Food development support device, food development support method, and food development support program

Abstract

To suitably assist with the development of a new food product, a food product development support device (1) comprises: a receiving means (11) that receives a request relating to the development of a new food product; an estimating means (12) that estimates a manufacturing method for a new product that conforms to the request, on the basis of the request and a trained model that learned the relationship between a method for manufacturing an existing product constituting an existing food product, and at least any one of ingredients used in the existing product, a product category of the existing product, a development concept of the existing product, and properties of the existing product; and an outputting means (13) that outputs information indicating the manufacturing method estimated by the estimating means.

Description

[Technical Field]

[0001] The present invention relates to a food development support device and the like that generates information related to food development. [Background technology]

[0002] In developing new food products, a process is carried out in which a combination that is considered promising for realizing the product concept is selected from a vast number of combinations of ingredients and manufacturing methods, a prototype product is produced, and its taste, appearance, texture, aroma, etc. are verified (see, for example, Patent Document 1 below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-104469 Summary of the Invention [Problem to be solved by the invention]

[0004] The development of new food products requires repeating the above process until a combination that realizes the product concept is found, which requires a great deal of time and effort, and therefore there is a need for technology to support the development of new food products.The same is true for the development of new cooking recipes.

[0005] One aspect of the present invention has been made in consideration of the above-mentioned problems, and one of its objectives is to provide a technology that favorably supports the development of new food products. [Means for solving the problem]

[0006] A food product development support device according to one aspect of the present invention includes a receiving means for receiving a request for the development of a new food product; a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on the request; and an output means for outputting information indicating the manufacturing method estimated by the estimation means.

[0007] In a food product development support method according to one aspect of the present invention, a computer receives a request for the development of a new food product, estimates a manufacturing method for the new product that matches the request based on the request and a trained model that has learned the relationship between at least one of the ingredients used in an existing product (which is an existing food product), the product category of the existing product, the development concept of the existing product, and the properties of the existing product, and the manufacturing method of the existing product, and outputs information indicating the estimated manufacturing method.

[0008] A food product development support program according to one aspect of the present invention causes a computer to perform the following processes: accepting a request for the development of a new food product; estimating a manufacturing method for a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product; and outputting information indicating the estimated manufacturing method. [Effects of the Invention]

[0009] According to one aspect of the present invention, it is possible to preferably support the development of new food products. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a food development assistance device according to a first exemplary embodiment of the present invention. [Figure 2] 1 is a flowchart showing the flow of a food product development support method according to a first exemplary embodiment of the present invention. [Figure 3] FIG. 1 is a diagram illustrating feature learning in graph-based relational learning. [Figure 4] FIG. 10 is a block diagram showing the configuration of a food development assistance device according to a second exemplary embodiment of the present invention. [Figure 5] FIG. 10 is a schematic diagram illustrating an example of a method for generating a new product graph by a graph generator according to a second exemplary embodiment of the present invention. [Figure 6] FIG. 10 is a schematic diagram illustrating an example of a prediction method performed by a link predictor according to a second exemplary embodiment of the present invention. [Figure 7] FIG. 10 is a schematic diagram showing an example of an evaluation method by an evaluation unit according to a second exemplary embodiment of the present invention. [Figure 8] FIG. 10 is a diagram showing an example of presentation by an output unit according to a second exemplary embodiment of the present invention. [Figure 9] FIG. 10 is a flowchart showing the flow of processing executed by a food development assistance device 2 according to a second exemplary embodiment of the present invention. [Figure 10] FIG. 10 is a diagram illustrating a method for identifying an existing product having a predetermined relationship with a new product by a link prediction unit according to a third exemplary embodiment of the present invention. [Figure 11] FIG. 10 is a diagram showing an overview of a food product development support method according to a fourth exemplary embodiment of the present invention. [Figure 12] FIG. 10 is a block diagram showing the configuration of a food development assistance device according to a fourth exemplary embodiment of the present invention. [Figure 13] FIG. 10 is a flowchart showing the flow of processing executed by a food product development assistance device according to a fourth exemplary embodiment of the present invention. [Figure 14] FIG. 10 is a diagram showing an overview of a food product development support method according to a fifth exemplary embodiment of the present invention. [Figure 15] FIG. 10 is a block diagram showing the configuration of a food development assistance device according to a fifth exemplary embodiment of the present invention. [Figure 16]FIG. 11 is a flowchart showing the flow of processing executed by a food development assistance apparatus according to a fifth exemplary embodiment of the present invention. [Figure 17] FIG. 10 is a diagram illustrating an example of predicting the properties of a new product based on feature amounts calculated from a new product graph and an existing product graph. [Figure 18] FIG. 1 is a configuration diagram for realizing a cosmetics manufacturing support device using software. DETAILED DESCRIPTION OF THE INVENTION

[0011] Exemplary Embodiment 1 A first exemplary embodiment of the present invention will be described in detail with reference to the drawings. This exemplary embodiment is a basic form of the exemplary embodiments described below.

[0012] (Food development support device) The configuration of a food product development assistance device 1 according to this exemplary embodiment will be described with reference to the drawings. Fig. 1 is a block diagram showing the configuration of a food product development assistance device 1 according to this exemplary embodiment.

[0013] As shown in FIG. 1, the food development assistance device 1 includes a receiving unit (receiving means) 11, an estimating unit (estimating means) 12, and an output unit (output means) .

[0014] The receiving unit 11 receives a request for the development of a new food product. The estimation unit 12 estimates a manufacturing method for a new product that matches the request, based on a trained model that has learned the relationship between at least one of ingredients used in an existing product (an existing food product), the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product, and the request received by the receiving unit 11. The output unit 13 outputs information indicating the manufacturing method estimated by the estimation unit 12.

[0015] The "manufacturing method" may include, for example, the type of ingredients, the type of seasoning, the order in which ingredients and seasonings are added, the blend of ingredients and seasonings, the cooking method (steaming, boiling, baking, frying, etc.), the order of cooking methods, the cooking temperature, the cooking time (mixing time, etc.), the cooking speed (mixing speed, etc.), the equipment and devices used in cooking, and the sterilization method. The "manufacturing method" also includes at least one of a manufacturing process and a recipe.

[0016] The food product development support device 1 having the above configuration can present to the user a manufacturing method for a new product that is deemed to be suitable for the request, based on the relationship between the ingredients used in the existing product, the product category, development concept, and / or properties of the existing product, and the manufacturing method for the existing product. Therefore, the above configuration has the effect of being able to provide suitable support for the development of new food products.

[0017] (Food Development Support Program) The functions of the food product development support device 1 described above can also be realized by a program. The food product development support program according to this exemplary embodiment causes a computer to execute the following processes: accepting a request for new food product development; estimating a manufacturing method for a new product that matches the request based on the request and a trained model that has learned the relationship between at least one of ingredients used in an existing product (an existing food product), the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product; and outputting information indicating the manufacturing method estimated by the estimation means. This food product development support program provides the effect of optimally supporting new food product development.

[0018] (Food development support method) The food product development support method according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow chart showing the flow of the food product development support method according to the first exemplary embodiment of the present invention.

[0019] In S11, the computer receives a request for new food product development. The request may be received via any input device. For example, the request may be received via a mouse, keyboard, touch panel, or voice input device.

[0020] In S12, the computer estimates a manufacturing method for a new product that matches the request received in S11, based on a trained model that has learned the relationship between the manufacturing method of the existing product and at least one of the ingredients used in the existing product, which is an existing food product, the product category of the existing product, the development concept of the existing product, and the properties of the existing product, and the request received in S11.

[0021] In S13, the computer outputs information indicating the estimated manufacturing method to any device, such as a display device to display the information, or an audio output device to output the information as audio.

[0022] As described above, in the food product development support method according to this exemplary embodiment, a computer receives a request for new food product development (S11), estimates a manufacturing method for the new product that matches the request based on the request and a trained model that has learned the relationship between the ingredients used in the existing product (which is an existing food product), the product category of the existing product, the development concept of the existing product, and / or the properties of the existing product, and the manufacturing method of the existing product (S12), and outputs information indicating the manufacturing method estimated in S12 (S13). This food product development support method has the effect of being able to effectively support the development of new food products.

[0023] Note that each step in the food product development support method described above may be executed by one computer (e.g., the food product development support device 1), or each step may be executed by a different computer. This also applies to the flows described in the second and subsequent exemplary embodiments.

[0024] [Graphs and Learning] In the following, in exemplary embodiment 1 and the exemplary embodiments described below (hereinafter referred to as each exemplary embodiment), a graph is described as an example of information that can be used to support food product development. Learning of the graph and prediction using the graph are also described.

[0025] (graph) A graph here refers to data with a structure consisting of multiple nodes and links connecting the nodes. The type of link that represents the relationship between nodes is also called a "relation." Links are also sometimes called edges. Graphs can be broadly divided into directed graphs, in which each link has a direction, and undirected graphs, in which each link does not have a direction. It is possible to use either directed graphs or undirected graphs, or to use a combination of the two.

[0026] In each exemplary embodiment, when a graph is used, the nodes may represent tangible or intangible elements related to the food production method. For example, ·ingredients ·seasoning Product Category Development concept · Properties (texture, aroma, appearance, allergies, etc.) Product identification information such as product name and product ID ·Manufacturing method It is possible to use a graph including nodes representing various elements such as the above. More precisely, properties refer to properties or states, and include, for example, texture, aroma, appearance, whether or not there are allergies, the details of the allergy, texture, whether it is liquid or solid, and whether it can be classified as a dish from any country or region on the planet (Japanese, Western, Chinese, etc.).

[0027] The graph may also contain multiple nodes corresponding to one element. For example, the nodes representing the ingredients of a food may each represent a separate node for each ingredient contained in the food, such as a node representing a first ingredient, a node representing a second ingredient, and a node representing a third ingredient. The same applies to other elements.

[0028] When there are nodes as elements like the above, the relationship represented by the link is The relationship between certain elements and ingredients The relationship between certain elements and seasonings Relationship between an element and a product category -Relationship between certain elements and development concept Relationship between certain elements and properties The relationship between an element and a product For example, a link connecting a node indicating an ingredient with a node indicating a property may represent a relationship in which the ingredient is a factor in the property.

