JP7776343B2 - Sales information management device, sales information management device control method, sales information management system and program - Google Patents

Description

The present invention relates to a sales information management device that manages sales information based on ticketing, a control method for the sales information management device, a sales information management system that manages sales information based on ticketing, and a program that causes a computer to execute functions for managing sales information based on ticketing.

Currently, ticket vending machines for purchasing specific products are installed in restaurants, train stations, stores, etc. For example, at a restaurant, a customer operates the ticket vending machine to select the product they want, and the machine issues a voucher corresponding to the selection. The customer can then use the issued voucher to receive food and drink.

In this case, it would be desirable for the ticket machine installer to understand what types of products groups of customers, such as families, married couples, or other couples, tend to purchase depending on the season and time of day. This would allow the installer to appropriately develop a product strategy for their store and efficiently develop their business.

Patent Document 1 below describes a group attribute estimation method for estimating the group attributes of customers who purchase products. In this method, changes in the distance between customers in real space are detected from images captured inside a store. Based on these changes, customers who form the same group are estimated. Attributes are then estimated for each customer in the group, and the group attributes are estimated based on the estimated attributes.

Patent No. 4198951

However, with the estimation method described above, when a store is crowded and customers from another group are approaching one group, the other group may be mistakenly assumed to be customers from the first group.

In light of these issues, the present invention aims to provide a sales information management device, a control method for a sales information management device, a sales information management system, and a program that can accurately estimate sales information for a customer group and the products purchased by that group.

A first aspect of the present invention relates to a sales information management device. The sales information management device according to this aspect includes a control unit that acquires sales information for each ticket issued by a ticket vending machine, estimates the timing at which customers dispersed from in front of the ticket vending machine based on captured images of the area around the ticket vending machine, and estimates a customer group and sales information corresponding to that group based on the timing of the dispersion and the timing of the issuance of the tickets.

With the sales information management device according to this aspect, customer groups and the sales information corresponding to those groups are estimated based on the timing at which customers leave the ticket vending machine and the timing at which tickets are issued by the ticket vending machine. Therefore, even when a group of customers from another group is approaching another group, such as when the store is crowded, it is unlikely that customers from the other group will be mistakenly estimated as customers from the first group. This makes it possible to accurately estimate customer groups and the sales information for the products purchased by that group.

In the sales information management device according to this aspect, the control unit can be configured to infer that customers who dispersed within a predetermined time before and after the timing of the ticket issuance belong to the same group, and to infer the sales information of the ticket issuance that inferred the group as the sales information corresponding to that group.

Typically, a customer who has performed the operation to issue a ticket will leave the ticket vending machine once the ticket has been issued. Furthermore, if the customer who performed the operation to issue a ticket is standing in front of the ticket vending machine together with another customer, the customer may leave the ticket vending machine once the ticket has been issued, or, once they have decided which item they wish to purchase, they may tell the customer who performed the ticket issuing operation which item and leave the ticket vending machine before the ticket is issued. Therefore, by assuming that customers who leave within a specified time before and after the timing of ticket issuance belong to the same group, as in the above configuration, it is possible to accurately identify customers who belong to the same group. Furthermore, by assuming that the sales information for this ticket is the sales information for the group, it is possible to accurately link the group and the sales information.

In the sales information management device according to this aspect, when multiple tickets are issued within a predetermined time interval, the control unit can be configured to infer that customers who are separated within the period between the first and last of the multiple tickets and within a predetermined time before and after the period belong to the same group, and to infer the sales information for the multiple tickets that resulted in the inferred group as the sales information corresponding to that group.

When customers in the same group purchase multiple products, multiple ticket issuing operations may be performed. In this case, these tickets are issued continuously in a constant flow, so the time interval between these issuances is significantly shorter than when tickets are issued by customers from different groups. For this reason, if multiple tickets are issued within a specified time interval, it can be assumed that these multiple tickets were issued by the same group. Therefore, as described above, by assuming that discrete customers within the period between the first and last issuances of multiple tickets issued within a specified time interval or within a specified time before and after the first and last tickets are the same group, it is possible to accurately identify customers who belong to the same group. Furthermore, by inferring the sales information for these multiple tickets as the sales information corresponding to the group, it is possible to accurately identify the sales information for the products purchased by the group.

In the sales information management device according to this aspect, the predetermined time before the predetermined time before or after ...

With this configuration, even if customers from the same group leave the ticket machine relatively early before the ticket issuance timing, these customers can still be included in the group. Furthermore, because the specified time period before the group starts from the time when the customer last left in the previous group estimation, customers from other groups will not be included in the group. This allows for more accurate estimation of customers in the same group.

In the sales information management device according to this aspect, the predetermined time before and after the event may be set to a fixed time that has been set in advance. This simplifies processing.

In the sales information management device according to this aspect, the control unit may be configured to infer that customers who dispersed from in front of the ticket vending machine in response to ticket issuance belong to the same group, and to infer the sales information of the ticket issuance that inferred the group as the sales information corresponding to that group.

Typically, customers disperse from in front of the ticket vending machine after issuing a ticket. Therefore, in most cases, customers who disperse from in front of the ticket vending machine in response to issuing a ticket can be assumed to be part of the same group. With the above configuration, customers who disperse from in front of the ticket vending machine in response to issuing a ticket can be assumed to be part of the same group. This makes it possible to accurately infer customers from the same group. Furthermore, the sales information for the ticket that inferred this group is inferred as the sales information corresponding to that group. This makes it possible to accurately infer the sales information for that group. Therefore, with the above configuration, it is possible to accurately infer the sales information for customer groups and the products purchased by that group.

In this configuration, if at least one other ticket is issued between the first ticket issuance timing at which the group is estimated and the immediately preceding second ticket issuance timing among a series of ticket issuance timings at which customers disperse from in front of the ticket vending machine in response to ticket issuance, the control unit can be configured to include sales information for the other tickets in the sales information corresponding to the group.

With this configuration, the sales information for other tickets that are likely to be included in the sales information for the group estimated using the first ticket issuance timing is also included in the sales information for the group. This allows for more accurate estimation of the group's sales information.

Furthermore, in this configuration, if another customer leaves the ticket vending machine between the timing a predetermined time before the oldest ticket issued among those corresponding to the group and the first ticket issuance timing, the control unit can be configured to include the other customer in the group.

With this configuration, other customers who are likely to be included in the group estimated based on the first ticket issuance timing are also included in the group. This allows for more accurate estimation of the customers included in the group.

In the sales information management device according to this aspect, the control unit can be configured to estimate, based on the captured image, other customers who face the customer estimated to be in the same group for a predetermined period of time or more, or other customers who have been in contact with the customer estimated to be in the same group for a predetermined period of time or more, and include the estimated customers in the group.

This configuration allows other customers who are likely to be included in the group to be included in the group, making it possible to more accurately estimate the customers included in the group.

In the sales information management device according to this aspect, the control unit may be configured to exclude customers who leave without remaining in front of the ticket vending machine from the estimated group.

This configuration prevents customers outside the group who simply pass by the ticket machine from being assumed to be customers in the same group. This allows for more accurate estimation of customers who are in the same group.

In the sales information management device according to this aspect, the control unit may be configured to estimate the attributes of the group based on the captured image.

In this way, by further estimating the attributes of a group, it is possible to further link the sales information of that group with the attributes of that group. Therefore, in stores where ticket vending machines are installed, it is possible to provide information to store managers about the relationship between group attributes and sales information.

