Store support method, information processing device, program, and store system

Abstract

A data processing device (100) is provided with: a user data storage unit (115) that stores use data relating to the use of a restaurant store by a user in association with a user identifier that identifies the user; a usage data acquisition unit (151) that acquires usage data of the user from the user data storage unit (115); a prediction unit (153) that acquires, on the basis of the use data, prediction data including a prediction result of the user's next consumption behavior; and a prediction data output unit 155 that outputs the prediction data. The data processing apparatus (100) may predict the next consumption behavior of the user using the restaurant store based on the usage data.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202480028899.X (22) Application Date 2024.05.14 (30) Priority Data 2023-113614 2023.07.11 JP (85) PCT International Application Entering National Phase Date 2025.10.28 (86) PCT International Application Application Data PCT / JP2024 / 017748 2024.05.14 (87) PCT International Application Publication Data WO2025 / 013400 JA 2025.01.16 (71) Applicant: Kura Sushi Co., Ltd. Address: 1-2-2 Fukasaka, Naka-ku, Sakai City, Osaka Prefecture, Japan (72) Inventor: Kunihiko Tanaka (74) Patent Agency: Shanghai Bixing Law Firm 31283 Patent Attorney Gao Xiaoli (51) Int.Cl. G06Q 30 / 01 (2006.01) G06Q 50 / 12 (2006.01) (54) Invention Title: Shop Support Method, Data Processing Apparatus, Program and Shop System (57) Abstract: A data processing apparatus 100 includes: a user data storage unit 115, which stores usage data related to a user's use of a restaurant shop in correspondence with a user identifier that identifies the user; a usage data acquisition unit 151, which acquires the user's usage data from the user data storage unit 115; a prediction unit 153, which acquires prediction data including a prediction result of the user's next consumption behavior based on the usage data; and a prediction data output unit 155, which outputs the prediction data. The data processing apparatus 100 can predict the next consumption behavior of a user who uses a restaurant shop based on the usage data.Claims 3 pages, Description 24 pages, Drawings 13 pages, CN 121039688 A 2025.11.28 CN 1 21 03 96 88 A 1. A store support method, implemented by a processor of a data processing device installed in a restaurant store, characterized in that: usage data is stored in a user data storage unit corresponding to a user identifier that identifies the user; the usage data is usage data related to the user's use of the store, including past usage data related to the user's consumption behavior in the past; based on the usage data obtained from the user data storage unit, prediction data including prediction results of the consumption behavior of users visiting the store is obtained; store status data indicating the busyness of the store is obtained at least based on the number of users in the store; based on the prediction data obtained for users visiting the store and the store status data, seat guidance data for guiding the users to reserved seats in the store is obtained as support data that can be used for the operation of the store; and the seat guidance data is output to a notification device used to guide users visiting the store to the reserved seats. 2. The store support method as claimed in claim 1, characterized in that, the seating guidance data is acquired to disperse the positions of users dining in the store after a predetermined time. 3. The store support method as claimed in claim 1 or 2, characterized in that, the restaurant has two or more seating groups, each consisting of two or more seats in the store, and the seating guidance data is acquired to make each seat in the identified seating group vacant after a predetermined time. 4. The store support method as claimed in any one of claims 1-3, characterized in that, the restaurant has two or more seating groups, each consisting of two or more seats in the store, and the seating guidance data is also acquired based on load data related to the store's operational load, and the load data is acquired based on at least one of the following: the quantity of goods ordered for each seating group, the ordering frequency, the future utilization rate of each seat in each seating group, and the number of events requiring staff intervention. 5. The store support method as claimed in claim 4, wherein, when there are two or more seating groups as the destination for guiding users visiting the store, a load score representing the load assuming that the user has been guided to each seating group is obtained as the load data, and the seating guidance data is obtained to guide the user visiting the store to the seating group with the lowest score.6. The store support method as claimed in claim 5, wherein the notification device includes a staff notification device for notifying the store staff, and outputs the score to the staff notification device so that the staff notification device notifies the staff of the score in association with the corresponding seating group. 7. A data processing apparatus, comprising: a user data storage unit that stores usage data corresponding to user identifiers identifying users, the usage data being usage data related to the user's use of a restaurant, including past usage data related to the user's past consumption behavior; a prediction unit that, based on the usage data obtained from the user data storage unit, obtains prediction data including prediction results of the user's next consumption behavior; a store status data acquisition unit that acquires store status data related to the status within a store; a support data acquisition unit that, based on the prediction data obtained by the prediction unit for users visiting the store, acquires support data usable for the operation of the store; and a support data output unit that outputs the support data. 8. The data processing apparatus of claim 7, characterized in that it comprises: a consumption data acquisition unit, which acquires consumption data related to the current consumption behavior of a user visiting a store, and stores the acquired consumption data as past usage data corresponding to a user identifier identifying the user in the user data storage unit. 9. The data processing apparatus of claim 7 or 8, characterized in that the usage data includes next usage data input by a user planning to use the store, related to a planned next use. 10. The data processing apparatus of any one of claims 7-9, characterized in that the prediction unit acquires prediction data including a prediction result of the user's next consumption behavior based on the usage data of one user in a group comprising two or more users and headcount data related to the number of users comprising the group. 11. The data processing apparatus of any one of claims 7-10, characterized in that the prediction unit acquires prediction data including a prediction result of the group's next consumption behavior based on the usage data, wherein the usage data is the usage data of each user in a group comprising two or more users, including group data related to the group containing users who have previously used the store and past usage data related to the consumption behavior of the group. 12. The data processing apparatus according to any one of claims 7-11, characterized in that it comprises: a seat data acquisition unit that acquires seat data, including data identifying the seats used by users visiting the store, and stores the acquired seat data in a user data storage unit corresponding to a user identifier identifying the user.13. The data processing apparatus according to any one of claims 7-12, characterized in that it comprises: an object behavior data acquisition unit, which acquires object behavior data related to the current behavior of a user visiting a store, which is different from a predetermined recorded object behavior, and stores the acquired object behavior data as usage data corresponding to a user identifier identifying the user in the user data storage unit. 14. The data processing apparatus according to any one of claims 7-13, characterized in that the prediction unit is configured to acquire prediction data including a prediction result of the user's future consumption behavior in the current usage opportunity, based on the usage data related to the user's consumption behavior in past usage opportunities and the usage data related to the user's past consumption behavior in the current usage opportunity. 15. The data processing apparatus according to any one of claims 7-14, characterized in that, the restaurant has two or more seating groups, each seating group consisting of two or more seats within the restaurant, the support data acquisition unit acquires load data related to the operational load of each seating group based on the prediction data acquired by the prediction unit for users visiting the restaurant and the restaurant status data, and acquires the support data based on the load data. 16. The data processing apparatus according to any one of claims 7-15, characterized in that, the support data acquisition unit acquires seating guidance data related to the seats used to guide users visiting the restaurant, as described in claim 2 / 3 page 3 CN 121039688 A, as the support data. 17. The data processing apparatus according to claim 16, characterized in that, the support data output unit outputs data representing the number of people in a group containing the users, through a device corresponding to the output destination of the seats used to guide users visiting the restaurant. 18. The data processing apparatus according to any one of claims 7-17, characterized in that it comprises: a future situation data acquisition unit that acquires future situation data relating to the future situation in the store using the predicted data acquired for users currently using a store and the predicted data acquired for users in the future using the store; and a future data output unit that outputs the future situation data in a manner that can be confirmed by staff.19. A program characterized in that a processor of a computer capable of accessing a user data storage unit performs the following operations, wherein the user data storage unit stores usage data corresponding to a user identifier that identifies the user, the usage data being usage data related to the user's use of a restaurant, including past usage data related to the user's consumption behavior during past use, wherein the operations are as follows: obtaining the user's usage data from the user data storage unit; obtaining prediction data based on the usage data, including prediction results of the user's next consumption behavior; and outputting the prediction data. 20. A store system, characterized in that it comprises: a data processing device; a notification device for notifying store staff; at least one processor; and at least one memory for recording computer program code, wherein: by executing the computer program code, the at least one processor causes the data processing device to perform the following operations: storing usage data corresponding to user identifiers identifying users in a user data storage unit, the usage data being usage data related to the user's use of the restaurant store, including past usage data related to the user's consumption behavior during past use; based on the usage data obtained from the user data storage unit, obtaining prediction data including prediction results of the consumption behavior of users visiting the store; obtaining store status data indicating the store's busyness based at least on the number of users in the store; based on the prediction data obtained for users visiting the store and the store status data, obtaining seating guidance data for guiding the users to reserved seats in the store as support data usable for the store's operation; outputting the seating guidance data to the notification device, and causing the notification device to perform the following operations: when the seating guidance data is input, notifying the staff to guide the users visiting the store to the reserved seats. Claims 3 / 3 Page 4 CN 121039688 A Store Support Method, Data Processing Apparatus, Program and Store System Technical Field

[0001] The present invention relates to a store support method, data processing apparatus, program and store system that can be used in a restaurant. Background Art

[0002] Patent Document 1 below describes a food delivery device used in a restaurant that stores food data ordered by a customer in association with the customer's personal data, and then displays the food data associated with the customer in the kitchen when the customer is dining.

[0003] Patent Document 2 below describes an electronic ordering system, including: an order input device that allows customers to easily and reliably order, reducing the restaurant's labor costs, by having customers input the ordered items; and an order output device that outputs the customer's ordered items sent from the order input device.In the system, orders from the order input device are sent to and output from the order output device, allowing customers to easily place orders without the need for a clerk to receive them.

[0004] Patent Document 3 below describes a shopping screen display system configured to provide product data that matches the user's personal characteristics. The system can select unpurchased products of the same level and stage based on the user's purchase history and make highly attractive product proposals.

[0005] [Prior Art Documents]

[0006] [Patent Documents]

[0007] [Patent Document 1] JP2007 / -275454

[0008] [Patent Document 2] JP2002 / -189788

[0009] [Patent Document 3] JP2000 / -105784 Summary of the Invention

[0010] However, if it is possible to predict the next consumption behavior of users of a restaurant, the restaurant can be operated more effectively, thereby providing users with a better user experience, which is very useful.

[0011] Therefore, the object of this disclosure is to provide a store support method, data processing apparatus, program, and store system that can predict the next consumption behavior of users of a restaurant store based on usage data.

[0012] The store support method of the first disclosure is implemented by a processor of a data processing apparatus installed in a restaurant store. Usage data is stored in a user data storage unit corresponding to a user identifier that identifies the user. The usage data is usage data related to the user's use of the store, including past usage data related to the user's consumption behavior in the past. Based on the usage data obtained from the user data storage unit, prediction data including the consumption behavior prediction results of users visiting the store is obtained. At least based on the number of users in the store, store status data indicating the busyness of the store is obtained. Based on the prediction data obtained for users visiting the store and the store status data, seat guidance data for guiding the users to a reserved seat in the store is obtained as support data that can be used for the operation of the store. The guidance data is output to a notification device used to guide users visiting the store to a reserved seat. Instruction Manual, Page 1 / 24, CN 121039688 A

[0013] Using the method described above, seat guidance data is obtained based on predicted data and store condition data. Then, the seat guidance data is output to a notification device, and a notification is sent through the notification device to guide the user to a reserved seat. Therefore, users can be guided to the optimal seat considering both predicted data of users visiting the store and the current store condition data. This allows for more efficient store operation and provides more comfortable service to users.

[0014] The second disclosed store support method, relative to the first disclosure, acquires seating guidance data to disperse the positions of diners in the store after a predetermined time.

