Purchase rate calculation device, purchase rate calculation method, and program

Abstract

Even when customers visit a store as a group, the present invention makes it possible to calculate the purchase rate in units of the group. In the present invention, a grouping unit (11) groups, on the basis of an image of customers entering a store, a plurality of the customers entering the store into a plurality of groups each including one or more customers. When a customer performs settlement on a POS device in the store, a group identification unit (12) identifies a group to which the customer belongs on the basis of an image of the customer who has performed the settlement. A purchase rate calculation unit (13) calculates the purchase rate of the group on the basis of the number of groups that have entered the store in a prescribed period and the number of groups that have performed purchase in the prescribed period.

Description

Purchase rate calculation device, purchase rate calculation method, and computer-readable medium

[0001] The present disclosure relates to a purchase rate calculation device, a purchase rate calculation method, and a computer-readable medium.

[0002] As a related technique, Patent Document 1 discloses an assistance device that supports sales increase in a retail store. The assistance device described in Patent Document 1 acquires video data from a camera installed in the retail store. The assistance device also acquires POS (Point of Sales) data from a POS register. The assistance device generates report information to support sales increase based on the video data from the store and the POS data. The report information includes visitor count information indicating the number of customers who visited the store during business hours for one day and purchase count information indicating the number of customers who purchased products during business hours for one day. The report information also includes purchase rate information indicating the proportion of customers who purchased products among customers who visited the store during business hours for one day.

[0003] Japanese Patent Application Laid-Open No. 2018-128895

[0004] In Patent Document 1, the report information includes a purchase rate that indicates the percentage of payments made relative to the number of people entering the store. The purchase rate can be used for product display and sales promotion planning. However, customers who visit a store are not limited to individuals; several customers may visit the store in groups, such as families, friends, or couples. In such cases, one person in the group may make the payment on behalf of the group.

[0005] For example, if five separate people enter a store and one of them makes a payment, the purchase rate calculated in Patent Document 1 is 1 / 5. Similarly, if a family of five enters a store and one of them makes a payment, the purchase rate calculated in Patent Document 1 is also 1 / 5. However, even if the purchase rate is the same, the actual meaning of the purchase rate differs between when one of five separate people makes a payment and when one of five people makes a payment.

[0006] In view of the above circumstances, the present disclosure aims to provide a purchase rate calculation device, a purchase rate calculation method, and a computer-readable medium that can calculate purchase rates on a group basis even when customers visit a store in groups.

[0007] To achieve the above object, the present disclosure provides, as a first aspect, a purchase rate calculation device. The purchase rate calculation device includes: a grouping unit that groups multiple customers entering a store into multiple groups, each group including one or more customers, based on images of the customers entering the store; a group identification unit that, when the customers make a payment at a POS device in the store, identifies a group to which the customers belong based on images of the customers who made the payment and determines the identified group as a group that has made a purchase; and a purchase rate calculation unit that calculates the group purchase rate based on the number of groups entering the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0008] The present disclosure provides, as a second aspect, a purchase rate calculation method, which includes grouping multiple customers entering a store into multiple groups, each group including one or more customers, based on images of the customers entering the store, identifying the group to which the customer belongs based on the image of the customer who made the payment when the customer makes a payment at a POS device in the store, determining the identified group as a group that has made a purchase, and calculating the group purchase rate based on the number of groups that enter the store in a specified period of time and the number of groups determined to have made the purchase in the specified period of time.

[0009] In a third aspect, the present disclosure provides a computer-readable medium storing a program for causing a computer to execute a process including: grouping multiple customers entering a store into multiple groups, each group including one or more customers, based on images of the customers entering the store; identifying the group to which the customer belongs based on the image of the customer who made the payment when the customer makes a payment at a POS device in the store; determining the identified group as a group that has made a purchase; and calculating a group purchase rate based on the number of groups entering the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0010] The purchase rate calculation device, purchase rate calculation method, and computer-readable medium according to the present disclosure can calculate the purchase rate on a group basis even when customers visit a store in groups.

[0011] A block diagram showing an example of a schematic configuration of a purchase rate calculation device according to the present disclosure. A block diagram showing an example of the configuration of a purchase rate calculation device according to an embodiment of the present disclosure. A diagram showing a specific example of customer information. A diagram showing a specific example of group information. A flowchart showing an operation procedure for determining group attributes. A flowchart showing an operation procedure for determining whether a purchase has been made. A flowchart showing an operation procedure for calculating a group purchase rate. A block diagram showing an example of the configuration of a computer device.

[0012] Prior to describing embodiments of the present disclosure, an overview of the present disclosure will be described. Fig. 1 shows an example of a schematic configuration of a purchase rate calculation device according to the present disclosure. The purchase rate calculation device 10 includes a grouping unit 11, a group identification unit 12, and a purchase rate calculation unit 13.