In this case, the control unit may be configured to estimate the attributes of each customer included in the group based on the captured image, and to estimate the attributes of the group based on the estimated attributes of each customer and the number of customers included in the group.

In this way, the attributes of a group (family, married couple, friends, single, etc.) can be estimated accurately by estimating the group's attributes based on the attributes of each customer in the group (gender, age, etc.) and the number of customers in the group.

The sales information management device according to this aspect includes a storage unit that stores information, and the control unit may be configured to store the group's attributes and the group's sales information in the storage unit in association with each other.

With this configuration, by appropriately reading the group attributes and sales information for those groups stored in the memory unit from the memory unit, it is possible to provide the manager of the store, etc. with information on the relationship between group attributes and sales information in the store, etc. where the ticket vending machine is installed.

The control unit may also be configured to extract facial information of each customer included in the group based on the captured image, and store the extracted facial information in the storage unit in association with at least one of the group and the sales information.

With this configuration, information such as customer repeat rates and product purchasing trends by the same customer can be provided to store managers, etc., based on the facial information stored in the memory unit.

In the sales information management device according to this aspect, the sales information may include the time of sale, the product sold, and the sales quantity. This allows the manager of a store or other facility to be provided with useful information indicating the relationship between customer attributes and product purchases.

A second aspect of the present invention relates to a control method for a sales information management device. The control method according to this aspect acquires sales information for each ticket issued by a ticket vending machine, estimates the timing at which customers dispersed from in front of the ticket vending machine based on captured images of the area around the ticket vending machine, and estimates a customer group and sales information corresponding to that group based on the timing of the dispersion and the timing of the issuance of the ticket.

A third aspect of the present invention relates to a sales information management system. The sales information management system according to this aspect includes a ticket vending machine, a camera that captures images of the area around the ticket vending machine, and a control unit that manages sales information for the ticket vending machine. The control unit acquires sales information for each ticket issued by the ticket vending machine, estimates the timing at which customers dispersed from in front of the ticket vending machine based on the images captured by the camera, and estimates a customer group and sales information corresponding to that group based on the timing of the dispersion and the timing of the issuance of the tickets.

A fourth aspect of the present invention is a program that causes a computer to perform the following functions: acquire sales information for each ticket issued by a ticket vending machine; estimate the timing at which customers dispersed from in front of the ticket vending machine based on captured images of the area around the ticket vending machine; and estimate a customer group and sales information corresponding to that group based on the timing of the dispersion and the timing of the issuance of the tickets.

The second to fourth aspects of the present invention achieve the same effects as the first aspect.

As described above, the present invention provides a sales information management device, a control method for a sales information management device, a sales information management system, and a program that can accurately estimate sales information for a customer group and the products purchased by that group.

The effects and significance of the present invention will become clearer from the description of the embodiments shown below. However, the embodiment shown below is merely an example of how the present invention may be put into practice, and the present invention is in no way limited to the embodiments described below.

FIG. 1 is a diagram showing the configuration of a sales information management system according to the first embodiment. FIG. 2 is a block diagram showing the configuration of a sales information management system according to the first embodiment. Fig. 3A is a flowchart showing a process of estimating customer departure timings according to embodiment 1. Fig. 3B is a flowchart showing a process of linking attributes of groups of customers who visit a store with sales information on products purchased by each group according to embodiment 1. FIG. 4 is a time chart schematically illustrating an example of processing for linking customer groups with sales information according to the first embodiment. FIG. 5 is a time chart schematically illustrating another example of the process of linking customer groups with sales information according to the first embodiment. Fig. 6(a) is a flowchart showing a group attribute estimation process according to embodiment 1. Fig. 6(b) is a diagram showing a state in which sales information and group attributes are linked according to embodiment 1. Fig. 6(c) is a diagram showing a state in which a group is linked with attributes and face information of customers included in the group according to embodiment 1. FIG. 7 is a time chart schematically illustrating an example of processing for linking a customer group with sales information according to a modification of the first embodiment. FIG. 8 is a flowchart showing a process for linking attributes of groups of customers who visit a store with sales information of products purchased by each group, according to the second embodiment. FIG. 9 is a time chart schematically illustrating an example of processing for linking customer groups with sales information according to the second embodiment. FIG. 10 is a flowchart schematically illustrating an example of processing for linking a customer group with sales information according to the first modification of the second embodiment. FIG. 11 is a time chart schematically illustrating an example of processing for linking a customer group with sales information according to the first modification of the second embodiment. FIG. 12 is a flowchart schematically illustrating an example of processing for linking a customer group with sales information according to the second modification of the second embodiment. FIG. 13 is a time chart schematically illustrating an example of processing for linking a customer group with sales information according to the second modification of the second embodiment. FIG. 14 is a time chart schematically illustrating another example of the process of linking customer groups with sales information according to the second modification of the second embodiment. FIG. 15 is a time chart schematically showing an example of processing for linking customer groups with sales information according to another modified example. FIG. 16 is a diagram showing a state in which sales information and face information of each group are linked together according to yet another modification.

Embodiments of the present invention will be described below with reference to the drawings.

<Embodiment 1>
FIG. 1 is a diagram showing the configuration of a sales information management system 1 according to the first embodiment.

The sales information management system 1 includes a ticket vending machine 10, a camera 20, and a sales information management device 30 (hereinafter referred to as the "management device 30").

The ticket vending machine 10 is installed in a store such as a restaurant. Customers visiting the store use the ticket vending machine 10 to purchase a voucher for the product they want. The camera 20 captures images of the area around the ticket vending machine 10. The camera 20 captures images of a specified area in front of the ticket vending machine 10 from behind the ticket vending machine 10. The management device 30 is connected to the ticket vending machine 10 and camera 20 so that they can communicate with each other. The management device 30 is installed in the office of the store where the ticket vending machine 10 is installed, for example. The management device 30 may also be installed in a facility other than a store. In this case, the management device 30 communicates with the ticket vending machine 10 and camera 20 via a public communications network such as the Internet.

Sales information based on ticket issuance is sent from the ticket vending machine 10 to the management device 30 at a predetermined timing, along with time information indicating the timing of ticket issuance. In addition, images captured by the camera 20 are sent to the management device 30 along with time information (time stamp). The management device 30 stores the sales information and time information received from the ticket vending machine 10, and the captured images and time information received from the camera 20. The management device 30 is, for example, configured as a server computer.

If multiple sets of ticket vending machines 10 and cameras 20 are installed in a store, the management device 30 may be connected to each set of ticket vending machines 10 and cameras 20 so that they can communicate with each other. In this case, the management device 30 stores the sales information and time information received from each set of ticket vending machines 10 and cameras 20, as well as the captured images and time information.

The ticket vending machine 10 has a roughly cubic housing that forms the outer shell of the device. A touch-panel operation and display unit 11 is located at the top front of the ticket vending machine 10. As will be explained later with reference to Figure 2, the operation and display unit 11 is configured with a transparent touch sensor 107 located on the top surface of a display 106. The display 106 is, for example, a liquid crystal display, and the touch sensor 107 is, for example, a pressure-sensitive (resistive) touch pad. However, the configuration of the operation and display unit 11 is not limited to this, and the touch sensor 107 may, for example, be a capacitance-type touch pad.

A banknote deposit/withdrawal slot 12 for depositing and withdrawing banknotes, a coin deposit slot 13 for depositing coins, a coin withdrawal slot 14 for withdrawing coins, and a ticket issuing slot 15 for issuing coupons are located in the center of the front of the ticket vending machine 10. Furthermore, a human presence sensor is located in the ticket vending machine 10. The human presence sensor detects when a customer is standing directly in front of the ticket vending machine 10.

