Cooking method determination system and cooking method determination method

Abstract

To provide a cooking method determination system and a cooking method determination method which allow for appropriately and easily determining excess and deficiency of contents of nutrients.SOLUTION: A cooking method determination system 100 includes: a machine learning unit 30 which generates a learning model by using affector data in a cooking process of processed foods and data on nutrient contents which change depending on affectors; a learning model recording unit 32 which records the learning model generated by learning; an estimated value calculation unit 33 which calculates estimated values of nutrient contents in the processed foods by using the learning model; a prescribed value recording unit 34 which records prescribed values of nutrient contents set for the respective processed foods; and a determination unit 35 which reads the respective prescribed values of nutrient contents from the prescribed value recording unit 34 and compares them with estimated values to determine whether or not the nutrient contents are within the prescribed values.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a cooking method determination system and a cooking method determination method. [Background technology]

[0002] Many consumers worry about what kind of diet they should follow to maintain their health. To address this concern, there is a need for optimized nutritional foods, which are ideal meals containing essential nutrients. Optimized nutritional foods as processed foods require not only recipes that include essential nutrients, but also consideration of variations in ingredients, processing, and changes in nutrients during the sales period. However, depending on cooking and storage conditions, nutrients can decay. Vitamins, in particular, lose their content during the processes of combining ingredients, processing, and storage, so careful consideration must be given to the selection and content of ingredients when designing recipes.

[0003] In designing such recipes, it is necessary to predict and determine whether the nutrient content will remain within specified values ​​during consumption, taking into consideration the nutrients contained in the processed food's ingredients, the environmental conditions of heat and light during the processing process, and the product form (e.g., frozen, room temperature, solid, liquid, etc.). Conventionally, processed food recipes have been designed by collecting experimental data on the changes in nutrient content caused by changing the set values ​​of processing conditions for various combinations of ingredients and / or nutrients, and predicting the changes in nutrients using the experimental data. Examples of this type of technology are described in Patent Documents 1 and 2.

[0004] Patent Document 1 relates to a recipe customization support system and method that, when a change in the component value of a specific nutrient contained in a dish is accepted from information on the ingredients, amounts, and cooking conditions used in the dish, changes the amounts and ingredients based on information on each ingredient and cooking, and provides a customized recipe. Patent Document 2 relates to a recipe nutritional value calculation device and recipe nutritional value calculation program that calculates the nutritional value contained in ingredients for each recipe and provides it to the user. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-139694 [Patent Document 2] Japanese Patent Application Laid-Open No. 2003-216737 Summary of the Invention [Problem to be solved by the invention]

[0006] However, predicting changes in nutrients through the accumulation of experimental data requires experimental data suited to a variety of conditions, which limits the development of diverse processed food recipes. In addition, processed foods often require recipe adjustments from the perspective of taste and flavor, making it difficult to predict whether the nutrient content is adequate for each condition.

[0007] The present invention has been made in view of the above circumstances, and aims to provide a cooking method determination system and cooking method determination method that can appropriately and easily determine whether the nutrient content is excessive or insufficient. [Means for solving the problem]

[0008] In order to achieve the above-mentioned object, one aspect of the present invention is a cooking method determination system having a machine learning means for generating a learning model using data on influencing factors in the cooking process of processed foods and data on nutrient content that changes due to the influencing factors, a learning model recording means for recording the learning model generated by learning, an estimated value calculation means for calculating an estimated value of the nutrient content in the processed food using the learning model, a specified value recording means for recording specified values ​​of the nutrient content set for each of the processed foods, and a determination means for reading the specified values ​​of each nutrient from the specified value recording means and comparing them with the estimated values ​​to determine whether the nutrient content is within the specified value.

