JP2023117423A - Prediction device, prediction system, prediction method, and program - Google Patents

Abstract

To provide a prediction device capable of appropriately predicting the number of orders of each menu.SOLUTION: A prediction device 20 includes: an attendance schedule acquisition section 21 that acquires attendance schedule information of a user; a reservation acquisition section 22 that acquires reservation information on a menu reserved by the user; an order history acquisition section 23 that acquires order history information of the user; and a prediction section 24 that predicts the number of orders of menu in a dining hall on the basis of the attendance schedule information, the reservation information, and the order history information. When a user scheduled to attend does not reserve a menu, the prediction section 24 estimates a menu to be ordered by the user on the basis of the order history information and predicts the number of orders on the basis of an estimation result.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a prediction device, a prediction system, a prediction method, and a program.

2. Description of the Related Art Techniques for automatically accepting menu orders in employee cafeterias, restaurants, and the like are known. As a related technique, for example, Patent Literature 1 discloses a product ordering system for a company cafeteria used in the company cafeteria. In this product ordering method, each employee transmits data including an employee identification number, a personal identification number, numerical values and symbols for menu reservation to a totalizing/processing device using a push-button telephone. The tabulation/processing device processes the transmitted data as reservation data to calculate the exact consumption of each menu.

JP-A-08-055161

In recent years, in order to reduce the risk of spreading infectious diseases, there are increasing opportunities to telework from home instead of going to the office. For companies with many employees who telework, it is difficult to ascertain the number of people using the employee cafeteria, making it difficult to predict the quantity of materials ordered. Therefore, if the number of dining room users is larger than expected, some menu items may be out of stock. The product ordering method disclosed in Patent Document 1 does not consider such a problem.

An object of the present disclosure is to provide a prediction device, a prediction system, a prediction method, and a program capable of appropriately predicting the number of menu orders in view of the above-described problems.

The prediction device according to the present disclosure is
a work schedule acquisition unit that acquires work schedule information of a user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
The prediction unit estimates the order menu of the user based on the order history information and predicts the number of orders based on the estimation result when the user who is scheduled to come to work has not made a menu reservation.

The prediction system according to the present disclosure is
a POS terminal that stores user order history information in the cafeteria;
a prediction device;
The prediction device is
a work schedule acquisition unit that acquires work schedule information of the user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user from the POS terminal;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
The prediction unit estimates the order menu of the user based on the order history information and predicts the number of orders based on the estimation result when the user who is scheduled to come to work has not made a menu reservation.

The prediction method according to the present disclosure is
a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
a prediction step of predicting the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user who is scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result.

The program according to the present disclosure is
a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
causing a computer to execute a prediction step of predicting the number of menu orders in a cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user who is scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result.

A prediction device, a prediction system, a prediction method, and a program according to the present disclosure make it possible to appropriately predict the number of menu orders.

1 is a block diagram showing the configuration of a prediction device according to Embodiment 1; FIG. It is a block diagram which shows the structure of the prediction system concerning Embodiment 2. FIG. FIG. 8 is a block diagram showing the configuration of a user terminal according to the second embodiment; FIG. 2 is a block diagram showing the configuration of a POS terminal according to a second embodiment; FIG. FIG. 7 is a block diagram showing the configuration of a server according to the second embodiment; FIG. 10 is a flowchart showing an office attendance schedule information registration process performed by the user terminal according to the second embodiment; FIG. 11 is a diagram showing an example of office attendance schedule information according to the second embodiment; FIG. 10 is a diagram showing an example of reservation information according to the second embodiment; FIG. 10 is a flowchart showing recording processing performed by a work recording unit when a user works from home in Embodiment 2. FIG. 10 is a flowchart showing recording processing performed by a work recording unit when a user comes to work in Embodiment 2; FIG. 10 is a diagram showing an example of work history information according to the second embodiment; FIG. FIG. 10 is a diagram showing an example of order history information according to the second embodiment; FIG. 10 is a flowchart showing a process of predicting the number of menu orders, which is performed by a prediction unit according to the second embodiment; FIG. 10 is a diagram showing an example of order prediction information according to the second embodiment; FIG. FIG. 11 is a diagram showing an example of order record information according to the second embodiment; FIG. FIG. 11 is a diagram showing an example of material table information according to the second embodiment; FIG. FIG. 11 is a sequence diagram showing processing of the prediction system according to the second embodiment; FIG. 11 is a block diagram showing the configuration of a prediction system according to Embodiment 3; FIG. FIG. 11 is a block diagram showing the configuration of a server according to a third embodiment; FIG. 14 is a flow chart showing recording processing performed by a work recording unit when a user comes to work in Embodiment 3. FIG. FIG. 12 is a diagram showing an example of physical condition information and order history information according to the third embodiment; 13 is a flowchart showing a process of predicting the number of menu orders, which is performed by a prediction unit according to the third embodiment; FIG. 11 is a sequence diagram showing processing of the prediction system according to the third embodiment; It is a figure which shows the hardware configuration example.

Embodiments of the present disclosure are described in detail below with reference to the drawings. In the drawings, the same or corresponding elements are labeled with the same reference numerals. Duplicate explanations are omitted as necessary for clarity of explanation.

<Embodiment 1>
A prediction device 20 according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of a prediction device 20 according to this embodiment. The prediction device 20 includes an office attendance schedule acquisition unit 21 , a reservation acquisition unit 22 , an order history acquisition unit 23 , and a prediction unit 24 .

The office attendance schedule acquisition unit 21 acquires office attendance schedule information of the user. The reservation acquisition unit 22 acquires reservation information regarding a user's reservation menu. The order history acquisition unit 23 acquires the order history information of the user. The prediction unit 24 predicts the number of menu orders in the cafeteria based on the office attendance schedule information, reservation information, and order history information. Further, when the user scheduled to come to work has not reserved a menu, the prediction unit 24 estimates the user's order menu based on the order history information, and predicts the number of orders based on the estimation result.

As described above, according to the prediction device 20 of the present embodiment, when a user who is scheduled to come to work has not reserved a menu, the order menu is estimated based on the user's order history information. Therefore, even if a user who is scheduled to come to work has not reserved a menu, the menu ordered by the user can be estimated. As a result, it is possible to appropriately predict the number of menu orders in the cafeteria.

<Embodiment 2>
Embodiment 2 is a specific example of Embodiment 1 described above. FIG. 2 is a block diagram showing the configuration of the prediction system 1000 according to this embodiment. The prediction system 1000 includes a user terminal 100 , a server (prediction device) 200 and a POS (Point Of Sale) terminal 300 . Each configuration is connected via a network N so as to be able to communicate with each other. The network N is a wired or wireless communication line. The configuration shown in FIG. 2 is an example. For example, a plurality of user terminals 100 and POS terminals 300 that communicate with the server 200 may be provided.

