Method and system for predicting stability values ​​of a determined fragrance in a determined fragrance base

Abstract

1. A method (100) for predicting a stability value of a determined fragrance in a determined fragrance base, comprising: - inputting (105) on a computer interface at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a fragrance ingredient composition; - inputting (110) on a computer interface a fragrance base digital identifier representing the material fragrance base; - determining (115) by the computer device a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing (120) on a computer interface a value representative of the determined stability value.

Description

[Technical Field]

[0001] The present invention is directed to a method for predicting the stability value of a determined fragrance in a determined fragrance base, and a system for predicting the stability value of a determined fragrance in a determined fragrance base.

[0002] The invention has particular application in the fragrance design and manufacturing industry. [Background technology]

[0003] The approaches described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued, and thus, unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section.

[0004] In the fragrance design and manufacturing industry, one of the key industrial challenges is providing fragrances that contribute to the commercial success of a product. Examples of such products include hair care products and luxury perfumes. These products are consumables and are typically consumed over a significant period of time. For example, shampoo may be consumed over several weeks, while perfume may be consumed over several months. Therefore, one of the key metrics when designing a fragrance product is stability or robustness, which can refer to, for example, the colorimetric, solubility, or olfactory stability of the product over time. For example, toothpaste must maintain a specific color to satisfy its user, and perfume must not change odor over time.

[0005] Such stability is influenced by the selection of the particular fragrance component as well as the selection of the product base, which conceptually corresponds to the chemical substrate that is scented by interaction with the fragrance component composition. The base may correspond, for example, to the chemical formula that forms the active portion of a toothpaste.

[0006] Conventionally, prior to mass commercialization of a product, a prototype of the product is constructed and analyzed to provide a quantitative assessment of, for example, the colorimetric, solubility, or olfactory stability of the product.

[0007] Such an approach is costly both in terms of time required and corresponding financial expenditure. Moreover, such an approach may produce inconsistent results due to limited sample sizes. The end result of such trial-and-error based approaches is the need to carry out significant reformulation of the product base or fragrance composition. Typically, such reformulation may be carried out independently on the base composition and fragrance composition without knowledge of the specific stability effects leading to the reformulation.

[0008] For these reasons, current methods are inadequate to reliably and proactively assess product stability, thus limiting the quality and timeliness of product development. Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention aims to address all or some of these drawbacks. [Means for solving the problem]

[0010] All embodiments disclosed and claimed herein relate to computer-implemented program processes that interact with digital data to provide a practical application of computer technology to the problem of providing accurate stability predictions that can be used to design and manufacture stable fragranced products (chemical compositions). This disclosure is not intended to encompass techniques for organizing human activities, performing mental processes, or implementing mathematical concepts, and any interpretation of the claims to encompass such techniques would be unreasonable based on this disclosure as a whole.

[0011] According to a first aspect, the present invention provides a method for predicting the stability value of a determined fragrance in a determined fragrance base, comprising: - inputting, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients; - inputting, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining, by a computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing, on a computer interface, a value representative of the determined stability value.

[0012] Such measures allow for the prediction of product stability, thus improving the speed and ability to design and manufacture the product.

[0013] In an optional embodiment, the subject method of the present invention includes the step of inputting, on a computer interface, a fragrance application digital identifier representative of the use of the input fragrance and the input base.

[0014] Such embodiments further improve the quality of the predictions by modeling the effects of the application or intended use of the product. Indeed, depending on the application, environmental influences (in terms of the medium, or the light intensity of the typical storage of the product) will affect the stability of the product.

[0015] In an optional embodiment, the determining step includes operating a trained classifier machine learning device, wherein the input composition and the input fragrance base are used as inputs of the classifier machine learning model, and the output is a stability class identifier representing the stability of the input composition in the input fragrance base.

[0016] Such embodiments allow for the determination of product stability based on the fragrance composition, base, and optionally application value.

[0017] In an optional embodiment, the method of the present invention comprises, upstream of the step of operating the trained classifier machine learning device, providing a set of example data to a classifier machine learning device, composition digital identifiers, each composition digital identifier being associated with a fragrance ingredient digital identifier; - for at least a portion of the exemplary composition digital identifiers, a fragrance-based digital identifier; - for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the stability of the exemplary composition; -operating a classifier machine learning device based on a set of example data; obtaining a trained classifier machine learning device.

