Information processing device and information processing method

Abstract

An information processing device 10 according to one embodiment comprises: an acquisition unit 12 that acquires a recipe creation request for a predetermined dish and user information about a user who browses the recipe; a determination unit 13 that determines a correction policy for recipe information prepared in advance for the predetermined dish on the basis of the user information; and an output unit 14 that outputs input information for indicating a generative AI model 31 to correct the recipe information based on the correction policy.

Description

Information processing device and information processing method

[0001] One aspect of the present disclosure relates to an information processing device and an information processing method.

[0002] Patent Document 1 discloses a system for acquiring user attribute information (age, cooking skills) and outputting recipe information aloud at an output tempo according to the attribute.

[0003] Japanese Patent Application Laid-Open No. 2020-107305

[0004] According to the system described in Patent Document 1, recipe content can be output aloud at a speed that corresponds to the user's cooking skill, etc., which can improve the convenience of the user who cooks according to the recipe to some extent, but the recipe content itself remains the same as the pre-prepared content. As such, the system does not customize the recipe content of a specific dish to make it more appropriate for the user, so there is room for improvement in terms of improving user convenience.

[0005] Therefore, an object of one aspect of the present disclosure is to provide an information processing device and an information processing method that can appropriately and easily generate recipe information for a predetermined dish that is suited to a user.

[0006] An information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires a recipe creation request for a specified dish and user information related to a user viewing the recipe, a determination unit that determines a correction policy for pre-prepared recipe information for the specified dish based on the user information, and an output unit that outputs input information to instruct a generative AI model to correct the recipe information based on the correction policy.

[0007] An information processing method according to another aspect of the present disclosure includes the steps of acquiring a recipe creation request for a specified dish and user information regarding a user viewing the recipe, determining a correction policy for pre-prepared recipe information for the specified dish based on the user information, and outputting input information for instructing a generative AI model to correct the recipe information based on the correction policy.

[0008] According to one aspect of the present disclosure, recipe information for a predetermined dish that is suited to a user can be appropriately and easily generated.

[0009] Fig. 1 is a block diagram showing the overall configuration of a system including an information processing device according to an embodiment; Fig. 2 is a diagram showing an example of correction information; Fig. 3 is a diagram showing an example of meta information of an image that can be added to recipe information; Fig. 4 is a diagram showing an example of a prompt output by an output unit; Fig. 5 is a flowchart showing an example of the operation of the information processing device; Fig. 6 is a diagram showing an example of the hardware configuration of the information processing device;

[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] Fig. 1 is a diagram showing the overall configuration of a system including an information processing device 10 according to one embodiment. The system shown in Fig. 1 includes the information processing device 10, a user terminal 20, and a generation AI server 30. The information processing device 10 is configured to be able to communicate with each of the user terminal 20 and the generation AI server 30 via any communication network. The information processing device 10 functions as a so-called RAG (Retrieval-Augmented Generation) system.

[0012] The information processing device 10 executes processing to cause the generative AI model to generate recipe information for a predetermined dish that is tailored to the user. As an example, the information processing device 10 is configured to generate and output input information for instructing the generative AI server 30 based on information received from the user terminal 20 (in this embodiment, a recipe creation request for the predetermined dish and user information). More specifically, the information processing device 10 generates and outputs input information for instructing the generative AI server 30 to generate recipe information tailored to the user by correcting existing recipe information prepared in advance for the predetermined dish based on user information (in this embodiment, the user's cooking skills, ingredient requirements, etc.).

[0013] As an example, the input information is information that constitutes at least a part of the prompt input to the generative AI model 31. The generative AI server 30 receives a prompt including such input information and inputs the prompt to the generative AI model 31, thereby generating and outputting recipe information corrected (customized) for the user. The recipe information output by the generative AI model 31 may be transmitted directly to the user terminal 20, or may be transmitted to the user terminal 20 via the information processing device 10. Alternatively, the recipe information may be accumulated (stored) on any server that the user can access via the user terminal 20, etc. In this case, the user can view the recipe information generated by the generative AI model 31 by accessing the server at any time.