[0029] (Learning and Prediction) For graphs such as those described above, graph-based relationship learning can be performed by applying machine learning techniques. Such learning enables classification and prediction processes to be performed using the graph. Note that in each exemplary embodiment, such learning may be performed as part of food production support, or a trained graph that has already undergone such learning may be used.

[0030] In graph-based relationship learning, first, the feature of each node is calculated. The feature may be calculated in the form of a feature vector, for example. By expressing the feature of each node as a feature vector, learning can be performed on graphs containing a mixture of nodes in various formats. For example, graph-based relationship learning can also be performed on graphs that include images, numerical values, etc. that indicate the various elements described above.

[0031] Next, the feature values ​​of each node are updated based on the links connected to each node and the nodes to which those links are connected. This process is similar to the convolution process in a convolutional neural network. This will be explained with reference to Figure 3. Figure 3 is a diagram explaining feature learning in graph-based relational learning.

[0032] The graph shown in Fig. 3 includes four nodes A to D. Node A is connected to nodes B and C, and node C is connected to node D. After calculating the initial features of these four nodes, convolution is performed multiple times as described below to update the features of each node.

[0033] In the first convolution, the initial feature of node A is multiplied by a predetermined weight and added to the feature of nodes B and C connected to node A. For node C, the initial feature of node C is multiplied by a predetermined weight and added to the feature of node D. If it is a directed graph, the weight is adjusted according to the direction of the link.

[0034] In the second convolution, as in the first convolution, the feature of each node is multiplied by a predetermined weight and then added with the feature of the node linked to that node. Here, the feature of node C reflects the feature of node D due to the first convolution. Therefore, in the second convolution, not only the feature of node C but also the feature of node D is reflected in node A.

[0035] By repeating the above process a number of times according to the node hierarchy, the features of each node directly or indirectly connected by links are mutually reflected. In graph-based relationship learning, the weight values ​​used for the weighting described above are optimized based on the known relationships between nodes. By using a trained graph, it is also possible to predict the relationships between nodes and the nodes to which links will lead, as described below.

[0036] (Node relationship prediction) By performing the above-described learning, it becomes possible to predict relationships between nodes that are not explicitly stated in the original graph. To perform node relationship prediction, the user simply specifies two nodes and requests that the relationship between those nodes be returned. For example, if a user inputs a request asking about the relationship between the "Product A" node and the "Tomato" node, node relationship prediction can predict that the relationship, i.e., the link, connecting these nodes is "ingredients." Furthermore, node relationship prediction can also calculate the probability (likelihood) of the predicted result. The same applies to node prediction, which will be described below.

[0037] (node ​​prediction) Furthermore, by performing the above-described learning, it is also possible to predict the nodes connected to a given node via a specified link. To perform node prediction, a user simply specifies a node and a link starting from that node, and requests that the node at the link destination be returned. For example, suppose a user inputs a request asking about the node connected to the "Product A" node via the "Ingredient" link. In this case, node prediction makes it possible to predict whether the node connected to the "Product A" node via the "Ingredient" link is a "tomato" or an "eggplant," for example.

[0038] Exemplary Embodiment 2 (Device configuration) The configuration of a food product development assistance device 2 according to a second exemplary embodiment of the present invention will be described with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of a food product development assistance device 2 according to this exemplary embodiment.

[0039] As shown in the figure, the food development support device 2 includes a receiving unit 201, a graph generating unit 202, a link predicting unit 203, an evaluating unit 204, a graph updating unit 205, a learning unit 206, an estimating unit 207, a basis generating unit 208, and an output unit 210.

[0040] In addition to these components, the food development support device 2 may also include an input device that accepts user input operations, an output device that outputs data from the food development support device 2, and a communication device that enables the food development support device 2 to communicate with other devices. The output mode of the output device is arbitrary, and may be, for example, a display output or an audio output.

[0041] The reception unit 201 receives a request for new food product development. The request includes information about the new product that the user wants to manufacture. As an example, the request includes at least one of the product category, ingredients, seasonings, development concept, and properties required for the new product, but is not limited to these.

[0042] As in the first exemplary embodiment, the term "properties" refers to a quality or state, and includes, for example, texture, aroma, appearance, whether or not there is an allergy, the details of the allergy, texture, whether the product is liquid or solid, etc.

[0043] The graph generation unit 202 references the request received by the reception unit 201, and generates a new product graph that represents the new product based on information about the new product the user wishes to manufacture, as indicated in the request. Specifically, the graph generation unit 202 generates a new product graph that represents the new product the user wishes to manufacture using nodes that represent the product category, development concept, properties, ingredients, or manufacturing method of the new product, and edges that represent the relationships between the nodes.

[0044] Here, as in Exemplary Embodiment 1, the above-mentioned "manufacturing method" may include, for example, the types of ingredients, the types of seasonings, the order in which the ingredients and seasonings are added, the blend of ingredients and seasonings, the cooking method (steaming, boiling, baking, frying, etc.), the order of cooking methods, the cooking temperature, the cooking time (mixing time, etc.), the cooking speed (mixing speed, etc.), the equipment and devices used in cooking, and the sterilization method. Furthermore, the above-mentioned "manufacturing method" includes at least one of a manufacturing process and a recipe.

[0045] The link prediction unit 203 uses the new product graph and the existing product graph to perform link prediction to predict the relationship between nodes that are not connected by links in the new product graph and the existing product graph. By performing this link prediction, the link prediction unit 203 predicts, for example, nodes that are linked to nodes included in the new product graph from among nodes included in the existing product graph that indicate ingredients, seasonings, or manufacturing methods used in the existing products.

[0046] Here, an existing product graph is a graph that represents one or more existing products using nodes that represent the development concept, properties, manufacturing method, or ingredients used in the existing product, and edges that represent the relationships between the nodes.

[0047] An existing product graph is a graph that represents one or more existing products with nodes that represent the ingredients, seasonings, properties, or manufacturing methods of the existing products, and edges that represent the relationships between the nodes. An existing product graph is a trained graph of the relationships between the nodes, and is a trained model. An existing product graph can also be called a knowledge graph. Note that a graph corresponding to one existing product may be called an existing product graph, or a graph corresponding to multiple existing products may be called an existing product graph.

[0048] According to the above configuration, nodes that link to nodes included in the new product graph are predicted from among nodes that indicate ingredients, seasonings, or manufacturing methods used in existing products. Nodes that link to nodes included in the new product graph are useful information for estimating a manufacturing method for a new product that matches the request. According to the above configuration, useful information for estimating a manufacturing method for a new product that matches the request can be identified.

[0049] Furthermore, the link prediction unit 203 may perform link prediction that respects the development concept of the new product. As an example, the link prediction unit 203 refers to a request received by the receiving unit 201 and identifies the development concept of the new product indicated by the request. Then, from among nodes included in the existing product graph that include nodes that match the identified concept, the link prediction unit 203 predicts a node that indicates an ingredient, seasoning, or manufacturing method used in the existing product and links to a node included in the new product graph.

[0050] According to the above configuration, the prediction range of nodes linked to nodes included in the new product graph is narrowed down to existing product graphs that include nodes that match the development concept of the new product, thereby making it possible to predict nodes that are likely to have contributed to the development concept of the new product.

[0051] The evaluation unit 204 evaluates the node predicted by the link prediction unit 203. As an example, the evaluation unit 204 refers to the request received by the reception unit 201 and identifies the property indicated by the request that is required for the new product. The evaluation unit 204 then determines whether or not the existing product graph including the node predicted by the link prediction unit 203 includes a node indicating the property required for the new product. If the existing product graph including the node predicted by the link prediction unit 203 includes a node indicating the property required for the new product, the evaluation unit 204 then evaluates the node predicted by the link prediction means higher than if the existing product graph does not include a node indicating the property.

[0052] Other nodes included in an existing product graph that includes a node indicating a certain property may be factors that give that property to the existing product. For example, if an existing product graph that includes a node indicating that the product is "popular among young people" includes a node called "tapioca" that indicates an ingredient of the existing product, the "tapioca" node may be a factor that makes the product "popular among young people."

[0053] Therefore, in the above configuration, among the nodes predicted by the link prediction unit 203, nodes in the existing product graph that include nodes indicating the properties required for the new product are rated higher than nodes in the existing product graph that do not include nodes indicating the properties required for the new product. Based on this rating, the user can decide whether to apply the ingredients, seasonings, or manufacturing methods indicated in the predicted nodes to the new product. This can contribute to the development of new products with desired properties. Specific examples of the rating by the rating unit 204 will be described later.

[0054] The graph update unit 205 updates the new product graph generated by the graph generation unit 202. As an example, the graph update unit 205 updates the new product graph by referring to the prediction result by the link prediction unit 203 and the evaluation result by the evaluation unit 204. A more specific example of the update process by the graph update unit 205 will be described later.

[0055] The learning unit 206 learns the relationships between the nodes included in the existing product graph based on various information about existing products, and generates a learned existing product graph. Unless otherwise specified, the existing product graph refers to one that has been learned by the learning unit 206. The learned existing product graph may also be loaded into the food development assistance device 2, in which case the learning unit 206 may be omitted.

[0056] The estimation unit 207 is configured to estimate a manufacturing method for a new product that matches the request, based on the trained model and the request received by the reception unit 201. Here, the trained model is a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, the product category of the existing product, the development concept of the existing product, and the properties of the existing product, and the manufacturing method for the existing product.

[0057] In this exemplary embodiment, as an example, an example will be described in which the trained model is a graph representing one or more of the existing products using nodes representing the development concept, properties, manufacturing method, or ingredients used in the existing product, and edges representing the relationships between the nodes, i.e., the above-mentioned existing product graph.

[0058] According to the above configuration, it is possible to estimate an appropriate manufacturing method by taking into consideration the development concept, properties, and manufacturing method of the existing product, or the interrelationships between the ingredients used in the multiple existing products.