[0013] The grouping unit 11 groups multiple customers entering the store into multiple groups, each including one or more customers, based on images of the customers entering the store. When a customer makes a payment at a POS device in the store, the group identification unit 12 identifies the group to which the customer belongs based on the image of the customer who made the payment. The group identification unit 12 determines the identified group as a group that has made a purchase. The purchase rate calculation unit 13 calculates the group purchase rate based on the number of groups that entered the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0014] In the present disclosure, the grouping unit 11 groups customers entering a store, and the group identification unit 12 determines the group to which a customer who has made a payment belongs as the group that has made a purchase. The purchase rate calculation unit 13 calculates the group purchase rate based on the number of groups that entered the store and the number of groups that have made a purchase. In the present disclosure, for example, if five people enter a store as a group and one of the five people makes a payment, that group is determined to be the group that has made a purchase. Therefore, the purchase rate calculation device 10 according to the present disclosure can calculate the purchase rate for each group even when customers visit a store in groups.

[0015] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the following description and drawings have been omitted or simplified as appropriate for clarity of explanation. In addition, in the following drawings, the same or similar elements are designated by the same reference numerals, and duplicate explanations will be omitted as necessary.

[0016] FIG. 2 shows an example configuration of a purchasing rate calculation device according to an embodiment of the present disclosure. The purchasing rate calculation device 110 includes an image acquisition unit 111, a POS data acquisition unit 112, a customer detection unit 113, a grouping unit 114, a group attribute determination unit 115, a purchasing group identification unit 116, a purchasing rate calculation unit 117, and an analysis unit 118. The purchasing rate calculation device 110 may be physically configured as a device having one or more processors and one or more memories. For example, at least a portion of the functions of each unit in the purchasing rate calculation device 110 may be realized by the processor executing processing in accordance with instructions read from the memory. The purchasing rate calculation device 100 corresponds to the purchasing rate calculation device 10 shown in FIG. 1.

[0017] The purchasing rate calculation device 110 is connected to multiple cameras 200 and one or more POS devices 210. The multiple cameras 200 are placed in a store and capture images of a predetermined area within the store. The multiple cameras 200 include a camera near the store entrance that captures images or videos of customers visiting the store. The multiple cameras 200 also include a camera that captures images or videos of the area of ​​the cash register counter where the POS device 210 is installed. The multiple cameras 200 may include one or more cameras that capture images or videos of an aisle area within the store. The multiple cameras 200 may also include a camera placed in a parking lot. The camera 200 may be a camera that captures images or videos within a predetermined angle of view, or may be an omnidirectional camera that can capture 360-degree images in all directions, up, down, left, and right.

[0018] The POS device 210 is a device that performs sales processing and the like in a store. The POS device 210 is also called a POS terminal or a cash register. The POS device 210 may be a regular cash register in which an employee registers purchased items and performs settlement. Alternatively, the POS device 210 may be a semi-self-service cash register in which an employee registers purchased items and customers pay at a cash register. The POS device 210 does not need to be a manned cash register that requires the involvement of an employee; the POS device 210 may be an unmanned cash register or a self-service cash register in which customers perform the process from registering purchased items to settling.

[0019] Video acquisition unit 111 acquires from camera 200 an image or video acquired by camera 200. Video acquisition unit 111 may acquire the image or video acquired by camera 200 in real time, or may acquire the image or video from a video storage device that stores the image or video acquired by camera 200. Camera 200 may include a microphone, and video acquisition unit 111 may acquire audio in addition to the image or video.

[0020] The customer detection unit 113 detects customers from images of the inside of the store acquired by the video acquisition unit 111. The customer detection unit 113 detects customers from images acquired by a camera 200 that captures the area at the entrance of the store, for example. For example, the customer detection unit 113 detects a person walking through the entrance of the store toward the interior of the store as a customer. The customer detection unit 113 assigns a customer ID (identifier) ​​to each customer detected at the entrance of the store. The customer detection unit 113 may detect customers from images acquired by a camera 200 that captures an area inside the store different from the entrance. The customer detection unit 113 may estimate attributes of the detected customers based on the images of the customers. The customer attributes include, for example, gender, age, and whether or not the customer is pregnant.

[0021] Note that even if a person is detected in an image, the customer detection unit 113 will not detect the person as a customer if the person is a store employee. For example, the customer detection unit 113 may detect a person entering or leaving an area where customers are not allowed, such as the area where the cash register is operated or the back room, as an employee rather than a customer. Alternatively, the customer detection unit 113 may detect a person wearing a store uniform, a person wearing a store employee ID, or a person wearing an intercom as an employee. If facial information of employees is registered, the customer detection unit 113 may detect the person as an employee if the face of the person detected in the image matches or is similar to the registered facial information.

