Method and system for determining emotional or sensory perception related to contact with flavor or fragrance components

Abstract

A method (400) of determining an emotional or sensory perception related to contact with a flavor or fragrance component comprises:-an input step (405) of inputting on a computer interface at least two digital representation identifiers of a flavor or fragrance physical component, the resulting input corresponding to a physical composition digital identifier representing a physical composition of the physical flavor or fragrance component; -a step (410) of operating instructions by the computing device, the instructions being configured to associate an input of a physical composition digital identifier with at least one value representative of:-the input flavor or fragrance physical composition digital representation of a relative ranking of the identifier with respect to the at least one determined perceptual emotion or sense; for at least one input flavor or fragrance physical component, digitally representing an identifier, representing a value for perceiving at least one determined perceived emotion or sense organ, and / or, by perceiving a perception of the at least one determined emotion or sense organ perceived by the perceived emotion or sense organ, representing a value for perceiving the at least one determined emotion or sense organ; a value representing a class of flavor or fragrance components in the classification of flavor or fragrance components, and a step (415) of providing, on the computer interface, at least one value obtained in the operating step for the input physical composition digital identifier.

Description

Technical Field

[0001] It is an object of the present invention to provide a method and system for determining the affective or sensory perception associated with exposure to a flavor or fragrance component.

[0002] It is particularly suitable for use in the flavor and fragrance industry. Background Art

[0003] In the field of flavor and fragrance design and production, one of the key industry challenges is to provide flavors and fragrances that contribute to the commercial success of products. These products range from dairy products to soft drinks and fine perfumes. The commercial success of products depends largely on the psychophysical response of consumers to the flavor or fragrance of the product. Such psychophysical response is related to the emotional or sensory perception of the flavor or fragrance. Such emotional or sensory perception is often associated with words (such as "energizing" or "romantic" smell).

[0004] The root causes of psychophysical responses can be difficult to discern, so at a broader level, it is possible to capture basic psychophysical affective or sensory responses that correspond, for example, to a clear and binary output from a consumer (i.e., the consumer “likes” or “dislikes” a product, flavor, or fragrance).

[0005] Traditionally, before a product, flavor or fragrance is industrialized on a large scale, a panel of people representing the target audience for the product, flavor or fragrance is consulted and shown the product, flavor or fragrance to capture their psychophysical emotional or sensory responses. Based on this feedback, the product, flavor or fragrance may go into production, be redesigned, or be discarded entirely.

[0006] Such methods are expensive, requiring not only a lot of time but also corresponding financial expenses. In addition, such methods may provide inconsistent results due to the limited number of samples from participating panelists. Finally, such results may be inaccurate considering that these methods lack modeling of important parameters that influence (bias) human response to the digital identifiers of the physical components of flavors or aromas.

[0007] For these reasons, current methods cannot reliably assess human psychophysical affective or sensory responses to products, scents, or flavors. Summary of the invention

[0008] The present invention aims to resolve all or part of these disadvantages.

[0009] According to a first aspect, the present invention is directed to a method for determining an emotion or sensory perception associated with exposure to a flavor or fragrance component, comprising:

[0010] - an input step of inputting at least two flavor or aroma physical component digital representation identifiers on a computer interface, the resulting input corresponding to a physical composition digital identifier representing the physical composition of the physical flavor or aroma component,

[0011] - an operating step, which operates instructions by a computing device, the instructions being configured to associate an input of a physical component digital identifier with at least one value representing:

[0012] - a digital representation of a physical flavor or aroma component identifier with respect to the relative ranking of at least one determined perceived emotion or sense,

[0013] - a digital representation of an identifier of at least one input flavor or aroma physical component, representing the perceived value of at least one determined perceived emotion or sensory organ, and / or

[0014] - a value representing a class of flavor or aroma ingredients in a flavor or aroma ingredient classification by perceiving an emotion or sensory perception of at least one determined emotion or sensory perception, and

[0015] - a providing step of providing, on a computer interface, at least one value obtained in the operating step for the input physical component digital identifier.

[0016] Such specification enables accurate determination of a human's actual physical response to a composition assembled (or materialized) from a digital representation of the composition.

[0017] Such provisions also allow the use of trained neural network devices or other algorithms in various scenarios, all of which are derived from the initial training of the neural network device. For example, in one scenario, the neural network device can be used to rank ingredients according to their contribution to the perception of a specific human emotion or sense. Perfumers and flavorists can then use such rankings to design physical composition digital identifiers intended to stimulate said human emotion or sense. In another scenario, an absolute value representing the intensity of the perceived human emotion or sense can be derived. Perfumers and flavorists can also use such values ​​to design physical composition digital identifiers. In a third scenario, ingredients can be classified into emotional or sensory impact categories, which also helps perfumers and flavorists design physical composition digital identifiers.

[0018] In a particular embodiment, the operating step is configured to operate a trained gradient boosting decision tree device after inputting a physical component digital identifier.

[0019] Such a provision allows the use of a trained gradient boosted decision tree device to predict the psychophysical affective or sensory responses of other physical composition digital identifiers without relying on panelists. This greatly reduces the time and expense required to evaluate the affective or sensory responses of consumers of designed physical composition digital identifiers or products containing physical composition digital identifiers. Furthermore, such a provision allows the psychophysical affective or sensory responses of said consumers to be reliably predicted.

[0020] In a specific embodiment, the method object of the present invention comprises:

[0021] - providing a step of providing an example data set to a gradient boosting decision tree device or a neural network device, comprising:

[0022] - at least two digital identifiers of the physical components of a flavour or aroma formed by digital representations of at least two physical components of the flavour or aroma, and

[0023] - for at least two of said aroma or flavor components at least one emotional or sensory perception value, said emotional or sensory perception value is associated with at least one emotional or sensory perception digital identifier, said emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses,

[0024] - an operating step of operating a gradient boosted decision tree device or a neural network device based on an example data set, and

[0025] - An obtaining step of obtaining a trained gradient boosting decision tree model or a trained neural network model.

[0026] Such a provision allows the use of a trained gradient boosted decision tree device to predict the psychophysical affective or sensory responses of other physical composition digital identifiers without relying on panelists. This greatly reduces the time and expense required to evaluate the affective or sensory responses of consumers of designed physical composition digital identifiers or products containing physical composition digital identifiers. Furthermore, such a provision allows the psychophysical affective or sensory responses of said consumers to be reliably predicted.

[0027] Preferably, any neural network used in a ranking configuration may be used instead of a conventional regression neural network model.

[0028] In certain embodiments, the example data also includes at least one digital identifier associated with the at least one physical component digital identifier that represents:

[0029] - the sex of the human being in contact with the materialized physical composition,

[0030] - the nationality of the person who came into contact with the materialized physical composition,

[0031] - the type of use of the physical composition,

[0032] - a chemical matrix of the composition used to support the physical composition, and / or

[0033] - The dosage of at least one physical ingredient flavour or fragrance physical ingredient represented by the corresponding digital representation identifier.

[0034] Such criteria influence the perceived emotion or sense by contacting the physical composition digital identifier of the flavor or aroma, and are therefore valuable parameters for the training of the gradient boosting decision tree device.

[0035] In a specific embodiment, the method object of the present invention includes, after the operation step, a determining step, which determines a numerical value representing the emotional or sensory response impact of at least one input flavor or fragrance component by a computing device; and a providing step, which provides the determined response impact value on a computer interface.

[0036] In a specific embodiment, the method object of the present invention includes a providing step after the determination step of determining a numerical value representing an emotional or sensory response impact, which provides at least one alternative flavor or fragrance physical component digital representation identifier for at least one input flavor or fragrance physical component digital representation identifier, thereby forming an alternative physical component digital representation identifier, which alternative physical composition digital representation identifier is a function of the value representing the emotional or sensory response impact associated with the input and the alternative flavor or fragrance physical component digital representation identifier.

[0037] In a particular embodiment, the providing step of providing at least one alternative flavor or aroma physical ingredient digital representation identifier is configured to also provide at least one value representing the concentration of at least one of the alternative flavor or aroma physical ingredient digital representation identifiers.

[0038] Such an embodiment allows for improved flavor or fragrance physical composition digital identifier design, thereby allowing perfumers and flavorists to dynamically select and improve physical composition digital identifiers.

[0039] In a particular embodiment, the step of providing at least one alternative flavor or aroma physical ingredient digital representation identifier is configured to also provide a minimum value and / or a maximum value representing the concentration of at least one of the alternative flavor or aroma physical ingredient digital representation identifiers.

[0040] Such an implementation allows for the suggestion of new ingredients having specific concentrations for ingredients that already have adjusted concentrations in the physical composition digital identifier.

[0041] Such an embodiment allows providing a value representing a performance threshold of the alternative component.

[0042] In a specific embodiment, the method object of the present invention includes an assembling step of assembling a physical composition corresponding to the input physical composition digital identifier or a providing step of providing the input physical composition digital identifier to a system configured to assemble the physical composition.

[0043] Such an implementation allows for the physical composition of a design to be materialized as digital identifiers.

[0044] In a specific embodiment, the method object of the present invention comprises:

[0045] - an assembling step of assembling a database associating at least one set of at least two identifiers of digital representations of physical ingredients of flavors or fragrances, and values ​​representative of measured human emotions or sensory perceptions, and

[0046] - A determination step, in which the computing device determines the instruction set to be operated in the operation step.