[0014] The user terminal 20 is a terminal device used by a user who wishes to obtain recipe information for a specific dish. The specific dish is, for example, a commonly known dish such as mapo tofu. However, the specific dish is not limited to a specific dish or a specific genre. The recipe information is information indicating the steps (recipe) for making the specific dish, and may include various content such as text, audio, images, and video.

[0015] The user terminal 20 may take any form, such as a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, a game console, etc. Although only one user terminal 20 is illustrated in FIG. 1 , the information processing device 10 may be configured to be able to execute the above-described support for generating recipe information customized for a user (i.e., the process for causing the generation AI model 31 to generate recipe information) for multiple users. In this case, the system illustrated in FIG. 1 may include multiple user terminals 20 used by multiple users, respectively.

[0016] The generation AI server 30 includes a generation AI model 31, and is a device that generates and provides content using the generation AI model 31. The generation AI model 31 is a model that can generate content (in this embodiment, corrected recipe information) in response to input of a prompt (input information) output by the information processing device 10, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and return the content as response information.

[0017] A prompt is information indicating an instruction or question input to the generative AI model 31 in an interactive system such as a dialogue with the generative AI model 31 or a command line interface (CLI). The prompt can include various types of input information. In this case, the generative AI model 31 generates response information targeted at the various types of input information. The type and format of the input information are not particularly limited, and the input information may include, for example, data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0018] The generative AI model 31 may be configured to include, for example, a large-scale language model (LLM) and a user interface (UI) for interacting with a user. The generative AI model 31 may be an interactive AI model capable of chatting with a user via text or voice. Examples of such a generative AI model 31 include ChatGPT, GPT-3.5, GPT-4V, and PaLM2. However, the generative AI model 31 may also be an AI model other than the large-scale language model described above.

[0019] The generative AI model 31 may be placed in a generative AI server 30 separate from the information processing device 10, as shown in FIG. 1, or may be placed in the information processing device 10. Alternatively, the generative AI model 31 may be placed in a user terminal 20, for example, like tsuzumi. In this case, each function of the information processing device 10 may also be placed in the user terminal 20. That is, the user terminal 20 itself may function as the information processing device 10 of this embodiment.

[0020] The information processing device 10 includes a storage unit 11 , an acquisition unit 12 , a determination unit 13 , and an output unit 14 .

[0021] The storage unit 11 stores various data handled by the information processing device 10. The storage unit 11 includes a knowledge database that is a search destination for information used to generate prompts for the generative AI model 31. In this embodiment, the storage unit 11 that functions as such a knowledge database is implemented on the information processing device 10, but the knowledge database may also be implemented outside the information processing device 10 (for example, on a network).

[0022] In this embodiment, the storage unit 11 stores user information of pre-registered users. An example of the user information is user profile information registered in association with the user's account. The user information may be information input (registered) by the user himself / herself, or information about the user's characteristics estimated from the information registered by the user and the user's behavior history (e.g., the usage history of the user terminal 20, etc.).

[0023] The user information may include, for example, information indicating the user's basic attributes such as the user's age and gender, as well as level information regarding the user's cooking skill level and the user's requests regarding ingredients. In this embodiment, the user information includes both the level information and the requests regarding ingredients. The storage unit 11 stores such user information for each user.

[0024] The level information is information indicating, for example, cooking skill, such as beginner, intermediate, or advanced. The level information may be registered by the user themselves, or may be information estimated from information input by the user (e.g., cooking history, cooking frequency, etc.). The level information may also be set for each cooking genre. For example, the level information of a user who is good at cooking Chinese food but not good at cooking Japanese food may be information associated with "advanced" for Chinese food and "beginner" for Japanese food.

