Method for aiding a selection of a cooking recipe

Abstract

The invention relates to a method (100) for aiding a selection of at least one cooking recipe from a complete list (Ltot) of recipes, which method comprises: - a first receiving step (E1) during which at least one guest profile (P1, PN) is received; - a step (E2) of determining a restricted list (Lres) of recipes from the complete list (Ltot) of recipes; - a step (E3) of transmitting a generative text query, to a generative language model (LLM), for generating a recommended list (Lrec) of recipes chosen from those of the restricted list (Lres); - a second receiving step (E4) during which the recommended list (Lrec) is received, in response to the generative text query; - a step (E5) of communicating the recommended list; and - a step (E6) of selecting a recipe from the recommended list (Lrec).

Description

[0001] DESCRIPTION

[0002] TITLE: Method for assisting in the selection of a cooking recipe

[0003] Technical Field

[0004] The invention relates to the field of preparing a culinary dish and more particularly to a method of assisting in the selection of at least one cooking recipe from a complete list of recipes.

[0005] Prior art

[0006] When a cook is preparing a meal, they often encounter difficulties finding recipe ideas that will appeal to several people. Indeed, the chosen recipe must take into account various factors such as allergies, intolerances, dislikes, and individual culinary preferences. Therefore, finding a recipe that pleases everyone while also meeting other criteria, such as cost, time, nutritional value, or seasonality, can prove to be a significant challenge.

[0007] There are applications that, using a generative language model, offer a list of recipes adapted to a list of selected ingredients and that take into account various parameters indicated by the user.

[0008] The drawback of this type of application is that it requires a long response time and a large textual query size, also called a "prompt," meaning a significant number of "tokens" for the generative language model. Furthermore, the generative language model sometimes fails to take into account all the parameters specified by the user.

[0009] Therefore, there is a need for a reliable, fast, and limited number of tokens required by the generative language model to assist in the selection of a cooking recipe.

[0010] Description of the invention

[0011] One embodiment relates to assistance in selecting at least one recipe from a complete list of recipes, said process being implemented by a system comprising:

[0012] A first stage of reception, of at least one guest profile including a unique guest profile identifier, and at least one restriction data point, and at least one preference data point;

[0013] A determination step in which the system determines a restricted list of recipes from the complete list of recipes based on at least one restriction data; A transmission step in which the system transmits to at least one generative language model, at least one textual request to generate a recommended list of recipes chosen from the recipes in the restricted list of recipes, said textual generation request including the restricted list of recipes, and at least one preference data from at least one guest profile;

[0014] A second stage of receiving, in response to the said textual request for generation, the recommended list of recipes;

[0015] A communication step via the recommended recipe list system;

[0016] A step whereby a user selects at least one recipe from the recommended list of recipes for implementation.

[0017] The method according to the invention aims to help a user select at least one recipe, taking into account the dietary restrictions and preferences of each guest. In this way, the user can quickly and easily determine a recipe for preparing a dish, or a series of dishes forming a complete menu, that will please all the guests.

[0018] A complete recipe list is defined as a list containing multiple recipes without any filtering. Each recipe details a list of ingredients, at least one recipe parameter, and recipe instructions for preparing a dish corresponding to that recipe.

[0019] A recipe parameter is a setting that applies to the recipe. Each recipe parameter is unique to that recipe. A recipe parameter can be defined for preparing a dish for one person, or for the entire recipe.

[0020] The process is implemented by a system that includes at least one human-machine interface and a bidirectional communication module with the generative language model. The generative language model can be integrated into the system or implemented on a remote server.

[0021] A generative language model is a large language model (LLM), specifically a pre-trained generative transformer model (GPT). In other words, a generative language model is an artificial intelligence model capable of generating output text from a text query. Generative language models are typically large language models (LLMs), especially pre-trained generative transformer models (GPTs), such as GPT-4, LaMDA, LLaMA, BLOOM, etc.

[0022] In the first step, the user enters at least one guest profile via the user interface. The guest profile corresponds to a person to whom the dish prepared from the recipe will be served. The guest profile lists characteristics, or culinary preferences, associated with this person. Therefore, there are as many guest profiles as there are people who will be eating the dish. The guest profile includes at least one restriction, corresponding to the person's dislikes, and at least one preference, corresponding to the person's tastes.

[0023] At least one restriction data point and at least one preference data point are received by the system.