[0047] Such an embodiment allows for the construction of a database that accurately represents the emotional or sensory reality perceived by a human being exposed to the composition.

[0048] In a particular embodiment, the step of assembling the database includes:

[0049] - a contacting step of bringing at least one person into contact with the physical composition of the flavor or fragrance physical ingredient,

[0050] - a measuring step of measuring the emotional or sensory perception of said at least one person upon contact with said physical component, and

[0051] - A recording step of recording in a database a value representative of the perceived emotion or sensory organ measured, associated with a set of digital identifiers representing the flavor or aroma physical ingredients of the composition used during the contacting step.

[0052] In a particular embodiment, the method object of the present invention includes a substitution step, which replaces the input flavor or aroma physical ingredient digital representation identifier with a different and equivalent flavor or aroma physical ingredient digital representation identifier, wherein the equivalence is defined in a database of equivalent flavor or aroma physical ingredient digital representation identifiers.

[0053] Such an embodiment allows a dynamic replacement of equivalent components and wherein the use of one of the equivalent components has been abandoned, in particular for ecological reasons.

[0054] In a specific embodiment, the operating steps include:

[0055] - a first associating step of associating, by means of a computing device, at least one olfactory or taste descriptor with at least one input identifier of a digital representation of a physical ingredient of a flavour or aroma, and

[0056] - A second associating step of associating, by means of a computing device, at least one human emotion or sensory perception as a function of at least one olfactory or taste descriptor associated with at least one input digital representation identifier of a flavor or fragrance physical ingredient.

[0057] Such an implementation allows for an indirect approach, wherein the method first determines descriptors associated with the components and then converts these descriptors into perceived emotions or senses.

[0058] In certain embodiments, at least one affective or sensory perception represents a perception of a health or hygiene benefit associated with contact with the physical composition.

[0059] According to a second aspect, the present invention is directed to a system for determining an emotion or sensory perception associated with exposure to a flavor or fragrance component, comprising:

[0060] - an input step of inputting at least two flavor or aroma physical component digital representation identifiers on a computer interface, the resulting input corresponding to a physical composition digital identifier representing the physical composition of the physical flavor or aroma component,

[0061] - an operating step, which operates instructions by a computing device, the instructions being configured to associate an input of a physical component digital identifier with at least one value representing:

[0062] - a digital representation of a physical flavor or aroma component identifier with respect to the relative ranking of at least one determined perceived emotion or sense,

[0063] - a digital representation of an identifier of at least one input flavor or aroma physical component, representing the perceived value of at least one determined perceived emotion or sensory organ, and / or

[0064] - a value representing a class of flavor or aroma ingredients in a flavor or aroma ingredient classification by perceiving an emotion or sensory perception of at least one determined emotion or sensory perception, and

[0065] - a providing step of providing, on a computer interface, at least one value obtained in the operating step for the input physical component digital identifier.

[0066] Such a provision provides similar benefits to those of the first aspect of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Other advantages, objects and specific features of the present invention will be apparent from the following non-exhaustive description of at least one specific embodiment of the present invention in conjunction with the accompanying drawings, in which:

[0068] Figure 1 A first specific embodiment of the system object of the present invention is schematically shown,

[0069] Figure 2 A first specific sequence of steps of the method object of the present invention is schematically shown,

[0070] Figure 3 A second specific sequence of steps of the method object of the present invention is schematically shown,

[0071] Figure 4 A second specific embodiment of the system object of the present invention is schematically shown,

[0072] Figure 5 A diagram schematically showing the effect of ingredients on emotional or sensory perception,

[0073] Figure 6 A third specific sequence of steps of the method object of the present invention is schematically shown,

[0074] Figure 7 schematically shows a fourth specific sequence of steps of the method object of the present invention, and

[0075] Figure 8 A specific embodiment of a computing system capable of executing a specific sequence of steps of the method object of the present invention is schematically shown. DETAILED DESCRIPTION

[0076] This description is not exhaustive, as every feature of one embodiment may be combined in an advantageous manner with any other feature of any other embodiment.

[0077] Various inventive concepts may be embodied as one or more methods, of which examples have been provided. The actions performed as part of a method may be ordered in any suitable manner. Thus, embodiments may be constructed in which the actions are performed in a different order than shown, which may include performing some actions simultaneously, even though shown as sequential actions in an illustrative embodiment.

[0078] The phrase "and / or" used in the specification and claims should be understood to mean "either or both" of the connected elements, i.e., elements that exist connected in some cases and separated in other cases. Multiple elements listed with "and / or" should be interpreted in the same manner, i.e., "one or more" connected elements. In addition to the elements explicitly identified in the "and / or" clause, other elements may optionally be present, whether or not they are related to the explicitly identified elements. Thus, as a non-limiting example, when used in conjunction with open language such as "including", a reference to "A and / or B" may refer to only A (optionally including elements other than B) in one embodiment; to only B (optionally including elements other than A) in another embodiment; to both A and B (optionally including other elements) in yet another embodiment; and so on.

[0079] As used in this specification and claims, "or" should be construed as inclusive.

[0080] As used herein in the specification and claims, the phrase "at least one" when referring to a list of one or more elements should be understood to refer to at least one element selected from any one or more elements in the list of elements, but does not necessarily include at least one of each element specifically listed in the list of elements, nor does it exclude any combination of elements in the list of elements. This definition also allows that in addition to the elements specifically identified in the list of elements referred to by the phrase "at least one", elements may optionally be present, whether related or unrelated to the specifically identified elements. Thus, as a non-limiting example, "at least one of A and B" (or equivalently, "at least one of A or B", or equivalently, "at least one of A and / or B") may refer to at least one, optionally including more than one A, without B (and optionally including elements other than B) in one embodiment; to at least one, optionally including more than one B, without A (and optionally including elements other than A) in another embodiment; to at least one, optionally including more than one A, and at least one, optionally including more than one B (and optionally including other elements) in yet another embodiment; and so on.

[0081] In the claims and the foregoing specification, all transitional phrases, such as "includes," "comprising," "carrying," "having," "containing," "involving," "holding," "consisting of," etc., shall be construed as open-ended, i.e., including but not limited to. Only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases, respectively.

[0082] It should be noted at this time that the drawings are not drawn to scale.

[0083] As used herein, the term "ingredient" refers to any ingredient, preferably with flavoring or perfuming capabilities. The term "compound" or "ingredient" refers to the same item as "ingredient". An ingredient may be formed of one or more chemical molecules. Thus, an ingredient may be considered a "simple" ingredient when it is primarily a single compound component, and a "complex" ingredient when it involves multiple compounds and the ratios of these compounds are within a certain range.

[0084] The term "physical composition numerical identifier" refers to a liquid, solid and / or gaseous combination of at least one component.

[0085] As used herein, "flavor" refers to the olfactory perception produced by at least one volatile component through prenasal and postnasal olfactory activation, enhancement and inhibition (when present) of odorant receptors and activation of taste buds containing taste receptor cells. Thus, for the purpose of illustration and not intended to limit the scope of the present disclosure, a "flavor" is produced by the olfactory and taste bud perceptions produced by the sum of a first volatile component that activates an odorant receptor or taste bud associated with a coconut note, a second volatile component that activates an odorant receptor or taste bud associated with a celery note, and a third volatile component that inhibits an odorant receptor or taste bud associated with a hay note.

[0086] As used herein, "aroma" refers to the olfactory perception produced by the sum of at least one volatile component activating, enhancing, and inhibiting (when present) odor receptors. Thus, for the purpose of illustration and not intended to limit the scope of the present disclosure, a "aroma" is produced by the olfactory perception produced by the sum of a first volatile component that activates an odor receptor associated with a coconut tonality, a second volatile component that activates an odor receptor associated with a celery tonality, and a third volatile component that inhibits an odor receptor associated with a hay tonality.

[0087] As used herein, the term "input device" is, for example, a keyboard, mouse, and / or touch screen suitable for interacting with a computing system to collect user input. In variations, the input device is logical in nature, such as a network port of a computing system configured to receive electronically transmitted input commands. Such an input device may be associated with a GUI (graphical user interface) or an API (application programming interface) displayed to a user. In other variations, the input device may be a sensor configured to measure a specified physical parameter associated with an intended use case. Figure 8 Examples of input devices are disclosed.

[0088] As used herein, the term "computing system" or "computer system" refers to any electronic computing device, whether unitary or distributed, capable of receiving numerical input and providing numerical output through any type of interface (digital and / or analog). In general, a computing system refers to a computer executing software that can access data storage or a client-server architecture where data and / or computation is performed on the server side and the client acts as an interface. Figure 8 An example of such a computing system is disclosed.

[0089] As used herein, the term "digital representation identifier" refers to any bijective digital representation of a physical item, such as a composition or a fragrance or flavor ingredient. Such a digital representation identifier may correspond to, for example, an entry in a database. For example, a digital representation identifier may refer to a label representing the name, chemical structure, or internal reference of a fragrance or flavor ingredient.

[0090] As used herein, the term "emotion or sensory perception" refers to any measurable emotion or sensory perception evoked by combining a human contact with a physical component digital identifier. For example, such a measurement may be observed using neuroimaging techniques. Such a perception may be related to an emotion felt by a human (e.g., happiness) or the human's perception of a sense (e.g., coldness).