[0025] The requirements regarding ingredients are, for example, information indicating the conditions, requests, etc. regarding ingredients of the person who will eat the food prepared by the user. Here, the person who will eat the food prepared by the user may include the user himself who prepares the food, or may include people other than the user (for example, the user's family, etc.). The requirements may include, for example, information regarding the food preferences, allergies, etc. of the person who will eat the food. For example, the requirements may include information indicating ingredients that the person who will eat the food does not like or is allergic to. Furthermore, the requirements regarding ingredients may include information regarding various desires, such as "I want to reduce calories," "I want to build muscle," and "I want to reduce food costs."

[0026] In addition to the above, the storage unit 11 stores multiple pieces of recipe information prepared in advance for each type of dish. The storage unit 11 also stores other information used to determine a correction policy for the recipe information (for example, seasonal ingredient information referenced in a second example of the correction policy determination process described below). Details of this information will be described later.

[0027] The acquisition unit 12 acquires a recipe creation request for a specific dish and user information related to a user viewing the recipe. The user viewing the recipe is a user who plans to cook using the recipe as a reference. The acquisition unit 12 accepts the recipe creation request for the specific dish from, for example, the user's user terminal 20. For example, the user may select a dish they want to make on a dedicated app installed on the user terminal 20, and a recipe creation request for the selected dish may be transmitted from the user terminal 20 (dedicated app) to the information processing device (acquisition unit 12).

[0028] The acquisition unit 12 may acquire user identification information (e.g., user account information) along with the recipe creation request. In this case, the acquisition unit 12 can acquire user information (in this embodiment, information including the above-mentioned level information and ingredient requirements) of the user corresponding to the identification information by referring to the storage unit 11 using the identification information as a search key. Note that the acquisition unit 12 may also acquire user information directly from the user (user terminal 20). For example, the user may select a dish they want to make on the dedicated app and input user information (e.g., level information and ingredient requirements) on the spot. In this case, the acquisition unit 12 can acquire user information from the user terminal 20 along with the recipe creation request.

[0029] The determination unit 13 determines a correction policy for recipe information prepared in advance for a specific dish corresponding to the recipe creation request acquired by the acquisition unit 12 based on the user information acquired by the acquisition unit 12 .

[0030] Recipe information includes, for example, a list of ingredients (such as types and amounts) used in a dish and explanatory information explaining each step (procedure) of the dish. The explanatory information includes, for example, at least one of text (explanatory text), images, and audio. Examples of recipe information correction include changing the expression of the text (or audio) included in the recipe information to a different expression, adding additional explanatory text, omitting (deleting) part of the recipe information (for example, a non-essential step but a clever idea for people with more time), and adding (attaching) an image (which may be a single still image, multiple still images showing each step in order, or a video) corresponding to some of the steps included in the recipe information. The correction policy is information indicating what correction should be made to the recipe information to be corrected.

[0031] An example of the process of the determination unit 13 will be described below, taking as an example a case where the predetermined dish that is the target of the recipe creation request is "mapo tofu."

[0032] First, the determination unit 13 determines recipe information corresponding to mapo tofu (a predetermined dish) as the recipe information to be corrected from among a plurality of recipe information prepared in advance for each type of dish. In the present embodiment, as described above, the storage unit 11 stores a plurality of recipe information prepared in advance for each type of dish. In this case, the determination unit 13 can acquire pre-prepared mapo tofu recipe information as the recipe information to be corrected by referring to the storage unit 11 using the dish corresponding to the recipe request information as a search key. Note that the recipe information to be corrected does not necessarily have to be selected from the recipe information pre-stored in the storage unit 11. For example, the recipe information to be corrected may be provided by the user (user terminal 20) to the information processing device 10 (acquisition unit 12) along with a recipe creation request. In this case, the determination unit 13 can determine the recipe information acquired by the acquisition unit 12 as the recipe information to be corrected.

[0033] Next, the determination unit 13 determines a correction policy for the recipe information determined as the correction target. Hereinafter, several examples of the process (correction policy determination process) for determining a correction policy by the determination unit 13 will be described.