When a human presence sensor detects that a customer is standing directly in front of the ticket vending machine 10, options are displayed on the operation and display unit 11. Here, options for food and drink available at the store are displayed. The customer touches the desired option from among the multiple options displayed on the operation and display unit 11. At this time, the customer can select multiple options at once. When the customer has finished selecting options, they touch the done button.

The customer then deposits bills or coins in the amount required to purchase the selected item into the bill deposit/withdrawal slot 12 or coin deposit slot 13. A voucher corresponding to the selected item is then issued from the ticket issuing slot 15. If the customer has selected multiple items, multiple vouchers are issued from the ticket issuing slot 15. If there is change, the bills or coins corresponding to the change are dispensed from the bill deposit/withdrawal slot 12 or coin withdrawal slot 14. This completes one step of the transaction.

Figure 2 is a block diagram showing the configuration of the sales information management system 1.

The ticket vending machine 10 includes a control unit 101, a memory unit 102, a banknote processing unit 103, a coin processing unit 104, a ticket issuing processing unit 105, a display 106, a touch sensor 107, a speaker 108, and a communication unit 109.

The control unit 101 includes a processing circuit such as a CPU (Central Processing Unit) and controls each unit according to programs stored in the memory unit 102. The memory unit 102 includes storage media such as ROM (Read Only Memory), RAM (Random Access Memory), and a hard disk, and stores programs executed by the control unit 101 and various data. The memory unit 102 is also used as a work area when the control unit 101 performs control.

The banknote processing unit 103 comprises a banknote storage unit for storing banknotes of various denominations, a transport unit for transporting banknotes, and a denomination discrimination unit for discriminating the denomination of transported banknotes, and is controlled by the control unit 101 to transport banknotes between the banknote storage unit and the banknote deposit/withdrawal slot 12 (see Figure 1). The coin processing unit 104 comprises a coin storage unit for storing coins of various denominations, a transport unit for transporting coins, and a denomination discrimination unit for discriminating the denomination of transported coins, and is controlled by the control unit 101 to transport coins between the coin storage unit and the coin deposit slot 13 and coin withdrawal slot 14 (see Figure 1).

The ticket issuing processing unit 105 includes a strip generating unit that generates paper strips and a printing unit that prints on the strips, and sends the vouchers, on which the names of food and drink items and other information have been printed by the printing unit, to the ticket issuing port 15.

The display 106 and touch sensor 107 make up the operation display unit 11 in Figure 1. The touch sensor 107 is a transparent film-like member that is overlaid on the display surface of the display 106. The display 106 displays predetermined information under the control of the control unit 101. The touch sensor 107 outputs coordinate information of the position touched by the operator to the control unit 101. The speaker 108 outputs predetermined audio under the control of the control unit 101. The output audio is output to the outside from an audio output window (not shown) formed on the housing of the ticket vending machine 10. The communication unit 109 communicates with the management device 30 under the control of the control unit 101.

The camera 20 comprises a control unit 201, an imaging unit 202, and a communication unit 203. The control unit 201 is configured, for example, by a microcomputer or the like, and controls each unit according to a program stored in built-in memory. The imaging unit 202 comprises an imaging lens and an imaging element, and captures images of the field of view under the control of the control unit 201. The communication unit 203 communicates with the management device 30 under the control of the control unit 201.

The management device 30 comprises a control unit 301, a memory unit 302, and a communication unit 303. The control unit 301 comprises a processing circuit such as a CPU, and controls each unit according to the programs stored in the memory unit 302. The memory unit 302 comprises storage media such as ROM, RAM, and a hard disk, and stores the programs executed by the control unit 301 and various data. The memory unit 302 is also used as a work area when the control unit 301 performs control.

In addition, the memory unit 302 stores a face recognition engine that the control unit 301 uses to perform face recognition from captured images. The memory unit 302 also stores an attribute estimation engine that the control unit 301 uses to estimate customer attributes such as age and gender from each piece of face information extracted by the face recognition engine.

The control unit 101 of the ticket vending machine 10 periodically transmits sales information based on each ticket issued during that period, which was temporarily stored in the memory unit 102, and time information indicating the timing of ticket issuance, to the management device 30 via the communication unit 109. The control unit 201 of the camera 20 also transmits, for example, image information captured continuously during the store's business hours and time information, which is a timestamp of the captured image, to the management device 30 via the communication unit 203.

The control unit 301 of the management device 30 stores in the memory unit 302 the sales information and time information received from the ticket vending machine 10 via the communication unit 303, and the captured images and time information received from the camera 20 via the communication unit 303. For example, after business hours for a day end, the control unit 301 of the management device 30 uses the sales information and time information for that day stored in the memory unit 302, and the captured images and time information for that day, to link the attributes of groups of customers who visited the store that day with the sales information of the products purchased by each group.

Figure 3(a) is a flowchart showing the process of estimating a customer's discrete timing.

The control unit 301 performs face recognition processing on one day's worth of captured images stored in the memory unit 302 (S101) and identifies faces contained in the captured images (S102). The control unit 301 tracks the identified faces in the series of captured images (S103) and estimates whether the tracked faces stayed in front of the ticket vending machine 10 and then dispersed from in front of the ticket vending machine 10 (S104).

In step S104, the control unit 301 determines whether the face being tracked stopped for a predetermined period of time or more (for example, several seconds or more) in an area set in the captured image that corresponds to the area in front of the ticket vending machine 10, and then moved out of (left) the captured image (the field of view of the camera 20). If the determination is YES, the control unit 301 estimates that the face being tracked stayed in front of the ticket vending machine 10 and then dispersed away from in front of the ticket vending machine 10 (S104: YES). If the determination is NO, the control unit 301 estimates that the face being tracked did not stay in front of the ticket vending machine 10, but dispersed away from in front of the ticket vending machine 10 (simply crossed in front of the ticket vending machine 10) (S104: NO).

If the determination in step S104 is YES, the control unit 301 stores the facial information of the tracked face and the discrete timing of this face in the memory unit 302. The stored facial information is obtained, for example, as the difference between the feature amounts at multiple sample points of a preset standard facial image and the feature amounts at corresponding sample points of the tracked facial image. Furthermore, the discrete timing is obtained, for example, as the time when the tracked face moves out of (exits) the captured image. Alternatively, the discrete timing may be the time when the face being tracked moves out of an area corresponding to the area in front of the ticket machine 10 set in the captured image. Furthermore, a matrix may be estimated from the captured image, and the time when the face being tracked moves out of that matrix may be used as the discrete timing.

If the determination in step S104 is NO, that is, if the tracked face disperses without remaining in front of the ticket vending machine 10, the control unit 301 ends processing for the tracked face without storing the facial information and dispersal timing for that face in the memory unit 302. The control unit 301 executes the process of Figure 3(a) for all faces identified in the captured images for one day that are the subject of processing. As a result, the facial information and dispersal timing of customers who remained in front of the ticket vending machine 10 on that day are stored in the memory unit 302.

Figure 3(b) is a flowchart showing the process of linking the attributes of groups of customers who visited a store with sales information for products purchased by each group.

The processing in Figure 3(b) is performed on the facial information and discrete timings of each customer stored in step S105 of Figure 3(a), as well as the sales information and time information (ticket issuance timing) stored for that day.