First, an outline of the prediction system 1000 will be described, and details of each configuration will be described later. The prediction system 1000 is, for example, an information processing system used to predict the quantity of menu items to be ordered in a company cafeteria used by users such as employees. The prediction system 1000 may be used, for example, for a restaurant such as a restaurant that has a contract with a corporation or the like to provide meals. The prediction system 1000 may also be used when predicting the order quantity of products to be provided at stores.

In this embodiment, a case where the prediction system 1000 is implemented in a staff cafeteria provided in the same building or site as an office will be described. In this embodiment, the user is a user of the company cafeteria. A user is, for example, an employee or an officer belonging to a corporation or the like.

In the prediction system 1000 , the user uses the user terminal 100 to register office attendance schedule information in the server 200 . The user registers in the server 200 whether to work at the office or work from home on a predetermined scheduled work day. As a result, the server 200 acquires office attendance schedule information regarding the user's attendance at office. If the user wishes to use the cafeteria on the day he or she is scheduled to come to work, the user uses the user terminal 100 to make a reservation for the menu to be ordered at the cafeteria. The server 200 receives a menu reservation from the user terminal 100 and stores reservation information regarding the reservation. The server 200 also acquires order history information for the user's restaurant from the POS terminal 300 .

The server 200 estimates the menu to be ordered by the user based on the user's order history information when the user who is scheduled to come to work has not made a reservation on the prediction target day for predicting the number of menu orders. The server 200 predicts the number of menu orders in the cafeteria based on the estimation result. As a result, it is possible to appropriately predict the number of orders for each menu, so that it is possible to appropriately order materials.

Next, each configuration of the prediction system 1000 will be described in detail.
First, the user terminal 100 will be described with reference to FIG. FIG. 3 is a block diagram showing the configuration of the user terminal 100. As shown in FIG. The user terminal 100 includes a registration section 110 , an input section 120 , a display section 130 and a communication section 170 .

A user terminal 100 is an information terminal used by a user. The user is, for example, an employee who can use the company cafeteria. The user terminal 100 is, for example, a mobile phone terminal, a smart phone, a tablet terminal, a PC (Personal Computer), or the like. A user uses the user terminal 100 in an office, home, or the like.

The registration unit 110 registers various information with the server 200 . The input unit 120 is an input device such as a keyboard. The display unit 130 is, for example, a display device such as a liquid crystal display or an organic EL display. The input unit 120 and the display unit 130 may be touch panels that allow the user to perform input by touching with a finger or the like. The communication unit 170 is a communication interface with the network N. FIG.

The user operates the user terminal 100 to register work schedule information regarding the user's work attendance. A predetermined attendance management application or the like may be used for registering the office attendance schedule information. The office attendance schedule information may include information indicating whether or not the user will work at a predetermined office attendance place. The predetermined office attendance place is, for example, inside a building or space managed by a corporation or the like. The predetermined office attendance place is, for example, an office of a corporation or the like, a factory, or the like.

In the following description, the working style of working at a predetermined office attendance place may be referred to as "work attendance". When the user goes to work, the user can use a company cafeteria provided at or near a predetermined work place. The employee cafeteria may be a restaurant or the like affiliated with the corporation.

Also, the user can work at a place other than the predetermined office attendance place. A user can work at home, a restaurant, a hotel, a coworking space, a telework space, or the like, for example. In the following description, a work pattern in which an employee works at a location other than a predetermined place of work may be referred to as "telecommuting". The user cannot use the company cafeteria when working from home.

The user uses the user terminal 100 to register in the server 200 a work schedule for a predetermined work schedule. A predetermined attendance management application or the like may be used in the registration process. The user terminal 100 registers in the server 200 whether the user will work at the office or work from home on the scheduled work day according to the user's operation.

In addition, the user registers his/her own work schedule, as well as the schedule of use of the cafeteria and the reservation menu from the user terminal 100 to the server 200 . Although the server 200 receives menu reservations in this embodiment, the present invention is not limited to this. A predetermined server for accepting and canceling menu reservations may be provided separately.

The office attendance schedule information registration process will be described with reference to FIG. FIG. 6 is a flowchart showing the office attendance schedule information registration process performed by the user terminal 100 . The user uses the user terminal 100 from home, office, or the like to perform a work schedule information registration process. The user operates the input unit 120 of the user terminal 100 while looking at the screen displayed on the display unit 130 via a predetermined application or the like, and inputs necessary information. Registration unit 110 receives input from the user and registers information in server 200 via communication unit 170 .

First, the registration unit 110 selects a scheduled working date for which information on a schedule of coming to work is to be registered, and registers working at the office or working from home as a working style in the server 200 (S101). The server 200 receives the registered information and stores it in the storage unit 290 of the server 200 as office attendance schedule information 291 .

The registration unit 110 determines whether or not the user's work style is work at the office (S102). If the work style is going to work (YES in S102), the registration unit 110 selects whether or not the user plans to use the cafeteria (S103).

If the user plans to use the cafeteria (YES in S103), the registration unit 110 selects whether or not to reserve the menu of the cafeteria (S104). When reserving a restaurant menu (YES in S104), the registration unit 110 registers the reserved menu in the server 200 (S105). The registration unit 110 may display, for example, a list of reservable menus on the display unit 130 and accept selection from the input unit 120 . The server 200 receives the registered information and stores it in the storage unit 290 as reservation information 292 .

If the work style is not going to the office (NO at S102), if the dining room is not planned to be used (NO at S103), or if the dining room menu is not reserved (NO at S104), the process ends.

By performing such registration processing, the server 200 can register the office attendance schedule information 291 and the reservation information 292 in the storage unit 290 in advance. Note that the server 200 may appropriately set a deadline for the user to register the schedule of coming to work and the reservation menu. For example, the server 200 may set the menu reservation time limit to 12:00 on the day before the scheduled date of coming to work, and may accept reservations up to that time.

FIG. 7 is a diagram showing an example of the office attendance schedule information 291. As shown in FIG. The office attendance schedule information 291 is information about the user's work schedule. As shown in FIG. 7, the office attendance schedule information 291 associates a user ID, a scheduled work day, and a work style 2911 with each other. A user ID is information for identifying a user. The user ID may be information such as an employee number, for example. Note that the user IDs correspond to user IDs used in various types of information described below. Therefore, in the prediction system 1000, user IDs can be used to associate and manage information about users. The scheduled work date is information indicating the scheduled work date. The work pattern 2911 indicates the work pattern on the scheduled working day.

FIG. 8 is a diagram showing an example of the reservation information 292. As shown in FIG. The reservation information 292 is information about the user's reservation menu. As shown in FIG. 8, the reservation information 292 is, for example, associated with a user ID, a scheduled work day, and a reservation menu 2922 . A user ID is information for identifying a user. The scheduled work date is information indicating the scheduled work date. The reserved menu 2922 is information indicating the menu reserved by the user.