[0034] (First example of correction policy determination process) Recipe information to be corrected is associated with the level of cooking skills required of the person viewing the recipe information (hereinafter referred to as the "target level"). For example, when recipe information to be corrected is selected from recipe information stored in the storage unit 11, the recipe information stored in the storage unit 11 is associated in advance with the target level. When recipe information to be corrected is not stored in the storage unit 11 (for example, when it is provided by the user), the target level of the recipe information may be input by the user. For example, a user can input the target level as "advanced" for recipe information that the user finds difficult.

[0035] The determination unit 13 may determine a correction policy based on a comparison result between a target level associated with the recipe information determined as a correction target and a level of the user's cooking skill indicated by level information included in the user information (hereinafter referred to as "user level"). For example, when there is a difference between the target level and the user level, the determination unit 13 may determine, as the correction policy, that the recipe information is changed to fill this difference.

[0036] For example, the determination unit 13 may determine the correction policy based on correction information prepared in advance. The correction information is, for example, stored in advance in the storage unit 11. Correction information may be prepared for each user level (for example, for beginners, for intermediate cooks, for advanced cooks, etc.). Furthermore, correction information may be prepared individually for each dish, or may be prepared for each group of multiple dishes that have the same or similar ingredients or some of the steps. In the former case, the determination unit 13 can acquire correction information for beginners that corresponds to mapo tofu by referring to the storage unit 11 using a predetermined dish (mapo tofu) and a user level (for example, beginner) as search keys.

[0037] 2 is a diagram showing an example of correction information for a certain dish. The correction information is information that associates at least the level of cooking skill (information on "target" in the example of FIG. 2), the content of the correction target (information on "content of correction target" in the example of FIG. 2), and the content of the correction (information on "content of correction" in the example of FIG. 2).

[0038] The correction information (table information) shown in FIG. 2 includes, as an example, the items "target," "type," "contents of correction target," and "contents of correction."

[0039] "Target" is information that pairs the target level (left side) of the recipe information to be corrected with the user level (right side), such as "Advanced → Beginner." The above example shows that the correction content is applied when the target level of the recipe information to be corrected is "Advanced" and the user level of the user viewing the recipe is "Beginner."

[0040] "Type" is information indicating the type (classification) of correction content. In the example of Fig. 2, "Image" indicates that a correction is to be made to add (attach) an image to recipe information, and "Expression" indicates that a correction is to be made to change the expression of text (explanatory text) included in the recipe information.

[0041] The "content of correction target" is information indicating the target to be corrected. The "content of correction" is information indicating the content of correction to be performed when the content of the correction target is included in the recipe information.

[0042] The correction information in the first line of Figure 2 indicates that if the recipe information includes a step corresponding to "fry until golden brown," a correction should be made to "attach an image of the step to the recipe information." The correction information in the second line of Figure 2 indicates that if the recipe information includes a step corresponding to "cutting," a correction should be made to "attach sequential images of the process." While these corrections involve attaching images, the correction information in the fourth line of Figure 2 indicates that if the recipe information includes a step corresponding to "add XX in desired amount and fry until the dough settles," a correction should be made to modify the expression as described in the "Correction Content."

[0043] Note that images to be added to recipe information in the correction information in the second and fourth lines of FIG. 2 may be stored in advance in the storage unit 11. Furthermore, meta information such as that shown in FIG. 3 may be associated with the images. FIG. 3 is a diagram showing an example of meta information for images (i.e., images that can be added to recipe information) that are pre-stored in the storage unit 11. As shown in FIG. 3, the meta information includes, for example, a description of the image, a target dish, a target step, and a target user level. The meta information in the first line of FIG. 3 is an example of meta information associated with an image of minced garlic. In this example, for the "minced garlic" step of the dish "mapo tofu," an "image of minced garlic" for a user with a user level of "beginner" is stored in the storage unit 11 as an image that can be added to recipe information.