[0091] Such emotions or sensations may fall into one of the following categories:

[0092] - Sensual (emotional, romantic, lustful),

[0093] - energy (full of energy, vigor, and spirit),

[0094] -happiness (surprising, joyful, healthy),

[0095] - Indulge (mouth-watering, thirsty, hungry),

[0096] - unpleasant (disgust, irritation, unpleasant surprise),

[0097] - nostalgic (nostalgic, melancholic, sad),

[0098] - interests (interesting, impressive, interesting),

[0099] - Calming (soothing, comforting, relaxing), and

[0100] -Spirituality.

[0101] Such emotions or sensations (or attributes or impressions as they are sometimes called) may also fall into one of the following categories:

[0102] - Aggression,

[0103] -Entertainment,

[0104] - Antiseptic,

[0105] - Man-made,

[0106] -Baby's,

[0107] - Caring,

[0108] - Cheap,

[0109] - Citrus,

[0110] - Classical,

[0111] - Clean,

[0112] -Comforting,

[0113] -Cream,

[0114] -desire,

[0115] -Disgusting,

[0116] - Easy to wear,

[0117] - edible,

[0118] - Elegant / refined,

[0119] - Energetic,

[0120] -Female,

[0121] - Floral,

[0122] -Fresh,

[0123] -Fruity,

[0124] -foodie,

[0125] - Green,

[0126] -Happy,

[0127] -Has characteristics,

[0128] -heavy,

[0129] -Impressive,

[0130] - Interested,

[0131] - Angry,

[0132] - Light,

[0133] - Like,

[0134] - Long-lasting,

[0135] - It makes me feel good.

[0136] - Male,

[0137] - Medicinal,

[0138] - Melancholic,

[0139] - modern,

[0140] - Moisturizing,

[0141] -Salivating,

[0142] - Natural,

[0143] - Neutral,

[0144] -New,

[0145] - Nostalgic,

[0146] - Old-fashioned,

[0147] - Overwhelming,

[0148] - pleasantly surprising, - pure,

[0149] -Brand new,

[0150] -Relaxed,

[0151] - Rejuvenating,

[0152] -Romantic,

[0153] -Sad,

[0154] - Sentimental,

[0155] - Soapy,

[0156] - soft,

[0157] - Soothing,

[0158] - Sour,

[0159] -Spicy,

[0160] -Sports,

[0161] - Strong,

[0162] -Sweet,

[0163] -That suits you very well.

[0164] - Unpleasant surprising,

[0165] - Well-being, and / or

[0166] - Wooden.

[0167] In this specification, the term "materialized" or "assembled" means existing outside the digital environment of the present invention. "Materialized" can mean, for example, readily found in nature or synthesized in a laboratory or chemical plant. In any case, the materialized physical component digital identifier presents a tangible reality. The term "to be compounded" or "compounded" refers to the act of materializing the physical component digital identifier, whether by extracting and assembling the components or by synthesizing and assembling the components.

[0168] The embodiments disclosed below are presented in a general manner.

[0169] For example, the present invention may be used to predict emotional or sensory responses of a human user, where a physical component digital identifier is presented that is intended to provide a "romantic" emotion or sensation.

[0170] Furthermore, the present invention may be used to predict overall like / dislike of a physical component digital identifier, or more specifically, like / dislike prediction of an aroma and / or like / dislike prediction of a flavor.

[0171] As an example input for the following examples, data from 3500 tests, each containing 8 test compositions and each with 80 to 100 panelists, can be used. Such data may illustrate different human biases:

[0172] National bias - in Mexico, panelists usually vote at 80-90%, while in Germany, 50-60% is high.

[0173] Application bias – testing the same flavoring ingredient in two different applications may produce different results, and

[0174] Testing bias – ingredients tested together can affect each other’s results – a very sweet ingredient tested with other ingredients may lower the sweetness scores of the other ingredients because all these comparisons are relative.

[0175] For example, the results of two different tests ranking the sweetness of three compositions might be:

[0176] -Test 1

[0177] - Composition 1 11.4

[0178] - Composition 2 26.3

[0179] - Composition 3 19.7

[0180] -Test 2

[0181] - Composition 1 21.4

[0182] - Composition 2 37.3

[0183] - Composition 3 25.7

[0184] In this example, we can see a fairly common situation - the values ​​in the two tests are different, while the relative relationship (i.e., ranking) remains the same - that is, one composition is sweeter than the other in both tests, while their scores in different tests may be different. Therefore, the score value is only valid in one specific test, and, rather than training the model object of the present invention to predict these scores (such as a regression model), the model is trained to correctly rank the compositions (hence the ranking model). One advantage of the ranking model is that it captures each test separately and adjusts their parameters to rank ingredients consistent with the ground truth ranking. As will be appreciated, such a provision allows prediction of pairwise rankings of ingredients that form a physical composition digital identifier.

[0185] Figure 1 A specific embodiment of the system 100 object of the present invention is shown. The system 100 is used to train a gradient boosted decision tree device or a neural network device, which associates a perceived emotion or sensory feeling with a flavor or a fragrance physical component digital identifier of at least one fragrance or flavor component, and the system 100 includes one or more computer processors and one or more computer readable media operably connected to the one or more computer processors, wherein the one or more computer readable media stores instructions that, when executed by the one or more computer processors, cause the one or more computer processors to perform at least the following steps:

[0186] - providing step 105, which provides an example data set to a gradient boosting decision tree device, including:

[0187] - at least two digital identifiers 101 of the physical components of a flavor or aroma formed by digital identifiers of at least two physical components of the flavor or aroma, and

[0188] - at least one emotional or sensory perception value 102 corresponding to at least two of said aroma or flavor components, said emotional or sensory perception value being associated with at least one emotional or sensory perception digital identifier, said emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses,

[0189] - Operation step 110, which operates a gradient boosting decision tree device based on the example data set, and

[0190] - An obtaining step 115 of obtaining a trained gradient boosted decision tree device.

[0191] Such a system 100 may be formed by any combination of methods performing the characteristic steps executed by a computer processor.

[0192] The providing step 105 may be performed through a computer interface (e.g., an API or any other digital input system). The providing step 105 may be initiated manually or automatically. The example data set may be assembled manually on a computer interface, or automatically by a computing system from a larger example data set.

[0193] Example data may include, for example:

[0194] - at least two digital identifiers 101 of the physical components of a flavor or aroma formed by digital identifiers of at least two physical components of the flavor or aroma, and

[0195] - At least one emotional or sensory perception value 102 corresponding to at least two of the aroma or flavor components, the emotional or sensory perception value being associated with at least one emotional or sensory perception digital identifier, the emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses.

[0196] For example, a fragrance or flavor physical ingredient digital representation identifier may correspond to the name of the ingredient or a reference to an entry in a database of characteristics associated with the ingredient. For example, such an identifier may be a universally unique identifier ("UUID").

[0197] The emotion or sensory perception value 102 may correspond to a numerical representation of the perception between panelists in a survey, for example, relative to the effect of the component on the determined emotion or sensory perception. Such a value 102 may be, for example, a relative difference between the components, and the difference refers to a quantification of the difference between the components relative to the effect of the components on the determined emotion or sensory perception. In other embodiments, the emotion or sensory perception value 102 is an absolute quantification, where the component itself is evaluated, rather than in relation to another component.

[0198] In a more advanced implementation, the example data set may also include:

[0199] - Sex of humans in contact with objectified physical components 103,

[0200] -Nationality of origin of the person who came into contact with the materialized physical composition 104,

[0201] - Type of use of physical composition 106,

[0202] - a chemical matrix 107 of the composition used to support the physical composition, and / or

[0203] - a dose 108 of at least one physical ingredient flavour or fragrance physical ingredient represented by a corresponding digital representation identifier.

[0204] Such an example dataset may be obtained by assembling physical component digital identifiers, presenting the physical component digital identifiers to human users, and recording the emotional or sensory responses of these users. These recordings may be categorized by type of emotional or sensory response (e.g., "relaxed," "romantic," "sad," "sensual," "thirsty," "soothing"). Such categorization may be performed manually, by associating a label with each emotional or sensory response, or automatically by a computing system configured to process text, audio, photo, or video recordings, thereby determining the response type among a list of possible response types. These emotional or sensory response types may be associated with the types of emotional or sensory response digital identifiers, which may then be used in the example dataset.

[0205] Such an emotional or sensory response or emotional or sensory perception may also correspond to the perception of a health or hygiene benefit associated with contact with the physical composition.

[0206] In a particular example, an example set may include a value representing at least one of the following:

[0207] - identifiers of the chemical composition of the perfume,

[0208] - a test stamp defining the identifier of the test,

[0209] -The number of respondents who indicated the number of consumers who have participated in testing and evaluating fragrances,

[0210] - measure the fragrance content (%) of the composition inside the test product,

[0211] - indicates the country where the test was conducted,

[0212] - Gender indicating the gender type of the consumer: Male and Female, Male, Female,

[0213] -Age group attributes representing the age groups of consumers: young and old, young, old,

[0214] - Segment names that define the purpose of the product at a high level: Body & Personal Care, Home & Fabric Care, Fine Fragrance,

[0215] - Sub-segment names that define the purpose of the product in a more specific way than the segment name: 13 attributes,

[0216] - Application name that defines the purpose of the product in a more specific way than the sub-segment name. It corresponds to the leaves of the tree structure defined by segment name, sub-segment name, application name: 158 attributes,

[0217] - Stage Name Tester that defines at which stage the product is tested, contains 123 attributes, this feature includes attributes such as "neat - squeeze bottle", "wet clothes", "wash", etc.,

[0218] - Perceived emotion or sense percentage score for the following emotions, senses, attributes or likes,

[0219] -Emotions: amused, comforted, craving, disgusted, energized, hungry, happy, impressed, interested, annoyed, melancholy, mouth-watering, nostalgic, surprised, refreshed, relaxed, rejuvenated, romantic, sad, soothing, unpleasantly surprised, happy,

[0220] -Attributes: aggressive, antiseptic, artificial, baby, caring, cheap, citrus, classic, clean, creamy, easy to wear, edible, elegant / delicate, feminine, floral, fresh, fruity, gourmet, green, with personality, heavy, light, long-lasting, makes me feel good, masculine, modern, moisturizing, natural, unisex, new, old-fashioned, strong, pure, sensual, soapy, soft, sour, spicy, tangy, sweet, that suits you, unique, woody and / or

[0221] -Like fractions.

