Menu creation support device, method, and program

Abstract

To provide a technique to prevent menus from becoming routine.SOLUTION: A menu creation support device acquires a collection of menu information each including at least one dish, and in creating a first menu schedule in a predetermined period on the basis of the acquired collection of menu information, creates a plurality of menu schedule candidates first. The menu creation support device calculates, for each of the created menu schedule candidates, the similarity of dishes between the plurality of pieces of menu information constituting the menu schedule candidate, selects, from among the plurality of menu schedule candidates, the menu schedule candidate satisfying a similar condition to which the similarity of dishes is set in advance, and creates the first menu schedule on the basis of the selected menu schedule candidate.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] One aspect of this invention relates to a menu creation support device, method, and program for assisting in creating a menu of meals provided to users, for example, in various facilities.

Background Art

[0002] For example, when creating a menu of meals provided to inpatients and residents in hospitals, nursing homes, etc., various requirements such as nutritional balance, diet therapy by disease, allergy countermeasures, nutritional components of ingredients, cooking methods, cooking time, countermeasures against monotony, seasonal and event menus, and balance of taste and appearance need to be considered. However, generally, the work of creating a menu is often carried out by a registered dietitian or the like based on their knowledge, experience, and intuition, which places a heavy burden on the registered dietitian and is difficult to inherit by a successor registered dietitian.

[0003] Therefore, a system has been proposed that uses a computer to generate a menu for a predetermined period to be proposed to users. This system generates a group of meal sets including a plurality of meal sets each containing a plurality of dishes, and generates a menu for a predetermined period based on the generated group of meal sets (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional system, the types of menus created are insufficient, and similar dishes often continue, so there is still a possibility of menu monotony.

[0006] This invention was made in view of the above circumstances, and in one aspect, aims to provide a technology that prevents menus from becoming monotonous. [Means for solving the problem]

[0007] To solve the above problems, a first aspect of the menu creation support device or menu creation support method according to the present invention acquires a set of menu information, each containing at least one dish, and when creating a first menu schedule for a predetermined period based on the acquired set of menu information, first creates a plurality of menu schedule candidates. Then, for each of the created menu schedule candidates, among the plurality of menu information constituting the menu schedule candidate... The aforementioned Similarity of dishes Total The similarity of the dishes is calculated from among the multiple menu schedule candidates. Total is pre-configured If it falls below the threshold The system selects one of the aforementioned menu schedule candidates and then creates the first menu schedule based on the selected menu schedule candidate.

[0008] According to a first aspect of this invention, for example, the similarity of dishes between the menus offered each day over a week is calculated, and a weekly menu schedule is created using multiple menus whose calculated similarity is below a threshold. This prevents menus containing similar dishes from appearing consecutively or frequently within a week, thereby preventing the menu from becoming monotonous.

[0009] Furthermore, a first aspect of this invention is characterized in that, when conditions regarding the types of food are specified by the recipient of the menu schedule, a second menu schedule corresponding to the conditions of the types of food requested by the recipient is created by using a plurality of menu information constituting the first menu schedule as basic menu information, and changing some of the dishes included in this basic menu information to other dishes according to the conditions of the types of food.

[0010] Therefore, for example, if a user specifies "calorie-restricted diet" as a dietary requirement, it becomes possible to create a new menu schedule that accommodates this requirement without significantly altering the composition of the basic menu information created for healthy individuals. Consequently, it becomes possible to easily create and provide a new menu schedule that satisfies the dietary requirements requested by the user without causing a significant increase in cooking costs, etc. [Effects of the Invention]

[0011] In other words, according to the first aspect of this invention, it is possible to provide a technology that prevents menus from becoming monotonous. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 shows an example of the configuration of a system equipped with a menu creation support device according to the first embodiment of this invention. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of a menu creation support device according to the first embodiment of this invention. [Figure 3] Figure 3 is a block diagram showing an example of the software configuration of a menu creation support device according to the first embodiment of this invention. [Figure 4] Figure 4 is a flowchart showing an example of the processing procedure and content of the menu creation support process performed by the control unit of the menu creation support device shown in Figure 3. [Figure 5] Figure 5 is a diagram illustrating an example of the operation of the menu creation support process shown in Figure 4. [Figure 6] Figure 6 shows an example of the dish information and its attribute information used in the menu creation support process shown in Figure 4. [Figure 7] Figure 7 shows an example of a cooking group generated by the menu creation support process shown in Figure 4. [Figure 8] Figure 8 is a block diagram showing an example of the software configuration of a menu creation support device according to a second embodiment of the present invention. [Figure 9]FIG. 9 is a flowchart showing an example of the processing procedure and processing content of the menu creation support process executed by the control unit of the menu creation support device shown in FIG. 8. [Figure 10] FIG. 10 is a flowchart showing an example of the processing procedure and processing content of the menu schedule optimization process among the menu creation support processes shown in FIG. 9. [Figure 11] FIG. 11 is a diagram for explaining an operation example of the attribute information addition process among the menu creation support processes shown in FIG. 9. [Figure 12] FIG. 12 is a diagram showing an example of attribute information related to food. [Figure 13] FIG. 13 is a diagram for explaining an operation example of the menu creation process among the menu creation support processes shown in FIG. 9. [Figure 14] FIG. 14 is a diagram for explaining an operation example of the menu schedule candidate creation process among the menu creation support processes shown in FIG. 9. [Figure 15] FIG. 15 is a diagram for explaining an operation example of the menu schedule optimization process shown in FIG. 10. [Figure 16] FIG. 16 is a diagram showing an example of the similarity calculated in the menu schedule optimization process shown in FIG. 10. [Figure 17] FIG. 17 is a block diagram showing an example of the software configuration of the menu creation support device according to the third embodiment of this invention. [Figure 18] FIG. 18 is a flowchart showing an example of the processing procedure and processing content of the menu schedule simple optimization process among the menu creation support processes shown in FIG. 17.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, embodiments of this invention will be described with reference to the drawings. In addition, hereinafter, regarding the terms related to the menu, the menu schedule is defined as a combination of a plurality of menus, the menu includes a plurality of dishes, and the dish includes a plurality of foods or food ingredients, and the description will be made.