[0022] The grouping unit 114 groups multiple customers detected by the customer detection unit 113 into multiple groups each including one or more customers based on the image acquired by the camera 200. The grouping unit 114 groups customers entering the store based on the distance between customers detected by the customer detection unit 113 in the image acquired by the camera 200 that captures the area around the entrance of the store, for example. The grouping unit 114 may also group customers entering the store based on the orientation of the customers detected by the customer detection unit 113 in the image acquired by the camera 200. When images can be acquired from a camera installed in a parking lot, the grouping unit 114 may group customers exiting the same car in the parking lot into the same group.

[0023] For example, when multiple customers are detected by the customer detection unit 113, the grouping unit 114 groups customers whose distance between them is within a predetermined value into the same group. The predetermined value used as the criterion for determining whether customers are in the same group may be changed depending on the level of congestion in the surrounding area, for example, the number of people per unit area. When there are customers holding hands, the grouping unit 114 groups the customers holding hands into the same group. When multiple customers are detected, the grouping unit 114 may measure the time that the customers are facing each other. If the measured time is equal to or longer than a certain period of time, the grouping unit 114 may group the customers into the same group. Note that when only one customer is detected from an image, the grouping unit 114 groups the customer into a group to which only that person belongs.

[0024] Furthermore, when customer voices are acquired, the grouping unit 114 may group customers based on the presence or absence of conversation between the customers, in addition to distance or orientation. For example, if the distance between multiple customers is within a predetermined value and customers who are within the predetermined value are conversing with each other, the grouping unit 114 groups the customers into the same group. The grouping unit 114 may count the number of conversations between customers and group the customers into the same group if the customers have conversed with each other two or more times. In this case, if a customer has only one conversation with an unknown person, such as when the customers bump into each other, the customer and the unknown person can be prevented from being grouped into the same group. The grouping unit 114 may group the customers by applying the images acquired by the camera 200 and the customer voices to the trained model. The grouping unit 114 corresponds to the grouping unit 11 shown in FIG. 1.

[0025] The customer information storage unit 121 stores information about each customer detected by the customer detection unit 113. The information stored in the customer information storage unit 121 is also called customer information. Figure 3 shows a specific example of customer information stored in the customer information storage unit 121. In Figure 3, customer ID indicates an identifier assigned to a customer. Entry time indicates the time when a customer identified by the customer ID entered the store. Customer attributes indicate the estimated attributes of a customer identified by the customer ID. Group ID indicates the identifier of a group to which a customer identified by the customer ID belongs.

[0026] The customer detection unit 113 assigns a customer ID to the detected customer and records the assigned customer ID in the customer information. The customer detection unit 113 also records the time when the customer was detected at the store entrance as the customer's entry time in the customer information. The customer detection unit 113 estimates the customer's attributes and records the estimated customer attributes in the customer information. The grouping unit 114 records the group ID of the group to which each customer belongs in the group ID. The grouping unit 114 records the same group ID for customers belonging to the same group.

[0027] After grouping customers at the store entrance, the grouping unit 114 may regroup them depending on the customer's subsequent behavior. For example, the grouping unit 114 determines whether a customer to be added to a group is detected based on an image of the customer acquired at a location other than the store entrance. As an example, the grouping unit 114 tracks the movement of customers within the store using images from cameras installed at multiple locations within the store. The grouping unit 114 determines whether two or more customers who were grouped into separate groups when they entered the store are moving together within the store after entering. If the grouping unit 114 determines that they are moving together, it determines that a customer to be added to a group has been detected. In this case, if the grouping unit 114 determines that a customer to be added has been detected, it adds the customer to the group.

[0028] For example, suppose that a customer with customer ID "001" is grouped into a group with group ID "Gr01" when entering the store, and a customer with customer ID "004" is grouped into a group with group ID "Gr04." In this case, suppose that the customer with customer ID "004" joins up with the customer with customer ID "001," the distance between the customer with customer ID "004" and the customer with customer ID "001" becomes equal to or less than a predetermined value, and they move together within the store. In this case, the grouping unit 114 may add the customer with customer ID "004" to the group with group ID "Gr01." Specifically, the grouping unit 114 may add the customer with customer ID "004" to the group with group ID "Gr01" by changing the group ID of the customer with customer ID "004" from "Gr04" to "Gr01" in the customer information stored in the customer information storage unit 121.

[0029] The group attribute determination unit 115 determines or estimates the attributes of each group. Group attributes include, for example, family, married couple, couple, and friend. The group attribute determination unit 115 determines the attributes of a group based on, for example, at least one of the distance between customers included in an image of customers entering a store, the number of customers belonging to the group, and the attributes of each customer belonging to the group. Instead of or in addition to the distance, number of customers, and attributes, the group attribute determination unit 115 may determine the attributes of a group based on the presence or absence of conversation between customers belonging to the group and the content of that conversation.