[0222] In a particular variation, the system 100 object of the present invention includes a preprocessing step (not shown) for preprocessing the input. For example, this preprocessing step can utilize a sparse matrix called a physical composition digital identifier matrix that stores weighted partitions of the components used, where the weighted sum of each composition adds up to 1. The physical composition digital identifier matrix can contain approximately 1 million components (rows) and 6351 components (columns), where the weights correspond to the number of given components (columns) within a given composition (row). The physical composition digital identifier matrix can be used unchanged, and each component identifier is replaced with its corresponding component physical composition digital identifier.

[0223] Furthermore, in order to select fragrances with doses strictly above 0, the encapsulation is binarized, all ages are used and the app names are removed, and a grid search algorithm is applied. This selects the best set of parameters for each emotion or sense, maximizing the results for each emotion or sense.

[0224] In addition, in order to maximize the information gain brought by the target encoding, the most important features can be calculated for each emotion or sense: gender, age group attribute, segment name, sub-segment name, fragrance volume. If the addition of a feature improves the quality index, the feature is considered the most important feature, indicating that it is a significant feature.

[0225] Operation step 110 may be performed, for example, by a computer program executing on a computing system. During this step 110, the gradient boosting decision tree apparatus is configured to determine operational values ​​of decision parameters within the tree structure, said values ​​being used in relation to future physical component digital identifiers, thereby providing specific knowledge associated with these physical component digital identifiers.

[0226] Optionally, during operation step 110, gradient boosted trees are sequentially constructed such that each new tree minimizes the ranking loss in the context of a neural network device optimized for ranking prediction.

[0227] In other embodiments, any other neural network device technology may be used during operation 110. Such a neural network device may implement, for example, a RankNet, LambdaRank, or SoftRank algorithm.

[0228] In such an embodiment, the system 100 object of the present invention includes devices for performing the following steps:

[0229] - providing step 105, which provides an example data set to the neural network device, including:

[0230] - at least two digital identifiers of the physical components of the aroma or flavor formed by digital representation identifiers of at least two physical components of the aroma or flavor, and

[0231] - at least one emotional or sensory perception value corresponding to at least two of said aroma or flavor components, said emotional or sensory perception value being associated with at least one emotional or sensory perception digital identifier, said emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses,

[0232] - an operation 110 of operating a neural network device based on the example data set, and

[0233] - An obtaining step 115 of obtaining a trained neural network model.

[0234] In previous systems, the same group of consumers tested products sequentially during each test. This leads to biased results. When testing a product, the perception of the consumer will be largely dependent on the previously tested products. Consumers will make comparisons unconsciously and therefore give results that are influenced by these comparisons. Therefore, a ranking algorithm based on the test tag attribute is an innovative idea to solve this problem, because the algorithm tries to rank the pairs of examples in each test, reproducing the real behavior as closely as possible. In addition, the test tag attribute defines an identifier in the dataset that allows the dataset to be used without any aggregation. Dividing the groups by the test tag feature forces the comparison of the compositions evaluated by consumers at the same time. Considering the technical coding implementation, the training-validation-test split can be done by first applying a random split according to the test tag (20% test set) and then splitting the group K-fold according to the test tag (20% validation set) again. Decision tree neural network device training can use CatBoost with YetiRank and QuerySoftmax algorithms. YetiRank and QuerySoftmax belong to the family of pairwise learning methods, which optimize the object function defined corresponding to the data example pairs retrieved by a given group. An important high-value concept introduced here is the accuracy measure related to the gap value. The gap value is the difference between the ground truth values ​​of two compositions tested together. The accuracy metric using the gap value is a novel metric that can be used in conjunction with the percentage of correctly predicted pairs to measure the accuracy of the predictions.

[0235] CatBoost has been shown to perform well in handling categorical variables. Hyperparameter tuning by maximizing the mean gap score over the maximum gap calculated for each emotion or sense can significantly improve the training output.

[0236] In certain variations, the system 100 object of the present invention includes a post-processing step (not shown) that performs post-processing by creating a distribution of predicted values ​​to determine the location of a particular composition in a particular environment. The component impact values ​​are related to the quantity, thereby selecting the most actionable components. Other component criteria filters can be applied.

[0237] The performance of the model can be measured in terms of weighted correctly sorted pairs. The sorting scheme is measured as the percentage of weighted correctly sorted pairs, which is defined as:

[0238] The performance of the model can be measured in terms of weighted correctly sorted pairs. The sorting scheme is measured as the percentage of weighted correctly sorted pairs, which is defined as:

[0239]

[0240] in:

[0241] -Et indicates the samples included in test t,

[0242] -predi is the ranking prediction score of sample i,

[0243] -y i is the sentiment or sensory score of sample i, and

[0244] -gap is a user-defined value.

[0245] The reason for using this score is that the percentage of correctly ranked pairs is weighted by the number of pairs included in each test and meets the condition |ya-yb|>gap. This condition selects only pairs where the absolute value of the difference in the emotion or sensory score is higher than the numerical gap value. Therefore, the general pattern that emerges is that when increasing the gap value, the score also increases.

[0246] Furthermore, to obtain a single value for automatic parameter tuning, the ranking scores for the distance from 0 to α*σ (emotional or sensory distribution) can be averaged.

[0247] The output of the ranking model is a ranking score, which is a technical value that represents a measurable difference in perceived emotional or sensory perception between physical composition digital identifiers. The higher the ranking value, the higher the ranking position. In order to relate these abstract ranking values ​​to meaningful outputs, a quantile transformer can be used to display the ranking of compositions in a specific context. For example, a composition has a freshness quantile of 0.68 - which means that the composition is fresher than 68% of the target country and sub-segment compositions.

[0248] To determine which set of ingredients has the greatest impact on each emotion or sense, it is important to remember that emotion or sense scores can be affected by country bias. Therefore, ingredient recommendations are provided by country bias.

[0249] Shappley Additive Explanations (SHAP), published by Lundberg and Lee in 2017, is widely regarded as the state-of-the-art method in the field of machine learning interpretability. SHAP assigns each feature of the input dataset an importance value for a particular prediction.

[0250] Selecting the most influential ingredients is not a trivial task, as ingredients with a positive or negative relationship between SHAP importance score and ingredient dosage need to be treated separately. Linear relationships determined by Spearman correlations are able to distinguish between positive and negative relationships. The ingredients with the most positive impact on each emotion or sense may be associated with defined boundary dosages given by the minimum and / or maximum amounts of the specific ingredient. The minimum amount of a specific ingredient can indicate the starting amount at which the ingredient becomes a reinforcer of a specific emotion or sense. Exceeding the minimum amount should increase the perception of a given emotion or sense until the maximum amount is reached. Defined as breakpoints, adding more than the amount indicated by the maximum amount results in a slow increase or saturation or decrease in the effect of the ingredient on a specific emotion or sense. The ingredients with the most negative impact also provide important additional information for the perfumer. Adding a negative ingredient in large amounts may significantly reduce the emotional or sensory attributes of a given emotion or sense.

[0251] Such a positive or negative relationship between the concentration of a component and the intensity of an emotion or sensory perception is Figure 5 As shown, where:

[0252] - shows footprints of two different components 601 and 602,

[0253] - The first component 601 has a positive relationship with a specific emotion or sensory perception intensity, the relationship being defined as:

[0254] - a minimum concentration boundary 605, below which no effect on the determined emotion or sense occurs,

[0255] - a maximum concentration boundary 610, beyond which there is no additional effect on the determined emotion or sense,

[0256] - an optimal range, between the minimum concentration boundary 605 and the maximum concentration boundary 610, where additional component concentrations proportionally affect the perceived emotion or sense,

[0257] - The second component 602 has a negative relationship with a particular emotion or sensory perception intensity, the relationship being defined as:

[0258] - a maximum concentration boundary 615, beyond which additional concentrations of the constituents will have a proportionally negative effect on the perceived emotion or sense,

[0259] - A range below the maximum concentration boundary 615, wherein no additional influence is exerted on the determined emotion or sense, regardless of the concentration of the second component 602.

[0260] Taking into account the positive or negative relationship, the final importance score of each component is calculated by taking the median of the positive or negative SHAP scores of each component with more than 50 positive or negative samples. In this way, the most contributing positive or negative component will be the one with the highest or lowest median score.

[0261] To determine the quantity range and boundaries, the data points appearing in the SHAP vs. quantity plot for each operational component can be approximated by a piecewise linear function.