[0015] By acquiring seating guidance data through this method, the positions of diners in the store are dispersed, allowing diners to enjoy their meals comfortably.

[0016] The third disclosed store support method, relative to the first disclosure, involves a restaurant having two or more seating groups, each consisting of two or more seats in the store, acquiring seating guidance data to ensure that each seat in a reserved seating group is vacant after a predetermined time.

[0017] Through this method, for example, when implementing the operation of stopping the use of confirmed seating groups during periods of relatively low future customer traffic, the use of confirmed seating groups can be stopped at an appropriate time. Furthermore, users who have reserved seats for future scheduled times can reliably use the seats, enabling efficient store operation.

[0018] The fourth disclosed store support method, relative to any of the first to third disclosures, involves a restaurant having two or more seating groups, each consisting of two or more seats within the store. Seating guidance data is also obtained based on load data related to the store's operational load, and load data is obtained based on at least one of the following: the quantity of goods ordered for each seating group, the ordering frequency, the future utilization rate of each seat in each group, and the number of events requiring staff intervention.

[0019] By this method, seating guidance data is also obtained based on load data related to the store's operational load, thus enabling the appropriate acquisition of seating guidance data according to the store's load. This allows for effective operation that takes into account the store's load.

[0020] The fifth disclosed store support method, relative to the fourth disclosure, involves obtaining seating guidance data for each seating group when there are two or more seating groups as the destination for guiding users visiting the store. This data represents a load score indicating that the user has been guided to each seating group, and guiding users visiting the store to the seating group with the lowest score.

[0021] By the method described, a score representing the load is obtained as load data, and seat guidance data is obtained to guide users to the seat group with the lowest score. Therefore, the store can be operated in a way that minimizes store load, and the store can be operated effectively.

[0022] In the sixth disclosed store support method, compared with the fifth disclosure, the notification device includes a staff notification device for notifying store staff, outputting the score to the staff notification device so that the staff notification device notifies the staff of the score in association with the corresponding seat.

[0023] By the method described, the score of each seat group is notified to the staff via the staff notification device.Therefore, staff can infer the store's load based on the scores of each seating group and flexibly determine the seats to guide users.

[0024] The seventh disclosed data processing apparatus includes: a user data storage unit that stores usage data corresponding to user identifiers that identify users, the usage data being usage data related to the user's use of the restaurant store, including past usage data related to the user's consumption behavior during past use; a prediction unit that acquires prediction data including prediction results of the user's next consumption behavior based on the usage data acquired from the user data storage unit; a store status data acquisition unit that acquires store status data related to the status within a store; a support data acquisition unit that acquires support data that can be used for the operation of the store based on the prediction data acquired by the prediction unit for users visiting the store and the store status data; and a support data output unit that outputs the support data.

[0025] With the above structure, the next consumption behavior of users using the restaurant store can be predicted based on usage data related to their past consumption behavior.

[0026] Furthermore, the data processing apparatus disclosed in the eighth disclosure, compared to the seventh disclosure, includes a consumption data acquisition unit that acquires consumption data related to the current consumption behavior of a user visiting a store, and stores the acquired consumption data as past usage data corresponding to a user identifier that identifies the user in a user data storage unit.

[0027] With this structure, the user's next consumption behavior can be predicted with higher accuracy based on data related to the consumption behavior of the user visiting the store this time.

[0028] Furthermore, the data processing apparatus disclosed in the ninth disclosure, compared to the seventh disclosure, includes next usage data input by a user planning to use the store, which is related to the next usage plan.

[0029] With this structure, the user's next consumption behavior can be predicted with higher accuracy based on data related to the next usage plan.

[0030] Furthermore, the data processing apparatus disclosed in the tenth disclosure, compared to the seventh disclosure, includes a prediction unit that acquires prediction data including the prediction result of the group's next consumption behavior based on the usage data of one user in a group containing two or more users and headcount data related to the number of users in the group.

[0031] With this structure, when multiple people visit, prediction data can be acquired based on the number of visitors.

[0032] In addition, the data processing apparatus disclosed in the eleventh disclosure, compared with the seventh disclosure, has a prediction unit that obtains prediction data based on usage data, including prediction results of the next consumption behavior of the group, wherein the usage data is the usage data of each user in a group containing two or more users, including group data related to the group containing the users in the past and past usage data related to the consumption behavior of the group.

[0033] With the above structure, prediction data can be obtained with higher accuracy when multiple people visit.

[0034] In addition, the data processing apparatus disclosed in the twelfth disclosure, compared with the seventh disclosure, includes a seat data acquisition unit, which acquires seat data, including data identifying the seat used by a user visiting the store, and stores the acquired seat data in a user data storage unit corresponding to the user identifier of the identified user.

[0035] With the above structure, prediction data of the user using the seat can be output for each seat.

[0036] In addition, the data processing apparatus disclosed in the thirteenth disclosure, compared with the seventh disclosure, includes an object behavior data acquisition unit, which acquires object behavior data related to the current behavior of the user visiting the store, i.e., a predetermined recorded behavior different from consumption behavior, and stores the acquired object behavior data as usage data in a user data storage unit corresponding to the user identifier of the identified user.

[0037] With the above structure, prediction data can be output using predetermined recorded object behavior different from consumption behavior.

[0038] Furthermore, in the data processing apparatus disclosed in the fourteenth disclosure, compared to the seventh disclosure, the prediction unit is configured to acquire prediction data including prediction results of the user's future consumption behavior in the current usage opportunity, based on usage data related to the user's consumption behavior in past usage opportunities and usage data related to the user's past consumption behavior in the current usage opportunity.

[0039] With this structure, prediction data related to future consumption behavior can be output based on usage data in the current usage opportunity.

[0040] Furthermore, in the data processing apparatus disclosed in the fifteenth disclosure, compared to the seventh to fourteenth disclosures, the restaurant has two or more seating groups, wherein each seating group consists of two or more seats in the store, and the support data acquisition unit acquires load data related to the store's operating load for each seating group based on the prediction data acquired by the prediction unit for users visiting the store and store status data, and acquires support data based on the load data.

[0041] With this structure, support data can be output based on the load data related to the store's operating load for each seating group.

[0042] Furthermore, in the data processing apparatus disclosed in the sixteenth disclosure, compared to the seventh to fourteenth disclosures, the support data acquisition unit acquires seating guidance data related to the seats of users being guided to the store as support data.

[0043] With the above structure, seating guidance data related to the seats of users being guided to the store can be output.

[0044] Furthermore, in the data processing apparatus disclosed in the seventeenth disclosure, compared to the sixteenth disclosure, the support data output unit outputs data representing the number of people in a group including users through a device corresponding to the output destination of the seats of users being guided to the store.

[0045] With the structure described above, data representing the number of people in a group containing the users is output in a manner corresponding to the seats of the users who are guided to the store, so that staff can easily prepare according to the number of people in the group containing the users and can operate the store smoothly.

[0046] In addition, the data processing apparatus disclosed in the eighteenth edition, relative to any of the seventh to fourteenth editions, includes: a future situation data acquisition unit, which uses prediction data acquired for users currently using a store and prediction data acquired for users who will use the store in the future to acquire future situation data related to the future situation in the store; and a future situation data output unit, which outputs the future situation data in a manner that can be confirmed by staff.

[0047] With the structure described above, staff can easily know the prediction results of the future situation in the store before starting work.

[0048] According to the data processing apparatus of this disclosure, the next consumption behavior of users who use the restaurant store can be predicted based on usage data. Brief Description of the Drawings

[0049] FIG1 is a diagram illustrating an example of a store conveyor device, etc., using the store system of this embodiment.

[0050] FIG2 shows a top view of the outline of the store system.

[0051] Figure 3 shows a top view of the overview of the store system.

[0052] Figure 4 shows a diagram of the block structure of the store system.

[0053] Figure 5 shows a diagram of an example of user data used by the data processing device.

[0054] Figure 6 shows a flowchart of an example of the operation of the data processing device.

[0055] Figure 7 shows a flowchart of an example of usage data update processing performed by the data processing device.

[0056] Figure 8 shows a flowchart of an example of support data output processing performed by the data processing device.

[0057] Figure 9 shows a flowchart of an example of future status data output processing performed by the data processing device.

[0058] Figure 10 shows a flowchart of a variation of the usage data update processing performed by the data processing device.

[0059] Figure 11 shows an example of a display screen based on support data displayed on the notification device.

[0060] Figure 12 shows another example of a display screen based on support data displayed on the notification device.

[0061] FIG13 shows an example of a display screen based on future status data displayed on the notification device. Specification 4 / 24 pages 8 CN 121039688 A

[0062] FIG14 shows another example of a display screen based on future status data displayed on the notification device.

[0063] FIG15 is an overview diagram of the computer system in the above embodiment.

[0064] FIG16 is a block diagram of the computer system.

[0065] FIG17 shows another example of a display screen based on supporting data displayed on the notification device. Detailed Description

[0066] Embodiments of the data processing device, a store system using the data processing device, etc., will be described below with reference to the accompanying drawings. Components with the same symbols in the embodiments perform the same operations, so further description is omitted.

[0067] The terms used below are generally defined as follows. Furthermore, the semantics of these terms should not always be interpreted as shown herein; for example, they should be interpreted according to the explanation given separately below.

[0068] An identifier for a certain item is a character or symbol, etc., that uniquely represents the item. An identifier is, for example, an ID, but the type is not limited as long as it is data that can identify the corresponding item. That is, the identifier can be the name of the object it represents, or a combination of various symbols to ensure unique correspondence.

[0069] Acquisition may include acquiring items input by users, etc., or it may include acquiring data stored in other devices. Acquiring data stored in other devices can include acquiring data stored in other devices via APIs, etc., or acquiring the content of document files (including web page content, etc.) provided by other devices via crawling, etc. Additionally, it can include acquiring data in a different format from the original data, such as acquiring data by optical text reading of image files, etc.

[0070] Alternatively, so-called machine learning methods can be used to acquire data. For example, machine learning methods can be used as follows: A machine learning method is used to configure a learner (learning data), which takes input data of a identified type as input and output data to be acquired as output. For example, two or more sets of input data and output data are prepared in advance, the two or more sets of data are provided to a module for configuring a machine learning learner to configure the learner, and the configured learner is stored in storage. Additionally, the learner can also be called a classifier. Furthermore, machine learning methods can be, for example, deep learning, random forest, SVM, etc. Moreover, for machine learning, functions in various machine learning frameworks such as fastText, tinySVM, random forest, and TensorFlow, as well as various existing libraries, can be used. Acquiring data using such a learner is sometimes referred to as acquisition via machine learning.

[0071] Furthermore, the learner is not limited to being obtained through machine learning. The learner may be, for example, a table showing the correspondence between input vectors and output data based on input data, etc.In this case, output data corresponding to the feature vector based on the input data can be obtained from the table, or two or more input vectors in the table and parameters for weighting each input vector can be used to generate a vector that approximates the feature vector based on the input data. The final output data can be obtained using the output data and parameters corresponding to each input vector used in the generation. Using such a learner to obtain data is sometimes referred to as acquisition using a correspondence. In addition, the learner may be, for example, a function that shows the relationship between the input vector based on the input data and the data used to generate the output data. In this case, for example, data corresponding to the feature vector based on the input data can be obtained by the function, and the obtained data can be used to obtain the output data. Using such a learner to obtain data is sometimes referred to as acquisition using a function.

[0072] Output data is a concept that includes displaying on a display, projecting using a projector, printing using a printer, voice output, sending to an external device, storing to a recording medium, passing the processing result to other processing devices or other programs, etc. Specifically, for example, it includes displaying data on a webpage, sending it as an email, outputting data for printing, etc.

