to or less than the third threshold (Yes in step S61), the information generating unit 230 determines the classification of this product as a normal product (step S63).

[0127] The third threshold is a time length that is set based on the average pre-hold start time of the entire store, for example. The average hold start interval can be calculated and acquired from the time-series shopping data in the information presentation system 10.

[0128] If the pre-holding elapsed time exceeds the third threshold (No in step S61), the information generating unit 230 judges whether the sales of this product are larger or smaller than the fourth threshold (step S62). The fourth threshold is a value of the number of units that is set based on the average sales of each product in the department to which the product belongs, for example, from the above-mentioned sales performance data.

[0129] If the sales of this product are equal to or less than the fourth threshold (No in step S62), the information generating unit 230 determines the classification of this product as a product whose location took a long time to identify (step S64).If the sales of this product are greater than the fourth threshold (No in step S62), the information generating unit 230 determines the classification of this product as a product that the customer was unsure whether to keep for purchase (step S65).

[0130] The reason why the products are classified as above using step S62 is that it is highly likely that the location of high-selling products in the store is already known to customers, but for some reason, customers are taking time to decide which product to purchase. For example, some reason may be that the number of items handled in the same department is large, making it difficult for customers to recognize the differences between products, or that new products are introduced relatively frequently or there are a large number of items, making it easy for customers to hesitate between new products and existing products. Also, it is highly likely that the location of low-selling products in the sales floor is difficult to find, or that customers know the location of the sales floor where the product they intend to buy is located, but that product is difficult to notice due to its location on the shelf or the way it is displayed.

[0131] The information generating unit 230, which has determined the classification of the product in the steps up to this point, sets the determined classification as classification information. The information generating unit 230 further generates store analysis information based on the classification information and the held product information of the product (step S66).

[0132] The store analysis information thus obtained is, for example, information obtained by statistically processing the results of the process shown in Fig. 6 executed over a predetermined period of time, and indicates products that belong to each category determined as described above. This store analysis information is output by the data output unit 250 as data that can be used by the store manager. For example, it may be presented to the store manager as a list of products that belong to each category.

[0133] Using such information, the store manager can, for example, change the location or number of faces of each product on the shelf, including the product that took a long time to locate, or use POP advertising for sales promotion. This makes it easier for customers to find the product and shop, and the store can reduce missed sales opportunities. In addition, for products that customers are unsure whether to keep or not, the store manager can encourage customers to pick up and keep the product by promoting the product they are more interested in selling, posting POP advertising to provide information on the differences between products, or changing the price setting.

[0134] In addition, since a customer may choose not to purchase either product or to purchase both products after hesitating about which to purchase, the store operator can thereby reduce missed sales opportunities and increase sales.

[0135] The above-described processing procedure, information used, and information presented are merely examples, and variations are possible.

[0136] For example, similarly to the above-mentioned case of the holding start interval, the pre-holding elapsed time may be corrected according to the physical spatial distance between the products. More specifically, L: The shortest path length between the product to be processed and the product for which retention was started or released immediately before that. V: Average walking speed (if information on time of day, store type, aisle width, and each customer is available, values ​​tailored to gender and age may be used) K: Correction coefficient (a value of 1.0 or more. A coefficient for taking into account time other than that required for movement, such as stopping in front of other products, and time spent other than considering purchasing the product being processed) As, Corrected pre-hold time elapsed = actual time elapsed - (L / V) x K This makes it possible to present more accurate information.

[0137] Furthermore, for example, in the case of a chain store, the fourth threshold value is not limited to the average sales volume at the store itself, and may be a number based on sales records at other stores of similar size and location.

[0138] In addition, instead of using the fourth threshold value in the judgment in step S62, clustering may be performed using unsupervised machine learning such as the k-means method, and products included in an appropriate cluster based on the elapsed time before retention and sales may be judged to belong to each category.

[0139] In the above example, the classification of products is determined based on the magnitude relationship between the pre-holding elapsed time or sales and a threshold value, but the above-mentioned classification of products may be determined using a method based on the pre-holding elapsed time or sales but without using a threshold value. For example, the classification may be determined using the percentile of the pre-holding elapsed time of a certain customer relative to the pre-holding elapsed time of all customers. Also, the classification may be determined using the percentile of the sales of a certain product relative to the sales of each product in the same department.

[0140] In addition, the pre-hold elapsed time or sales used in the calculation of the above threshold or percentile does not have to be obtained from the time-series shopping data of all customers. For example, the pre-hold elapsed time or sales obtained from the time-series shopping data of customers in a recent certain period or customers in the same time period may be used.