[0014] [First Embodiment] (Example configuration) (1) System Figure 1 shows an example of the configuration of a support system equipped with a menu creation support device SVA according to the first embodiment of this invention.

[0015] The support system according to the first embodiment includes a menu creation support device SVA that provides menu creation support services, and enables the transmission of information data via a network NW between the menu creation support device SVA and the database group DB1 to DBm, and between the menu creation support device SVA and user terminals UT1 to UTn.

[0016] The database group DB1 to DBm stores information such as past menu lists, lists of dishes, information about the ingredients that make up each dish, and recipe data. For example, it stores menu information managed by the nutritional food service management system and information defined in the Japanese Standard Tables of Food Composition by the Ministry of Education, Culture, Sports, Science and Technology.

[0017] User terminals UT1 to UTn are used by users receiving the menu creation support service and consist of, for example, personal computers. User terminals UT1 to UTn are used to request the menu creation support device SVA to create a menu schedule and to receive menu schedule information transmitted from the menu creation support device SVA in response to this request.

[0018] A network (NW) comprises, for example, a wide-area network centered on the internet, and an access network for accessing this wide-area network. The access network may, but is not limited to, a public data communication network using wireless technology or a LAN (Local Area Network).

[0019] (2) Menu creation support device SVA The menu planning support system (SVA) is comprised of a server computer, for example, located on the cloud or the web. Alternatively, the menu planning support system (SVA) may be comprised of a personal computer used by a system administrator.

[0020] Figures 2 and 3 are block diagrams showing examples of the hardware and software configurations of the menu creation support device SVA, respectively.

[0021] The menu creation support device SVA includes a control unit 1A that uses a hardware processor such as a Central Processing Unit (CPU), and a storage unit having a program storage unit 2A and a data storage unit 3A, and a communication interface (hereinafter referred to as I / F) unit 4A are connected to this control unit 1A via a bus 5A.

[0022] The communication interface unit 4A uses communication protocols defined in the network NW to send and receive information data between the database group DB1 to DBm and between the user terminals UT1 to UTn. The communication interface unit 4A can also communicate data with administrator terminals (not shown) used by system administrators, etc.

[0023] The program storage unit 2A is configured, for example, by combining a non-volatile memory that can be written to and read at any time, such as an SSD (Solid State Drive), and a non-volatile memory such as a ROM (Read Only Memory), and stores application programs necessary to execute various controls according to one embodiment, in addition to middleware such as an OS (Operating System). Hereafter, the OS and each application program will be collectively referred to as a program.

[0024] The data storage unit 3A combines, for example, a non-volatile memory such as an SSD that can be written to and read at any time, and a volatile memory such as RAM (Random Access Memory), as a storage medium. Its storage area includes a cooking information storage unit 31A, a cooking group learning model storage unit 32A, a combination storage unit 33A, a combination score learning model storage unit 34A, a combination score storage unit 35A, and a menu information storage unit 36A.

[0025] Of these, the cooking group learning model memory unit 32A stores a pre-trained learning model for generating cooking groups. The learning model for generating cooking groups is trained to cluster multiple input dishes based on their names, classify them into multiple cooking groups, and output the classification results.

[0026] The combination score learning model storage unit 34A stores a pre-trained learning model for calculating combination scores. The learning model for calculating combination scores is trained to output a score for a given combination of cooking groups, with a value corresponding to the number of times the dishes included in those cooking groups have appeared in past menus.

[0027] The control unit 1A includes, as processing functions necessary to carry out the first embodiment of this invention, a cooking information acquisition processing unit 11A, a cooking group generation processing unit 12A, a cooking group combination generation processing unit 13A, a combination score calculation processing unit 14A, a menu creation processing unit 15A, and a menu information transmission processing unit 16A.

[0028] The cooking information acquisition processing unit 11A acquires a set of cooking information from the database group DB1 to DBm and stores the acquired set of cooking information in the cooking information storage unit 31A. Each piece of cooking information includes at least information representing the name of the dish.

[0029] The dish group generation processing unit 12A uses the learning model for generating dish groups stored in the dish group learning model storage unit 32A to group the dish information stored in the dish information storage unit 31A with similar dish names, and stores the information representing the resulting dish group in the combination storage unit 33A. An example of the above dish information grouping process will be explained in detail in the operation example.

[0030] The cooking group combination generation processing unit 13A generates multiple cooking group combinations based on information representing multiple cooking groups stored in the combination storage unit 33A, and stores the generated cooking group combinations in the combination storage unit 33A in association with combination identification information (combination ID).

[0031] The combination score calculation processing unit 14A uses the learning model for calculating combination scores stored in the combination score learning model storage unit 34A to obtain a score for each combination of the multiple cooking groups, corresponding to the number of times each cooking group in the combination has appeared in past menus. The combination score calculation processing unit 14A then stores the combination score in the combination score storage unit 35A, associating it with the combination ID. An example of the above combination score calculation process will be explained in detail in the operation example.