For example, if the user plans to work from home, the user does not use the cafeteria, so the reservation menu is "none". The reservation menu 2922 is also "none" when the user is planning to come to work and does not plan to use the cafeteria. For example, this applies when the user eats out or eats at his/her own seat.

If the user is planning to come to work and has reserved a dining room menu, reservation menu 2922 includes information about the reservation menu. The information about the reservation menu is, for example, information for identifying the user's reservation menu. Information for identifying a menu may be, for example, a menu name such as "A lunch" or "B lunch".

The user is planning to come to work on a predetermined scheduled work day and is planning to use the cafeteria, but there is a case where the menu is not reserved. In this case, the reservation menu 2922 does not have to designate a specific menu. Specifically, the reservation menu 2922 may be information such as "undecided" as indicated by shading in FIG.

For example, user U5 registers that he is scheduled to come to work on December 1st and that he will use the cafeteria. However, user U5 has not registered the reservation menu. In such a case, the server 200 registers the reservation information 292 with the reservation menu 2922 set to "undecided".

Next, the POS terminal 300 will be described with reference to FIG. FIG. 4 is a block diagram showing the configuration of the POS terminal 300. As shown in FIG. The POS terminal 300 includes an authentication section 310 , accounting section 320 , communication section 370 and storage section 390 . The POS terminal 300 is an information processing device that is installed in the employee cafeteria and performs accounting processing for the menu ordered by the user. The POS terminal 300 is operated by, for example, restaurant staff who perform accounting processing. The POS terminal 300 may be a self-checkout counter where the user himself/herself performs checkout.

The authentication unit 310 performs user authentication processing. For example, the authentication unit 310 authenticates the user using the user's employee ID card or the like, and acquires a user ID that identifies the user. The user ID may be, for example, an employee number. The authentication unit 310 acquires the user ID by reading the employee number written on the employee ID card using, for example, a reader (not shown). Not limited to this, the authentication unit 310 may acquire a user ID using biometric authentication such as face authentication.

The accounting unit 320 performs accounting processing according to the contents of the user's order. For example, a cafeteria staff registers the order by inputting the user's order from a button, touch panel, or the like. The cafeteria staff informs the user of the price, and the user pays the price using cash, credit card, electronic money, or the like. The accounting method is not limited to these, and any method may be used. Accounting section 320 accepts payment and issues a receipt. This completes the accounting process. After completing the accounting process, the accounting unit 320 stores the order information regarding the order in the storage unit 390 as the order information 391 . The order information 391 is, for example, information in which an order date/time 3911, a user ID 3912, and an order menu 3913 are associated with each other.

Accounting section 320 transmits order information 391 to server 200 via communication section 370 . The accounting unit 320 may transmit the order information 391 at predetermined time intervals, or may transmit each time accounting processing is performed. Accounting section 320 may also transmit order information 391 in response to a request from server 200 .

A communication unit 370 is a communication interface with the network N. FIG. The storage unit 390 is a storage device that stores programs for realizing each function of the POS terminal 300 . The storage unit 390 also stores the order information 391 described above.

Next, the configuration of the server 200 will be explained. The server 200 is an example of the prediction device 20 of the first embodiment. The server 200 is an information processing device that communicates with the user terminal 100 and the POS terminal 300 and performs predetermined prediction processing.

The configuration of the server 200 will be described with reference to FIG. FIG. 5 is a block diagram showing the configuration of the server 200. As shown in FIG. The server 200 includes a work recording unit 205 , an office arrival schedule acquisition unit 210 , a reservation acquisition unit 220 , an order history acquisition unit 230 , a prediction unit 240 , an adjustment unit 250 , a communication unit 270 , and a storage unit 290 .

The work recording unit 205 stores information about work as a work history in the storage unit 290 when the user works at the office or works from home. The work recording unit 205 records the work history as work history information 293 in the storage unit 290 in association with the date information, user ID, and the like. The work recording unit 205 determines whether the work type is telecommuting or going to work, and records the respective work histories.

Processing when the user works from home will be described with reference to FIG. FIG. 9 is a flowchart showing recording processing performed by the work recording unit 205 when the user works from home.

The work recording unit 205 determines whether the user has logged into the user terminal 100 in order to determine whether the user has started working (S201). A well-known technique may be used to determine whether to log in to the user terminal 100 .

When it is determined that the user has logged in to the user terminal 100 (YES in S201), the work recording unit 205 records the work history information 293 with the user's work style as "working from home", and records the order history information related to restaurant menu orders. "None" is recorded in 294 (S202). The order history information 294 is information including a restaurant usage history 2941 and a usage menu 2942 . Details will be described later.

The processing when the user goes to work will be described with reference to FIG. 10 . FIG. 10 is a flowchart showing recording processing performed by the work recording unit 205 when the user goes to work.

The work recording unit 205 determines whether or not the user has passed through the gate (S301). A gate is provided at an entrance of an office or the like where a user goes to work, and is a device for restricting the entrance of the user. The gate opens and closes under the control of an admission control device that controls locking and unlocking of the gate. The entrance control device authenticates the user using, for example, the user's employee ID card or biometric information, unlocks the gate in response to successful authentication, opens the gate, and allows the user to pass through.

If the authentication succeeds, the server 200 receives a notification from the entrance control device and determines whether the user has passed through the gate. When it is determined that the user has passed through the gate (YES in S301), the work recording unit 205 sets the work style to "going to work" and records the work history of the user in the work history information 293 (S302). If it is determined that the vehicle has not passed through the gate (NO in S301), the process ends. The work recording unit 205 may constantly monitor whether or not the user passes through the gate. Also, as in a third embodiment described later, the user's body temperature may be measured together with the user's authentication.

The work recording unit 205 determines whether or not the user has used the cafeteria after entering the office (S303). Here, the work recording unit 205 refers to the order history information 294 acquired by the order history acquisition unit 230, which will be described later, to determine whether or not the user has used the cafeteria. The order history information 294 is information acquired from the POS terminal 300 . Without being limited to this, the work recording unit 205 may receive a report from the user as to whether or not the cafeteria is used, and make the determination. Further, for example, when user authentication and entrance control are performed at a gate provided at the entrance of a cafeteria, the work recording unit 205 may perform the determination based on the authentication result.

If it is determined that the user did not use the cafeteria (NO in S303), the process ends. When it is determined that the user has used the cafeteria (YES in S303), the work recording unit 205 acquires the order history information 294 regarding the menu ordered by the user from the POS terminal 300 (S304). The work recording unit 205 associates the order history information 294 with the work history information 293 and records them in the storage unit 290 (S305). By doing so, the server 200 can record the information of the menu used in the cafeteria by the user who came to work.