[0073] Data acceptance is a concept that includes accepting data input from input devices such as keyboards, mice, and touch panels; receiving data transmitted from other devices via wired or wireless communication lines; and accepting data read from recording media such as optical discs, magnetic disks, and semiconductor memories.

[0074] Updating various types of data stored in data processing devices is a concept that includes not only changing existing data but also adding new data to existing data and deleting some or all of the existing data.

[0075] (Embodiment)

[0076] The outline of this embodiment is as follows. According to this embodiment, the data processing device acquires and outputs prediction data, including prediction results of users' next consumption behavior, based on usage data of users of a restaurant that is related to their use of the restaurant. Usage data may include past usage data related to consumption behavior during past use, for example, data related to the consumption behavior of users who visited the restaurant during this dining opportunity. Usage data may be next usage data related to the next use plan input by users who plan to use the restaurant. Hereinafter, the data processing device configured in this way and the store system using the data processing device will be described.

[0077] First, an example of a store using a store system will be described, which uses a data processing device.

[0078] FIG1 is a diagram illustrating an example of a conveyor device 900, etc., in a store using the store system 1 of this embodiment. FIG2 is a top view showing an outline of the store system 1.Figure 3 is a top view showing an outline of the store system 1.

[0079] The store system 1 according to this embodiment is used, for example, in a restaurant or similar establishment. Figure 1 shows some of the equipment. Figures 2 and 3 show an example of a first conveyor 910 and a second conveyor 920 in a restaurant or similar establishment. A restaurant is, for example, a so-called conveyor belt sushi restaurant. In addition, the store using the store system 1 can be a restaurant of other business types or industries, or it can be a non-restaurant establishment. In addition, the goods provided to users can be paid or free.

[0080] In addition, in this embodiment, the term "goods" refers to food such as sushi. For example, it can be nigiri sushi, hand roll sushi, or other dishes. In addition, food can include beverages, snacks, containerized food, packaged food, etc. In addition, goods can also include other valuable items besides food.

[0081] In this embodiment, the store system 1 allows users visiting the store to order goods at each seat. In addition, in the store system 1, goods can be transported to the user's seat by the conveyor 900.

[0082] Here, "seat" is a concept, referring to a seat or table used by a user as a destination for goods. A seat, for example, corresponds to a customer group consisting of one or more users who purchase goods (a customer group may contain one or more users, or it may be a single user). For example, when a customer group consisting of multiple users visits a restaurant, the customer group will be guided to a table in the restaurant, where the table is equivalent to a seat. Alternatively, for example, when a customer group consisting of one user arrives at a restaurant, the customer group will be guided to a bar seat in the restaurant, where the bar seat is equivalent to a seat. In addition, a seat is not limited to an actual seat or table. A seat can also be other seats corresponding to a group of one or more users, indicating the purchaser, orderer, destination, etc. of the group. Such a seat can be real or virtual. That is, a seat is a concept, representing a unit for collecting goods fees as a destination for goods.

[0083] In addition, in this embodiment, the restaurant has two or more seat groups, which consist of two or more seats in the restaurant. Seat groups can be areas divided for the convenience of restaurant operation. For each seating group, staff responsible for service, cleaning, etc., may be assigned, or the application of the specification (page 6 / 24, CN 121039688 A) may be determined based on the number of customers using the store. Each seating group is typically configured to include two or more seats or tables relatively close to each other, but the invention is not limited thereto. For example, each of the two or more individually chargeable seats included in a seating group may correspond to seats or tables that are far apart from each other in the store.

[0084] The store system 1 includes a conveying device 900, a data processing device 100, and a notification device 700. In this embodiment, a first conveying device 910 and a second conveying device 920 are provided as the conveying device 900, but it is not limited thereto.

[0085] A store using the store system 1 includes, for example, a store 1a where customers dine and a kitchen 1b where goods are cooked or prepared. The store 1a includes, for example, tables 980 and seats 981 for customers to dine at. The tables 980 can be bar tables 980b where customers can line up to eat.

[0086] The notification device 700 is, for example, a receiving terminal corresponding to each seat. Two or more seats can share one notification device 700. Alternatively, two or more notification devices 700 can be used corresponding to one seat. In addition, the notification device 700 is installed in the kitchen 1b and can be configured to be used by store staff. In this case, the notification device 700 for notifying staff is a staff notification device. In addition, the notification device 700 is disposed in the aisle of the store 1a, etc., and can be configured to be used by staff or users who have left their seats (e.g., users who have been guided to their seats, users who have finished their meals, etc.).

[0087] The notification function of the notification device 700 can generally be implemented by a processor, memory, etc. That is, the notification content of yesterday's notification device 700 is generally implemented by software (computer program code), which is recorded on a recording medium such as ROM. However, some or all of the functions of the notification device 700 can be implemented by hardware circuits (dedicated circuits).

[0088] In this embodiment, a group of customers can use the notification device 700 to order goods, etc. The notification device 700 is configured to correspond to the seats they use and has a screen such as a touch panel, i.e., a notification display unit 761.

[0089] In addition, although a tablet-type data terminal device is shown as the notification device 700 in the figure, mobile data terminal devices, personal computers (PCs), etc. can also be used as the notification device 700.

[0090] In the store system 1, users at the corresponding seats can order items 5, etc., using the so-called electronic menu displayed by the notification device 700. For the structure used to accept such orders for items 5, known structures can be used, for example. For instance, the data processing device 100 accepts orders at each seat based on user order operations to the notification device 700, etc., corresponding to each seat, and sends the order details to a terminal (not shown) located in the kitchen 1b, thereby providing the items 5 corresponding to the order.

[0091] Furthermore, in this embodiment, the store system 1 can be used, for example, with a terminal device 600 (as shown in FIG. 4), which can communicate with the data processing device 100 via a network, etc.The terminal device 600 can be considered as part of the store system 1, or it can be considered as not being included in the store system 1. The terminal device 600 is used by users, for example. That is, the store system 1 can be configured so that customers, i.e., users, of restaurants, can use the terminal device 600, etc. In this case, customer groups can use one or more terminal devices 600 they hold to order goods, etc. In this case, for example, the structure of the store system described in the above-mentioned Patent Document 2 can be adopted.

[0092] In addition, for the terminal device 600, mobile data terminal devices such as so-called smartphones can be used, for example. The terminal device 600 has a terminal display unit 661 (shown in FIG4) which is a screen such as a touch panel. In addition, tablet-type data terminal devices and personal computers (PCs) such as laptops can also be used as terminal devices 600.

[0093] In addition, the terminal device 600 can be used by staff such as restaurant waiters, for example. That is, it can also be configured so that staff can use the store system 1 by using the terminal device 600. For example, staff can use terminal device 600 to send data such as order details from each seat to data processing device 100 to process orders.

[0094] In this embodiment, notification device 700 is configured to receive data output (sent) by data processing device 100, as per specification page 7 / 24 11 CN 121039688 A, and display the received data on notification display unit 761. Similarly, when using terminal device 600, display on terminal display unit 661 can also be performed based on data received from data processing device 100.

[0095] Furthermore, in store system 1, devices that can communicate with each other can communicate with each other through networks such as local area networks or the Internet, but are not limited to this. The number of devices included in store system 1 is not limited, and other devices may also be included in store system 1.

[0096] Conveying device 900 is used to transport goods to each seat. The first conveying device 910 and the second conveying device 920 will be described below. Furthermore, as the conveying device 900, only the first conveying device 910 or the second conveying device 920 may be used. Additionally, as the conveying device 900, a device of a different form from the first or second conveying device may be used together with the first conveying device 910 or the second conveying device 920. Alternatively, only a device of a different form from the first conveying device 910 or the second conveying device 920 may be used as the conveying device 900. For example, a self-moving device that moves automatically within the store 1a and distributes goods to each seat may also be used as the conveying device 900.

[0097] As shown in FIG2, the first conveying device 910, for example, has a conveying path 916 on which a plate containing goods 5, such as sushi, is placed.A conveyor path 916 is laid in the store 1a to transport plates to the vicinity of each table 980. The conveyor path 916 may consist of, for example, a crescent chain with a flat upper surface, but is not limited thereto. The conveyor path 916 is configured to transport plates along a predetermined conveying direction, circulating them between the tables 980 in the store 1a and the kitchen 1b. The second conveyor device 920 is not shown in Figure 2.

[0098] The second conveyor device 920 is disposed above the first conveyor device 910. The vertical position of the second conveyor device 920 relative to the first conveyor device 910 is not limited thereto.

[0099] As shown in Figure 3, the second conveyor device 920 has a conveyor path 926 disposed above the conveyor path 916. The conveyor path 926 can hold plates containing the goods 5. The conveyor path 926 is laid in the store 1a to transport plates to the vicinity of each table 980. The conveyor path 926 may consist, for example, of a conveyor belt with configurable plates, but may also be configured to move the configurable plate holder along the conveying direction.

[0100] The conveyor path 926 may convey plates along a predetermined conveying direction (as indicated by the arrow in FIG2) to deliver goods to each table 980 in the store 1a. The conveyor path 926 is configured to pass between seats arranged with the conveyor path 926 sandwiched between each other when viewed from above, but is not limited thereto. A plurality of conveyor paths 926 are provided in the store 1a. One end of each conveyor path 926 is located in the kitchen 1b.

[0101] The second conveying device 920 is driven by a conveyor control unit that controls the operation of the second conveyor device 920. The conveyor control unit is, for example, a control circuit capable of controlling the drive of a motor (not shown) used to drive the conveyor path 926. The conveyor path 926 is driven by the conveyor control unit to convey plates containing goods 5 such as sushi from the kitchen 1b to the store 1a.

[0102] In this embodiment, the second conveying device 920 can provide goods 5, etc., by identifying a seat as the delivery destination. That is, the second conveying device 920 is configured to convey goods 5, etc., to the identified delivery destination. For example, the delivery destination can be identified by instructions to staff in the kitchen 1b, etc., but it can also be identified based on data output from the data processing device 100, etc. When conveying goods 5 to the delivery destination, the second conveying device 920 conveys goods 5 from upstream to the delivery destination, and stops conveying when goods 5 arrive at the delivery destination. Thus, the user can reach out from the seat at the delivery destination to the goods 5 stopped on the conveying path 926 and obtain goods 5.

[0103] In this embodiment, the restaurant can provide users with self-service goods prepared in advance for user consumption, as well as ordered goods provided to users according to the order each time an order is received from the user. Self-service goods are provided by the first conveying device 910.On the other hand, the ordered goods are provided by the second conveyor 920. That is, in this embodiment, the restaurant can be described as a conveyor belt sushi restaurant, including a first conveyor 910 and a second conveyor 920. The first conveyor 910 has a conveyor path 916 that circulates within the store to provide self-service goods. The second conveyor 920 is different from the first conveyor 910 and can transport the ordered goods to the confirmed delivery destination. In addition, it can also be configured so that the ordered goods are provided by the first conveyor 910.

[0104] The store system 1 uses a detection device 991, which will be described later, to detect the user's confirmed object behavior (sometimes referred to as recorded object behavior). The store system 1 has an anomaly detection unit 990, which detects whether an anomaly has occurred based on the detection result of the detection device 991. Here, an anomaly may refer to the existence of the user's object behavior, the receipt of a detection result indicating that the user's object behavior may exist, etc. The anomaly detection unit 990 is configured to detect whether an anomaly has occurred at each seat used by the user, but is not limited thereto.