The control unit 301 references the time information (ticket issuance timing) of one day's worth of sales information stored in the memory unit 302 (S111). The control unit 301 groups tickets issued consecutively at a predetermined time interval or less as tickets issued by the same group of customers (S112). The predetermined time interval in step S112 is set to approximately the time interval between tickets issued when customers in the same group issue tickets sequentially (for example, several tens of seconds). The control unit 301 infers that customers (face information) among the grouped tickets that include discrete timings either in the period from the earliest ticket to the last ticket issued, or in a predetermined time before or after this period, belong to the same group (S113).

The control unit 301 estimates that the sales information of the tickets grouped in step S112 is the sales information of the customers estimated to be in the same group in step S113 (S114). The control unit 301 estimates the attributes of the group (family, married couple, single, etc.) based on the facial information of the customers estimated to be in the same group (S115). The control unit 301 associates the estimated attributes of the group with the sales information estimated for the group in step S114 and stores them in the memory unit 302 (S116). Furthermore, the control unit 301 associates the attributes and facial information of the customers included in the group with the group and stores them in the memory unit 302 (S117).

In step S112, if a specified ticket issuance timing is not consecutive with other ticket issuance timings within a specified time interval, the control unit 301 will assume that only tickets issued at that timing are issued by the same group. In this case, in step S113, the control unit 301 will assume that customers (face information) whose discrete timings are included within a specified time before or after the specified ticket issuance timing are from the same group.

Figure 4 is a time chart that schematically illustrates an example of the process of linking customer groups with sales information using the process shown in Figure 3(b).

The top row of Figure 4 shows the timing of ticket issuance. Here, tickets TC1 to TC3 are issued. The second row from the top of Figure 4 shows the timing when customer faces are recognized from the captured image. Here, the faces of customers C1 to C7 are recognized and tracked. The third row from the top of Figure 4 shows the timing when customers C1 to C7 leave the ticket vending machine 10. Customers C1 and C2 leave the ticket vending machine 10 at substantially the same time, and customer C3 leaves the ticket vending machine 10 alone. Furthermore, customers C4 to C7 leave the ticket vending machine 10 at substantially the same time.

The second row from the bottom in Figure 4 shows customers who are presumed to be in the same group, and the bottom row in Figure 4 shows the ticketing (sales information) linked to each group. Here, the sales information for ticketing TC2 is linked to the group of customers C1 and C2, and the sales information for ticketing TC1 and TC3 is linked to the group of customers C3 to C7. This linking is performed as follows using the processing in Figure 3(b).

First, the time interval ΔT10 between issuances TC1 and TC3 is shorter than the predetermined time interval in step S112 of Figure 3(b). Therefore, in step S112, issuances TC1 and TC3 are grouped as tickets issued by the same group. Since the time interval between issuances TC2 and TC3 is longer than the predetermined time interval, issuances TC2 and TC3 are not grouped.

Next, predetermined times ΔT11 and ΔT12 are set for the grouped ticket issuances TC1 and TC2, and customers whose discrete timing falls within either the time interval ΔT10 or the predetermined times ΔT11 and ΔT12 are presumed to be in the same group (step S113 in Figure 3(b)). The predetermined times ΔT11 and ΔT12 are set to, for example, predetermined fixed times (e.g., several tens of seconds). Here, because the discrete timings of customer C3 and customers C4 to C7 fall within the predetermined times ΔT11 and ΔT12, customers C3 to C7 are presumed to be in the same group.

Note that, because ticket issuance TC2 is not grouped with other tickets, predetermined times ΔT11 and ΔT12 are set before and after the issuance timing of ticket issuance TC2. Here, because the discrete timing of customers C1 and C2 is included in the later predetermined time ΔT12, it is assumed that customers C1 and C2 are in the same group.

Once customers are grouped in this way, the sales information of the tickets that have been estimated for the group is estimated as the sales information corresponding to that group (step S114 in Figure 3(b)). In this case, the tickets estimated for the group of customers C3 to C7 are tickets TC1 and TC3, so the sales information of tickets TC1 and TC3 is linked to the group of customers C3 to C7. Furthermore, the ticket estimated for the group of customers C1 and C2 is ticket TC2, so the sales information of ticket TC2 is linked to the group of customers C1 and C2.

Note that, unlike the example in Figure 4, there may be cases where the time interval ΔT10 set by ticketing TC1 and TC3 and the predetermined times ΔT11 and ΔT12 before and after it contain only the discrete timing of one customer. Similarly, there may be cases where the predetermined times ΔT11 and ΔT12 before and after it set by ticketing TC2 contain only the discrete timing of one customer. In these cases, it is presumed that a group is made up of a single customer, and sales information is linked to this group in the same way as above.

In addition, in the example of Figure 4, the predetermined time ΔT11 and the predetermined time ΔT12 are shown as having the same length of time, but the predetermined time ΔT11 and the predetermined time ΔT12 do not necessarily have to be the same length. For example, the predetermined time ΔT11 set at the front may be set longer than the predetermined time ΔT12 set at the rear.

Furthermore, the predetermined time periods ΔT11 and ΔT12 before and after the predetermined time periods ΔT11 and ΔT12 do not necessarily have to be preset fixed times. For example, as shown in FIG. 5, the predetermined time period ΔT11 before the predetermined time periods ΔT11 and ΔT12 before the predetermined time periods ΔT11 and ΔT12 may start immediately after the last discrete timing of the customer in the previous group estimation, i.e., in the example of FIG. 5, the latest discrete timing of customers C1 and C2. This makes it possible to prevent customers associated with the same group from being missed.

Figure 6(a) is a flowchart showing the group attribute estimation process performed in step S115 of Figure 3(b).

The control unit 301 references the facial information of customers included in the same group (S131). The control unit 301 estimates the attributes (gender, age) of each customer based on the referenced facial information (S132). The control unit 301 estimates the attributes (gender, age) of each customer in the group and the number of customers included in the group (number of facial information pieces) (S133). The control unit 301 estimates the attributes of the group (family, married couple, couple, single, etc.) based on the estimated attributes (gender, age) of each customer in the group and the number of customers (S134).

For example, if a group includes only male and female customers of parent generation age and customers of child generation age, the control unit 301 estimates the attribute of the group as family. If a group includes only male and female customers of the same age and at least one customer of the same age (regardless of gender), and the age difference between these customers is within a range that would allow them to be considered parent and child, the control unit 301 estimates the attribute of the group as family. If a group includes only male and female customers of parent generation age, the control unit 301 estimates the attribute of the group as married couple. If a group includes only male and female customers of younger generation age, the control unit 301 estimates the attribute of the group as couple. If a group includes multiple males or multiple females of younger generation age, the control unit 301 estimates the attribute of the group as friends. If a group includes only one customer, the control unit 301 estimates the attribute of the group as single. The control unit 301 estimates the attributes of the group as described above based on group attribute estimation rules previously stored in the memory unit 302.

Figure 6(b) is a diagram showing the state in which sales information and group attributes are linked through the processing of step S116 in Figure 3(b).

As shown in Figure 6(b), the sales information includes the date and time of sale, the product sold, and the price. The sales information also includes the sales quantity of each product. In the linkage in the top row of Figure 6(b), the products sold are one each of products A, B, C, and D. In the linkage in the fifth row from the top of Figure 6(b), the products sold are two products G and one product H.

Figure 6(c) is a diagram showing the state in which a group is linked to the attributes and facial information of the customers included in the group through the processing of step S117 in Figure 3(b).

As shown in Figure 6(c), customer attributes include gender, age, and number of people. Customer attributes are linked to the group attributes of the corresponding group. In addition, facial information of the customers who make up each group is linked to each customer.