[0024] Based on the information above, the system determines the shortlist of recipes. In other words, the system processes the entire recipe list to remove those recipes incompatible with at least one restriction criterion. The shortlist therefore takes into account, with certainty because it is generated by a deterministic algorithm, at least one restriction criterion. The shortlist of recipes comprises recipes selected from the entire recipe list.

[0025] The system then transmits this restricted list, along with at least one preference data from at least one guest profile, to the generative language model using the generation text query during the transmission step.

[0026] The textual query, generally called a "prompt," corresponds to an input text for the generative language model, defining what is being asked of it. The textual query is in natural language, that is, the "normal" language spoken by a human being, and not a structured computer language. Natural language can be written without prior training, unlike all computer languages.

[0027] Regarding the structure of the text query, it is sufficient that the generative language model be able to understand that we want to obtain a recommended list of recipes from the recipes in the restricted list of recipes, taking into account at least one preference data from at least one guest profile.

[0028] More specifically, the text query includes a sentence defining that a desired action of the generative language model is the generation of a recommended list of recipes chosen from the recipes in the restricted list of recipes, the selection having to take into account at least one preference data from at least one guest profile.

[0029] During the second reception stage, the system receives the response to the textual generation request from the generative language model, consisting of the recommended list of recipes. The system then communicates this list to the user via the human-machine interface, for example, through a display screen.

[0030] Finally, the user selects one of the recipes from the recommended list of recipes so that they can review it in preparation for its implementation.

[0031] Thus, the process according to the invention makes it possible to select a subset of recipes from the complete list of recipes in order to improve a response time of the generative language model, while ensuring, by a deterministic algorithm, that all the restriction data have been taken into account.

[0032] Furthermore, creating a restricted list of recipes allows the generative language model to process only a portion of the complete recipe list. This is particularly advantageous because it limits the size of the text query, i.e., the "prompt," and therefore the number of "tokens," i.e., units of information used by the LLM, and thus the time / cost required to obtain a response to the text query.

[0033] Finally, the process also helps to limit the risk of hallucination of the generative language model so that the recommended list corresponds to the context of realizing the recipe specified by the user.

[0034] The subject of this presentation may also exhibit one or more of the following characteristics, taken alone or in combination.

[0035] In some embodiments, the first step also includes receiving at least one selection criterion for a recipe parameter, with the system determining the shortlist of recipes also based on at least one selection criterion.

[0036] The selection criterion for a recipe parameter is a criterion that defines the recipe parameter. In other words, the user wants the recipe parameter to meet the selection criterion. There is as many selection criteria as there are recipe parameters considered by the user.

[0037] In the first step, the user also specifies at least one selection criterion for the recipe parameter that is passed to the system. The system can then, using its deterministic algorithm, select recipes from the restricted list based on this selection criterion; that is, the recipes from the complete list whose recipe parameter meets the selection criterion.

[0038] The context in which the recipe is created is therefore clearly defined and taken into account. The limited list of recipes considers more parameters, thus improving the response time and reliability of the generative language model.

[0039] The selection criterion can be a minimum value, a maximum value, or a range.

[0040] In some embodiments, the first step also includes receiving at least one criterion for choosing a menu parameter, the system determining the shortlist of recipes also based on at least one menu criterion.

[0041] The selection criterion for the menu parameter is a criterion that defines the menu parameter the user wishes to implement. There is as many selection criteria as there are menu parameters considered by the user.

[0042] A menu parameter is a setting that applies to all the dishes in the menu as a whole. Menu parameters can be defined for the creation of the menu. For example, a menu parameter can be chosen from: the total number of calories in the menu, or a general theme for the menu.

[0043] The menu theme could be a menu where each recipe includes an ingredient from the sea, from a particular country, or where each recipe can be easily transported for a picnic.

[0044] In some embodiments, at least one recipe parameter is chosen from: an estimated time to prepare the recipe, an estimated budget for the recipe, an estimated number of calories in the recipe, a recipe type, or the seasonality of the recipe ingredients.

[0045] The type of recipe corresponds to a category of function of the dish obtained when preparing the recipe within the meal, such as an appetizer, a main course, a side dish, a dessert, an amuse-bouche...

[0046] A selection criterion can be applied to each recipe parameter. Examples are given in the table below:

[0047] Table 1]

[0048] In some embodiments, the restricted list of recipes includes a number of recipe restrictions.

