Meal proposal system, meal proposal method, and program

Abstract

A meal proposal system (1) comprises one or more processors (110). The one or more processors acquire held foodstuff information relating to one or more held foodstuffs, meal candidate information indicating a plurality of meal candidates, and external information stored in an external device, and estimate a user's shopping motivation. When the shopping motivation is estimated to be high, the one or more processors (i) determine, from the plurality of meal candidates, one or more first meal candidates including at least one foodstuff selected from all kinds of foodstuffs, and (ii) output first presentation information including the determined one or more first meal candidates. When the shopping motivation is estimated to be low, the at least one processors (i) determine, from the plurality of meal candidates, one or more second meal candidates including at least one held foodstuff selected from the one or more held foodstuffs, and (ii) outputs second presentation information including the determined one or more second meal candidates.

Description

Meal suggestion system, meal suggestion method, and program

[0001] The present disclosure relates to a meal suggestion system, a meal suggestion method, and a program.

[0002] Patent Literature 1 discloses a technology that suggests one or more recipes that include ingredients owned by a user from among a plurality of recipes based on inventory information of ingredients owned by the user. This technology aims to reduce food waste by suggesting recipes that prioritize ingredients that have been purchased recently or whose expiration date is approaching.

[0003] Japanese Patent Application Laid-Open No. 2022-074812

[0004] The present disclosure provides a meal suggestion system and the like that can encourage a user to consume food in a planned manner according to the user's shopping motivation.

[0005] A meal suggestion system according to one aspect of the present disclosure includes one or more processors, which acquire held food information regarding one or more held foods that are foods held by a user, meal candidate information indicating a plurality of meal candidates, and external information stored in an external device, analyze the external information to estimate the user's willingness to go out and shop, and if the result of the estimation of shopping desire shows that the shopping desire is high, (i) determine one or more first meal candidates from the plurality of meal candidates, the first meal candidates including at least one food selected from all types of food, and (ii) output first presentation information including the determined one or more first meal candidates, and if the result of the estimation of shopping desire shows that the shopping desire is low, (i) determine one or more second meal candidates from the plurality of meal candidates, the second meal candidates including at least one held food selected from the one or more held foods, and (ii) output second presentation information including the determined one or more second meal candidates.

[0006] Furthermore, a meal suggestion method according to one aspect of the present disclosure is a meal suggestion method executed by one or more processors, which acquires held food information regarding one or more held foods that are foods held by a user, meal candidate information indicating a plurality of meal candidates, and external information stored in an external device, analyzes the external information to estimate the user's willingness to go out and shop, and if the result of the estimation of shopping desire shows that the user's shopping desire is high, (i) determines one or more first meal candidates from the plurality of meal candidates, the first meal candidates including at least one food selected from all types of food, and (ii) outputs first presentation information including the determined one or more first meal candidates, and if the result of the estimation of shopping desire shows that the user's shopping desire is low, (i) determines one or more second meal candidates from the plurality of meal candidates, the second meal candidates including at least one held food selected from the one or more held foods, and (ii) outputs second presentation information including the determined one or more second meal candidates.

[0007] These general or specific aspects may be realized by a device, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or by any combination of a device, an integrated circuit, a computer program, and a non-transitory recording medium.

[0008] The meal suggestion system and the like in the present disclosure can encourage a user to consume food in a planned manner according to the user's shopping motivation.

[0009] FIG. 1 is a diagram illustrating an overview of a meal suggestion system according to an embodiment. FIG. 2 is a block diagram illustrating an example of the configuration of a meal suggestion device according to an embodiment. FIG. 3 is a flowchart illustrating an example of processing executed by a processor. FIG. 4 is a diagram illustrating an example of shopping information used to calculate a shopping motivation index. FIG. 5 is a diagram illustrating an example of an evaluation index corresponding to shopping day information. FIG. 6 is a diagram illustrating a day of the week when a user is likely to go shopping. FIG. 7 is a diagram illustrating an example of an evaluation index corresponding to shopping weather information. FIG. 8 is a diagram illustrating an example of an evaluation index corresponding to an overall inventory index of a refrigerator. FIG. 9 is a diagram illustrating an example of an evaluation index corresponding to an inventory index for each item in a refrigerator. FIG. 10 is a diagram illustrating an example of cooking information used to calculate a cooking motivation index. FIG. 11 is a diagram illustrating a first example of data on time periods that are the target of the cooking motivation index. FIG. 12 is a diagram illustrating a second example of data on time periods that are the target of the cooking motivation index. FIG. 13 is a diagram illustrating a third example of data on time periods that are the target of the cooking motivation index. FIG. 14 is a diagram illustrating a first method. FIG. 15 is a diagram illustrating an example of an evaluation index for a peak season. FIG. 16 is a diagram illustrating an example of an evaluation index for evaluating meal candidates. FIG. 17 is a diagram illustrating a second method. FIG. 18 is a diagram showing an example of evaluation indices for evaluating recipe candidates. FIG. 19 is a diagram showing an example of evaluation indices for evaluating ready-to-eat candidates. FIG. 20 is a diagram for explaining the third method. FIG. 21 is a diagram showing an example of evaluation indices for evaluating food products. FIG. 22 is a diagram showing an example of evaluation indices for evaluating meal candidates. FIG. 23 is a diagram for explaining evaluation indices for eating out and ready-to-eat meals used in the fourth method. FIG. 24 is a diagram showing an example of evaluation indices for evaluating ready-to-eat candidates and eating out candidates. FIG. 25 is a diagram showing an example of presented information. FIG. 26 is a diagram showing another example of presented information. FIG. 27 is a diagram showing an example of recipe details. FIG. 28 is a diagram showing an example of menu details.

[0010] (Findings that form the basis of the present disclosure) In conventional technologies such as Patent Literature 1, recipes are proposed that include ingredients that the user owns, which reduces the number of recipe candidates and may result in the proposed recipes becoming monotonous. In this case, there is a risk that the user will not accept the proposed recipes and will ignore them, which may decrease the frequency with which the user uses recipe suggestions made by the conventional technology, and may prevent the goal of reducing ingredient waste from being achieved.

[0011] In order to prevent suggested recipes from becoming monotonous, it is conceivable to provide the user with a variety of recipes by encouraging the user to purchase any missing ingredients. However, depending on the user's situation, there may be cases where the user does not want to go out of their way to go shopping. In such cases, suggesting a recipe to the user on the assumption that the user will purchase additional ingredients may lead to dissatisfaction among the user and cause the user to not accept the suggested recipe.

[0012] Therefore, the present inventors have come up with a meal suggestion system that can encourage a user to consume food in a planned manner according to the user's shopping motivation.

[0013] A meal suggestion system according to a first aspect of the present disclosure includes one or more processors, which acquire held food information regarding one or more held foods that are foods held by a user, meal candidate information indicating a plurality of meal candidates, and external information stored in an external device, analyze the external information to estimate the user's willingness to go out and shop, and if the result of the estimation of shopping desire shows that the shopping desire is high, (i) determine one or more first meal candidates from the plurality of meal candidates, which include at least one food selected from all types of food, and (ii) output first presentation information including the determined one or more first meal candidates, and if the result of the estimation of shopping desire shows that the shopping desire is low, (i) determine one or more second meal candidates from the plurality of meal candidates, which include at least one held food selected from the one or more held foods, and (ii) output second presentation information including the determined one or more second meal candidates.

[0014] According to this, when the user's shopping motivation is high, one or more first meal candidates are determined, which include at least one food selected from all types of food, regardless of whether the food is owned by the user, and when the user's shopping motivation is low, one or more second meal candidates are determined, which include one owned food. In this way, when the user's shopping motivation is high, a variety of meals can be suggested to the user, and when the user's shopping motivation is low, meals can be suggested to the user to consume the owned food. Therefore, the user can be encouraged to consume food in a planned manner according to the user's shopping motivation.

[0015] A meal suggestion system according to a second aspect of the present disclosure is the meal suggestion system according to the first aspect, wherein the one or more processors estimate the shopping intention based on at least one of shopping day information regarding the likelihood of the user going shopping on each day of the week, shopping weather information regarding the likelihood of the user going shopping in each weather, and total quantity information regarding the total quantity of the one or more food items owned.

[0016] This allows for an effective estimation of shopping intentions.

[0017] A meal suggestion system according to a third aspect of the present disclosure is the meal suggestion system according to the first or second aspect, wherein the one or more processors acquire user information about the user, analyze the user information to estimate the user's cooking motivation, and if the estimated cooking motivation is high, (i) determine one or more third meal candidates from the plurality of meal candidates such that meal candidates requiring a high cooking load are prioritized, and (ii) output third presentation information including the one or more determined third meal candidates; and if the estimated cooking motivation is low, (i) determine one or more fourth meal candidates from the plurality of meal candidates such that meal candidates requiring a low cooking load are prioritized, and (ii) output fourth presentation information including the one or more determined fourth meal candidates.

