GENERATION APPARATUS, GENERATION METHOD, AND PROGRAM

Abstract

To provide a shift generation device for easily generating a register shift according to situations of a congestion.SOLUTION: A generation device 10 according to one embodiment of the present disclosure includes: a number determination unit 120 for determining the number of operating cash registers in each time zone of a target day so that the congestion degree of users of cash registers satisfies a congestion condition; and a determination unit 130 for determining employees who are to be in charge of cash registers so that the restriction conditions of the employees are satisfied, in each time zone of the target day, on the basis of the number of the operating cash registers.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to techniques for generating a shift. [Background technology]

[0002] In retail stores, in order to improve customer satisfaction and prevent the spread of infectious diseases, it is necessary to avoid congestion. For example, it is necessary to avoid congestion in queues at cash registers. Hereinafter, a cash register is also simply referred to as a cash register. In addition, a company that operates a retail store has a desire to improve employee productivity by appropriately determining an employee shift in charge of an appropriate cash register according to the degree of congestion. Hereinafter, an employee in charge of a cash register is also referred to as a cashier. A cashier shift is also referred to as a cash register shift. However, in order to generate a cash register shift, various constraints including the working patterns of employees must be taken into consideration. Therefore, generating a cash register shift requires a lot of work.

[0003] Cited Document 1 describes a security support method for lending resources such as personnel and goods between stores. The store support method in Cited Document 1 generates lending information for lending resources from a lending source store that can lend the resources to a lending destination store based on a demand forecast for the resources at the lending destination store.

[0004] Cited Document 2 describes an operating number determination device that calculates the number of operating registers for a plurality of registers based on an estimated number of waiting people and cost information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2017 / 163280 [Patent Document 2] Patent No. 6785460 Summary of the Invention [Problem to be solved by the invention]

[0006] The technology of Patent Document 1 enables the flexibility of resources such as personnel and goods between stores, but does not contribute to the generation of register shifts. The technology of Patent Document 2 calculates the number of operating registers, but does not generate register shifts. Therefore, the technologies of Patent Document 1 and Patent Document 2 cannot easily generate register shifts according to the congestion situation.

[0007] One object of the present disclosure is to provide a shift generation device that makes it easy to generate cash register shifts according to the congestion situation. [Means for solving the problem]

[0008] A generation device according to one aspect of the present disclosure includes a number determination means for determining the number of cash registers in operation for each time period on a target day so that the degree of congestion of cash register users satisfies a congestion condition, and a determination means for determining an employee in charge of the cash register for each time period on the target day based on the number of cash registers in operation so as to satisfy the constraint conditions for that employee.

[0009] A generation method according to one aspect of the present disclosure determines the number of cash registers in operation for each time period on a target day so that the degree of congestion of cash register users satisfies a congestion condition, and based on the number of cash registers in operation, determines an employee in charge of the cash register for each time period on the target day so that the employee's constraint conditions are satisfied.

[0010] A program according to an aspect of the present disclosure causes a computer to execute a number determination process for determining the number of operating cash registers for each time period of a target day so that the degree of congestion of users of the cash registers satisfies a congestion condition, and a determination process for determining an employee in charge of the cash register for each time period of the target day based on the number of operating cash registers so as to satisfy a constraint condition for the employee. One aspect of the present disclosure is also realized by a storage medium that stores the above-mentioned program. Effect of the Invention

[0011] The present disclosure has the effect of making it easier to create register shifts according to the congestion situation. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram illustrating an example of a configuration of a generating device according to a first embodiment of the present disclosure. [Diagram 2] FIG. 2 is a flowchart illustrating an example of the operation of the generating device according to the first embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating an example of a configuration of a generating device according to a second embodiment of the present disclosure. [Figure 4] FIG. 4 is a flowchart illustrating an example of the operation of the generating device according to the first embodiment of the present disclosure. [Diagram 5] FIG. 5 is a block diagram illustrating an example of a configuration of a generation system according to a third embodiment of the present disclosure. [Figure 6] FIG. 6 is a flowchart illustrating an example of an operation of the generating device according to the third embodiment of the present disclosure to receive information from a store server device. [Figure 7] FIG. 7 is a flowchart illustrating an example of an operation for calculating a congestion degree of a generation device according to the third embodiment of the present disclosure. [Figure 8] FIG. 8 is a flowchart illustrating an example of an operation of generating a model of the generating device according to the third embodiment of the present disclosure. [Figure 9] FIG. 9 is a block diagram illustrating an example of a configuration of a generation system according to a fourth embodiment of the present disclosure. [Figure 10] FIG. 10 is a flowchart illustrating an overall operation of the generating device according to the fourth embodiment of the present disclosure. [Figure 11] FIG. 11 is a flowchart showing the operation of the guidance process of the generation device according to the fourth embodiment of the present disclosure. [Figure 12] FIG. 12 is a flowchart illustrating an operation of an allocation process of the generating device according to the fourth embodiment of the present disclosure. [Figure 13] FIG. 13 is a flowchart showing the operation of the release process of the generating device according to the fourth embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating an example of a hardware configuration of a computer capable of realizing each of the generating devices according to the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0014] <First embodiment> 1 is a block diagram illustrating an example of a configuration of a generating device according to a first embodiment of the present disclosure. In the example illustrated in FIG. 1, a generating device 10 includes a number determination unit 120 and a determination unit 130.

[0015] The number determination unit 120 determines the number of operating cash registers for each time period on a target day so that the degree of congestion of cash register users satisfies the congestion condition. The determination unit 130 determines an employee who will be in charge of the cash register for each time period on the target day based on the number of operating cash registers so that the employee's constraint condition is satisfied.

[0016] The cash register described above is a cash register (i.e., a cash register) located in one store. The degree of congestion is, for example, the number of users waiting to make a payment at a cash register in that store (for example, an average value). A payment includes, for example, identifying an item sold by the store and purchased by a user, and paying for the item sold by the store and purchased by a user. The item is identified, for example, by reading information that identifies the item, such as a barcode. The payment is made, for example, by cash, electronic money, a credit card, QR (Quick Response) code payment, etc.

[0017] The number of units determining unit 120 may predict the number of customers based on, for example, a customer number prediction model that predicts the number of customers from a time period. Then, the number of units determining unit 120 may determine the number of operating cash registers for each time period of the target day based on the relationship between the predicted number of customers, the number of operating cash registers, and the congestion degree of users of the cash registers, so that the congestion degree satisfies the congestion condition. The customer number prediction model represents the relationship between the time period and the number of customers, and is obtained, for example, by machine learning. The number of units determining unit 120 may determine the number of operating cash registers for each time period of the target day based on a congestion degree model that represents the relationship between the number of customers, the number of operating cash registers, the congestion degree, and the like, and is obtained by machine learning, so that the congestion degree satisfies the congestion condition. The number of units determining unit 120 may determine the number of operating cash registers for each time period of the target day so that the congestion degree satisfies the congestion condition, without using the congestion degree model obtained by machine learning. The machine learning method will be described later.

[0018] The congestion condition is, for example, a condition set for the number of users waiting to make a payment at a cash register in a store. The congestion condition may be expressed by an upper limit of the number of users waiting to make a payment at a cash register in a store. In this case, the congestion condition is met when the number of users waiting to make a payment at a cash register in a store is equal to or less than the upper limit. The congestion condition may be expressed by a range of the number of users waiting to make a payment at a cash register in a store (i.e., a combination of an upper limit and a lower limit). In this case, the congestion condition is met when the number of users waiting to make a payment at a cash register in a store is equal to or less than the upper limit and equal to or more than the lower limit. The customer number prediction model may represent the relationship between a time period, the number of customers, calendar information, and the like. The calendar information is, for example, information on the date of the month, the day of the week, and holidays. Each of the time periods is, for example, a time period that is set as a shift unit. Each of the time periods is at least one of the divisions obtained by dividing the business hours of the store into an appropriately set length of time. The number of operating cash registers is the number of cash registers in which employees are processing payments. The target day is, for example, a day designated in advance.

[0019] The determination unit 130 may determine an employee who will be in charge of the cash register for each time period on the target day by a method based on any of various existing algorithms for solving a combinatorial optimization problem. The method for solving the combinatorial optimization problem may be, for example, any of quantum annealing, pseudo-quantum annealing, heterogeneous mixture learning, and reverse effect learning. The constraint condition for an employee is that the time period during which the employee is determined to be in charge of the cash register is designated in advance as the time period during which the employee can be in charge of the cash register. The determination unit 130 may determine the cash register shift so as to maintain fairness among employees. For example, the determination unit 130 may determine the cash register shift so that the ratio of the number of determined time periods to the number of time periods during which the employee can be in charge of the cash register within a predetermined period (for example, a period of one month) is equal for each employee. The determination unit 130 may determine the cash register shift regardless of fairness among employees.

[0020] <Operation> Next, the operation of the generating device according to the first embodiment of the present disclosure will be described in detail with reference to the drawings.

[0021] FIG. 2 is a flowchart showing an example of the operation of the generating device according to the first embodiment of the present disclosure. In the example shown in FIG. 2, the number determination unit 120 determines the number of operating cash registers for each time period on the target day so that the congestion degree satisfies the congestion condition (step S11). The number determination unit 120 predicts the number of customers for each time period on the target day, and determines the number of operating cash registers for each time period on the target day based on the relationship between the predicted number of customers, the congestion degree of cash register users, the time period, and the number of operating cash registers. The determination unit 130 determines the employee in charge of the cash register for each time period on the target day based on the determined number of operating cash registers so as to satisfy the employee constraint condition (step S12).

[0022] <Effects> This embodiment has the effect of facilitating the generation of cash register shifts according to the congestion situation, because the determination unit 130 determines the difference in the number of cash registers in operation, and determines the employee who will be in charge of the cash register for each time period on the target day based on the determined number of operating units.

[0023] <Second embodiment> Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings.