[0059] Furthermore, the estimation unit 207 may estimate a manufacturing method for a new product that matches the request received by the reception unit 201, based on the nodes predicted by the link prediction unit 203 through the above-described processing.

[0060] The basis generating unit 208 generates basis information indicating the basis of the estimation made by the estimating unit 207. Various methods can be applied to generate the basis information. The method of generating the basis information will be described later.

[0061] As described above, the output unit 210 outputs various information generated by the food development support device 2, such as information indicating the production method estimated by the estimation unit 207. The destination of the information output is arbitrary, and for example, if the food development support device 2 is equipped with an output device as described above, the information may be output to that output device. Alternatively, for example, the information may be output to an output device external to the food development support device 2.

[0062] (Outline of food development support methods) 5 is a diagram illustrating an overview of a food product development support method according to this exemplary embodiment. In this exemplary embodiment, as an example, a manufacturing method for a new product that matches the request is estimated while sequentially adding nodes that indicate ingredients and manufacturing methods to a new product graph.

[0063] In this exemplary embodiment, link prediction is performed using a new product graph and an existing product graph. The new product graph shown in the upper left corner of Fig. 5 is an example of a new product graph generated by the graph generation unit 202 based on a request received by the reception unit 201. The new product graph includes nodes and links indicating that the new product contains "tomato" as an ingredient and that the new product is required to have a "smooth" texture.

[0064] Furthermore, the existing product graph shown in the upper center of Figure 5 includes nodes and links indicating that existing product A has a "smooth" texture, contains "eggs" as an ingredient, and is cooked by "steaming" in its manufacturing method. Similarly, the existing product graph shown in the upper right corner of Figure 5 includes nodes and links indicating that existing product B has a "fragrant" aroma, contains "cheese" as an ingredient, and is cooked by "baking" in its manufacturing method.

[0065] By learning the existing product graphs for various existing products as described above, it becomes possible to perform link prediction to determine which ingredients and manufacturing methods are likely to be applicable to which products. In other words, the food product development support method according to this exemplary embodiment predicts ingredients and manufacturing methods that are likely to be applicable to new products through link prediction, and estimates the manufacturing method for the new product by adding nodes to the new product graph based on the prediction results.

[0066] 5, the link prediction unit 203 predicts a node connected to the "new product" node in the new product graph shown in the top left corner by a link of "ingredients." Then, as shown in the bottom left corner, the link prediction predicts that the node connected to the "new product" node by the link of "ingredients" is "egg," and based on this, the graph generation unit 202 adds an "egg" node to the new product graph.

[0067] After determining the ingredients for the new product in this way, the link prediction unit 203 performs link prediction on the nodes connected to the "new product" node by the "manufacturing method" link in the new product graph after the node addition. This makes it possible to predict the manufacturing method taking into account the nodes indicating ingredients that were added based on the results of link prediction.

[0068] According to the food product development support method of this exemplary embodiment, by repeating the above process, it is possible to sequentially predict ingredients and cooking methods that will give a new product a smooth texture, and to recommend a manufacturing method that includes each of the predicted ingredients and cooking methods.

[0069] (Prediction method by link prediction unit) Fig. 6 is a diagram illustrating the prediction method by the link prediction unit 203. Fig. 6 shows an existing product graph in which existing products A to C are represented by nodes that represent the ingredients, properties, or manufacturing methods of the existing products, and edges that represent the relationships between the nodes. For example, the node for "existing product A" and the node for "smooth" are connected by an edge that represents "texture," which indicates that existing product A has a smooth texture.

[0070] 6 includes nodes for multiple existing products, existing products A to C, but a graph consisting of only nodes related to one existing product may also be called an existing product graph. In this case, similar products are identified using multiple existing product graphs corresponding to each of the multiple existing products.

[0071] Such an existing product graph can be generated from the ingredients, properties, and manufacturing methods of each existing product. Furthermore, by learning the relationship between the ingredients and properties shown in the existing product graph and the manufacturing methods of existing products, it becomes possible to infer the relationship between the ingredients and properties of a new product and the manufacturing methods of existing products.

[0072] Figure 6 also shows a new product graph in which new products are represented by nodes that represent the ingredients, properties, or manufacturing methods of the new products, and edges that represent the relationships between the nodes. More specifically, the new product graph shown in Figure 6 includes nodes and links that indicate that the new product has a "smooth" texture and a "fragrant" aroma, as well as nodes and links that indicate that the new product contains the ingredients "tomato" and "egg."

[0073] The graph generation unit 202 generates the new product graph as described above based on the request for a new product received by the reception unit 201. This new product graph may be updated with reference to the prediction result by the link prediction unit 203, as outlined in FIG.

[0074] The link prediction unit 203 uses the new product graph and existing product graph generated in this way to perform link prediction to predict the relationships between nodes that are not connected by links in the new product graph and the existing product graph. By performing this link prediction, the link prediction unit 203 predicts, as an example, from among nodes included in the existing product graph that indicate ingredients, seasonings, or manufacturing methods used in the existing product, nodes that link to nodes included in the new product graph.

[0075] For example, as shown by the dashed line in FIG. 6, there is no link between the "tomato" node in the new product graph and the "tomato" node in existing product A. By performing link prediction, the link prediction unit 203 can predict the probability that the relationship between these nodes is "same." Then, based on the predicted probability, the link prediction unit 203 can identify nodes in the existing product graph that link to nodes included in the new product graph. For example, the link prediction unit 203 may identify nodes in the existing product graph whose predicted probability value is equal to or greater than a threshold as nodes that link to nodes in the new product graph.

[0076] In addition, the link prediction unit 203 can predict, from among the nodes included in the existing product graph that include nodes that meet pre-set conditions or conditions set by the user, nodes that indicate ingredients, seasonings, or cooking methods used in the existing product and link to nodes included in the new product graph.

[0077] For example, the link prediction unit 203 can predict, from among the nodes included in an existing product graph that includes a node that matches the development concept of a new product, a node that indicates the ingredients, seasonings, or cooking methods used in the existing product and links to a node included in the graph of the new product.

[0078] (Evaluation method by the evaluation department) 7 is a schematic diagram showing an example of an evaluation method by the evaluation unit 204. As described above, as an example, the evaluation unit 204 refers to a request received by the reception unit 201 and identifies properties indicated in the request that are required for the new product.

[0079] Figure 7 shows an example where the desired properties of a new product include a smooth texture and a fragrant aroma. In this example, the recommendation level is set to "5" when one property matches the request.

[0080] The evaluation unit 204 determines whether or not a node indicating the properties required for the new product is included in the existing product graph including the node predicted by the link prediction unit 203. If the existing product graph including the node predicted by the link prediction unit 203 includes a node indicating the properties required for the new product, the evaluation unit 204 evaluates the node predicted by the link prediction means higher than if the node indicating the properties is not included.

[0081] In the example shown in Fig. 7, existing product graph D including nodes predicted by the link prediction unit 203 includes nodes and links indicating that the product has a "smooth" texture as a property, but does not include nodes and links indicating that the product has a "fragrant" aroma. On the other hand, existing product graph E including nodes predicted by the link prediction unit 203 includes nodes and links indicating that the product has a "smooth" texture, as well as nodes and links indicating that the product has a "fragrant" aroma, as shown in Fig. 7.

[0082] In such a case, the evaluation unit 204 gives a higher evaluation to the existing product graph E than to the existing product graph D. In other words, when the existing product graph including the node (ingredient: tomato) predicted by the link prediction unit 203 includes a node indicating a property required for the new product, the evaluation unit 204 gives a higher evaluation to the node (ingredient: tomato) predicted by the link prediction means than when the node indicating the property is not included.

[0083] In this way, by determining in advance the degree of suitability for a request and the recommendation level corresponding to that degree, the evaluation unit 204 can calculate the recommendation level for each existing product.

[0084] The evaluation unit 204 may also increase the recommendation level of an existing product that is more similar to the new product. For example, assume that the new product graph includes nodes and links that indicate multiple ingredients of the new product. In this case, the recommendation level of an existing product that shares ingredients with the new product may be higher than that of an existing product that does not share ingredients with the new product.

[0085] In addition, the evaluation unit 204 may, for example, give a higher recommendation level to an existing product that can be manufactured with manufacturing equipment available to the user than to an existing product that cannot be manufactured with manufacturing equipment available to the user. The manufacturing equipment available to the user may be input as a request. The evaluation unit 204 may also calculate the recommendation level by combining the various evaluation criteria for the recommendation level described above.

[0086] (Example of manufacturing method upon request) The output unit 210 may output the manufacturing method of the new product estimated by the estimation unit 207 in response to the request received by the reception unit 201 and the recommendation level calculated by the evaluation unit 204 in a format such as that shown in Fig. 8. Fig. 8 is a diagram showing a presentation example in which a manufacturing method of the new product in response to the request is presented together with the recommendation level.

[0087] In the example of Fig. 8, the production method (cooking method) estimated by the estimation unit 207, additional ingredients to be added to the ingredients included in the request, allergy possibility, and recommendation level are presented. Furthermore, as shown in Fig. 8, the output unit 210 may present the production method of the new product estimated by the estimation unit 207 by category. Specific categories here include, but are not limited to, Japanese style, Western style, Chinese style, etc.

[0088] By presenting the user with information such as that shown in FIG. 6, the user can recognize ingredients and manufacturing methods that should be added to a new product.

[0089] (Method of generating evidence information) Next, a method for generating evidence information by the evidence generation unit 209 will be described. As described above, various techniques can be applied to generate evidence information. For example, when the request received by the receiving unit 201 includes information indicating a development concept for a new product or information indicating ingredients to be used in the new product, the evidence generation unit 208 may generate evidence information including, as evidence for estimation, information on existing products that have the same development concept as the development concept for the new product or information on existing products that use the same ingredients as those used in the new product. Then, the output unit 210 may output the generated evidence information.

[0090] Information on existing products with the same development concept as the development concept required for the new product, or information on existing products that use the same ingredients as those used in the new product, can be useful information for determining whether the new product manufactured using the estimated manufacturing method conforms to the development concept or whether the ingredients should be used in the new product.