[0105] In this embodiment, the detection device 991 is, for example, a camera (hereinafter sometimes referred to as camera 991). The camera 991 is arranged, for example, at each seat, and can be configured to capture images (which may be still images or moving images) within a predetermined detection area including the seat. It can be said that the anomaly detection unit 990 detects whether an anomaly has occurred, for example, based on the images captured by the camera 991.

[0106] In addition, specifically, the object behavior is, for example, an act that causes damage to the object corresponding to the goods or seat or damages its value, a predetermined nuisance act, etc., but is not limited thereto. The object behavior may, for example, be an action that is different from the action that the user can perform during normal dining.

[0107] The anomaly detection unit 990 may, for example, be configured to use learning data to detect whether an anomaly has occurred. The learning data consists of input data and output data, wherein the input data includes images of a person who has previously performed what is considered an object action or a state containing the result of such an action, and images of a person performing an object action or a state not containing the result of such an action. The output data includes data indicating whether it is an object action (or, whether it is an anomaly) corresponding to each image.

[0108] As shown in FIG1, in this embodiment, each seat is separated by a partition 985 of a certain height, and the camera 991 is configured to use the space occupied by one seat separated by the partition 985 as the shooting range. Furthermore, the camera's position is not limited to this. Additionally, images including multiple seats can be obtained using a single camera 991.

[0109] In addition, the detection device 991 may be equipped with a device other than a camera, such as a photoelectric sensor. Furthermore, a microphone for detecting speech, etc., may also be used as the detection device 991. In this case, for example, the behavior of generating a sound greater than or equal to a predetermined value can be treated as an object behavior.

[0110] FIG4 is a diagram showing the block structure of the store system 1.

[0111] As shown, the data processing device 100 includes a storage unit 110, a receiving unit 120, a receiving unit 130, a processing unit 140, and a transmitting unit 170.

[0112] The storage unit 110 includes a user data storage unit 115.

[0113] The storage unit 110 is preferably a non-volatile recording medium, but it may also be implemented with a volatile recording medium. Although it stores data acquired in each device, the process of storing data, etc., is not limited to this. For example, data, etc., may be stored by a recording medium, data transmitted via a communication line, etc., or data input via an input device, etc.

[0114] The user data storage unit 115 stores user data related to users using the store. In this embodiment, user data is data corresponding to the user identifier, i.e., the user identifier, and the data related to the user. User data may include various types of data. User data is received by the receiving unit 120, processed by the receiving unit 130, obtained as a result of data processing performed by the processing unit 140, and stored in the user data storage unit 115. Specification 9 / 24 pages 13 CN 121039688 A

[0115] In this embodiment, data related to each user may be stored as user data. User data may include predetermined attribute values ​​related to the status of a user's visit to the restaurant. Predetermined attribute values ​​may include, for example, the number of people in the user's customer group, the time of arrival (or the time elapsed after arriving at the store), the time spent in the store, the time when the dining opportunity ends (or the time of departure), etc., but are not limited to these. It may also include data such as the number of adults and children in the customer group. In addition, it may also include an identifier for identifying the person in charge of various service work for the seat used by the user. Additionally, if it is possible to identify other users (also known as companion users) who visited with the user and formed a customer group with the user, a user identifier for identifying the companion user may also be included.

[0116] Furthermore, some of the user data used in this embodiment are as follows.

[0117] FIG5 is a diagram showing an example of user data used by the data processing apparatus 100.

[0118] In the example shown in the figure, for example, the attribute value of the person in charge of the service work for the seat used by the user, such as the seat confirmation data, the time of visit, and the person in charge of the service work for the seat used by the user, and the user identifier (user ID) for confirming other data recorded in each use opportunity of the user are recorded in correspondence with the user identifier (user ID) that identifies the user as user data.

[0119] The seat confirmation data may include, for example, the table number that can identify the table 980 used by the user and the seat number that can identify the seat 981 of the user using the bar table 980b, and other seat identifiers.

[0120] In this way, when the user data includes the identifier related to the person in charge of the seat, the person in charge corresponding to the user or the seat can be identified based on the user data of each user. In addition, the user data may also include other data besides this. For example, as described below, it may include data related to past visits. In addition, any data (such as the person in charge identifier, etc.) may be stored as data different from the user data. That is, data that can be stored in the storage unit 110, etc., in association with the user identifier or the seat identifier, or data that can be obtained in association with the user identifier or the seat identifier, can be stored as user data.

[0121] In addition, the attribute values ​​of the user data also include usage identifiers related to the usage data described later. The usage data of the user, which is recorded separately as user data using the usage identifier as a keyword, can be identified. Furthermore, the storage method of the usage data is not limited to this and can be appropriately configured.

[0122] The data that can be included in the user data can be described as follows. In this embodiment, usage data related to the user's use of the restaurant is stored in the user data storage unit 115 as user data corresponding to the user identifier that identifies the user. Usage data includes, for example, the predetermined attribute values ​​related to the user's state of visiting the restaurant, or data related to the goods purchased at that time, but is not limited to these. Attribute data input by the user, obtained from the user, and related to the user's attributes can be interpreted as being included in the usage data; such attribute data can also be obtained separately from the usage data. Attribute data can include, for example, data such as the user's address, age, occupation, gender, preferences, etc., and is not limited to data related to these attributes.

[0123] Usage data can include, for example, consumption data related to the user's consumption behavior. Consumption behavior refers to, for example, the purchase of product 5, the consumption of product 5, etc., but is not limited to these. Consumer behavior can also refer to placing an order for product 5, or staying in a store to purchase product 5. Consumer data can be, for example, data related to purchase records of product 5. Data related to purchase records can include order data indicating the processing status of orders placed at each seat. Consumer data can be consumption data for the seat corresponding to the user.Furthermore, if data related to the purchase records of each user within a customer group can be obtained, then each user's consumption data can be included in the user's user data. Specifically, consumption data may include, for example, the amount of product 5 consumed, preference data such as the type of product 5 consumed more often, the product name, menu name, etc., the ordering method used, the time spent in the store, etc., but is not limited to this.

[0124] Consumption data may be, for example, data related to the ordering of products, and data corresponding to seats or users. Consumption data may include, for example, product identifiers and the number of items ordered. Consumption data may be, for example, data sent from a user-operable terminal such as a notification device 700 during the user's dining opportunity. Consumption data may correspond to seat identification data such as seat identifiers for identifying seats and terminal identifiers for identifying terminal devices 600. Therefore, it can be said that consumption data corresponds to users.

[0125] In addition, consumption data may include, for example, product identifiers and amounts. Consumption data can be, for example, data indicating that a plate containing item 5 has been supplied (provided) to a customer group. In other words, consumption data can also be data after an order. In addition, consumption data can be, for example, data related to the amount or quantity of item 5 consumed by the user. In this embodiment, item 5 is provided to the user in a predetermined unit on a plate. In this case, the number of plates containing item 5 consumed by the user can also be used as consumption data.

[0126] Usage data can also be data related to the operation of the second conveying device 920 corresponding to the user. When the second conveying device 920 is used specifically to provide ordered items, such data can be regarded as data on the quantity or timing of ordered items consumed by the user, the ordering frequency or consumption frequency. By using such data and other consumption data, the absolute quantity of ordered items consumed, the ratio of ordered items consumed to self-service items consumed, the ratio of ordered items consumed to total consumption, or the frequency of provision of ordered items can be regarded as usage data.

[0127] Here, in this embodiment, usage data can include past usage data related to the user's past consumption behavior when using the restaurant. A restaurant can refer to a single, identified establishment, or to each of two or more establishments that have a predetermined association (e.g., forming a group of restaurants). Past usage data can be, for example, consumption data from past usage opportunities, but is not limited to this. Past usage data can include data related to the time or moment a user previously used the service. For example, past usage data can include data related to the time of arrival or stay, departure time, etc. Additionally, past usage data can include group data related to a group containing users who previously used the service, as well as consumption data for said group, and other data related to consumption behavior.Group data may include, for example, the number of people in a customer group, but is not limited to this.

[0128] In addition, user data may also include usage data related to the purchase records (this purchase record) up to the present in the user's current dining opportunity.

[0129] In addition, usage data may include next usage data related to the next usage reservation entered by the user who plans to use the store. The next usage reservation may be, for example, a reservation for visiting the store in the future, or the user's desired usage pattern after arriving at the store and starting to dine. That is, next usage data may be, for example, data related to the user's store usage reservation, or data related to the user's usage pattern for dining in the future. Data related to the usage reservation may include, for example, the reservation time related to usage (reservation of arrival time, stay time, etc.), data such as the number of people in the user's customer group, the type of seat desired (e.g., bar seat or table seat, etc.), consumption data obtained when ordering product 5 in advance, etc., but is not limited to this. In addition, the user's usage pattern here may include, for example, data such as the number of people in the user's customer group, the type of seat desired, consumption data obtained when ordering product 5 in advance, etc., but is not limited to this. The data used next time may be, for example, data input in advance by the user using the user's terminal device 600, or data input by the user visiting the store using the notification device 700, etc.

[0130] The receiving unit 120 receives data sent from other devices. The receiving unit 120 is usually implemented by a wireless or wired communication unit, but it may also be implemented by a unit that receives broadcasts.

[0131] The receiving unit 120 stores the received data, for example, in the storage unit 110. In this embodiment, the user may, for example, use the notification device or the terminal device 600 to input data and send the data to the data processing device 100. The receiving unit 120 may store each piece of data sent in the storage unit 110 in correspondence with a terminal identifier or a seat identifier. Specification 11 / 24 pages 15 CN 121039688 A That is, the receiving unit 120 may correspond the received data with a user identifier. In this embodiment, the receiving unit 120 can receive consumption data sent from each terminal device 600 or notification device 700, and store it in the storage unit 110 in correspondence with a terminal identifier or a seat identifier. Additionally, when receiving data from the notification device 700, the receiving unit 120 can identify the seat identifier based on the sent data, the seat identifier being used to identify the seat corresponding to the notification device 700 associated with the transmission. Furthermore, when receiving data from the terminal device 600, the receiving unit 120 can identify the terminal identifier associated with the transmission based on the sent data.

[0132] The receiving unit 130 receives data input using an input unit (not shown) connected to the data processing device 100.The receiving unit 130 stores the received data, for example, in the storage unit 110. Additionally, the input unit can be a numeric keypad, keyboard, mouse, menu screen, etc. The receiving unit 130 can be implemented using a device driver for an input unit such as a numeric keypad or keyboard, or control software for a menu screen, etc. The receiving unit 130 can accept data input through input operations performed using a reading device (e.g., a code reader, etc.) connected to the data processing device 100 (e.g., data read by the device).

[0133] Furthermore, it can be said that the receiving unit 130 accepts data received by the receiving unit 120 as input data to the data processing device 100. That is, inputting data to the data processing device 100 can be interpreted as this data being indirectly input into the data processing device 100 by the user via the notification device 700, terminal device 600, etc.

[0134] Additionally, the receiving unit 120 or the receiving unit 130 can also receive or accept data sent or input by store staff.

[0135] The processing unit 140 performs various processing steps. Various processes refer to the processes performed by various parts of the processing unit 140 as follows. The processing unit 140 can generally be implemented by a processor, memory, etc. The processing steps of the processing unit 140 are generally implemented by software (computer program code), which is recorded in a recording medium such as ROM. However, some or all of the processing can be implemented by hardware (dedicated circuitry).

[0136] Here, in this disclosure, the term "processor" refers to a processor as one or more pieces of hardware configured to execute program code (i.e., one or more instructions that make up a program) included in a program. In other words, a "processor" is a hardware device capable of executing one or more programmed processes. For example, a "processor" can be a general-purpose processor or a dedicated processor, including but not limited to CPUs, microprocessors, GPUs, and DFPs (data flow processors).