The information in Figures 6(b) and (c) is stored in the memory unit 302 of the management device 30 in steps S116 and S117 of Figure 3(b). The store manager can refer to the information in Figures 6(b) and (c), for example, via a terminal that can communicate with the management device 30. In this case, the terminal may display sales information compiled by group attribute for a specified period (day of the week, week, month, season, etc.) or time period. For example, the total amount may be displayed for each group attribute. Alternatively, the number of purchases or the ratio of purchase amounts for each product may be displayed for a group attribute selected by the manager. Furthermore, for a product selected by the manager, the terminal may display trends for group attributes that purchased the product (for example, the number of purchases or the ratio of purchases for each group attribute).

The repeat rate of the same customer over a specified period may also be displayed based on facial information. Furthermore, the type of group in which the same customer visits the store may also be displayed. For example, the ratio of the number of visits by the same customer who visited the store alone to the number of visits by other customers over a specified period may be displayed. Furthermore, for a group of customers who visited the store multiple times as singles over a specified period, the ratio of the number of times this group purchased the same product to the total number of visits by this group of customers may be displayed.

The control unit 301 of the management device 30 may be capable of executing the aggregation and editing functions required to cause the terminal to display the above-described data. Such functions may be included in the above-described program stored in the memory unit 302 of the management device 30.

<Effects of First Embodiment>
According to the first embodiment, the following effects can be achieved.

In the configuration of Figure 2, the control unit 301 of the management device 30 acquires sales information for each ticket issued by the ticket vending machine 10 via the communication unit 303, and estimates the timing at which customers dispersed from in front of the ticket vending machine 10 based on captured images around the ticket vending machine 10 using the processing of Figure 3(a). Then, using the processing of Figure 3(b), estimates the customer group and the sales information corresponding to that group based on the timing of dispersion and the timing of ticket issuance. This prevents customers from the other group from being mistakenly assumed to be customers of the first group, even when a group of customers is approaching another group, such as when the store is crowded. Therefore, it is possible to accurately estimate the customer group and the sales information for the products purchased by that group.

As shown in FIG. 3(b), the control unit 301 infers that customers who are separated within a predetermined time before and after the timing of ticket issuance belong to the same group (S113), and infers the sales information of the ticket issuance that represents the inferred group as the sales information corresponding to that group (S114). For example, in the example of FIG. 4, the control unit 301 infers that customers C1 and C2 who are separated within predetermined times ΔT11 and ΔT12 before and after the timing of ticket issuance TC2 belong to the same group, and infers the sales information of ticket issuance TC2 as the sales information corresponding to that group.

Typically, a customer who has performed the operation to issue a ticket will leave the ticket vending machine once the ticket has been issued. Furthermore, if the customer who performed the operation to issue a ticket is standing in front of the ticket vending machine together with another customer, the customer may leave the ticket vending machine once the ticket has been issued, or, once they have decided which item they wish to purchase, they may tell the customer who performed the ticket issuing operation which item and leave the ticket vending machine before the ticket is issued. Therefore, by assuming that customers who leave within a specified time before and after the timing of ticket issuance belong to the same group, it is possible to accurately identify customers who belong to the same group. Furthermore, by assuming that the sales information for this ticket is the sales information for the group, it is possible to accurately link the group and the sales information.

As shown in FIG. 3(b), when multiple tickets are issued within a predetermined time interval, the control unit 301 infers that customers who are dispersed within the period between the first and last issuances of these multiple tickets and within a predetermined time before and after the first and last issuances of these multiple tickets belong to the same group (S113), and infers the sales information of the multiple tickets that this inferred group belongs to the same group (S114). For example, in the example of FIG. 4, when multiple tickets TC1 and TC3 are issued within a predetermined time interval, the control unit 301 infers that customers C3 to C7 who are dispersed within the time interval ΔT10 between the first and last issuances of these multiple tickets TC1 and TC3 and within predetermined times ΔT11 and ΔT12 before and after the time interval belong to the same group, and infers the sales information of these multiple tickets TC1 and TC3 belongs to the same group.

When customers in the same group purchase multiple products, multiple ticket issuing operations may be performed. In this case, these tickets are issued continuously in a constant flow, so the time interval between these issuances is significantly shorter than when tickets are issued by customers from different groups. For this reason, if multiple tickets are issued within a specified time interval, it can be assumed that these multiple tickets were issued by the same group. Therefore, as described above, by assuming that discrete customers within the period between the first and last issuances of multiple tickets issued within a specified time interval or within a specified time before and after the first and last tickets are the same group, it is possible to accurately identify customers who belong to the same group. Furthermore, by inferring the sales information for these multiple tickets as the sales information corresponding to the group, it is possible to accurately identify the sales information for the products purchased by the group.

As shown in Figure 5, the predetermined time ΔT11 before and after ΔT12 can be set to start immediately after the last customer separation timing in the previous group estimation. This allows customers from the same group to be included in the group even if they separate from the ticket vending machine 10 relatively earlier than the ticket issuance timing. Furthermore, because the predetermined time ΔT11 before the start timing starts immediately after the last customer separation timing in the previous group estimation, customers from other groups will not be included in the group. This allows for more accurate estimation of customers in the same group.

As shown in Figure 4, the predetermined time before and after may be set to a fixed time that has been set in advance. This simplifies the process.

As shown in FIG. 3(a), the control unit 301 sets customers who have stayed in front of the ticket vending machine 10 and then dispersed as targets for group estimation (S105). This prevents customers who are not in the group but simply pass by the ticket vending machine from being estimated as being in the same group. This allows for more accurate estimation of customers who are in the same group.

As shown in FIG. 3(b), the control unit 301 estimates the group's attributes based on the captured image (S115). In this way, by estimating the group's attributes, the sales information for that group can be further linked to the group's attributes. Therefore, in a store or the like where the ticket vending machine 10 is installed, information on the relationship between the group attributes and the sales information can be provided to the store manager or the like.

As shown in FIG. 6(a), the control unit 301 estimates the attributes of each customer included in the group based on the captured image (S132), and estimates the attributes of the group based on the estimated attributes of each customer and the number of customers included in the group (S134). In this way, by estimating the attributes of the group (family, married couple, couple, friends, single, etc.) based on the attributes of each customer included in the group (gender, age, etc.) and the number of customers included in the group, the attributes of the group can be accurately estimated.

As shown in FIG. 3(b), the control unit 301 associates the group attributes with the group sales information and stores them in the memory unit 302 (S116). As a result, by appropriately reading out the group attributes and sales information stored in the memory unit 302 from the memory unit 302 as described above, it is possible to provide the manager of the store, etc. with information on the relationship between the group attributes and sales information in the store, etc. where the ticket vending machine 10 is installed.

As shown in FIG. 3(b), the control unit 301 associates the facial information of each customer included in the group with the group and stores it in the memory unit 302 (S117). This makes it possible to provide information such as the customer's repeat customer rate and the product purchasing trends of the same customer to the manager of the store, etc., based on the facial information stored in the memory unit 302.

As shown in Figure 6(b), sales information may include the time of sale (sale date and time), the product sold, and the sales quantity. This allows store managers, etc., to be provided with useful information showing the relationship between customer attributes and product purchases.

<Example of change>
In the process of Figure 3(b), when multiple tickets are issued within a specified time interval, these tickets are grouped and then customers are grouped based on these tickets. However, it is also possible to first group customers whose tickets are issued at discrete times within a specified time before and after each ticket, and then group tickets issued within the specified time interval together with that group.