[0018] Such embodiments allow for the determination of product stability based on the fragrance composition, base, and optionally application value.

[0019] In an optional embodiment, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing a duration since assembly of the bond.

[0020] Such embodiments allow for the determination of product stability, including modeling the effects of the product's age since manufacture.

[0021] In an optional embodiment, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the concentration of the composition in the base of that bond.

[0022] Such embodiments allow for determination of product stability, including modeling the effect of the concentration of fragrance compositions in the base of the product.

[0023] In an optional embodiment, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the application of the bond.

[0024] Such embodiments allow for determination of product stability, including modeling the effects of product application.

[0025] In an optional embodiment, the trained classifier machine learning model is a classifier gradient boosting decision tree device.

[0026] In an optional embodiment, the subject method of the present invention comprises, downstream of the step of operating the trained gradient boosting decision tree device, a step of determining, by a computer device, a numerical value representing a stability impact for at least one input fragrance ingredient digital identifier, and a step of providing the determined stability impact numerical value on a computer interface.

[0027] Such an embodiment allows for the isolation of fragrance ingredients with the best or worst stability to be performed.

[0028] In an optional embodiment, the method in question of the present invention comprises, downstream of the step of determining the numerical value representing the stability impact, a step of providing at least one alternative fragrance ingredient digital identifier for at least one fragrance ingredient digital identifier input and forming a composition in response to the numerical value representing the stability impact of that input and of that alternative fragrance ingredient digital identifier.

[0029] Such embodiments allow for dynamic reformulation of the fragrance composition to enhance the stability of the composition.

[0030] In an optional embodiment, the step of providing at least one alternative fragrance ingredient digital identifier is further configured to provide at least one value representative of a concentration of the at least one alternative fragrance ingredient digital identifier.

[0031] In an optional embodiment, the step of providing at least one alternative fragrance ingredient digital identifier is configured to further provide a minimum value and / or a maximum value representing the concentration of the at least one alternative fragrance ingredient digital identifier.

[0032] In an optional embodiment, the subject method of the present invention includes the step of physically assembling the input composition in an input fragrance base.

[0033] Such measures allow the materialization of the composition and base into the final product.

[0034] In an optional embodiment, the method of the present invention comprises: - constructing a database of fragrance ingredient digital identifiers, in which physical fragrance ingredients are associated with fragrance ingredient digital identifiers according to a one-to-one relationship; and / or - configuring a database of fragrance-based digital identifiers, wherein physical base components are associated with fragrance-based digital identifiers according to a one-to-one relationship; At least one of the databases is used during the input step.

[0035] Such measures allow the definition of a realistic and accurate database representing physical or material items such as bases or ingredients.

[0036] According to a second aspect, the present invention provides a system for predicting a stability value for a determined fragrance in a determined fragrance base, comprising: - one or more computer systems comprising one or more hardware processors and storage media; - instructions stored on a storage medium, which instructions, when executed by a computer system, cause the computer system to: - inputting, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients; - inputting, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining, by a computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing, on a computer interface, a value representative of the determined stability value; to carry out the order and A system comprising:

[0037] Such a measure provides similar benefits to those of the first aspect of the invention.

[0038] Other advantages, objects and particular features of the present invention will become apparent from the following non-exhaustive description of at least one particular embodiment of the method or system that is the subject of the invention, taken in conjunction with the accompanying drawings. [Brief explanation of the drawings]

[0039] [Figure 1] 1 is a schematic representation of a first particular sequence of steps of the method that is the subject of the present invention; FIG. [Figure 2] 1 is a schematic diagram of a particular embodiment of the system that is the subject of the present invention; [Figure 3] FIG. 2 is a schematic representation of a second particular sequence of steps of the method that is the subject of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0040] This description is not exhaustive, as each feature of one embodiment may be advantageously combined with any other feature of any other embodiment.