FIG. 11 is a diagram showing an example of the work history information 293. As shown in FIG. As shown in FIG. 11, the work history information 293 is, for example, information in which user IDs, work days, and work styles 2931 are associated with each other. A user ID is information for identifying a user. The working day is information indicating the date on which the worker worked. The work type 2931 indicates the work type on the working day.

FIG. 12 is a diagram showing an example of the order history information 294. As shown in FIG. Note that FIG. 12 also shows work history information 293 (working style 2931) for explanation. As shown in FIG. 12, the order history information 294 is, for example, information in which user IDs, working days, cafeteria usage history 2941, and usage menus 2942 are associated with each other.

The user ID and working days correspond to the user ID described above. The cafeteria usage history 2941 is information indicating whether or not the user has used the cafeteria. When the user works from home, the user does not use the cafeteria, so the cafeteria usage history 2941 is "none". Also, when the user goes to work, the cafeteria usage history 2941 is "yes" or "no".

The available menu 2942 is information indicating the menu ordered by the user at the cafeteria. A user may order a pre-registered reserved menu, or may order a desired menu by using a cafeteria without making a reservation. Note that the user may use a menu different from the reserved menu. Further, for example, when the user who used the cafeteria brought in a lunch box, the cafeteria usage history 2941 may be "yes" and the usage menu 2942 may be "no".

In this way, by storing the work history information 293 and the order history information 294 in association with each user in the storage unit 290, it is possible to manage the user's work history and the usage status of the cafeteria for each user. .

Returning to FIG. 5, the description is continued. The office attendance schedule acquisition unit 210 is an example of the office attendance schedule acquisition unit 21 of the first embodiment. The office attendance schedule acquisition unit 210 acquires the office attendance schedule information of the user from the result of the office attendance schedule information registration process described above, and stores the office attendance schedule information 291 in the storage unit 290 . The office attendance schedule acquisition unit 210 may acquire the office attendance schedule information of the user from any application that performs attendance management and schedule management.

The reservation acquisition unit 220 is an example of the reservation acquisition unit 22 of the first embodiment. The reservation acquisition unit 220 acquires reservation information related to the user's reservation menu from the result of the office attendance schedule information registration process described above, and stores the reservation information 292 in the storage unit 290 . The reservation acquisition unit 220 may acquire reservation information from a predetermined server that accepts and cancels menu reservations.

The order history acquisition unit 230 is an example of the order history acquisition unit 23 of the first embodiment. The order history acquisition unit 230 acquires the user's order history from the POS terminal 300 and stores the order history information 294 in the storage unit 290 . The order history acquisition unit 230 may acquire the order history from the POS terminal 300 at predetermined time intervals. For example, the order history acquisition unit 230 may acquire the order history of the current day from the POS terminal 300 after the cafeteria closes, or may acquire the order history every hour, for example. Also, the order history may be acquired for each accounting process at the POS terminal 300 .

The prediction unit 240 is an example of the prediction unit 24 of the first embodiment. The prediction unit 240 predicts the number of menu orders in the cafeteria based on the office attendance schedule information 291 , reservation information 292 , and order history information 294 . Based on the office attendance schedule information 291, the prediction unit 240 predicts the number of people at work on a prediction target day for which the number of orders is to be predicted. The prediction target date may be the current day or a predetermined future date. The prediction unit 240 may predict the number of orders at predetermined time intervals. The prediction unit 240 may predict the number of orders at a predetermined time every day.

Based on the reservation information 292, the prediction unit 240 acquires the number of users who have made menu reservations among the users who are scheduled to come to work on the prediction target day. The prediction unit 240 also acquires the number of reservations for each menu based on the reservation information 292 .

The prediction unit 240 estimates the menu to be ordered by the user who has not made a menu reservation among the users who are scheduled to come to work, based on the past record of use of the cafeteria. For example, the prediction unit 240 estimates the user's order menu based on the order history information 294 when the user who is scheduled to come to work has not reserved a menu.

As shown in FIG. 12, the server 200 stores, as the order history information 294, the menu ordered by the user on the day he/she came to work. The prediction unit 240 calculates the number of orders for each menu of the user obtained from the order history information 294, and estimates the menu ordered by the user based on the calculated number of orders.

For example, as shown in the examples of FIGS. 7 and 8, on December 1, user U5 is scheduled to come to work, and the reservation menu is "undecided." The prediction unit 240 refers to the order history information 294 and calculates the number of past orders of the user U5. If the user U5 has ordered "A lunch" the most in the past, the prediction unit 240 estimates that the menu item ordered by the user U5 on December 1st is "A lunch." The prediction unit 240 changes the reservation menu from “undecided” to “A lunch” and stores the change result in the storage unit 290 as order prediction information 296 .

FIG. 14 is a diagram showing an example of order prediction information 296. As shown in FIG. The order prediction information 296 is, for example, the user ID, the scheduled work date, and the estimated menu 2962 associated with each other. The user ID and scheduled work date are the same as the reservation information 292 shown in FIG.

For example, in FIG. 8, user U5's reservation menu 2922 on December 1st was "undecided." In FIG. 14, "A lunch" estimated according to the number of orders is shown as estimated menu 2962. In FIG. In this way, the prediction unit 240 can predict a menu item according to the user's order tendency by estimating the user's order menu item according to the past number of orders.

It should be noted that, for example, in the case where the menu with the most orders has been discontinued, the prediction unit 240 may estimate the menu with the second highest number of orders as the order menu. By the prediction unit 240 estimating the menu in descending order of the number of orders, the order menu can be estimated with high accuracy.

Alternatively, the prediction unit 240 may estimate the menu according to the category of the menu. For example, in the case of a user who frequently orders meat-based menus, the prediction unit 240 estimates the meat-based menu currently being served as the order menu. Thereby, even when the menu is changed, the prediction section 240 can estimate the order menu according to the user's preference. Not limited to this, the prediction unit 240 may estimate the order menu by taking into consideration the price range of the menu.

In addition, the prediction unit 240 may calculate the number of orders during a predetermined period in the past. For example, the prediction unit 240 calculates the number of orders by using the user's order history for the last year. Thereby, the prediction unit 240 can estimate a menu corresponding to changes in the user's preferences. Also, the prediction unit 240 may appropriately change the predetermined period for calculating the number of orders according to the season or the like. For example, when making a prediction for December 1st, the number of orders may be calculated using the user's order history from November to December one year ago. As a result, it is possible to estimate the order menu according to changes in season and temperature.

Also, the prediction unit 240 may estimate the order menu based on the order history information 294 of a plurality of users. For example, the prediction unit 240 refers to the order history information 294 and calculates the number of menu items ordered by a plurality of users who use the cafeteria. The prediction unit 240 may calculate the number of times limited to users who have used the cafeteria within a predetermined period (for example, one year).

FIG. 15 is a diagram showing an example of the order record information 297. As shown in FIG. The order record information 297 is obtained by totaling the order history information 294 of a plurality of users. The order record information 297 is, for example, information in which order menus, categories, order dates, and the number of orders are associated with each other.