[0049] In other words, after applying the criteria, including restriction data, the number of recipes on the restricted list is limited to the number of restrictions.

[0050] In some embodiments, the number of restrictions is specified by the user.

[0051] In some embodiments, the number of restrictions is fixed and predetermined.

[0052] In some embodiments, the number of restrictions is between 50 and 1000 recipes, preferably between 100 and 500 recipes, for example 150 recipes.

[0053] In some embodiments, the restricted list of recipes includes the number of restricted recipes, said recipes being chosen from among the most popular recipes.

[0054] In some embodiments, at least one restriction data point is chosen from: a type of diet, a food, a food group, an allergy.

[0055] The restriction data lists the person's dislikes, intolerances, or allergies.

[0056] Thus, the restriction data allows us to take into account characteristics that the recipe selected by the user must not have.

[0057] In some embodiments, at least one preference datum includes at least one preferred recipe. The preference datum corresponds to the person's tastes. The preference datum corresponds to at least, and preferably a plurality, of recipes that appeal to that person. The preference datum can therefore be a list of recipes that the person likes.

[0058] The generative language model must then process all of this preference data to determine the recommended list of recipes.

[0059] In some embodiments, the at least one text-based generation query further includes a sentence defining a desired action of the generative language model as the generation of an explanatory text for each recipe in the recommended recipe list, explaining why that recipe was chosen based on at least one preference data point of at least one guest profile. The text-based query may also specify that, for each recipe in the recommended recipe list, the generative language model should indicate in a text why that recipe was selected based on at least one preference data point.

[0060] In cases where multiple guest profiles have been entered, the explanatory text indicates why this recipe was selected with regard to each preference data of each profile.

[0061] The explanatory text thus allows the user to understand the choice that has been made.

[0062] In some embodiments, at least one textual generation query further includes a sentence defining that the response to the textual generation query must be in a user-structured file in a predefined markup language.

[0063] The file is said to be "structured" in that it is formatted according to an expected model, i.e. an "empty" or skeleton file.

[0064] In some embodiments, the predefined markup language is JavaScript Object Notation.

[0065] JavaScript Object Notation (JSON) is a text-based data format derived from the object notation of the JavaScript language, but other languages, such as those based on XML or HTML, can also be used. By definition, any file in a markup language like JSON is structured. In some embodiments, at least one text-based generation query also includes a sentence defining that a desired action of the generative language model is to suggest a music and / or beverage accompaniment for each recipe in the recommended recipe list.

[0066] Thus, the user can accompany the served dish with a drink or music.

[0067] In some embodiments, the system is chosen from: a mobile terminal, a cooking appliance, a set comprising a mobile terminal and a cooking appliance.

[0068] In the overall system, some steps can be performed by the mobile terminal while others are performed by the cooking appliance. For example, the first reception step, the determination step, and the transmission step can be performed by the mobile terminal, while the second reception step, the communication step, and the selection step are performed by the cooking appliance.

[0069] In some embodiments, the process includes an implementation step in which the system is configured to assist the user in implementing the selected recipe.

[0070] The assistance provided during the implementation stage may be programming a cooking appliance or a step-by-step guide to the recipe.

[0071] In some embodiments, the process includes a recording step in which the recipe selected from the recommended list of recipes is recorded and then passed to at least one generative language model during a new generation text query.

[0072] Thus, a history of the selected recipes is created and transmitted to the generative language model in order to improve the selection of the recommended list in a subsequent iteration.

[0073] In some embodiments, at least one textual generation query is of the form:

[0074] “P(Pref1,..., PrefN, Lres)

[0075] Lres: DOC

[0076] Prefl: DOCPrefl

[0077] PrefN: DOCPrefN

[0078] Where Prefl, PrefN is a reference to at least one preference data from guest profile 1 to N; Lres is a reference to the shortlist of recipes; P(...) the generation text query; DOC is a text of the recipes from the shortlist of recipes in a text file; DOCPrefl, DOCPrefN is a text of at least one preference data from guest profile 1 to N.

[0079] Brief description of the drawings

[0080] The invention will be better understood, thanks to the following description, which relates to one or more embodiments according to the present invention, given by way of non-limiting examples and explained with reference to the accompanying schematic drawings, in which: [FIG. 1] is a sequence diagram of the process according to the invention;

[0081] [FIG. 2] is a representation of the method according to the invention implemented by a mobile terminal. [FIG. 3] is a representation of the method according to the invention implemented by a cooking appliance.