[0024] 3 is a block diagram illustrating an example of a configuration of a generating device 11 according to a second embodiment of the present disclosure. In the example illustrated in FIG. 3, the generating device 11 includes an instruction receiving unit 110, a number determining unit 120, a determining unit 130, an output unit 140, a model storage unit 150, a condition receiving unit 160, and a condition storage unit 170.

[0025] <Instruction Receiving Unit 110> The instruction receiving unit 110 receives an instruction (hereinafter also referred to as a generation instruction) to generate an allocation of employees in charge of cash registers for a target day. The generation instruction includes information indicating the target day. The information indicating the target day may indicate multiple target days (e.g., a week or a month). The instruction receiving unit 110 may receive an instruction to create a shift schedule as a generation instruction. The instruction receiving unit 110 sends information indicating the target day (hereinafter also referred to as target day information) to the number determination unit 120.

[0026] <Model Storage Unit 150> The model storage unit 150 stores information for determining the number of cash registers in operation. The information for determining the number of cash registers in operation will be described later. The model storage unit 150 may store calendar information that indicates the relationship between the date and the type of day (e.g., day of the week and public holiday). The model storage unit 150 may also store time zone information that is information that can identify each time zone. The time zone information may be represented, for example, by the start time and end time of operation of the cash registers in the store for each type of day, and information that identifies the boundary times of the time zones. The time zone information may be represented, for example, by the start time of each of a plurality of time zones and the end time of the last time zone.

[0027] In this embodiment, the information for determining the number of operating cash registers includes a customer number prediction model that represents the relationship between a time period and the number of customers, and a congestion model that represents the relationship between the number of customers, the number of operating cash registers, and the congestion level of the cash registers. That is, in this embodiment, the information for determining the number of operating cash registers can be said to represent the relationship between the congestion level of users of the cash registers, the time period, and the number of operating cash registers. In this case, the customer number prediction model can be said to be a predictor configured to predict the number of customers based on the time period. Also, the congestion level model can be said to be a predictor configured to determine the number of operating cash registers based on the number of customers and a threshold value of the congestion level of the cash register. The customer number prediction model may represent the relationship between calendar information, time period, and the number of customers. In this case, the customer number prediction model can be said to be a prediction model configured to predict the number of customers in the time period of the target day based on information specifying the target day and the time period. The customer number prediction model may be obtained by machine learning using data including the number of customers in the past, calendar information, and time period recorded in advance. The congestion level model may be obtained by machine learning using data including the congestion level in the past, time period, and the number of operating cash registers recorded in advance, for example. The machine learning method may be any of various existing methods such as a method called heterogeneous mixture learning including FAB inference (Factorized Asymptotic Bayesian Inference) and the like, and inverse reinforcement learning. Heterogeneous mixture learning is disclosed in, for example, U.S. Patent Publication US2014 / 0222741A1 and the like.

[0028] The information for determining the number of operating cash registers may include a customer number prediction model, but may not include a congestion model obtained by machine learning. In other words, the number determination unit 120 may determine the number of operating cash registers without relying on a congestion model obtained by machine learning. An example of this case will be described later as a modified example.

[0029] <Number of units determination unit 120> The number of units determining unit 120 receives target day information indicating the target day from the instruction receiving unit 110. The number of units determining unit 120 determines the number of operating cash registers for each time period on the target day based on the relationship between the congestion degree of users of the cash register, the time period, and the number of operating cash registers so that the congestion degree satisfies the congestion condition. As described above, in this embodiment, the information for determining the number of operating cash registers includes a customer number prediction model and a congestion degree model. In this case, specifically, the number of units determining unit 120 predicts the number of customers for each time period on the target day based on the customer number prediction model, and determines the number of operating cash registers for each time period on the target day so that the congestion degree satisfies the congestion condition based on the predicted number of customers. The number of units determining unit 120 sends the determined number of operating cash registers for each time period on the target day to the determination unit 130. The number of units determining unit 120 of this embodiment has the same function as the number of units determining unit 120 of the first embodiment, and may perform the same operation as the number of units determining unit 120 of the first embodiment.

[0030] Incidentally, when the business hours of a store vary depending on the day of the week and whether or not it is a public holiday, the number determination unit 120 may determine the number of operating cash registers so that the congestion level of the cash registers satisfies the congestion condition based on the calendar information as well. Specifically, the customer number prediction model may represent the relationship between the calendar information, the time period, the number of operating cash registers, and the number of customers. In this case, when the number of customers varies depending on the day of the week and further varies depending on whether or not it is a public holiday, the accuracy of determining the number of operating cash registers so that the congestion level satisfies the congestion condition can be improved. In the following description of this embodiment, a case will be described in which the number determination unit 120 predicts the number of customers for each time period on a target day based on the calendar information, the time period, and the number of operating cash registers.

[0031] The information for determining the number of operating cash registers, the calendar information, and the time zone information may be stored in the model storage unit 150. The number determination unit 120 may hold information for determining the number of operating cash registers in advance. In this case, the information for determining the number of operating cash registers does not need to be stored in the model storage unit 150. The number determination unit 120 reads out the information for determining the number of operating cash registers, the calendar information for the target day, and the time zone information for the target day, which are stored in the model storage unit 150. Then, the number determination unit 120 determines the number of operating cash registers for each time zone on the target day, as described above.

[0032] <Condition Receiving Unit 160> The condition receiving unit 160 receives information indicating whether each employee can handle the cash register for each time period (hereinafter, also referred to as preferred shift information). The condition receiving unit 160 may receive preferred shift information for a period of two or more days (for example, one week, one month, or two or more months). The condition receiving unit 160 may receive shift information input by each employee using an input device such as a keyboard of the generating device 11 or a mobile terminal such as a smartphone connected to the generating device 11. The condition receiving unit 160 may receive preferred shift information for each employee input by an operator of the generating device 11.

[0033] The condition receiving unit 160 stores the received desired shift information in the condition storage unit 170 as information representing a constraint condition.

[0034] <Condition storage section 170> The condition storage unit 170 stores information representing the constraint conditions stored by the condition receiving unit 160 (that is, the above-mentioned desired shift information).

[0035] <Decision Unit 130> The determination section 130 of this embodiment has the same functions as the determination section 130 of the first embodiment, and may perform the same operations as those of the first embodiment.

[0036] The determination unit 130 receives the number of operating cash registers for each time period on the target day from the number determination unit 120. The determination unit 130 reads out information representing the constraint conditions (i.e., desired shift information) stored in the condition storage unit 170.

[0037] The determination unit 130 determines an employee who will be in charge of the cash register for each time period on the target day based on the received number of operating cash registers for each time period on the target day, so as to satisfy the constraint condition of the employee. The constraint condition is, for example, that an employee is determined as the employee who will be in charge of the cash register during the time period designated as the time period during which the employee can be in charge of the cash register.

[0038] The determination unit 130 sends to the output unit 140 information indicating the employee in charge of the cash register for each time period on the target day that has been determined.

[0039] <Output unit 140> The output unit 140 receives information representing the employee in charge of the cash register for each time period on the target day from the determination unit 130. The output unit 140 outputs information representing the employee in charge of the cash register for each time period on the target day (hereinafter, also referred to as shift information).

[0040] The generating device 11 may collectively output information representing employees in charge of cash registers, with each of the store's business days included in a specified period determined as a target day. The generating device 11 may output information representing employees in charge of cash registers, with each of the store's business days included in a specified period determined as a target day, in the form of a table. In this case, the output information is also referred to as a shift table. The output format is not limited to the above example. The output format may be other formats.

[0041] <Operation> Next, the operation of the generation device 11 according to the first embodiment of the present disclosure will be described in detail with reference to the drawings.

[0042] 4 is a flowchart illustrating an example of the operation of the generating device 11 according to the first embodiment of the present disclosure. At the start of the operation of FIG. 4, information for determining the number of operating cash registers is stored in the model storage unit 150. In addition, information representing the constraint conditions is stored in the condition storage unit 170.

[0043] First, the instruction receiving unit 110 receives an instruction to generate an allocation for a target day (step S101). Next, the number determining unit 120 predicts the number of customers for each time period on the target day (step S102). The number determining unit 120 determines the number of operating cash registers for each time period on the target day based on the predicted number of customers (step S103). Next, the determining unit 130 determines the employee in charge of the cash register for each time period on the target day so as to satisfy the constraints (step S104). The output unit 140 outputs information on the employee in charge of the cash register for each time period on the target day (step S105).

[0044] <Effects> The present embodiment described above has the same effects as the first embodiment, for the same reasons as those for the effects of the first embodiment.

[0045] <Specific example of the second embodiment> The information for determining the number of operating cash registers includes, for example, a customer number prediction model and a congestion degree model. The customer number prediction model and the congestion degree model will be described in detail below. The customer number prediction model and the congestion degree model are learned, for example, by the learning unit 230 of the third embodiment described later. In other words, the customer number prediction model and the congestion degree model are learned, for example, by the learning unit 230 of the third embodiment described later.

[0046] The customer number prediction model represents the relationship between calendar information, time periods, and the number of customers. The customer number prediction model is, for example, a predictor configured to predict the number of customers in a specified time period on a target day from the calendar information of the target day. The customer number prediction model is, for example, a predictor obtained by machine learning using data including pre-recorded past calendar information, time periods, and the number of customers. As described above, the machine learning method may be any of various existing methods, such as heterogeneous mixture learning and inverse reinforcement learning.

[0047] The congestion model represents the relationship between the congestion degree determined based on an image of a queue of users at a cash register, the number of customers, and the number of operating units. The congestion model is, for example, a predictor configured to predict the number of operating units from the number of customers and a specified congestion degree. In other words, the congestion model is configured to predict the number of operating cash registers such that the number of users waiting to pay at the cash register is equal to or less than the specified congestion degree when the number of customers at the store is the input number of customers. The congestion model is, for example, a predictor obtained by machine learning using data including the past congestion degree, the number of customers, and the number of operating units that have been recorded in advance. As described above, the machine learning method may be any of various existing methods, such as heterogeneous mixture learning and inverse reinforcement learning.