[0030] The group attribute determination unit 115 may further determine or estimate the family structure of the group based on the attributes of each customer belonging to the group. For example, the group attribute determination unit 115 may determine the number of generations in the family. Specifically, the group attribute determination unit 115 may determine whether the family is a family of adults only, a family including adults and children, or a family including two generations of adults and children. The group attribute determination unit 115 may also determine whether the group includes a pregnant customer.

[0031] The POS data acquisition unit 112 acquires POS data from the POS device 210. The POS data includes the time when the customer made a payment and information about the products purchased by the customer. If multiple POS devices 210 are installed in a store, the POS data includes information identifying the POS device 210 at which the customer made a payment.

[0032] When a customer makes a payment at the POS device 210, the purchasing group identification unit 116 identifies the group to which the customer belongs based on an image of the customer who made the payment. For example, the purchasing group identification unit 116 detects the customer from an image acquired by the camera 200 that captures the area of ​​the POS device 210, and identifies the detected customer. The purchasing group identification unit 116 references the customer information storage unit 121 to identify the group to which the identified customer belongs. The purchasing group identification unit 116 determines that the identified group is a group that has made a purchase. If even one of the multiple customers belonging to a group has made a payment, the purchasing group identification unit 116 determines that the group is a group that has made a purchase.

[0033] The purchasing group identification unit 116 may determine whether a customer has made a payment based on an image of the area of ​​the POS device 210. For example, the purchasing group identification unit 116 may determine that a customer has made a payment if it is detected from the image that a receipt has been issued by the POS device 210 or that the customer has received a receipt. Alternatively, the purchasing group identification unit 116 may determine that a customer has made a payment if it is detected from the image that change or a card serving as a payment medium has been ejected from the POS device 210 or that the customer has received change or a card. The purchasing group identification unit 116 may determine that a customer has made a payment if it is detected from the image that the customer has swiped a card or a terminal device over the POS device 210. Even if a customer is detected in the image of the area of ​​the POS device 210, if it is not detected that the customer has made a payment, the purchasing group identification unit 116 determines that the customer has not made a payment.

[0034] The purchasing group identification unit 116 may obtain the time of payment from an image acquired by the camera 200 capturing an image of the area of ​​the POS device 210. For example, the purchasing group identification unit 116 may obtain the time at which it is detected in the image that a receipt has been issued as the time of payment. Alternatively, the purchasing group identification unit 116 may obtain the time at which it is detected in the image that change or the payment medium presented by the customer has been dispensed as the time of payment. Furthermore, the purchasing group identification unit 116 may obtain the time at which it is detected in the image that the customer has moved the payment medium to a predetermined position as the time of payment.

[0035] The purchasing group identification unit 116 may associate the group that made the purchase with the POS data based on the acquired payment time and the payment time included in the POS data acquired by the POS data acquisition unit 112. For example, the purchasing group identification unit 116 may associate, with the group that made the purchase, the POS data acquired from the POS device 210 where the customer made the payment, which has the smallest difference between the payment time included in the POS data and the payment time acquired from the image. If one image includes multiple POS devices 210, the purchasing group identification unit 116 may determine which of the multiple POS devices 210 the customer made the payment at, depending on the customer's position on the image. The purchasing group identification unit 116 corresponds to the group identification unit 12 shown in FIG. 1.

[0036] The group information storage unit 122 stores information about each group. The information stored in the group information storage unit 122 is also called group information. FIG. 4 shows a specific example of group information stored in the group information storage unit 122. In FIG. 4, group ID indicates a group identifier. group attribute indicates the attribute of the group identified by the group ID. family structure indicates the family structure of the group identified by the group ID. purchase indicates whether or not a purchase has been made in the group identified by the group ID. purchased items indicate items purchased by customers belonging to the group identified by the group ID.

[0037] The group attribute determination unit 115 records the determined or estimated attributes of the group in the group information. Furthermore, if the group attribute determination unit 115 determines or estimates the family structure, it records the estimated family structure in the group information. The purchasing group identification unit 116 records "Yes" in the group information for groups that have made purchases, indicating that a purchase has been made. For example, in the group information, the initial value of the information indicating whether or not a purchase has been made for each group is "No," indicating that no purchase has been made. The purchasing group identification unit 116 changes the information indicating whether or not a purchase has been made from "No" to "Yes" for groups that have made purchases. When the purchasing group identification unit 116 associates POS data with a group that has made a purchase, it records the products purchased by customers included in the POS data in the group information.