[0009] Another aspect of the present invention is a cooking method determination method using a computer, comprising: a machine learning step of performing machine learning to generate a learning model using data on influencing factors in the cooking process of processed foods and data on nutrient contents that change due to the influencing factors; a learning model recording step of recording the learning model generated by learning; an estimated value calculation step of calculating an estimated value of the nutrient content in the processed foods using the learning model; a specified value recording step of recording specified values ​​of the nutrient content set for each of the processed foods; and a determination step of reading out the specified values ​​for each nutrient recorded in the specified value recording step and comparing them with the estimated values ​​to determine whether the nutrient content is within the specified value. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide a cooking method determination system and a cooking method determination method that can appropriately and easily determine whether a nutrient content is excessive or insufficient. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram showing a cooking method determination system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing a hardware configuration of an information processing device of a cooking method determination system according to an embodiment of the present invention. FIG. [Figure 3] 10 is a table showing examples of ingredients corresponding to recipes. [Figure 4] 1 is a table showing an example of nutrients corresponding to ingredients. [Figure 5] 10 is a table showing an example of the amount of change in nutrients for each recipe. [Figure 6] 1 is a table showing the decay rate of nutrients over time. [Figure 7] 1 is a table showing cooking conditions and storage conditions for each recipe. [Figure 8] 10 is a flowchart showing an example of the processing flow from construction of a learning model to recording. [Figure 9]1 is a table showing ingredient and cooking substitution data. [Figure 10] 10 is a flowchart showing an example of the flow of a nutrient content determination process performed by the cooking method determination system according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0013] <System configuration> First, the overall system configuration will be described. Figure 1 shows a cooking method determination system 100 according to one embodiment of the present invention. The cooking method determination system 100 provides a service that predicts the decay of nutrient content in recipe designs for nutritionally optimized meals and the like, and presents users with recipe designs that meet nutrient content requirements from processing to sales. In this embodiment, for example, a recipe (optimized nutritional diet) is prepared and saved according to a recipe, and nutrient decay data is collected. At this time, data (auxiliary data) related to pH, moisture content, heating time, storage temperature, light, etc. are also collected. Then, a learning model is generated using the auxiliary data and the nutrient decay results as learning data. By using such a learning model, it is possible to estimate (predict) the amount of nutrient decay when cooking and storing in a specific manner. For example, when developing a new recipe, it is possible to estimate the nutrient decay corresponding to the process based on the input of ingredients and steps. It is also possible to suggest changes to the cooking method based on the estimation results, suggest the addition of ingredients, or suggest a different menu to combine with missing nutrients.

[0014] The cooking method determination system 100 is realized by an information processing device 1 that transmits and receives various information to and from a user terminal 2 via a communication network such as the Internet. The information processing device 1 functions as a server that provides the user terminal 2 with various information related to cooking methods and nutrients.

[0015] The user terminal 2 is an information processing device used by a user or the like who is considering recipe design. The user terminal 2 is configured by a personal computer, a tablet, a smartphone, or the like. The user terminal 2 may exchange various types of information with the information processing device 1 using a pre-installed program, or may exchange various types of information via a web browser.

[0016] <Hardware configuration> Next, we will explain an example of hardware that makes up the information processing device 1. Fig. 2 is a block diagram showing the hardware configuration of the information processing device 1 of the cooking method determination system 100 according to this embodiment. The information processing device 1 includes a CPU (Central Processing Unit) 11 as a processor, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20.

[0017] The CPU 11 executes various processes in accordance with programs recorded in the ROM 12 or programs loaded from the storage unit 18 into the RAM 13. The RAM 13 also stores data and the like required for the CPU 11 to execute various processes. The CPU 11, the ROM 12, and the RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14.

[0018] The input / output interface 15 is connected to an output unit 16, an input unit 17, a memory unit 18, a communication unit 19, and a drive 20. The output unit 16 is composed of a display, a speaker, etc., and outputs various information as images and sounds. The input unit 17 is composed of a keyboard, a mouse, a touch play display, etc., and inputs various information. The memory unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), etc., and stores various data. The communication unit 19 communicates with other devices via a network including the Internet.

[0019] Removable media 21, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately attached to the drive 20. Programs read from the removable media 21 by the drive 20 are installed in the storage unit 18 as needed. The removable media 21 can also store various data stored in the storage unit 18 in the same way as the storage unit 18.