[0048] As described above, the information for determining the number of operating cash registers includes, for example, a customer number prediction model and a congestion degree model. The number determination unit 120 predicts the number of customers for each time period on a target day using the customer number prediction model, and determines the number of operating cash registers using the congestion degree model based on the predicted number of customers.

[0049] <First Modification> The generating device according to the first modified example has the same configuration as the generating device 11 according to the second embodiment shown in Fig. 3, and operates in the same manner as the generating device 11 according to the second embodiment, except for the differences described below. Note that the first modified example can also be applied to the first, third, and fourth embodiments.

[0050] The congestion degree model may be configured to predict the number of operating cash registers for each type. Specifically, the congestion degree model is configured to predict the number of operating cash registers for each type from a specified congestion degree and a predicted number of customers in a manner that minimizes costs while satisfying allocation conditions.

[0051] The types of cash registers include, for example, normal registers, semi-self-service registers, and full self-service registers. A normal register is a register where an employee reads the barcode of a product and processes the payment. A semi-self-service register is a register where an employee reads the product information of a product (for example, a barcode attached to the product) and a user uses a payment terminal to make a payment. The payment terminal is a terminal that a user operates to make a payment. A full self-service register is a register where a user uses a payment terminal equipped with a product information reading device to read the product information of a product and processes the payment. The allocation conditions are the minimum number of operating units for each type of cash register and the number of employees in charge of each type of cash register. The minimum number of operating units for each type of cash register may be, for example, 1 for normal registers, 0 for semi-self-service registers, and 0 for full self-service registers. The number of employees in charge of each type of cash register may be one employee per normal register, one employee per semi-self-service register, one employee for all full self-service registers, etc. The minimum number of operating cash registers for each type and the number of employees in charge of each type of cash register are not limited to these examples. The cost is, for example, the total number of employees in charge of the cash registers.

[0052] The customer number prediction model may represent the relationship between the calendar information and the time period and the number of customers for each customer segment. The customer segment model is, for example, a predictor configured to predict the number of customers for each customer segment from the calendar information and the time period. In this case, the customer number model is, for example, a predictor obtained by machine learning using data including the past calendar information and the time period recorded in advance and the number of customers for each customer segment. In this modified example, the machine learning method may be any of various existing methods such as heterogeneous mixture learning and inverse reinforcement learning. The customer segment is represented, for example, by the gender and age group of the user. The age group is an age category including one or more ages that is appropriately set. The gender and age group may be determined and input by an employee, for example, at the time of payment at the cash register. The gender and age group may be determined, for example, by a face image analysis method that determines the gender and age group from a face image obtained by imaging with an imaging device attached to image the face of the cash register user at the time of payment at the cash register.

[0053] In this case, the congestion degree model is configured to predict the number of customers for each type of cash register from the specified congestion degree and the number of customers for each customer segment, and to predict the number of operating cash registers for each type of cash register. The mixture degree model is a predictor obtained by machine learning using data including the past congestion degree recorded in advance, the number of customers for each customer segment, and the number of operating cash registers for each type of cash register. The machine learning method in this case may also be any of various existing methods, such as heterogeneous mixture learning and inverse reinforcement learning.

[0054] When a congestion degree model has been obtained for each type of cash register, the number determination unit 120 determines the number of operating cash registers for each type during each time period on the target day based on this congestion degree model so that the congestion degree satisfies the congestion condition.

[0055] <Third embodiment> Next, a third embodiment of the present disclosure will be described in detail with reference to the drawings.

[0056] <Configuration> 5 is a block diagram illustrating an example of a configuration of a generation system 3 according to a third embodiment of the present disclosure. In the example illustrated in FIG. 5, the generation system 3 includes a generation device 12, a store server device 20, an imaging device 30, and a cash register device 50.

[0057] The generating device 12 includes an instruction receiving unit 110, a number determining unit 120, a determination unit 130, an output unit 140, a model storage unit 150, a condition receiving unit 160, and a condition storage unit 170. The instruction receiving unit 110, the number determining unit 120, the determination unit 130, the output unit 140, the model storage unit 150, the condition receiving unit 160, and the condition storage unit 170 are the same as the components in the second embodiment that are given the same names and the same symbols. The instruction receiving unit 110, the number determining unit 120, the determination unit 130, the output unit 140, the model storage unit 150, the condition receiving unit 160, and the condition storage unit 170 operate in the same manner as the components in the second embodiment that are given the same names and the same symbols. The generating device 12 performs the same operation as the generating device 11 according to the second embodiment shown in FIG. 3.

[0058] The generation device 12 of this embodiment further includes a sales information receiving unit 210, a sales information storage unit 220, a learning unit 230, an image receiving unit 240, a congestion determination unit 250, and an image information storage unit 260. The generation device 12 is communicatively connected to each of the store server device 20 and the imaging device 30. The store server device 20 is connected to each of the register devices 50, which are the above-mentioned cash registers.

[0059] <Register device 50> The cash register device 50 transmits data obtained by the payment (hereinafter also referred to as payment data) to the store server device 20. The data obtained by the payment (i.e., payment data) includes, for example, information on the date and time when the payment was made. The data obtained by the payment may include, for each payment, a combination of information identifying the item sold and the price of the item sold, and information on the amount paid.

[0060] The cash register device 50 also transmits to the store server device 20 the time when the cash register device 50 is set, for example, by an employee, to a state where a transaction can be performed, and the time when the cash register device 50 is set, for example, by an employee, to a state where a transaction cannot be performed.

[0061] <Store Server Device 20> The store server device 20 receives payment data from the cash register devices 50. The store server device 20 stores the received payment data. The store server device 20 receives from each of the cash register devices 50 the time when the cash register devices 50 were set to a state where a transaction can be performed and the time when the cash register devices 50 were set to a state where a transaction cannot be performed. The store server device 20 stores information (hereinafter referred to as operation information) indicating the time when each of the cash register devices 50 was set to a state where a transaction can be performed and the time when the cash register devices 50 were set to a state where a transaction cannot be performed.

[0062] The store server device 20 transmits data on the time of the payment, which is included in the payment data, as sales information data to the sales information receiving unit 210 of the generating device 12. The store server device 20 transmits operation information indicating the time when each of the cash registers 50 was set to a state in which a transaction could be performed and the time when each of the cash registers 50 was set to a state in which a transaction could not be performed, to the sales information receiving unit 210 of the generating device 12.

[0063] <Sales information receiving unit 210> The sales information receiving unit 210 receives data on the time of payment as sales information data from the store server device 20. The sales information receiving unit 210 stores the received sales information data in the sales information storage unit 220.

[0064] In addition, the sales information receiving unit 210 receives operation information indicating the time when each of the cash register devices 50 is set to a state in which a transaction can be performed and the time when each of the cash register devices 50 is set to a state in which a transaction cannot be performed from the store server device 20. The sales information receiving unit 210 stores the received operation information in the sales information storage unit 220.

[0065] <Sales information storage unit 220> The sales information storage unit 220 stores the sales information and operation information stored by the sales information receiving unit 210.

[0066] <Imaging device 30> The imaging device 30 captures images of users waiting to make a payment at the cash register 50 (in other words, an image of the queue of users at the cash register). The imaging device 30 is installed so as to capture images of all users waiting to make a payment at all cash registers 50 in the store. Multiple imaging devices 30 may be installed so that all users waiting to make a payment at all cash registers 50 in the store are captured by at least one of the multiple imaging devices 30. The images may be moving images, or multiple still images obtained by capturing images at a predetermined time interval. The imaging device 30 transmits the captured images to the image receiving unit 240 of the generation device 12.

[0067] <Image Reception Unit 240> The image receiving unit 240 receives an image captured by the imaging device 30. The image receiving unit 240 sends the received image to the congestion determination unit 250.

[0068] <Congestion determination unit 250> The congestion determination unit 250 receives images of users waiting to make a payment at the cash register 50 (in other words, images of the queue of users at the cash register) captured by the imaging device 30 from the image receiving unit 240. The congestion determination unit 250 identifies the number of users waiting to make a payment at each of the cash registers 50 based on the received images.

[0069] Specifically, the congestion determination unit 250 extracts a person's area from the received image by, for example, any one of various existing person area extraction methods. The congestion determination unit 250 may extract the person's face area by any one of the existing face area extraction methods. The congestion determination unit 250 estimates the position of the person in the store whose area has been extracted by using the installation position of the imaging device 30, the direction of the optical axis, and camera parameters such as focal length. Note that the installation position of the imaging device 30, the direction of the optical axis, and camera parameters such as focal length are measured in advance and provided to the congestion determination unit 250.

[0070] The congestion determination unit 250 may further determine the direction in which the person is facing by using any of the existing methods for determining the posture of a person. The congestion determination unit 250 may determine the movement of the determined person by tracking the area of ​​the person extracted from a plurality of consecutive images. In this case, the congestion determination unit 250 identifies the face area of ​​the same person extracted from consecutive images by matching the face of the face area extracted from consecutive images using any of the existing face matching methods. Then, the congestion determination unit 250 determines the movement of the person by tracking the position in the store of the person determined to be the same person.

[0071] The congestion determination unit 250 identifies the cash register 50 where the person at the estimated position is waiting to make a payment, based on the position of the cash register 50 in the store and the position of the queue of users waiting to make a payment at the cash register 50. The position of the cash register 50 in the store and the position of the queue of users waiting to make a payment at the cash register 50 are provided in advance to the congestion determination unit 250. The congestion determination unit 250 may determine whether the person whose area has been extracted is waiting in queue at the cash register 50, based on the position, orientation, and movement of the person.