[0038] The purchase rate calculation unit 117 calculates the group purchase rate based on the number of groups that enter the store during a predetermined period and the number of groups that are determined to have made a purchase during the predetermined period. The purchase rate calculated by the purchase rate calculation unit 117 is also called a group purchase rate. The purchase rate calculation unit 117 references, for example, the customer information storage unit 121 and the group information storage unit 122, and acquires the total number of groups that entered the store during the predetermined period and the number of groups that made a purchase among the groups that entered the store during the predetermined period. The purchase rate calculation unit 117 calculates the ratio of groups that made a purchase to the total number of groups that entered the store as the group purchase rate.

[0039] The purchase rate calculation unit 117 may calculate a group purchase rate for each group attribute. In this case, the purchase rate calculation unit 117 may acquire, for a specific attribute, the total number of groups of the specific attribute that entered the store and the number of groups of the specific attribute that made a purchase. The purchase rate calculation unit 117 may calculate the ratio of the number of groups of the specific attribute that made a purchase to the total number of groups of the specific attribute that entered the store as the group purchase rate for that characteristic attribute.

[0040] Furthermore, the purchase rate calculation unit 117 may calculate a group purchase rate for one or more products selected from a plurality of products sold in a store. In this case, the purchase rate calculation unit 117 refers to the group information storage unit 122 and obtains the number of groups that have made a purchase and whose purchased products include the selected specific product. The purchase rate calculation unit 117 may calculate the ratio of the number of groups whose purchased products include the specific product to the total number of groups that entered the store during a predetermined period as the group purchase rate for the specific product.

[0041] The purchase rate calculation unit 117 outputs the group purchase rate to a person such as a store manager. The purchase rate calculation unit 117 displays the group purchase rate on a display device, for example. The store manager can use the group purchase rate when displaying products, planning sales promotion measures, etc. The purchase rate calculation unit 117 corresponds to the purchase rate calculation unit 13 shown in FIG. 1.

[0042] Here, the group attribute determination unit 115 may determine or estimate a resale group, which indicates a group of customers who are interested in reselling, as an attribute of the group. The group attribute determination unit 115, for example, acquires customer voices and determines whether customers belonging to the group are speaking a foreign language. Here, a foreign language may mean a language other than the official language of the country where the store is located, or a language that is different from one or more languages ​​spoken by residents of the area where the store is located. If the group attribute determination unit 115 determines that customers belonging to the group are speaking a foreign language, the group may be determined or estimated to be a resale group.

[0043] Furthermore, customers who enter a store for the purpose of reselling are likely to stay for a short period of time because they come to the store to purchase a specific product. The group attribute determination unit 115 may measure the stay time of customers belonging to a group and determine whether the group is a resale group based on the stay time. For example, the group attribute determination unit 115 may determine that a group whose stay time is shorter than the expected stay time of a typical customer is a resale group.

[0044] The group attribute determination unit 115 may determine whether a group is a resale group based on the number of products purchased in each group. The group attribute determination unit 115 may, for example, determine whether customers belonging to a group have purchased a predetermined number or more of a specific product. When the group attribute determination unit 115 determines that customers belonging to a certain group have purchased a predetermined number or more of a specific product, the group may be determined or estimated to be a resale group.

[0045] Furthermore, the group attribute determination unit 115 may determine whether a group is a resale group based on the type or category of purchased products. If the types or categories of purchased products in a certain group are biased toward a specific type or category, the group attribute determination unit 115 may determine or estimate that the group is a resale group.

[0046] The analysis unit 118 analyzes purchasing trends for each group attribute based on the group information stored in the group information storage unit 122 and the POS data associated with the group that made a purchase. The analysis unit 118 analyzes, for example, the purchase amount, popular products, popular product categories, and store visit time for each group attribute. The analysis unit 118 outputs the analysis results to a person such as a store operations manager. The store operations manager can use the analysis results of the analysis unit 118 to consider, for example, which people to target for promotional measures. Furthermore, the store operations manager can recognize the appropriate stocking order and purchase quantity for a certain product from the analysis results of the analysis unit 118.

[0047] Next, the operating procedure of the purchase rate calculation device 110 will be described. The operating procedure of the purchase rate calculation device 110 corresponds to the purchase rate calculation method. First, the operating procedure of determining group attributes in the purchase rate calculation device 110 will be described. FIG. 5 shows the operating procedure of determining group attributes. The video acquisition unit 111 acquires images and audio of the store entrance and other locations from the camera 200 (step A1). The customer detection unit 113 detects customers from the images acquired in step A1 (step A2). In step A2, the customer detection unit 113 detects multiple customers from images acquired by the camera 200 capturing an image of the store entrance area, for example.

[0048] The grouping unit 114 calculates the distance between the multiple customers detected in step A2 (step A3). The grouping unit 114 determines whether the distance is within a predetermined value (step A4). If the grouping unit 114 determines in step A4 that the distance is within the predetermined value, it determines whether there is a conversation between the customers who are within the predetermined distance (step A5). If the grouping unit 114 determines that there is a conversation in step A5, it groups the customers who are within the predetermined distance into the same group (step A6).