[0032] The menu creation processing unit 15A reads the corresponding combination score from the combination score storage unit 35A for each combination of cooking groups, and extracts combinations of cooking groups whose read combination scores are equal to or greater than a threshold. The menu creation processing unit 15A then generates multiple combinations of cooking groups by selectively associating multiple cooking items one-to-one with each other within the extracted combinations of cooking groups, and stores these generated combinations of cooking items as menu information in the menu information storage unit 36A.

[0033] The menu information transmission processing unit 16A transmits multiple menu information stored in the menu information storage unit 36A to user terminals UT1 to UTn via the communication interface unit 4A.

[0034] (Example of operation) Next, we will explain an example of the operation of the menu creation support device SVA configured as described above.

[0035] Figure 4 is a flowchart showing an example of the processing procedure and content of the menu creation support process executed by the control unit 1A of the menu creation support device SVA.

[0036] (1) Gathering information on cooking In step S10, the control unit 1A of the menu creation support device SVA first accesses the database group DB1 to DBm via the communication I / F unit 4A under the control of the cooking information acquisition processing unit 11A, and collects cooking information managed as cooking masters in the database group DB1 to DBm and stores it in the cooking information storage unit 31A.

[0037] Figure 6(a) shows an example of collected food information, in which food information is represented by associating food codes with food names. Figure 6(b) shows an example of the category that the above food code represents, in which case each digit of the food code is associated with a category hierarchy.

[0038] (2) Creation of cooking groups In step S11, the control unit 1A of the menu creation support device SVA then performs the following process under the control of the cooking group generation processing unit 12A to group the cooking information into those with similar names using a learning model for cooking group generation.

[0039] In other words, the cooking group generation processing unit 12A first uses, for example, a large amount of cooking information stored in the cooking master and labels indicating the cooking groups to which it will be classified as training data to train a machine learning model such as a neural network to learn the relationships between dishes. Then, it stores the trained model, including the model parameters after training, in the cooking group learning model storage unit 32A.

[0040] The cooking group generation processing unit 12A then reads cooking information one by one from the cooking information storage unit 31A during the estimation phase and inputs it into the learning model for cooking group generation. The learning model for cooking group generation then performs a process to cluster the input cooking information based on its cooking name and classify it into cooking groups with similar names, and outputs the labels of the classified cooking groups, i.e., cooking group IDs.

[0041] The cooking group generation processing unit 12A stores the classified cooking information in the combination storage unit 33A, associating it with the cooking group ID output from the learning model for cooking group generation. As a result, the combination storage unit 33A stores a set of cooking information classified into each of the multiple cooking group IDs, each associated with that cooking group.

[0042] Figure 5(a) shows an example of the operation of the above-mentioned dish group generation process, in which dishes 1 to 9 are classified into three dish groups: A, B, and C. Figure 7 shows an example of the results of the grouping process, with dishes classified into fish group A and fish group B, respectively.

[0043] (3) Calculation of scores for combinations of cooking groups In step S12, the control unit 1A of the menu creation support device SVA, under the control of the cooking group combination generation processing unit 13A, combines multiple cooking groups stored in the combination storage unit 33A in pairs to generate multiple pairs of cooking group combinations. The generated cooking group combinations are then stored in the combination storage unit 33A in association with combination identification information (combination ID).

[0044] Next, the control unit 1A of the menu creation support device SVA, under the control of the combination score calculation processing unit 14A, performs the following process to calculate the combination score for each combination of the above-mentioned cooking groups.

[0045] In other words, the combination score calculation processing unit 14A first acquires information representing past menu performance from the database group DB1 to DBm during the learning phase. Then, using the combinations of the above-mentioned cooking groups and the number of times the dishes included in the cooking groups that make up the combination have appeared in past menus as training data, it trains a machine learning model such as a neural network to learn the relationships between cooking groups.

[0046] More specifically, the learning model is trained to output a combination score for each combination of cooking groups, with the value increasing as the frequency of appearance of the dishes included in that cooking group in past menus increases. The combination score calculation processing unit 14A then stores the learning model for calculating cooking groups, including the trained model parameters, in the combination score learning model storage unit 34A.

[0047] In the estimation phase, the combination score calculation processing unit 14A selects one combination of cooking groups from the combination storage unit 33A in step S13, and in step S14, inputs the selected cooking group into the learning model for calculating the combination score.

[0048] The learning model for calculating the combination score outputs a combination score that corresponds to the number of times the dishes included in the input group of dishes have appeared in past menus; in other words, the more times a dish has appeared in past menus, the higher the score value.

[0049] The combination score calculation processing unit 14A then stores the combination score output from the learning model for calculating the combination score in the combination score storage unit 35A, associating it with the combination ID of the cooking group.

[0050] Figure 5(b) shows an example of the operation of the above combination score calculation process. In this example, the score for the combination of Group A and Group B is calculated to be "90 points", the score for the combination of Group A and Group C is calculated to be "20 points", and the score for the combination of Group B and Group D is calculated to be "80 points".

[0051] (4) Menu creation The control unit 1A of the menu creation support device SVA then performs the menu creation process as follows, under the control of the menu creation processing unit 15A.

[0052] In other words, in step S15, the menu creation processing unit 15A first compares the score for the combination of cooking groups obtained by the combination score calculation processing unit 14A with a preset threshold. If the combination score is equal to or greater than the threshold as a result of the comparison, the menu creation processing unit 15A selects the combination of cooking groups for menu creation in step S16.