[0072] At this time, the congestion determination unit 250, for example, determines, as candidates for users waiting for payment, people who are present within a range that is designated in advance as an area where a queue can be made for the cash register 50. The congestion determination unit 250 excludes from the candidates people who satisfy exclusion conditions related to position, orientation, and direction. The exclusion condition may be, for example, that the person is moving in a direction that forms an angle with the direction toward the cash register 50 of a predetermined angle or more. The exclusion condition may be, for example, that the person is facing a direction that forms an angle with the direction toward the cash register 50 of a predetermined angle or more. The congestion determination unit 250 may create a cluster by setting a person whose distance from the position of the cash register 50 is a predetermined distance or less as the initial state of the cluster, and adding a person whose distance from any person included in the cluster is within a predetermined distance to the cluster. In this case, the exclusion condition may be that the person is not included in the cluster. The exclusion condition may not be these examples. The exclusion condition is not limited to these examples. The exclusion condition may be determined as appropriate.

[0073] The congestion determination unit 250 may determine the number of people in the queue of the cash register 50 (i.e., users waiting to pay at the cash register 50) as the congestion degree. When a plurality of waiting positions are defined in the queue, the congestion determination unit 250 may determine whether a person is detected within a predetermined distance from the position of the waiting position, and may determine the order of the last waiting position among the waiting positions where a person is detected within the predetermined distance as the congestion degree. The congestion determination unit 250 may classify the people in the queue into one or more groups based on the closeness of the distance between the people, and may determine the number of groups as the congestion degree. In this case, the congestion determination unit 250 first performs a group generation process of selecting, for example, one person in the queue who is not included in any group, and classifying the selected person into a new group. The congestion determination unit 250 performs an addition process of detecting a person who is a predetermined distance or less from any person included in the group, and adding the detected person to the group. When there is no person who is a predetermined distance or less from any person included in the group, the congestion determination unit 250 repeats the group generation process and the addition process. When there are no more people in the queue who are not included in any group, the congestion determination unit 250 determines the number of groups as the congestion degree.

[0074] The congestion determination unit 250 determines the congestion level for all of the cash registers 50. The congestion determination unit 250 stores the congestion level of each of the cash registers 50 and the time when the image from which the congestion level was obtained was captured in the image information storage unit 260. Note that the congestion determination unit 250 may regard the time when the image receiving unit 240 receives the image from the imaging device 30 as the time when the image was captured. Note that the congestion determination unit 250 may store the received image in the image information storage unit 260.

[0075] <Image information storage unit 260> The image information storage unit 260 stores, as congestion degree information, the congestion degree of each cash register 50 and the time when the image from which the congestion degree was obtained was captured.

[0076] <Learning Section 230> The learning unit 230 reads out the sales information and operation information from the sales information storage unit 220, and calculates the number of customers for each time period from the read out sales information. The learning unit 230 also calculates the number of operating cash registers 50 from the operation information. The number of customers is the number of users who made a transaction at any of the cash registers 50 at a time included in each time period. The number of operating cash registers 50 is the number of cash registers 50 in which an employee was processing a transaction during each time period. Note that if there is a cash register 50 that was operating only for part of the time period, the learning unit 230 adds the proportion of the time that that cash register 50 was operating relative to the length of the time period to the number of cash registers 50 in operation.

[0077] The learning unit 230 also reads out congestion degree information from the image information storage unit 260. Based on the operation information and congestion degree information, the learning unit 230 calculates the average of the congestion degrees (also referred to as individual congestion degrees) of the operating cash registers 50 in each time period as the congestion degree (also referred to as overall congestion degree when distinguished from the individual congestion degree). The learning unit 230 calculates the transition of the average value of the individual congestion degrees, which is obtained by, for example, dividing the sum of the individual congestion degrees by the operating cash registers 50. Then, the learning unit 230 calculates the average of the individual congestion degrees by adding a value obtained by multiplying the average value by the ratio of the length of time during which the average value of the individual congestion degrees continued without changing to the length of the time period in the transition of the average value of the individual congestion degrees for each time period to the overall congestion degree. The learning unit 230 regards the calculated average of the individual congestion degrees as the overall congestion degree.

[0078] Furthermore, the learning unit 230 reads out the calendar information from the model storage unit 150.

[0079] The learning unit 230 learns a customer number prediction model using any of the existing machine learning methods based on the calendar information and the number of customers for each time period on business days when the store is open. The learning unit 230 learns a congestion degree model using any of the existing machine learning methods based on the calendar information, the number of operating cash registers 50, the number of customers, and the congestion degree (i.e., the overall congestion degree) for each time period on business days when the store is open.

[0080] As mentioned above, the machine learning method may be any of a variety of existing methods, such as, for example, heterogeneous mixture learning and inverse reinforcement learning.

[0081] The learning unit 230 stores, in the model storage unit 150, information representing the obtained customer number prediction model and information representing the congestion degree model.

[0082] The number prediction unit 120 may determine the number of operating cash registers without using a congestion degree model obtained by machine learning. In this case, the learning unit 230 does not need to learn the congestion degree model.

[0083] <Operation> Next, the operation of the generating device 12 according to the third embodiment of the present disclosure will be described in detail with reference to the drawings.

[0084] Fig. 6 is a flowchart illustrating an example of an operation of the generating device 12 according to the third embodiment of the present disclosure to receive information from the store server device 20. In the example illustrated in Fig. 6, the sales information receiving unit 210 receives sales information and operation information from the store server device 20 (step S201). The sales information receiving unit 210 stores the received sales information and operation information in the sales information storage unit 220 (step S202).

[0085] FIG. 7 is a flowchart showing an example of an operation of calculating a congestion degree of the generating device 12 according to the third embodiment of the present disclosure. In the example shown in FIG. 7, the image receiving unit 240 receives an image from the imaging device 30 (step S211). Next, the congestion determination unit 250 extracts a person from the image (step S212). Specifically, the congestion determination unit 250 extracts a person area from the image and estimates the position in the store of the person from whose person area the congestion determination unit 250 has been extracted. Then, the congestion determination unit 250 determines people who are waiting to pay among the extracted people (step S213). The congestion determination unit 250 calculates a congestion degree from the determined people who are waiting to pay (step S214). Specifically, the congestion determination unit 250 calculates an individual congestion degree of each cash register device 50. The congestion determination unit 250 stores information on the calculated congestion degree in the image information storage unit 260 (step S215).

[0086] FIG. 8 is a flowchart showing an example of an operation of generating a model of the generating device 12 according to the third embodiment of the present disclosure. In the example shown in FIG. 8, the learning unit 230 reads out sales information from the sales information storage unit 220 (step S221). The learning unit 230 further reads out congestion degree information, which is information on the congestion degree, from the image information storage unit 260 (step S222). The learning unit 230 generates a customer number prediction model based on the relationship between the calendar information and time period of the sales information and the number of customers (step S223). The learning unit 230 generates a congestion degree model based on the congestion degree, the number of customers, and the number of cash registers sold (step S224). The learning unit 230 stores the customer number prediction model and the congestion degree model in the model storage unit 150 (step S225). As described above, when the number determination unit 120 is configured to determine the number of operating cash registers without using a congestion degree model obtained by machine learning, the generating device 12 does not need to perform the operation of step S224. In this case, the learning unit 230 does not need to store the congestion degree model in the model storage unit 150.

[0087] <Effects> The present embodiment described above has the same effects as the first embodiment, for the same reasons as those for the effects of the first embodiment.

[0088] <Second Modification> The generating device according to the second modified example has the same configuration as the generating device 12 according to the third embodiment shown in Fig. 5, and operates in the same manner as the generating device 12 according to the third embodiment, except for the differences described below. Note that the second modified example can also be applied to the third modified example and the fourth modified example described below.

[0089] In this modification, the learning unit 230 learns the customer number prediction model and the congestion degree model of the first modification.

[0090] <Third modified example> In a third variation, the congestion model may be trained using calendar information, in which case the congestion model determines the number of operating cash registers based on the calendar information for the target day.

[0091] The customer number prediction model and the congestion degree model may be trained using at least one of the weather, maximum temperature, minimum temperature, average temperature, maximum humidity, minimum humidity, and average humidity for at least one day included in a predetermined period including the current day. In this case, the customer number prediction model predicts the number of customers based on at least one of the results or forecasts of the weather, maximum temperature, minimum temperature, average temperature, maximum humidity, minimum humidity, and average humidity for at least one day included in a predetermined period including the current day. The congestion degree model determines the number of operating units based on at least one of the results or forecasts of the weather, maximum temperature, minimum temperature, average temperature, maximum humidity, minimum humidity, and average humidity for at least one day included in a predetermined period including the current day.

[0092] The customer number prediction model and the congestion degree model may be trained using other information. In this case, the customer number prediction model predicts the number of customers using actual values ​​or predicted values ​​of the information used for training. The congestion degree model determines the number of operating units using actual values ​​or predicted values ​​of the information used for training.

[0093] <Fourth embodiment> Next, a fourth embodiment of the present disclosure will be described in detail with reference to the drawings.

[0094] <Configuration> 9 is a block diagram illustrating an example of a configuration of a generation system 4 according to a fourth embodiment of the present disclosure. In the example illustrated in FIG. 9, the generation system 4 includes a generation device 13 and an imaging device 30.

[0095] The generating device 13 includes an instruction receiving unit 110, a number determining unit 120, a determination unit 130, an output unit 140, a model storage unit 150, a condition receiving unit 160, and a condition storage unit 170. The instruction receiving unit 110, the number determining unit 120, the determination unit 130, the output unit 140, the model storage unit 150, the condition receiving unit 160, and the condition storage unit 170 are the same as the components in the second embodiment that are given the same names and the same symbols. The instruction receiving unit 110, the number determining unit 120, the determination unit 130, the output unit 140, the model storage unit 150, the condition receiving unit 160, and the condition storage unit 170 operate in the same manner as the components in the second embodiment that are given the same names and the same symbols. The generating device 13 performs the same operation as the generating device 11 according to the second embodiment shown in FIG. 3. In addition to the same operations as those of the determining unit 130 in the second embodiment, the determining unit 130 performs the operations described below.