[0082] [FIG. 4] is a representation of the method according to the invention implemented by an assembly comprising a mobile terminal and a cooking appliance. Description of embodiments

[0083] Only the elements necessary for understanding the invention have been shown. To facilitate reading the drawings, the same elements bear the same reference numbers from one figure to another.

[0084] The present invention relates to a method 100 for assisting in the selection of at least one cooking recipe from a complete list of recipes Ltot, as shown in Figures 1 to 4. The method 100 according to the invention aims to help a user Usr / A select at least one cooking recipe by taking into account restrictions Res1, ResN and culinary preferences Prefl, PrefN of each guest 1, N. In this way, the user Usr / A of the method can quickly and easily determine a cooking recipe that will prepare a dish pleasing to all the guests 1, N.

[0085] Process 100 is implemented by a Syst system that includes at least one human-machine interface and a bidirectional communication module with the LLM generative language model. The generative language model can be integrated into the Syst system or implemented on a remote server.

[0086] The Syst system is chosen from a mobile terminal, as illustrated in Fig. 2, a cooking appliance, as illustrated in Fig. 3, or a combination of a mobile terminal and a cooking appliance, as illustrated in Fig. 4.

[0087] The generative language model (LLM) is a large language model, specifically a pre-trained generative transformer (GPT) model. In other words, the LLM is an artificial intelligence model capable of generating output text from a text query. Typically, the LLM is a large language model, specifically a pre-trained generative transformer (GPT) model, such as GPT-4, LaMDA, LLaMA, BLOOM, etc.

[0088] During the first acceptance step E1 of the process, the user Usr / A enters, via the human-machine interface, at least one guest profile P1, PN. In the figures illustrated, the guest profiles P1, PN are numbered from 1 to N. Alternatively, each guest 1, N enters their own guest profile P1, PN.

[0089] Each guest profile P1, PN corresponds to a person 1, N to whom the dish prepared from the recipe will be served. The guest profile P1, PN therefore includes a unique identifier. The guest profile P1, PN lists characteristics, or culinary tastes, associated with this person. There are thus as many guest profiles P1, PN as there are people 1, N who will be eating the dish. The guest profile P1, PN includes at least one restriction data point, Res1, ResN, and at least one preference data point, Prefl, PrefN. More specifically, the restriction data point Res1, ResN lists the dislikes, intolerances, or allergies of person 1, N. The at least one restriction data point Res1, ResN can be chosen from: a type of diet, a food, a food group, or an allergy.

[0090] Thus the restriction data Res1, ResN allows us to take into account characteristics that the recipe which will be selected by the user Usr / A must not have.

[0091] The preference data Prefl, PrefN corresponds to the tastes of person 1, N. The preference data Prefl, PrefN corresponds to at least, and preferably a plurality, of recipes that appeal to said person. The preference data Prefl, PrefN can therefore be a list of recipes that the person likes.

[0092] At least one restriction data Res1, ResN, and at least one preference data Prefl, PrefN are received by the Syst system.

[0093] In some embodiments, the user Usr / A also specifies at least one CS selection criterion of a recipe parameter which is transmitted to the Syst system.

[0094] A recipe parameter is a setting that applies to the recipe as a whole. Each recipe has its own unique parameter. A recipe parameter can be defined for preparing a dish for one person, or for the entire recipe.

[0095] At least one recipe parameter is chosen from, for example: an estimated preparation time, an estimated budget, an estimated number of calories, or a recipe type. The recipe type corresponds to a category or function of the dish obtained when the recipe is prepared within a meal, such as an appetizer, a main course, a side dish, a dessert, or an amuse-bouche.

[0096] The CS selection criterion for the recipe parameter is a criterion that defines the recipe parameter. In other words, the user Usr / A wants the chosen recipe parameter to meet the CS selection criterion. There is as many CS selection criteria as there are recipe parameters considered by the user Usr / A.

[0097] The CS selection criterion can be a minimum, maximum, or range value of the recipe parameter.

[0098] For each recipe parameter, a CS selection criterion can be applied. Examples are given in the table below:

[0099] Table 2] In some embodiments, the user Usr / A also specifies at least one criterion for choosing a menu parameter,

[0100] The menu parameter selection criterion defines the menu parameter the user wishes to implement. There are as many selection criteria as there are menu parameters considered by the user Usr / A.