The order menu is information indicating the menu ordered by the user. The menu names are shown here. A category is information indicating the classification of a menu. As an example, categories of "meat-based dishes", "fish-based dishes", and "noodles" are shown here. The category may indicate, for example, the genre of the menu, such as "Japanese style" and "Western style". The order date is information indicating the date when the user ordered the menu. Order time zone or order time may be used instead of date. The number of orders is information indicating the number of menu items ordered by users. FIG. 15 shows the number of orders for each menu on each order date and the total number of orders on each order date.

The prediction unit 240 refers to the order record information 297 and estimates the menu ordered by the user according to the number of orders for each menu. For example, the prediction unit 240 estimates the menu ordered the most by the user as the menu ordered by the user. The menu with the largest number of orders is assumed to be popular among multiple users. In this way, by identifying a popular menu and estimating it as the user's order menu, the prediction unit 240 can accurately estimate the order menu. This also prevents popular menu items from running out of ingredients. Note that the prediction unit 240 may calculate the number of orders for each attribute of the user, such as gender and age. Thereby, the prediction unit 240 can estimate the user's order menu based on the tendency of orders in the user group with closer attributes.

In addition, the prediction unit 240 calculates the number of people scheduled to come to work on the prediction target day, calculates the total number of people whose reservation menu is “undecided” among the number of people scheduled to come to work, and uses a predetermined ratio to You may guess the menu. For example, assume that the number of people scheduled to come to work is 100. Assume that there are 30 users among them who plan to use the cafeteria and whose reservation menu is "undecided". For example, if there are menus a, b, and c in descending order of popularity, the prediction unit 240 may estimate that 15, 10, and 5 users will order menus a, b, and c, respectively.

As described above, the prediction unit 240 estimates an order menu for a user scheduled to come to work whose order menu is “undecided”. Thereby, the prediction unit 240 can identify a menu that is highly likely to be ordered based on the order history of the user, the popularity of the menu, and the like. The prediction unit 240 performs similar estimation for all users scheduled to come to work on the prediction target day, and uses the estimation results to predict the total number of menu orders. Thereby, the prediction unit 240 can appropriately predict the number of orders for the menu.

Now, with reference to FIG. 13, the order quantity prediction processing will be described. FIG. 13 is a flowchart showing the process of predicting the number of menu orders, which is performed by the prediction unit 240 . It is assumed that the server 200 stores the user's work history for a predetermined period and the menu order history for the day the user came to work. In addition, it is assumed that the user has previously registered office attendance information and reservation information for the prediction target date. Therefore, the server 200 stores in the storage unit 290 in advance the office attendance schedule information 291 , reservation information 292 , work history information 293 , and order history information 294 .

The prediction unit 240 refers to the office attendance schedule information 291 and determines whether or not the user is scheduled to come to work (S401). When it is determined that the user does not plan to come to work (NO in S401), the prediction unit 240 predicts that there will be no order (S407).

When determining that the user is scheduled to come to work (YES in S401), the prediction unit 240 refers to the reservation information 292 and determines whether or not a reservation menu is registered (S402). When determining that the reserved menu is registered (YES in S402), the prediction unit 240 estimates that the user will order the reserved menu (S403).

If it is determined in step S402 that the reserved menu is not registered (NO in S402), the prediction unit 240 determines whether or not the reserved menu is "undecided" (S404). If it is not "undecided" (NO in S404), the user is planning to come to work, but has registered that he or she will not use the cafeteria. Therefore, in this case, the prediction unit 240 estimates that the user will not place an order (S407).

If the reservation menu is "undecided" (YES in S404), the prediction unit 240 refers to the dining room usage history 2941 of the order history information 294 and determines whether or not the user has used the dining room in the past (S405). ). The prediction unit 240 may refer to the restaurant usage history 2941 for a predetermined period (for example, within one year).

If the user has not used the cafeteria in the past (NO in S405), the prediction unit 240 estimates that the user will not place an order (S407). If the user has used the cafeteria in the past (YES in S405), the prediction unit 240 estimates the order menu from past trends (S406).

Specifically, the prediction unit 240 refers to the order history information 294 and calculates the number of orders by the user for each menu. The prediction unit 240 estimates a user's order menu according to the number of orders. For example, the prediction unit 240 estimates the menu ordered most frequently in the past year as the ordered menu. Also, the prediction unit 240 may calculate the number of orders placed by a plurality of users and estimate the most popular menu as the ordered menu. Since the estimation of the menu has already been explained, the detailed explanation is omitted here. The prediction unit 240 stores order prediction information 296 based on the estimation result.

Through the processing described above, the prediction unit 240 estimates the user's order menu on the prediction target date. The prediction unit 240 determines whether or not the estimation of the order menu has been completed for all users on the prediction target date (S408). If the estimation of order menus has not been completed for all users (NO in S408), the process returns to step S401 and the subsequent processes are continued. When the estimation of order menus for all users has been completed (YES in S408), the total number of orders for each menu is predicted based on the estimation results (S409). Specifically, the prediction unit 240 calculates the total number of each menu on the assumption that the estimated menu will be ordered on the prediction target date.

Note that the prediction unit 240 may predict the number of orders every day, or may collectively predict the number of orders for a predetermined period (for example, one week). The prediction unit 240 may perform ordering processing for materials based on the order prediction information 296 .

FIG. 16 is a diagram showing an example of the material table information 298. As shown in FIG. The ingredient table information 298 is information indicating the ingredients and their amounts required for each menu. The material list information 298 is, for example, a menu, category, material, and quantity associated with each other. Menus and categories are similar to those described above. Ingredients and quantities indicate the names of ingredients required for each menu and their quantities.

The prediction unit 240 refers to the ingredients table information 298 and calculates the ingredients and the quantities corresponding to the predicted number of orders for each menu. The prediction unit 240 orders necessary materials using telephone, FAX, e-mail, or a predetermined application. The prediction unit 240 may predict the number of orders every day and use the prediction results for the daily material ordering process. The prediction unit 240 may also use daily prediction results for ordering materials within a predetermined period. The predetermined period may be arbitrarily set, for example, one week, one month, or the like.

Returning to FIG. 5, the description is continued. The adjustment unit 250 adjusts user admission so that the number of users in the cafeteria is less than a predetermined number. For example, the adjustment unit 250 refers to the reservation information 292 and calculates the number of people expected to use the cafeteria on a predetermined prediction target date. The adjustment unit 250 predicts the number of users in the cafeteria based on the expected number of users. For example, the adjustment unit 250 predicts the number of users entering the cafeteria using information such as the opening hours of the cafeteria, break times, and the average length of stay of users. When the adjustment unit 250 predicts that the number of users in the cafeteria will exceed a predetermined number, it adjusts the entry of users so that the number of users in the cafeteria is less than the predetermined number.