[0020] The hardware configuration described here is merely an example. The computer described in this embodiment including the information processing device 1 may have a configuration common to that of FIG. 2, or a different configuration. For example, the user terminal 2 in FIG. 1 may have a configuration similar to the hardware configuration shown in FIG. 2, or a different configuration. Furthermore, the computer may be configured by two or more computers.

[0021] <Functional configuration> Next, we will explain the functional configuration of the information processing device 1. As shown in Fig. 1, the information processing device 1 includes a machine learning unit 30, a classification determination unit 31, a learning model recording unit 32, an estimated value calculation unit 33, a specified value recording unit 34, a determination unit 35, a presentation unit 36, and a material recording unit 40 as functional units realized on a processor (CPU 11).

[0022] The machine learning unit 30 is a machine learning means for performing supervised learning or the like using a data set including data on influential factors in the cooking process of processed foods and data on nutrient contents that change due to the influential factors. The data set may be, for example, material property data, chemical property data, environmental property data, etc. An example of the data set used for machine learning will be described with reference to FIGS. 3 to 7.

[0023] The ingredient property data indicating the properties of ingredients will be described with reference to Figures 3 and 4. Figure 3 is a table showing an example of ingredients corresponding to a recipe. The table in Figure 3 displays ingredients corresponding to a recipe ID that identifies the recipe as a processing method, and information for specifying the amount of the ingredient. In this example, white sauce, cheese, ham, chicken, penne, bacon, mushrooms, tomatoes, etc. are displayed as ingredients. Numbers are also displayed as information indicating the amount of each ingredient. A 0 in the table indicates that the ingredient is not used.

[0024] FIG. 4 is a table showing an example of nutrients corresponding to ingredients. The table in FIG. 4 displays information for identifying the amount of nutrients (mg) contained per a given weight (100g) of ingredient. In this example, vitamin C, vitamin A, calcium, and iron are shown as nutrients corresponding to the ingredients. The ingredients shown in FIG. 4 correspond to the ingredients shown in FIG. 3.

[0025] Chemical property data showing changes in the nutrients of ingredients will be described with reference to Figures 5 and 6. Figure 5 is a table showing an example of the amount of change in nutrients for each recipe. The table in Figure 5 displays the nutrient content before and after cooking corresponding to the recipe ID, related information related to the nutrients, and test information. In this example, the initial vitamin C content and initial calcium content are shown as the nutrient content before cooking, and the post-cooking vitamin C content and post-cooking calcium content are shown as the nutrient content after cooking. In addition, the pH value and moisture content (%) are shown as related information related to the nutrients. Furthermore, the test information shows the number of tests conducted to identify the nutrient content before and after cooking for each recipe. Note that data with a test count of 0 is a theoretical value extracted from a paper or the like. When the test is performed multiple times, the content may be the average value of the multiple tests, or a value weighted according to the importance of the test data.

[0026] Figure 6 is a table showing the nutrient decay rate that changes over time. The table in Figure 6 displays the elapsed period, the nutrient decay rate corresponding to the elapsed period, and test information. In this example, the elapsed period is shown in months, with the period immediately after processing being set to 0. Additionally, the vitamin C decay rate (%) and calcium decay rate (%) corresponding to the elapsed period (elapsed months) are shown as nutrient decay rates. Furthermore, the test information shows the number of tests conducted to confirm the nutrient decay rate. Note that data with a test count of 0 is a theoretical value extracted from a paper or the like. When using theoretical values ​​extracted from papers, etc., it is assumed that the decay rate will be that of a single nutrient. However, this is not limited to this, and if the decay rate for each recipe can be measured (estimated), it is advisable to use the decay rate for that recipe.

[0027] With reference to FIG. 7, the environmental characteristic data indicating cooking conditions and storage conditions will be described. FIG. 7 is a table showing cooking conditions and storage conditions for each recipe. The table in FIG. 7 displays information indicating cooking conditions corresponding to a recipe ID, information indicating storage conditions, and test information. In this example, cooking temperature (°C) and heating time (minutes) are displayed as information indicating cooking conditions. Furthermore, freezing temperature (°C), freezing period, irradiated light (lux), irradiation period of irradiated light, and packaging form are displayed as information indicating storage conditions. Furthermore, the test information shows the number of tests in which cooking and storage were performed while satisfying the cooking and storage conditions. Note that data with a number of tests of 0 is a theoretical value extracted from a paper or the like.