[0137] In this disclosure, the term "memory" is a non-migrating physical recording medium, i.e., one or more hardware memories configured to record computer program code and / or data in a manner accessible from the processor. "Memory" can be implemented by memory technologies such as SRAM, SDRAM, non-volatile / flash memory, or other types of memory. The computer code that makes up the program is recorded in memory and executed by a processor, thereby enabling the processing unit 140 to perform various functions.

[0138] In addition, in this embodiment, the processing unit 140 is configured to control the operation of the second conveying device 920. By controlling the drive of the conveying path 926 of the second conveying device 920 based on the control of the processing unit 140, each seat can be identified to deliver the goods 5.

[0139] In this embodiment, the processing unit 140 is configured to make predictions related to the user's use of the store based on user data.This prediction function is implemented by a user data acquisition unit 141, a seat data acquisition unit 143, a store status data acquisition unit 145, a consumption data acquisition unit 147, an object behavior data acquisition unit 149, a usage data acquisition unit 151, a prediction unit 153, a prediction data output unit 155, a support data acquisition unit 163, a support data output unit 165, a future status data acquisition unit 167, and a future status data output unit 169, all provided on the processing unit 140. Each part of these processing units 140 can perform the following processing:

[0140] The user data acquisition unit 141 acquires user data related to the user who is the object of prediction. For example, the user data acquisition unit 141 acquires user data corresponding to the user identifier of the object user or the seat identifier that identifies the seat corresponding to the user.

[0141] The seat data acquisition unit 143 acquires seat data, which includes data identifying the seat used by the user visiting the store. The seat data acquisition unit 143 stores the acquired seat data in the user data storage unit 115 in correspondence with the user identifier of the identified user. For example, the seat data acquisition unit 143 acquires the seat identifier of the seat used by the identified user as seat data. And, the seat identifier is stored as user data in correspondence with the user identifier of the seat used by the user in the usage opportunity. Thus, the seat used by the user in the identified usage opportunity can be identified for a user.

[0142] In this way, by storing the seat data as user data, the user who has used the seat can be identified based on the seat data. In addition, predictive data of the user using the seat can be output for each seat.

[0143] The store status data acquisition unit 145 acquires store status data related to the status of a store. The store status data may be, for example, data representing the level of busyness (e.g., the level of crowding) in the store. The level of crowding may be an indicator based on factors such as the number of users entering the store, the number of orders processed or the number of orders per unit time, and the time required from ordering to providing the goods 5, but is not limited to these. For example, the above-mentioned factors such as the number of users and the number of orders can be used as the level of crowding. In addition, seat occupancy rate, number of users within a reserved unit of time, values ​​corresponding to the number of reservations, or values ​​obtained using these data can be used as store status data.

[0144] The store status data acquisition unit 145 can, for example, acquire store status data based on the store status (order quantity, number of users, etc.) stored in the storage unit 110. In this embodiment, user data of other users visiting the store, such as prediction data or consumption data obtained for other users, are used as store status data, but are not limited to this.For example, the store status data acquisition unit 145 can be configured to acquire store status data based on images obtained by taking pictures of the store using a camera 991 or the like.

[0145] The consumption data acquisition unit 147 acquires consumption data related to the current consumption behavior of a user visiting the store. In addition, the consumption data acquisition unit 147 stores the acquired consumption data as past usage data in the user data storage unit 115, corresponding to the user's identifier. The consumption data acquisition unit 147 can be configured, for example, to acquire the consumption data of a user currently making a consumption behavior one by one. In this case, the consumption data acquisition unit 147 can be configured, for example, to acquire consumption data based on the user's order acceptance status, plate return status, etc. In addition, the consumption data acquisition unit 147 can be configured to acquire consumption behavior related to a user's consumption behavior in a recent dining opportunity at a predetermined time. In this case, the consumption data acquisition unit 147 can be configured, for example, to acquire consumption data based on data such as the order record of the product 5 stored in the storage unit 110 or the like, corresponding to the user's identifier.

[0146] The object behavior data acquisition unit 149 acquires object behavior data related to the current recorded object behavior of the user visiting the store. Furthermore, the object behavior data acquisition unit 149 stores the acquired object behavior data as usage data, corresponding to the user identifier that identifies the user, in the user data storage unit 115. As described above, object behavior can be a predetermined behavior different from consumption behavior.

[0147] In this embodiment, the object behavior data acquisition unit 149 is configured to acquire object behavior data based on the result that the anomaly detection unit 990 detects an anomaly in each seat used by the user. The object behavior data of the user using the seat can be stored based on the result that an anomaly has been detected in each seat.

[0148] Furthermore, the object behavior data acquisition unit 149 can, for example, be configured to acquire object behavior data based on data input by staff, etc. For example, it can also be configured to store object behavior data when a staff member knows that a user has performed object behavior, and when the staff member inputs data using the notification device 700, terminal device 600, etc. In this case, for example, object behavior data can be stored by having staff input user identifiers, seat identifiers, etc. using a predetermined method, as per the instruction manual (pages 13 / 24, CN 121039688 A).

[0149] The data acquisition unit 151 acquires user usage data from the user data storage unit 115. The data acquisition unit 151 is configured, for example, to acquire the user's usage data when making a prediction for a user using a prediction function.

[0150] The prediction unit 153 acquires prediction data based on the usage data acquired by the data acquisition unit 151.The prediction unit 153 is configured, for example, to acquire prediction data for each user based on the user's usage data. The prediction data refers to data including prediction results of the user's next consumption behavior.

[0151] The consumption behavior prediction results include, for example, prediction results of the consumption quantity of product 5, prediction results related to preferences, i.e., prediction results of the types, names, menu names, etc. of product 5 that are likely to be consumed, prediction results related to the user's order quantity of product 5, prediction results of the time spent in the store, etc., but are not limited to these. The order quantity of product 5 refers to, for example, data indicating the quantity of product 5 that is specifically ordered and transported by the second conveyor 920 in a store where product 5 can be purchased even without ordering and is transported to the seat by the first conveyor 910, but is not limited to this. The order quantity refers to the order quantity per unit time (i.e., the order frequency).

[0152] The next consumption behavior may refer to the consumption behavior when visiting the store in the future. In addition, the next consumption behavior may refer to the consumption behavior of the user who is currently dining in the store, i.e., the consumption behavior after this visit opportunity.

[0153] Alternatively, pre-configured learning data can be used to obtain prediction data. For example, various methods can be used, such as the acquisition through machine learning, acquisition using functions, acquisition using correspondences, etc. In this case, for example, the learning data can be composed of the usage data of each of two or more users stored in the past.

[0154] In addition, the processing unit 140 can perform the following processing: for each user or two or more users corresponding to a shared attribute value, learning data is composed using past usage data. And, the prediction unit 153 can use the learning data corresponding to the user as the prediction object to predict the next consumption behavior.

[0155] Here, the user can be a single user or a customer group.

[0156] In this embodiment, for a customer group containing any one user whose usage data is stored as user data, prediction data including the prediction result of the group's next consumption behavior can be obtained based on the user's usage data and the number of people in the customer group. In other words, the prediction unit 153 can obtain prediction data including the prediction result of the customer group's next consumption behavior based on the usage data of one user in a customer group containing two or more users and the number of people related to the number of users in the customer group. When multiple people visit, predictive data can be obtained based on the number of visitors. For example, predictive data such as the amount of product 5 purchased and the length of time spent in the store can be obtained for each customer group. More specifically, as an example, for a certain user, predictive data such as the amount of product purchased ("20 plates") and the length of time spent in the store ("30 minutes") for a two-person customer group, and predictive data such as the amount of product purchased ("35 plates") and the length of time spent in the store ("40 minutes") for a four-person customer group can be obtained.

[0157] In addition, in this case, the number of people in the customer group can be data representing the number of people for each attribute value of a predetermined attribute of each person. For example, the number of adults and children that make up the customer group can be used as the number of people data.

[0158] In addition, when obtaining prediction data for a customer group that includes any one user whose usage data is stored as user data, the prediction unit 153 can obtain the prediction data as follows. For example, the prediction unit 153 can use group data related to the group that includes the users who have used the product in the past and past usage data related to the consumption behavior of the group to obtain the prediction data. When multiple people visit, the prediction data can be obtained with higher accuracy. When a new user is included in the group, for example, data related to the average consumption behavior of the user can be used to obtain the prediction data. Specification 14 / 24 pages 18 CN 121039688 A

[0159] In addition, the prediction unit 153 can be configured to obtain prediction data including the prediction result of the group's next consumption behavior based on the usage data of each user in a customer group that includes two or more users. That is, when a customer group of two or more people includes two or more users whose usage data is stored as user data, the prediction unit 153 can obtain prediction data for the customer group based on the usage data of each user. In this case, for example, the prediction data for the customer group can be obtained by combining the usage data obtained for each user. Alternatively, for example, prediction data can be obtained as the prediction data for the customer group, which is the average of the prediction data obtained for each user based on the user's usage data and the number of users.

[0160] While the user or customer group being predicted is currently dining in the store, the prediction unit 153 is configured to obtain prediction data including the prediction result of the user's future consumption behavior in the current usage opportunity, based on usage data related to the user's consumption behavior in past usage opportunities and usage data related to the user's past consumption behavior in the current usage opportunity. In other words, the prediction unit 153 can repeatedly obtain (update) prediction data while the user is using the store. Thus, prediction data related to future consumption behavior can be output based on the usage data in the current usage opportunity.

[0161] In addition, the prediction unit 153 can acquire prediction data related to the consumption of ordered goods as prediction data. The prediction data related to the consumption of ordered goods may include, for example, the absolute quantity of the consumption of ordered goods (e.g., the number of plates, the amount, etc.), the ratio of the consumption of ordered goods to the consumption of self-service goods, the ratio of the consumption of ordered goods to the total consumption, or the frequency of the provision of ordered goods.Such predictive data can be obtained, for example, by the data acquisition unit 151 based on data obtained from the user data storage unit 115 as usage data corresponding to the user, and data related to the operation performed by the second conveying device 920 corresponding to the user. Such predictive data can be used to determine the degree to which ordered goods need to be provided, and can be considered useful data. In particular, in this embodiment, predictive data can be output more accurately based on data related to the operation of the second conveying device 920.

[0162] The predictive data output unit 155 outputs predictive data. In this embodiment, the predictive data output unit 155 stores predictive data in the storage unit 110, for example (an example of output). Thus, support data can be obtained using the predictive data. In addition, the output of predictive data is not limited to this. For example, the predictive data can also be sent to a notification device 700 used by staff so that staff can view the predictive data in the store.

[0163] In this embodiment, the data processing device 100 can use the predictive data to output support data that can be used for store operation, or output future situation data related to the future situation in the store.

[0164] The support data acquisition unit 163 acquires support data that can be used for store operation based on the prediction data acquired by the prediction unit 153 for users visiting the store. Additionally, the prediction data output unit 165 outputs the support data. By outputting the support data, store operation can be easily facilitated.