[0141] Also, instead of percentiles, the above classification may be determined using ascending or descending ranks.

[0142] Also, classification may be performed not for individual products but for product departments. In this case, the average sales may be calculated based on, for example, the figures for other stores as described above, or the sales composition ratios between other stores or departments in the same store.

[0143] In addition, store analysis information indicating such classification may also be provided to manufacturers of products sold in the store for use. For example, a manufacturer of a product classified as a product that is difficult to find can add information about the characteristics of the product to the package of the product or make changes to improve visibility.

[0144] [2-3. Classification based on return after product retention begins] Next, a process of classification based on the incidence rate of product returns (hereinafter, referred to as return rate) will be described.

[0145] For example, it is considered that the situation where a customer hesitates to buy a product, even if it is held, is returned to the sales floor before checkout occurs more frequently than for products that are not. As mentioned above, after hesitating to buy, a customer may choose to buy neither or both, which may result in the store missing a sales opportunity. Also, for customers, if they decide not to buy either because they are unable to decide, they will have to spend time and effort to buy something else instead or to consider what to buy, and if they are forced to buy both, they will incur unnecessary expenses and the quality of their shopping experience will decrease.

[0146] If store managers can obtain such product information, they can reduce missed sales opportunities and increase sales by presenting product information to customers, for example, through POP advertising. In addition, they can provide customers with a high-quality shopping experience that reduces waste of time and money by allowing them to decide which products to purchase after obtaining product information.

[0147] FIG. 7 is a flowchart showing an example of a procedure of processing by the information generating unit 230 for the information presentation system 10 to output store analysis information using classification of each product based on the occurrence rate of return.

[0148] In this example, a classification of the degree of indecision of a customer as to whether to purchase or return a product for which the customer was unsure whether to purchase is determined based on the return rate of the product. The information generating unit 230 can calculate and acquire the return rate of each product from the time-series shopping data as shown in Fig. 3. For example, the return rate of a certain product is calculated as the ratio of the total number of occurrences of returns to the total number of occurrences of holding the product.

[0149] The information generating unit 230, which has acquired the return rate for a certain product, determines whether or not the return rate is greater than a predetermined threshold (step S71). If the return rate is greater than the predetermined threshold (Yes in step S71), the information generating unit 230 classifies the product as a product for which customers are likely to be unsure whether or not to purchase it (step S72).

[0150] This predetermined threshold value is a probability that is set in the information presentation system 10 based on the return rate of the entire department to which the product belongs, which is calculated from the above-mentioned time-series shopping data, for example.

[0151] If the return rate is equal to or lower than the threshold value (No in step S71), the product is classified as a product that customers are unlikely to hesitate to purchase (step S73).

[0152] The information generating unit 230, which has determined the classification of the product in the steps up to this point, sets the determined classification as classification information. The information generating unit 230 further generates store analysis information based on the classification information and the retained product information of the product (step S74).

[0153] The store analysis information thus obtained is, for example, information obtained by statistically processing the results of the process shown in Fig. 7 executed over a predetermined period of time, and indicates the products that belong to each category determined as described above. This store analysis information is output by the data output unit 250 as data that can be used by the store manager. For example, it may be presented to the store manager as a list of products that belong to each category.

[0154] Using such information, store managers can post POP advertisements to promote products they want to sell or to provide information on the differences between products, change pricing, etc. This allows store managers to improve the quality of customers' shopping experience and reduce lost sales opportunities, leading to increased sales.

[0155] The above-described processing procedure, information used, and information presented are merely examples, and variations are possible.

[0156] For example, the store analysis information may include classification based on a continuous value such as an index value (a confusion index) indicating the degree of confusion based on a return rate. Hesitation index = exp(return rate - threshold) / (1+exp(return rate - threshold)) It may be calculated as follows:

[0157] Also, classification may be based on descending or ascending return rates or percentiles within a product category rather than comparison to a threshold.

[0158] In addition, store analysis information showing such classifications may be provided to and used by manufacturers of products sold in stores. For example, manufacturers of products that are difficult to choose can use such information to renew packages to differentiate them from competing products, release products of different sizes, develop sales promotion methods, or develop new products.

[0159] The classification of hesitation in 2-2 above differs in that it is hesitation before holding a product or hesitation after holding a product during shopping. Users of store analysis information can plan sales strategies with this point in mind.