[0028] Next, the classification determination unit 31 will be described. The classification determination unit 31 is a classification determination means that determines the reliability of data in a dataset based on test information and a preset determination criterion. The classification determination unit 31 of this embodiment performs processing to classify the data included in the dataset into highly reliable first influence factor data and less reliable second influence factor data, using the number of tests as a criterion for reliability.

[0029] For example, a case will be described in which a judgment criterion is set such that if the number of tests is two or more (a predetermined number of times), it is judged to be reliable first influence factor data, and if the number of tests is less than two (a predetermined number of times), it is judged to be unreliable second influence factor data. In this case, the number of tests for recipe ID "A0001" in the table of Fig. 5 is three, so it is judged to be first influence factor data. On the other hand, the number of tests for recipe IDs "A0002" and "A0003" is zero, so it is judged to be second influence factor data.

[0030] Next, the learning model recording unit 32 is a learning model recording means that performs a process of storing a learning model in the storage unit 18 using a data set.

[0031] 8, the construction and recording of a learning model by the machine learning unit 30, the classification determination unit 31, and the learning model recording unit 32 will be described. Fig. 8 is a flowchart showing an example of the processing flow from construction to recording of a learning model.

[0032] In step S11, the classification determination unit 31 acquires data on influential factors in the processing and storage of processed foods and stores it in the memory unit 18. The influential factor data includes data on the recipes in the above-mentioned data set, ingredients for each recipe, the nutrient content of each ingredient (nutrient content before cooking), cooking conditions for the recipe, storage conditions, the time elapsed since processing, etc.

[0033] In step S12, the classification determination unit 31 acquires data on changes in nutrients due to the influencing factor data and stores the data in the storage unit 18. The data on changes in nutrients is data such as the nutrient content after cooking in the above-mentioned data set and the decay rate depending on the elapsed time, and is data corresponding to the influencing factors.

[0034] In step S13, the classification determination unit 31 performs a classification process to determine the reliability of the data for which the number of tests is set. The classification determination unit 31 of this embodiment classifies the data into first influence factor data with high reliability and second influence factor data with low reliability based on the number of tests set for each data in the data set.

[0035] In step S14, the classification determination unit 31 determines whether the data set has sufficient highly reliable data. For example, the classification determination unit 31 determines that sufficient data has been prepared when the number of first influence factor data is equal to or greater than a predetermined threshold value or when the number of first influence factor data accounts for a certain percentage or greater.

[0036] If it is determined that there is sufficient data required for learning, the process proceeds to step S15 (step S14; Yes). If it is determined that there is not enough data required for learning, the conditions for machine learning are not met, and the learning process ends.

[0037] In step S15, the machine learning unit 30 performs machine learning based on the influencing factor data sorted by the classification determination unit 31 and the data set of nutrient changes, and constructs a learning model.

[0038] In step S16, the learned model recording unit 32 stores the learned model in the memory unit 18 in order to use the learned model in determining a cooking method, which will be described later. Through this series of processes, the learned model becomes available to the information processing device 1.

[0039] Next, returning to FIG. 1, the estimated value calculation unit 33, the specified value recording unit 34, the determination unit 35, the presentation unit 36, and the material recording unit 40 will be described as functional units for determining the cooking method.

[0040] The estimated value calculation unit 33 is an estimated value calculation means that calculates an estimated value of the nutrient content of the processed food to be estimated. The estimated value calculation unit 33 calculates an estimated value of the nutrient content using the learning model made available by the learning model recording unit 32.

[0041] The specified value recording unit 34 is a specified value recording means for recording specified values ​​of nutrient contents set for each processed food (recipe). The specified values ​​are numerical values ​​that serve as a criterion for determining whether the nutrient contents are appropriate. Although the specified values ​​are not particularly limited, in this embodiment, an example will be described in which the specified values ​​are upper and / or lower limit values ​​that are set in advance for each nutrient to meet the predetermined standards in the optimized nutritional diet.