[0091] According to the above configuration, the basis for the proposed manufacturing method is based on existing products with the same development concept and ingredients, which allows the user to easily understand the contents and manufacturing method of the new product.

[0092] In addition, the evidence information generated by the evidence generation unit 208 may include information indicating a manufacturing method for an existing product that has the same development concept as the development concept of the new product, or an existing product that uses the same ingredients as those used in the new product.

[0093] The existing product graph of an existing product that has the same development concept as the new product's development concept or that uses the same ingredients as those used in the new product includes a node that indicates the development concept or ingredient. Therefore, the evidence generation unit 208 first identifies an existing product graph that includes a node that indicates the development concept or ingredient. Then, the evidence generation unit 208 generates evidence information that indicates the manufacturing method of the existing product shown in the identified existing product graph. For example, the evidence generation unit 208 may generate evidence information that indicates at least one of the properties, ingredients, and manufacturing method shown in the identified existing product graph.

[0094] The manufacturing method of an existing product that has the same development concept as the development concept of a new product, or an existing product that uses the same ingredients as those used in the new product, is a useful reference for determining whether a new product manufactured by the estimated manufacturing method matches the development concept or whether the new product uses those ingredients. Whether the estimated manufacturing method is effective for making the new product conform to the desired development concept, or Whether the assumed manufacturing method is effective for making the new product using the desired ingredients This provides the user with valuable information to determine the

[0095] Furthermore, the evidence generation unit 208 may generate evidence information based on the result of link prediction by the link prediction unit 203. As an example, the link prediction unit 203 uses the existing product graph and the new product graph to predict the probability that a node indicating a specific allergy will be linked to a node included in the new product graph. Then, the evidence generation unit 208 generates evidence information according to the predicted probability.

[0096] This enables the evidence generating unit 208 to generate evidence information such as that shown as "allergy possibility" in Fig. 8. As shown in Fig. 8, the output unit 210 presents evidence information based on the predicted result of the probability that a predetermined allergy will appear in the new product, in addition to information indicating the manufacturing method of the new product estimated by the estimation unit 12.

[0097] By outputting the evidence information as shown in FIG. 8 by the output unit 210, the user can be provided with useful information for determining whether the estimated manufacturing method has the potential to cause a specific allergy in a new product.

[0098] (Generating evidence for link prediction results) The basis generating unit 208 can also generate basis information by analyzing the new product graph and the existing product graph. A method for generating basis information by analyzing the new product graph and the existing product graph will be described below.

[0099] For example, the basis generator 208 may mine one or more rules from the new product graph and the existing product graph using PCA (Principal Component Analysis) reliability based on the OWA (Open-world assumption).The basis generator 208 may then generate basis information using the mined one or more rules.For example, the method described in the following document may be applied to rule mining.

[0100] Luis Galarraga et. al, “Fast rule mining in ontological knowledge bases with AMIE +”, The VLDB Journal (2015) 24:707-730 As an example, the rule to be processed by the basis generating unit 208 is expressed as follows, using Head r(x, y) and Body { B1 , . . . , Bn}:

number

number

[0101] The basis generating unit 208 sets the following as the conditions for the mining process: Connected: All values ​​(variables, entities) in the rule are shared between different atoms. Closed: All variables in the rule must appear at least twice. Not reflexive: Rules containing reflexive atoms such as r(x, x) are not mined. Mining processing is carried out under the following conditions.

[0102] Furthermore, the basis generating unit 208

number

number

[0103] For example, suppose that the basis generation unit 208 has mined a rule that, for two products that satisfy the conditions of "shared concept" or "shared ingredients," "an element included in one manufacturing method can be applied to the manufacturing method of the other." In this case, when the link prediction unit 203 predicts that an element included in the manufacturing method of an existing product will be an element included in the manufacturing method of a new product, the basis generation unit 208 may generate basis information indicating that the existing product and the new product "shared concept" or "shared ingredients" as the basis for this prediction.

[0104] By presenting the above-described basis information, the user can easily understand the contents and manufacturing method of the new product.

[0105] (Processing flow) The flow of the process (food development support method) executed by the food product development support device 2 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of the process executed by the food product development support device 2.

[0106] In S201, the receiving unit 201 receives a request for new food product development. In S201, for example, a request indicating the product category, development concept, properties, or ingredients used in the new product of the new product that the user intends to manufacture is received. That is, as described above, the request includes, for example, at least one of the product category, ingredients, development concept, properties, etc.

[0107] In S202, the graph generation unit 202 generates a new product graph based on the request input in S201. For example, the graph generation unit 202 may generate a new product graph represented by nodes representing the product category, development concept, properties, ingredients, or manufacturing method of the requested new product, and edges representing the relationships between the nodes.

[0108] In S202, a manufacturing method for the new product can be estimated by generating a new product graph for the new product that satisfies all of the properties indicated in the request received in S201. Note that the new product graph at this stage only needs to include nodes and links that indicate that the new product satisfies the above properties.

[0109] In S203, the link prediction unit 203 predicts nodes that link to nodes included in the new product graph generated in S202. As described above, this node is predicted by link prediction using the learned existing product graph and the new product graph.

[0110] In S203, the link prediction unit 203 may, for example, predict nodes connected to a "new product" node via links for "ingredients," "seasonings," or "manufacturing method." Alternatively, it may predict nodes connected to nodes indicating ingredients or seasonings or nodes indicating manufacturing methods. For example, it may predict a node connected to a node indicating ingredients via a "weight" link, or it may predict a node connected to a node indicating cooking via a "heating time" link. This makes it possible to estimate details of the ingredients, seasonings, and manufacturing method of the new product.

[0111] In S204, the evaluation unit 204 evaluates the node predicted in S203. For example, the evaluation unit 204 references the received request and identifies the properties indicated by the request that are required for the new product. The evaluation unit 204 then determines whether the existing product graph including the predicted node contains a node indicating the properties required for the new product. If the existing product graph including the predicted node contains a node indicating the properties required for the new product, the evaluation unit 204 assigns a higher rating to the node predicted by the link prediction means than if the existing product graph does not contain a node indicating the properties. The rating is represented, for example, by a recommendation level, and the higher the rating, the greater the recommendation level.

[0112] In S205, the graph update unit 205 determines whether or not to confirm the manufacturing method of the new product. If it is determined that the manufacturing method is confirmed (YES in S205), the process proceeds to S207, and if it is determined that the manufacturing method is not confirmed (NO in S205), the process proceeds to S206.

[0113] The conditions for determining the manufacturing method in S205 may be determined in advance. For example, thresholds may be set for the number of nodes representing ingredients and the number of nodes representing manufacturing methods, and the manufacturing method may be determined when the number of nodes included in the new product graph both exceeds the threshold. Furthermore, for example, whether or not to determine the manufacturing method may be determined based on user input. In this case, it is preferable that the output unit 210 outputs the new product graph or the ingredients and manufacturing method shown therein and presents this information to the user.

[0114] In S206, the graph update unit 205 adds nodes and links to the new product graph. The links and nodes to be added may be determined according to a user input, or may be determined by the graph update unit 205. Note that in S206, the graph update unit 205 may replace a node included in the current new product graph with another node according to a user input.

[0115] Once the new product graph has been updated with the addition of nodes and links, the process returns to S203, where nodes that link to the nodes included in the updated new product graph are predicted. In other words, in the process of Fig. 9, node prediction in S203, node evaluation in S204, and updating of the new product graph are repeated until a YES determination is made in S205.

[0116] In S207, the estimation unit 207 estimates a manufacturing method for the new product that matches the request received in S101. Specifically, the estimation unit 207 estimates that the manufacturing method shown in the new product graph when the determination in S205 is YES is the manufacturing method for the new product that matches the request.

[0117] In S208, the basis generating unit 208 generates basis information indicating the basis for the estimation in S207. Specifically, the basis generating unit 208 may generate basis information including, as the basis for the estimation, information on existing products that have the same development concept as the development concept of the new product, or information on existing products that use the same ingredients as those used in the new product.

[0118] In S209, the output unit 210 outputs information indicating the manufacturing method estimated in S207. At this time, the output unit 210 may also output the basis information generated in S208. This completes the processing of FIG.

[0119] Exemplary Embodiment 3 A third exemplary embodiment of the present invention will be described in detail with reference to the drawings. The configuration of the food product development support device according to this exemplary embodiment is similar to the configuration of the food product development support device 1 according to exemplary embodiment 2. However, in the food product development support device according to this exemplary embodiment, the processing by the link prediction unit 203 and the estimation unit 207 differs from that of the food product development support device 1 according to exemplary embodiment 2.

[0120] The link prediction unit 203 according to this exemplary embodiment uses the new product graph and the existing product graph to perform link prediction for predicting relationships between nodes that are not connected by links in the new product graph and the existing product graph, and identifies the existing products that have a predetermined relationship with the new product through the link prediction.The estimation unit 207 according to this exemplary embodiment then estimates a manufacturing method for the new product that matches the request, based on the existing products identified by the link prediction unit 203.

[0121] Since information on existing products that have a predetermined relationship with a new product to be developed is useful in developing a new product, the above configuration can favorably support the development of new food products.

[0122] The processing by the link prediction unit 203 and the estimation unit 207 according to this exemplary embodiment will be described below with reference to Fig. 10. Fig. 10 is a diagram illustrating a method for identifying an existing product having a predetermined relationship with a new product by the link prediction unit 203 according to this exemplary embodiment. Note that, in the example of Fig. 10, a case where the "predetermined relationship" is a "similar" relationship is taken as an example, but this does not limit this exemplary embodiment.

[0123] (Regarding identification of similar products) Fig. 10 is a diagram illustrating a method for identifying similar products by the link prediction unit 203. Fig. 10 shows an existing product graph in which existing products A to C are represented by nodes that represent the texture, ingredients, aroma, seasoning, or manufacturing method of the existing products, and edges that represent the relationships between the nodes. For example, the node for "existing product A" and the node for "smooth" are connected by an edge that represents "texture," which indicates that existing product A has a smooth texture.