[0160] [2-4. Classification of product competition] Store managers can understand to some extent the competitive relationship between products based on general knowledge, intuition, and experience. However, it has been difficult to understand how customers consider competing products on the sales floor without special surveys such as in-store observation, video recording, and questionnaires. Moreover, it is particularly difficult to discover competitive relationships between products that are not one-to-one.

[0161] Here, the products held by the customers may be replaced by competing products. The information presentation system 10 can obtain such information and present it to the store manager.

[0162] FIG. 8 is a flowchart showing an example of a procedure of processing by the information generating unit 230 for the information presentation system 10 to output store analysis information using classification regarding competitive relationships between products.

[0163] In this example, the presence or absence of a competitive relationship between products is determined using the occurrence of retention of a certain product, the occurrence of returns of products of different categories from this product, and the relationship between each product between departments obtained based on the retained product information of each product. The information generating unit 230 can obtain the occurrence of retention and returns of such products from the time-series shopping data as shown in Fig. 3 (step S81). In addition, the relationship between each product between departments can be obtained by referring to the product master for the product indicated by the retained product information.

[0164] The information generating unit 230 detects the occurrence of the retention of a certain product (hereinafter referred to as a first product) and the occurrence of the return of a product of a different category from the first product (hereinafter referred to as a second product) from the time-series shopping data of one shopping trip of a certain customer, and judges whether the information on these occurrences conforms to the conditions indicating or denying the existence of a competitive relationship. More specifically, the information generating unit 230 judges whether the information on the time interval between the occurrence of the retention of the first product and the occurrence of the return of the second product obtained from the time-series shopping data, the above-mentioned retained product information of each of the first product and the second product, and the department information of each of the first product and the second product obtained using the product master meets a predetermined condition. These conditions will be described with reference to the examples shown in Figures 9A and 9B.

[0165] Figure 9A is a table showing examples (a) to (e) of conditions that indicate the existence of a competitive relationship (hereinafter, also referred to as competitive eligibility conditions). The arrows indicate the order of occurrence in chronological order, the solid lines surrounding each product name (product A, etc.) indicate the occurrence of retention of each product, and the dashed lines indicate returns. Each example will be explained below.

[0166] The example condition (a) is an example of a condition for determining the existence of a competitive relationship between one-to-one products.

[0167] In this example, if product A, which was once held, is returned and then product B is held within a time interval equal to or less than a threshold value from the return of product A, product A and product B are determined to be in conflict with each other.

[0168] Alternatively, if product B belongs to a department similar to product A, product A and product B are determined to be in competition. Multiple departments are similar if, for example, multiple departments set in a tree structure have a common parent department (the department one level above) and these departments are similar.

[0169] The number of hierarchical levels, which is the criterion for determining whether departments are similar to each other, is not limited to one level and may be set appropriately. In addition, even when product departments are not set in a tree structure or are set in a tree structure, exceptional similarity relationships between departments may be separately defined and provided in the information presentation system 10 as data such as a table that can be referenced by the information generating unit 230. Depending on the criterion for determining whether departments are similar to each other, it is possible to determine the existence of a competitive relationship between products that have traditionally been determined not to be competitive. For example, even when product A is almond chocolate and product B is cafe latte, it may be determined that a competitive relationship exists.

[0170] The example condition (b) is an example of a condition for determining the existence of a competitive relationship between one-to-many products.

[0171] In this example, if product A and product C, which were once held, are returned in order, and then product B is held within a time interval of the threshold value after product A is returned, products A and C are determined to be in conflict with product B.

[0172] Alternatively, if the return of product A, the return of product C, and the retention of product B occur within a time interval equal to or less than a predetermined threshold, it is determined that products A and C compete with product B.

[0173] Alternatively, when product B belongs to a category similar to product A and product C, product A and product C are determined to be in competition with product B.

[0174] For example, if product A is salmon rice balls, product C is plum rice balls, and product B is a bento lunch box, and a customer selects one bento lunch box instead of two rice balls, it can still be determined that a competitive relationship exists.

[0175] Example condition (c) is also an example of a condition for determining the existence of a competitive relationship between one-to-one products, and is a case in which the order of the return of product A and the retention of product B is reversed.

[0176] In this example, if the return of product A occurs within a time interval equal to or less than a threshold value from the occurrence of the retention of product B, product A and product B are determined to be in conflict with each other.

[0177] Alternatively, when product B belongs to a similar category to product A, product A and product B are determined to be in competition with each other.