[0042] The determination unit 35 is a determination means for determining whether the estimated values ​​of the nutrient contents calculated by the estimated value calculation unit 33 are within specified values. The determination unit 35 reads out the specified values ​​of the nutrients recorded by the specified value recording unit 34 and compares them with the estimated values ​​of the nutrient contents.

[0043] The presentation unit 36 ​​is a presentation means for presenting alternative information for ingredients and / or cooking methods. The presentation unit 36 ​​presents alternative information for ingredients and / or cooking methods when the determination unit 35 determines that the estimated nutrient content does not match the specified value. The presentation unit 36 ​​can also present multiple types of alternative information if there are multiple variations in the alternative methods.

[0044] The material recording unit 40 is a material recording means for recording the material and cooking substitution data presented by the presentation unit 36.

[0045] Figure 9 is a table showing ingredient and cooking substitution data. The table in Figure 9 displays the target ingredient, substitute ingredient, cost evaluation, taste change, consumption threshold, and calorie change corresponding to the nutrient. In this example, vitamin C, calcium, and iron are shown as nutrients. The target ingredient is the ingredient that can be substituted, and green peppers, salmon, clams, etc. are shown.

[0046] There are multiple substitute ingredients (variations) for the same nutrient and target ingredient combination. For example, for the combination of vitamin C and bell peppers, a vitamin C additive is listed as the first substitute ingredient and lemon juice as the second substitute ingredient. For the combination of calcium and salmon, a calcium additive is listed as the first substitute ingredient and cheese as the second substitute ingredient. For the combination of iron and clams, an iron additive is listed as the first substitute ingredient and tofu as the second substitute ingredient.

[0047] A cost rating, a taste change, a usage threshold, and a calorie change are set for each substitute ingredient. The cost rating is a numerical value that indicates the degree of cost when changing to a substitute ingredient. The cost rating may be a numerical value that indicates direct monetary value, or may be an index that indicates the degree of cost increase. The taste change is information that indicates the degree of taste change when changing to a substitute ingredient. In this embodiment, if the degree of taste change is large, a value of "large" is set; if the degree of taste change is medium, a value of "medium" is set; if the degree of taste change is slight, a value of "slight" is set; and if the taste change is almost nonexistent or not noticeable, a value of "none" is set.

[0048] The usage threshold is a numerical value that serves as a reference for setting substitution information by the presentation unit 36. In this embodiment, the condition for presentation of substitution information by the presentation unit 36 ​​is that the estimated value of the nutrient decay rate is greater than the usage threshold. Note that the presentation unit 36 ​​may present a nutrient additive when the estimated value of the nutrient of the substitute material is equal to or less than the usage threshold.

[0049] The calorie change is a numerical value indicating the degree of calorie change when a substitute material is used. The calorie change may be a direct change in calories or an index indicating the degree of calories. The calorie change may also be used as a criterion for the presentation unit 36 ​​to select a substitute.

[0050] Next, a series of processes for determining a cooking method based on information input from the user terminal 2 will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of the flow of the process for determining nutritional content by the cooking method determination system 100 according to this embodiment.

[0051] In step S21, the estimated value calculation unit 33 acquires influential factor data on ingredients, processing, and storage in recipe design from the user terminal 2. The influential factor data includes data on the recipe, ingredients for each recipe, the nutrient content of each ingredient (nutrient content before cooking), cooking conditions for the recipe, storage conditions, the time elapsed since processing, etc.

[0052] In step S22, the estimated value calculation unit 33 inputs the influencing factor data acquired from the user terminal 2 into the learning model recorded by the learning model recording unit 32, and causes the learning model to calculate an estimated value of the nutrient content. The estimated value of the nutrient content output by the learning model includes, for example, the amount of change in the nutrient content after cooking using a recipe, the amount of change in the nutrient content due to the storage method, and the decay rate according to the elapsed time after processing.