For example, the adjustment unit 250 sets the usage start time and notifies the user of the set usage start time. The adjustment unit 250 sets the use start time, for example, in order of menu reservation. In this case, an early utilization start time is set for a user who made an early menu reservation. Further, the adjustment unit 250 may receive a reservation for the use start time from the user and set the use start time. In this case, the adjustment unit 250 adjusts the number of users in the cafeteria to a predetermined number or more for the time period when many requests for the use start time are made. By doing so, it is possible to restrict the entry of users into the cafeteria, thereby avoiding congestion in the cafeteria. This leads to prevention of the spread of infectious diseases, for example.

Note that the adjustment unit 250 may perform adjustment and notification on the day of use, or may perform the adjustment and notification on or before the day before use. Further, the adjusting section 250 may adjust the number of people for each menu. As a result, it is possible to prevent the concentration of orders for a specific menu in a short period of time, thereby avoiding congestion. Note that the server 200 may set and notify the usage start time even to users who have not made menu reservations or the like.

A communication unit 270 is a communication interface with the network N. FIG. The storage unit 290 is a storage device in which programs for realizing each function of the server 200 are stored. The storage unit 290 stores the various information described above. Specifically, the storage unit 290 stores user information 290A about the user's work and use of the cafeteria, and cafeteria information 290B about the cafeteria. The user information 290A includes office attendance schedule information 291 , reservation information 292 , work history information 293 , and order history information 294 . The cafeteria information 290B includes order forecast information 296, order record information 297, and bill of materials information 298. FIG.

Next, processing of the prediction system 1000 will be described with reference to FIG. 17 . FIG. 17 is a sequence diagram showing processing of the prediction system 1000. As shown in FIG.

The user terminal 100 registers office attendance schedule information according to the user's operation (S1001). The server 200 acquires the office attendance schedule information from the user terminal 100 and stores it as the office attendance schedule information 291 (S1002). The server 200 predicts the number of people who come to work each day (S1003). The user terminal 100 registers the reservation menu in the server 200 (S1004). The server 200 receives registration of a reservation menu from the user terminal 100 and stores it as reservation information 292 in the storage unit 290 .

The server 200 notifies the user who is at work and who has a menu reservation of the cafeteria usage time (S1005). The server 200, for example, sets a use start time for each user and notifies the time. When the user arrives at the office and uses the cafeteria, the user performs accounting processing at the POS terminal 300 (S1006). After the transaction processing, the POS terminal 300 associates information such as the user ID, date and time information, usage menu, etc., and transmits it to the server 200 (S1007). Server 200 stores the received information as order history information 294 .

When predicting the number of orders for the prediction target date, the server 200 refers to the reservation information 292 and acquires the number of reservations for each menu (S1008). If the user scheduled to come to work has not reserved a menu, the server 200 estimates the user's order menu based on the order history information 294, and predicts the number of orders based on the estimation result (S1009). By doing so, the server 200 can place an order for materials based on the prediction result.

As described above, in the prediction system 1000 according to this embodiment, the server 200 performs predetermined prediction processing to predict the number of menu orders. In the server 200, the office attendance schedule acquisition unit 210 acquires office attendance schedule information of the user. The reservation acquisition unit 220 acquires reservation information regarding a user's reservation menu. The order history acquisition unit 230 acquires the order history information of the user.

The prediction unit 240 predicts the number of menu orders in the cafeteria based on the office attendance schedule information, reservation information, and order history information. The prediction unit 240 estimates the user's order menu based on the order history information and predicts the number of orders based on the estimation result when the user who is scheduled to come to work has not reserved a menu. The prediction unit 240 can estimate the order menu based on the number of times the user has ordered for each menu obtained from the order history information. The prediction unit 240 can also estimate an order menu based on order history information of multiple users.

With such a configuration, the prediction system 1000 according to this embodiment can appropriately predict the number of menu orders in the cafeteria. Therefore, food loss can be reduced by linking the user's work schedule with the dining room reservation system.

Moreover, the server 200 can further include an adjustment unit that adjusts the user entry time so that the number of users in the cafeteria is equal to or less than a predetermined value. This makes it possible to avoid crowding of users in the cafeteria.

Note that the configurations shown in FIGS. 2 to 5 are merely examples, and the prediction system 1000 may be configured using a device or the like in which multiple configurations are aggregated. For example, the server 200, the user terminal 100, and the POS terminal 300 may be partly integrated into the same device. Further, for example, each functional unit in the server 200 or the like may perform distributed processing using a plurality of devices or the like.

<Embodiment 3>
Next, Embodiment 3 will be described. In the prediction system 1000 described in the second embodiment, this embodiment further acquires the physical condition information of the user and predicts the number of orders by adding the physical condition information. In the following description, descriptions of portions that overlap with the second embodiment will be omitted as appropriate, and description will focus on portions that differ from the second embodiment.

FIG. 18 is a block diagram showing the configuration of a prediction system 1000a according to this embodiment. A prediction system 1000 a according to this embodiment includes a user terminal 100 , a server 200 a, a POS terminal 300 and a detection device 400 . Each component included in the prediction system 1000a is connected via a network N so as to be communicable. The network N is a wired or wireless communication line. The configuration shown in FIG. 18 is an example, and a plurality of user terminals 100 and POS terminals 300 communicating with the server 200a may be provided.

A prediction system 1000a includes a detection device 400 in addition to the configuration of the second embodiment. The detection device 400 is a sensor that detects physical condition information regarding the physical condition of the user. The physical condition information is, for example, the user's body temperature, blood pressure, heart rate, or blood oxygen level. The physical condition information is not limited to these, and may include various information regarding the user's physical condition. The physical condition information may include subjective symptoms of the user. Here, a case where the physical condition information is the body temperature of the user will be described.

The detection device 400 detects the physical condition information of the user when the user arrives at the office or the like. For example, the detection device 400 is provided near a gate, takes a picture of the user when the user passes through the gate, and measures the body temperature of the user based on the taken image. The detecting device 400 transmits body temperature information indicating the measured body temperature to the server 200a.

The configuration of the server 200a will be described with reference to FIG. FIG. 19 is a block diagram showing the configuration of the server 200a. The server 200a corresponds to the server 200 of the second embodiment. In the server 200a, in addition to the configuration of the server 200 shown in FIG. 5, the work recording unit 205a has a function as a physical condition information acquisition unit that acquires physical condition information of the user.

When the user works, the work recording unit 205a stores information about work in the storage unit 290 as a work history. Further, when the user comes to work at an office or the like, the work recording unit 205 a acquires physical condition information from the detection device 400 and records it in the storage unit 290 as physical condition information 295 .

The processing when the user goes to work will be described with reference to FIG. 20 . FIG. 20 is a flowchart showing recording processing performed by the work recording unit 205a when the user goes to work.