[0165] The support data is, for example, seat guidance data related to guiding users to their seats at the store. Seat guidance data includes, for example, data such as seat identifiers that identify seats, or data that identifies a group of seats consisting of two or more seats within the store. A group of seats is preferably composed of multiple seats that are relatively close together. Furthermore, the support data is not limited to seat guidance data. For example, data such as the increase or decrease in the number of staff performing services as instructed by users, or the increase or decrease in the number of staff preparing goods 5 in the kitchen, can also be acquired as support data. Furthermore, in stores that provide different services based on the user's preferences, for example, the system can be configured to acquire data related to the preferred content or the service to be provided as support data. Additionally, the system can be configured to acquire data related to a predicted order when the user makes an order, as support data. Additionally, when the predicted data can be directly used as support data, the support data acquisition unit 163 can also be configured to acquire the predicted data as support data. Specification 15 / 24 pages 19 CN 121039688 A

[0166] In this embodiment, the support data acquisition unit 163 is configured to acquire support data based on store status data and predicted data. For example, support data can be acquired based on the store's status and predicted data to enable effective store operation.For example, when acquiring seat guidance data as supporting data, seat guidance data can be acquired based on store condition data such as the vacancy status of each seat in the store, the time elapsed since each seat was first used, and the prediction results of user dwell time, in order to meet reservation criteria.

[0167] Reservation criteria can be defined from different perspectives. For example, by acquiring seat guidance data, the positions of customer groups dining in the store can be more dispersed after the reservation time (not concentrated in certain seat groups), and the positions of seats used after the reservation time can be avoided from being concentrated in the store. Users can use the store comfortably. In addition, the workload of staff responsible for each seat group can be distributed. In addition, reservation criteria can be set so that each seat in the confirmed seat group becomes vacant after the reservation time. For example, when the use of the confirmed seat group is stopped during a period of relatively few customers in the future, the use of a specific seat group can be stopped at an appropriate time, or at a future reservation time, users who have reserved seats can reliably use the seats, and the store can operate effectively.

[0168] Supporting data can be acquired as follows. In this embodiment, the support data acquisition unit 163 acquires load data related to the store's operational load based on the forecast data acquired by the forecast unit 153 for users visiting the store and store status data. Furthermore, the support data acquisition unit 163 acquires support data based on the acquired load data. This allows for more efficient store operation by acquiring support data. Load data can include, for example, data for each seat group representing the order quantity of product 5, order frequency, future occupancy rate of each seat in the seat group, the number and frequency of events requiring staff intervention, etc., but is not limited to these. Data indicating future changes in these data can also be used as load data. For example, when acquiring such load data, the support data acquisition unit 163 can guide users visiting the store to seats in the seat group with the lowest load. Additionally, when there are multiple options for the user's destination, the load data for each seat group can be acquired when each option is selected, and support data can be acquired based on the acquired load data.

[0169] Furthermore, the support data acquisition unit 163 may, for example, acquire a score 200 representing the overall store load when the option is selected, corresponding to each option that can be used as a user's destination, and acquire support data using the option with the lowest load (see FIG17). In this way, by acquiring support data, the store can be operated more efficiently.

[0170] Here, in this embodiment, the support data output unit 165 may output user-related data as support data in a manner corresponding to the seat of the user guiding them to the store. The manner corresponding to the seat may be, for example, by displaying the support data through a notification device 700 used at the seat, or by outputting the support data so that the staff corresponding to the seat can confirm it.For example, the support data output unit 165 can output support data to a device such as a notification device 700 corresponding to the seat of the user being guided to the store or a terminal device 600 used by staff responsible for the work related to the seat. In this case, the guided user can easily know the seat to be used by looking at the display on the notification device 700. In addition, the staff can easily know the seat to be guided to. Data related to the user can be output in a manner corresponding to the seat of the user being guided to the store, and the store can be operated smoothly.

[0171] In addition, data such as the number of people in a customer group including the user can also be output as support data. As a result, the staff corresponding to the seat as the guidance destination can easily know the data of the next user to use the seat, or can make necessary preparations or take other actions. Therefore, the store can be operated smoothly. In addition, the output of support data can be in a form different from the form of displaying the number of people on the notification device 700 or the like at the seat. For example, data based on prediction data or the like can be sent to the terminal of the person in charge, or voice representing support data can be output. In addition, support data can also be broadcast to the notification device 700 or the like. Instruction manual, pages 16 / 24, 20 CN 121039688 A

[0172] The future situation data acquisition unit 167 uses prediction data acquired for users currently using a store and prediction data acquired for users who will use the store in the future to acquire future situation data related to the future situation in the store. In addition, the future situation data output unit 169 outputs the acquired future situation data so that store staff can check it. The so-called output data so that store staff can check it means, for example, sending data to the notification device 700 or terminal device 600 used by the staff to display data. For example, when there is a notification device 700 or the like that displays a seating chart in which the status of each seat is displayed, the data representing the future status of each seat can be displayed on the device as future situation data. In addition, it is not limited to this, for example, the data can also be sent by outputting data via voice or the like.

[0173] The future situation data is, for example, the status of each seat in the store in the near future (e.g., tens of minutes later, several hours later, etc.), vacancy rate, etc., but is not limited to this. For example, it could be the sales revenue for the day, the sales quantity of product 5, etc. The future situation data acquisition unit 167 can, for example, use predicted data of each user currently using the store or users planning to visit in the future (users with appointments, etc.) to acquire future situation data. If a user has already arrived at the store but is waiting to be seated (a user waiting in line), the predicted data of that user can be used to acquire future situation data.By outputting future situation data in this way, staff can easily know the predicted results about the future situation in the store before starting work.

[0174] The sending unit 170 sends the data to other devices via a network or the like. The sending unit 170 sends the data to the notification device 700 or the terminal device 600, for example. In other words, the sending unit 170 outputs the data to the notification device 700 or the terminal device 600, for example.

[0175] In addition, the receiving unit 170 can usually be implemented by a wireless or wired communication unit, but it can also be implemented by a broadcast unit.

[0176] In this embodiment, the data processing device 100 is configured, for example, to perform prediction functions, etc., by performing various operations. These operations are performed by the processing unit 140 using various components to perform control operations, etc. Hereinafter, as a specific example of this embodiment, assuming that a user visits the store and is in a state where he / she can be guided to sit down, prediction data related to the user is acquired, and seating guidance data is output as support data.

[0177] FIG6 is a flowchart showing an example of the operation of the data processing device 100.

[0178] For example, the processing shown in the figure is performed periodically. However, it is not limited to this; it can also be performed when other predetermined execution conditions are met (e.g., a predetermined time has arrived or predetermined data has been detected).

[0179] (Step S101) The processing unit 140 determines whether the time for updating the usage data has arrived. If it is determined that the update time has arrived, it proceeds to step S102; otherwise, it proceeds to step S103. Furthermore, the time for updating the usage data can be, for example, a periodic visit or the occurrence of a predetermined event. Predetermined events include, for example, the acceptance of order data, the provision of ordered goods, a user visit, departure, the acceptance of appointments, the acceptance of staff instructions, or the detection of object behavior, but are not limited to these. It can also be any predetermined number of events from two or more predetermined events occurring.

[0180] (Step S102) The processing unit 140 performs usage data update processing. The usage data update processing will be explained later.

[0181] (Step S103) The processing unit 140 determines whether the time for outputting support data has arrived. When it is determined that the time for outputting support data has arrived, the process proceeds to step S104; otherwise, it proceeds to step S105. For example, when a customer visiting the store is redirected to their seat, the processing unit 140 can determine that the time for outputting support data has arrived. The time for outputting support data is not limited to this; for example, it could be a regular visit or the occurrence of a scheduled event. Scheduled events could be, for example, the acceptance of an appointment or the acceptance of instructions from staff, but are not limited to these.

[0182] (Step S104) The processing unit 140 performs support data output processing. The support data output processing will be described later.Instruction manual 17 / 24 pages 21 CN 121039688 A

[0183] (Step S105) The processing unit 140 determines whether the time for outputting future status data has arrived. When it is determined that the time for outputting future status data has arrived, it proceeds to step S106; otherwise, it returns to step S101. For example, when an instruction operation is performed by a staff member through a notification device 700, the processing unit 140 can determine that the time for outputting future status data has arrived. The time for outputting future status data is not limited to this; for example, it could be a regular visit.

[0184] (Step S106) The processing unit 140 performs future status data output processing. The future status data output processing will be described later. Then it returns to step S101.

[0185] FIG7 is a flowchart showing an example of the usage data update processing performed by the data processing device 100.

[0186] (Step S121) The processing unit 140 obtains the next usage data of any user and stores it in correspondence with the user identifier. That is, it updates the next usage data of the user. In addition, the processing can be performed when there is re-accepted next-use data, that is, when there is next-use data that has not been stored.

[0187] (Step S122) The processing unit 140 obtains the consumption data for each seat. In addition, the processing can be performed when there is re-acceptable consumption data, that is, when there is consumption data that has not been stored. For example, the consumption data after the last use data update processing can be used as the object.

[0188] (Step S123) When a customer leaves the store, the processing unit 140 obtains the customer's departure time. For example, the departure time can be the time when the checkout is completed, or the time when there is an instruction to stop using the product, but it is not limited to these.

[0189] (Step S124) The processing unit 140 stores the data obtained in steps S122 and S123 as past use data and the user identifier of the user corresponding to each data. That is, the past use data of each user is updated.

[0190] (Step S125) The processing unit 140 determines whether object behavior data has been obtained. When it is determined that object behavior data has been obtained, the process proceeds to step S126; otherwise, the data update process ends.

[0191] (Step S126) The processing unit 140 stores the obtained object behavior data as usage data corresponding to the user identifier of the user who was determined to have performed object behavior. Then, the data update process ends. In addition, the user who was determined to have performed object behavior can be identified, for example, based on data used to identify the seat where an anomaly was detected by the anomaly detection unit 990.

[0192] FIG8 is a flowchart showing an example of the support data output processing performed by the data processing device 100.

[0193] The processing unit 140 first acquires prediction data for the predicted target user, such as a user who can be guided to a seat.

[0194] (Step S141) That is, the processing unit 140 acquires the usage data of the predicted target user from the user data storage unit 115.

[0195] (Step S142) The processing unit 140 uses the usage data to acquire and output the prediction data of the user. For example, the processing unit 140 outputs the prediction data by storing the prediction data in the user data storage unit 115.

[0196] (Step S143) The processing unit 140 acquires store status data.

[0197] Next, the processing unit 140 uses the prediction data and store status data to acquire seat guidance data as support data.

[0198] (Step S144) That is, the processing unit 140 uses the user's prediction data and store status data to acquire load data.

[0199] (Step S145) The processing unit 140 uses the load data to acquire seat guidance data.

[0200] (Step S146) The processing unit 140 outputs the acquired seat guidance data. For example, the seat guidance data is output so that the notification device 700 in the store that the user or the staff responsible for guiding can confirm, the notification device 700 at page 18 / 24 of the seating instruction manual 22 CN 121039688 A which is the destination of the guidance, etc., are displayed based on the seat guidance data. Then, the support data output process ends.

[0201] FIG9 is a flowchart showing an example of the future status data output process performed by the data processing device 100.

[0202] (Step S161) The processing unit 140 acquires the prediction data of the users currently using the store. In other words, the processing unit 140 acquires store status data including the prediction data of the users currently using the store. The prediction data acquired in the support data output process and the like and stored in the user data storage unit 115 can be acquired. In addition, the prediction data of the users can be reacquired based on the usage data of each user.

[0203] (Step S162) The processing unit 140 acquires the prediction data of the users who will use the store in the future. The processing unit 140 may, for example, obtain predictive data based on the user's next usage data and past usage data.

[0204] (Step S163) The processing unit 140 uses the predictive data obtained in steps S161 and S162 to obtain future status data.

[0205] (Step S164) The processing unit 140 outputs the obtained future status data. For example, the future status data is output so that the notification device 700, terminal device 600, etc. used by the staff can display it based on the future status data.