[0053] In step S23, the determination unit 35 acquires a specified value corresponding to the recipe to be determined from the specified values ​​of the nutrient contents for each recipe recorded by the specified value recording unit 34.

[0054] In step S24, the determination unit 35 compares the estimated value of the nutrient content output by the learning model with the specified value of the nutrient content.

[0055] In step S25, if the estimated value satisfies the specified value, the determination unit 35 proceeds to step S26 (step S25; Yes). In step S26, the determination unit 35 displays on the user terminal 2 that the recipe design specified by the user matches the specified value. After the processing of step S26, the processing of the flowchart ends.

[0056] In step S25, if the estimated value does not satisfy the specified value, the determination unit 35 proceeds to step S27 (step S25; No). In step S27, the presentation unit 36 ​​acquires a substitute material corresponding to the target material that does not satisfy the specified value from the substitute materials recorded by the material recording unit 40.

[0057] In step S28, the presentation unit 36 ​​acquires a usage threshold value to be set for the acquired substitute material.

[0058] In step S29, the presentation unit 36 ​​determines whether the utilization threshold is greater than the estimated value of the attenuation rate. If the utilization threshold is greater than the estimated value of the attenuation rate, the presentation unit 36 ​​proceeds to step S30 (step S29; Yes). If the utilization threshold is equal to or less than the estimated value of the attenuation rate, the presentation unit 36 ​​proceeds to step S35 (step S29; No).

[0059] In step S30, if the threshold value for using the substitute ingredient is lower than the nutrient decay rate estimated in the initial recipe design, the presentation unit 36 ​​determines that the use of the substitute ingredient is effective, and creates influence factor data for the substitute ingredient.

[0060] In step S31, the estimated value calculation unit 33 inputs influential factor data corresponding to the substitute ingredient into the learning model, and causes the learning model to calculate an estimated value of the nutrient content of the recipe that reflects the substitute ingredient.

[0061] In step S32, if the estimated value of the recipe reflecting the substitute material satisfies the specified value, the determination unit 35 proceeds to step S33 (step S32; Yes).If the estimated value of the substitute material does not satisfy the specified value, the determination unit 35 proceeds to step S35 (step S32; No).

[0062] In step S33, the determination unit 35 determines whether the calorie change set for the substitute ingredient is less than a specified value. If the calorie change is less than the specified value, the determination unit 35 proceeds to step S34 (step S33; Yes). If the calorie change is not less than the specified value, the determination unit 35 proceeds to step S35 (step S33; No).

[0063] In step S34, the presentation unit 36 ​​presents to the user terminal 2 substitute ingredients and information about substitute ingredients that satisfy the specified nutrient content values ​​and have a small calorie change, and then ends the processing of the flowchart.

[0064] On the other hand, in step S35, since there are no suitable substitute ingredients, the presentation unit 36 ​​displays recipe design recreation information to the user terminal 2 and ends the processing of the flowchart. The recreation information includes text instructing the user terminal 2 to recreate the recipe design, information on the cost and taste of the ingredients and substitute ingredients of the recipe design specified by the user, as well as data on nutritional additives.

[0065] (1) As explained above, the cooking method determination system 100 of this embodiment includes a machine learning unit 30 that generates a learning model using data on influencing factors in the cooking process of processed foods and data on nutrient content that changes due to the influencing factors; a learning model recording unit 32 that records the learned model generated by learning; an estimated value calculation unit 33 that calculates an estimated value of the nutrient content in processed foods using the learning model; a specified value recording unit 34 that records specified values ​​of the nutrient content set for each processed food; and a determination unit 35 that reads the specified values ​​of each nutrient from the specified value recording unit 34 and compares them with the estimated values ​​to determine whether the nutrient content is within the specified value. This makes it possible to use machine learning to accurately and easily estimate the nutrient content of processed foods, which varies depending on various conditions such as cooking and storage methods and is difficult to estimate.

[0066] (2) In addition, the cooking method determination system 100 of this embodiment further includes a classification determination unit 31 that classifies the influencing factor data into first influencing factor data and second influencing factor data according to the reliability based on the number of tests, and the influencing factor data includes data related to the material characteristics, environmental characteristics, and chemical characteristics in the cooking of processed foods. This allows the reliability of the learning source data used to construct the learning model to be determined based on the classification results by the classification determination unit 31.