[0178] Example condition (d) is also an example of a condition for determining the existence of a competitive relationship between one to many products, and is a case in which the order of the return of product A and product C and the retention of product B is reversed from example condition (b).

[0179] In this example, if product A and product C are returned within a time interval equal to or less than a threshold value from the occurrence of retention of product B, product B is determined to be in conflict with products A and C.

[0180] Alternatively, if the holding of product B, the return of product A, and the return of product C occur at time intervals equal to or less than a predetermined threshold, it is determined that product B competes with products A and C.

[0181] Alternatively, when product A and product C belong to a similar category to product B, product B is determined to be in competition with products A and C.

[0182] Furthermore, by combining a plurality of the above example conditions, it is possible to determine whether or not there is a competitive relationship even when the order in which a plurality of products are purchased or returned is more complicated.

[0183] In condition example (e), by combining condition example (a) and condition example (c), it is determined that there is a competitive relationship between product A and product B, and a competitive relationship between product B and product C. In light of the shopping scene example, after a customer puts product A and product C in a shopping cart, they return product A and quickly put product B in the shopping cart instead. At this point, it is determined that product A and product B are in competition with each other in light of condition example (a). Now, after putting product B in the shopping cart and looking inside, the customer thinks that if they buy product B, they also do not need product C, and immediately returns product C. Now, it is determined that product B and product C are in competition with each other in light of condition example (c).

[0184] In this manner, the information presentation system 10 according to the present embodiment can detect competitive relations in customer psychology that are manifested in the start of keeping a product and the occurrence of a return, which typically occur during shopping behavior.

[0185] FIG. 9B is a table showing an example (f) of a condition indicating the absence of a competitive relationship (hereinafter, referred to as a competitive ineligible condition) and an example (g) of an exception thereto.

[0186] In condition example (f), if product A is returned within a time interval equal to or less than the threshold after the second retention of product A, it is determined that product A and product B do not compete even if retention of product B begins after that. Since the second retention of product A is highly likely to be due to a customer error, such as double scanning of the product's barcode, in such a case it is determined that there is no competition between product A and product B.

[0187] In contrast, in the example of condition (g), although there is a short period between the second retention of product A and the return of product A, if the retention of product B also occurs during that time, it is highly likely that the second retention of product A is not due to an erroneous operation as described above, and therefore it is determined that there is a competitive relationship between products A and B.

[0188] In the determination using these example conditions, the threshold value for comparing the magnitude relationship with the time interval is an example of the sixth threshold value in this embodiment.

[0189] In step S82, the information generation unit 230 determines whether the information on the time interval between the occurrence of the retention of the first product and the occurrence of the return of the second product, the retained product information for each of the first product and second product, and the department information for each of the first product and second product obtained using the product master meet the competitive ineligibility condition, that is, whether or not it meets condition example (f) among the above condition examples, and if it does, whether or not it does not meet condition example (g).

[0190] If these pieces of information meet the competitive ineligibility condition (Yes in step S82), the information generating unit 230 determines the classification of the first product and the second product as products that are not in competition with each other (step S85).

[0191] If these conditions do not match the competitive ineligible conditions (No in step S82), the information generation unit 230 further determines whether these conditions match the competitive eligible conditions, that is, any of the example conditions (a) to (e) among the above example conditions (step S83).

[0192] If the conflict qualifying condition is not met (No in step S83), the information generating unit 230 determines the classification of the first product and the second product as products that do not conflict with each other (step S85).

[0193] If the competition eligibility condition is met (Yes in step S84), the information generating unit 230 determines that the classifications of the first product and the second product are products that compete with each other (step S84).

[0194] The information generating unit 230, which has determined the classification of the product in the steps up to this point, sets the determined classification as classification information. The information generating unit 230 further generates store analysis information based on the classification information and the held product information of the product (step S86).

[0195] The store analysis information thus obtained is, for example, information obtained by statistically processing the results of the process shown in Fig. 8 executed over a predetermined period of time, and indicates products that belong to each category determined as described above. This store analysis information is output by the data output unit 250 as data that can be used by the store manager. For example, it may be a list showing combinations of products that are frequently determined to be in a competitive relationship in order of frequency.

[0196] The above-described processing procedure and presented information are merely examples, and the following modifications are possible.

[0197] For example, a determination of competition between products may be made based on statistics of the frequency of co-occurrence of the retention of a certain product and the return of another product in a single shopping trip of a customer, without using the similarity relationship between product categories. Although it is likely to take time to obtain useful store analysis information, it is expected that store analysis information indicating competitive relationships or combined purchases that were previously unknown will be obtained.