[0206] In addition, in the above description, the data update processing can update the usage data of users who meet predetermined conditions.Here, the predetermined condition may refer, for example, to a user who has finished a dining opportunity (e.g., a user who has paid the bill or left the store), but is not limited to this. In this case, the usage data update process may be performed as follows.

[0207] FIG10 is a flowchart showing a modified example of the usage data update process performed by the data processing device 100.

[0208] (Step S221) The processing unit 140, as in step S121 above, acquires the next usage data of any user and stores it in correspondence with the user identifier.

[0209] (Step S222) After performing the previous usage data update process, the processing unit 140 determines whether any user has finished a dining opportunity. If a user has finished using the service, the user is used as the update target for processing after step S223; otherwise, the usage data update process ends.

[0210] (Step S223) The processing unit 140 acquires the consumption data corresponding to the update target user.

[0211] (Step S224) The processing unit 140 acquires the departure time of the update target user.

[0212] (Step S225) The processing unit 140 determines whether object behavior data corresponding to the update target user has been obtained.

[0213] If it is determined that object behavior data has been obtained, then proceed to step S226; otherwise, proceed to step S227.

[0214] (Step S226) The processing unit 140 obtains object behavior data corresponding to the update target user.

[0215] (Step S227) The processing unit 140 stores the obtained update target user data as past usage data and the user's user identifier. Then, the usage data update process ends.

[0216] When the prediction function is used as described above, support data or future status data is output. In this embodiment, when support data or future status data is output in this way, the notification device 700, etc., which is the output destination, displays, for example, an output screen so that staff can confirm. In addition, in this example, it is assumed that the data output for displaying a screen for staff to confirm is support data or future status data.

[0217] FIG11 is a diagram showing an example of a display screen 81 based on support data displayed on the notification device 700.

[0218] As shown in the figure, in this embodiment, when the notification device 700 outputs support data, a display screen 81 based on support data is displayed on the notification display unit 761 of the notification device 700. In the example shown in the figure, an example of a display screen 81 displayed on the notification device 700 for staff members is shown, for example, the notification device 700 is configured so that staff members engaged in guiding customers in the store can confirm this.

[0219] On display screen 81, for example, data indicating the destination seat for the user who has been identified as a seat guide is displayed, such as "Please guide to seat number 11," and data indicating that the customer should be guided to that seat. Additionally, in this embodiment, data indicating the number of customers is displayed, allowing staff to easily know the number of customers or easily identify the customer to be guided as another customer. Display screen 81 includes a confirmation button 812, configured so that by operating the confirmation button, one can move from display screen 81 to another screen.

[0220] Furthermore, display screen 81 can simultaneously display usage data of the user being guided and reference data based on prediction data. This type of data can, for example, use data indicating the last time the user arrived at the store or data indicating the predicted length of stay. Thus, staff can know how the user uses the store, whether they are accustomed to using the store, and when they expect to dine, and keep this in mind to provide appropriate service. Additionally, data indicating the degree to which the staff responsible for the seat should provide service to the user can be used as reference data. This data can, for example, be displayed as a score indicating the degree. The predicted score is displayed along with past performance, allowing staff to know, before starting work, the extent to which ordered goods or other customer services need to be delivered to users. This reference data can be an example of supporting data. Displaying reference data allows staff to work with the reference data in mind, thereby enabling them to serve users more effectively and provide more attentive service.

[0221] Figure 12 is a diagram showing another example of a display screen 82 based on supporting data displayed on the notification device 700.

[0222] In the example shown in the figure, an example of a display screen 82 displayed for staff in the notification device 700 is shown, for example, when guiding a customer to a seat, which is positioned at the seat that is the destination of the guidance.

[0223] The display screen 82, for example, displays data indicating that the customer should be guided to the seat where the notification device 700 is located. Displaying this data allows staff preparing the seat for the next customer to be welcomed to a seat in an appropriate state. Additionally, in this embodiment, data indicating the number of customers is displayed, for example, so that staff can easily know the number of customers or easily identify the customer to be guided as another customer. When seating needs to be prepared based on the number of customers, preparations can be carried out efficiently. Furthermore, the example shown in the image also displays data on customers who may require special dishes, tableware, or seating (such as children). Therefore, by confirming that staff on display screen 82 can prepare for such customers in advance, the store can operate more smoothly.

[0224] FIG. 17 is a diagram showing another example of the display screen 83 displayed on the notification device 700.

[0225] In another example, the display screen 83 displays data indicating the destination seats for guidance, and displays a score 200 representing the store's operational load assuming that customers have been guided to each seat group A to C. The score 200 is acquired by the processing unit 140 as load data. More specifically, the processing unit 140 calculates the score 200 based on at least one of the following: the quantity of goods ordered for each seat group A to C, the ordering frequency, the future utilization rate of each seat in each seat group A to C, and the number of events requiring staff intervention.

[0226] The display screen 83 displays the score 200 corresponding to each seat group A to C. The magnitude of the score 200 indicates the magnitude of the load, and the example in the figure shows the case where the load is expected to be the highest when customers are guided to seat group A. On the other hand, the case where the load is expected to be the lowest when customers are guided to seat group B is also shown. Therefore, the display screen 83 displays seat group B as the guidance destination. In addition, it can be seen that the score of seat group C is 15 points, which is greater than that of seat group B, but much smaller than that of seat group C.

[0227] Thus, by displaying the score 200 of each seat group A to C on the display screen 83, the staff can grasp the load when guiding customers. Furthermore, considering the score 200, the staff can also guide customers to the designated seats based on their own judgment. For example, although seat group B is displayed as the destination on the display screen 83, it can be seen that even if the customer is guided to seat group A according to the score 200, the load will not be too large. Therefore, the staff can determine whether to guide the customer to seat group A based on the store conditions (e.g., whether seat group B, the destination, is dirty). Therefore, the store can be operated flexibly and more considerate services can be provided to users.

[0228] FIG13 is a diagram showing an example of a display screen 85 based on future situation data displayed on the notification device 700. Figure 14 is a diagram showing another example of a display screen 86 based on future situation data displayed on the notification device 700.

[0229] As shown in the figure, in this embodiment, when the notification device 700 outputs future situation data, a display screen 85, 86 based on the future situation data is displayed on the notification display unit 761 of the notification device 700. In the example shown in the figure, an example of display screens 85, 86 displayed on the notification device 700 for staff members is shown, for example, the notification device 700 being set up in the store for staff members who guide customers to check.

[0230] In the example described below, display screen 85 displays data indicating the occupancy status of each seat, including predictions of future status (e.g., the predicted time until the end of use). Additionally, display screen 86 displays predictions of the future status of each seat group, for example, visually displaying the predicted busyness of each seat group. Furthermore, in this embodiment, these displays are in the form of diagrams, corresponding to the positional relationships of each seat or seat group within the store, allowing staff to easily grasp the displayed content.

[0231] In display screen 85, the occupancy status of each seat is displayed as follows. For example, when a customer is not using a seat, it is displayed that the seat is vacant. On the other hand, when a customer is using a seat, the time elapsed since the start of use and the predicted time until the end of use are displayed (predicted time). This display makes it easy to confirm the time elapsed since the start of use for each seat. Furthermore, displaying the predicted time until the end of use allows staff to easily know how long it will take for each seat to become vacant. Therefore, useful data can be provided for staff to work effectively.

[0232] In display screen 86, the future busyness of each seat group is displayed as follows. For example, the level of busyness for each seating group in each future time period is represented by shades of light. The level of busyness can vary, for example, based on order frequency, number of people in the seating group, etc., but is not limited to this. In the display screen 86, for example, time periods with higher busyness are displayed in a darker color, so it is easy to know which seating groups are likely to be busy at what time. For time periods or seating groups with higher busyness, measures such as temporarily increasing the number of staff can be taken. Therefore, the store can be operated more efficiently, and comfortable service can be provided to customers. In addition, the method of displaying the level of busyness is just an example; for example, the changes in the level of busyness can also be displayed in a chart, or it can be displayed in a score, etc.

[0233] As described above, the data processing device 100 can acquire and output prediction data including the prediction results of the user's next consumption behavior based on the usage data of users of the restaurant store related to the use of the store. The usage data can include past usage data related to consumption behavior during past use or next usage data related to the next use plan. As a result, the next consumption behavior of users of the restaurant store can be predicted with higher accuracy. In addition, since the prediction data can be used to output support data or future situation data, the store can be operated more efficiently.

[0234] Alternatively, the processing in this embodiment can also be implemented by software. Furthermore, the software can be distributed via software download or the like. Alternatively, the software can be recorded on a recording medium such as an optical disc for distribution. The software implementing the data processing apparatus 100 in this embodiment is the following program.That is, the program uses a computer with access to the user data storage unit as a data acquisition unit, a prediction unit, and a prediction data output unit. The user data storage unit stores usage data related to the user's use of the restaurant in correspondence with the user identifier that identifies the user. The usage data acquisition unit acquires the user's usage data from the user data storage unit. The prediction unit acquires prediction data based on the usage data, including prediction results of the user's next consumption behavior. The prediction data output unit outputs the prediction data.

[0235] (Others)

[0236] FIG15 is a general diagram of the computer system 800 in the above embodiment. FIG16 is a block diagram of the computer system 800.

[0237] These figures show the structure of the computer, which executes the program described in this specification to implement the data processing device, etc., of the above embodiment. The above embodiment can be implemented by computer hardware and computer programs executed thereon.

[0238] The computer system 800 includes a computer 801 with an optical disc drive, a keyboard 802, a mouse 803, and a monitor 804.

[0239] In addition to the optical disc drive (ODD) 8012, the computer 801 also includes an MPU 8013, a bus 8014 connected to the optical disc drive 8012, a ROM 8015 for storing programs such as boot programs, a RAM 8016 connected to the MPU 8013 for temporarily storing application program instructions and providing temporary storage space, and a hard disk (HDD) 8017 for storing application programs, system programs, and data. Although not shown here, the computer 801 may also include a network card that provides a connection to a LAN.

[0240] The program that enables the computer system 800 to perform the functions of the data processing apparatus, etc., of the above-described embodiments is stored in the optical disc 8101, or may be inserted into the optical disc drive 8012 and further transferred to the hard disk 8017. Alternatively, the program may be sent to the computer 801 via a network (not shown) and stored in the hard disk 8017. The program is loaded into RAM 8016 during execution. The program can be loaded directly from optical disc 8101 or the network.

[0241] The program does not necessarily include an operating system (OS) or third-party programs that enable the computer 801 to perform the functions of the data processing device, etc., described in the above embodiments. The program may only include instruction portions that call appropriate functions (modules) in a controlled manner to obtain the desired results. How the computer system 800 operates is well known, and its detailed description is omitted.

[0242] In addition, in the above program, the data transmission step or data reception step does not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0243] Furthermore, the number of computers executing the above program can be one or more. That is, centralized processing or distributed processing can be performed.

[0244] Furthermore, in the above embodiments, two or more components existing in a device can be physically implemented through a single medium.

[0245] In the above embodiments, each component can be configured using dedicated hardware, or components that can be implemented using software can be implemented by executing a program. For example, each component can be implemented by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. During execution, the program execution unit can execute the program while accessing the storage unit or the recording medium. In addition, the program can be executed by downloading from a server or the like, or by reading a program recorded on a predetermined recording medium (e.g., optical disc, magnetic disk, semiconductor memory, etc.). In addition, the program can also be used as a program constituting a program product. Furthermore, the number of computers executing the program can be one or more. That is, centralized processing or distributed processing can be performed.

[0246] Furthermore, in the above embodiments, each process (each function) can be implemented centrally by a single device (system), or it can be implemented distributedly by multiple devices (in this case, the system consisting of multiple devices described in the distributed processing specification 22 / 24 pages 26 CN 121039688 A can be managed as a single "device").