Figure 7 is a time chart that shows an example of the process of linking customer groups with sales information in this case.

In this case, customers C4 to C7, who are separated by a predetermined time ΔT11 and ΔT12 before and after the issuance of ticket TC1, are grouped together, and customer C3, who is separated by a predetermined time ΔT11 and ΔT12 before and after the issuance of ticket TC3, is grouped together. Since the time interval ΔT10 between ticket issuance TC1 and ticket issuance TC3 is less than or equal to the predetermined time interval, customers C4 to C7 and customer C3, who are grouped for ticket issuance TC1 and ticket issuance TC3, respectively, are grouped as being in the same group, and the sales information for ticket issuance TC1 and ticket issuance TC3 is linked as the sales information for this group.

As with the process in Figure 3(b), this process also estimates that customers dispersed within the time interval ΔT10 between the first and last issuance of multiple tickets TC1, TC3 issued within a specified time interval or less, and within the specified times ΔT11, ΔT12 before and after that, belong to the same group, and the sales information for the multiple tickets TC1, TC3 that estimated that group is estimated as the sales information corresponding to that group. This allows for accurate estimation of customer groups and their sales information.

<Embodiment 2>
In the above embodiment 1, customers whose timings are discrete within a predetermined time before and after the timing of ticket issuance are presumed to be in the same group, but in embodiment 2, customers who dispersed in response to ticket issuance, i.e., customers who dispersed within a predetermined time from the timing of ticket issuance, are presumed to be in the same group.

Figure 8 is a flowchart showing the process of linking the attributes of groups of customers who visit a store with sales information for products purchased by each group.

In embodiment 2, the process shown in FIG. 8 is executed instead of the process shown in FIG. 3(b). The other configurations and controls in this embodiment are the same as those in embodiment 1 above.

The control unit 301 sequentially references the time information (ticket issuance timing) of one day's worth of sales information stored in the memory unit 302 (S201). The control unit 301 compares the referenced ticket issuance timing with the discrete timing stored in step S105 of FIG. 3(a) and determines whether any customers have dispersed in response to the issuance of a ticket at this ticket issuance timing (S202). Specifically, the control unit 301 determines whether any discrete timing occurs within the period from this ticket issuance timing until a predetermined time has elapsed. This predetermined time is set based on the time that can normally be expected for a group of customers to disperse after completing the ticket issuance operation. The predetermined time can be set to, for example, several tens of seconds.

If there are no customers who dispersed in response to the issuance of tickets at this ticket issuance timing (S202: NO), the control unit 301 determines that there are no customers who will form a group for this ticket issuance timing and terminates processing for this ticket issuance timing.

On the other hand, if there are customers who dispersed in response to the issuance of this ticket at this timing (S202: NO), the control unit 301 estimates that the facial information (customers) containing the dispersed timings within the period from this timing until a predetermined time has elapsed are included in the same group (S203), and further estimates the sales information for that timing as the sales information for that group (S204). The control unit 301 then estimates the attributes of that group (S205) and associates the estimated group attributes with the sales information for that group, storing them in the storage unit 302 (S206). The control unit 301 then associates the group, customer attributes, and facial information with each other, storing them in the storage unit 302 (S207). The processing in steps S205 to S207 is the same as the processing in steps S115 to S117 in FIG. 3(b), respectively.

Once the processing for this ticket issuance timing is completed, the control unit 301 references the next ticket issuance timing and executes the processing from step S201 onwards for this ticket issuance timing. The control unit 301 repeatedly executes the same processing for each ticket issuance timing for one day.

Figure 9 is a time chart that schematically illustrates an example of the process of linking customer groups with sales information when the process in Figure 8 is performed.

In this example, the period ΔT20 from ticket issuance TC1 until a predetermined time has passed includes discrete timings for customers C4 to C7. Therefore, customers C4 to C7 are presumed to be part of the same group, and the sales information for ticket issuance TC1 is linked to this group. Furthermore, the period ΔT20 from ticket issuance TC2 until a predetermined time has passed includes discrete timings for customers C1 and C2. Therefore, customers C1 and C2 are presumed to be part of the same group, and the sales information for ticket issuance TC2 is linked to this group.

In contrast, the period ΔT20 from ticket issuance TC3 until a predetermined time has elapsed does not include any discrete timing for any customers. Therefore, no customer group is estimated for ticket issuance TC3, and the sales information for ticket issuance TC3 is not linked to any group.

<Effects of the Second Embodiment>
Usually, once a ticket has been issued, customers disperse from in front of the ticket vending machine 10. Therefore, in most cases, customers who disperse from in front of the ticket vending machine in response to ticket issuance can be assumed to be part of the same group. According to the processing of the second embodiment, as described above, customers who disperse from in front of the ticket vending machine in response to ticket issuance can be assumed to be part of the same group. Therefore, customers in the same group can be accurately assumed. Furthermore, the sales information of the ticket that has been issued to infer this group is assumed to be the sales information corresponding to the group. Therefore, the sales information of the group can be accurately estimated. Therefore, the processing of the second embodiment can also accurately infer the group of customers and the sales information of the products purchased by the group.

<Modification 1>
According to the processing of the second embodiment, as shown in the example of Fig. 9, a customer group is not estimated for ticket TC3, and the sales information of ticket TC3 is not linked to any group. However, because customers C1 and C2 are separated according to ticket TC2, it is highly likely that ticket TC3 was issued by a group of customers who separated according to the subsequent ticket TC1.

Therefore, in Modification Example 1, if at least one other ticket is issued between the first ticket issuance timing at which the group is estimated and the immediately preceding second ticket issuance timing among a series of ticket issuance timings at which customers disperse from in front of the ticket vending machine 10 in response to ticket issuance, the sales information for that other ticket is included in the sales information corresponding to the group estimated by the first ticket issuance timing.

Figure 10 is a time chart that schematically illustrates an example of the process of linking customer groups with sales information in Modification Example 1.

Figure 10 shows only steps S204 and S205 of the flowchart in Figure 8, and omits the other steps. Steps other than steps S204 and S205 are the same as those in Figure 8. In Modification Example 1, step S211 is added between steps S204 and S205. In step S211, the control unit 301 adds sales information for tickets issued after the previous ticket issuance for the group to the sales information for that group.

Figure 11 is a time chart that schematically shows an example of the process of linking customer groups with sales information when the process of Figure 10 is performed.

The example in Figure 11 is the same as the example in Figure 9. Therefore, as in the case of Figure 9, dispersed customers C4 to C7 are grouped according to ticket TC1, and the sales information of ticket TC1 is linked to this group. Furthermore, dispersed customers C1 and C2 are grouped according to ticket TC2, and the sales information of ticket TC2 is linked to this group.

Furthermore, in this example, there is at least one other issuance TC3 between issuance TC1 (first issuance timing) and the immediately preceding issuance TC2 (second issuance timing) (period ΔT30). Therefore, in step S211 of FIG. 10, the control unit 301 includes the sales information of the other issuance TC3 in the sales information corresponding to the group of customers C4 to C7. As a result, the sales information corresponding to the group of customers C4 to C7 becomes the sales information for issuance TC1 and TC3.

According to the processing of Modification Example 1, the sales information for ticket issuer TC3, which is likely to have been made by the group of customers C4 to C7, is further included in the sales information for the group of customers C4 to C7. This allows for a more accurate estimation of the group's sales information.