[0018] According to this, when the user's motivation to cook is high, one or more first meal candidates that require a high cooking load are determined, and when the user's motivation to cook is low, one or more second meal candidates that require a low cooking load are determined. Thus, meal candidates can be proposed according to the user's motivation to cook.

[0019] A meal suggestion system according to a fourth aspect of the present disclosure is the meal suggestion system according to the third aspect, wherein the plurality of meal candidates include cooking recipes indicating steps and ingredients for preparing the meal of the meal candidates, the user information includes recipe interest information regarding interest in the cooking recipes, and the one or more processors estimate the cooking motivation based on at least one of the recipe interest information, cooking appliance information regarding cooking appliances owned by the user, family information indicating the user's family composition, location information of the user, and schedule information indicating the user's schedule.

[0020] This allows for effective estimation of the willingness to cook.

[0021] A meal suggestion system according to a fifth aspect of the present disclosure is the meal suggestion system according to the third or fourth aspect, wherein the one or more processors, when the shopping willingness is high and the cooking willingness is high, (i) determine one or more fifth meal candidates from the plurality of meal candidates, which include at least one food item selected from all types of food, such that meal candidates requiring a large cooking load are prioritized, and (ii) output fifth presentation information including the one or more determined fifth meal candidates; and when the shopping willingness is high and the cooking willingness is low, (i) determine one or more fifth meal candidates from the plurality of meal candidates, which include at least one food item selected from all types of food, such that meal candidates requiring a small cooking load are prioritized, and (ii) output fifth presentation information including the determined one or more fifth meal candidates. (ii) outputting sixth presentation information including the one or more sixth meal candidates that have been determined; if the shopping desire is low and the cooking desire is high, (i) determining one or more seventh meal candidates from the plurality of meal candidates, which include at least one held food item selected from the one or more held foods, such that meal candidates requiring a high cooking load are given priority; (ii) outputting seventh presentation information including the one or more determined seventh meal candidates; if the shopping desire is low and the cooking desire is low, (i) determining one or more eighth meal candidates from the plurality of meal candidates, such that meal candidates requiring a low cooking load are given priority; and (ii) outputting eighth presentation information including the one or more determined eighth meal candidates.

[0022] A meal suggestion system according to a sixth aspect of the present disclosure is the meal suggestion system according to the fifth aspect, wherein, in determining the one or more fifth meal candidates, the one or more processors calculate a meal selection index for each of one or more meal candidates among the plurality of meal candidates that includes at least one food selected from all types of food, based on at least one of the content rate of the one or more owned foods, the seasonality of the meal candidate, and the recency of the meal candidate, and determine the one or more fifth meal candidates from the one or more meal candidates in descending order of the meal selection index.

[0023] A meal suggestion system according to a seventh aspect of the present disclosure is a meal suggestion system according to the fifth or sixth aspect, wherein the plurality of meal candidates includes one or more recipe candidates represented by cooking recipes and one or more intermediate meal candidates representing intermediate meals, and the one or more processors, in determining the one or more sixth meal candidates, calculate a meal selection index for each of the one or more recipe candidates based on at least one of the time required to cook the recipe candidate, the number of steps required to cook the recipe candidate, and the number of foods used in the recipe candidate, and calculate a meal selection index for each of the one or more intermediate meal candidates based on at least one of the price of the intermediate meal candidate and the time required to purchase the intermediate meal candidate, and determine the one or more sixth meal candidates from the plurality of meal candidates in descending order of meal selection index.

[0024] A meal suggestion system according to an eighth aspect of the present disclosure is a meal suggestion system according to any one of the fifth to seventh aspects, wherein the one or more processors, in determining the one or more seventh meal candidates, calculate a meal selection index for each of one or more meal candidates among the plurality of meal candidates that includes at least one held food selected from the one or more held foods based on at least one of the content rate of the one or more held foods, the seasonality of the meal candidate, and the recency of the meal candidate, and determine the one or more seventh meal candidates from the one or more meal candidates in descending order of the meal selection index.

[0025] A meal suggestion system according to a ninth aspect of the present disclosure is the meal suggestion system according to any one of the fifth to eighth aspects, wherein the plurality of meal candidates include one or more recipe candidates represented by cooking recipes, one or more take-out meal candidates representing take-out meals, and one or more eating out candidates representing eating out, and wherein, in determining the one or more eighth meal candidates, the one or more processors determine, for each of the one or more recipe candidates, at least one of the time required to cook the recipe candidate, the number of steps required to cook the recipe candidate, and the number of foods used in the recipe candidate. a meal selection index for the recipe candidate based on the one or more candidate ready-to-eat meals calculated based on at least one of the price of the candidate ready-to-eat meal and the time required to purchase the candidate ready-to-eat meal; a meal selection index for the candidate ready-to-eat meal based on at least one of the opening hours of a store that offers the candidate ready-to-eat meal and the distance from the current location to the store; and one or more eighth meal candidates are determined from the one or more candidate meals in descending order of meal selection index.

[0026] A meal suggestion method according to a tenth aspect of the present disclosure is a meal suggestion method executed by one or more processors, which acquires held food information regarding one or more held foods that are foods held by a user, meal candidate information indicating a plurality of meal candidates, and external information stored in an external device, analyzes the external information to estimate the user's willingness to go out and shop, and if the result of the estimation of shopping willingness shows that the user's shopping willingness is high, (i) determines one or more first meal candidates from the plurality of meal candidates, which include at least one food selected from all types of food, and (ii) outputs first presentation information including the determined one or more first meal candidates, and if the result of the estimation of shopping willingness shows that the user's shopping willingness is low, (i) determines one or more second meal candidates from the plurality of meal candidates, which include at least one held food selected from the one or more held foods, and (ii) outputs second presentation information including the determined one or more second meal candidates.

[0027] According to this, when the user's shopping motivation is high, one or more first meal candidates are determined, which include at least one food selected from all types of food, regardless of whether the food is owned by the user, and when the user's shopping motivation is low, one or more second meal candidates are determined, which include one owned food. In this way, when the user's shopping motivation is high, a variety of meals can be suggested to the user, and when the user's shopping motivation is low, meals can be suggested to the user to consume the owned food. Therefore, the user can be encouraged to consume food in a planned manner according to the user's shopping motivation.

[0028] A program according to an eleventh aspect of the present disclosure is a program for causing a computer to execute the meal suggestion method according to the tenth aspect.

[0029] These general or specific aspects may be realized by a device, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or by any combination of a device, an integrated circuit, a computer program, and a non-transitory recording medium.

[0030] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of well-known matters or redundant explanation of substantially the same configuration may be omitted. This is to avoid unnecessary redundancy in the following explanation and to facilitate understanding by those skilled in the art.

[0031] The inventors have provided the accompanying drawings and the following description to enable those skilled in the art to fully understand the present disclosure, and do not intend for them to limit the subject matter described in the claims.

[0032] (Embodiment) [Configuration] FIG. 1 is a diagram for explaining an overview of a meal suggestion system according to an embodiment.

[0033] The meal suggestion system 1 is composed of a meal suggestion device 100. The meal suggestion device 100 suggests meals to the user U1. For example, the meal suggestion device 100 suggests meals to the user U1 depending on the situation of the user U1. The meal suggestion device 100 may suggest meals to encourage consumption of the foods 11 to 15 owned by the user U1. The meal suggestion device 100 can also be said to be a device that supports the planned consumption of the foods 11 to 15 by the user U1.

[0034] For example, when the user U1 acquires the foods 11 to 15, the user U1 registers the stored food information relating to the acquired foods 11 to 15 in the meal suggestion device 100.

[0035] Based on the registered stored food information and the proposed food information related to the food proposal history up to that point, the meal proposal device 100 proposes foods to be consumed each time (e.g., when the user U1 prepares a meal) so that the user U1 can consume the foods 11-15 in a planned manner. In other words, the meal proposal device 100 proposes the planned consumption timing for the food obtained by the user U1 for each type of food. Here, planned consumption means consuming the food by the expiration date by which the user U1 can safely eat the food, or by the best-before date by which the food maintains its quality and can be eaten deliciously. Hereinafter, unless otherwise specified, the use-by date will be described as including the concept of a best-before date. Note that the best-before date may also include the concept of a best-before date. Furthermore, the use-by date may include a use-by date set by the user or a use-by date set for each food in the food DB 153 described below.

[0036] The foods 11 to 15 may be food ingredients such as vegetables, meat, fish, rice, etc., or may be processed foods made from processed food ingredients. In Figure 1, the foods 11 to 15 are exemplified by Chinese cabbage, onion, cabbage, carrot, and raw meat, respectively.