[0101] A menu parameter is a setting that applies to all the dishes in the menu as a whole. Menu parameters can be defined for the creation of the menu. For example, a menu parameter can be chosen from: the total number of calories in the menu, or a general theme for the menu.

[0102] The menu theme could be a menu where each recipe includes an ingredient from the sea, from a particular country, or where each recipe can be easily transported for a picnic.

[0103] The process 100 then includes a determination step E2 in which the Syst system determines a restricted list Lres of recipes based on a complete list Ltot of recipes, and at least one restriction data point Res1, ResN. According to embodiments, the determination step E2 can also determine the restricted list Lres of recipes based also on at least one selection criterion CS and / or at least one menu criterion.

[0104] The complete list (Ltot) of recipes is defined as a list comprising a plurality of recipes on which no filtering has been performed. Each recipe details a list of ingredients, at least one recipe parameter, and recipe instructions for preparing a dish corresponding to that recipe.

[0105] The Syst system processes the complete list Ltot of recipes to remove from the complete list Ltot those recipes incompatible with at least one restriction data point Res1, ResN. The Syst system can also remove from the complete list Ltot recipes that do not meet the selection criterion CS and / or the choice criterion.

[0106] The restricted list Lres therefore takes into account, with certainty because it is generated by a deterministic algorithm, at least one restriction parameter Res1, ResN, and optionally the selection criterion CS and / or the choice criterion. The restricted list Lres of recipes includes recipes selected from the complete list Ltot of recipes.

[0107] In some embodiments, the restricted list of recipes includes a number of recipe restrictions.

[0108] In other words, after applying the criteria associated with at least one restriction data Res1, ResN, and selection criteria CS and / or choice criteria, the number of recipes in the restricted list Lres is limited to the number of restrictions.

[0109] In some embodiments, the number of restrictions is specified by the user Usr / A, for example during the first acceptance step. In other embodiments, the number of restrictions is fixed and predetermined.

[0110] In some embodiments, the number of restrictions is between 50 and 1000 recipes, preferably between 100 and 500 recipes, for example 150 recipes.

[0111] In some embodiments, the restricted list of recipes includes the number of restricted recipes, said recipes being chosen from among the most popular recipes.

[0112] A context for the creation of the recipe is therefore specified and taken into account in a certain way through the restricted list of recipes.

[0113] The process 100 then includes a transmission step E3 in which the Syst system transmits to at least one generative language model LLM, at least one textual request for generating a recommended list Lrec of recipes chosen from the recipes in the restricted list Lres of recipes, said textual generation request comprising the restricted list Lres of recipes, and at least one preference data Prefl, Pref N of at least one guest profile P1, PN.

[0114] The textual query, generally called a "prompt," corresponds to an input text for the generative language model, defining what is being asked of it. The textual query is in natural language, that is, the "normal" language spoken by a human being, and not a structured computer language. Natural language can be written without prior training, unlike all computer languages.

[0115] Regarding the structure of the text query, it is sufficient that the generative language model be able to understand that we want to obtain a recommended list Lrec of recipes from the recipes in the restricted list Lres of recipes taking into account at least one preference data Prefl, PrefN of at least one guest profile P1, PN.

[0116] More specifically, the text query includes a sentence defining that a desired action of the LLM generative language model is the generation of a recommended list Lrec of recipes chosen from the recipes in the restricted list Lres of recipes, the selection having to take into account at least one preference data Prefl, PrefN of at least one guest profile P1, PN.

[0117] The textual generation query is, for example, of the form:

[0118] “P(Pref1,..., PrefN, Lres)

[0119] Lres: DOC

[0120] Prefl: DOCPrefl

[0121] PrefN: DOCPrefN »

[0122] Where Prefl, PrefN is a reference to at least one preference data from guest profile 1 to N; Lres is a reference to the shortlist of recipes; P(...) the generation text query; DOC is a text of the recipes from the shortlist of recipes in a text file; DOCPrefl, DOCPrefN is a text of at least one preference data from guest profile 1 to N.

[0123] In some embodiments, the at least one generation text query further includes a sentence defining that a desired action of the LLM generative language model is to write an explanatory text, for each recipe in the recommended list Lrec of recipes, of the choice of said recipe in relation to at least one preference data Prefl, PrefN of at least one guest profile P1, PN.

[0124] The explanatory text tells the user Usr / A why this recipe was selected with regard to at least one preference data Prefl, PrefN of at least one guest profile P1, PN.