[0262] Example of composition optimization: Improve the hedonic attribute for the shampoo ingredients that have a ranking quantile of 0.265 according to the hedonic model (which means that the ingredient brings more hedonics than 26% of US hair care compositions, but less than 74% of US hair care compositions, so there is room for improvement) for the target US market. Using the Shap values, the most important positive and negative ingredient contributors in the ingredient space can be identified. Among the most important positive contributors, two ingredients are already above the saturation limit, so these ingredients can remain as they are, but the amount of ingredient 3 can be increased (the current amount is 0.2%, while the recommended saturation limit or upper limit for this ingredient is 0.4%). The amounts of the two negative ingredients are above the recommended maximum limit, so these ingredients can be reduced to reduce their negative impact. The following table shows these impacts individually and in combination:

[0263] Initial impact Initial quantity Change quantity Happiness attribute improvement Ingredient 1 burden 0.00125 0.000741 0.3034 Ingredient 2 burden 0.000416 0.000130 0.2969 Ingredient 3 just 0.002083 0.004167 0.3707 Change all together 0.4513

[0264] By adjusting these three ingredients, the likeability quantile score was increased from 0.26 to 0.45. Therefore, the ingredient is now more liked than 45% of US hair care ingredients.

[0265] Another output is the so-called “DNA”, which models customer behavior in different countries. For example, the attribute “clean” is perceived differently for a specific country in terms of olfactory characteristics. In order to retrieve these translations from affective or sensory attributes to olfactory descriptors, the correlation between the global ranking of a specific country composition predicted by the model and the olfactory characteristics of the composition can be calculated. The top positively and negatively correlated olfactory descriptors show the associations humans have with specific attributes and emotions or senses. For some attributes, all countries are consistent - for example, the attribute sweetness will be associated with chocolate, caramel, vanilla for almost all countries, while for other attributes significant differences are observed. For example, the attribute “natural” - among the most correlated olfactory descriptors in China are orange, grapefruit, lemon, citrus and green, while for the United States there are water, lily of the valley, lily of the valley and green, with grapefruit and citrus being the top negative correlations for natural.

[0266] An example of the classification output of the model is as follows: Based on the aggregation of different ranking results for relevant categories (emotion or sensory, attributes), the present invention can classify compositions into groups (sub-segments + countries) relevant to the desired context. For example, composition 1 is the top category for shower gel in the United States because of its high predicted quantiles for liking (0.74), cleaning (0.69), natural (0.81), and non-aggressive (0.23).

[0267] For this particular use, the model inputs are a dictionary of numeric identifiers of the physical composition of the composition in the format {Ingredient 1: Quantity 1, Ingredient 2: Quantity 2, ...} and a dictionary of additional information {Country: United States, Segment: Personal Care, Sub-Segment: Hair Care, Gender: Female}. A set of dictionaries describing the compositions we tested is converted into a matrix format for input to the model. The target values ​​given to the model are the results of the blind tests, and they can be in different formats depending on the situation: for training ranking, the "relevant value in each test" can be used, that is, the percentage of participants voting for a specific attribute and emotion or sense, or the average of the scores given by participants for a specific composition and a specific attribute. For regression, the target value is the score given by each user; for classification, the target value is the predicted ranking score corresponding to particularly important attributes and emotions or senses and likes.

[0268] For such specific use, the model outputs are the ranking quantiles for each attribute / emotion or sensory / liking in the ranking approach, the average score for all test participants in the regression approach, and the associated classes for the composition of specific countries and sub-segments in the classification approach.

[0269] The obtaining step 115 may be performed via a computer interface (eg, an API or any other digital output system). The obtained trained gradient boosting decision tree device or neural network device may be stored in a data storage device, such as a hard disk or a database.

[0270] Figure 2 A specific sequence of steps of the object of the method 200 of the present invention is schematically represented. The method 200 is used to train a gradient boosting decision tree device or a neural network device to associate a perceived emotion or sensory feeling with a flavor or fragrance physical component digital identifier including at least one aroma or flavor component, and comprises at least the following steps:

[0271] - providing a step of providing an example data set 105 to a gradient boosting decision tree device or a neural network device, comprising:

[0272] - at least two digital identifiers of the physical components of a flavour or aroma formed by digital representations of at least two physical components of the flavour or aroma, and

[0273] - at least one emotional or sensory perception value corresponding to at least two of said aroma or flavor components, said emotional or sensory perception value being associated with at least one emotional or sensory perception digital identifier, said emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses,

[0274] - an operation step 110 of operating a gradient boosting decision tree device or a neural network device based on the example data set, and

[0275] - An obtaining step 115 of obtaining a trained gradient boosting decision tree model or a trained neural network model.

[0276] It is to be understood that the present invention is also directed to a computer-implemented gradient boosting decision tree device or neural network device 305, characterized in that the neural network device is implemented by Figure 2 The computer implemented method 200 is shown to achieve.

[0277] It should be understood that the present invention is also intended to provide a computer program product, which, when executed on a computer, comprises executing Figure 2 Instructions for step 200 of the disclosed method.

[0278] It is understood that the present invention also corresponds to a computer-readable medium storing, when executed on a computer, Figure 2 Instructions for the steps of method 200 are shown.

[0279] Figure 3 A specific sequence of steps of a method 400 of the present invention is schematically shown. The method 400 is used to determine an emotion or sensory perception associated with contact with a flavor or fragrance component, comprising:

[0280] - an input step 405 of inputting at least two flavor or fragrance physical component digital representation identifiers on a computer interface, the resulting input corresponding to a physical composition digital identifier representing a physical composition of a physical flavor or fragrance component,

[0281] - Operation step 410, which is operated by a computing device with instructions configured to associate the input of the physical component digital identifier with at least one value representing the following:

[0282] - a relative ranking of a digital representation of a physical flavor or aroma component identifier with respect to at least one determined human affective or sensory perception,

[0283] - a digital representation of an identifier of at least one input flavor or aroma physical component, representing a value perceived by at least one determined human emotion or sensory perception, and / or

[0284] - a value of a class of flavor or aroma ingredients in a flavor or aroma ingredient classification by a perceived human emotional or sensory perception of at least one determined human emotional or sensory response, and

[0285] - A providing step 415 of providing, on a computer interface, at least one value obtained in the operating step for the input physical component digital identifier.

[0286] The input step 405 can be performed manually, for example, or automatically on a computer interface, such as a graphical user interface ("GUI"). During this input step 405, the flavor and / or fragrance physical component digital representation identifiers can be selected to form physical component digital identifiers representing equivalent real fragrances. In advanced embodiments, relative or absolute amounts of the flavor and / or fragrance physical component digital representation identifiers can be entered. At the beginning of this input step 405, the physical component digital identifiers are defined.

[0287] Operation step 410 is performed, for example, by a computing device. During such operation step 410, an expert system algorithm may be run, wherein a series of setting instructions are executed to provide values ​​representing the following based on the composition of the input:

[0288] - a relative ranking of a digital representation of a physical flavor or aroma component identifier with respect to at least one determined human affective or sensory perception,

[0289] - a digital representation of an identifier of at least one input flavor or aroma physical component, representing a value perceived by at least one determined human emotion or sensory perception, and / or

[0290] - Representing the value of a class of flavor or aroma ingredients in a flavor or aroma ingredient classification by the perception of a human emotional or sensory perception of at least one determined human emotional or sensory response.

[0291] In other embodiments, during the operation 410, a trained gradient boosted tree model or a trained neural network model may be operated to determine the value.

[0292] For example, during this operation step 410, the input physical composition digital identifier is fed to a gradient boosted decision tree device, and the gradient boosted decision tree device returns at least one of the following:

[0293] - a relative ranking of the input flavor or aroma physical composition digital representation identifier relative to at least one determined emotional or sensory perception obtained by operating the trained gradient boosting decision tree device,

[0294] - for at least one input flavor or aroma physical component digital representation identifier, representing the value of at least one determined emotional or sensory perception obtained by operating the trained gradient boosting decision tree device, and / or

[0295] - representing the value of a class of flavor or aroma ingredients in the flavor or aroma ingredient classification by the perception of an emotion or sensory perception of at least one determined emotion or sensory perception.

[0296] Providing step 415 is performed by displaying the predicted human response output by the gradient boosted decision tree device, for example, on a computer screen.

[0297] In a specific embodiment, for example Figure 3 In the illustrated embodiment, the method 400 object of the present invention includes, after step 410, a determination step 420 of determining a numerical value representing an emotional or sensory response impact corresponding to at least one input flavor or aroma component by a computing device, and a providing step 415 of providing the determined response impact numerical value on a computer interface.

[0298] Reaction impact is a numerical value that represents the ranking position relative to all other recipes for a specific input (i.e., quantile). For example, when there are no two recipes that can be compared and predicted to be fresher than the other, a comparison can be made to the context (e.g., all women's shampoos in the U.S.). For example, if a recipe has a freshness quantile of 0.56, it means that the recipe is fresher than 56% of the women's shampoo recipes in the U.S., but less fresh than 44% of the women's shampoo recipes in the U.S.

[0299] In a specific embodiment, for example Figure 3 In the illustrated embodiment, the method 400 object of the present invention includes, after the determination step 420 of determining a numerical value representing the emotional or sensory response impact, a providing step 435, which provides at least one alternative flavor or aroma physical component digital representation identifier for at least one flavor or aroma physical component digital representation identifier input, thereby forming a physical component digital identifier, which is a function of the numerical value representing the emotional or sensory response impact of the input and the alternative flavor or aroma component.