[0198] In addition, the competitive relationship between products may be indicated in the store analysis information not as the presence or absence of the competitive relationship as described above, but as, for example, strength. As a more specific example, products may be classified based on a continuous value such as an index value indicating the strength of the competitive relationship between products that is calculated based on the distance between departments in the tree structure of the departments or the frequency at which the products are determined to be in a competitive relationship as described above.

[0199] Based on such information on competition between products, store managers can improve sales by considering product lineups, product placement, suggestive POP advertising, etc. Also, for customers, receiving proposals for new products or product combinations that can be substitutes for products they have previously purchased is expected to improve the quality of their shopping experience, such as breaking out of a rut at a store they frequently shop at or increasing satisfaction by being able to shop from a wider range of options.

[0200] In the above example, the store analysis information is used by the store manager as information on sales performance, but it may also be used during shopping. For example, the data output unit 250 outputs store analysis information indicating the customer, the product returned by the customer, and the product classified as competing with the returned product to a system that recommends products to the customer via digital signage or an information device held by the customer. This system may then introduce products competing with the returned product to the customer. Alternatively, the product that the store wants to sell may be introduced to a customer who has started holding a product classified as competing with a product that the store wants to sell.

[0201] In addition, such store analysis information may be provided to and used by manufacturers of products sold in the store. From the newly discovered competitive relationships, the manufacturers may obtain hints for new markets or sales promotion activities that are different from the conventional ones.

[0202] [2-5. Classification of customer personnel composition] Previously, it was difficult to link the fact that a customer was a group to sales performance data, and information on group-specific product purchasing trends was scarce compared to information on individual customers.

[0203] By using information on the time intervals between occurrences of holding a plurality of products, which is acquired by the information presentation system 10, it is possible to determine that customers form a group in a given case. Such a case will be described below.

[0204] Fig. 10A is a diagram showing the arrangement of products by department in a certain store. Also, in Fig. 10A, arrows are used to show the movement of a certain customer during shopping at this store. Fig. 10B is a diagram showing a part of the department of the held products and the time interval when the held products started to be held, as shown in the time-series shopping data acquired during the shopping trip by this customer.

[0205] Comparing Figure 10A with Figure 10B, for example, even though there is a relatively large distance between the meat section and the bottled drink section, the time interval between the occurrence of holding a meat product and the occurrence of holding a bottled drink is 3 seconds, which is shorter than the time interval between the other products, given the distance between the sections. Similarly, the time interval between the occurrence of holding a prepared food product and the occurrence of holding a magazine is also 2 seconds, which is shorter than the distance between the sections. Considering the speed at which people move, such movement between sections is impossible, and it can be inferred that it is highly likely that multiple people were shopping together.

[0206] In the information presentation system 10, a customer is classified as either a group customer or a non-group customer, and selling floor analysis information is generated, using the processing procedure exemplified in FIG.

[0207] In this example, the time interval when a customer holds an item, held item information indicating the item held by the customer, and the time required for moving the item held by the customer along the route between sales floors (travel time) are used. The information generating unit 230 can acquire this time interval and held item information from time-series shopping data as shown in FIG. 3 (steps S111 and S112). The average length of time required for the route between sales floors for the item held by the customer can be acquired by referring to the sales floor master for the item indicated by the held item information. For example, the sales floor master indicates the distance of the shortest route between sales floors in each department. In this case, the information generating unit 230 calculates the travel time from this distance and the average walking speed of a person. Alternatively, the sales floor master may directly indicate the average travel time according to the distance of the shortest route between sales floors in each department.

[0208] The information generating unit 230, which has acquired these pieces of information, determines whether or not the time interval is equal to or less than the required travel time (step S113).

[0209] If the time interval is equal to or less than the travel time (step S113: Yes), the information generating unit 230 determines that the customer is classified as a group customer (step S114). If the time interval is greater than the travel time (step S113: No), the information generating unit 230 determines that the customer is classified as a customer that is not a group customer (step S115).

[0210] The information generating unit 230, which has determined the classification of the customer in the steps up to this point, sets the determined classification as classification information. The information generating unit 230 further generates store analysis information based on the classification information and held product information indicating the products held by the customer (step S116).