[0125] The explanatory text thus allows the user Usr / A to understand the choice of recipes from the recommended list Lrec that was made.

[0126] In some embodiments, at least one generation text query further includes a sentence defining that a desired action of the LLM generative language model is to suggest a music and / or drink accompaniment for each recipe in the Lrec recommended recipe list.

[0127] Thus, the user can accompany the served dish with a drink or music.

[0128] In some embodiments, at least one textual generation query further includes a sentence defining that the response to the textual generation query must be in a user-structured file in a predefined markup language.

[0129] The file is said to be "structured" in that it is formatted according to an expected model, i.e. an "empty" or skeleton file.

[0130] In some embodiments, the predefined markup language is JavaScript Object Notation.

[0131] JavaScript Object Notation (JSON) is a textual data format derived from the object notation of the JavaScript language, but other languages, such as those based on XML or HTML, can also be used. By definition, any file in a markup language like JSON is structured. Thus, assuming the expected Lrec recommended list is in a file called recommended_list.txt, that is, a user-structured file in a predefined markup language, we can, for example, use the following textual query, with comments and explanations that are not part of the query in bold:

[0132] "Can you recommend a list of five recipes from the Restricted Recipe List for all Guests to eat together, and explain why the recommendation will appeal to the different Guests, taking into account each Guest's preferences, with Guest P1 having these Preference Data (l), ..., and Guest PN having these Preference Data (N)? The response must be in the form of a JSON file containing only a recipe reference, its title, and the reason for the selection. [Phrase P defining the desired action] Restricted Recipe List: Restricted_List.txt [to be embedded]"

[0133] Preference data: DOCPref1.txt [to be embedded]

[0134] Preference data: DOCPrefN.txt [to be embedded] »

[0135] Of course, the number of recipes in the recommended list Lrec of recipes may be different, or defined by the user Usr / A.

[0136] Process 100 then includes a second reception step E4, in which the Syst system receives from the LLM generative language model the response to the textual generation request consisting of the recommended list of recipes. Then, the Syst system communicates this list to the user Usr / A via the human-machine interface, for example, a display screen, during the communication step E5.

[0137] Finally, the user Usr / A selects one of the recipes from the recommended list Lrec of recipes so that they can review it for implementation during a selection step E6.

[0138] Optionally, process 100 includes a recording step in which the selected recipe is recorded and then passed to at least one LLM generative language model during a subsequent textual generation query. This creates a history of selected recipes, thus improving the selection of the recommended Lrec list in a later iteration.

[0139] Optionally, process 100 includes an implementation step in which the Syst system is configured to assist the user Usr / A in implementing the selected recipe.

[0140] The assistance provided during the implementation stage may be programming a cooking appliance or a step-by-step guide to the recipe.

[0141] The method 100 according to the invention allows a subset of recipes to be selected from the complete list Ltot of recipes in order to improve the response time of the generative language model LLM, while ensuring, by a deterministic algorithm, that all the restriction data Res1, ResN have been taken into account.

[0142] Furthermore, creating the restricted list Lres of recipes allows the generative language model LLM to process only a portion of the complete list Ltot of recipes. This is particularly advantageous because it limits the size of the textual query, i.e., the "prompt," and therefore the number of "tokens," i.e., units of information used by the generative language model LLM, and thus the time / cost required to obtain a response to the textual query. Finally, this process also reduces the risk of the generative language model becoming misled, ensuring that the recommended list Lrec corresponds to the context in which the recipe specified by the user Usr / A is executed.

[0143] Figure 2 illustrates method 100 according to the invention implemented by a mobile application. The user Usr / A enters the guest profiles 1, N in the mobile application, specifically in a front-end application. The determination step E2 is then performed by a back-end application of the mobile application. The back-end application may be linked to an integrated or remote database, designated in the figure as the "Database".

[0144] Figure 3 illustrates method 100 according to the invention implemented by a Product IHM cooking appliance. The user Usr / A enters the guest profiles 1, N into the cooking appliance, specifically via a human-machine interface, and then the determination step E2 is performed by an integrated back-end application of the cooking appliance. The integrated back-end application can be linked to a database that is either embedded in the cooking appliance or hosted on an external "cloud" server.