[0053] Next, in step S17, the menu creation processing unit 15A generates all possible combinations of dishes included in each of the selected dish groups by creating a one-to-one correspondence between the dishes contained in each dish group. Then, in step S18, the menu creation processing unit 15A stores all of the generated dish combinations as menu information in the menu information storage unit 36A. As a result, the menu information storage unit 36A stores not only existing dish combinations but also new dish combinations that have not been previously thought to exist as new menu information.

[0054] Figure 5(c) shows an example of the menu creation process described above. In this example, for combinations of Group A and Group B that are judged to have a combination score of 90 points or higher than the threshold, all combinations of dishes included in Group A and dishes included in Group B are created as menu information.

[0055] In step S19, the control unit 1A of the menu creation support device SVA determines whether it has finished selecting all combinations of cooking groups that were previously generated by the cooking group combination generation processing unit 13A. If, as a result of this determination, there are still unselected combinations of cooking groups, the control unit 1A returns to step S13. It then selects one of the next combinations of cooking groups and executes a series of processes from the calculation of the combination score to the creation of menu information as described above in steps S14 to S18. Thereafter, the calculation of the combination score and the creation of menu information are repeatedly executed for all unselected combinations of cooking groups.

[0056] (5) Sending menu information On the other hand, if it is determined in step S19 that the selection of all combinations of cooking groups has been completed, the control unit 1A of the menu creation support device SVA proceeds to step S20. Then, under the control of the menu information transmission processing unit 16A, it reads the set of menu information stored in the menu information storage unit 36A and transmits the read set of menu information from the communication I / F unit 4A to, for example, the user terminals UT1 to UTn that requested menu creation.

[0057] (effect) As described above, in the first embodiment, multiple pieces of dish information are grouped together based on similar dish names using a learning model for generating dish groups, combinations of these dish groups are generated, and for each generated combination of dish groups, a combination score is calculated using a learning model for calculating combination scores, based on the number of times the dish has appeared in past menu records. Combinations of dish groups whose calculated combination score is above a threshold are extracted, combinations of dishes are generated between those dish groups, and these generated combinations of dishes are provided to the user as menu information.

[0058] Therefore, it becomes possible to increase the amount of menu information that can be provided, which increases the menu options for users when creating a menu schedule, thereby preventing menu monotony. In addition, combinations of dish groups with high combination scores, that is, combinations of dish groups that have appeared frequently in past menu records, are extracted, and new dish combinations are created by associating dishes with each other within these dish groups. As a result, it becomes possible to provide users with new menus that feel less jarring compared to the menus that were previously provided, and that offer "dish combinations that seem like they should have existed but didn't" before.

[0059] [Second Embodiment] A second embodiment of this invention first adds attribute information to dish information, and then creates multiple menu information by combining dishes based on this attribute information. Then, multiple menu schedule candidates for, for example, one week are created by combining the created menu information, the degree of similarity between dishes in the menu information is calculated for each created menu schedule candidate, menu schedule candidates with a calculated dish similarity below a threshold are selected, and based on the selected menu schedule candidates, an optimized menu schedule is created so that menus containing similar dishes do not appear consecutively, and this is provided to the user.

[0060] (Example configuration) Figure 8 is a block diagram showing an example of the software configuration of the menu creation support device SVB according to the second embodiment of this invention. The hardware configuration of the menu creation support device SVB is the same as that shown in Figure 2 of the first embodiment, so it is not shown here.

[0061] The data storage unit 3B of the menu creation support device SVB includes a recipe data storage unit 31B, an information addition learning model storage unit 32B, a cooking information storage unit 33B, a menu creation learning model storage unit 34B, a menu information storage unit 35B, a menu schedule creation learning model storage unit 36B, a menu schedule candidate storage unit 37B, an optimization learning model storage unit 38B, and an optimized menu schedule storage unit 39B.

[0062] Of these, the information-adding learning model storage unit 32B stores data representing a pre-trained learning model for information addition. The learning model for information addition is a machine learning model, such as a neural network, that has been trained to estimate and output attribute information of a dish or food when a dish name and food name included in the dish information are input. Recipe datasets containing the attributes of the dish information and dish image data are used as training data.

[0063] The menu creation learning model storage unit 34B stores data representing a pre-trained menu creation learning model. The menu creation learning model is a machine learning model, such as a neural network, that has been trained to combine multiple dish information, taking into account their attribute information, when multiple dish information is input, in order to create menu information. As training data, for example, multiple dish information and their attribute information included in past menu history list data (menu master) are used.

[0064] The menu schedule creation learning model storage unit 36B stores data representing the menu schedule creation learning model. The menu schedule creation learning model is a machine learning model, such as a neural network, that has been trained to create a candidate menu schedule for one week by combining menu information that satisfies the constraints when multiple menu information and constraints are input. The training data used consists of multiple menu information and constraints included in the menu history list data. The constraints include nutritional value, cost, and variations (e.g., seasonality).

[0065] The optimization learning model memory unit 38B stores data representing a pre-trained optimization learning model. The optimization learning model is a machine learning model, such as a neural network, that has been trained to estimate the similarity of dish names when dish information is input. The training data used consists of a large number of dish names (for example, Japanese text data) and ground truth data of similarity between dish names.

[0066] The control unit 1B of the menu creation support device SVB includes, as control functions necessary for carrying out the second embodiment of this invention, a recipe data acquisition processing unit 11B, an attribute information addition processing unit 12B, a menu creation processing unit 13B, a menu schedule candidate creation processing unit 14B, a menu schedule optimization processing unit 15B, and a menu schedule transmission processing unit 16B.