Steps S1301 and S1302 are the same as steps S301 and S302 shown in FIG. 10, so description thereof is omitted. The work recording unit 205a records the body temperature measured by the detecting device 400 in the storage unit 290 as the physical condition information 295 in association with the user ID (S1302a). Since steps S1303 to S1305 are the same as steps S303 to S305 shown in FIG. 10, description thereof is omitted.

FIG. 21 is a diagram showing an example of physical condition information 295 and order history information 294. As shown in FIG. Note that FIG. 21 also shows work history information 293 (working style 2931) for explanation. As shown in FIG. 21, work history information 293 and order history information 294 are associated with body temperature measurement results as physical condition information 295 . Since other contents are the same as the order history information 294 shown in FIG. 12, detailed description thereof will be omitted.

Returning to FIG. 19, the description continues. Further based on the physical condition information 295, the prediction unit 240a predicts the number of orders for the menu. For example, when the body temperature of the user who has come to work is equal to or higher than a predetermined value (for example, 37.5° C.), the prediction unit 240a determines that the user tends to have a fever. The prediction unit 240a changes the office attendance schedule information 291 of the user within a predetermined period (for example, two weeks) from the day when it is determined that the user has a fever tendency. If the working style is "work at the office", the prediction unit 240a changes it to "work at home". When the prediction unit 240a determines that the user has a fever, the prediction unit 240a estimates the number of orders by estimating that there is no order from the user for a predetermined period.

For example, in the example of FIG. 21, user U1 has a body temperature of 37.5° C. measured on November 3rd, when he went to work. In this case, the prediction unit 240a changes the work style to work from home within two weeks from November 3, even if user U1 has registered that he/she will work at the office after November 3rd. Also, the prediction unit 240a estimates that there is no order for the user U1 during the period even if the user U1 has registered a reservation menu during the period. By doing so, the prediction unit 240a can predict the number of menu orders according to the user's physical condition information.

Order quantity prediction processing according to the present embodiment will be described with reference to FIG. FIG. 22 is a flowchart showing a process of predicting the number of menu orders, which is performed by the prediction unit 240a.

Steps S1401 to S1405 are the same as steps S401 to S405 shown in FIG. 13, so description thereof will be omitted. If the user has used the cafeteria in the past (YES in S1405), the prediction unit 240a determines whether the user tends to have a fever (S1405a).

If it is determined that there is a tendency to have a fever (YES in S1405a), the prediction unit 240a changes the work style to "work from home" within a predetermined period from the day on which it is determined that there is a tendency to have a fever. The prediction unit 240a estimates that there will be no user orders during this period (S1407). If it is determined that there is no heat generation tendency (NO in S1405a), the process proceeds to step S1406.

Steps S1406 to S1409 are the same as steps S406 to S409 shown in FIG. 13, so description thereof will be omitted. Note that the order of processing executed by the prediction unit 240a is not limited to that shown in FIG. For example, it may be determined whether or not the user has a tendency to overheat (S1405a) before step S1405.

Next, processing of the prediction system 1000a will be described with reference to FIG. FIG. 23 is a sequence diagram showing processing of the prediction system 1000a.

First, the user passes through a gate (S2000a). Detecting device 400 measures the body temperature of the user when passing through the gate, and registers the measurement result in server 200 (S2000b).
The server 200 stores the measurement result as the physical condition information 295 in the storage unit 290 in association with the work history information 293 . Steps S2001 to S2009 are the same as steps S1001 to S1009 shown in FIG. 17, so description thereof will be omitted.

The prediction unit 240a re-predicts the number of orders when there is a user whose body temperature is equal to or higher than the predetermined value (S2009a). For example, the prediction unit 240a predicts the number of orders assuming that there is no order for the user by canceling the reservation menu of the user or subtracting the number of orders according to the number of users. In addition, the prediction unit 240a estimates that the user who tends to have a fever does not have a reservation order not only on the day when it is determined that he/she has a fever, but also within a predetermined period from that day. As a result, the prediction unit 240a can appropriately predict the number of orders for each menu even when the user cannot come to work for a period of time due to an infectious disease or the like.

As explained above, according to the prediction system 1000a according to the present embodiment, the same effects as those of the second embodiment can be obtained. In addition, since the server 200a estimates the order menu by taking into account the physical condition information of the user, it is possible to more accurately predict the number of orders for each menu.

Note that the configurations shown in FIGS. 18 and 19 are merely examples, and the prediction system 1000a may be configured using a device or the like in which multiple configurations are aggregated. For example, the server 200a, the user terminal 100, the POS terminal 300, and the detection device 400 may be partly integrated into the same device. Further, for example, each functional unit in the server 200a or the like may perform distributed processing using a plurality of devices or the like.

<Hardware configuration example>
Each functional configuration unit of the server 200, the server 200a, the user terminal 100, the POS terminal 300, and the detection device 400 may be implemented by hardware (eg, hardwired electronic circuit, etc.) that implements each functional configuration unit. Alternatively, it may be realized by a combination of hardware and software (for example, a combination of an electronic circuit and a program for controlling it). A case will be described below in which each functional configuration unit such as the server 200 is implemented by a combination of hardware and software.

FIG. 24 is a block diagram illustrating the hardware configuration of a computer 900 that implements the server 200 and the like. Computer 900 may be a dedicated computer designed to implement server 200 or the like, or may be a general-purpose computer. The computer 900 may be a portable computer such as a smart phone or a tablet terminal.

For example, by installing a predetermined application on the computer 900, the computer 900 implements each function of the server 200 and the like. The application is configured by a program for realizing the functional components of the server 200 and the like.

Computer 900 has a bus 902 , processor 904 , memory 906 , storage device 908 , input/output interface 910 and network interface 912 . A bus 902 is a data transmission path for the processor 904, memory 906, storage device 908, input/output interface 910, and network interface 912 to transmit and receive data to and from each other. However, the method of connecting the processors 904 and the like to each other is not limited to bus connection.

The processor 904 is various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array). The memory 906 is a main memory implemented using a RAM (Random Access Memory) or the like. The storage device 908 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like.

The input/output interface 910 is an interface for connecting the computer 900 and input/output devices. For example, the input/output interface 910 is connected to an input device such as a keyboard and an output device such as a display device.

A network interface 912 is an interface for connecting the computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

The storage device 908 stores a program that implements each functional component of the server 200 or the like (a program that implements the application described above). The processor 904 implements each functional component of the server 200 and the like by reading this program into the memory 906 and executing it.