[0037] The food is not limited to the food exemplified in FIG. 1. The food may be a frozen food product in which cooked food is frozen and then thawed by the user U1 to complete the meal, or a meal kit in which the user U1 performs simple cooking to complete the meal. The food may also be a prepared food product such as a prepared meal in which ingredients are cooked to complete the meal, or a takeout meal served at a restaurant. Hereinafter, food that can be purchased at a store and is complete as a meal is also referred to as a ready-made meal.

[0038] 1, the meal suggestion device 100 is, for example, a smartphone, but is not limited to this and may be any device equipped with a computer. The meal suggestion device 100 may be, for example, a tablet terminal, a VPA (Virtual Personal Assistant) device, or a PC (Personal Computer).

[0039] FIG. 2 is a block diagram illustrating an example of the configuration of a meal suggestion device according to an embodiment.

[0040] 2, the meal suggestion device 100 includes a processor 110, an input IF (Interface) 120, a main memory 130, a communication IF (Interface) 140, a storage 150, and an output IF (Interface) 160. Note that the meal suggestion device 100 does not need to include all of the input IF 120, the communication IF 140, and the output IF 160, as long as it includes one of the input IF 120 and the communication IF 140 that has a function of acquiring information, and one of the communication IF 140 and the output IF 160 that has a function of outputting information.

[0041] The processor 110 is a processor that executes programs stored in the storage 150 or the like.

[0042] The input IF 120 is an interface for receiving input from a user. The input IF 120 may be a pointing device such as a mouse, a touchpad, a touch panel, or a trackball, or may be a keyboard. The input IF 120 may also be an interface for receiving input by voice uttered by the user. In other words, the input IF 120 may be a microphone. The input IF 120 may also be a camera for capturing images.

[0043] The main memory 130 is a volatile storage area that is used to temporarily store data generated during processing by the processor 110, used as a work area when the processor 110 executes a program, and used to temporarily store data received by the communication IF 140 and data accepted by the input IF 120.

[0044] The communication IF 140 is a communication interface for transmitting data to and from external information devices such as smartphones, tablet terminals, PCs, and servers. The communication IF 140 may be, for example, an interface for wireless communication such as a wireless LAN interface or a Bluetooth (registered trademark) interface. The communication IF 140 may also be an interface for wired communication such as a USB (Universal Serial Bus) or a wired LAN interface. Note that the communication IF 140 is not limited to the above, and may also be a communication interface for transmitting data to and from external devices via a communication network.

[0045] The storage 150 is a non-volatile storage device that holds various data such as programs, etc. The storage 150 stores various data generated as a result of processing by the processor 110, for example.

[0046] The output IF 160 is a device that presents at least a part of the processing results by the processor 110. The output IF 160 may be a display that displays information, or may be a speaker that outputs information as sound, such as voice.

[0047] (Storage) A specific example of information stored in the storage 150 will be described.

[0048] The storage 150 includes an inventory management database 151, a meal suggestion database 152, and a food database 153. The storage 150 may also store external information and user information related to users. Note that the external information need not be stored in the storage 150 as long as it is acquired by the meal suggestion device 100 from an external device (server) via a network.

[0049] The inventory management DB 151 is a database for managing the owned food information registered by user U1. The owned food information includes, for each of one or more owned foods owned by user U1, the type of the owned food, the quantity of the owned food, and the expiration date of the owned food. The owned food information may further include, for each of one or more owned foods, the purchase route of the owned food, the origin of the owned food, the manufacturer of the owned food, and the product name of the owned food. The purchase route includes the retail store or electronic commerce (EC) site that sold the corresponding owned food to the user. When the meal suggestion device 100 receives an input indicating that user U1 has added a new owned food, the quantity specified in the input is added to the owned food information. Furthermore, when the meal suggestion device 100 receives an input indicating that user U1 has consumed a owned food, the quantity specified in the input is subtracted from the owned food information. The quantity of the owned food may be subtracted not only when the owned food is consumed, but also when the owned food is discarded or transferred to another user, in response to an input. When the quantity of the owned food becomes zero, the owned food may be deleted from the owned food information.

[0050] The meal suggestion DB 152 is a database for managing meal candidate information indicating multiple meal candidates for meals to be suggested to the user. The multiple meal candidates include cooking recipes indicating the steps and ingredients for preparing the meal. The multiple meal candidates may also include take-out meal candidates indicating take-out meals. The take-out meal candidates include information on stores that offer take-out meals. Stores that offer take-out meals include restaurants that offer take-out meals and delivery stores that offer take-out meals. Information on these stores includes, for example, the store's location, store business hours, store contact information (telephone number, email address, SNS ID), and congestion status.

[0051] Food DB 153 is a database for managing food information related to food. The food information includes, for each type of food, the number of days that the food can be stored. The food information may also include, for each type of food, the amount in circulation, price, and nutritional value. If the food is an ingredient, the food information may also include seasonal information for the ingredient. The seasonal information is information about the season for an ingredient, and is expressed, for example, by the period corresponding to the season (season period) or the season corresponding to the season.

[0052] External information is information acquired from an external device. External information includes information generated by the external device or information acquired by the external device from another device. External information includes, for example, a user's shopping information and a user's cooking information. A user's shopping information may be generated based on a user's food shopping history, an update history of the user's food information, etc. A user's cooking information may be generated based on a user's cooking history, etc. Note that external information may also include a user's behavioral history itself. A user's behavioral history includes a user's food shopping history, a user's search history and / or browsing history for recipe sites, a user's cooking history, etc.

[0053] The user information is information generated by the meal suggestion device 100 based on input by the user to the meal suggestion device 100. The user information can also be said to be internal information. Input by the user includes, for example, input in response to a medical interview given to the user. The user information is information about the user. Specifically, the user information may include attribute information indicating the user's attributes, or may include behavioral history information indicating the user's behavioral history.

[0054] The user attributes may be, for example, the user's hobbies or preferences related to cooking and / or eating, or the user's age, gender, residential area, annual income, marital status, whether with or without children, occupational category, place of employment, educational background, etc. Here, the user's hobbies or preferences related to cooking and / or eating include the user's shopping habits, the user's cooking habits, etc.

[0055] Furthermore, the behavioral history information included in the user information may be generated based on the user's responses to questions inquiring about the actions the user has taken. The user's behavioral history indicated by the behavioral history information may include the user's search history and / or browsing history for recipe sites, the user's cooking history, etc., and may be generated based on the user's responses to the questions. Furthermore, the user information may include, for example, the user's cooking information. The user's cooking information may be generated based on the user's search history and / or browsing history for recipe sites, the user's cooking history, etc. The user's cooking information may be generated based on the user's responses to the questions.

[0056] The external information may include information about the user's attributes and behavioral history generated based on input to a medical interview given to the same user on another device.

[0057] In this disclosure, "managing information" means storing information in storage, changing part of the information stored in the storage, adding new information, or deleting part of the stored information.

[0058] [Operation] Next, a description will be given of the processing executed by the processor 110 of the meal suggestion device 100. Fig. 3 is a flowchart showing an example of the processing executed by the processor.

[0059] The processor 110 acquires the stored food information, meal candidate information, and external information from the storage 150 (S11).

[0060] Next, processor 110 analyzes the external information to estimate the user's shopping willingness (S12). Shopping willingness is the user's willingness to go out and do shopping at the time of estimating the shopping willingness. Specifically, processor 110 estimates the user's shopping willingness by calculating a shopping willingness index. In this way, processor 110 calculates the shopping willingness index based on at least the external information, but may also calculate the shopping willingness index based on user information in addition to the external information.

[0061] A method for calculating the shopping willingness index will now be described. Fig. 4 is a diagram showing an example of external information used to calculate the shopping willingness index.

[0062] As shown in FIG. 4 , the external information includes date and time information, day of the week information, time information, weather information, and a refrigerator inventory index. The date and time information indicates date and time in a predetermined time unit. The date and time information indicates, for example, date and time in one-day units, i.e., date. The date and time information includes the current date and time, dates and times in the past and future of the current date and time. The day of the week information indicates the day of the week corresponding to the date indicated by the date and time information. The day of the week information is included in calendar information. The calendar information includes the year, month, week, date, day of the week, and consecutive holidays. The day of the week information included in the external information may be referred to as shopping day of the week information. The time information indicates time periods obtained by further dividing the time indicated by the date indicated by the date and time information into multiple periods. The time information indicates, for example, morning, which indicates the first half of the day, and afternoon, which indicates the second half of the day. The weather information indicates the weather during the time period indicated by the time information. The weather information indicates actual weather conditions for the current and past dates and times, and forecasted weather conditions for future dates and times. The weather information included in the external information may be referred to as shopping weather information. The refrigerator inventory index correlates with the refrigerator inventory amount in the time period indicated by the time information. The higher the value of the refrigerator inventory index, the greater the inventory amount. The refrigerator inventory index indicates the actual refrigerator inventory amount at the current and past dates and times, and indicates the inventory amount predicted from the past fluctuations in refrigerator inventory amount at the future dates and times. For example, the future refrigerator inventory amount may be calculated by the average, median, etc. of the past inventory amount by day of the week. The future refrigerator inventory amount is not limited to being calculated by the average, median, etc. of the past inventory amount by day of the week as described above, as long as it is calculated from a trend that can be seen from the past fluctuations in refrigerator inventory amount.