[0067] The recipe data acquisition processing unit 11B acquires recipe datasets and cooking image datasets from the database group DB1 to DBm, and stores the acquired recipe datasets and cooking image datasets in the recipe data storage unit 31B.

[0068] The attribute information addition processing unit 12B uses the above-mentioned learning model for adding information to estimate attribute information corresponding to the input dish name and food, such as category and main / side dish classification, and stores the estimated attribute information added to the dish name in the dish information storage unit 33B.

[0069] The menu creation processing unit 13B inputs multiple pieces of dish information into a learning model for menu creation and retrieves menu information created by combining the multiple pieces of dish information from the learning model for menu creation.

[0070] The menu schedule candidate creation processing unit 14B inputs multiple menu information and constraints into a learning model for menu schedule creation, and obtains multiple menu schedule candidates for one week created by combining menu information that satisfies the above constraints from the learning model for menu schedule creation. The menu schedule candidate creation processing unit 14B stores the obtained multiple menu schedule candidates in the menu schedule candidate storage unit 37B.

[0071] The menu schedule optimization processing unit 15B inputs the dish information contained in the multiple menu information constituting each menu schedule candidate into the optimization learning model, and obtains an estimated similarity value of the dish information between the menu information and the sum of the similarity values ​​across all menu information from the optimization learning model. The menu schedule optimization processing unit 15B then selects menu schedule candidates whose sum of similarity is less than a threshold, and stores the selected menu schedule candidates as optimized menu schedules in the optimized menu schedule storage unit 39B.

[0072] The menu schedule transmission processing unit 16B reads the optimized menu schedule information from the optimized menu schedule storage unit 39B and transmits the read optimized menu schedule information to user terminals UT1 to UTn via the communication interface unit 4B.

[0073] (Example of operation) Next, we will explain the operation of the menu creation support device SVB, which is configured as described above.

[0074] Figure 9 is a flowchart showing an example of the processing procedure and content of the menu creation support process executed by the control unit 1B of the menu creation support device SVB.

[0075] (1) Adding attribute information to recipe information Prior to creating menu information, the control unit 1B of the menu creation support device SVB performs the following process to add attribute information to the dish information.

[0076] Specifically, in step S30, the control unit 1B first acquires a recipe dataset and a cooking image dataset from the database group DB1 to DBm under the control of the recipe data acquisition processing unit 11B, and temporarily stores the acquired recipe dataset and cooking image dataset in the recipe data storage unit 31B. The recipe dataset is a collection of recipe names linked to food items and categories. The cooking image dataset is a collection of cooking images linked to recipe names.

[0077] Next, in step S31, the control unit 1B performs the process of adding attribute information to the cooking information under the control of the attribute information addition processing unit 12B as follows.

[0078] In other words, the attribute information addition processing unit 12B first reads the recipe dataset and the dish image dataset from the recipe data storage unit 31B during the learning phase, and uses these as training data to train a machine learning model such as a neural network. As a result, a learning model is constructed that can estimate the category, main dish / side dish classification, and color scheme corresponding to the input dish information.

[0079] Once the learning model for adding attribute information is constructed, the attribute information adding processing unit 12B inputs, in the estimation phase, the dish names and food names included in multiple dish information obtained from, for example, the database group DB1 to DBm, into the learning model for adding information. The learning model for adding information estimates attribute information corresponding to the input dish names and food names, such as category, main dish / side dish classification, and color. The attribute information adding processing unit 12B adds the attribute information estimated by the learning model to the dish information and stores it in the dish information storage unit 33B.

[0080] Figure 11 shows an example of the operation of the attribute information addition processing unit 12B described above. Figure 12 shows an example of a recipe dataset that can be used to train the learning model for attribute information addition described above.

[0081] (2) Creation of menu information In step S32, the control unit 1B of the menu creation support device SVB then creates menu information using a learned model for menu creation under the control of the menu creation processing unit 13B as follows.

[0082] In other words, the menu creation processing unit 13B first uses the multiple dish information and attribute information stored in the dish information storage unit 33B as training data to train a machine learning model such as a neural network during the learning phase. As a result, a learning model for menu creation is constructed that, when dish information is input, creates menu information by combining dishes that differ in category, main / side dish classification, and color.

[0083] Next, when the estimation phase is set, the menu creation processing unit 13B retrieves a list of past menu records from the database group DB1 to DBm. The menu creation processing unit 13B then inputs the information of multiple dishes included in the retrieved list of past menu records into the menu creation learning model, and retrieves multiple menu information created by combining dishes with different categories, main / side dish classifications, and colors from this menu creation learning model. The retrieved multiple menu information is then stored in the menu information storage unit 35B.

[0084] Figure 13 shows an example of the operation of the menu creation process by the menu creation processing unit 13B.

[0085] (3) Creating a menu schedule In step S33, the control unit 1B of the menu creation support device SVB creates menu schedule candidates using a learning model for menu schedule creation, under the control of the menu schedule candidate creation processing unit 14B, as follows.

[0086] In other words, the menu schedule candidate creation processing unit 14B first trains a machine learning model, such as a neural network, in the learning phase, using multiple menu information included in the menu history list data, along with constraints such as nutritional value, cost, and variation (e.g., seasonality), as training data to create multiple menu schedule candidates for, for example, one week. Then, it stores the training model data for menu schedule creation, including the trained parameters, in the menu schedule creation training model storage unit 36B.