[0041] Various inventive concepts may be embodied as one or more methods, examples of which are provided. The actions performed as part of a method may be ordered in any suitable manner. Thus, while shown as sequential actions in the exemplary embodiments, embodiments may be constructed in which actions are performed in an order different from that illustrated, which may include performing some actions simultaneously.

[0042] The indefinite articles "a" and "an," as used in the specification and claims, unless expressly indicated otherwise, should be understood to mean "at least one."

[0043] The term "and / or," as used in the specification and claims, should be understood to mean "either or both" of the elements so conjoined, i.e., elements present conjunctively in some cases and disjunctively in other cases. Multiple elements listed with "and / or" should be construed in the same manner, i.e., "one or more" of the elements so conjoined. Other elements, whether related or unrelated to those elements specifically identified, may optionally be present other than the elements specifically identified by the "and / or" clause. Thus, as a non-limiting example, a reference to "A and / or B," when used in conjunction with open-ended language such as "comprising," can refer in one embodiment to A only (optionally including elements other than B); in another embodiment, to B only (optionally including elements other than A); in yet another embodiment, to both A and B (optionally including other elements), etc.

[0044] As used in this specification and the claims, "or" should be understood to have the same meaning as "and / or" as defined above. For example, when separating items in a list, "or" or "and / or" shall be interpreted as inclusive, i.e., including at least one of, but also including more than one of, several elements or a list of elements, and optionally including additional unlisted items. Only terms clearly indicated to the contrary, such as "only one of" or "exactly one of," or, when used in the claims, "consisting of," shall refer to the inclusion of exactly one element of several elements or a list of elements. In general, as used herein, the term "or," when used in the claims, when preceded by terms of exclusivity, such as "either," "one of," "only one of," "exactly one of," "consisting essentially of," shall be interpreted only as indicating exclusive alternatives (i.e., "one or the other, but not both") and shall have its ordinary meaning as used in the field of patent law.

[0045] As used in this specification and claims, the phrase "at least one," when referring to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed in the list of elements, and not excluding any combinations of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to those 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") can refer in one embodiment to at least one A, optionally including more than one, with no B (and optionally including elements other than B); in another embodiment to at least one B, optionally including more than one, with no A (and optionally including elements other than A); in yet another embodiment to at least one A, optionally including more than one, and at least one B (and optionally including other elements), optionally including more than one, etc.

[0046] In the claims and the above specification, all transitional phrases such as "comprising," "including," "carrying," "having," "containing," "involving," "holding," "composed of," and the like, are to be understood to be open-ended, i.e., to mean including, but not limited to. Only the transitional phrases "consisting of" and "consisting essentially of," respectively, shall be closed or semi-closed transitional phrases.

[0047] At this point, please note that the drawings are not to scale.

[0048] As used herein, the term "ingredient" refers to a perfuming ingredient, flavor ingredient, perfume carrier, flavor carrier, perfume adjuvant, flavor adjuvant, perfume modulator, or flavor modulator. Preferably, such fragrances or fragrance compounds are volatile. Such ingredients may be natural ingredients. Ingredient is intended to mean an ingredient selected for its contribution to a designed flavor or fragrance. Such ingredients may be defined by a CAS ("Chemical Abstracts Service") number.

[0049] By "perfuming ingredient" herein is meant a compound used in a perfume preparation or composition to impart a hedonic effect. In other words, for such an ingredient to be considered perfuming, one skilled in the art must recognize that it not only has an odor, but can also impart or modify the odor of the composition in a positive or pleasant way.

[0050] The nature and type of fragrance ingredients do not warrant a more detailed description herein, and are in any case not exhaustive; those skilled in the art can select them based on their general knowledge and according to the intended use or application and the desired organoleptic effect. Generally speaking, these fragrance ingredients belong to various chemical classes, such as alcohols, lactones, aldehydes, ketones, esters, ethers, acetates, nitriles, terpenoids, nitrogen- or sulfur-containing heterocyclic compounds, and essential oils, and the fragrance ingredients can be of natural or synthetic origin. In each case, the fragrance ingredients are listed in references such as S. Arctander, Perfume and Flavor Chemicals, 1969, Montclair, New Jersey, USA, or its recent versions, or other works of a similar nature, as well as in the abundant patent literature in the field of perfumery. It is also understood that the fragrance ingredients may be compounds known to release various types of fragrance ingredients in a controlled manner, also known as pro-perfumes or pro-fragrances.