[0124] 10 includes nodes for multiple existing products, existing products A to C, but a graph consisting of only nodes related to one existing product may also be called an existing product graph. In this case, similar products are identified using multiple existing product graphs corresponding to each of the multiple existing products.

[0125] Such an existing product graph can be generated from the texture, ingredients, aroma, seasonings, or manufacturing method of each existing product. Furthermore, by learning the relationship between the texture, ingredients, aroma, seasonings, etc. shown in the existing product graph and the manufacturing method of the existing product, it becomes possible to infer the relationship between the texture, ingredients, aroma, seasonings, etc. of a new product and the manufacturing method of the existing product.

[0126] 10 also shows a new product graph in which new products are represented by nodes that represent the texture, ingredients, aroma, seasonings, manufacturing method, etc. of the new product, and edges that represent the relationships between the nodes. More specifically, the new product graph shown in FIG. 10 includes nodes and links that indicate that the new product has a "smooth" texture, nodes and links that indicate that the new product has a "fragrant" aroma, and nodes and links that indicate that the new product uses an ingredient called "tomato."

[0127] The graph generating unit 202 generates the new product graph as described above based on the request for a new product received by the receiving unit 201. That is, when a request is received requesting that the new product have a smooth texture, a fragrant aroma, and use tomatoes as an ingredient in the new product, a new product graph as shown in Fig. 10 is generated.

[0128] By using the new product graph and existing product graph generated in this way, the link prediction unit 203 can identify existing products that have a predetermined relationship with the new product. For example, it is possible to identify existing products that are similar to the new product, as well as existing products that are dissimilar to the new product, existing products that belong to the same category as the new product, existing products that have effects in common with the new product, etc.

[0129] The above identification can be achieved by link prediction, which predicts the relationship between nodes that are not connected by links in the new product graph and the existing product graph. For example, as shown by the dashed line in Figure 10, there is no link between the "new product" node in the new product graph and the "existing product A" node in the existing product graph.

[0130] By performing link prediction, the link prediction unit 203 can predict the probability that the relationship between these nodes is "similar." Similarly, the link prediction unit 203 can predict the probability that the relationship between the "new product" node and the nodes of existing products B and C included in the existing product graph is "similar." Then, the link prediction unit 203 can identify similar products based on the predicted probabilities. For example, the link prediction unit 203 may identify existing products whose predicted probability value is equal to or greater than a threshold as similar products.

[0131] The link prediction unit 203 can also identify existing products that meet preset conditions or conditions set by the user as existing products that have a predetermined relationship with the new product. For example, it is possible to identify an existing product that shares at least some of the ingredients with the new product as a similar product, or to identify an existing product that shares at least some of the manufacturing method with the new product as a similar product.

[0132] The estimation unit 207 estimates a manufacturing method for a new product that matches the request based on the existing products identified by the link prediction unit 203. Information about existing products that have a predetermined relationship with the new product to be developed is useful in developing a new product, so the above configuration can effectively support the development of new food products.

[0133] Exemplary Embodiment 4 A food product development support device 3 according to a fourth exemplary embodiment of the present invention will be described with reference to the drawings. The food product development support device 3 supports the development of a new product using a base product. One method of developing a new product is to develop a new product based on a base product that is considered to be preferable. The food product development support device 3 supports the development of a new product in such cases.

[0134] (overview) FIG. 11 is a diagram showing an overview of a food product development support method according to this exemplary embodiment. In this exemplary embodiment, an example of supporting new food product development using a base product graph and an existing product graph is described. Note that FIG. 11 shows nodes such as existing product A and existing product B as nodes included in the existing product graph, but other nodes included in the existing product graph are omitted from the illustration. The existing product graph used in this exemplary embodiment is the same as the diagram on the right side of FIG. 5 described in exemplary embodiment 2.

[0135] A base product graph is a graph that includes multiple nodes related to the production of a base product that will be used as the basis for a new product to be developed. The base product graph shown in Figure 11 includes a node indicating that the base product has a "smooth" texture, a node indicating that it contains the ingredient "tomato," and a node and link indicating that the "cooking method" is that it is produced by boiling. Such a base product graph can be generated from the texture, ingredients, aroma, seasonings, cooking method, etc. of the base product.

[0136] For example, a base product graph can be generated by accepting input from a user of the texture, ingredients, aroma, seasonings, cooking method, etc. of a base product. At this time, requests for the texture, etc. required for a new product based on the base product may also be accepted. In addition, the user may select a base product from among the existing products shown in the existing product graph. In this case, the existing product graph of the selected existing product may be used as the base product.

[0137] In the food product development support method according to this exemplary embodiment, a base product graph and an existing product graph are used to identify existing products that have a predetermined relationship with the base product through link prediction for predicting relationships between nodes that are not connected by links in the base product graph and the existing product graph. Then, based on the manufacturing methods of the identified existing products, a manufacturing method for a new product that is based on the base product and matches the request is estimated.

[0138] The manufacturing method of an existing product that has a predetermined relationship with the base product is useful information for estimating a manufacturing method of a new product that is based on the base product and matches the request. Therefore, the food product development support method according to this exemplary embodiment can estimate a manufacturing method of a new product that matches the request by taking this useful information into consideration.

[0139] Link prediction makes it possible to identify existing products that have various relationships with the base product. For example, it is possible to identify existing products that are similar to the base product, as well as existing products that are dissimilar to the base product, existing products that belong to the same category as the base product, and existing products that have a common texture with the base product.

[0140] An example of identifying an existing product similar to a base product is shown in Figure 11. Specifically, in the example of Figure 11, existing product Z is identified as an existing product similar to the base product among multiple existing products shown in the existing product graph, and the existing product graph of existing product Z is extracted.

[0141] Here, the existing product graph of existing product Z extracted as described above contains a node indicating that existing product Z has a "fragrant" aroma, a node indicating that it contains the ingredient "eggplant," and a node and link indicating that it is produced using the cooking method "stir-frying." These nodes show that existing product Z is similar to the base product, but has a fragrant aroma that is not found in the base product. It can be said that this aroma may be due to the cooking method of stir-frying eggplant, an ingredient not included in the base product.

[0142] Based on the above, in the example of Fig. 11, a production method is recommended in which eggplant is added and fried to add a fragrant aroma to the base product. In this way, the food product development support method according to this exemplary embodiment makes it possible to estimate and recommend a production method for a new product that meets a user's request.

[0143] (Device configuration) The configuration of the food product development assistance device 3 according to this exemplary embodiment will be described with reference to Fig. 12. Fig. 12 is a block diagram showing the configuration of the food product development assistance device 3 according to this exemplary embodiment.

[0144] As shown in the figure, the food development support device 3 includes a receiving unit 301, a graph generating unit 302, a link predicting unit 303, a property predicting unit 304, an estimating unit 305, a basis generating unit 306, and an output unit 307. In addition to these components, like the food development support device 2 of exemplary embodiment 2, the food development support device 3 may also include an input device that receives input operations from a user, an output device for outputting data from the food development support device 3, a communication device that enables the food development support device 3 to communicate with other devices, and the like.

[0145] The receiving unit 301 receives requests related to the development of new cosmetic products. This request may include, for example, the texture or fragrance desired for the new product, ingredients or seasonings to be used in the new product, a manufacturing method for the new product, etc. The request may also include, for example, information specifying a base product that will be the base for the new product, as well as the texture, ingredients, fragrance, seasonings, manufacturing method, etc.

[0146] The graph generation unit 302 generates a base product graph that represents the base product based on the information about the base product. Specifically, the graph generation unit 302 generates a base product graph that represents the base product with nodes that represent the texture, ingredients, aroma, seasonings, or manufacturing method of the base product, and edges that represent the relationships between the nodes. Note that if the base product graph is included in the existing product graph, the graph generation unit 302 can simply extract the base product graph from the existing product graph.

[0147] The link prediction unit 303 uses a base product graph including multiple nodes related to the manufacture of a base product on which a new product to be developed is based, and multiple existing product graphs generated for each of multiple existing products, to perform link prediction to predict relationships between nodes that are not connected by links in the base product graph and the existing product graph, thereby identifying existing products that have a predetermined relationship with the base product. Hereinafter, existing products that are similar to the base product will be referred to as "similar products to the base product." As described above, link prediction can identify existing products that have any relationship with the base product, in addition to similar relationships.

[0148] The property prediction unit 304 predicts properties (texture, aroma, etc.) that can be added to the base product. Specifically, the property prediction unit 304 refers to the existing product graph of the similar product to the base product identified by the link prediction unit 303, and predicts, among the properties shown in the existing product graph, properties that are not present in the base product as properties that can be added to the base product.

[0149] The estimation unit 305 estimates a manufacturing method for a new product that matches the request based on the existing product identified by the link prediction means. The estimation unit 305 estimates a manufacturing method for a new product that matches the request based on a trained model that has learned the relationship between the texture, ingredients, aroma, or seasoning of the existing product and the manufacturing method for the existing product, and the request received by the receiving unit 301. Specifically, the trained model is the existing product graph described above. As described above, the link prediction unit 303 performs link prediction using the existing product graph, and therefore the estimation unit 305 performs the above estimation based on the result of link prediction by the link prediction unit 303, thereby realizing estimation based on the trained model.

[0150] The basis generating unit 306 generates basis information indicating the basis for the estimation by the estimation unit 305. The basis generating unit 306 is similar to the basis generating unit 208 described in the second exemplary embodiment, and therefore detailed description thereof will not be repeated.

[0151] The output unit 307 outputs various information generated by the food development support device 3, such as information indicating the production method estimated by the estimation unit 305. As with the output unit 210 described in the second exemplary embodiment, the destination of the information output by the output unit 307 is not particularly limited.

[0152] As described above, the food product development assistance device 3 includes a link prediction unit 303 that identifies existing products that have a predetermined relationship with the base product by link prediction to predict relationships between nodes that are not connected by links in the base product graph and the existing product graph, using a base product graph including multiple nodes related to the production of a base product that is the basis for the new product to be developed and multiple existing product graphs generated for each of multiple existing products. Furthermore, the estimation unit 305 estimates a production method for the new product that matches the request, based on the existing products identified by the link prediction unit 303.