[0087] When the estimation phase is set, the menu schedule candidate creation processing unit 14B reads out multiple menu information stored in the menu information storage unit 35B and inputs it into the learning model for menu schedule creation. If the user specifies constraints at this time, these constraints are also input into the learning model for menu schedule creation. As a result, the learning model for menu schedule creation creates multiple menu schedule candidates for one week, combining multiple menu information so as to satisfy the above constraints.

[0088] The menu schedule candidate creation processing unit 14B stores multiple menu schedule candidates created by the learning model for menu schedule creation in the menu schedule candidate storage unit 37B.

[0089] Figure 14 shows an example of the process for creating the above menu schedule candidates.

[0090] (4) Optimization of menu schedule In step S34, the control unit 1B of the menu creation support device SVB then performs the following process to select an optimized menu schedule candidate from among multiple menu schedule candidates, under the control of the menu schedule optimization processing unit 15B, such that similar dishes do not appear consecutively or frequently.

[0091] In other words, the menu schedule optimization processing unit 15B first acquires a large amount of cooking information from the database group DB1 to DBm during the learning phase, and uses the correct data of the names of the dishes and the similarity between the dish names as training data to train a machine learning model such as a neural network. As a result, for example, when multiple dish names included in one week's worth of menu information are input, an optimization learning model is constructed that estimates the similarity between each dish name and the sum of this similarity for one week.

[0092] When the estimation phase is set, the menu schedule optimization processing unit 15B then uses a learning model for optimization to create an optimized menu schedule, as follows:

[0093] Figure 10 is a flowchart showing an example of the processing procedure and content of the optimization process performed by the menu schedule optimization processing unit 15B.

[0094] In other words, the menu schedule optimization processing unit 15B first selects one menu schedule candidate from the menu schedule candidate storage unit 37B in step S341. Subsequently, in steps S342 and S343, the menu schedule optimization processing unit 15B inputs multiple dish information contained in the multiple menu information constituting the selected menu schedule candidate into the optimization learning model. As a result, the optimization learning model estimates the similarity of the dish names of each of the input dish information, and further outputs the sum of these similarities for one week.

[0095] Next, in step S344, the menu schedule optimization processing unit 15B compares the total similarity for one week output from the optimization learning model with a threshold value to determine whether the total similarity is less than the threshold value. If the total similarity is less than the threshold value, the menu schedule optimization processing unit 15B proceeds to step S345, selects the menu schedule candidate as the optimized menu schedule, and stores it in the optimized menu schedule storage unit 39B.

[0096] Next, the menu schedule optimization processing unit 15B determines whether it has finished selecting all the menu schedule candidates stored in the menu schedule candidate storage unit 37B. If there are still menu schedule candidates that have not yet been selected, it returns to step S341. Then, it selects one of the next unselected menu schedule candidates from the menu schedule candidate storage unit 37B and performs the series of optimization processes in steps S342 to S345 on the selected menu schedule candidate.

[0097] Furthermore, even if it is determined in step S344 that the total similarity is not below the threshold, the menu schedule optimization processing unit 15B returns to step S341 and executes the series of optimization processes in steps S342 to S345 for the next unselected menu schedule candidate.

[0098] Thereafter, the menu schedule optimization processing unit 15B repeatedly executes the series of optimization processes described in steps S342 to S346 until it has finished optimizing all menu schedule candidates stored in the menu schedule candidate storage unit 37B.

[0099] Figure 15 shows an example of the operation of the dish similarity estimation process using the optimization learning model described above. Figure 16 shows an example of the dish similarity estimation result for a candidate menu schedule.

[0100] (5) Sending optimized menu schedule information In step S35, the control unit 1B of the menu creation support device SVB reads the optimized menu schedule information from the optimized menu schedule storage unit 39B under the control of the menu schedule transmission processing unit 16B, and transmits the read menu schedule information from the communication I / F unit 4B to the user terminals UT1 to UTn of the users who requested the creation of a menu schedule.

[0101] Furthermore, if multiple optimized menu schedule information is stored in the optimized menu schedule storage unit 39B, the menu schedule transmission processing unit 16B may select and transmit one menu schedule information with the smallest total similarity score from among the multiple menu schedule information, or it may transmit all of the multiple menu schedule information. Alternatively, it may select and transmit a certain number of menu schedule information from among the multiple menu schedule information, in order of increasing total similarity score.

[0102] (effect) As described above, in the second embodiment, attribute information is added to each of the multiple dish information items, and menu information is created by combining the multiple dish information items based on this attribute information. Then, multiple menu schedule candidates for, for example, one week are created by combining the created multiple menu schedule candidates, and the similarity of dishes between the menu information items is calculated for each created menu schedule candidate, and the sum of the calculated similarity for one week is calculated. Then, menu schedule candidates whose calculated sum of similarity is less than a threshold are selected, and the selected menu schedule candidates are sent as optimized menu schedules to the user terminals UT1 to UTn that requested the creation.

[0103] Therefore, according to the second embodiment, menu information is created by considering attribute information added to the cooking information, making it possible to create menu information that takes into account categories, main and side dish classifications, and color schemes.

[0104] Furthermore, the similarity of dishes between menu items is calculated for each menu schedule candidate, and menu schedule candidates whose total similarity value for one week is below a threshold are selected as menu schedules. This makes it possible to provide users with optimized menu schedules that do not contain similar dishes consecutively or frequently. Consequently, users can create a week's worth of menus based on the above-mentioned optimized menu schedule, thereby preventing menu monotony.