[0051] By "perfume carrier" is meant herein a material that is substantially neutral from the perfume point of view, i.e. a material that does not significantly modify the organoleptic properties of the perfuming ingredients. The carrier may be liquid or solid.

[0052] As liquid carriers, non-limiting examples include emulsifying systems, i.e., solvents and surfactant systems, or solvents commonly used in perfumery.A detailed description of the nature and type of solvents commonly used in perfumery cannot be exhaustive.However, non-limiting examples include the most commonly used solvents such as butylene glycol or propylene glycol, glycerol, dipropylene glycol and its monoethers, 1,2,3-propanetriyl triacetate, dimethyl glutarate, dimethyl adipate 1,3-diacetyloxypropan-2-yl acetate, diethyl phthalate, isopropyl myristate, benzyl benzoate, benzyl alcohol, 2-(2-ethoxyethoxy)-1-ethanol, triethyl citrate, or mixtures thereof. In the case of compositions comprising both a perfume carrier and a perfume base, other suitable perfume carriers than those specified above may include ethanol, water / ethanol mixtures, limonene or other terpenes, isoparaffins such as those known under the trademark Isopar® (manufacturer: Exxon Chemical), or glycol ethers and glycol ether esters such as those known under the trademark Dowanol® (manufacturer: Dow Chemical Company), or hydrogenated castor oil such as those known under the trademark Cremophor® RH 40 (manufacturer: BASF).

[0053] Solid carrier refers to a material that can be chemically or physically bonded to a fragrance composition or some components of the fragrance composition.Generally, such solid carriers are used to stabilize the composition or to control the evaporation rate of the composition or some components.The use of solid carriers is currently used in the art, and those skilled in the art know how to achieve the desired effect.However, non-limiting examples of solid carriers can include absorbent gums or polymers or inorganic materials, such as porous polymers, cyclodextrins, wood-based materials, organic or inorganic gels, clays, gypsum talc, or zeolites.

[0054] Other non-limiting examples of solid carriers can include encapsulating materials.Examples of such materials can include wall-forming and plasticizing materials such as monosaccharides, disaccharides or trisaccharides, natural or modified starch, hydrocolloids, cellulose derivatives, polyvinyl acetate, polyvinyl alcohol, protein or pectin, or the materials cited in references such as H. Scherz, Hydrokolloides: Stabilisatoren, Dickungs-und Geliermittel in Lebensmitteln, Band 2 der Schriftenreihe Lebensmittelchemie, Lebensmittelqualitat, Behr's Verlag GmbH & Co., Hamburg, 1996.Encapsulation is a process well known to those skilled in the art, and can be carried out by using techniques such as spray drying, coagulation or even extrusion, or can be comprised of coating encapsulation, including coacervation and complex coacervation techniques.

[0055] Non-limiting examples of solid carriers include core-shell capsules with aminoplast, polyamide, polyester, polyurea or polyurethane type resins, or mixtures thereof (all of which are well known to those skilled in the art), using techniques such as phase separation processes induced by polymerization, interfacial polymerization, coacervation or all of which are described in the prior art, optionally in the presence of polymeric stabilizers or cationic copolymers.

[0056] Resins can be produced by polycondensation of aldehydes (e.g., formaldehyde, 2,2-dimethoxyethanal, glyoxal, glyoxylic acid, or glycolaldehyde, and mixtures thereof) with amines such as urea, benzoguanamine, glycoluril, melamine, methylolmelamine, methylated methylolmelamine, guanazole, and mixtures thereof. Alternatively, preformed resins, such as alkylolated polyamines, can be used, such as those commercially available under the trademarks Urac® (manufactured by Cytec Technology Corp.), Cymel® (manufactured by Cytec Technology Corp.), Urecoll®, or Luracoll® (manufactured by BASF).