[0153] According to the above configuration, existing products that have a predetermined relationship with the base product are identified, and a manufacturing method for a new product that meets the request is estimated based on the identified existing products. Information about existing products that have a predetermined relationship with the base product that forms the basis of the new product is useful in developing a new product. Therefore, the above configuration can contribute to the development of new food products that use the base product.

[0154] (Processing flow) The flow of the process (food development support method) executed by the food product development support device 3 will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the flow of the process executed by the food product development support device 3.

[0155] In S301, the receiving unit 301 receives a request for the development of a new food product. Here, it is assumed that the received request includes information about a base product. The information about the base product may be sufficient to generate a base product graph in the next step S302. For example, the received request may include information about the texture, ingredients, aroma, seasonings, manufacturing method, etc. of the base product.

[0156] In S302, the graph generation unit 302 generates a base product graph based on the information input in S301. For example, if input of the texture, ingredients, and cooking method of a base product is received in S301, the graph generation unit 302 may generate a base product graph including nodes and links indicating the texture, ingredients, and cooking method.

[0157] In S303, the link prediction unit 303 performs link prediction using the pre-learned existing product graph and the base product graph generated in S302, and predicts (specifies) products similar to the base product.

[0158] In S304, the property prediction unit 304 predicts properties that can be added to the base product based on the identification result of S303. Specifically, the property prediction unit 304 refers to the existing product graph of a product similar to the base product identified in S303, and predicts, among the properties shown in the existing product graph, properties that are not present in the base product as properties that can be added to the base product.

[0159] Here, the output unit 307 may output the properties predicted by the property prediction unit 304 and present them to the user, allowing the user to select the properties desired for the new product from the presented properties. In this case, the receiving unit 301 receives the properties selected by the user as a request.

[0160] The request received in S301 may also include the texture, aroma, etc. desired for the new product. In this case, after the processing of S304, the property prediction unit 304 determines whether the requested texture, aroma, etc. are included in the predicted properties. If the property prediction unit 304 determines that the requested texture, aroma, etc. are not included, it may cause the output unit 307 to output a message to the effect that a manufacturing method for a new product having the requested texture, aroma, etc. could not be estimated, and the processing of FIG. 13 may end.

[0161] In S305, the estimation unit 305 estimates elements of the manufacturing method to be applied to the base product. Specifically, the estimation unit 305 refers to the existing product graph and identifies existing products that have properties that match the request from among the existing products identified in S303 as being similar to the base product. Note that the request here refers to the request received in S301 or a request based on the prediction result in S304. In addition, here, the estimation unit 305 does not need to identify existing products that have all of the requested properties; it is sufficient to identify existing products that have at least some of the requested properties.

[0162] Then, the estimation unit 305 refers to the existing product graph of the existing product estimated in S305, and estimates elements included in the manufacturing method of the existing product that are not included in the manufacturing method of the base product as elements of the manufacturing method of the new product. The manufacturing method including these elements is the estimated result of the manufacturing method of the new product that matches the request.

[0163] In S306, the basis generation unit 306 generates basis information that indicates the basis for the estimation in S305. Specifically, the basis generation unit 306 may generate basis information that includes information about existing products that have the same properties as the properties required for the new product, and this basis information may include information that indicates a manufacturing method for the existing products that have the same properties as the properties required for the new product. For example, the basis generation unit 306 may generate, as basis information, the product name of the existing product identified in S305 (an existing product that has properties that match the request among existing products identified as being similar to the base product) and its manufacturing method that is shown in the existing product graph.

[0164] In S307, the output unit 307 outputs information indicating the manufacturing method estimated in S305. At this time, the output unit 307 may also output the basis information generated in S306. This completes the processing shown in FIG.

[0165] As described above, the estimation unit 305 may estimate, as an element of the manufacturing method for the new product, an element that is not included in the manufacturing method for the base product, among the elements included in the manufacturing method for a product similar to the base product identified by the link prediction unit 303 in S303.

[0166] An element that is included in the manufacturing method of an existing product similar to the base product but is not included in the manufacturing method of the base product is likely to be an element that is compatible with the manufacturing method of the base product. Therefore, with the above configuration, an element that is likely to be compatible with the manufacturing method of the base product can be estimated as an element of the manufacturing method of the new product.

[0167] Various conditions can be set for the link prediction in S303. For example, the link prediction unit 303 may identify an existing product that is similar to the base product and has at least one of the properties required for the new product. The properties required for the new product may be identified based on the request received in S301.

[0168] Such information about existing products is extremely useful in estimating a manufacturing method for a new product having the desired properties. Therefore, this configuration makes it possible to accurately estimate a manufacturing method for a food product having the desired properties. Note that if an existing product having the predetermined properties is identified in S303, the process of S304 may be omitted.

[0169] Furthermore, in S303, the link prediction unit 303 may identify a manufacturing method for an existing product that is similar to the base product and has properties that match the request by link prediction using the base product graph and the existing product graph. In this case, the estimation unit 305 may estimate elements included in the manufacturing method identified in this way as elements of the manufacturing method for the new product. Even without going through the process of identifying similar products, similar relationships between products are learned when learning the existing product graph, so it is possible to identify a manufacturing method for an existing product that has properties that match the request by the above link prediction. In this case, the processes of S303 to S306 are omitted.

[0170] Exemplary Embodiment 5 A food product development support device 4 according to a fifth exemplary embodiment of the present invention will be described with reference to the drawings. The food product development support device 4 supports the development of new products with desired properties. One method of developing new products is to develop products with properties that are thought to be desired by consumers. The food product development support device 4 supports the development of new products in such cases.

[0171] (overview) 14 is a diagram showing an overview of a food product development support method according to this exemplary embodiment. In this exemplary embodiment, an example will be described in which a manufacturing method for a new product that matches a request is estimated while a new product graph is updated.

[0172] In this exemplary embodiment, link prediction is performed using a new product graph and an existing product graph, similar to exemplary embodiment 2. The new product graph shown in the top left corner of Fig. 14 includes nodes and links indicating that the ingredients of the new product include "tomato" and that the cooking method for the new product is "simmering."

[0173] Furthermore, the existing product graph shown in the upper center of Fig. 14 includes nodes and links indicating that existing product A has a "refreshing" texture, contains "eggplant" as an ingredient, and is cooked by "grilling." Similarly, the existing product graph shown in the upper right corner of Fig. 14 includes nodes and links indicating that existing product B has a "fragrant" aroma, contains "cheese" as an ingredient, and is cooked by "grilling."

[0174] By learning the existing product graphs for various existing products as described above, it becomes possible to link-predict what kind of products are likely to have what kind of properties. In other words, in the food product development support method according to this exemplary embodiment, a new product graph is provisionally set, and link-predicts the probability that a new product shown in the new product graph will have the requested properties.

[0175] For example, in the example in Figure 14, the probability that the "smooth" node will be connected to the "new product" node in the new product graph shown on the top left corner via the "texture" link is predicted to be 30%, which is not a sufficiently high probability.

[0176] Therefore, as shown in the bottom left of the figure, the node connected to the "New Product" node in the new product graph by the "Ingredients" link is changed from "Tomato" to "Avocado," and link prediction is performed again. As a result, the predicted probability that the "Smooth" node will be connected to the "New Product" node by the "Texture" link has changed to 80%.

[0177] Therefore, according to the food product development support method of this exemplary embodiment, it is possible to recommend the use of "avocado" as a measure to give the new product a smooth texture. Note that although the ingredients are replaced in the example of FIG. 14, ingredients can also be added. In addition, it is also possible to similarly recommend a manufacturing method for producing a new product that meets the request.

[0178] (Device configuration) The configuration of a food product development assistance device 4 according to a fifth exemplary embodiment of the present invention will be described with reference to Fig. 15. Fig. 15 is a block diagram showing the configuration of a food product development assistance device 4 according to this exemplary embodiment.

[0179] As shown in the figure, the food development support device 4 includes a receiving unit 401, a graph generating unit 402, a link predicting unit 403, a graph updating unit 404, an estimating unit 405, a basis generating unit 406, and an output unit 210. In addition to these components, like the food development support device 2 of exemplary embodiment 2, the food development support device 4 may also include an input device that receives user input operations, an output device that outputs data from the food development support device 4, a communication device that enables the food development support device 4 to communicate with other devices, and the like.

[0180] The receiving unit 401 receives a request for the development of a new food product. This request may include, for example, the properties (texture, aroma, etc.) required for the new product, the ingredients or seasonings to be used in the new product, the manufacturing method to be applied when manufacturing the new product, etc. Furthermore, this request may also include, for example, a threshold value for the probability that the desired efficacy will be manifested in the new product.

[0181] Similar to the graph generator 202 in the second exemplary embodiment, the graph generator 402 generates a new product graph that graphically represents a new product that the user wants to manufacture, based on information about the new product.

[0182] The link prediction unit 403 uses a new product graph including multiple nodes related to the manufacture of a new product to be developed and an existing product graph to calculate the probability that a node exhibiting a predetermined property will be linked to a node included in the new product graph by link prediction for predicting the relationship between nodes that are not connected by links in the new product graph and the existing product graph. The predetermined property is a property that matches the request accepted by the accepting unit 401.

[0183] The graph update unit 404 updates the new product graph. Specifically, the graph update unit 404 performs either or both of a process of replacing nodes included in the new product graph with other nodes and a process of adding new nodes to the new product graph.

[0184] The new product graph may be updated according to user input or automatically. In the former case, the graph update unit 404 may cause the output unit 210 to output a list of nodes included in the current new product graph, as well as candidate nodes to be added to the new product graph or to replace nodes in the current new product graph. In the latter case, the graph update unit 404 may select nodes to be added from these candidates. Candidate nodes may be extracted from the existing product graph of an existing product that has the requested properties.