[0063] Processor 110 calculates the user's shopping willingness index at the time of estimation based on external information. Specifically, processor 110 calculates the shopping willingness index based on the day of the week information, weather information, and overall refrigerator inventory index that correspond to the time of estimation from the external information. The day of the week information, weather information, and overall refrigerator inventory index each have an evaluation index corresponding to the information.

[0064] The day of the week information may be information stored in storage 150 or information acquired from an external device via communication IF 140. The weather information is information acquired from an external device via communication IF 140. The refrigerator inventory index is information acquired from inventory management DB 151 of storage 150.

[0065] Fig. 5 is a diagram showing an example of an evaluation index calculated from the difference in refrigerator inventory index. Fig. 6 is a diagram showing days of the week when users are likely to go shopping. The evaluation index corresponding to the shopping day information is information regarding the likelihood of the user going shopping on each day of the week. A higher evaluation index is associated with each day of the shopping day information as the likelihood that the user will go shopping on that day increases.

[0066] 6, the days of the week when the user is likely to go shopping are an example of user information obtained from the user's response to a questionnaire. Furthermore, the days of the week when the user is likely to go shopping may be set to a default value before a response from the user is obtained, and information with a default value set is an example of external information.

[0067] The evaluation index for each day of the week shown in Fig. 5 may be generated based on the days of the week when it is easy for the user to go shopping, as shown in Fig. 6. In this evaluation index, a large evaluation index may be set for calendar information that is identified as easy to go to, and a small evaluation index may be set for calendar information that is identified as not going to go to or difficult to go to.

[0068] Depending on the user's attributes, there is a tendency for users to go shopping on certain days of the week and on other days. If the user is working, they tend to go shopping on their days off. For example, if the user works on a weekday, they tend to be more likely to go shopping on weekends and holidays when they have more free time than on weekdays. In other words, it can be said that users tend to go shopping on certain days of the week. Therefore, an evaluation index corresponding to day of the week information can be determined depending on the user's attributes. Since the user's attributes are generated based on the user's answers to the user's questions, it can be said that the evaluation index for day of the week information is determined based on the user's answers to the user's questions.

[0069] The evaluation index corresponding to the day of the week information may be determined based on the user's past shopping history. That is, a higher evaluation index may be associated with a higher shopping frequency based on the user's shopping frequency for each day of the week.

[0070] 7 is a diagram showing an example of an evaluation index corresponding to the shopping weather information. The evaluation index corresponding to the shopping weather information is information about the likelihood of a user going shopping under each weather condition. A higher evaluation index is associated with each weather condition in the shopping weather information, the more likely the user is to go shopping under that weather condition.

[0071] There are weather conditions that are favorable for users to go shopping and weather conditions that are not. For example, users are more likely to go shopping when it is not raining or snowing (clear or cloudy) than when it is raining or snowing. For this reason, a higher evaluation index may be associated with weather when it is not raining or snowing (clear or cloudy) than with weather when it is raining or snowing. Furthermore, because users tend to refrain from going out when an alert or advisory is in effect, a lower evaluation index may be associated with weather when an alert or advisory is in effect than with other weather conditions. Note that the weather information may also include outside temperature. For example, a temperature range of outside temperature that a user finds comfortable may be associated with a higher evaluation index than a temperature range outside that temperature range. Note that the weather information may also include precipitation, sunshine hours, humidity, general weather conditions, etc.

[0072] 8 is a diagram showing an example of an evaluation index corresponding to the total inventory index of a refrigerator. The total inventory index of a refrigerator is an index that correlates with the total amount of food stored in the refrigerator.

[0073] The larger the overall inventory index of a refrigerator, the greater the inventory amount, and therefore users tend to refrain from shopping. For this reason, the larger the overall inventory index of a refrigerator, the lower the evaluation index that may be associated with it.

[0074] Processor 110 calculates evaluation indices corresponding to the day of the week information, weather information, and overall refrigerator inventory index corresponding to the time of estimation, based on external information and the correspondence relationships between evaluation indices shown in FIGS. 5, 7, and 8. Processor 110 then calculates the user's shopping willingness index at the time of estimation based on the calculated evaluation indices corresponding to the day of the week information, weather information, and overall refrigerator inventory index. Specifically, processor 110 calculates the shopping willingness index so that the higher the evaluation indices corresponding to the day of the week information, weather information, and overall refrigerator inventory index, the higher the evaluation indices. For example, processor 110 may calculate the shopping willingness index by multiplying the evaluation indices corresponding to the day of the week information, weather information, and overall refrigerator inventory index, or by adding them together, or by weighted addition. Processor 110 may also calculate the shopping willingness index using a machine learning model such as a decision tree based on the evaluation indices corresponding to the day of the week information, weather information, and overall refrigerator inventory index.

[0075] It should be noted that the processor 110 calculates the user's shopping willingness index based on the evaluation index corresponding to the day of the week information, weather information, and the inventory index of the entire refrigerator, but this is not limited to this, and the user's shopping willingness index may be calculated based on at least one of the day of the week information, weather information, and the inventory index of the entire refrigerator.

[0076] The shopping willingness index may be calculated based on an evaluation index based on the inventory index for each item in the refrigerator in addition to the inventory index for the entire refrigerator, or may be calculated based on an evaluation index based on the inventory index for each item in the refrigerator instead of the inventory index for the entire refrigerator.

[0077] FIG. 9 is a diagram showing an example of an evaluation index corresponding to an inventory index for each refrigerator item. The inventory index for each refrigerator item is an index that correlates with the amount of each item stored in the refrigerator. In FIG. 9, meat and fish, vegetables, eggs and dairy products are exemplified as food items. The food items are not limited to the example in FIG. 9 and may include other items.

[0078] As with the overall inventory index, the higher the inventory index for each refrigerator item, the greater the inventory amount, and therefore the user tends to refrain from shopping. For this reason, a lower evaluation index may be associated with a higher inventory index for each refrigerator item. Note that the inventory index for each item reflects the individual user's tendencies depending on the item. For example, if a user frequently consumes eggs and dairy products, the evaluation index for eggs and dairy products may be set to be higher overall than that of a user who consumes them less frequently. Specifically, the evaluation index for a user who frequently consumes eggs and dairy products may be calculated by multiplying the evaluation indexes of other users by a coefficient greater than 1, or by adding a constant to the evaluation indexes of other users. Note that the evaluation index for food inventory index may be calculated not only for each food item, but also for each location where the food is stored.

[0079] Although the example of calculating the evaluation index according to the food stored in the refrigerator has been given, the evaluation index may be calculated according to the total amount of food stored in the user's possession, not limited to the food stored in the refrigerator, but stored in a location other than the refrigerator, and this evaluation index may be used to calculate the shopping motivation index. The total amount of food stored is calculated based on the food storage information managed in the inventory management DB 151.

[0080] The evaluation index corresponding to the shopping day information, the evaluation index corresponding to the shopping weather information, and the evaluation index corresponding to the refrigerator inventory index (overall or for each item) may be set to a value individually corrected according to user information generated in response to the user's responses to a user questionnaire and external information including the user's food shopping history trends. A weighting coefficient may be used for the correction according to the user information. For example, a reference evaluation index corresponding to each piece of information may be determined, and the reference evaluation index may be multiplied by a coefficient determined in accordance with the user information to determine the evaluation index corresponding to each piece of information for each user. Furthermore, in each piece of information, the evaluation index corresponding to a specific item may be used as a reference, and the evaluation indexes for other items may be calculated using a coefficient. For example, the evaluation index for the other items may be calculated by multiplying the evaluation index of the specific item used as a reference by a coefficient for calculating the evaluation index for the other items.

[0081] In addition to the evaluation indices exemplified above, the shopping motivation index may be calculated based on evaluation indices based on store food sale information, store location information, the user's schedule, etc. Sale information is likely to increase the user's motivation to go shopping. Furthermore, if the store is located close to the user's home, the user's motivation to go shopping is likely to increase. Furthermore, if the user's schedule is free, the user's motivation to go shopping is likely to increase. Sale information and store location information are acquired from an external device via communication IF 140. The user's schedule may be included in user information acquired based on input received from the user via input IF 120, or may be included in external information acquired from an external device via communication IF 140. The schedule acquired from the external device is information already registered in the external device by the user.

[0082] Returning to the description of FIG.