<Modification 2>
According to the processing of the above-described modified example 1, customer C3 is not included in any group, as shown in the example of Fig. 11. However, customer C3 is scattered near ticket issue TC3, which was estimated to have been issued by the group of customers C4 to C7 by the processing of step S211 of Fig. 10, and therefore is more likely to be included in the group of customers C4 to C7 than in the group of customers C1 and C2.

Therefore, in Modification Example 2, if another customer leaves the front of the ticket vending machine 10 between the timing of the referenced ticket issuance and the timing predating the oldest ticket issuance corresponding to the group by a predetermined amount of time, the other customer is included in the group.

Figure 12 is a time chart that schematically illustrates an example of the process of linking customer groups with sales information in Modification Example 2.

Figure 12 shows only steps S204, S205, and S211 from the flowchart in Figure 10, and omits the other steps. Steps other than steps S204, S205, and S211 are the same as those in Figure 10. In Modification Example 2, step S212 has been added between steps S211 and S205.

In step S212, if another customer leaves the ticket vending machine 10 between the time a predetermined time (for example, several tens of seconds) before the oldest ticket issued corresponding to the group and the time of the referenced ticket issuance, the control unit 301 includes the other customer in the group.

Figure 13 is a time chart that schematically illustrates an example of the process of linking customer groups with sales information when the process of Figure 12 is performed.

The example in Figure 13 is the same as the example in Figure 11. Therefore, as in the case of Figure 11, dispersed customers C4 to C7 are grouped according to ticket TC1, and the sales information for tickets TC1 and TC3 is linked to this group.

Furthermore, in this example, another customer C3 is scattered between the timing predating the oldest ticket issuance TC3 of the tickets TC1 and TC3 corresponding to the group of customers C4 to C7 by a predetermined time ΔT21 and the referenced ticket issuance timing (ticket issuance TC1). Therefore, in step S212 of FIG. 12, the control unit 301 includes the other customer C3 in the group of customers C4 to C7. As a result, customers C3 to C4 are grouped, and the sales information of tickets TC1 and TC3 is linked to this group.

According to the processing of Modification Example 2, customer C3, who is likely to be included in the group of customers C4 to C7, is also included in the group of customers C4 to C7. This allows for a more accurate estimation of the customers included in the group.

Note that, as in the example of Figure 14, if no other tickets were issued in the period ΔT30 between ticket issuance TC1 and ticket issuance TC2, the control unit 301 will include another customer C3 in the group of customers C4 to C7 in step S212 of Figure 12 if the other customer C3 was separated between the timing going back a predetermined time ΔT21 from ticket issuance TC1 and the referenced ticket issuance timing (ticket issuance TC1).

<Modification 3>
In the second embodiment, whether or not customers have dispersed in response to the issuance of tickets is estimated based on whether or not customers have dispersed within a predetermined time period since the issuance of tickets. However, the method for estimating whether or not customers have dispersed in response to the issuance of tickets is not limited to this.

For example, customers who dispersed at substantially the same time can be presumed to be part of the same group, and if the timing of these customers' dispersion falls within the period from the immediately preceding ticket issuance until a predetermined time has elapsed, it can be presumed that these customers dispersed in response to the issuance of a ticket at this timing, and the group can be linked to the sales information for that ticket.

Alternatively, customers who dispersed at substantially the same time can be presumed to be in the same group, and if the timing of ticket issuance falls within the period from the latest timing of dispersal of these customers to a timing going back a predetermined amount of time, it can be presumed that these customers dispersed in response to the issuance of a ticket at this timing, and the group can be linked to the sales information for that ticket.

<Other changes>
In the above-described first and second embodiments and their modifications, the attributes of each customer are estimated based on the facial information of each customer acquired from a captured image, but the attributes of each customer may also be estimated based on the appearance or physical characteristics of each customer, such as clothing or height. In this case, the attributes of each customer may be estimated by taking into account the appearance or physical characteristics in addition to the facial information.

Furthermore, the voices of customers standing in front of the ticket vending machine 10 may be picked up by a microphone, and this voice (conversation, voiceprints, etc.) may be further taken into consideration to estimate the attributes of each customer or group.

In the above-described first and second embodiments and their modifications, customer groups were estimated based on the timing at which customers dispersed from in front of the ticket machine. However, customer groups may also be estimated by taking into account factors such as the distance and contact between customers and the orientation of their faces. For example, in the example shown in FIG. 4, customer C3 was added to the group of customers C4 to C7 when the timing at which another customer C3 dispersed was included between the earliest ticket issuance timing T3 corresponding to the group and a predetermined time ΔT11 or ΔT21. However, as shown in FIG. 15, customer C8 may also be added to the group of customers C3 to C7 when customer C3 and customer C8 remain in contact with each other, or when customer C8's face faces face each other for a predetermined period of time or longer. This allows other customers who are likely to be included in the group to be included in the group, thereby more accurately estimating the customers included in the group.

In this configuration, contact between customers can be estimated, for example, by whether the bodies of customers being tracked using facial images overlap. Furthermore, customers who are added to a group due to contact or face orientation do not necessarily have to be customers who are not included in any group, but may also be customers who are estimated to be included in another group.

Furthermore, the method for estimating customer groups and sales information corresponding to those groups based on the timing of dispersal and the timing of ticket issuance is not limited to the methods described in the first and second embodiments and modified examples above.

For example, customers who dispersed at substantially the same time may be presumed to be in the same group, and ticket sales information whose ticket issuance timing falls within a predetermined time from the dispersion timing of the earliest dispersed customer within this group may be linked to that group. In this case, ticket sales information whose ticket issuance timing falls within a predetermined time from the dispersion timing of the last dispersed customer within this group may also be linked to that group.

In addition, customer groups and the tickets (sales information) corresponding to those groups may be estimated using AI (artificial intelligence) processing of the timing of ticket issuance over a specified period and the timing of customer departures. Furthermore, the attributes of a group may be estimated using AI processing of the attributes and number of customers included in the group.

Furthermore, the types and contents of group attributes are not limited to those shown above. For example, based on the similarity of facial information, further group attributes such as brothers and sisters may be added. Furthermore, age groups and the number of people in each age group may also be included as group attributes.

In addition, in the above-described first and second embodiments and their modifications, the facial information of customers included in a group is linked to the group as shown in FIG. 6(c), but the facial information of customers included in each group may also be linked to the sales information of each group as shown in FIG. 16.

In addition, in the above-described first and second embodiments and their modifications, one day's worth of sales information and captured images are processed, but the processing targets are not limited to this. For example, one week's worth of sales information and captured images may be processed, or sales information and captured images for a specific time period over one month may be processed. The manager of the store or the like may be able to specify these processing targets via the terminal.

Furthermore, the configurations of the ticket vending machine 10, camera 20, and management device 30 are not limited to those shown in the above embodiment. For example, while the above describes a ticket vending machine 10 that allows multiple tickets to be purchased at once, the ticket vending machine 10 may also be a type that allows tickets to be purchased one at a time.

Furthermore, in the above-mentioned embodiments 1 and 2 and their modifications, the sales information management system 1 is configured with the ticket vending machine 10, camera 20, and management device 30 arranged separately, but the ticket vending machine 10, camera 20, and management device 30 do not necessarily have to be arranged separately.