[0096] The generation device 13 further includes a display control unit 310, an allocation unit 320, a notification unit 330, an image reception unit 340, a congestion determination unit 350, a work status reception unit 360, and a work status management unit 370. The image reception unit 340 and the congestion determination unit 350 operate in the same manner as the image reception unit 240 and the congestion determination unit 250 of the third embodiment shown in Fig. 5, respectively. However, the congestion determination unit 350 shown in Fig. 9 does not store congestion degree information in the image information storage unit 260.

[0097] <Congestion determination unit 350> The congestion determination unit 350 determines, for each cash register, whether the congestion level indicates that the cash register is more crowded than a first standard, and whether the congestion level indicates that the cash register is less crowded than a second standard. The first standard and the second standard are, for example, thresholds for the congestion level. The congestion level corresponding to the value of the first standard indicates that there are more users waiting in the cash register queue to make a payment, compared to the congestion level corresponding to the value of the second standard.

[0098] In other words, the congestion determination unit 350 extracts, from among the operating cash registers, cash registers whose congestion level is higher than a first standard and cash registers whose congestion level is lower than a second standard. In the following description, a cash register whose congestion level is higher than the first standard is referred to as a "congested cash register." Also, a cash register whose congestion level is lower than the second standard is referred to as an "uncrowded cash register."

[0099] The congestion determination unit 350 transmits the extracted information for identifying the crowded cash register and the information for identifying the unoccupied cash register to the display control unit 310. Specifically, when there are crowded and unoccupied cash registers, the congestion determination unit 350 transmits an instruction to display the guidance including the information for identifying the crowded and unoccupied cash registers to the display control unit 310. The instruction to display the guidance (hereinafter also referred to as the guidance display instruction) may be, for example, a message or signal set in advance. The instruction to display the guidance may be information for identifying the crowded cash register and information for identifying the unoccupied cash register. When there are only crowded cash registers and when there are only unoccupied cash registers, the congestion determination unit 350 transmits a guidance non-display instruction, which is an instruction not to display the guidance, to the display control unit 310. The guidance non-display instruction may be, for example, a message or signal set in advance that is different from the message or signal of the guidance display instruction.

[0100] The congestion determination unit 350 also sends the congestion degree of each cash register that is in operation to the allocation unit 320.

[0101] <Display control unit 310> The display control unit 310 receives information identifying crowded cash registers and information identifying unoccupied cash registers from the congestion determination unit 350. Specifically, the display control unit 310 receives a guidance display instruction including information identifying crowded cash registers and information identifying unoccupied cash registers from the congestion determination unit 350. In addition, the display control unit 310 receives an instruction not to display guidance from the congestion determination unit 350.

[0102] When the display control unit 310 receives an instruction to display guidance including crowded and unoccupied cash registers, the display control unit 310 displays guidance, which is a display showing guidance to unoccupied cash registers, on a display device viewable within the queue range of that cash register. The guidance may be a text display indicating the location of the unoccupied cash register or the direction to that location. The guidance may be a graphic display indicating the location of the unoccupied cash register. The guidance may be a text and graphic display. When the display control unit 310 receives an instruction not to display guidance, the display control unit 310 does not display guidance.

[0103] The display control unit 310 may display advertisements for products on the display device. The display control unit 310 may display advertisements for products located around a cash register. The area around the cash register is, for example, next to the cash register on the side closer to the area where queues form.

[0104] Specifically, when a guidance display instruction is received from the congestion determination unit 350 (i.e., when the conditions for displaying guidance are satisfied), the display control unit 310 generates, for example, the guidance as described above, and displays the guidance and advertisements, for example, alternately and repeatedly. More specifically, when a guidance display instruction is received from the congestion determination unit 350, the display control unit 310 performs a setting to display, for example, the guidance and advertisements, for example, alternately and repeatedly. Then, the display control unit 310 displays, for example, alternately and repeatedly until the next guidance display instruction is received or a guidance display instruction is received.

[0105] When receiving a guide-guide non-display instruction from the congestion determination unit 350, the display control unit 310 sets to display the advertisement and not to display the guide guidance. Then, the display control unit 310 displays the advertisement and does not display the guide guidance until receiving the next guide-guide display instruction.

[0106] The display control unit 310 may display on the display device, other than advertisements and guidance, notices and other information. The display control unit 310 may display, for example, a display showing the congestion degree of each cash register. In this case, the congestion determination unit 350 sends the congestion degree of each cash register to the display control unit 310. The display control unit 310 then receives the congestion degree of each cash register from the congestion determination unit 350. In the display showing the congestion degree of each cash register, the congestion degree of each cash register may be represented by at least one of characters, figures, colors, and the like.

[0107] <Work Status Reception Unit 360> The work status receiving unit 360 receives an employee's identification information and an input indicating the start or end of work, which are input using an input device such as a keyboard, mouse, touch panel, or card reader of the generating device 13. The employee's identification information and the input indicating the start or end of work may be in any form of employee's identification information and input indicating the start or end of work used in an existing work management method. The method of receiving the employee's identification information and the input indicating the start or end of work may be any method of receiving the employee's identification information and input indicating the start or end of work used in an existing work management method.

[0108] When an input indicating that an employee has started work is received, the work status receiving unit 360 sends information indicating that the employee has started work to the work status management unit 370. When an input indicating that an employee has finished work is received, the work status receiving unit 360 sends information indicating that the employee has finished work to the work status management unit 370. Information identifying the employee is added to the information indicating that the employee has started work and the information indicating that the employee has finished work.

[0109] The work status receiving unit 360 receives from the cash register information indicating that the cash register has been changed to a state where it can process payments, and information identifying the employee who changed the cash register to a state where it can process payments. The work status receiving unit 360 also receives from the cash register information indicating that the cash register has been changed to a state where it cannot process payments. The information identifying the cash register is added, for example, to the information indicating that the cash register has been changed to a state where it can process payments, and the information indicating that the cash register has been changed to a state where it cannot process payments.

[0110] In the following explanation, the information indicating that the cash register has been changed to a state where it can handle transactions and the information identifying the employee who changed the cash register to a state where it can handle transactions will be referred to as an "operational notification." Also, the information indicating that the cash register has been changed to a state where it cannot handle transactions will be referred to as an "inoperational notification."

[0111] In this embodiment, the cash register is configured to send an operation notification to the work status receiving unit 360 of the generation device 13 when the employee changes the status of the cash register to a status where transactions can be performed. The cash register is also configured to send an inactivity notification to the work status receiving unit 360 of the generation device 13 when the employee changes the status of the cash register to a status where transactions cannot be performed.

[0112] When the work status receiving unit 360 receives an operating notification from the cash register, it sends the operating notification to the work status management unit 370. When the work status receiving unit 360 receives an inactive notification from the cash register, it sends the inactive notification to the work status management unit 370.

[0113] The work status receiving unit 360 receives the work schedule of each employee, for example, input by an operator of the generation device 13. The work schedule is, for example, information indicating the scheduled work start time and work end time of each employee on business days included in a predetermined period. The work status receiving unit 360 sends the received work schedule to the work status management unit 370.

[0114] <Decision Unit 130> The determination unit 130 of this embodiment further sends information indicating the employee in charge of the cash register for each time period on the day thus determined to the working status management unit 370.

[0115] <Work Status Management Unit 370> The work status management unit 370 receives, from the work status reception unit 360, information indicating that the employee has started working and information indicating that the employee has finished working, for each employee. The work status management unit 370 generates information on employees who are working, based on the information indicating that the employee has started working and information indicating that the employee has finished working, for each employee. For example, when the work status management unit 370 receives information indicating that the employee has started working, the work status management unit 370 sets the employee to an employee currently working. Specifically, when the work status management unit 370 receives information indicating that the employee has started working, the work status management unit 370 adds the employee to information on employees currently working (for example, a list of employees currently working). When the work status management unit 370 receives information indicating that the employee has finished working, the work status management unit 370 sets the employee to an employee not currently working. Specifically, when the work status management unit 370 receives information indicating that the employee has finished working, the work status management unit 370 removes the employee from information on employees currently working (for example, a list of employees currently working).

[0116] The work status management unit 370 receives an operating notification and an inactive notification for each cash register from the work status reception unit 360.

[0117] When the work status management unit 370 receives an operation notification, the employee identified by the operation notification is designated as the employee in charge of the cash register. Specifically, when the work status management unit 370 receives an operation notification, the employee identified by the operation notification is added to information (e.g., a list) of employees in charge of the cash register. Also, when the work status management unit 370 receives an operation notification, the cash register identified by the operation notification is designated as an operating cash register. Specifically, when the work status management unit 370 receives an operation notification, the cash register identified by the operation notification is added to information (e.g., a list) of operating cash registers.

[0118] When the work status management unit 370 receives an out-of-work notice, it sets the employee identified by the out-of-work notice as an employee not in charge of the cash register. Specifically, when the work status management unit 370 receives an out-of-work notice, it excludes the employee identified by the out-of-work notice from information (e.g., a list) of employees not in charge of the cash register. Furthermore, when the work status management unit 370 receives an out-of-work notice, it sets the cash register identified by the out-of-work notice as a cash register that is not in operation. Specifically, when the work status management unit 370 receives an out-of-work notice, it excludes the cash register identified by the out-of-work notice from information (e.g., a list) of cash registers that are in operation.

[0119] The work status management unit 370 receives the work schedule from the work status reception unit 360. The work status management unit 370 sends the received work schedule to the allocation unit 320.

[0120] The work status management unit 370 receives information indicating employees in charge of cash registers for each time period on the day from the determination unit 130. The work status management unit 370 identifies the number of cash registers scheduled to be in operation for each time period on the day from the received information indicating employees in charge of cash registers. If the number of employees in charge of cash registers is the same as the number of cash registers scheduled to be in operation, the work status management unit 370 sets the number of employees in charge of cash registers to the number of cash registers scheduled to be in operation.