[0145] Figure 4 illustrates method 100 according to the invention implemented by the assembly comprising a mobile application and a cooking appliance. In this embodiment, the guest profiles P1 and PN are populated via a front-end application of the mobile application and then transferred via a back-end application to an embedded or remote database, which performs the determination step. This database transmits the elements of the transmission step E3 either directly to the generative language model or via an integrated back-end application of the cooking appliance. The second reception step E4 is performed by the integrated back-end application of the cooking appliance. Finally, the communication step E5 is carried out on a Product HMI (Human-Machine Interface).

[0146] Although the present invention has been described with reference to specific embodiments, it is evident that modifications and changes can be made to these examples without departing from the general scope of the invention as defined by the claims. In particular, individual features of the various embodiments illustrated / mentioned can be combined in additional embodiments. Therefore, the description and drawings should be considered in an illustrative rather than restrictive sense.

[0147] It is also evident that all the characteristics described with reference to a process are transposable, alone or in combination, to a device, and conversely, all the characteristics described with reference to a device are transposable, alone or in combination, to a process.

Claims

DEMANDS 1. A method (100) to assist in selecting at least one cooking recipe from a complete list (Ltot) of recipes, said method (100) being implemented by a system (Syst), comprising: A first reception step (E1), of at least one guest profile (P1, PN) including a unique identifier of the guest profile (P1, PN), and at least one restriction data (Res1, ResN), and at least one preference data (Prefl, PrefN); A determination step (E2) in which the system (Syst) determines a restricted list (Lres) of recipes from the complete list (Ltot) of recipes based on at least one restriction data (Res1, ResN); A transmission step (E3) in which the system (Syst) transmits to at least one generative language model (LLM), at least one textual request to generate a recommended list (Lrec) of recipes chosen from the recipes in the restricted list (Lres) of recipes, said textual generation request comprising the restricted list (Lres) of recipes, and at least one preference data (Prefl, PrefN) of at least one guest profile (P1, PN); A second reception step (E4) in response to said textual generation request, of the recommended list (Lrec) of recipes; A communication step (E5) by the system (Syst) of the recommended list (Lrec) of recipes; A selection step (E6) by a user (Usr / A) of at least one recipe from the recommended list (Lrec) of recipes for implementation.

2. Method (100) according to claim 1, wherein the first step (E1) also includes receiving at least one selection criterion (CS) of a recipe parameter, the system (Syst) determining the restricted list (Lres) of recipes also according to at least one selection criterion (CS).

3. Method (100) according to claim 2, wherein at least one recipe parameter is chosen from: an estimated time to complete the recipe, an estimated budget for the recipe, an estimated number of calories in the recipe, a type of recipe, a seasonality of the ingredients in the recipe.

4. Method (100) according to any one of the preceding claims, wherein at least one restriction data point (Res1, ResN) is chosen from: a type of diet, a food, a food family, an allergy.

5. Method (100) according to any one of the preceding claims, wherein at least one preference data point (Prefl, PrefN) comprises at least one preference recipe.

6. Method (100) according to any one of the preceding claims, wherein the at least one generation text query further comprises a sentence defining that a desired action of the generative language model (LLM) is to write an explanatory text, for each recipe in the recommended list (Lrec) of recipes, of the choice of said recipe in relation to the at least one preference data (Prefl, PrefN) of the at least one guest profile (P1, PN).

7. Method (100) according to any one of the preceding claims, wherein at least one textual generation query further comprises a sentence defining that the response to the textual generation query must be in a user-structured file in a predefined markup language.

8. Method (100) according to any one of the preceding claims, wherein the system (Syst) is selected from: a mobile terminal, a cooking appliance, an assembly comprising a mobile terminal and a cooking appliance.

9. Method (100) according to any one of the preceding claims, comprising an implementation step in which the system is configured to assist the user (Usr / A) in an implementation of the selected recipe.

10. Method (100) according to any one of the preceding claims, comprising a registration step in which the recipe selected from the recommended list of recipes is registered and then passed to at least one generative language model (LLM) during a new generation text query.

11. A method (100) according to any one of the preceding claims, wherein at least one textual generation query is of the form: “P(Pref1,..., PrefN, Lres) Lres: DOC Prefl: DOCPrefl PrefN: DOCPrefN Where Prefl, PrefN is a reference to at least one preference data from guest profile 1 to N; Lres is a reference to the shortlist of recipes; P(...) the generation text query; DOC is a text of the recipes from the shortlist of recipes in a text file; DOCPrefl, DOCPrefN is a text of at least one preference data from guest profile 1 to N.

Images