[0049] If it is determined in step A4 that the distance exceeds a predetermined value, or if it is determined in step A5 that there is no conversation, the grouping unit 114 groups the multiple customers into different groups. The group attribute determination unit 115 determines the group attributes for each group (step A7).

[0050] Next, the operational procedure for determining whether or not a purchase has been made in the purchasing rate calculation device 110 will be described. Figure 6 shows the operational procedure for determining whether or not a purchase has been made. The video acquisition unit 111 acquires, from the camera 200, an image of the area in the store where the POS device 210 is installed (step B1). The purchasing group identification unit 116 detects people, i.e., customers, from the image acquired in step B1 (step B2). The purchasing group identification unit 116 identifies the group to which the customer detected in step B2 belongs (step B3). In step B3, the purchasing group identification unit 116 acquires, for example, the group ID associated with the customer ID of the customer detected in step B2 from the customer information stored in the customer information storage unit 121.

[0051] The purchasing group identification unit 116 determines whether the customer has purchased a product (step B4). In other words, the purchasing group identification unit 116 determines whether the customer has made a payment at the POS device 210. If the purchasing group identification unit 116 determines in step B4 that the customer has purchased a product, it determines that the group identified in step B3 is a group that has made a purchase. In this case, the purchasing group identification unit 116 records information indicating a purchase for the group identified in step B3 (step B5). If the purchasing group identification unit 116 determines in step B4 that the customer has not purchased a product, it does not record information indicating a purchase for the group identified in step B3 in the group information storage unit 122.

[0052] Next, the operational procedure for calculating the group purchase rate in the purchase rate calculation device 110 will be described. Figure 7 shows the operational procedure for calculating the group purchase rate. The purchase rate calculation unit 117 references the customer information storage unit 121 and the group information storage unit 122 to obtain the number of groups that entered the store during a predetermined period, i.e., the number of visiting groups (step C1). The purchase rate calculation unit 117 also obtains the number of groups that made a purchase among the groups that entered the store during the predetermined period (step C2).

[0053] The purchase rate calculation unit 117 calculates the group purchase rate based on the number of visiting groups acquired in step C1 and the number of groups that made a purchase acquired in step C2 (step C3). In step C3, the purchase rate calculation unit 117 calculates the group purchase rate, for example, by dividing the number of groups that made a purchase by the number of visiting groups. The purchase rate calculation unit 117 may calculate the group purchase rate for a predetermined time period, such as a time period outside of store business hours. Alternatively, the purchase rate calculation unit 117 may calculate the group purchase rate every time a predetermined period of time has passed.

[0054] In this embodiment, the grouping unit 114 groups customers entering the store. When a customer makes a payment, the purchasing group identification unit 116 determines the group to which the paying customer belongs as the group that made a purchase. The purchase rate calculation unit 117 calculates the group purchase rate based on the number of groups that entered the store and the number of groups that made a purchase. In this embodiment, when multiple customers enter the store as a single group, if one of the customers in that group makes a payment, that group is determined to have made a purchase. If the purchase rate is calculated on an individual basis, the more customers in a group, the lower the calculated purchase rate. In this embodiment, the purchase rate calculation device 110 can calculate the purchase rate on a group basis even when customers visit the store in groups, thereby preventing the purchase rate from being calculated as low compared to the number of customers. The purchase rate calculation device 110 according to this embodiment is particularly useful in stores where customers are expected to visit in groups rather than individually.

[0055] In the present disclosure, the purchase rate calculation device 110 may be configured using a computer device or a server device. Fig. 8 shows an example configuration of a computer device that may be used in the purchase rate calculation device 110. The computer device 500 has a control unit (CPU: Central Processing Unit) 510, a storage unit 520, a ROM (Read Only Memory) 530, a RAM (Random Access Memory) 540, a communication interface (IF: Interface) 550, and a user interface 560.

[0056] The communication interface 550 is an interface for connecting the computer device 500 to a communication network via wired communication means, wireless communication means, etc. The user interface 560 includes a display unit such as a display, and an input unit such as a keyboard, a mouse, and a touch panel.

[0057] The storage unit 520 is an auxiliary storage device that can store various types of data. The storage unit 520 does not necessarily have to be a part of the computer device 500, but may be an external storage device or cloud storage connected to the computer device 500 via a network.

[0058] The ROM 530 is a non-volatile storage device. For example, a semiconductor storage device with a relatively small capacity, such as a flash memory, is used for the ROM 530. The programs executed by the CPU 510 can be stored in the storage unit 520 or the ROM 530. The storage unit 520 or the ROM 530 stores various programs for realizing the functions of each unit in the purchase rate calculation device 110, for example.