[0121] The work status management unit 370 sends to the allocation unit 320 information on employees on duty, information on employees in charge of cash registers, information on cash registers that are in operation, and the number of cash registers that are scheduled to be in operation.

[0122] <Allocation Unit 320> The allocation unit 320 receives the congestion degree of each cash register in operation from the congestion determination unit 350. The allocation unit 320 also receives information on employees on duty, information on employees in charge of cash registers, information on cash registers in operation, and the number of cash registers scheduled to be in operation from the work status management unit 370. The allocation unit 320 further receives work schedules from the work status management unit 370.

[0123] The allocation unit 320 holds in advance information indicating whether each employee has the ability to operate a cash register (hereinafter, referred to as ability information). The ability information is provided to the allocation unit 320 in advance by, for example, an operator of the generation device 13.

[0124] If the number of cash registers whose congestion level is higher than the first criterion (i.e., crowded cash registers) satisfies the third criterion, the allocation unit 320 allocates employees who satisfy the second constraint to the cash registers that are not in operation.

[0125] The allocation unit 320 appropriately selects an idle cash register to which an employee is to be allocated from among cash registers not included in the information on the operating cash registers. The third criterion may be represented by a threshold value for the number of busy cash registers. In this case, the third criterion is satisfied when the number of busy cash registers is equal to or greater than the threshold. The third criterion may be represented by a threshold value for the ratio of the number of busy cash registers to the number of operating cash registers. In this case, the third criterion is satisfied when the ratio of the number of busy cash registers to the number of operating cash registers is equal to or greater than the threshold. The third criterion may be appropriately determined. The second constraint condition is, for example, that an employee has the ability to be in charge of a cash register, as indicated by the ability condition, that the employee is on duty, and that the employee is not in charge of a cash register. The second constraint condition is satisfied, for example, when the ability information indicates that an employee has the ability to be in charge of a cash register, the information on the employees on duty includes information on the employees, and the information on the employees in charge of the cash register does not include information on the employees. The second constraint condition may further include that the time from the time the allocation unit 320 selects an employee who satisfies the second constraint condition to the time the employee's work schedule indicates the end of the employee's work is longer than a predetermined time.

[0126] Furthermore, when the number of operating cash registers is less than the number of cash registers that are scheduled to be in operation, the allocation unit 320 may allocate employees that satisfy the second constraint to the cash registers that are not in operation.

[0127] If the number of cash registers that indicate a level of congestion less than the second criterion (i.e., quiet registers) satisfies the fourth criterion, the allocation unit 320 may remove any of the employees in charge of the cash registers from their responsibility for the cash registers.

[0128] The fourth criterion may be expressed by a threshold value for the number of idle cash registers. In this case, the fourth criterion is met when the number of idle cash registers is equal to or greater than the threshold. The fourth criterion may be expressed by a threshold value for the ratio of the number of idle cash registers to the number of operating cash registers. In this case, the fourth criterion is met when the ratio of the number of idle cash registers to the number of operating cash registers is equal to or greater than the threshold. The fourth criterion may be determined as appropriate. The fourth criterion does not need to be the same as the third criterion.

[0129] The allocation unit 320 may exclude employees who satisfy appropriately set exclusion conditions from working the cash register. The exclusion condition may be, for example, that the employee has been working the cash register for the longest time. The exclusion condition may be, for example, that the employee is working at a quiet cash register. The exclusion condition may be, for example, that the employee has the shortest time until the end of work as indicated by the work schedule among the employees working the cash register. The exclusion condition may be a condition other than these examples. The exclusion condition may be expressed by a logical expression of at least one of the conditions shown in the above examples. When multiple employees satisfy the exclusion condition, the allocation unit 320 may select one employee from the multiple employees according to an appropriately determined method.

[0130] If the number of operating cash registers is equal to or less than the number of cash registers that are scheduled to be in operation, the allocation unit 320 does not need to remove the employee in charge of the cash register from being in charge of the cash register.

[0131] The allocation unit 320 sends information identifying the employee assigned to the out-of-operation cash register to the notification unit 330. The allocation unit 320 also sends information identifying the employee excluded from the employees in charge of the cash register to the notification unit 330.

[0132] <Notification section 330> The notification unit 330 receives information identifying an employee assigned to an out-of-operation cash register from the allocation unit 320. When the notification unit 330 receives information identifying an employee assigned to an out-of-operation cash register, the notification unit 330 notifies the employee assigned to the out-of-operation cash register that he or she has been assigned to the cash register.

[0133] Furthermore, the notification unit 330 receives information identifying an employee who has been removed from the employees in charge of the cash register from the allocation unit 320. When the notification unit 330 receives information identifying an employee who has been removed from the employees in charge of the cash register, the notification unit 330 notifies the employee who has been removed from the employees in charge of the cash register that he or she has been removed from the employees in charge of the cash register.

[0134] The method of notifying the employee by the notification unit 330 may be, for example, to send a message representing the content of the notification to a mobile terminal held by the employee. In this case, the mobile terminal receives the message representing the content of the notification and displays the received message. The method of notifying the employee by the notification unit 330 may be, for example, to send a signal representing the content of the notification to a mobile terminal held by the employee. In this case, the mobile terminal may receive the signal and perform a different operation depending on the content of the notification represented by the signal. The operation that differs depending on the content of the notification represented by the signal may be, for example, to generate at least one of a sound, a vibration, and a light of a pattern that is predetermined depending on the content of the notification represented by the signal. The method of notifying the employee by the notification unit 330 may be, for example, to notify an operator who makes an announcement in the store. In this case, the operator who makes an announcement in the store makes an announcement depending on the content of the notification.

[0135] <Operation> Next, the operation of the generating device 13 according to the fourth embodiment of the present disclosure will be described in detail with reference to the drawings.

[0136] FIG. 10 is a flowchart showing the overall operation of the generating device 13 according to the fourth embodiment of the present disclosure. In the example shown in FIG. 10, the image receiving unit 340 receives an image from the imaging device 30 (step S301). Next, the congestion determining unit 350 determines the congestion degree of each cash register based on the image (step S302). Next, the generating device 13 performs a guidance process to display a guide to guide a user from a crowded cash register to a non-crowded cash register (step S303). Then, the determining unit 130 performs an allocation process to assign an employee to an inactive cash register (step S304). The determining unit 130 further performs a release process to release the allocation of the employee to the active cash register (step S305). The guidance process, allocation process, and release process will be described in detail below.

[0137] Fig. 11 is a flowchart showing the operation of the guidance process of the generating device 13 according to the fourth embodiment of the present disclosure. In the example shown in Fig. 11, the display control unit 310 determines whether the congestion degree of each cash register satisfies the condition for displaying the guidance guidance (step S311). If the condition for displaying the guidance guidance is not satisfied (NO in step S312), the display control unit 310 sets the display device to display an advertisement (step S315).

[0138] When the condition for displaying the guide is satisfied (YES in step S312), the display control unit 310 generates the guide (step S313). Then, the display control unit 310 sets the guide and the advertisement to be repeatedly displayed (step S314).

[0139] Fig. 12 is a flowchart showing the operation of the allocation process of the generating device 13 according to the fourth embodiment of the present disclosure. In the example shown in Fig. 12, the allocation unit 320 determines whether a condition for additional allocation is satisfied, that is, an employee who is not in charge of a cash register is allocated to a cash register that is not in operation (step S321). If the condition for additional allocation is not satisfied (NO in step S322), the generating device 13 ends the operation shown in Fig. 12.

[0140] If the condition for additional allocation is not met (YES in step S322), the allocation unit 320 allocates the employee who satisfies the second constraint to the cash register that is not in operation (step S323). Then, the notification unit 330 notifies the employee who is assigned to the cash register (step S324).

[0141] Fig. 13 is a flowchart showing the operation of the release process of the generating device 13 according to the fourth embodiment of the present disclosure. In the example shown in Fig. 13, the allocation unit 320 determines whether a condition for releasing the allocation of the employee in charge of the operating cash register to the cash register is satisfied (step S331). If the condition for releasing the allocation is satisfied (NO in step S332), the generating device 13 ends the operation shown in Fig. 13.

[0142] If the conditions for canceling the allocation are met (YES in step S332), the allocation unit 320 selects an employee whose allocation to the cash register is to be cancelled (step S333). The allocation unit 320 notifies the selected employee that the allocation to the cash register has been cancelled (step S334).

[0143] <Effects> The present embodiment described above has the same effects as the first embodiment, for the same reasons as those for the effects of the first embodiment.

[0144] This embodiment has the effect of better achieving both improved cash register efficiency and improved customer satisfaction. This is because, when the conditions for displaying guidance are met, the display control unit 310 displays guidance to guide users waiting in line at a crowded cash register from the crowded cash register to an unoccupied cash register. Then, when the conditions for additional allocation are met, the allocation unit 320 allocates an employee not in charge of a cash register to an idle cash register. Furthermore, when the conditions for de-allocation are met, the allocation unit 320 de-allocates the employee in charge of the cash register from the allocation to the cash register.

[0145] <Fourth modified example> The generating device according to the fourth embodiment may further include the sales information receiving unit 210, the sales information storage unit 220, the learning unit 230, the image receiving unit 240, the congestion determination unit 250, and the image information storage unit 260 included in the generating device 12 according to the third embodiment. In this case, the generating device according to the fourth embodiment further includes the same functions as the generating device 12 according to the third embodiment, and further performs the same operations as the generating device 12 according to the third embodiment. In this case, the image receiving unit 340 may also operate as the image receiving unit 240. And the congestion determination unit 350 may also operate as the congestion determination unit 250.

[0146] <Fifth modified example> The congestion determination unit 350 according to the fourth embodiment may determine the congestion degree for each type of cash register (in other words, the congestion degree of the cash register type). In this case, the congestion determination unit 350 calculates the average congestion degree of cash registers of the same type in an operating state as the congestion degree of the cash register type. Then, the congestion determination unit 350 determines whether or not the cash register is a congested cash register for each type. Furthermore, the congestion determination unit 350 determines whether or not the cash register is an idle cash register for each type.