[0105] [Third Embodiment] In the third embodiment of this invention, when a user terminal sends a request for a menu schedule specifying a type of meal, such as a low-salt diet or a low-calorie diet, the system uses a menu schedule optimized in the second embodiment so that the menus are not consecutive as a base menu, and then modifies some of the cooking information constituting the base menu according to constraints corresponding to the requested type of meal to create a menu schedule corresponding to the requested type of meal and provides it to the user.

[0106] (Example configuration) Figure 17 is a block diagram showing an example of the software configuration of the menu creation support device SVC according to the third embodiment of this invention. In Figure 17, the same reference numerals are used for parts that are the same as those in Figure 8, and detailed explanations are omitted. The hardware configuration of the menu creation support device SVC is the same as that in Figure 2, so it is not shown.

[0107] The data storage unit 3C of the menu creation support device SVC includes, as shown in Figure 8, a recipe data storage unit 31B, an information-adding learning model storage unit 32B, a cooking information storage unit 33B, a menu creation learning model storage unit 34B, a menu information storage unit 35B, a menu schedule creation learning model storage unit 36B, a menu schedule candidate storage unit 37B, an optimization learning model storage unit 38B, and an optimized menu schedule storage unit 39B, as well as a simplified optimized menu schedule storage unit 30C.

[0108] The simplified optimized menu schedule storage unit 30C is used to store menu schedule information that has been simplified and optimized according to the type of meal.

[0109] The control unit 1C of the menu creation support device SVC includes, in addition to the recipe data acquisition processing unit 11B, attribute information addition processing unit 12B, menu creation processing unit 13B, menu schedule candidate creation processing unit 14B, menu schedule optimization processing unit 15B, and menu schedule transmission processing unit 16B shown in Figure 8, a simplified optimization processing unit 11C, which is a control function unit necessary for implementing the third embodiment of this invention.

[0110] When a user sends a request from a user terminal UT1 to UTn to create a menu schedule specifying a type of diet, such as a low-salt diet or a low-calorie diet, the simplified optimization processing unit 11C reads an optimized menu schedule stored in the optimized menu schedule storage unit 39B, uses the read menu schedule as a base menu, and modifies some of the cooking information included in the multiple menu information constituting this menu schedule according to the constraints corresponding to the above-mentioned diet type, thereby creating a simplified optimized menu schedule.

[0111] (Example of operation) Next, we will explain an example of the operation of the menu creation support device SVC configured as described above.

[0112] Figure 18 is a flowchart showing an example of the contents of a processing procedure manual for the menu creation support process executed by the control unit 1C of the menu creation support device SVC according to the third embodiment of this invention. In Figure 18, the same reference numerals are used for parts that are the same as those in Figure 9, and detailed explanations are omitted.

[0113] The control unit 1C of the menu creation support device SVC, under the control of the simplified optimization processing unit 11C, determines in step S40 whether or not it has received a request to create a menu schedule specifying the type of food from user terminals UT1 to UTn. If it determines that it has received a request to create a menu schedule specifying the type of food, the simplified optimization processing unit 11C proceeds to step S41 and performs the simplified optimization process of the menu schedule as follows.

[0114] In other words, the simplified optimization processing unit 11C reads the optimized menu schedule from the optimized menu schedule storage unit 39B as basic menu information. Then, using this menu schedule as the base menu, it changes some of the dish information included in the multiple menu information constituting this menu schedule to other dish information that satisfies the constraints corresponding to the specified food type.

[0115] For example, suppose "calorie-restricted diet" is specified as the meal type. In this case, the simplified optimization processing unit 11C, in accordance with the constraints prepared in advance for "calorie-restricted diet," extracts the food information included in the multiple menu information constituting the menu schedule in which the calories exceed the upper limit defined by the constraints. Then, it reads the food information that satisfies the constraints from the multiple food information stored in the food information storage unit 33B, and changes the extracted high-calorie food information to the read low-calorie food information.

[0116] The simplified optimization processing unit 11C stores the modified menu schedule, along with a food type ID representing low calories, in the simplified optimization menu schedule storage unit 30C.

[0117] The simplified optimization processing unit 11C performs the simplified optimization processing described above for each menu schedule stored in the optimized menu schedule storage unit 39B. If all the food information included in the multiple menu information constituting the menu schedule satisfies the food type constraints, the food information modification process does not need to be performed, or the information may be changed to food information with lower calories.

[0118] In step S35, the control unit 1C of the menu creation support device SVC reads the menu schedule information, which has been simply optimized to correspond to the type of meal, from the simplified optimized menu schedule storage unit 30C under the control of the menu schedule transmission processing unit 16B, and transmits the read menu schedule information from the communication I / F unit 4C to the requesting user terminals UT1 to UTn.

[0119] (effect) As described above, in the third embodiment, when a user sends a request for a menu schedule specifying a type of diet, such as a low-salt diet or a low-calorie diet, the menu schedule stored in the optimized menu schedule storage unit 39B is used as the base menu, and the cooking information included in the menu information constituting this base menu that does not satisfy the constraints of the above-mentioned diet is changed to other cooking information that does satisfy the constraints of the above-mentioned diet, thereby creating a menu schedule that corresponds to the request for the above-mentioned diet.

[0120] Therefore, it becomes possible to create menu schedules that meet the demand for specific food types with relatively simple processing, without significantly altering the base menu. Consequently, it becomes possible to create and provide new menu schedules that meet the food type requirements requested by users without causing a significant increase in cooking costs.