[0083] Next, processor 110 analyzes the user information to estimate the user's motivation to cook (S13). The motivation to cook is the user's motivation to cook ingredients and prepare a meal at the time of estimating the motivation to cook. Specifically, processor 110 estimates the user's motivation to cook by calculating a cooking motivation index. In this way, processor 110 calculates the cooking motivation index based on at least the user information, but the cooking motivation index may also be calculated based on external information in addition to the user information.

[0084] Here, a method for calculating the cooking motivation index will be described. Fig. 10 is a diagram showing an example of cooking information used to calculate the cooking motivation index.

[0085] As shown in FIG. 10 , the cooking information includes date and time information, a recipe search flag, and a recipe detail viewing flag. The date and time information indicates either the time when the user searched for a cooking recipe using the meal suggestion device 100 or the time when the user viewed the details of a cooking recipe. The recipe search flag is information indicating whether the user searched for a cooking recipe using the meal suggestion device 100 at the date and time indicated by the corresponding date and time information. If the user searched for a cooking recipe, the recipe search flag is indicated as "1." If the user did not search for a cooking recipe, the recipe search flag is indicated as "0." The recipe detail viewing flag is information indicating whether the user viewed the details of a cooking recipe using the meal suggestion device 100 at the date and time indicated by the corresponding date and time information. If the user viewed the details of a cooking recipe, the recipe detail viewing flag is indicated as "1." If the user did not view the details of a cooking recipe, the recipe detail viewing flag is indicated as "0." Whether the user viewed the details of a cooking recipe using the meal suggestion device 100 does not have to be indicated by a flag of "1" or "0," but may be indicated by whether the viewing time is 0 or greater than 0. Viewing time may be expressed in units such as, for example, seconds, minutes, hours, combinations thereof, or other units.

[0086] The processor 110 estimates the user's motivation to cook using, for example, cooking information from the time of the estimated motivation to cook up to a predetermined time (e.g., six hours) prior. For example, if the estimated time of the motivation to cook is 19:00, the processor 110 estimates the user's motivation to cook using information from 13:00 onwards, six hours prior, as indicated by hatching in FIG. 10 . After 13:00, the processor 110 counts information where the recipe search flag is set to "1" and information where the recipe details viewing flag is set to "1." The processor 110 calculates a cooking motivation index based on the count results of the recipe search flag and the count results of the recipe details viewing flag. Specifically, the processor 110 calculates a cooking motivation index that increases as the count results of the recipe search flag and the recipe details viewing flag increase. For example, the processor 110 may calculate the cooking motivation index by multiplying the count result of the recipe search flag and the count result of the recipe detail viewing flag, by adding them together, or by performing a weighted addition. The processor 110 may also calculate the cooking motivation index using a machine learning model such as a decision tree based on the count result of the recipe search flag and the count result of the recipe detail viewing flag. The recipe search flag and the recipe detail viewing flag may be obtained based on a user's input to the input IF 120, or may be obtained from the storage 150 in which the history of the input is recorded. In addition to the recipe search flag and the recipe detail viewing flag, the cooking motivation index may also be calculated based on the time spent viewing the recipe details.

[0087] The processor 110 may estimate the user's motivation to cook based on recipe interest information related to interest in cooking recipes, rather than on the count results of the recipe search flag and the recipe detail viewing flag. The recipe interest information is information correlated with the level of interest in cooking using cooking recipes. The recipe interest information may include, in addition to the count results of the recipe search flag and the recipe detail viewing flag, at least one of cooking appliance information related to the user's cooking appliances, family information indicating the user's family structure, the number of times the cooking appliances are used, the user's location information, and schedule information indicating the user's schedule. Alternatively, the recipe interest information may include at least one of the following information instead of the count results of the recipe search flag and the recipe detail viewing flag. The cooking appliance information is the type and number of cooking appliances owned by the user. The cooking appliance information may be information registered in advance in, for example, an external device, along with a user ID for identifying the user. The number of owned cooking appliances may be associated with an evaluation index such that the higher the number of owned appliances, the higher the evaluation index for calculating the cooking motivation index. The family information may be associated with an evaluation index such that the larger the user's family, the higher the evaluation index for calculating the cooking motivation index. The number of times a cooking appliance is used is calculated by counting, for example, opening and closing a refrigerator, turning an induction cooking heater on and off, starting a microwave oven to heat, etc. The number of times a cooking appliance is used may be associated with an evaluation index such that the more times it is used, the higher the evaluation index for calculating a cooking motivation index. The user's location information may be associated with an evaluation index such that the closer the user's location is to the user's home, the higher the evaluation index for calculating a cooking motivation index. The schedule information may be associated with an evaluation index such that the fewer the number of user schedules in the time period at the time of estimation, the higher the evaluation index for calculating a cooking motivation index.

[0088] The cooking appliance information may be acquired based on a user's input to the input IF 120, from the storage 150 recording the history of the input, or from an external device storing the input record via the communication IF 140. The family structure information may be acquired based on a user's input to the input IF 120, from the storage 150 recording the history of the input, or from an external device storing the input record via the communication IF 140. The number of times the cooking appliances have been used may be acquired via the communication IF 140 from an external device storing the operation logs of the cooking appliances. The user's location information may be acquired via the communication IF 140 from an external device storing location information detected by the user's device, or, if the meal suggestion device 100 has a GPS receiver capable of acquiring the user's location information, may be determined based on information received by the GPS receiver. The user's schedule may be acquired based on a user's input accepted via the input IF 120, or from an external device via the communication IF 140. The schedule acquired from the external device is information that has already been registered in the external device by the user.

[0089] Next, the data of the time period that is the subject of the cooking motivation index will be described. Fig. 11 is a diagram for explaining a first example of the data of the time period that is the subject of the cooking motivation index.

[0090] As shown in FIG. 11 , when user U1 searches for a cooking recipe using an app using the meal suggestion device 100, the data from a time a predetermined time before the data update time, which is included in the search time when user U1 was searching, is used to calculate the cooking motivation index. The calculated cooking motivation index indicates the motivation to cook a meal scheduled to come next after the search time. The data includes app logs, inventory data, etc. The app logs include input history by user U1 to the app, app operation history, etc. The inventory data includes update history of the inventory management DB 151, etc. The data is updated periodically.

[0091] FIG. 12 is a diagram illustrating a second example of data on time periods that are the subject of the cooking motivation index.

[0092] 12, when user U1 searches for a cooking recipe using the app on the meal suggestion device 100, the cooking motivation index is calculated based on the data update time before the search time and the data (cooking information) from a time a predetermined time before the data update time. The calculated cooking motivation index indicates the motivation to cook a meal scheduled to come next after the search time.

[0093] FIG. 13 is a diagram illustrating a third example of data on time periods that are the subject of the cooking motivation index.

[0094] 13, when user U1 searches for a cooking recipe in an app using the meal suggestion device 100, data (cooking information) from a time period starting from a predetermined time before the search time, during which the app is likely to be used (i.e., excluding time periods during which the app is likely not being used), is used to calculate the cooking motivation index. The calculated cooking motivation index indicates the motivation to cook a meal scheduled to come at the next opportunity after the search time.

[0095] 3, the processor 110 next determines whether the shopping willingness index is higher than the threshold T1 (S14). If the processor 110 determines that the shopping willingness index is higher than the threshold T1 (Yes in S14), it executes step S15, and if the processor 110 determines that the shopping willingness index is equal to or lower than the threshold T1 (No in S14), it executes step S18.

[0096] In step S15, processor 110 determines whether the cooking motivation index is higher than threshold value T2. If processor 110 determines that the cooking motivation index is higher than threshold value T2 (Yes in S15), it executes step S16, and if processor 110 determines that the cooking motivation index is equal to or lower than threshold value T2 (No in S15), it executes step S17.

[0097] In step S16, the processor 110 determines meal candidates using the first method.

[0098] In step S17, the processor 110 determines meal candidates using the second method.

[0099] In step S18, processor 110 determines whether the cooking motivation index is higher than threshold value T2. If processor 110 determines that the cooking motivation index is higher than threshold value T2 (Yes in S18), it executes step S19, and if processor 110 determines that the cooking motivation index is equal to or lower than threshold value T2 (No in S18), it executes step S20.

[0100] In step S19, the processor 110 determines meal candidates using the third method.

[0101] In step S20, the processor 110 determines meal candidates using the fourth method.

[0102] Next, specific examples of steps S11 to S15 and S18 will be described.

[0103] First, a specific example of the calculation result of the shopping motivation index will be described.

[0104] The shopping willingness index is calculated starting from the time when the user searches for a cooking recipe in the app using the meal suggestion device 100. Note that the shopping willingness index may be calculated at a predetermined timing, such as a specific time.

[0105] For example, if a cooking recipe search is performed at 10:30 on October 9, 2023, shopping information for the morning of October 9, 2023 is used to calculate the shopping motivation index. If the evaluation index for the day of the week information is 10, the evaluation index for the weather information is 0, and the evaluation index for the refrigerator inventory index is 3, the sum of these values, 13, is calculated as the shopping motivation index.