[0147] The display control unit 310 may display an indication indicating the degree of congestion of each cash register for each type of cash register.

[0148] The allocation unit 320 allocates an employee to any of the cash registers that are not in operation and that indicate that the congestion level of the type is the most crowded. The allocation unit 320 may also select a cash register from which to release an employee allocation from among the cash registers that indicate that the congestion level of the type is the least crowded.

[0149] The notification unit 330 may notify an employee assigned to a cash register of the type that indicates the highest congestion level among the types of cash registers that are not in operation.

[0150] <Sixth Modification> In the third embodiment, the number of customers is the number of times a transaction was processed at the cash register 50 (i.e., a cash register) calculated from sales information, whereas in the sixth variant, the number of customers is the number of people who entered the store.

[0151] In this case, the imaging device 30 is also attached to the entrance of the store so as to capture images of people entering and leaving the store. The image receiving unit 240 also receives images from the imaging device 30 attached to the entrance of the store. The congestion determination unit 250 then extracts visitors to the store from the images captured by the imaging device 30 attached to the store, and counts the number of visitors to the store for each time period. The congestion determination unit 250 stores the number of visitors for each time period in the image information storage unit 260. The learning unit 230 reads out the number of visitors for each time period from the image information storage unit 260 as the number of customers.

[0152] The number of customers may be the number of customers staying in the store. In this case, the congestion determination unit 250 may count the number of people entering the store and the number of people leaving the store. The congestion determination unit 250 may derive the transition of the number of customers staying in the store from the number of people entering and the number of people leaving. Then, the congestion determination unit 250 may calculate the average number of customers staying in the store for each time period from the transition of the number of customers staying in the store.

[0153] <Seventh Variation> In this modification, the number estimation unit 120 determines the number of operating cash registers without using a congestion degree model obtained by machine learning. The number determination unit 120 predicts the number of customers for each time period on the target day using a customer number prediction model as described above. Then, the number determination unit 120 determines the number of operating cash registers for each time period on the target day based on the predicted number of customers for each time period on the target day, without relying on the congestion degree model obtained by machine learning, so that the congestion degree satisfies the congestion condition.

[0154] Specifically, for example, the number determination unit 120 uses past sales information in advance to calculate the average processing time required for one transaction per cash register in operation (hereinafter, also referred to as the average processing time). The number determination unit 120 may calculate the maximum number of transactions per unit time per cash register (hereinafter, referred to as the maximum number of transactions) from the processing time required for one transaction. The maximum number corresponds to the number of transactions per unit time per cash register when an employee in charge of the cash register continues to process transactions without a break. The number determination unit 120 calculates, for each time slot on the target day, the minimum number of operating cash registers that satisfies the congestion condition based on the maximum number of transactions (or the average processing time), the predicted number of customers, and the number of operating cash registers and congestion level at the end of the previous time slot. In addition, the number determination unit 120 calculates the congestion level at the end of the time slot when the number of operating cash registers is the calculated number of operating cash registers as follows. Specifically, the number determination unit 120 calculates the number of people waiting to pay at the start of a time period (referred to as a target time period) for which the number of operating units is to be calculated, based on the degree of congestion of the cash register in the time period immediately preceding the target time period and the number of operating cash registers. When the degree of congestion is the average number of users waiting in line, the number determination unit 120 determines the product of the degree of congestion and the number of operating cash registers as the number of people waiting to pay at the start of the target time period (referred to as the remaining number of people). For example, the number determination unit 120 calculates the minimum number of operating units such that the sum of the remaining number of people and the calculated number of customers minus the product of the maximum number of transactions and the number of operating cash registers does not exceed the value obtained by subtracting the average number of people indicated by the threshold value of the congestion condition multiplied by the number of operating cash registers. Note that the number of operating units in this case is a natural number. The number-of-machine determination unit 120 determines the degree of congestion at the end of the target time period by subtracting the product of the maximum number of transactions and the calculated number of machines in operation from the sum of the remaining number of people and the calculated number of customers, and dividing the result by the calculated number of machines in operation.

[0155] The number determining unit 120 may determine the number of operating cash registers by a method other than the example of the method described above.

[0156] <Other embodiments> Each of the generating devices according to the embodiments of the present disclosure can be realized by a computer including a memory in which a program read from a storage medium is loaded and a processor that executes the program. Each of the generating devices according to the embodiments of the present disclosure can also be realized by dedicated hardware. Each of the generating devices according to the embodiments of the present disclosure can also be realized by a combination of the above-mentioned computer and dedicated hardware.

[0157] FIG. 14 is a diagram illustrating an example of a hardware configuration of a computer 1000 that can realize each of the generating devices according to the embodiment of the present disclosure. In the example illustrated in FIG. 14, the computer 1000 includes a processor 1001, a memory 1002, a storage device 1003, and an I / O (Input / Output) interface 1004. The computer 1000 can also access a storage medium 1005. The memory 1002 and the storage device 1003 are, for example, storage devices such as a RAM (Random Access Memory) and a hard disk. The storage medium 1005 is, for example, a storage device such as a RAM or a hard disk, a ROM (Read Only Memory), or a portable storage medium. The storage device 1003 may be the storage medium 1005. The processor 1001 can read and write data and programs from the memory 1002 and the storage device 1003. The processor 1001 can access, for example, the store server device 20 and the imaging device 30 via the I / O interface 1004. The processor 1001 can access a storage medium 1005. The storage medium 1005 stores a program that causes the computer 1000 to operate as a generating device according to an embodiment of the present disclosure.

[0158] The processor 1001 loads a program stored in the storage medium 1005, which causes the computer 1000 to operate as a generating device according to an embodiment of the present disclosure, into the memory 1002. Then, the processor 1001 executes the program loaded into the memory 1002, causing the computer 1000 to operate as a generating device according to an embodiment of the present disclosure.

[0159] The instruction receiving unit 110, the number determining unit 120, the deciding unit 130, the output unit 140, and the condition receiving unit 160 can be realized, for example, by the processor 1001 that executes a program loaded in the memory 1002. The sales information receiving unit 210, the learning unit 230, the image receiving unit 240, and the congestion determining unit 250 can be realized, for example, by the processor 1001 that executes a program loaded in the memory 1002. The display control unit 310, the allocation unit 320, the notification unit 330, the image receiving unit 340, the congestion determining unit 350, the working status receiving unit 360, and the working status management unit 370 can be realized, for example, by the processor 1001 that executes a program loaded in the memory 1002. The model storage unit 150, the condition storage unit 170, the sales information storage unit 220, and the image information storage unit 260 can be realized, for example, by the memory 1002 and the storage device 1003 such as a hard disk device included in the computer 1000. It is also possible to realize some or all of the instruction receiving unit 110, the number determination unit 120, the decision unit 130, the output unit 140, the model storage unit 150, the condition receiving unit 160, and the condition storage unit 170 by dedicated circuits. It is also possible to realize some or all of the sales information receiving unit 210, the sales information storage unit 220, the learning unit 230, the image receiving unit 240, the congestion determination unit 250, and the image information storage unit 260 by dedicated circuits. It is also possible to realize some or all of the display control unit 310, the allocation unit 320, the notification unit 330, the image receiving unit 340, the congestion determination unit 350, the work status receiving unit 360, and the work status management unit 370 by dedicated circuits.

[0160] Furthermore, some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0161] (Appendix 1) a number determination means for determining the number of operating cash registers for each time period on a target day so that the degree of congestion of users of the cash registers satisfies a congestion condition; a determination means for determining an employee who will be in charge of the cash register for each time period on the target day based on the number of operating units so as to satisfy a constraint condition for the employee; A generating device comprising:

[0162] (Appendix 2) The number of units determining means predicts the number of customers for each time period on the target day using a customer number prediction model that represents the relationship between a time period and the number of customers, and determines the number of operating units based on the predicted number of customers. 2. The generating device of claim 1.

[0163] (Appendix 3) The number determination means determines the number of operating cash registers of each type for each time period of the target day, The determination means determines the employee who will be in charge of the cash registers of each type for each time period of the target day based on the number of operating units of each type. 3. The generating device of claim 2.

[0164] (Appendix 4) The customer number prediction model represents a relationship between a time period and the number of customers for each customer segment, the number determination means determines the number of operating cash registers of each type for each time period on the target day based on the number of customers for each customer segment; 4. The generating device of claim 3.

[0165] (Appendix 5) A learning means for learning the customer number prediction model based on sales information in the cash register. Equipped with The sales information includes information on the date and time of a transaction for each of the cash registers and each of the users. 5. The generating device according to any one of claims 2 to 4.

[0166] (Appendix 6) A congestion determination means for determining the degree of congestion based on an image of a waiting area in which a queue occurs at the cash register. 6. The generating device according to claim 1, further comprising:

[0167] (Appendix 7) the congestion determination means determines, for each of the cash registers, whether the congestion degree indicates that the cash register is more crowded than a first standard and whether the congestion degree indicates that the cash register is less crowded than a second standard; a display control means for displaying, on a display device viewable from within the range, a guide display indicating a cash register whose congestion level is less than the second standard when there is a cash register whose congestion level is greater than the first standard; 7. The generating device of claim 6, further comprising:

[0168] (Appendix 8) an allocation means for allocating the employees that satisfy a second constraint condition to the cash registers that are not in operation when the number of the cash registers that indicate the degree of congestion is greater than the first criterion satisfies a third criterion; a notification means for notifying the employee assigned to the out-of-service cash register; 8. The generating device of claim 7, comprising:

[0169] (Appendix 9) The display control means further displays an advertisement. 9. The generating device of claim 7 or 8.

[0170] (Appendix 10) Determine the number of operating cash registers for each time period on a target day so that the degree of congestion of users of the cash registers satisfies a congestion condition; determining an employee in charge of the cash register for each time period on the target day based on the number of operating units so as to satisfy the constraints of the employee; Generation method.