For example, instead of camera 20, a camera that captures images of the area in front of the ticket vending machine 10 may be installed on the ticket vending machine 10. In this case, the image captured by the camera and time information (timestamp) are sent from the ticket vending machine 10 to the management device 30 along with sales information and time information (ticket issuance timing). Alternatively, the functions of the management device 30 may be installed on the ticket vending machine 10, and the management device 30 may be omitted. In this case, the ticket vending machine 10 is also used as a sales information management device. The image captured by camera 20 and time information (timestamp) are sent from the camera 20 to the ticket vending machine 10. Alternatively, the functions of the camera 20 and management device 30 may be installed on the ticket vending machine 10, and the camera 20 and management device 30 may be omitted from the sales information management system 1.

In addition, the embodiments of the present invention may be modified as appropriate within the scope of the claims.

1 Sales information management system 10 Ticket vending machine 20 Camera 30 Sales information management device 301 Control unit 302 Storage unit

Claims (23)

A control unit is provided,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets ;
The control unit, in estimating the group and the sales information,
Customers who have dispersed within a predetermined time before and after the timing of issuing the tickets are assumed to be in the same group;
A sales information management device that estimates the sales information of the ticket issuance that estimates the group as the sales information corresponding to the group . A control unit is provided,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
The control unit, in estimating the group and the sales information,
If multiple tickets are issued within a predetermined time interval, customers who are separated within a period between the first and last tickets issued and within a predetermined time before and after the period are assumed to be in the same group;
A sales information management device that estimates the sales information of the plurality of tickets that have estimated the group as the sales information corresponding to the group. 3. The sales information management device according to claim 1 , wherein the predetermined time before the predetermined time before and after the predetermined time starts immediately after the last discrete timing of the customer in the previous group estimation. 4. The sales information management device according to claim 1 , wherein the predetermined time before and after the event is a fixed time that is set in advance. A control unit is provided,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
The control unit, in estimating the group and the sales information,
Customers who disperse from in front of the ticket vending machine in response to ticket issuance are assumed to be in the same group;
A sales information management device that estimates the sales information of the ticket issuance that estimates the group as the sales information corresponding to the group. The control unit
A sales information management device as described in claim 5, wherein if at least one other ticket is issued between a first ticket issuance timing at which the group is estimated and a second ticket issuance timing immediately preceding that, among a series of ticket issuance timings at which customers disperse from in front of the ticket machine in response to ticket issuance, sales information for the other ticket issuance is included in the sales information corresponding to the group . The control unit
A sales information management device as described in claim 6, wherein if another customer leaves in front of the ticket machine between a timing that is a predetermined time before the oldest ticket issuance corresponding to the group and the first ticket issuance timing, the other customer is included in the group. The control unit estimates, based on the captured image, other customers who face the customer estimated to be in the same group for a predetermined period of time or more, or other customers who have been in contact with the customer estimated to be in the same group for a predetermined period of time or more, and includes the estimated customers in the group . The sales information management device according to claim 1 , wherein the control unit excludes customers who do not stay in front of the ticket vending machine and who have dispersed from the group of customers to be estimated. The sales information management device according to claim 1 , wherein the control unit estimates an attribute of the group based on the captured image. The sales information management device according to claim 10, wherein the control unit estimates attributes of each customer included in the group based on the captured image, and estimates attributes of the group based on the estimated attributes of each customer and the number of customers included in the group . A storage unit for storing information is provided,
The sales information management device according to claim 10 , wherein the control unit causes the storage unit to store the attributes of the groups and the sales information of the groups in association with each other . 13. The sales information management device according to claim 12, wherein the control unit extracts facial information of each customer included in the group based on the captured image, and stores the extracted facial information in the storage unit in association with at least one of the group and the sales information. The sales information management device according to claim 1 , wherein the sales information includes a sales time, a sold product, and a sold quantity. A method for controlling a sales information management device, comprising:
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
In estimating the group and the sales information,
Customers who have dispersed within a predetermined time before and after the timing of issuing the tickets are assumed to be in the same group;
A control method for a sales information management device, which estimates the sales information of the ticketing that estimates the group as the sales information corresponding to the group . A method for controlling a sales information management device, comprising:
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
In estimating the group and the sales information,
If multiple tickets are issued within a predetermined time interval, customers who are separated within a period between the first and last tickets issued and within a predetermined time before and after the period are assumed to be in the same group.
A control method for a sales information management device that estimates the sales information of the plurality of tickets that have been estimated as the sales information corresponding to the group. A method for controlling a sales information management device, comprising:
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on a captured image of the vicinity of the ticket vending machine;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
In estimating the group and the sales information,
Customers who disperse from in front of the ticket vending machine in response to ticket issuance are assumed to be in the same group;
A control method for a sales information management device, which estimates the sales information of the ticketing that estimates the group as the sales information corresponding to the group. Ticket machines and
a camera that captures images of the vicinity of the ticket vending machine;
a control unit that manages sales information of the ticket vending machine,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on the image captured by the camera;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets ;
The control unit, in estimating the group and the sales information,
Customers who have dispersed within a predetermined time before and after the timing of issuing the tickets are assumed to be in the same group;
A sales information management system that estimates the sales information of the ticketing that estimates the group as the sales information corresponding to the group . Ticket machines and
a camera that captures images of the vicinity of the ticket vending machine;
a control unit that manages sales information of the ticket vending machine,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on the image captured by the camera;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
The control unit, in estimating the group and the sales information,
If multiple tickets are issued within a predetermined time interval, customers who are separated within a period between the first and last tickets issued and within a predetermined time before and after the period are assumed to be in the same group.
A sales information management system that estimates the sales information of the multiple tickets that have been estimated for the group as the sales information corresponding to the group. Ticket machines and
a camera that captures images of the vicinity of the ticket vending machine;
a control unit that manages sales information of the ticket vending machine,
The control unit
Acquire sales information for each ticket issued by the ticket vending machine,
The timing at which customers dispersed from in front of the ticket vending machine is estimated based on the image captured by the camera;
Inferring a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the tickets;
The control unit, in estimating the group and the sales information,
Customers who disperse from in front of the ticket vending machine in response to ticket issuance are assumed to be in the same group;
A sales information management system that estimates the sales information of the ticketing that estimates the group as the sales information corresponding to the group. On the computer,
A function to obtain sales information for each ticket issued by the ticket vending machine;
a function of estimating the timing at which customers leave the ticket vending machine based on captured images of the vicinity of the ticket vending machine;
and a function of estimating a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the ticket ;
In the function of estimating the group and the sales information,
A function of estimating that customers who have dispersed within a predetermined time before and after the timing of the ticket issuance belong to the same group;
and a function of estimating the sales information of the ticket that estimated the group as the sales information corresponding to the group . On the computer,
A function to obtain sales information for each ticket issued by the ticket vending machine;
a function of estimating the timing at which customers leave the ticket vending machine based on captured images of the vicinity of the ticket vending machine;
and a function of estimating a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the ticket;
In the function of estimating the group and the sales information,
When multiple tickets are issued within a predetermined time interval, it is possible to estimate that customers who are separated within a period between the first and last tickets issued and within a predetermined time before and after the period belong to the same group.
and a function of estimating the sales information of the plurality of tickets that have been estimated as the sales information corresponding to the group. On the computer,
A function to obtain sales information for each ticket issued by the ticket vending machine;
a function of estimating the timing at which customers leave the ticket vending machine based on captured images of the vicinity of the ticket vending machine;
and a function of estimating a customer group and sales information corresponding to the group based on the timing of the dispersion and the timing of the issuance of the ticket;
In the function of estimating the group and the sales information,
A function of inferring that customers who have dispersed from in front of the ticket vending machine in response to ticket issuance belong to the same group;
and a function of estimating the sales information of the ticket that estimated the group as the sales information corresponding to the group.