[0044] 2 may include image identification information (e.g., part of the meta information) for identifying an image to be attached to recipe information. In this case, when the correction content indicates that an image should be attached to recipe information, the determination unit 13 can acquire the image to be attached from the storage unit 11 based on the image identification information.

[0045] (Second Example of Correction Policy Determination Process) The determination unit 13 may determine, as the correction policy, changing ingredients included in the recipe information based on ingredient-related requirements included in the user information. For example, consider a case where the requirements include information about the food preferences (e.g., disliked ingredients) or allergies of the person who will eat the dish prepared by the user. In this case, if the recipe information to be corrected includes an ingredient that the person who will eat the dish dislikes or is allergic to, the determination unit 13 may determine, as the correction policy, to change the ingredient to another ingredient.

[0046] In addition, if the requirements regarding ingredients include information regarding desires such as "reducing calories," "strengthening muscles," or "reducing food costs," the determination unit 13 may determine, as a correction policy, to change some of the ingredients included in the recipe information to ingredients that are suitable for the above desires.

[0047] Here, information on combinations of ingredients that can be substituted for each other and ingredients suitable for each request as described above may be stored in advance in the storage unit 11. In this case, the determination unit 13 can determine which ingredients included in the recipe information should be substituted with which ingredients by referring to the information stored in the storage unit 11 as described above.

[0048] In the second example, the determination unit 13 may determine ingredients to use in place of ingredients included in the recipe information based on information about the time period when the recipe creation request was acquired by the acquisition unit 12 and information about ingredients that are in season for each time period (hereinafter referred to as "seasonal ingredient information"). The information about the time period is, for example, information indicating the date on which the recipe creation request was received. The seasonal ingredient information is, for example, information that associates a time period with ingredients that are in season during that time period. Examples of seasonal ingredient information include information that associates the "April to June" period with the ingredient "asparagus" that is in season during that time period, and information that associates the "September to October" period with the ingredient "Pacific saury" that is in season during that time period.

[0049] For example, when recipe information includes "ingredient A," an ingredient that should be changed to another ingredient based on the above requirements, the determination unit 13 extracts "ingredient B," which is in season on the date of receipt of the recipe creation request, based on the date of receipt and the seasonal ingredient information. Then, when ingredient A and ingredient B are interchangeable, the determination unit 13 determines, as a correction policy, to change ingredient A included in the recipe information to ingredient B. In this way, the determination unit 13 may determine, as a correction policy, to preferentially substitute ingredients that are in season.

[0050] The output unit 14 outputs input information for instructing the generation AI model 31 (generation AI server 30) to correct the recipe information based on the correction policy determined by the determination unit 13. In the present embodiment, as an example, the output unit 14 outputs (generates) the entire prompt as input information. The generation AI model 31 inputs the prompt output from the output unit 14, thereby generating and outputting recipe information corrected (customized) for the user. The corrected recipe information may be composed of text data only, or may include data in a format other than text data, such as diagrams and images.

[0051] FIG. 4 is a diagram illustrating an example of a prompt output by the output unit 14. In the example of FIG. 4, the prompt includes user information, recipe information to be corrected, and generation conditions, as well as a task (instruction) such as "Generate recipe information by correcting the recipe information to be corrected based on the user information and the generation conditions." Here, the "recipe information to be corrected" in the prompt may describe the content of the recipe information to be corrected determined by the determination unit 13. Furthermore, the "generation conditions" in the prompt may describe the content of the correction policy determined by the correction policy determination process of the determination unit 13, as described above. If the correction content is to modify an expression, for example, an instruction such as "Please change the expression 'X' contained in the recipe information to be corrected to the expression 'Y'" may be described as part of the generation conditions. If the correction content is to add an image, for example, an instruction such as "Please insert image 'Y' as an explanatory image indicating step 'X' of the recipe information to be corrected" may be described as part of the generation conditions, along with image data to be added. Furthermore, the output unit 14 may determine, for example, in what description form to include the correction policy determined by the determination unit 13 in the prompt, based on description rules predetermined for each correction policy.