[0300] For example, an alternative flavor or fragrance physical ingredient digital representation identifier is selected as a function of the impact of the flavor or fragrance ingredient according to the determined emotion or sensory perception.

[0301] In certain embodiments, providing step 435 is configured to provide a value for the amount or concentration of the substitute flavor or fragrance ingredient.

[0302] If an alternative flavor or fragrance physical ingredient digital representation identifier is associated with a similar emotion or sensory perception value or impact, then the alternative flavor or fragrance physical ingredient digital representation identifier may be selected during providing step 435. Such similar emotion or sensory perception value or impact may be determined if the emotion or sensory perception value or impact of the alternative ingredient (or alternative candidate) is within an acceptable range of the emotion or sensory perception value or impact of the original ingredient.

[0303] In the simple variant, the emotional or sensory perceived value or impact of the ingredients is assessed based on only one emotional or sensory perceived value.

[0304] In more complex variations, several affective or sensory perception values ​​or impacts of the component are evaluated, thus providing a more complete match between the affective or sensory perceptions associated with contact with the replaced component and the original component.

[0305] In providing step 435, a single original component may be replaced by multiple candidate components, and similarly, multiple original components may be replaced by a single candidate component.

[0306] In certain variations, instead of or in addition to providing an alternative flavor or aroma physical ingredient digital representation identifier, providing step 435 is configured to provide an alternative amount or concentration for at least one of the input flavor or aroma physical ingredient digital representation identifiers of the physical component digital identifier.

[0307] In a specific embodiment, for example Figure 3 In the illustrated embodiment, the method 400 of the present invention includes an assembling step 430 of assembling the composition represented by the input physical component digital identifier.

[0308] Such an assembly step 430 can be performed in a number of ways, such as in a laboratory or a chemical plant.

[0309] In a specific embodiment, the method 400 of the present invention includes:

[0310] - an assembly step 401 of assembling a database associating at least one set of at least two identifiers of digital representations of physical ingredients of flavours or aromas with values ​​representative of measured human emotions or sensory perceptions, and

[0311] A determination step 407 , of determining, by the computing device, a set of instructions to be operated on during an operation step 410 .

[0312] The assembling step 401 can be performed manually, automatically or semi-automatically using any input device. During the assembling step 401, a set of at least two flavor or fragrance physical component digital representation identifiers (corresponding to a composition or a portion of a composition) are associated with a value representing a measured human emotion or sensory perception in a computer memory.

[0313] The nature of determining step 407 depends on the type of instruction to be operated during operating step 410. For example, the determining step 407 may correspond to Figure 2 Disclosed method 200. In other embodiments, the determining step 407 may correspond to a regression algorithm used on the assembled database.

[0314] In a specific embodiment, step 401 of building a database includes:

[0315] - a contacting step 402 of contacting at least one human being with the physical composition of the flavor or fragrance physical component,

[0316] - a measuring step 403 of measuring the emotional or sensory perception of at least one human being in contact with the physical composition, and

[0317] - A recording step 404 of recording in a database the value representative of the measured human affective or sensory perception associated with the set of digital representation identifiers of the flavor or fragrance physical ingredients representative of the physical ingredients of the composition used during the contacting step.

[0318] The measuring step 403 may be performed by any type of sensor commonly used to measure the intensity or presence of human emotions or sensory perceptions.

[0319] The recording step 404 may be performed by any input device suitable for the particular use case.

[0320] In a particular embodiment, the method 400 object of the present invention includes a replacement step 406, which replaces the input flavor or aroma physical ingredient digital representation identifier with a different and equivalent flavor or aroma physical ingredient digital representation identifier, wherein the equivalence is defined in a database of equivalent flavor or aroma physical ingredient digital representation identifiers.

[0321] Such a replacement step 406 may be performed by creating a synonym dictionary between flavor or aroma physical ingredient digital representation identifiers and searching for synonyms for the input flavor or aroma physical ingredient digital representation identifier.

[0322] In a particular embodiment, operation 410 includes:

[0323] - a first associating step 411 of associating, by means of a computing device, at least one olfactory or taste descriptor with at least one input identifier of a digital representation of a physical component of a flavor or fragrance, and

[0324] - A second associating step 412 of associating, by means of a computing device, at least one human emotion or sensory perception as a function of at least one olfactory or taste descriptor associated with at least one input flavor or fragrance physical ingredient digital representation identifier.

[0325] Emotions and attributes can be translated into a set of olfactory descriptors or tonality. Liking in a specific context can be understood through concepts other than the actual measured attributes (e.g., in China, natural is more associated with citrus descriptors (lemon, grapefruit), while in European countries, natural refers to mild things like almond).

[0326] Such associations can be obtained by exposing a user to a recipe and asking which descriptors best fit the recipe and which emotion or sensory perception best describes the emotion or sense perceived by the user. From such sampling, general association rules can be statistically determined.

[0327] Figure 5 A specific embodiment of the system 500 object of the present invention is schematically shown. The flavor or aroma prediction emotion or sensory perception determination system 500 includes:

[0328] - an input step 505 of inputting at least two flavor or fragrance physical component digital representation identifiers on a computer interface (510), the resulting input corresponding to a physical composition digital identifier representing a physical composition of a physical flavor or fragrance component,

[0329] - Operation step 515, which is operated by a computing device (520) with instructions configured to associate the input of the physical component digital identifier with at least one value representing:

[0330] - a relative ranking of a digital representation of a physical flavor or aroma component identifier with respect to at least one determined human affective or sensory perception,

[0331] - a digital representation of an identifier of at least one input flavor or aroma physical component, representing a value of at least one determined human emotional or sensory perception, and / or

[0332] - a value for a class of flavour or aroma ingredients in a flavour or aroma ingredient classification represented by a perception of a human emotion or sensory perception of at least one determined human emotion or sensory response, and

[0333] - providing step 525 of providing, on the computer interface, at least one value obtained in the operating step for the input physical component digital identifier.

[0334] Figure 3 Particular implementations of devices, interfaces, and computing devices are disclosed.

[0335] Figure 6 The specific step sequence of the method 700 object of the present invention is schematically represented. Such a specific step sequence uses example data, which may include, for example:

[0336] - at least one flavour or fragrance physical ingredient digital representation identifier, said at least one flavour or fragrance physical ingredient digital representation identifier forming a physical composition digital identifier, said physical composition digital identifier optionally being associated with the physical composition digital identifier, and

[0337] - a perceived human response associated with at least one physical component digital identifier of the example set.

[0338] In a more advanced implementation, the example data set may also include:

[0339] - at least one solvent digital identifier associated with the physical composition digital identifier,

[0340] - at least one dosage digital identifier associated with the physical component digital identifier,

[0341] - at least one pH value of the composition digital identifier associated with the physical composition digital identifier,

[0342] - at least one citral concentration digital identifier associated with the physical composition digital identifier,

[0343] - at least one expiration date of the product digital identifier associated with the physical component digital identifier and / or

[0344] - at least one complete sensory data of a constituent digital identifier associated with the physical constituent digital identifier.

[0345] Such example data may be obtained by assembling physical composition digital identifiers of ingredients, presenting said physical composition digital identifiers to human users, and recording the responses of these users in a database. These records may be categorized by response type (e.g., "like," "dislike," "smile," "walk away"). Such categorization may be performed manually, by associating a label with each response, or automatically by a computing system configured to process text, audio, photo, or video records, thereby determining the response type in a list of possible response types. These response types may be associated with a response digital identifier, which may then be used in the example data set.

[0346] The example data may then be input 705 into a gradient boosted tree apparatus, which may then be operated 710 to train a trained gradient boosted tree model 305 obtained as an output 715 of a training step 710 of training the gradient boosted tree model.

[0347] The purpose of such an example is to predict a value representing a reaction associated with a particular association of ingredients forming a physical component digital identifier, while Figures 1 to 5 An example of predicting the relative value of a reaction associated with a particular association of components that form a physical component digital identifier (i.e., a particular physical component digital identifier is more likely to trigger a particular emotion or sense in the user than another physical component digital identifier).

[0348] In a specific embodiment, the method object of the present invention includes, after the operating step of operating the trained gradient boosting tree device set, a determining step of determining, by a computing device, a numerical value representing a reaction effect of at least one input flavor or fragrance component, and a providing step of providing the determined reaction effect numerical value on a computer interface.

[0349] Figure 7 Such an embodiment is shown, Figure 7 The embodiment of the method 800 object of the present invention is schematically shown. The flavor or fragrance prediction system 800 for predicting the impact of human response includes:

[0350] - at least two inputs 805, comprising at least two digital representation identifiers of physical components of flavor or aroma, the resulting inputs 805 corresponding to the digital representation identifiers of physical components of flavor or aroma, each input 805 comprising a different set of digital representation identifiers of physical components of flavor or aroma,

[0351] -according to Figure 6 at least one gradient boosting tree device set 810 of the method shown, wherein the input 805 physical component digital identifiers are input into a single gradient boosting tree device set 810, the gradient boosting tree device set 810 being configured to provide a prediction for each input 805 physical component digital identifier, and

[0352] - Its predicted output 815 of the impact of each flavor or aroma physical ingredient digital representation identifier as a function of the prediction of the decision tree neural network device 810.

[0353] Such a prediction output 815 may be obtained by making a relative comparison of the human response prediction outputs for each physical component digital identifier and associating an impact score with each component based on the component components of the physical component digital identifier.