[0106] Furthermore, for example, if a cooking recipe search is performed at 5:30 p.m. on October 9, 2023, shopping information for the afternoon of October 9, 2023 is used to calculate the shopping motivation index. If the evaluation index for the day of the week information is 10, the evaluation index for the weather information is 10, and the evaluation index for the refrigerator inventory index is 5, the sum of these values, 25, is calculated as the shopping motivation index.

[0107] If the threshold T1 for determining whether the shopping motivation index is high or not is 20, at 10:30 on October 9, 2023, the shopping motivation index will be determined to be low, and at 17:30 on October 9, 2023, the shopping motivation index will be determined to be high.

[0108] Next, a specific example of the calculation result of the cooking motivation index will be described.

[0109] The cooking motivation index is calculated starting from the time when the user searches for a cooking recipe in the app using the meal suggestion device 100. Note that the cooking motivation index may also be calculated at a predetermined timing, such as a specific time.

[0110] For example, if a cooking recipe search is performed at 10:30 on October 9, 2023, cooking information from 4:30 on October 9, 2023, six hours earlier, to the time of the search, is used to calculate the cooking motivation index. If the count result of the recipe search flag is 0 and the count result of the recipe detail viewing flag is 0, these values ​​are added together to calculate the cooking motivation index (0).

[0111] For example, if a cooking recipe search is performed at 17:30 on October 9, 2023, cooking information from 11:30 on October 9, 2023, six hours earlier, to the time of the search, is used to calculate the cooking motivation index. If the count result of the recipe search flag is 4 and the count result of the recipe detail viewing flag is 8, these values ​​are added together to calculate a cooking motivation index of 12.

[0112] If the threshold T2 for determining whether the cooking motivation index is high or not is 10, at 10:30 on October 9, 2023, the cooking motivation index will be determined to be low, and at 17:30 on October 9, 2023, the cooking motivation index will be determined to be high.

[0113] Therefore, at 10:30 on October 9, 2023, it is determined that the shopping willingness index is low and the cooking willingness index is low, so meal candidates will be determined using the fourth method. Also, at 17:30 on October 9, 2023, it is determined that the shopping willingness index is high and the cooking willingness index is high, so meal candidates will be determined using the first method.

[0114] The first method will be described below with reference to Fig. 14, which is a diagram for explaining the first method.

[0115] In the first method, the processor 110 selects at least one food item from all types of food (food selection). The processor 110 then determines one or more meal candidates that include the at least one selected food item, such that meal candidates requiring a high cooking load are prioritized (recipe selection). The one or more meal candidates determined by the first method are an example of one or more fifth meal candidates.

[0116] Specifically, the processor 110 selects foods from all types of foods based on the evaluation index for the seasonal period. "All types of foods" refers not only to foods managed as in stock in the inventory management DB 151, but also to all types of foods managed in the food DB 153, all types of foods available for purchase from stores by the user, or all foods managed in the food DB 153 and foods available for purchase from stores by the user. The processor 110 prioritizes the selection of foods calculated with a high evaluation index. The processor 110 then evaluates each meal candidate (cooking recipe) based on the evaluation index for the content rate of the food in stock, the evaluation index for seasonality (temperature sensation), and the evaluation index for newly added foods, and determines one or more meal candidates to present to the user based on the evaluation index (meal selection index) of the evaluation results.

[0117] FIG. 15 is a diagram showing an example of an evaluation index for evaluating food products.

[0118] Uncooked food ingredients have designated peak seasons. The peak seasons include three periods: the first week, an intermediate period, and a final week. The peak seasons indicate, for example, periods when ingredients are most readily available, with the greatest amount of ingredients being available during the intermediate period. For this reason, the highest evaluation index is set for the intermediate period, and lower evaluation indexes are set for the first week and the final week than for the intermediate period. The evaluation indexes for peak seasons may be stored, for example, in food DB 153.

[0119] FIG. 16 is a diagram showing an example of an evaluation index for evaluating meal candidates.

[0120] Based on the information shown in Figure 16, an evaluation index corresponding to the content rate of the stored food contained in the meal candidate, an evaluation index corresponding to the seasonality (temperature sensation) of the meal candidate, and an evaluation index corresponding to the period since the meal candidate was newly added (recency of the meal candidate) are calculated.

[0121] For example, the processor 110 may calculate the meal selection index by multiplying an evaluation index corresponding to the content rate of owned foods contained in the meal candidates, an evaluation index corresponding to the seasonality (temperature sensation) of the meal candidates, and an evaluation index corresponding to the period since the meal candidates were newly added, or may calculate the meal selection index by adding these together, or may calculate the meal selection index by weighted addition. Furthermore, the processor 110 may calculate the meal selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the content rate of owned foods contained in the meal candidates, the evaluation index corresponding to the seasonality (temperature sensation) of the meal candidates, and the evaluation index corresponding to the period since the meal candidates were newly added.

[0122] Next, the second method will be described with reference to FIG.

[0123] In the second method, processor 110 selects at least one food item from all types of food. Then, processor 110 determines one or more meal candidates that include the at least one selected food item and prioritize meal candidates that require a small amount of effort to cook. The one or more meal candidates determined by the second method are an example of one or more sixth meal candidates.

[0124] Specifically, if the meal candidate is a recipe candidate represented by a cooking recipe, processor 110 calculates a meal selection index for the recipe candidate based on evaluation indices related to the cooking time, the number of steps required for cooking, and the number of foods (e.g., the number of foods and seasonings) included in the recipe candidate. Furthermore, if the meal candidate is a take-out meal candidate represented by a ready-to-eat meal, processor 110 calculates a meal selection index for the take-out meal candidate based on evaluation indices related to the price of the take-out meal candidate and the time required to purchase the take-out meal candidate. Processor 110 then determines one or more meal candidates to present to the user in descending order of the evaluation results' evaluation index (meal selection index). The time required to purchase the take-out meal candidate may be calculated based, for example, on the distance from the user's home or current location to a take-out meal store and the mode of transportation.

[0125] FIG. 18 is a diagram showing an example of evaluation indexes for evaluating recipe candidates.

[0126] Based on the information shown in Figure 18, an evaluation index corresponding to the content rate of the stock food contained in the recipe candidate, an evaluation index corresponding to the number of steps in the recipe candidate, and an evaluation index corresponding to the cooking time of the recipe candidate are calculated.

[0127] For example, processor 110 may calculate the meal selection index by multiplying an evaluation index corresponding to the content rate of a stock food contained in a recipe candidate, an evaluation index corresponding to the number of steps in the recipe candidate, and an evaluation index corresponding to the cooking time of the recipe candidate, or by adding them together, or by weighted addition. Processor 110 may also calculate the meal selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the content rate of a stock food contained in a recipe candidate, the evaluation index corresponding to the number of steps in the recipe candidate, and the evaluation index corresponding to the cooking time of the recipe candidate. In this way, the meal selection index may be calculated by multiplying, adding, or weighted addition of multiple types of evaluation indexes, or by using a machine learning model such as a decision tree.

[0128] The evaluation index used to calculate the meal selection index may include an evaluation index related to the cooking method (for example, type of cooking such as frying, baking, or boiling).

[0129] FIG. 19 is a diagram showing an example of evaluation indexes for evaluating candidate ready-to-eat meals.

[0130] Based on the information shown in Figure 19, an evaluation index corresponding to the price of the candidate take-out meal and an evaluation index corresponding to the time required to purchase the candidate take-out meal are calculated. Note that the candidate take-out meal information indicating the candidate take-out meals is obtained from an external device that manages store information regarding stores that sell candidate take-out meals. The store information includes candidate take-out meal information. The external device that manages the store information may be a device managed by a company that operates the store, or it may be a device managed by a company that collectively manages store information for different stores.

[0131] For example, processor 110 may calculate the meal selection index by multiplying the evaluation index corresponding to the price of the ready-to-eat meal candidate and the evaluation index corresponding to the time required to purchase the ready-to-eat meal candidate together, or by adding them together, or by weighted addition. Processor 110 may also calculate the meal selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the price of the ready-to-eat meal candidate and the evaluation index corresponding to the time required to purchase the ready-to-eat meal candidate.

[0132] Next, the third method will be described with reference to FIG.

[0133] In the third method, processor 110 selects one food item from one or more held foods. Then, processor 110 determines one or more meal candidates that include at least one selected held food item, such that meal candidates requiring a high cooking load are prioritized. The one or more meal candidates determined by the third method are an example of one or more seventh meal candidates.