[0052] Next, an example of the operation (information processing method) of the information processing device 10 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the operation of the information processing device 10.

[0053] In step S1, the acquisition unit 12 acquires a recipe creation request for a predetermined dish (e.g., mapo tofu) and user information. As an example, the acquisition unit 12 accepts a recipe creation request from the user terminal 20 of a user who requires recipe information, and acquires the user information of the user from the storage unit 11.

[0054] In steps S2 to S6, the determination unit 13 determines a correction policy for the recipe information prepared in advance for a predetermined dish based on the user information acquired in step S1.

[0055] In step S2, the determination unit 13 determines recipe information to be corrected. As an example, the determination unit 13 determines recipe information corresponding to mapo tofu (a predetermined dish) from among a plurality of pieces of recipe information (a plurality of pieces of recipe information prepared in advance for each type of dish) pre-stored in the storage unit 11 as the recipe information to be corrected.

[0056] Steps S3 and S4 correspond to the first example of the correction policy determination process described above. In step S3, the determination unit 13 determines whether there is a difference between the user level and the target level of the recipe information to be corrected. If it is determined that there is a difference (step S3: YES), the determination unit 13 determines a correction policy based on the correction information (see FIG. 2) described above (step S4). In step S4, the determination unit 13 may execute the process described in the first example of the correction policy determination process described above. On the other hand, if it is not determined that there is a difference (step S3: NO), the process of step S4 is skipped.

[0057] Steps S5 and S6 correspond to the second example of the correction policy determination process described above.

[0058] In step S5, the determination unit 13 determines whether the user information includes a requirement related to ingredients. If it is determined that the requirement is included (step S5: YES), the determination unit 13 determines that the correction policy is to change the ingredients included in the recipe information based on the requirement (step S6). In step S6, the determination unit 13 may execute the process described in the second example of the correction policy determination process. On the other hand, if it is determined that the requirement is not included (step S5: NO), the process of step S6 is skipped.

[0059] In step S7, the output unit 14 generates and outputs a prompt (see FIG. 4 ) based on the correction policy determined by the determination unit 13. The output prompt is input to the generation AI model 31, and the generation AI model 31 outputs recipe information corrected for the user. As an example, the output unit 14 acquires the recipe information output from the generation AI model 31 and transmits it to the user terminal 20. As a result, the user can receive recipe information appropriately customized for the user for a specific dish. For example, the user can receive recipe information that matches their cooking skill (user level) or recipe information in which ingredients have been appropriately changed in accordance with their ingredient requirements (food allergies, etc.). Specific examples of corrections made to recipe information when the user is a beginner include adding (inserting) an image showing the amount of chili bean paste (e.g., an image of chili bean paste on a tablespoon) during the explanation of the step of adding chili bean paste included in the cooking steps, or changing the expression "your desired amount" to a more specific expression such as "your desired amount in the range of 1 to 1.5 tablespoons."

[0060] Note that if the determination results of both steps S3 and S5 are "NO" (i.e., if the determination unit 13 determines that correction of recipe information is not necessary), the process of step S7 does not need to be executed. In this case, it can be determined that the recipe information to be corrected (existing recipe information) is already suitable for the user, and therefore the output unit 14 may provide (transmit) the existing recipe information to the user (user terminal 20).

[0061] In the information processing device 10 and information processing method described above, in response to receiving a recipe creation request for a specific dish, a correction policy for recipe information prepared in advance for the specific dish is determined based on user information of the user viewing the recipe (the person requesting recipe creation). Subsequently, a prompt (input information) is output to instruct the generation AI model 31 to correct the recipe information based on the correction policy thus determined. As a result, the generation AI model 31 can generate recipe information that is appropriately customized (corrected) for the user. Therefore, the information processing device 10 and its information processing method can appropriately and easily generate recipe information for a specific dish that is tailored to the user.