[0247] Furthermore, in the above embodiments, data exchange between components can be performed, for example, when the two components performing the data exchange are physically different, by one component outputting data and the other component receiving data, or when the two components performing the data exchange are physically the same, by transferring from the processing stage corresponding to one component to the processing stage corresponding to the other component.

[0248] Furthermore, in the above embodiments, data related to the processes performed by each component, such as data received, acquired, selected, generated, sent, and received by each component, and data such as thresholds, formulas, and addresses used by each component in the processing, can be temporarily or permanently stored in a recording medium (not shown), even if not explicitly described in the above description. Additionally, each component or a storage unit (not shown) can also store data in the recording medium (not shown). In addition, each component or readout unit (not shown) may also read data from the recording medium (not shown).

[0249] Furthermore, in the above embodiment, when the data used by each component, such as thresholds, addresses, and various settings used by each component in processing, can be changed by the user, the user may appropriately change these data, or may not change them, even if not explicitly stated in the above description.When a user is able to change this data, the change can be achieved, for example, through a receiving unit (not shown) that accepts a change instruction from the user and a change unit (not shown) that changes the data according to the change instruction. The receiving unit (not shown) accepts the change instruction, for example, by accepting data from an input device, by receiving data transmitted via a communication line, or by accepting data read from a predetermined recording medium.

[0250] This disclosure is not limited to the above embodiments, and various modifications can be made, which are also included within the scope of this disclosure.

[0251] Embodiments can also be constructed by appropriately combining the above embodiments or variations. In addition, some components or functions in the above embodiments or variations may be omitted.

[0252] (Structure)

[0253] The structure of the data processing apparatus according to the above embodiments can be as follows.

[0254] That is, the data processing apparatus includes: a user data storage unit that stores usage data related to the user's use of the restaurant in a corresponding manner with a user identifier that identifies the user; a usage data acquisition unit that acquires the user's usage data from the user data storage unit; a prediction unit that acquires prediction data including a prediction result of the user's next consumption behavior based on the usage data; and a prediction data output unit that outputs the prediction data. Here, the data processing apparatus includes an object behavior data acquisition unit that acquires object behavior data related to the user's current behavior at the restaurant, i.e., a predetermined recorded object behavior that is different from the consumption behavior, and stores the acquired object behavior data as the usage data in the user data storage unit in a corresponding manner with a user identifier that identifies the user.

[0255] In addition, in the above structure, the object behavior data acquisition unit can be configured to acquire object behavior data based on the result that an anomaly detection unit used in the restaurant detects that an anomaly has occurred in each seat used by the user.

[0256] With the above structure, object behavior data of the user using the seat can be stored based on the result that an anomaly has occurred in each seat.

[0257] In addition, with the above structure, the restaurant can provide self-service goods prepared in advance for users to consume, as well as ordered goods provided to users according to the order each time an order is received from a user. The prediction data can include data related to the consumption of ordered goods.

[0258] With the above structure, prediction data related to the consumption of ordered goods can be output.

[0259] In addition, with the above structure, the data related to the consumption of ordered goods can be, for example, the absolute quantity of ordered goods, the ratio of the consumption of ordered goods to the consumption of self-service goods, the ratio of the consumption of ordered goods to the total consumption, or the frequency of the provision of ordered goods.

[0260] With the above structure, prediction data that can grasp the degree to which ordered goods need to be provided can be output.

[0261] Furthermore, in the above structure, the restaurant is a conveyor belt sushi restaurant, which includes a first conveyor device and a second conveyor device. The first conveyor device has a conveyor path that circulates within the store and provides self-service goods. The second conveyor device is different from the first conveyor device and can transport ordered goods to a confirmed delivery destination. The data acquisition unit can acquire data related to the user's operation performed by the second conveyor device as usage data.

[0262] With the above structure, prediction data can be output more accurately based on the data related to the operation of the second conveyor device.

[0263] As described above, the data processing apparatus according to this disclosure has the effect of being able to predict the next consumption behavior of users of a restaurant based on usage data, and is very useful as a data processing apparatus, etc. Instruction manual, page 24 / 24; Figure 1 (CN 121039688 A); Figure 2 (CN 121039688 A); Figure 3 (CN 121039688 A); Figure 4 (CN 121039688 A); Figure 5 (CN 121039688 A); Figure 6 (CN 121039688 A); Figure 7 (CN 121039688 A); Figure 8 (CN 121039688 A); Figure 9 (CN 121039688 A); Figure 10 (CN 121039688 A); Figure 11 (CN 121039688 A). Figure 12. Appendix to the instruction manual, page 10 / 13, 38 CN 121039688 A. Figure 13. Figure 14. Appendix to the instruction manual, page 11 / 13, 39 CN 121039688 A. Figure 15. Figure 16. Appendix to the instruction manual, page 12 / 13, 40 CN 121039688 A. Figure 17. Appendix to the instruction manual, page 13 / 13, 41 CN 121039688 A.

Claims

1. A store support method, implemented by a processor in a data processing device installed in a restaurant store, characterized in that, in, The usage data is stored in the user data storage unit in correspondence with the user identifier that identifies the user. The usage data is usage data related to the user's use of the store, including past usage data related to the user's consumption behavior in the past. Based on the usage data obtained from the user data storage unit, predictive data is obtained, including prediction results of the consumption behavior of users visiting the store. Based at least on the number of users in the store, obtain store status data indicating the store's busyness. Based on the predicted data obtained from users visiting the store and the store status data, seating guidance data is obtained to direct users to reserved seats within the store as supporting data that can be used for store operations. The seat guidance data is output to the notification device used to guide users visiting the store to the reserved seats.

2. The store support method as described in claim 1, characterized in that, in, The seating guidance data is acquired so that the locations of users dining in the store are dispersed after a predetermined time.

3. The store support method as described in claim 1 or 2, characterized in that, in, The restaurant has two or more seating groups, each consisting of two or more seats within the establishment. The seat guidance data is acquired so that each seat in the identified seat group becomes available after a predetermined time.

4. The store support method as described in any one of claims 1-3, characterized in that, in, The restaurant has two or more seating groups, each consisting of two or more seats within the establishment. The seating guidance data is also obtained based on load data related to store operational load. The load data is obtained based on at least one of the following: the quantity of goods ordered for each seat group, the ordering frequency, the future utilization rate of each seat in each seat group, and the number of events requiring staff intervention.

5. The store support method as described in claim 4, characterized in that, in, When there are two or more seating groups as the destination for users visiting the store, a load score representing the load assuming the users have been directed to each seating group is obtained as the load data for each seating group. Obtain the seating guidance data to direct users visiting the store to the seating group with the lowest score.

6. The store support method as described in claim 5, characterized in that, in, The notification device includes a staff notification device for notifying the store staff. The score is output to a staff notification device so that the staff notification device associates the score with the corresponding seat group and notifies the staff.

7. A data processing apparatus, characterized in that, include: The user data storage unit stores usage data corresponding to user identifiers that identify users. The usage data is usage data related to the user's use of the restaurant, including past usage data related to the user's consumption behavior in the past. The prediction unit acquires prediction data, including predictions of the user's next consumption behavior, based on the usage data obtained from the user data storage unit. The store status data acquisition department acquires store status data related to the status of a store. The support data acquisition unit acquires support data that can be used for the operation of the store based on the prediction data acquired by the prediction unit for users visiting the store; as well as The support data output unit outputs the support data.

8. The data processing apparatus as described in claim 7, characterized in that, This includes: The consumer data acquisition unit acquires consumer data related to the current consumption behavior of users visiting the store, and stores the acquired consumer data as past usage data in the user data storage unit, corresponding to the user identifier that identifies the user.

9. The data processing apparatus as described in claim 7 or 8, characterized in that, in, The usage data includes next-use data related to the next use reservation, entered by users who plan to use the store.

10. The data processing apparatus according to any one of claims 7-9, characterized in that, in, The prediction unit obtains prediction data, including predictions of the user's next consumption behavior, based on usage data of one user in a group consisting of two or more users and population data related to the number of users in the group.

11. The data processing apparatus according to any one of claims 7-10, characterized in that, in, The prediction unit acquires prediction data based on usage data, including prediction results of the group's next consumption behavior. The usage data is the usage data of each user in a group containing two or more users, including group data related to the group containing users who have used the service in the past and past usage data related to the group's consumption behavior.

12. The data processing apparatus according to any one of claims 7-11, characterized in that, This includes: The seat data acquisition unit acquires seat data, including data identifying the seats used by users visiting the store, and stores the acquired seat data in a user data storage unit in correspondence with the user identifier that identifies the user.

13. The data processing apparatus according to any one of claims 7-12, characterized in that, This includes: The object behavior data acquisition unit acquires object behavior data related to the current behavior of users visiting the store, which is different from the predetermined object behavior of consumption behavior, and stores the acquired object behavior data as the usage data in the user data storage unit in correspondence with the user identifier that identifies the user.

14. The data processing apparatus according to any one of claims 7-13, characterized in that, in, The prediction unit is configured to obtain prediction data, including prediction results of the user's future consumption behavior in the current usage opportunity, based on the usage data related to the user's consumption behavior in past usage opportunities and the usage data related to the user's past consumption behavior in the current usage opportunity.

15. The data processing apparatus according to any one of claims 7-14, characterized in that, in, The restaurant has two or more seating groups, each consisting of two or more seats within the establishment. The support data acquisition unit acquires load data related to the store's operational load for each seating group based on the prediction data acquired by the prediction unit for users visiting the store and the store status data, and acquires the support data based on the load data.

16. The data processing apparatus according to any one of claims 7-15, characterized in that, in, The support data acquisition unit acquires seat guidance data related to the seats of users who are guided to visit the store as the support data.

17. The data processing apparatus as claimed in claim 16, characterized in that, in, The support data output unit outputs data representing the number of people in a group that includes the user, through a device that outputs a destination corresponding to the seat of the user who was guided to the store.

18. The data processing apparatus according to any one of claims 7-17, characterized in that, This includes: The future situation data acquisition unit uses the predicted data acquired for users currently using a store and the predicted data acquired for users in the future using the store to acquire future situation data related to the future situation within the store; and The future data output unit outputs the future status data in a manner that allows staff to verify it.

19. A program, characterized in that, The processor of the computer with access to the user data storage unit performs the following operation, wherein the user data storage unit stores usage data corresponding to user identifiers that identify the user, the usage data being usage data related to the user's use of the restaurant, including past usage data related to the user's past consumption behavior. The operation is as follows: The user's usage data is obtained from the user data storage unit. Based on the aforementioned usage data, predictive data is obtained, including predictions of the user's next consumption behavior. Output the predicted data.

20. A store system, characterized in that, include: Data processing device; A notification device for informing store staff; At least one processor; as well as At least one memory for recording computer program code, wherein: By executing the computer program code, the at least one processor causes the data processing device to perform the following operations: The usage data is stored in the user data storage unit in correspondence with the user identifier that identifies the user. The usage data is related to the user's use of the restaurant, including past usage data related to the user's consumption behavior during past use. Based on the usage data obtained from the user data storage unit, predictive data is obtained, including prediction results of the consumption behavior of users visiting the store. At least based on the number of users in the store, data indicating the store's busyness should be obtained. Based on the predicted data obtained from users visiting the store and the store status data, seating guidance data is obtained to direct users to reserved seats within the store as supporting data that can be used for store operations. The seat guidance data is output to the notification device. And the notification device performs the following operations: When the seat guidance data is entered, the staff is notified to guide the users visiting the store to the reserved seats.

Images