[0185] The estimation unit 405 estimates a manufacturing method for a new product that matches the request based on the probability calculated by the link prediction unit 403. That is, the estimation unit 405 estimates a manufacturing method for a new product that matches the request based on a trained model that has learned the relationship between the ingredients, seasonings, properties, etc. of existing products and the manufacturing methods for existing products, and the request received by the reception unit 401. Specifically, the trained model is the above-mentioned existing product graph. As described above, the link prediction unit 403 performs link prediction using the existing product graph, and therefore the estimation unit 405 performs the above estimation based on the result of link prediction by the link prediction unit 403, thereby performing estimation based on the trained model.

[0186] The basis generating unit 406 generates basis information indicating the basis of the estimation by the estimating unit 405. The basis generating unit 406 is similar to the basis generating unit 208 in the second exemplary embodiment, and therefore detailed description thereof will not be repeated.

[0187] The output unit 210 outputs various information generated by the food development support device 4, such as information indicating the production method estimated by the estimation unit 405. As with the output unit 210 of the second exemplary embodiment, the destination of the information output by the output unit 210 is not particularly limited.

[0188] As described above, the food development support device 4 includes a link prediction unit 403 that calculates the probability that a node exhibiting a predetermined property will be linked to a node included in the new product graph by link prediction to predict the relationship between nodes that are not connected by links in the new product graph and the existing product graph, using a new product graph that includes multiple nodes related to the production of a new product to be developed and an existing product graph, and the estimation unit 405 estimates a production method for the new product that matches the request based on the probability calculated by the link prediction unit 403.

[0189] According to the above configuration, the food product development support device 4 estimates a manufacturing method for a new product that meets the request based on the probability that a node exhibiting a predetermined property will be linked to a node included in the new product graph. The probability that a node exhibiting a predetermined property will be linked to a node included in the new product graph indicates the likelihood that the new product will have the predetermined property, and response information generated based on this probability is useful in the development of new products. Therefore, the above configuration can contribute to the development of new food products with desired properties.

[0190] (Processing flow) Next, the flow of the process (food product development support method) executed by the food product development support device 4 will be described with reference to Fig. 16. Fig. 16 is a flowchart showing the flow of the process executed by the food product development support device 4.

[0191] In S401, the receiving unit 401 receives a request for the development of a new food product. In S401, for example, a request indicating the properties required for the new product, some of the ingredients to be used in manufacturing the new product, etc. is received.

[0192] In S402, the graph generation unit 402 generates a new product graph based on the information input in S401. For example, if input of the properties required for the new product and one of the ingredients to be used in manufacturing the new product is received in S401, the graph generation unit 402 may generate a new product graph including nodes and links indicating the properties and ingredients.

[0193] In S403, the link prediction unit 403 calculates the probability that a node that shows properties that match the request received in S401 will be linked to a node included in the new product graph generated in S402. As described above, this probability is calculated by link prediction using the learned existing product graph and the new product graph.

[0194] In S404, the graph update unit 404 determines whether the probability calculated in S403 is equal to or greater than a threshold value. If it is determined that the probability is equal to or greater than the threshold value (YES in S404), the process proceeds to S406, and if it is determined that the probability is less than the threshold value (NO in S404), the process proceeds to S405.

[0195] If the request received in S401 specifies multiple properties, predictions are made for each property in S403, and if the probability for all properties is equal to or greater than the threshold, a YES result is made in S404, and if even one property is below the threshold, a NO result is made. This makes it possible to estimate a manufacturing method for a new product that satisfies all of the requested properties.

[0196] The request may also indicate that the food does not have a specific property, such as not being an allergenic food. In this case, in S403, the probability that the node with that property is linked is calculated, and in S404, it is determined whether the probability is equal to or less than a threshold.

[0197] In S405, the graph update unit 404 updates the new product graph. Specifically, the graph update unit 404 may replace a node included in the current new product graph with another node, or may add a new node and link to the current new product graph. As described above, the update content may be determined according to a user input, or may be determined by the graph update unit 404.

[0198] 16, the calculation of the probability in S403 and the update of the new product graph in S405 are repeated until the determination in S404 is YES.

[0199] In S406, the estimation unit 405 estimates a manufacturing method for the new product that matches the request received in S401. Specifically, the estimation unit 405 estimates that the manufacturing method shown in the new product graph when the determination in S404 is YES is the manufacturing method for the new product that matches the request.

[0200] In S407, the basis generating unit 406 generates basis information indicating the basis for the estimation in S406. Specifically, the basis generating unit 406 may generate basis information including information on an existing product having the same properties as those required for the new product, and this basis information may include information indicating a manufacturing method for the existing product having the same properties as those required for the new product.

[0201] In S408, the output unit 210 outputs information indicating the manufacturing method estimated in S406. At this time, the output unit 210 may also output the basis information generated in S407. This ends the processing shown in FIG.

[0202] [Modification] As described above, by using a new product graph and an existing product graph, it is possible to predict the properties of a new product shown in the new product graph by link prediction. Furthermore, new product property prediction can also be performed by methods other than link prediction. This will be explained with reference to FIG. 17. FIG. 17 is a diagram illustrating an example of predicting the properties of a new product based on feature quantities calculated from the new product graph and the existing product graph. FIG. 17 shows existing product graphs for existing products A to C and a new product graph for a new product. Note that the nodes and links included in these graphs are omitted from the illustration.

[0203] Here, the feature quantities for each existing product can be calculated by multiplying the feature quantities of each node included in the existing product graph by a weight corresponding to the link connected to that node and adding the results together. Therefore, if learning is performed to update the weights so that the calculated feature quantities correspond to the properties of the existing products, it becomes possible to predict the properties of new products from the feature quantities of the new product graph calculated by applying the weights.

[0204] For example, in the example of Figure 17, the feature amount calculated from the existing product graph of existing product A, which is known to be Chinese style, is trained to fall within a range in the feature space corresponding to the attribute "Chinese style." Also, the feature amount calculated from the existing product graph of existing product B, which is known to be Japanese style, is trained to fall within a range in the feature space corresponding to the attribute "Japanese style."

[0205] In this case, as shown in the figure, if the feature quantity calculated from the new product graph is within the range corresponding to the attribute "Japanese style," it can be predicted that the new product has the attribute "Japanese style." Such an attribute prediction method can be applied as an alternative method to the attribute prediction methods in each of the exemplary embodiments described above.

[0206] [Software implementation example] Some or all of the functions of the food development support devices 1, 2, 3, and 4 (hereinafter referred to as "food development support device 1, etc.") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0207] In the latter case, the food product development support device 1 and the like are realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in FIG. 18. The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for operating the computer C as the food product development support device 1 and the like. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the food product development support device 1 and the like.

[0208] The processor C1 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0209] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0210] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0211] [Appendix 1] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiments are also included in the technical scope of the present invention.

[0212] [Appendix 2] Some or all of the above-described embodiments can also be described as follows: However, the present invention is not limited to the following described aspects.

[0213] (Appendix 1) A food development support device comprising: a receiving means for receiving a request for the development of a new food product; a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product; an estimation means for estimating a manufacturing method of a new product that matches the request based on the request; and an output means for outputting information indicating the manufacturing method estimated by the estimation means.

[0214] According to the above configuration, it is possible to preferably support the development of new food products.

[0215] (Appendix 2) The food development support device described in Appendix 1 is characterized in that the request includes information indicating the development concept of the new product or information indicating the ingredients to be used in the new product, and the device is equipped with a basis generation means for generating basis information including, as the basis for the estimation, information on existing products that have the same development concept as the development concept of the new product or information on existing products that use the same ingredients as those used in the new product, and the output means further outputs the basis information.

[0216] According to the above configuration, the basis for the proposed manufacturing method (recipe, etc.) is based on existing products with the same development concept and ingredients, which allows the developer (user) to easily understand the contents and manufacturing method of the new product.

[0217] (Appendix 3) The food development support device described in Appendix 2, wherein the basis information includes information indicating a manufacturing method for an existing product that has the same development concept as the development concept of the new product or an existing product that uses the same ingredients as those used in the new product.

[0218] According to the above configuration, the developer can judge based on experience whether the outputted manufacturing method for the new product is suitable for the request as a product.

[0219] (Appendix 4) The food development support device described in Appendix 1, wherein the trained model is an existing product graph that represents one or more of the existing products using nodes that represent the development concept, properties, manufacturing method, or ingredients used in the existing product of the existing product, and edges that represent the relationships between the nodes.

[0220] The above-mentioned existing product graph represents existing products using nodes that represent the development concept, properties, and manufacturing method of the existing products or the ingredients used in the multiple existing products, and edges that represent the relationships between the nodes. Therefore, with the above-mentioned configuration, it is possible to estimate an appropriate manufacturing method by taking into account the mutual relationships between the development concept, properties, and manufacturing method of the existing products or the ingredients used in the multiple existing products.

[0221] (Appendix 5) The food development support device according to Appendix 4, further comprising: a link prediction means for predicting, by link prediction using a new product graph including a plurality of nodes related to the production of a new product to be developed and the existing product graph, relationships between nodes not connected by links in the new product graph and the existing product graph, from among nodes included in the existing product graph that indicate ingredients, seasonings, or cooking methods used in the existing product, nodes that link to nodes included in the new product graph, and the estimation means for estimating a production method for a new product that matches the request, based on the nodes predicted by the link prediction means.

[0222] According to the above configuration, nodes that link to nodes included in the new product graph are predicted from among nodes that indicate ingredients, seasonings, or cooking methods used in existing products. Nodes that link to nodes included in the new product graph are useful information for estimating a manufacturing method for a new product that matches the request. According to the above configuration, this useful information can be taken into consideration to estimate a manufacturing method for a new product that matches the request.

[0223] (Appendix 6) The food development support device described in Appendix 5, wherein the link prediction means predicts, from among nodes included in the existing product graph that include nodes that match the development concept of the new product, nodes that indicate ingredients, seasonings, or cooking methods used in the existing product and link to nodes included in the new product graph.