[0211] The store analysis information thus obtained is, for example, information obtained by statistically processing the results of the process shown in Fig. 11 executed over a predetermined period of time, and indicates products purchased by customers belonging to each category determined as described above. This store analysis information is output by the data output unit 250 as data usable by the store manager. For example, it may be presented to the store manager as a list of products purchased by customers belonging to each category.

[0212] Using such information, store managers can, for example, create sales areas that group customers frequently purchase near each other and display guidance to these sales areas. In addition, the area around the sales area can be designed to have wider aisles. This increases convenience for group customers and improves the quality of their shopping experience. For stores, this increases the frequency with which group customers visit the store, and group customers tend to spend more per customer, leading to increased sales.

[0213] (Other embodiments) In the above-described embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU (central processing unit) or a processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Here, the software program that realizes the store analysis server of the above-described embodiments is a program such as the following.

[0214] In other words, this program causes a computer to acquire product identification information from a reader that uses a sensor to sequentially read product identification information indicating products held by a customer while shopping in a physical store, acquire time-series shopping data, which is data regarding the holding of products by the customer over time, based on this product identification information, acquire classification information indicating classifications of customers or products based on this time-series shopping data, generate store analysis information based on this classification information and held product information indicating products held or returned by the customer, and output this store analysis information as data that can be used by the operator of the physical store.

[0215] Although the information presentation system according to one or more aspects has been described based on the embodiment, the present invention is not limited to this embodiment. As long as it does not deviate from the spirit of the present invention, various modifications conceived by a person skilled in the art may also be included in the scope of the present invention. [Industrial Applicability]

[0216] The present invention can be used in a system that provides a store manager with information based on the behavior of customers who are shopping in a store and who hold products that they are considering purchasing. [Explanation of symbols]

[0217] 10 Information presentation system 100 Reader 110, 111, 112, 113 Sensors 120 Transmitter 200 Store analysis server 210 Receiving unit 220 Data Acquisition Department 230 Information generation section 240 Store Master 250 Data output section

Claims

1. A data acquisition unit that acquires time-series shopping data of customers shopping in a physical store from multiple cameras installed in the store; obtaining a time interval between an occurrence of holding a first product by the customer and an occurrence of returning a second product different from the first product from the time-series shopping data, and held product information indicating the first product and the second product, respectively; Based on the time interval and the held product information, determining a degree of competition between the first product and the second product; an information generating unit that generates analysis information based on the retained product information and the result of the determination; A data output unit that outputs the analysis information, The information generating unit If the time interval is equal to or less than a predetermined threshold, or if the first product that was once held is returned and then held within a time interval equal to or less than a threshold from the return of the first product, it is determined that the first product and the second product are in conflict with each other. Information presentation system.

2. A data acquisition unit that acquires time-series shopping data of customers shopping in a physical store from a plurality of cameras installed in the store; obtaining a time interval between an occurrence of holding a first product by the customer and an occurrence of returning a second product different from the first product from the time-series shopping data, and held product information indicating the first product and the second product, respectively; Based on the time interval and the held product information, determining a degree of competition between the first product and the second product; an information generating unit that generates analysis information based on the retained product information and the result of the determination; A data output unit that outputs the analysis information, The information generating unit If the time interval is equal to or greater than a predetermined threshold, it is determined that the first product and the second product do not compete with each other. Information presentation system.

3. The data acquisition unit is acquiring statistical data on the frequency of occurrence of the retention of the first item and the return of another item in shopping by a plurality of customers; The information generating unit determining a degree of competition between the first product and another product based on the statistical data without using a similarity relationship between the product categories; 3. The information presentation system according to claim 1 or 2.

4. The data output unit includes: Output combinations of products that are frequently determined to be in a competitive relationship.

3. The information presentation system according to claim 1 or 2.

5. The information presentation system The system collects time-series shopping data from multiple cameras installed in the store while customers are shopping in the store, obtaining a time interval between an occurrence of holding a first product by the customer and an occurrence of returning a second product different from the first product from the time-series shopping data, and held product information indicating the first product and the second product, respectively; Based on the time interval and the held product information, determining a degree of competition between the first product and the second product; generating analysis information based on the held product information and the result of the determination; Outputting the analysis information; In the determination of the degree of contention, If the time interval is equal to or less than a predetermined threshold, or if the first product that was once held is returned and then held within a time interval equal to or less than a threshold from the return of the first product, it is determined that the first product and the second product are in conflict with each other. Information presentation method.

6. A program for causing a computer of the information presentation system to execute the information presentation method according to claim 5.

Images