[0354] Figure 8 A block diagram of an example computer system 900 is shown that can be used to implement embodiments of the present invention. Figure 8 In the example of FIG. 1 , a computer system 905 and instructions for implementing the disclosed techniques in hardware, software, or a combination of hardware and software are represented in a schematic manner, such as by boxes and circles, with the same level of detail that ordinary technicians in the field of the present disclosure typically use to communicate computer architecture and computer system implementation.

[0355] The computer system 905 includes an input / output (IO) subsystem 920, which may include a bus and / or other communication mechanism for transferring information and / or instructions between components of the computer system 905 via electronic signal paths. The I / O subsystem 920 may include an I / O controller, a memory controller, and at least one I / O port. The electronic signal paths are schematically represented in the figure, for example, by lines, unidirectional arrows, or bidirectional arrows.

[0356] At least one hardware processor 910 is coupled to the I / O subsystem 920 for processing information and instructions. The hardware processor 910 may include, for example, a general purpose microprocessor or microcontroller and / or a dedicated microprocessor, such as an embedded system or a graphics processing unit (GPU) or a digital signal processor or an ARM processor. The processor 910 may include an integrated arithmetic logic unit (ALU) or may be coupled to a separate ALU.

[0357] The computer system 905 includes one or more memory units 925, such as a main memory, which is connected to the I / O subsystem 920 for electronically digitally storing data and instructions to be executed by the processor 910. The memory 925 may include volatile memory, such as various forms of random access memory (RAM) or other dynamic storage devices. The memory 925 may also be used to store temporary variables or other intermediate information during the execution of instructions executed by the processor 910. When these instructions are stored in a non-temporary computer-readable storage medium accessible to the processor 910, they can turn the computer system 905 into a special-purpose machine that is customized to perform the operations specified in the instructions.

[0358] The computer system 905 also includes non-volatile memory, such as a read-only memory (ROM) 930 or other static storage device coupled to the I / O subsystem 920, for storing information and instructions for the processor 910. The ROM 930 may include various forms of programmable ROM (PROM), such as an erasable PROM (EPROM) or an electronically erasable PROM (EEPROM). The units of the persistent memory 915 may include various forms of non-volatile RAM (NVRAM), such as FLASH memory, solid-state memory, magnetic disks or optical disks, such as CD-ROMs or DVD-ROMs, and may be coupled to the I / O subsystem 920 to store information and instructions. The memory 915 is an example of a non-transitory computer-readable medium that may be used to store instructions and data that, when executed by the processor 910, result in the execution of a computer-implemented method to perform the techniques herein.

[0359] The instructions in the memory 925, ROM 930 or memory 915 may include one or more groups of instructions organized as modules, methods, objects, functions, routines or calls. These instructions may be organized as one or more computer programs, operating system services or applications including mobile applications. These instructions may include: operating system and / or system software; one or more libraries for supporting multimedia, programming or other functions; data protocol instructions or stacks for implementing TCP / IP, HTTP or other communication protocols; file format processing instructions for parsing or presenting files encoded using HTML, XML, JPEG, MPEG or PNG; user interface instructions for presenting or interpreting commands for graphical user interfaces (GUIs), command line interfaces or text user interfaces; application software, such as office suites, Internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games or miscellaneous applications. These instructions may implement a Web server, a Web application server or a Web client. The instructions may be organized into a presentation layer, an application layer and a data storage layer, such as a relational database system, object storage, a graph database, a flat file system or other data storage using structured query language (SQL) or non-SQL.

[0360] The computer system 905 can be connected to at least one output device 935 through the I / O subsystem 920. In one embodiment, the output device 935 is a digital computer display or a human-machine interface. Examples of displays that can be used for various embodiments include a touch screen display or a light emitting diode (LED) display or a liquid crystal display (LCD) or an electronic paper display. The computer system 905 may include other types of output devices 935 as a substitute or supplement for a display device. Examples of other output devices 935 include a printer, a ticket printer, a plotter, a projector, a sound card or a video card, a speaker, a buzzer or a piezoelectric device or other sound device, a lamp or an LED or LCD indicator, a tactile device, an actuator or a servo device.

[0361] At least one input device 940 is coupled to I / O subsystem 920 for communicating signals, data, command selections, or gestures to processor 910. Examples of input device 940 include touch screens, microphones, still and video digital cameras, alphanumeric and other keys, keypads, keyboards, graphics tablets, image scanners, joysticks, clocks, switches, buttons, dials, and sliders.

[0362] Another input device is a control device 945, which can perform cursor control or other automatic control functions, such as navigating in a graphical interface on a display screen, as an alternative or supplement to the input function. The control device 945 can be a touch pad, a mouse, a trackball, or a cursor direction key, which is used to convey direction information and command selections to the processor 910 and control the cursor movement on the display 935. The input device can have at least two degrees of freedom on two axes, a first axis (e.g., x) and a second axis (e.g., y), allowing the device to specify a position in a plane. Another input device is a wired, wireless, or optical control device, such as a joystick, a stick, a console, a steering wheel, a pedal, a gearshift mechanism, or other types of control devices. The input device 940 may include a combination of multiple different input devices, such as a camera and a depth sensor.

[0363] In another embodiment, the computer system 905 may include an Internet of Things (IoT) device in which one or more of the output device 935, the input device 940, and the control device 945 are omitted. Alternatively, in such an embodiment, the input device 940 may include one or more cameras, motion detectors, thermometers, microphones, earthquake detectors, other sensors or detectors, measurement devices, or encoders, and the output device 935 may include a dedicated display (e.g., a single-line LED or LCD display), one or more indicators, display panels, meters, valves, solenoids, actuators, or servo devices.

[0364] The computer system 905 may implement the techniques described herein using custom hardwired logic, at least one ASIC or FPGA, firmware, and / or program instructions or logic that, when loaded and used or executed in conjunction with a computer system, cause or program the computer system to operate as a special purpose machine. According to one embodiment, the techniques herein are performed by the computer system 905 in response to the processor 910 executing at least one sequence of at least one instruction contained in the main memory 925. Such instructions may be read into the main memory 925 from another storage medium (e.g., the memory 915). Executing the sequence of instructions contained in the main memory 925 causes the processor 910 to perform the processing steps described herein. In alternative embodiments, hardwired circuits may be used in place of or in conjunction with software instructions.

[0365] The term "storage medium" as used herein refers to any non-temporary medium that stores data and / or instructions that cause a machine to operate in a particular manner. Such storage media may include non-volatile media and / or volatile media. Non-volatile media include, for example, optical or magnetic disks, such as memory 915. Volatile media include dynamic memory, such as memory 925. Common forms of storage media include, for example, hard disks, solid-state drives, flash drives, magnetic data storage media, any optical or physical data storage media, memory chips, etc.

[0366] Storage media are distinct from transmission media, but may be used in conjunction with transmission media. Transmission media participate in the transmission of information between storage media. For example, transmission media include coaxial cables, copper wires, and optical fibers, including the wires that make up the I / O subsystem 920 bus. Transmission media may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0367] Various forms of media may be used to transmit at least one sequence of at least one instruction to the processor 910 for execution. For example, the instructions may initially be transmitted to a disk or solid-state drive of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a communication link (e.g., an optical fiber or coaxial cable or a telephone line) using a modem. A modem or router local to the computer system 905 may receive the data on the communication link and convert the data into a format that the computer system 905 can read. For example, a receiver (e.g., a radio frequency antenna or an infrared detector) may receive the data carried in a wireless or optical signal, and appropriate circuitry may provide the data to the I / O subsystem 920, such as placing the data on a bus. The I / O subsystem 920 transmits the data to the memory 925, from which the processor 910 retrieves and executes the instructions. The instructions received by the memory 925 may optionally be stored on the memory 915 before or after execution by the processor 910.

[0368] The computer system 905 also includes a communication interface 960 coupled to the bus 920. The communication interface 960 provides two-way data communication coupled to a network link 965, which is directly or indirectly connected to at least one communication network, such as a network 970 or a public or private cloud on the Internet. For example, the communication interface 960 can be an Ethernet network interface, an integrated services digital network (ISDN) card, a cable modem, a satellite modem, or a modem, thereby providing a data communication connection with a corresponding type of communication line, such as an Ethernet cable or any type of metal cable or fiber optic line or telephone line. The network 970 broadly represents a local area network (LAN), a wide area network (WAN), a campus network, the Internet, or any combination thereof. The communication interface 960 can include a LAN card, thereby providing a data communication connection with a compatible LAN, or a wired cellular radiotelephone interface, thereby sending or receiving cellular data according to a cellular radiotelephone wireless network standard, or a wired satellite wireless interface, thereby sending or receiving digital data according to a satellite wireless network standard. In any such implementation, the communication interface 960 sends and receives electrical, electromagnetic, or optical signals through signal paths that carry digital data streams representing various types of information.

[0369] The network link 965 typically provides electrical, electromagnetic or optical data communication to other data devices directly or through at least one network using, for example, satellite, cellular, Wi-Fi or Bluetooth technology. For example, the network link 965 can provide a connection to the host 950 through the network 970.