[0067] (3) Furthermore, in this embodiment, the machine learning unit 30 generates a learning model using both the first influence factor data and the second influence factor data, or either of the selected data, for machine learning based on the judgment result by the classification judgment unit 31. This makes it possible to construct a learning model according to the application and purpose, such as by performing machine learning using only the first influence factor data to build a highly accurate learning model when high accuracy is required, or by performing machine learning using both the first influence factor data and the second influence factor data to build a learning model when a large amount of data is required for learning.

[0068] (4) Furthermore, the cooking method determination system 100 of this embodiment further includes a material recording unit 40 that records substitute information for ingredients and cooking methods, and a presentation unit 36 ​​that refers to the material recording unit 40 and presents the substitute information based on the determination result of the determination unit 35. This means that if the estimated nutrient content does not meet the specified value, an alternative will be presented, eliminating the need to redesign the recipe from scratch and allowing for smooth recipe design.

[0069] (5) In addition, in this embodiment, if the estimated nutrient values ​​of a processed food using the ingredients and / or cooking method presented by the presentation unit 36 ​​do not fall within the specified values ​​after a predetermined period of time has passed, data on nutritional additives is presented along with information on cost and taste. This means that even if substitutions are made and the nutritional content does not fall within the specified range, new recipes can be designed based on the cost, taste information, and nutritional additive data provided.

[0070] (6) In this embodiment, the presentation unit 36 ​​acquires the calorie value of the processed food and determines whether the amount of change in the calorie value is smaller than a specified value based on the substitution information for the ingredients and / or cooking method. This makes it possible to prevent the selection of a substitute that would significantly change the calorie value, which is an important indicator for determining processed foods.

[0071] (7) In addition, the cooking method determination method of this embodiment includes a machine learning step of performing machine learning to generate a learning model using data on influencing factors in the cooking process of processed foods and data on nutrient content that changes due to the influencing factors; a learning model recording step of recording the learning model generated by learning; an estimated value calculation step of calculating an estimated value of the nutrient content in the processed food using the learning model; a specified value recording step of recording specified values ​​of the nutrient content set for each processed food; and a determination step of reading out the specified values ​​of each nutrient recorded in the specified value recording step and comparing them with the estimated values ​​to determine whether the nutrient content is within the specified value.

[0072] Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope of achieving the object of the present invention are included in the present invention.

[0073] The presentation unit 36 ​​may be configured to present a suggestion to change (increase) the amount of material corresponding to a nutrient if the nutrient (estimated result) contained in the material after a predetermined period of time is lower than a predetermined value and the nutrient is a first nutrient for which no upper limit is set for intake. This allows the amount of material to be increased only when no upper limit is set, thereby avoiding the occurrence of a situation where a nutrient for which an upper limit is set is set too high.

[0074] Furthermore, the presenting unit 36 ​​may be configured to perform processing to present a substitute (substitution process) or the addition of an additive when the nutrient (estimated result) contained in the material after a predetermined period of time is lower than a predetermined value and the nutrient is a second nutrient for which an upper limit on intake is set (for example, potassium). This can prevent the occurrence of a situation in which the upper limit on intake of a nutrient for the processed food is set exceeds the upper limit when a nutrient is set higher in amount in consideration of attenuation after processing.

[0075] The presentation unit 36 ​​may also be configured to present substitutes or the addition of additives in consideration of the degree of influence of the taste. For example, the substitutes or the addition of additives to be displayed on the user terminal 2 may be determined depending on the degree of change in taste in the table of Fig. 9, or those with a small change in taste may be displayed preferentially. Furthermore, a parameter such as strong bitterness may be added as the degree of influence of the taste, and the addition of substitutes or additives may be presented depending on the degree of bitterness.

[0076] Furthermore, the presentation unit 36 ​​may take calories into consideration when presenting substitutes or the addition of additives. For example, the presentation unit 36 ​​may present (select) substitute information so that the calories (amount of change) fall within a predetermined range.