[0134] Specifically, the processor 110 calculates a food selection index for each food based on the expiration date of the food, the number of days since the food was registered as owned, and an evaluation index related to the recent usage history of the food. The processor 110 then evaluates each meal candidate (cooking recipe) based on the evaluation index for the content rate of the owned food, the evaluation index for seasonality (temperature sensation), and the evaluation index for newly added food, and determines one or more meal candidates to be presented to the user based on the evaluation results with the highest evaluation index (meal selection index).

[0135] FIG. 21 is a diagram showing an example of evaluation indexes for evaluating food products.

[0136] 21 , a food selection index for a food is calculated based on the food's expiration date, the number of days since the food was registered as owned, and an evaluation index related to the food's recent usage history. For example, processor 110 may calculate the food selection index by multiplying the evaluation index corresponding to the food's expiration date, the evaluation index corresponding to the number of days since the food was registered as owned, and the evaluation index corresponding to the food's recent usage history, or by adding them together, or by weighted addition. Furthermore, processor 110 may calculate the food selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the food's expiration date, the evaluation index corresponding to the number of days since the food was registered as owned, and the evaluation index corresponding to the food's recent usage history.

[0137] FIG. 22 is a diagram showing an example of an evaluation index for evaluating meal candidates.

[0138] Based on the information shown in Figure 22, an evaluation index corresponding to the content rate of the stored food contained in the meal candidate, an evaluation index corresponding to the seasonality (temperature sensation) of the meal candidate, and an evaluation index corresponding to the period since the meal candidate was newly added (recency of the meal candidate) are calculated.

[0139] For example, the processor 110 may calculate the meal selection index by multiplying an evaluation index corresponding to the content rate of owned foods contained in the meal candidates, an evaluation index corresponding to the seasonality (temperature sensation) of the meal candidates, and an evaluation index corresponding to the period since the meal candidates were newly added, or may calculate the meal selection index by adding these together, or may calculate the meal selection index by weighted addition. Furthermore, the processor 110 may calculate the meal selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the content rate of owned foods contained in the meal candidates, the evaluation index corresponding to the seasonality (temperature sensation) of the meal candidates, and the evaluation index corresponding to the period since the meal candidates were newly added.

[0140] Next, the fourth method will be described. Fig. 23 is a diagram for explaining the evaluation index for eating out and taking out meals used in the fourth method.

[0141] In the fourth method, the processor 110 determines one or more meal candidates from the plurality of meal candidates such that meal candidates requiring a small amount of cooking effort are prioritized. The one or more meal candidates determined by the fourth method are an example of the one or more eighth meal candidates.

[0142] The cooking load is calculated so that it is smaller the shorter the cooking time, the fewer the number of cooking steps, and the fewer the number of foods included in the recipe candidate. A low cooking load means that the load is smaller than a predetermined load (a load threshold). Specifically, when a meal candidate is a recipe candidate represented by a cooking recipe, the processor 110 calculates the meal selection index of the recipe candidate based on evaluation indices related to the cooking time, the number of cooking steps, and the number of foods included in the recipe candidate (e.g., the number of foods and seasonings used). The evaluation indices used to calculate the meal selection index may also include an evaluation index related to the cooking method (e.g., the type of cooking, such as frying, baking, or boiling). The cooking load is calculated based on the difficulty of the cooking method. The difficulty of the cooking method may be preset depending on the cooking method. Furthermore, when a meal candidate is a take-out meal candidate represented by a take-out meal, the processor 110 calculates the meal selection index of the take-out meal candidate based on evaluation indices related to the price of the take-out meal candidate and the time required to purchase the take-out meal candidate. Furthermore, when the meal candidate is a dining-out candidate represented by "eating out," the processor 110 calculates a meal selection index for the dining-out candidate based on the business hours of the restaurant that offers the dining-out candidate and an evaluation index related to the distance from the current location to the restaurant. The processor 110 then determines one or more meal candidates to present to the user in descending order of the evaluation index (meal selection index) of the evaluation results. Note that the meal candidates are not limited to ready-meal candidates or dining-out candidates, but may also include meal delivery candidates or meal delivery candidates. Meal delivery candidates or meal delivery candidates indicate meal candidates that will be delivered to the user by a service provider.

[0143] FIG. 24 is a diagram showing an example of evaluation indexes for evaluating candidate ready-to-eat meals and candidate eating-out meals.

[0144] Based on the information shown in FIG. 24, an evaluation index corresponding to the opening hours of the restaurant that offers the dining out candidate and an evaluation index corresponding to the distance from the current location to the restaurant are calculated.

[0145] For example, processor 110 may calculate the meal selection index by multiplying an evaluation index corresponding to the business hours of a restaurant that offers a dining out candidate and an evaluation index corresponding to the distance from the current location to the restaurant, or by adding them together, or by weighted addition. Processor 110 may also calculate the meal selection index using a machine learning model such as a decision tree based on the evaluation index corresponding to the business hours of a restaurant that offers a dining out candidate and an evaluation index corresponding to the distance from the current location to the restaurant.

[0146] The evaluation index of the recipe candidate and the evaluation index of the ready-to-eat meal candidate may be calculated in the same manner as in the second method.

[0147] Returning to FIG. 3 , the processor 110 then generates presentation information including one or more meal candidates determined by any one of the first, second, third, and fourth methods, and outputs the generated presentation information (S21). The presentation information is output from the output IF 160. For example, as shown in FIG. 25 , the presentation information 161 is displayed on a display provided in the meal suggestion device 100. For example, the presentation information 161 may display one or more determined meal candidates with priority over other meal candidates. The presentation information 161 may display one or more determined meal candidates (e.g., “recommended recipes (time-saving)”) at the top of the screen. When multiple meal candidates are determined as the one or more meal candidates, the higher the meal selection index, the higher the priority. For example, multiple icons included in “recommended recipes (time-saving)” each represent the multiple determined meal candidates, and the meal candidates indicated by the icons located on the left side are displayed with priority over the meal candidates indicated by the icons located on the right side.

[0148] 26, the presented information 162 may include only a plurality of meal candidates determined by a method executed according to the level of the shopping motivation index and cooking motivation index. In this case, meal candidates indicated by icons arranged at the top are displayed in priority over meal candidates indicated by icons arranged at the bottom.

[0149] The presented information is not limited to suggesting only one or more meal candidates determined by a method executed according to the levels of the shopping willingness index and cooking willingness index, and may also display one or more meal candidates determined by other methods. In this case, the one or more meal candidates determined by a method executed according to the levels of the shopping willingness index and cooking willingness index are displayed in priority over one or more meal candidates determined by other methods. Displaying the meal candidates in priority may include displaying them at the top, displaying them with a larger icon than the other meal candidates, displaying them in bolder font than the other meal candidates, or displaying them in a frame for emphasis.

[0150] [Effects, etc.] According to the meal suggestion system 1 of this embodiment, when the user's shopping motivation is high, one or more first meal candidates are determined, which include at least one food selected from all types of food, regardless of whether the food is owned by the user. When the user's shopping motivation is low, one or more second meal candidates are determined, which include one owned food. In this way, when the user's shopping motivation is high, a variety of meals can be suggested to the user, and when the user's shopping motivation is low, meals can be suggested to the user to consume the owned food. Therefore, the user can be encouraged to consume food in a planned manner according to the user's shopping motivation.

[0151] Furthermore, according to the meal suggestion system 1, when the user's motivation to cook is high, one or more first meal candidates that require a high cooking load are determined, and when the user's motivation to cook is low, one or more second meal candidates that require a low cooking load are determined. Thus, meal candidates can be suggested according to the user's motivation to cook.

[0152] [Other Examples of Presentation Information] (1) As shown in Fig. 27, the presentation information 163 may include recipe details. When displaying the recipe details, for example, if it is determined that the user has a low desire to shop and a high desire to cook, and a cooking recipe including a food item not included in the food items in the user's possession is proposed as a meal candidate, the user may be prompted to purchase missing ingredients from an online supermarket.

[0153] (2) As shown in Figure 28, the presented information 164 may include details of a take-out meal menu. When displaying the details of the take-out meal menu, information about the opening hours of the store that offers the take-out meal and information about delivery ordering services may be presented. In addition, information encouraging the user to order food items that are low in stock may be presented.

[0154] [Modification] In the above embodiment, the meal suggestion system 1 has been described as including only the meal suggestion device 100, but this is not limiting. The meal suggestion system 1 may also include a mobile terminal owned by a user and a meal suggestion device. The mobile terminal has the functions of the meal suggestion device 100 in the embodiment for accepting input from the user and presenting presented information to the user. The meal suggestion device has all the functions of the meal suggestion device 100 except for the input IF 120 and the output IF 160. In this way, the meal suggestion system 1 may also include two devices: a mobile terminal and a meal suggestion device. The mobile terminal and the meal suggestion device are connected to each other via a network so that they can communicate with each other.