[0059] The program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include RAM, ROM, flash memory, solid-state drives (SSDs) or other memory technologies, compact discs (CDs), digital versatile discs (DVDs), Blu-ray discs or other optical disc storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. The program may also be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0060] The RAM 540 is a volatile storage device. Various semiconductor memory devices such as DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory) are used for the RAM 540. The RAM 540 can be used as an internal buffer for temporarily storing data, etc. The CPU 510 loads and executes a program stored in the storage unit 520 or the ROM 530 into the RAM 540. The CPU 510 executes the program, thereby realizing the functions of each unit in the purchase rate calculation device 110. The CPU 510 may have an internal buffer for temporarily storing data, etc.

[0061] In each of the above embodiments, the purchase rate calculation device 110 does not necessarily have to be configured as a single device. The purchase rate calculation device 110 may be configured using multiple physically separated devices.

[0062] The above describes the embodiments of the present disclosure in detail, but the present disclosure is not limited to the above-described embodiments, and changes and modifications to the above-described embodiments that do not deviate from the spirit of the present disclosure are also included in the present disclosure.

[0063] For example, some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0064] [Supplementary Note 1] A purchase rate calculation device comprising: a grouping unit that groups multiple customers entering a store into multiple groups each including one or more customers based on images of the customers entering the store; a group identification unit that, when the customer makes a payment at a POS (Point of Sales) device in the store, identifies the group to which the customer belongs based on an image of the customer who made the payment and determines the identified group as a group that has made a purchase; and a purchase rate calculation unit that calculates the group purchase rate based on the number of groups entering the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0065] [Supplementary Note 2] The purchasing rate calculation device according to Supplementary Note 1, wherein the grouping unit groups the plurality of customers into the plurality of groups based on at least one of the distance between the customers and the orientation of the customers included in images of the customers entering the store.

[0066] [Supplementary Note 3] The purchase rate calculation device according to Supplementary Note 2, wherein the grouping unit groups the plurality of customers into the plurality of groups based on the presence or absence of conversation between the customers in addition to the distance.

[0067] [Supplementary Note 4] The purchase rate calculation device according to any one of Supplementary Notes 1 to 3, further comprising a group attribute determination unit that determines the attributes of the group based on at least one of the distance between customers included in an image of customers entering the store, the number of customers belonging to the group, the attributes of each of the customers belonging to the group, and conversations between the customers belonging to the group.

[0068] [Supplementary Note 5] The purchase rate calculation device described in Supplementary Note 4, wherein the attributes of the group include family, and when the group attribute determination unit determines that the attribute of the group is family, it further determines the family structure of the group based on the attributes of each of the customers belonging to the group.

[0069] [Supplementary Note 6] The purchase rate calculation device according to Supplementary Note 4 or 5, wherein the purchase rate calculation unit calculates the purchase rate for each attribute of the group.

[0070] [Supplementary Note 7] The purchase rate calculation device according to any one of Supplementary Notes 4 to 6, wherein the group attributes include a resale group that indicates a group of customers who are interested in reselling.

[0071] [Appendix 8] The group attribute determination unit determines whether customers belonging to the group have purchased a predetermined number or more of a specific product, and if it determines that customers belonging to the group have purchased a predetermined number or more of a specific product, determines the attribute of the group to be a resale group.

[0072] [Appendix 9] The group attribute determination unit acquires the voice of the customer, determines whether the customer belonging to the group is speaking a foreign language, and if it determines that the customer belonging to the group is speaking a foreign language, determines the attribute of the group to be a resale group. This is the purchase rate calculation device described in Appendix 7 or 8.

[0073] [Appendix 10] The purchase rate calculation device described in any one of Appendices 1 to 9, wherein the grouping unit determines whether a customer to be added to the group is detected based on an image of the customer acquired at a location other than the store entrance, and if it determines that a customer to be added has been detected, adds the customer to the group of customers.

[0074] [Appendix 11] A purchase rate calculation device described in any one of Appendices 1 to 10, further comprising a data acquisition unit that acquires POS data including the time of payment made at the POS device, and the group identification unit associates the POS data with the identified group based on the time of payment acquired from an image of the customer who made the payment and the time of payment made included in the POS data.

[0075] [Appendix 12] The group identification unit, based on the image of the customer who made the payment, identifies at least one of the time a receipt was issued in the image, the time change or payment medium was ejected from the POS device, or the time the customer moved the payment medium to a specified position, and uses the identified time as the time of payment obtained from the image of the customer who made the payment. This is the purchase rate calculation device described in Appendix 11.

[0076] [Supplementary Note 13] The purchasing rate calculation device according to any one of Supplementary Notes 1 to 12, wherein the purchasing rate calculation unit calculates the purchasing rate for one or more products selected from a plurality of products sold at the store.