[0077] Furthermore, the above-described series of processes can be executed by hardware or software. In other words, the above-described functional configuration is merely an example and is not particularly limited. That is, it is sufficient for the information processing device 1 to have the function of executing the above-described series of processes as a whole, and the type of functional block used to realize this function is not particularly limited to the above example. Furthermore, the location of the functional block is not particularly limited and may be arbitrary. For example, the functional block of the information processing device 1 may be transferred to another device, etc. Conversely, the functional block of another device may be transferred to a server, etc. Furthermore, one functional block may be configured as a single piece of hardware, a single piece of software, or a combination thereof.

[0078] When a series of processes is executed by software, the programs constituting the software are installed onto a computer or the like from a network or a recording medium. The computer may be a computer incorporated into dedicated hardware. The computer may also be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

[0079] The recording medium containing such a program may be configured as not only a removable medium (not shown) that is distributed separately from the device main body in order to provide the program, but also a recording medium that is provided in a state that it is pre-installed in the device main body, etc. Since the program can be distributed via a network, the recording medium may be installed in or accessible to a computer that is connected or connectable to the network.

[0080] In this specification, the steps describing the program recorded on the recording medium include not only processes that are performed in chronological order, but also processes that are not necessarily performed in chronological order but are performed in parallel or individually. Also, in this specification, the term "system" means an overall device composed of multiple devices or multiple means, etc. [Explanation of symbols]

[0081] 1. Information processing equipment 2. User terminal 30 Machine Learning Department 31 Classification judgment section 32 Learning model recording section 33 Estimated value calculation section 34 Default value recording section 35 Judgment section 36 Presentation part 40 Material Recording Section 100 Cooking method decision system

Claims

1. a machine learning means for generating a learning model using data on influential factors in the cooking process of processed foods and data on the nutrient content that changes depending on the influential factors; a learning model recording means for recording the learning model generated by learning; an estimated value calculation means for calculating an estimated value of the nutrient content of the processed food using the learning model; a specified value recording means for recording the specified value of the nutrient content set for each of the processed foods; a determining means for determining whether the content of each nutrient is within a specified value by reading the specified value of each nutrient from the specified value recording means and comparing it with the estimated value; A cooking method determination system having the above.

2. The influencing factor data includes data relating to material characteristics, environmental characteristics, and chemical characteristics in cooking the processed food, and the method further comprises a classification determination means for classifying each data into first influencing factor data and second influencing factor data according to reliability based on the number of tests. The cooking method determination system according to claim 1 .

3. the machine learning means generates the learning model using both the first influence factor data and the second influence factor data, or a selected one of the data, for machine learning based on the determination result by the classification determination means; The cooking method determination system according to claim 2 .

4. an ingredient recording means for recording substitution information for ingredients and cooking methods; a presentation means for referring to the material recording means and presenting alternative information based on the determination result of the determination means, The cooking method determination system according to claim 1 .

5. The presenting means presents data on nutritional additives together with information on cost and taste when the estimated value of the nutrient does not fall within a specified value after a predetermined period of time has elapsed for the processed food using the ingredients and / or cooking method presented in the presented substitution information. The cooking method determination system according to claim 4 .

6. The presentation means acquires the calorie value of the processed food, and determines whether the amount of change in the calorie value is smaller than a specified value based on the substitution information of ingredients and / or cooking methods. The cooking method determination system according to claim 4 .

7. A cooking method determination method using a computer, comprising: a machine learning step of performing machine learning to generate a learning model using data on influential factors in the cooking process of processed foods and data on nutrient contents that change due to the influential factors; a learning model recording step of recording the learning model generated by learning; an estimation step of calculating an estimated value of the nutrient content in the processed food using the learning model; a specified value recording step of recording the specified value of the nutrient content set for each of the processed foods; a determination step of determining whether the nutrient contents are within the specified values ​​by reading out the specified values ​​of the nutrients recorded in the specified value recording step and comparing them with the estimated values; A method for determining cooking methods, including:

Images