[0370] In addition, network link 965 can provide connection through network 970, or provide connection to other computing devices through network interconnection equipment and / or computers operated by Internet Service Provider (ISP) 975. ISP 975 provides data communication services through a global packet data communication network represented as Internet 980. Server computer 955 can be connected to Internet 980. Server 955 broadly represents any computer, data center, virtual machine or virtual computing instance with or without a virtual machine hypervisor, or a computer executing a containerized program system (such as DOCKER or Kubernetes). Server 955 can represent an electronic digital service implemented using multiple computers or instances, and accessed and used by transmitting Web service requests, uniform resource locator (URL) strings with parameters in HTTP payloads, API calls, application service calls or other service calls. Computer system 905 and server 955 can form elements of a distributed computing system, which includes other computers, processing clusters, server farms or other computer organizations that collaborate to perform tasks or execute applications or services. Server 955 may include one or more groups of instructions organized as modules, methods, objects, functions, routines, or calls. These instructions may be organized as one or more computer programs, operating system services, or applications including mobile applications. These instructions may include operating systems and / or system software; one or more libraries to support multimedia, programming, or other functions; data protocol instructions or stacks to implement TCP / IP, HTTP, or other communication protocols; file format processing instructions to parse or render files encoded using HTML, XML, JPEG, MPEG, or PNG; user interface instructions to render or interpret commands for a graphical user interface (GUI), command line interface, or text user interface; application software, such as an office suite, an Internet access application, a design and manufacturing application, a graphics application, an audio application, a software engineering application, an educational application, a game, or a miscellaneous application. Server 955 may include a web application server that hosts a presentation layer, an application layer, and a data storage layer, such as a relational database system using structured query language (SQL) or non-SQL, an object store, a graph database, a flat file system, or other data storage.

[0371] Computer system 905 may send messages and receive data and instructions, including program code, through the network, network link 965, and communications interface 960. In the Internet example, server 955 may transmit the requested code for an application program through Internet 980, ISP 975, local network 970, and communications interface 960. The received code may be executed by processor 910 as it is received, and / or stored in memory 915 or other non-volatile storage for later execution.

[0372] The execution of the instructions described in this section may implement a process in the form of an instance of an executing computer program, which consists of program code and its current activity. Depending on the operating system (OS), a process may consist of multiple threads of execution that execute instructions concurrently. In such a case, a computer program is a passive collection of instructions, and a process may be the actual execution of these instructions. Multiple processes may be associated with the same program; for example, opening multiple instances of the same program generally means that multiple processes are being executed. Multitasking may be implemented to allow multiple processes to share the processor 910. Although each processor 910 or core of a processor executes a single task at a time, the computer system 905 may be programmed to implement multitasking, thereby allowing each processor to switch between executing tasks without having to wait for each task to complete. In an embodiment, switching may be performed when a task performs an input / output operation, when a task indicates that it can be switched, or when a hardware interrupt occurs. Time sharing may be implemented to provide the appearance of executing multiple processes concurrently at the same time by quickly performing context switching, thereby allowing for fast response to interactive user applications. In one embodiment, for security and reliability, the operating system may prevent direct communication between independent processes, thereby providing a strictly mediated and controlled inter-process communication function.

Claims

1. A method (400) for determining an emotion or sensory perception associated with exposure to a flavor or fragrance component, characterized in that It includes: - an input step (405) of inputting at least two flavor or fragrance physical component digital representation identifiers on a computer interface, the resulting input corresponding to a physical composition digital identifier representing the physical composition of the physical flavor or fragrance component, - an operation step (410) of operating instructions by a computing device configured to associate an input of a physical component digital identifier with at least one value representing: - a relative ranking of the input digital representation of the physical component of the flavor or aroma with respect to at least one determined perceived emotion or sense, - a digital representation of an identifier for at least one input flavor or aroma physical component, representing the perceived value of at least one determined perceived emotion or sensory organ, and / or - a value representing a class of flavor or aroma components in a classification of flavor or aroma components by perceiving at least one determined emotion or sensory perception through a perceived emotion or sensory organ, and - a providing step (415) of providing, on a computer interface, at least one value obtained in the operating step for the input physical component digital identifier.

2. The method (400) of claim 1, wherein: The operation step (410) is configured to operate the trained gradient boosting decision tree device after inputting the physical component digital identifier.

3. The method (400) according to claim 2, comprising: - providing a step (105) of providing an example data set to a gradient boosting decision tree device or a neural network device, comprising: - at least two digital identifiers of the physical components of the aroma or flavor formed by digital representation identifiers of at least two physical components of the aroma or flavor, and - at least one emotional or sensory perception value corresponding to at least two of said aroma or flavor components, said emotional or sensory perception value being associated with at least one emotional or sensory perception digital identifier, said emotional or sensory perception digital identifier representing a type of emotional or sensory response of a human being to a materialized physical component digital identifier from a finite list of emotional or sensory responses, - an operation step (110) of operating a gradient boosting decision tree device or a neural network device based on the example data set, and - An obtaining step (115) of obtaining a trained gradient boosting decision tree model or a trained neural network model.

4. The method (400) of claim 3, wherein: The example data also includes at least one digital identifier associated with the at least one physical component digital identifier, the at least one digital identifier representing the following: - contact with the sex of human beings in the materialized physical components (103), - the nationality of the human being who came into contact with the materialized physical composition (104), - the type of use of the physical composition (106), - a chemical matrix (107) for supporting the composition of the physical composition, and / or - a dosage (108) of at least one physical ingredient flavour or fragrance physical ingredient represented by a corresponding digital representation identifier.

5. The method (400) according to any one of claims 2 to 4 comprises, after the operation step (410), a determination step (420), which determines, by means of a computing device, a numerical value representing the emotional or sensory response impact of at least one input flavor or aroma component; and a providing step (415), which provides the determined response impact numerical value on a computer interface.

6. The method (400) according to claim 5 comprises, after the determination step (420) of determining the numerical value representing the affective or sensory response impact, a providing step (435), which provides at least one alternative flavor or aroma physical ingredient digital representation identifier for at least one input flavor or aroma physical ingredient digital representation identifier, thereby forming an alternative physical composition digital identifier, which is a function of the value representing the affective or sensory response impact associated with the input and the alternative flavor or aroma physical ingredient digital representation identifier.

7. The method (400) of claim 6, wherein: The providing step (435) of providing at least one alternative aroma or flavor physical ingredient digital representation identifier is configured to also provide at least one value representing the concentration of at least one of said alternative aroma or flavor physical ingredient digital representation identifiers.

8. The method (400) according to any one of claims 6 or 7, wherein: The providing step (435) of providing at least one alternative flavor or aroma physical ingredient digital representation identifier is configured to also provide a minimum value and / or a maximum value representing the concentration of at least one of the alternative flavor or aroma physical ingredient digital representation identifiers.

9. The method (400) according to any one of claims 1 to 8, comprising an assembling step (430), which assembles a physical composition corresponding to the input physical composition digital identifier or provides the input physical composition digital identifier to a system configured to assemble the physical composition.

10. The method (400) according to any one of claims 1 to 9, comprising: - an assembling step (401) of assembling a database associating at least one set of at least two identifiers of digital representations of physical ingredients of flavours or fragrances with values ​​representing measured human emotions or sensory perceptions, and - A determination step (407) of determining, by the computing device, a set of instructions to be operated during this operation step (410).

11. The method (400) of claim 10, wherein: The assembling step (401) of assembling a database includes: - a contacting step (402) of contacting at least one human being with the physical composition of the flavor or fragrance physical component, - a measuring step (403) of measuring an emotion or sensory perception of at least one human being in contact with the physical composition, and - A recording step (404) of recording in a database a value representative of the perceived emotion or sensory organ measured, associated with a set of digital representation identifiers of the flavor or fragrance physical ingredients representative of the physical ingredients of the composition used during the contacting step.

12. The method (400) according to any one of claims 1 to 11, comprising a replacement step (406) of replacing the input flavor or aroma physical ingredient digital representation identifier with a different and equivalent flavor or aroma physical ingredient digital representation identifier, the equivalence being defined in a database of equivalent flavor or aroma physical ingredient digital representation identifiers.

13. The method (400) according to any one of claims 1 to 12, wherein: The operation step (410) includes: a first associating step (411) of associating, by means of a computing device, at least one olfactory or taste descriptor with at least one input digital representation identifier of a flavor or fragrance physical ingredient, and A second associating step (412) is performed by a computing device to associate at least one perceived emotion or sensory perception as a function of at least one olfactory or taste descriptor associated with at least one input flavor or fragrance physical component digital representation identifier.

14. The method (400) according to any one of claims 1 to 13, wherein: At least one affective or sensory perception represents a perception of a health or hygiene benefit associated with contact with the physical composition.

15. A system (500) for determining an emotion or sensory perception associated with exposure to a flavor or fragrance component, characterized in that It includes: - an input step (505) of inputting at least two flavor or fragrance physical component digital representation identifiers on a computer interface (510), the resulting input corresponding to a physical composition digital identifier representing the physical composition of the physical flavor or fragrance component, - an operation step (515) of operating instructions by a computing device (520) configured to associate the input of the physical component digital identifier with at least one value representing: - a relative ranking of the input digital representation of the physical component of the flavor or aroma with respect to at least one determined perceived emotion or sense, - a digital representation of an identifier for at least one input flavor or aroma physical component, representing the perceived value of at least one determined perceived emotion or sensory organ, and / or - a value representing a class of flavor or aroma components in a classification of flavor or aroma components by perceiving at least one determined emotion or sensory perception through a perceived emotion or sensory organ, and - a providing step (525) of providing, on a computer interface, at least one value obtained during the operating step for the input physical component digital identifier.

Images