[0077] [Supplementary Note 14] A purchase rate calculation method comprising: grouping a plurality of customers entering a store into a plurality of groups, each group including one or more customers, based on images of the customers entering the store; when the customers make a payment at a POS (Point of Sales) device in the store, identifying the group to which the customers belong based on the images of the customers who made the payment and determining the identified group as a group that has made a purchase; and calculating the group purchase rate based on the number of groups entering the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0078] [Supplementary Note 15] A non-transitory computer-readable medium that stores a program for causing a computer to execute a process including: grouping multiple customers entering a store into multiple groups, each group including one or more customers, based on images of the customers entering the store; when the customers make a payment at a POS (Point of Sales) device in the store, identifying the group to which the customers belong based on images of the customers who made the payment and determining the identified group as a group that has made a purchase; and calculating the group purchase rate based on the number of groups entering the store in a specified period and the number of groups determined to have made a purchase in the specified period.

[0079] 10: Purchase rate calculation device 11: Grouping unit 12: Group identification unit 13: Purchase rate calculation unit 110: Purchase rate calculation device 111: Video acquisition unit 112: POS data acquisition unit 113: Customer detection unit 114: Grouping unit 115: Group attribute determination unit 116: Purchase group identification unit 117: Purchase rate calculation unit 118: Analysis unit 121: Customer information storage unit 122: Group information storage unit 200: Camera 210: POS device 500: Computer device 510: Control unit 520: Storage unit 530: ROM 540: RAM 550: Communication IF 560: User IF

Claims

1. a grouping unit that groups a plurality of customers entering the store into a plurality of groups, each group including one or more customers, based on images of the customers entering the store; a group identification unit that, when the customer makes a payment at a POS (Point of Sales) device in the store, identifies a group to which the customer belongs based on an image of the customer who made the payment and determines the identified group as a group that made a purchase; A purchase rate calculation device comprising a purchase rate calculation unit that calculates the group purchase rate based on the number of groups that enter the store during a specified period and the number of groups that are determined to have made a purchase during the specified period.

2. The purchasing rate calculation device according to claim 1 , wherein the grouping unit groups the plurality of customers into the plurality of groups based on at least one of the distance between the customers and the orientation of the customers included in the image of the customers entering the store.

3. The purchase rate calculation device according to claim 2 , wherein the grouping unit groups the plurality of customers into the plurality of groups based on the presence or absence of conversation between the customers in addition to the distance.

4. 4. The purchase rate calculation device according to claim 1, further comprising a group attribute determination unit that determines the attributes of the group based on at least one of the distance between customers included in an image of customers entering the store, the number of customers belonging to the group, the attributes of each of the customers belonging to the group, and conversations between the customers belonging to the group.

5. the group's attributes include family; The purchase rate calculation device according to claim 4 , wherein the group attribute determination unit, when determining that the attribute of the group is family, further determines the family structure of the group based on the attributes of each of the customers belonging to the group.

6. The attributes of the group include a resale group indicating a group of customers who intend to resell, The purchasing rate calculation device described in claim 4, wherein the group attribute determination unit determines whether customers belonging to the group have purchased a predetermined number or more of a specific product, and if it determines that customers belonging to the group have purchased a predetermined number or more of a specific product, determines the attribute of the group to be a resale group.

7. The purchasing rate calculation device according to any one of claims 1 to 3, wherein the grouping unit determines whether a customer to be added to the group is detected based on an image of the customer acquired at a location other than the store entrance, and if it determines that a customer to be added has been detected, adds the customer to the group of customers.

8. The device further includes a data acquisition unit that acquires POS data including the time when the payment was made at the POS device, A purchase rate calculation device described in any one of claims 1 to 3, wherein the group identification unit associates the POS data with the identified group based on the time of payment obtained from an image of the customer who made the payment and the time of payment included in the POS data.

9. Based on images of customers entering the store, the customers entering the store are grouped into a plurality of groups, each group including one or more customers; When the customer makes a payment at a POS (Point of Sales) device in the store, the group to which the customer belongs is identified based on an image of the customer who made the payment, and the identified group is determined to be the group that made the purchase; A purchase rate calculation method for calculating a group purchase rate based on the number of groups that enter the store during a specified period and the number of groups that are determined to have made a purchase during the specified period.

10. Based on images of customers entering the store, the customers entering the store are grouped into a plurality of groups, each group including one or more customers; When the customer makes a payment at a POS (Point of Sales) device in the store, the group to which the customer belongs is identified based on an image of the customer who made the payment, and the identified group is determined to be the group that made the purchase; A program for causing a computer to execute a process including calculating a group purchase rate based on the number of groups entering the store during a specified period and the number of groups determined to have made a purchase during the specified period.