[0171] (Appendix 11) predicting the number of customers for each time period on the target day using a customer number prediction model that represents the relationship between time periods and the number of customers, and determining the number of operating units based on the predicted number of customers; 11. The method of generating the same according to claim 10.

[0172] (Appendix 12) determining the number of operating cash registers by type for each time period on the target day; Based on the number of operating units for each type, the employee in charge of the cash register for each type is determined for each time period of the target day. 12. The method of generating the same according to claim 11.

[0173] (Appendix 13) The customer number prediction model represents a relationship between a time period and the number of customers for each customer segment, determining the number of operating cash registers for each type for each time period on the target day based on the number of customers for each customer segment; 13. The method of generating the same according to claim 12.

[0174] (Appendix 14) learning the customer number prediction model based on sales information of the cash register; The sales information includes information on the date and time of a transaction for each of the cash registers and each of the users. A method for generating a signal according to any one of claims 11 to 13.

[0175] (Appendix 15) The degree of congestion is determined based on a waiting image obtained by capturing an image of an area where a queue occurs at the cash register. A method for generating a signal according to any one of claims 10 to 14.

[0176] (Appendix 16) determining, for each of the cash registers, whether the congestion degree indicates that the cash register is busier than a first standard and whether the congestion degree indicates that the cash register is less busy than a second standard; When there is a cash register whose congestion level is higher than the first standard, a guide display showing the cash register whose congestion level is lower than the second standard is displayed on a display device viewable within the range. 16. The method of generating the same according to claim 15.

[0177] (Appendix 17) When the number of the cash registers indicating that the congestion degree is greater than the first criterion satisfies a third criterion, the employee who satisfies the second constraint condition is assigned to the cash register that is not in operation; notifying the employee assigned to the out-of-service cash register; 17. The method of generating the same according to claim 16.

[0178] (Appendix 18) Plus, display ads 18. The method of generating the compound according to claim 16 or 17.

[0179] (Appendix 19) A number determination process for determining the number of operating cash registers for each time period on a target day so that the degree of congestion of users of the cash registers satisfies a congestion condition; a determination process for determining an employee who will be in charge of the cash register for each time period on the target day based on the number of operating units so as to satisfy the constraints of the employee; A program that causes a computer to execute the following.

[0180] (Appendix 20) The number of units determination process predicts the number of customers for each time period on the target day using a customer number prediction model that represents the relationship between a time period and the number of customers, and determines the number of operating units based on the predicted number of customers. 19. The program according to claim 19.

[0181] (Appendix 21) The number determination process determines the number of operating cash registers of each type for each time period of the target day, The determination process determines the employee who will be in charge of the cash register of each type for each time period of the target day based on the number of operating units of each type. 21. The program according to claim 20.

[0182] (Appendix 22) The customer number prediction model represents a relationship between a time period and the number of customers for each customer segment, The number determination process determines the number of operating cash registers of each type for each time period on the target day based on the number of customers for each customer segment. 22. The program according to claim 21.

[0183] (Appendix 23) A learning process for learning the customer number prediction model based on sales information at the cash register. on the computer, The sales information includes information on the date and time of a transaction for each of the cash registers and each of the users. 23. A program according to any one of appendices 20 to 22.

[0184] (Appendix 24) A congestion determination process for determining the congestion degree based on a waiting image obtained by capturing an area where a queue occurs at the cash register. 24. The program according to any one of claims 19 to 23, which causes a computer to execute the program.

[0185] (Appendix 25) the congestion determination process determines, for each of the cash registers, whether the congestion degree indicates that the cash register is more crowded than a first standard and whether the congestion degree indicates that the cash register is less crowded than a second standard; a display control process for displaying, on a display device viewable from the range, a guide display indicating a cash register whose congestion level is less than the second standard when the cash register whose congestion level is greater than the first standard is present; The program according to claim 24, further causing a computer to execute the above steps.

[0186] (Appendix 26) an allocation process for allocating the employees that satisfy the second constraint condition to the cash registers that are not in operation when the number of the cash registers that indicate the degree of congestion is greater than the first criterion satisfies a third criterion; a notification process for notifying the employee assigned to the out-of-service cash register; 26. The program according to claim 25, which causes a computer to execute the above steps.

[0187] (Appendix 27) The display control process further includes displaying an advertisement. 27. The program according to claim 25 or 26.

[0188] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0189] 3. Generation System 4. Generator System 10 Generator 11 Generator 12 Generator 13 Generator 20 Store server device 30 Imaging device 50 Register device 110 Instruction Reception Department 120 Number of vehicles determination section 130 Decision Section 140 Output section 150 Model Memory Section 160 Conditions Reception Department 170 Condition memory section 210 Sales Information Reception Department 220 Sales information storage unit 230 Learning Department 240 Image Reception Department 250 Congestion Judgment Unit 260 Image information storage unit 310 Display control unit 320 Allocation Section 330 Notification Department 340 Image Reception Department 350 Congestion Judgment Unit 360 Work Status Reception Department 370 Working Status Management Department 1000 Computers 1001 Processor 1002 Memory 1003 Storage device 1004 I / O Interface 1005 Storage medium

Claims

1. A generating device, comprising: a congestion determination means for determining a congestion level based on an image of an area where a queue occurs at a cash register; a number determination means for determining the number of operating cash registers for each time period on a target day so that the congestion degree of users of the cash registers satisfies a congestion condition; a determination means for determining an employee who will be in charge of the cash register for each time period on the target day based on the number of operating units so as to satisfy a constraint condition for the employee; Equipped with the congestion determination means determines, for each of the cash registers, whether the congestion degree indicates that the cash register is more crowded than a first standard and whether the congestion degree indicates that the cash register is less crowded than a second standard; The generating device comprises: a display control means for displaying, on a display device viewable from within the range, a guide display indicating a cash register whose congestion level is less than the second standard when there is a cash register whose congestion level is greater than the first standard; Further equipped with The constraint condition of the employee is that the employee is determined as the employee in charge of the cash register during a time period designated as a time period during which the employee is in charge of the cash register; The first criterion is a first threshold value that is a threshold value for the congestion degree, The second criterion is a second threshold value that is a threshold value for the congestion degree, and is the second threshold value that represents that the congestion degree is not high compared to the first criterion. generator.

2. The number of units determining means predicts the number of customers for each time period on the target day using a customer number prediction model that represents the relationship between a time period and the number of customers, and determines the number of operating units based on the predicted number of customers. The generating device of claim 1 .

3. The number determination means determines the number of operating cash registers of each type for each time period of the target day, The determination means determines the employee who will be in charge of the cash registers of each type for each time period of the target day based on the number of operating units of each type. The generating device according to claim 2 .

4. The customer number prediction model represents a relationship between a time period and the number of customers for each customer segment, the number determination means determines the number of operating cash registers of each type for each time period on the target day based on the number of customers for each customer segment; The generating device according to claim 3 .

5. A learning means for learning the customer number prediction model based on sales information in the cash register. Equipped with The sales information includes information on the date and time of a transaction for each of the cash registers and each of the users. A generating device according to any one of claims 2 to 4.

6. an allocation means for allocating the employees that satisfy a second constraint condition to the cash registers that are not in operation when the number of the cash registers that indicate the degree of congestion is greater than the first criterion satisfies a third criterion; a notification means for notifying the employee assigned to the out-of-service cash register; Equipped with the third criterion being that the number of crowded cash registers, which are the cash registers whose congestion degree is more crowded than the first criterion, is greater than a third threshold, which is a threshold for the number of the crowded cash registers; The second constraint condition is at least that the employee has the ability to man the cash register as indicated by the ability condition, that the employee is on duty, and that the employee is not manning the cash register. A generating device according to any one of claims 1 to 5.

7. A computer comprising: A congestion level is determined based on an image of a waiting area of ​​the cash register where a queue occurs; determining the number of cash registers in operation for each time period on a target day such that the degree of congestion of users of the cash registers satisfies a congestion condition; determining an employee in charge of a cash register for each time period on the target day based on the number of operating units so as to satisfy the constraints of the employee; determining, for each of the cash registers, whether the congestion degree indicates that the cash register is busier than a first standard and whether the congestion degree indicates that the cash register is less busy than a second standard; when there is a cash register whose congestion level is greater than the first standard, displaying a guide display on a display device viewable within the range that indicates the cash register whose congestion level is less than the second standard, The constraint condition of the employee is that the employee is determined as the employee in charge of the cash register during a time period designated as a time period during which the employee is in charge of the cash register; The first criterion is a first threshold value that is a threshold value for the congestion degree, The second criterion is a second threshold value that is a threshold value for the congestion degree, and is the second threshold value that represents that the congestion degree is not high compared to the first criterion. Generation method.

8. A program, comprising: a congestion determination process for determining a congestion level based on an image of an area where queues occur at the cash register; a number determination process for determining the number of operating cash registers for each time period on a target day so that the congestion degree of users of the cash registers satisfies a congestion condition; a determination process for determining an employee who will be in charge of the cash register for each time period on the target day based on the number of operating units so as to satisfy the constraints of the employee; Run the following on your computer: the congestion determination process determines, for each of the cash registers, whether the congestion degree indicates that the cash register is more crowded than a first standard and whether the congestion degree indicates that the cash register is less crowded than a second standard; The program is a display control process for displaying, on a display device viewable from the range, a guide display indicating a cash register whose congestion level is less than the second standard when the cash register whose congestion level is greater than the first standard is present; and causing the computer to further execute the The constraint condition of the employee is that the employee is determined as the employee in charge of the cash register during a time period designated as a time period during which the employee is in charge of the cash register; The first criterion is a first threshold value that is a threshold value for the congestion degree, The second criterion is a second threshold value that is a threshold value for the congestion degree, and is the second threshold value that represents that the congestion degree is not high compared to the first criterion. program.

Images