[0062] The determination unit 13 may determine, as the recipe information to be corrected, recipe information corresponding to a predetermined dish from among a plurality of recipe information prepared in advance for each type of dish. According to the above configuration, it is possible to easily and appropriately determine the recipe information to be corrected.

[0063] As described in the first example of the correction policy determination process, the user information may include level information (user level) regarding the user's cooking skill level. The determination unit 13 may then determine the correction policy based on a comparison result between the target level associated with the recipe information and the user level. In the above embodiment, the determination unit 13 determines that the recipe information needs to be corrected when there is a difference between the target level and the user level. According to the above configuration, when the target level of the recipe information to be corrected does not match the user level, the generation AI model 31 can correct the recipe information so that the content matches the user level. As a result, it is possible to obtain recipe information that is appropriately corrected for the user. Note that in the above embodiment, using FIG. 2 and the like, a case was described in which, when the target level (advanced) of the recipe information to be corrected is higher than the user level (beginner), an explanatory image is added, the expression is changed, or other content that is difficult for the user included in the recipe information is modified. However, correction based on the level difference is not limited to the above example. For example, if the target level (beginner) of the recipe information to be corrected is lower than the user level (advanced), the determination unit 13 may determine as a correction policy to delete explanations for beginners included in the recipe information (unnecessary information that is bothersome to advanced users).

[0064] The determination unit 13 may determine a correction policy based on correction information (see FIG. 2 ) that associates the user's cooking skill level, the content of the correction target, and the content of the correction. According to the above configuration, a correction policy can be easily determined based on correction information that defines general rules for correction in advance. In the above embodiment, the determination unit 13 determined a correction policy based on correction information prepared in advance for each combination of target level and user level (e.g., as shown in FIG. 2 , a combination of target level "Advanced" and user level "Beginner" such as "Advanced → Beginner"). According to this configuration, it is possible to appropriately correct recipe information according to the combination of target level and user level. However, the search key ("target") of the correction information may simply be information indicating the user level "Beginner." In other words, the correction information may be prepared as information that is uniformly applied to users belonging to a certain user level (e.g., "Beginner") regardless of the target level of the recipe information to be corrected.

[0065] As described in the second example of the correction policy determination process, the user information may include a user's request for ingredients. The determination unit 13 may then determine, as a correction policy, changing the ingredients included in the recipe information based on the request. According to the above configuration, if the recipe information to be corrected includes ingredients that are unsuitable for the user (e.g., ingredients that the user dislikes or is allergic to), the recipe information can be corrected by the generation AI model 31 so that the ingredients are changed to other ingredients. As a result, it is possible to obtain recipe information that is appropriately corrected for the user.

[0066] The determination unit 13 may determine ingredients to use in place of ingredients included in the recipe information based on information about the time when the recipe creation request was acquired and information about seasonal ingredients for each period. That is, as described in the second example of the correction policy determination process, the determination unit 13 may determine, as the correction policy, that seasonal ingredients be used preferentially. With the above configuration, when there is an ingredient that should be substituted with another ingredient based on the requirements, it is possible to have the generation AI model 31 correct the recipe information so that a more appropriate ingredient (i.e., a seasonal ingredient) is used.

[0067] [Note] The present disclosure includes the following aspects.

[0068] [1] An information processing device comprising: an acquisition unit that acquires a recipe creation request for a specified dish and user information regarding a user viewing the recipe; a decision unit that determines a correction policy for recipe information prepared in advance for the specified dish based on the user information; and an output unit that outputs input information to instruct a generative AI model to correct the recipe information based on the correction policy.

[0069] [2] The information processing device of [1], wherein the determination unit determines recipe information corresponding to the specified dish from among a plurality of recipe information prepared in advance for each type of dish as recipe information to be corrected.

[0070] [3] An information processing device according to [1] or [2], wherein the user information includes level information relating to the level of the user's cooking skills, and the determination unit determines the correction policy based on a comparison result between the level associated with the recipe information and the level of the user's cooking skills indicated by the level information.