[0121] [Other embodiments] (1) In the second embodiment, multiple menu information is created based on cooking information based on past menu records stored in the database group DB1 to DBm, and menu schedule candidates are created based on this menu information. However, the embodiment is not limited to this, and menu schedule candidates may be created using a larger number of menu information created by the menu creation support device SVA in the first embodiment.

[0122] (2) The configuration, processing procedures, and processing contents of each control function unit of the menu creation support device, the period for creating a menu schedule, etc., can be modified without departing from the spirit of this invention.

[0123] Although several embodiments of this invention have been described in detail above, the above description is merely illustrative in all respects of this invention. Needless to say, various improvements and modifications can be made without departing from the scope of this invention. In other words, when implementing this invention, specific configurations may be adopted as appropriate depending on the embodiment.

[0124] In short, this invention is not limited to the embodiments described above, and the components can be modified and implemented in practice without departing from the gist of the invention. Furthermore, various inventions can be formed by appropriately combining the multiple components disclosed in the embodiments described above. For example, some components may be deleted from all the components shown in the embodiments. Moreover, components from different embodiments may be appropriately combined. [Explanation of Symbols]

[0125] SVA, SVB, SVC... Menu creation support devices DB1~DBm...Database group UT1~UTn…User terminals NW...Network 1A, 1B, 1C… Control Units 2A, 2B, 2C... Program memory units 3A,3B,3C…Data storage section 4A, 4B, 4C…Communication I / F section 5A... Bus 11A…Cooking Information Acquisition Processing Unit 12A...Cooking Group Generation Processing Unit 13A...Cooking Group Combination Generation Processing Unit 14A...Combination score calculation processing unit 15A... Menu creation processing unit 16A... Menu Information Transmission Processing Unit 11B... Recipe data acquisition processing unit 12B...Attribute Information Addition Processing Unit 13B... Menu Creation Processing Section 14B... Menu Schedule Candidate Creation Processing Unit 15B... Menu Schedule Optimization Processing Unit 16B... Menu Schedule Transmission Processing Unit 11C...Simplified Optimization Processing Unit 31A…Cooking information storage unit 32A…Cooking Group Learning Model Memory Unit 33A... Combinatorial memory unit 34A... Combinatorial score learning model memory unit 35A...Combination score storage unit 36A... Menu information storage unit 31B... Recipe data storage unit 32B... Information-adding learning model memory unit 33B...Cooking information storage section 34B...Memory unit for learning model for menu creation 35B... Menu information storage unit 36B...Memory unit for learning model for menu schedule creation 37B... Menu schedule candidate memory unit 38B... Optimization learning model memory unit 39B...Optimized menu schedule memory unit 30C...Simple Optimized Menu Schedule Storage Unit

Claims

1. A first processing unit that obtains a set of menu information, each containing at least one dish, A second processing unit that, when creating a first menu schedule for a predetermined period based on the set of menu information, creates multiple menu schedule candidates and calculates the sum of the similarity scores of the dishes among the multiple menu information constituting each of the created menu schedule candidates, A third processing unit selects a menu schedule candidate from among a plurality of menu schedule candidates such that the sum of the similarity scores of the dishes is less than a predetermined threshold, and creates the first menu schedule based on the selected menu schedule candidate. A menu creation support device equipped with the following features.

2. The system further comprises a fourth processing unit for obtaining constraints for the dishes included in the menu information, including at least one of seasonality, nutritional value, and unit price. The second processing unit generates a plurality of menu schedule candidates by combining the menu information including the dishes that satisfy the constraints, The third processing unit selects from a plurality of menu schedule candidates such that the sum of the similarity scores of the dishes is less than the threshold, and creates the first menu schedule using the selected combination of menu information. The menu creation support device according to claim 1.

3. A fifth processing unit that obtains conditions regarding the type of food requested by the user, A sixth processing unit takes the multiple menu information constituting the first menu schedule as basic menu information, changes some of the dishes included in the basic menu information to other dishes according to the conditions relating to the type of food, and uses the modified menu information to create a second menu schedule that corresponds to the conditions relating to the type of food requested by the user. The menu creation support device according to claim 1, further comprising the above.

4. The fifth processing unit acquires information representing nutritional restrictions as conditions related to the type of food, The sixth processing unit, based on information representing the nutrition of the dishes included in the basic menu information, changes a portion of the dishes included in the basic menu information to other dishes that satisfy the nutritional restrictions. The menu creation support device according to claim 3.

5. A method for supporting menu creation performed by an information processing device, The process of each obtaining a set of menu information that includes at least one dish, When creating a first menu schedule for a predetermined period based on the set of menu information, the process involves creating multiple menu schedule candidates and calculating the sum of the similarity scores of the dishes among the multiple menu information constituting each of the created menu schedule candidates, The process of selecting a menu schedule candidate from among multiple menu schedule candidates such that the sum of the similarity scores of the dishes is less than a predetermined threshold, and creating the first menu schedule based on the selected menu schedule candidate. A menu creation support method equipped with the following features.

6. The process of obtaining the requirements regarding the type of food requested by the user, The process involves using the multiple menu information constituting the first menu schedule as basic menu information, changing some of the dishes included in the basic menu information to other dishes according to conditions relating to the type of food, and using the modified menu information to create a second menu schedule that corresponds to the conditions relating to the type of food requested by the user. The menu creation support method according to claim 5, further comprising the above.

7. A program that causes a processor in a menu creation support device to execute a process performed by a processing unit in a menu creation support device according to any one of claims 1 to 4.

Images