[0155] (Other Embodiments) In the above-described embodiment, the meal recommendation system 1 may suggest meals over multiple dates. In this case, a previously suggested meal may be re-suggested based on the cooking motivation index and shopping motivation index for that day. This allows the previously suggested meal to be effectively utilized to consume the food in the event that the number of foods managed as in stock in the inventory management DB 151 increases after the user has shopped for the suggested food, or in the event that the food to be used in the previously suggested meal is in stock, such as when the food planned for use by the user is not cooked. For example, the re-suggested meal may be suggested when multiple future meals are suggested, or may be suggested only the next time the meal is suggested. Furthermore, the re-suggested meal may be a meal that has already been suggested, not limited to a meal from a past date, but may also be a meal that has been suggested for a future date.

[0156] In the above-described embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may also be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0157] Each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or each may be a separate circuit. Each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0158] Furthermore, the general or specific aspects of the present disclosure may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a computer-readable non-transitory recording medium.

[0159] For example, the present disclosure may be realized as a meal suggestion method executed by a meal suggestion device (computer or DSP), or may be realized as a program for causing a computer or DSP to execute the meal suggestion method.

[0160] In the above-described embodiments, the processes executed by a specific processing unit may be executed by another processing unit. The order of the processes in the operation of the meal suggestion device described in the above-described embodiments may be changed, and the processes may be executed in parallel.

[0161] In addition, this disclosure also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art would think of, or forms realized by arbitrarily combining the components and functions of each embodiment within the scope that does not deviate from the intent of this disclosure.

[0162] The present disclosure is useful as a meal suggestion system that can encourage a user to consume food in a planned manner according to the user's shopping motivation.

[0163] 1 Meal recommendation system 11 to 15 Food 100 Meal recommendation device 110 Processor 120 Input IF 130 Main memory 140 Communication IF 150 Storage 151 Inventory management DB 152 Meal recommendation DB 153 Food DB 160 Output IF

Claims

1. Equipped with one or more processors, The one or more processors mentioned above are: The system acquires information about one or more food items owned by the user, information about multiple meal options, and external information stored on an external device, including at least the user's shopping information. By analyzing the aforementioned external information, the user's willingness to go out and shop is estimated. If the shopping intent is high as a result of the estimation of the shopping intent, (i) one or more first meal candidates are determined from the multiple meal candidates, including at least one food item selected from all types of food, and (ii) first presentation information including the one or more first meal candidates that were determined is output. If the shopping intention is low as a result of the estimation of the shopping intention, (i) one or more second meal candidates are determined from the multiple meal candidates, including at least one food item selected from the one or more food items that the user possesses, and (ii) second presentation information including the one or more second meal candidates that were determined is output. A meal suggestion system.

2. The external information further includes a refrigerator inventory index The meal suggestion system according to claim 1.

3. The one or more processors estimate the user's shopping intent based on at least one of the following: shopping day information regarding the likelihood of the user going shopping on each day of the week; shopping weather information regarding the likelihood of the user going shopping in each weather condition; and total quantity information regarding the total amount of the one or more food items the user possesses. The meal suggestion system according to claim 1.

4. The one or more processors mentioned above are: Obtain user information relating to the aforementioned user, By analyzing the user information, the user's willingness to cook is estimated. If the cooking motivation is high as a result of the estimation of the cooking motivation, (i) one or more third meal candidates are selected from the multiple meal candidates such that meal candidates requiring a large cooking burden are prioritized, and (ii) third presentation information including the selected one or more third meal candidates is output. If the cooking motivation is low as a result of the estimation of the cooking motivation, (i) one or more fourth meal candidates are selected from the multiple meal candidates so that meal candidates with a low burden are prioritized, and (ii) fourth presentation information including the one or more selected fourth meal candidates is output. A meal suggestion system according to any one of claims 1 to 3.

5. The aforementioned list of meal candidates includes a cooking recipe that shows the procedure and ingredients for preparing the meal candidate, The user information includes recipe interest information regarding interest in the cooking recipes, The one or more processors mentioned above are: The cooking motivation is estimated based on at least one of the following: recipe interest information, cooking equipment information relating to cooking equipment owned by the user, family information indicating the user's family structure, the user's location information, and schedule information indicating the user's schedule. The meal suggestion system according to claim 4.

6. The one or more processors mentioned above are: If the desire to shop is high and the desire to cook is high, (i) one or more fifth meal candidates are determined from the plurality of meal candidates such that meal candidates that include at least one food selected from all types of food and that require a large amount of preparation are given priority, and (ii) fifth presentation information including the one or more determined fifth meal candidates is output. If the desire to shop is high and the desire to cook is low, (i) one or more sixth meal candidates are determined from the plurality of meal candidates such that meal candidates that include at least one food selected from all types of food and that require little effort to prepare are given priority, and (ii) sixth presentation information including the one or more sixth meal candidates that have been determined is output. If the desire to shop is low and the desire to cook is high, (i) one or more seventh meal candidates are determined from the plurality of meal candidates such that meal candidates that include at least one food item selected from the one or more food items that are in possession and that require a large amount of effort to prepare are given priority, and (ii) seventh presentation information including the one or more seventh meal candidates that have been determined is output. If the desire to shop is low and the desire to cook is low, (i) one or more eighth meal candidates are selected from the multiple meal candidates so that meal candidates with less cooking burden are prioritized, and (ii) eighth presentation information including the selected one or more eighth meal candidates is output. The meal suggestion system according to claim 4.

7. The one or more processors, in determining the one or more fifth meal candidates, For each of the one or more meal candidates among the aforementioned multiple meal candidates, which include at least one food selected from all types of food, Based on the content of one or more of the aforementioned food items, the seasonality of the meal candidate, and the novelty of the meal candidate, the meal selection index for the meal candidate is calculated. From the above one or more meal candidates, the above one or more fifth meal candidates are determined in order of the highest meal selection index. The meal suggestion system according to claim 6.

8. The aforementioned multiple meal candidates include one or more recipe candidates represented by cooking recipes and one or more ready-to-eat meal candidates representing ready-to-eat meals. The one or more processors, in determining the one or more sixth meal candidates, For each of the one or more recipe candidates mentioned above, a meal selection index for that recipe candidate is calculated based on at least one of the following: the cooking time required for that recipe candidate, the number of steps required for that recipe candidate, and the number of food items used in that recipe candidate. For each of the one or more prepared meal candidates mentioned above, a meal selection index for that prepared meal candidate is calculated based on at least one of the price of the prepared meal candidate and the time required to purchase the prepared meal candidate. From the aforementioned list of meal candidates, one or more sixth meal candidates are selected in order of the highest meal selection index. The meal suggestion system according to claim 6.

9. The one or more processors, in determining the one or more seventh meal candidates, For each of the one or more meal candidates among the aforementioned multiple meal candidates, which includes at least one food item selected from the one or more food items mentioned above, Based on the content of one or more of the aforementioned food items, the seasonality of the meal candidate, and the novelty of the meal candidate, the meal selection index for the meal candidate is calculated. From the above one or more meal candidates, the above one or more seventh meal candidates are determined in order of the highest meal selection index. The meal suggestion system according to claim 6.

10. The aforementioned multiple meal candidates include one or more recipe candidates represented by cooking recipes, one or more ready-to-eat meal candidates representing ready-to-eat meals, and one or more restaurant meal candidates representing eating out. The one or more processors, in determining the one or more eighth meal candidates, For each of the one or more recipe candidates mentioned above, a meal selection index for that recipe candidate is calculated based on at least one of the following: the cooking time required for that recipe candidate, the number of steps required for that recipe candidate, and the number of food items used in that recipe candidate. For each of the one or more prepared meal candidates mentioned above, a meal selection index for that prepared meal candidate is calculated based on at least one of the price of the prepared meal candidate and the time required to purchase the prepared meal candidate. For each of the one or more restaurant options mentioned above, a meal selection index for that restaurant option is calculated based on at least one of the following: the operating hours of the restaurant offering the restaurant option and the distance from the current location to the restaurant. From one or more meal candidates, one or more eighth meal candidates are selected in order of the highest meal selection index. The meal suggestion system according to claim 6.

11. A meal suggestion method executed by one or more processors, The system acquires information about one or more food items owned by the user, information about multiple meal options, and external information stored on an external device, including at least the user's shopping information. By analyzing the aforementioned external information, the user's willingness to go out and shop is estimated. If the shopping intent is high as a result of the estimation of the shopping intent, (i) one or more first meal candidates are determined from the multiple meal candidates, including at least one food item selected from all types of food, and (ii) first presentation information including the one or more first meal candidates that were determined is output. If the shopping intention is low as a result of the estimation of the shopping intention, (i) one or more second meal candidates are determined from the multiple meal candidates, including at least one food item selected from the one or more food items that the user possesses, and (ii) second presentation information including the one or more second meal candidates that were determined is output. Methods for suggesting meals.

12. A program for causing a computer to execute the meal suggestion method described in claim 11.