[0224] According to the above configuration, the prediction range of nodes linked to nodes included in the new product graph is narrowed down to the existing product graph including nodes that match the new product development concept, making it possible to predict nodes that are likely to have contributed to the new product development concept.

[0225] (Appendix 7) evaluation means for evaluating the nodes predicted by the link prediction means; The food development support device according to claim 5, wherein the evaluation means, when the existing product graph including the node predicted by the link prediction means includes a node indicating a property required for the new product, evaluates the node predicted by the link prediction means higher than when the existing product graph does not include a node indicating the property.

[0226] Other nodes included in an existing product graph that includes a node indicating a certain property may be factors that give that property to the existing product. For example, if an existing product graph that includes a node indicating that the product is "popular among young people" includes a node called "tapioca" that indicates an ingredient of the existing product, the "tapioca" node may be a factor that makes the product "popular among young people."

[0227] Therefore, according to the above configuration, among the nodes predicted by the link prediction means, nodes in the existing product graph that include nodes indicating the properties required for the new product are rated higher than nodes in the existing product graph that do not include nodes indicating the properties required for the new product. Based on this rating, the user can decide whether to apply the ingredients, seasonings, or cooking methods indicated in the predicted nodes to the new product. This can contribute to the development of new products with desired properties.

[0228] (Appendix 8) 3. The food development support device according to claim 1, further comprising: a link prediction means for identifying existing products having a predetermined relationship with the new product by link prediction using a new product graph including a plurality of nodes related to the production of a new product to be developed and a plurality of existing product graphs generated for each of a plurality of existing products, to predict the relationship between nodes that are not connected by links in the new product graph and the existing product graph; and an estimation means for estimating a production method for the new product that matches the request, based on the existing products identified by the link prediction means.

[0229] According to the above configuration, existing products that have a predetermined relationship with the new product are identified, and a manufacturing method for the new product that meets the request is estimated based on the identified existing products. Since information about existing products that have a predetermined relationship with the new product to be developed is useful in developing a new product, the above configuration can effectively support the development of new food products.

[0230] (Appendix 9) 3. The food development support device according to claim 1, further comprising: a link prediction means for identifying existing products having a predetermined relationship with the base product by link prediction using a base product graph including a plurality of nodes related to the manufacture of a base product on which the new product to be developed is based, and a plurality of existing product graphs generated for each of a plurality of existing products, to predict the relationship between nodes that are not connected by links in the base product graph and the existing product graph; and an estimation means for estimating a manufacturing method of a new product that conforms to the request, based on the existing products identified by the link prediction means.

[0231] According to the above configuration, existing products that have a predetermined relationship with the base product are identified, and a manufacturing method for a new product that meets the request is estimated based on the identified existing products. Information about existing products that have a predetermined relationship with the base product that forms the basis of the new product is useful in developing new products, so the above configuration can contribute to the development of new food products that use the base product.

[0232] (Appendix 10) 3. The food product development support device according to claim 1, further comprising: a link prediction means for calculating the probability that a node exhibiting a predetermined property will be linked to a node included in the new product graph by link prediction using a new product graph including a plurality of nodes related to the production of a new product to be developed and the existing product graph, to predict a relationship between nodes that are not connected by links in the new product graph and the existing product graph; and wherein the estimation means estimates a production method for the new product that meets the request based on the probability calculated by the link prediction means.

[0233] According to the above configuration, a manufacturing method for a new product that meets a request is estimated based on the probability that a node exhibiting a predetermined property is linked to a node included in the new product graph. The probability that a node exhibiting a predetermined property is linked to a node included in the new product graph indicates the likelihood that the new product will have the predetermined property, and response information generated based on this probability is useful in the development of new products. Therefore, the above configuration can contribute to the development of new food products with desired properties.

[0234] (Appendix 11) A food development support method in which a computer receives a request for the development of a new food product, estimates a manufacturing method for a new product that matches the request based on the request and a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product, and outputs information indicating the estimated manufacturing method.

[0235] According to the above configuration, it is possible to preferably support the development of new food products.

[0236] (Appendix 12) A food development support program that causes a computer to execute the following processes: receiving a request for the development of a new food product; estimating a manufacturing method for a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product; and outputting information indicating the estimated manufacturing method.

[0237] [Appendix 3] Some or all of the above-described embodiments can also be expressed as follows.

[0238] A food development support device comprising at least one processor, the processor performing a reception process for receiving a request for the development of a new food product, an estimation process for estimating a manufacturing method for a new product that matches the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, the product category of the existing product, the development concept of the existing product, and properties of the existing product, and a manufacturing method for the existing product, and the request, and an output process for outputting information indicating the estimated manufacturing method.

[0239] The food development assistance device may further include a memory that stores a program for causing the processor to execute the reception process, the estimation process, and the output process. The program may be recorded on a computer-readable, non-transitory, tangible recording medium. [Explanation of symbols]

[0240] 1,2,3,4...Food development support equipment 11. Reception 12…Estimation part 13...Output section 201, 301, 401...Reception 202, 302, 402...Graph generation section 203,403...Link prediction section 204...Evaluation Department 205,404...Graph update section 206…Study Department 207,305,405…Estimation part 208, 306, 406...Evidence generation section 210,307...Output section 304...Property prediction section 407...Feature extraction unit

Claims

1. A means for receiving requests regarding new food product development; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; an output means for outputting information indicating the manufacturing method estimated by the estimation means; Equipped with the request includes information indicating a development concept of the new product or information indicating ingredients to be used in the new product; a basis generating means for generating basis information including information on an existing product that has the same development concept as the development concept of the new product, or information on an existing product that uses the same ingredients as those used in the new product, as the basis for the estimation; The output means further outputs the basis information. Food development support equipment.

2. A receiving means for receiving requests regarding the development of new food products; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; an output means for outputting information indicating the manufacturing method estimated by the estimation means; Equipped with The trained model is an existing product graph that represents one or more of the existing products using nodes that represent the development concept, properties, manufacturing method, or ingredients used in the existing product, and edges that represent the relationships between the nodes. Food development support equipment.

3. A receiving means for receiving requests regarding the development of new food products; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; an output means for outputting information indicating the manufacturing method estimated by the estimation means; a link prediction means for using a new product graph including a plurality of nodes related to the manufacture of a new product to be developed and a plurality of existing product graphs generated for each of a plurality of existing products to predict a relationship between nodes that are not connected by a link in the new product graph and the existing product graph, and for identifying the existing products that have a predetermined relationship with the new product; the estimation means estimates a manufacturing method of a new product that matches the request based on the existing product identified by the link prediction means; Food development support equipment.

4. A receiving means for receiving requests regarding the development of new food products; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; an output means for outputting information indicating the manufacturing method estimated by the estimation means; a link prediction means for using a base product graph including a plurality of nodes related to the manufacture of a base product on which a new product to be developed is based and a plurality of existing product graphs generated for each of a plurality of existing products to predict a relationship between nodes that are not connected by a link in the base product graph and the existing product graph, and for identifying the existing products that have a predetermined relationship with the base product; the estimation means estimates a manufacturing method of a new product that matches the request based on the existing product identified by the link prediction means; Food development support equipment.

5. A receiving means for receiving requests regarding the development of new food products; an estimation means for estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; an output means for outputting information indicating the manufacturing method estimated by the estimation means; a link prediction means for calculating the probability that a node showing a predetermined property will be linked to a node included in the new product graph by link prediction for predicting a relationship between nodes not connected by a link in the new product graph and the existing product graph, using a new product graph including a plurality of nodes related to the manufacture of a new product to be developed and existing product graphs generated for each of a plurality of existing products; the estimation means estimates a manufacturing method of the new product that matches the request based on the probability calculated by the link prediction means; Food development support equipment.

6. The basis information includes information indicating a manufacturing method of an existing product that has the same development concept as the development concept of the new product, or an existing product that uses the same ingredients as those used in the new product. The food development support device according to claim 1.

7. a link prediction means for predicting, by link prediction using a new product graph including a plurality of nodes related to the production of a new product to be developed and the existing product graph, relationships between nodes not connected by links in the new product graph and the existing product graph, from among nodes included in the existing product graph that indicate ingredients, seasonings, or cooking methods used in the existing product, which nodes will link to nodes included in the new product graph; 3. The food product development assistance device according to claim 2, wherein the estimation means estimates a manufacturing method for the new product that matches the request based on the nodes predicted by the link prediction means.

8. 8. The food development support device according to claim 7, wherein the link prediction means predicts, from among nodes included in the existing product graph that include a node that matches the development concept of the new product, a node that indicates ingredients, seasonings, or cooking methods used in the existing product and that links to a node included in the new product graph.

9. evaluation means for evaluating the nodes predicted by the link prediction means; 8. The food development support device according to claim 7, wherein, when the existing product graph including the node predicted by the link prediction means includes a node indicating a property required for the new product, the evaluation means evaluates the node predicted by the link prediction means higher than when the existing product graph does not include a node indicating the property.

10. The computer We accept requests for new food product development, A manufacturing method of a new product that conforms to the request is estimated based on the request and a trained model that has learned the relationship between at least one of ingredients used in an existing product that is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product; outputting information indicating the estimated manufacturing method; the request includes information indicating a development concept of the new product or information indicating ingredients to be used in the new product; Generate evidence information including, as the basis for the estimation, information on existing products that have the same development concept as the development concept of the new product, or information on existing products that use the same ingredients as the ingredients used in the new product; further outputting the grounds information; Food development support methods.

11. For computers, Processing requests for new food product development; A process of estimating a manufacturing method of a new product that conforms to the request based on a trained model that has learned the relationship between at least one of ingredients used in an existing product, which is an existing food product, a product category of the existing product, a development concept of the existing product, and properties of the existing product, and a manufacturing method of the existing product, and the request; a process of outputting information indicating the estimated manufacturing method; Execute the request includes information indicating a development concept of the new product or information indicating ingredients to be used in the new product; A process of generating evidence information including, as the basis for the estimation, information on existing products that have the same development concept as the development concept of the new product, or information on existing products that use the same ingredients as those used in the new product; a process of further outputting the grounds information; A food development support program that implements the above.

Images