[0071] [4] An information processing device according to any one of [1] to [3], wherein the user information includes level information relating to the level of the user's cooking skill, and the determination unit determines the correction policy based on correction information that correlates the user's level of cooking skill, the content to be corrected, and the content of the correction.

[0072] [5] The information processing device of any of [1] to [4], wherein the user information includes requests from the user regarding ingredients, and the determination unit determines, as the correction policy, to change the ingredients included in the recipe information based on the requests.

[0073] [6] The information processing device of [5], wherein the determination unit determines ingredients to use in place of ingredients included in the recipe information based on information regarding the time when the recipe creation request was acquired and information regarding ingredients that are in season for each period.

[0074] [7] An information processing method including the steps of: acquiring a recipe creation request for a specified dish and user information regarding a user viewing the recipe; determining a correction policy for recipe information prepared in advance for the specified dish based on the user information; and outputting input information for instructing a generative AI model to correct the recipe information based on the correction policy.

[0075] [Definition of Terms, etc.] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., using wires, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or the multiple devices.

[0076] Functions include, but are not limited to, judging, determining, calculating, computing, processing, deriving, investigating, searching, verifying, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, expecting, anticipating, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning.

[0077] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs the information processing method of the present disclosure. Fig. 6 is a diagram illustrating an example of the hardware configuration of the information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0078] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in Fig. 6, or may be configured to exclude some of the apparatuses.

[0079] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0080] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0081] The processor 1001 also reads programs (program code), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, each functional unit of the information processing device 10 (e.g., the determination unit 13, etc.) may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0082] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing an information processing method according to an embodiment of the present disclosure.

[0083] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0084] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0085] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0086] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0087] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0088] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0089] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0090] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0091] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0092] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0093] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0094] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0095] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0096] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0097] The names used for the parameters described above are not intended to be limiting in any way. Furthermore, the mathematical formulas and the like that use these parameters may differ from those explicitly disclosed in this disclosure. The various information elements may be identified by any suitable names, and the various names assigned to these various information elements are not intended to be limiting in any way.

[0098] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0099] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0100] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0101] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0102] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0103] 10...information processing device, 11...memory unit, 12...acquisition unit, 13...determination unit, 14...output unit, 20...user terminal, 30...generation AI server, 31...generation AI model

Claims

1. An information processing device comprising: an acquisition unit that acquires a recipe creation request for a specified dish and user information regarding a user viewing the recipe; a determination unit that determines a correction policy for recipe information prepared in advance for the specified dish based on the user information; and an output unit that outputs input information to instruct a generative AI model to correct the recipe information based on the correction policy.

2. The information processing device according to claim 1, wherein the determination unit determines recipe information corresponding to the specified dish from among a plurality of recipe information prepared in advance for each type of dish as the recipe information to be corrected.

3. The information processing device described in claim 1, wherein the user information includes level information regarding the level of the user's cooking skills, and the determination unit determines the correction policy based on a comparison result between the level associated with the recipe information and the level of the user's cooking skills indicated by the level information.

4. The information processing device described in claim 1, wherein the user information includes level information regarding the level of the user's cooking skill, and the determination unit determines the correction policy based on correction information that correlates the user's cooking skill level, the content to be corrected, and the content of the correction.

5. The information processing device of claim 1, wherein the user information includes requests from the user regarding ingredients, and the determination unit determines, as the correction policy, to change the ingredients included in the recipe information based on the requests.

6. An information processing device as described in claim 5, wherein the determination unit determines ingredients to be used in place of ingredients included in the recipe information based further on information regarding the time when the recipe creation request was acquired and information regarding ingredients that are in season for each period.

7. An information processing method including the steps of: acquiring a recipe creation request for a specified dish and user information regarding a user viewing the recipe; determining a correction policy for pre-prepared recipe information for the specified dish based on the user information; and outputting input information for instructing a generative AI model to correct the recipe information based on the correction policy.