Each of the processors executes one or more programs containing instructions for causing the computer to perform the algorithms described with the drawings. This program includes instructions (or software code) that, when read into a computer, cause the computer to perform one or more of the functions described in the embodiments. The program may be stored on various types of non-transitory computer readable medium or tangible storage medium. By way of example, and not limitation, computer readable media or tangible storage media may include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drives (SSD) or other memory technology, CDs -ROM, digital versatile disc (DVD), Blu-ray disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disc storage or other magnetic storage device. The program may be transmitted over various types of transitory computer readable medium or communication medium. By way of example, and not limitation, transitory computer readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

It should be noted that the present disclosure is not limited to the above embodiments, and can be modified as appropriate without departing from the spirit of the present disclosure.

Some or all of the above-described embodiments can also be described in the following supplementary remarks, but are not limited to the following.
(Appendix A1)
a work schedule acquisition unit that acquires work schedule information of a user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
The prediction unit estimates the order menu of the user based on the order history information and predicts the number of orders based on the estimation result when the user scheduled to come to work has not reserved a menu.
(Appendix A2)
The prediction device according to appendix A1, wherein the prediction unit estimates the order menu based on the number of orders for each menu of the user obtained from the order history information.
(Appendix A3)
The prediction device according to appendix A1 or A2, further comprising an adjusting unit that adjusts admission of the users so that the number of users in the cafeteria is less than a predetermined number.
(Appendix A4)
further comprising a physical condition information acquisition unit that acquires physical condition information related to the physical condition of the user;
The prediction device according to any one of Appendices A1 to A3, wherein the prediction unit predicts the number of orders further based on the physical condition information.
(Appendix A5)
the physical condition information includes body temperature information of the user;
The prediction device according to Appendix A4, wherein, when the user's body temperature is equal to or higher than a predetermined value, the prediction unit predicts the number of orders on the assumption that there is no order from the user for a predetermined period.
(Appendix A6)
The prediction device according to any one of Appendices A1 to A5, wherein the prediction unit estimates the order menu based on the order history information of the plurality of users.
(Appendix B1)
a POS terminal that stores user order history information in the cafeteria;
a prediction device;
The prediction device is
a work schedule acquisition unit that acquires work schedule information of the user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user from the POS terminal;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
A prediction system in which the prediction unit estimates an order menu for the user based on the order history information and predicts the number of orders based on the estimation result when the user scheduled to come to work has not made a menu reservation.
(Appendix B2)
The prediction system according to appendix B1, wherein the prediction unit estimates the order menu based on the number of orders for each menu of the user obtained from the order history information.
(Appendix C1)
a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
a prediction step of predicting the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result.
(Appendix C2)
The prediction method according to appendix C1, wherein, in the prediction step, the order menu is estimated based on the number of orders for each menu of the user obtained from the order history information.
(Appendix D1)
Acquiring the user's attendance schedule information in the prediction device,
obtaining, in the prediction device, reservation information about the user's reservation menu;
storing order history information of the user at the POS terminal;
obtaining the order history information of the user from the POS terminal in the prediction device;
predicting the number of orders for a menu in a cafeteria in the prediction device based on the information on the schedule to come to work, the reservation information, and the order history information;
In the prediction of the number of orders, if the user who is scheduled to come to work has not reserved a menu, the order menu of the user is estimated based on the order history information, and the number of orders is predicted based on the estimation result. Prediction method .
(Appendix D2)
The prediction method according to appendix D1, wherein in the prediction of the number of orders, the order menu is estimated based on the number of orders for each menu of the user obtained from the order history information.
(Appendix E1)
a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
causing a computer to execute a prediction step of predicting the number of menu orders in a cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user who is scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result.
(Appendix E2)
The program according to appendix E1, wherein, in the prediction step, the order menu is estimated based on the number of orders for each menu of the user obtained from the order history information.

20 prediction device 21 work schedule acquisition unit 22 reservation acquisition unit 23 order history acquisition unit 24 prediction unit 100, 100a user terminal 110 registration unit 120 input unit 130 display unit 170 communication unit 200, 200a server (prediction device)
205, 205a Work recording unit 210 Work schedule acquisition unit 220 Reservation acquisition unit 230 Order history acquisition unit 240, 240a Prediction unit 250 Adjustment unit 270 Communication unit 290 Storage unit 290A User information 290B Restaurant information 291 Work schedule information 292 Reservation information 2922 Reservation menu 293 Work history information 294 Order history information 2941 Cafeteria usage history 2942 Use menu 295 Physical condition information 296 Order forecast information 2962 Estimated menu 297 Order record information 298 Material list information 300 POS terminal 310 Authentication unit 320 Accounting unit 370 Communication unit 390 Storage unit 391 Order Information 3911 Order date and time 3912 User ID
3913 order menu 400 detector 900 computer 902 bus 904 processor 906 memory 908 storage device 910 input/output interface 912 network interface 1000, 1000a prediction system N network

Claims (10)

a work schedule acquisition unit that acquires work schedule information of a user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
The prediction unit estimates the order menu of the user based on the order history information and predicts the number of orders based on the estimation result when the user scheduled to come to work has not reserved a menu. The prediction device according to claim 1, wherein the prediction unit estimates the order menu based on the number of orders for each menu of the user obtained from the order history information. 3. The prediction device according to claim 1, further comprising an adjustment unit that adjusts the admission of the users so that the number of users in the cafeteria is less than a predetermined number. further comprising a physical condition information acquisition unit that acquires physical condition information related to the physical condition of the user;
The prediction device according to any one of claims 1 to 3, wherein the prediction unit predicts the number of orders further based on the physical condition information. the physical condition information includes body temperature information of the user;
The prediction device according to claim 4, wherein when the user's body temperature is equal to or higher than a predetermined value, the prediction unit predicts the number of orders assuming that there is no order from the user for a predetermined period. The prediction device according to any one of claims 1 to 5, wherein the prediction unit estimates the order menu based on the order history information of the plurality of users. a POS terminal that stores user order history information in the cafeteria;
a prediction device;
The prediction device is
a work schedule acquisition unit that acquires work schedule information of the user;
a reservation acquisition unit that acquires reservation information about the user's reservation menu;
an order history acquisition unit that acquires order history information of the user from the POS terminal;
a prediction unit that predicts the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
A prediction system in which the prediction unit estimates an order menu for the user based on the order history information and predicts the number of orders based on the estimation result when the user scheduled to come to work has not made a menu reservation. The prediction system according to claim 7, wherein the prediction unit estimates the order menu based on the number of orders for each menu of the user obtained from the order history information. a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
a prediction step of predicting the number of menu orders in the cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result. a work schedule acquisition step for acquiring work schedule information of the user;
a reservation obtaining step of obtaining reservation information about the user's reservation menu;
an order history acquisition step of acquiring order history information of the user;
causing a computer to execute a prediction step of predicting the number of menu orders in a cafeteria based on the work schedule information, the reservation information, and the order history information;
In the prediction step, if the user who is scheduled to come to work has not made a menu reservation, the user's order menu is estimated based on the order history information, and the number of orders is predicted based on the estimation result.

Images