[0057] Other resins are produced by polycondensation of a polyol such as glycerol and a polyisocyanate, for example the trimer of hexamethylene diisocyanate, the trimer of isophorone diisocyanate or xylylene diisocyanate, or the biuret of hexamethylene diisocyanate, or the trimer of xylylene diisocyanate with trimethylolpropane (known under the trade name Takenate®, manufactured by Mitsui Chemicals, Inc.), among which the trimer of xylylene diisocyanate with trimethylolpropane and the biuret of hexamethylene diisocyanate are preferred.

[0058] Some of the leading literature on the encapsulation of perfumes by polycondensation of amino resins, i.e., melamine-based resins, with aldehydes, includes articles such as those published by K. Dietrich et al., Acta Polymerica, 1989, Vol. 40, pp. 243, 325, and 683, and 1990, Vol. 41, p. 91. Such articles already describe the various parameters affecting the preparation of such core-shell microcapsules, according to prior art methods that are further detailed and exemplified in the patent literature. U.S. Patent No. 4,396,670 to Wiggins Teape Group Limited is a relevant early example of the latter. Since then, many other authors have added to the literature in this field, and while it is impossible to cover all published developments here, a general knowledge of encapsulation technology is highly important. Recent relevant publications disclosing the suitable use of such microcapsules are represented, for example, by K. Bruyninckx and M. Dusselier, ACS Sustainable Chemistry & Engineering, 2019, vol. 7, pp. 8041-8054, by H.Y. Lee et al., Journal of Microencapsulation, 2002, vol. 19, pp. 559-569, by WO 01 / 41915, or further by S. Bone et al., Chimia, 2011, vol. 65, pp. 177-181.

[0059] By "perfume adjuvant" herein is meant an ingredient that may impart additional benefits such as color, specific lightfastness, chemical stability, etc. A detailed description of the nature and types of adjuvants commonly used in perfumed compositions cannot be exhaustive, but it must be mentioned that such ingredients are well known to those skilled in the art. Specific, non-limiting examples include viscosity agents (e.g., surfactants, thickeners, gelling and / or rheology modifiers), stabilizers (e.g., preservatives, antioxidants, heat / light and / or buffers or chelating agents, e.g., BHT), colorants (e.g., dyes and / or pigments), preservatives (e.g., antibacterial, antimicrobial, antifungal, or anti-irritant agents), abrasives, skin cooling agents, fixatives, insect repellents, ointments, vitamins, and mixtures thereof.

[0060] "Perfume modulator" is herein understood to be an agent capable of influencing the way in which the odor of a composition incorporating the modulator, particularly the evaporation rate and intensity, can be perceived by an observer or its user over time, compared to the same perception in the absence of the modulator. Perfume modulators are also known as fixatives. In particular, the modulators allow for an extended period of time for which a fragrance is perceived. Non-limiting examples of suitable modulators include methyl glucoside polyol; ethyl glucoside polyol; propyl glucoside polyol; isocetyl alcohol; PPG-3 myristyl ether; neopentyl glycol diethylhexanoate; sucrose laurate; sucrose dilaurate, sucrose myristate, sucrose palmitate, sucrose stearate, sucrose distearate, sucrose tristearate, hyaluronic acid disaccharide sodium salt, sodium hyaluronate, propylene glycol propyl ether; dicetyl ether; polyglycerin-4 ether. ether; Isoceteth-5; Isoceteth-7, Isoceteth-10; Isoceteth-12; Isoceteth-15; Isoceteth-20; Isoceteth-25; Isoceteth-30; Disodium Lauroamphodipropionate; Hexaethylene Glycol Monododecyl Ether; and mixtures thereof; Neopentyl Glycol Diisononanoate; Cetearyl Ethylhexanoate; Panthenol Ethyl Ether, DL-Panthenol, N-Hexadecyl n-nonanoate, Noctadecyl n-nonanoate, Pro-Fragrance, Cyclodextrin, encapsulated forms, and any combination thereof.

[0061] As used herein, the term "flavoring ingredient" refers to a compound used in a flavor preparation or composition to impart a hedonic effect. In other words, such ingredients are considered flavoring ingredients, and those skilled in the art should recognize that they are not simply flavorful, but can impart or modify the taste of the composition in a positive or pleasant way. The nature and type of flavoring ingredients present in the composition do not warrant a detailed description herein, and those skilled in the art can select them based on their general knowledge according to the intended use or application and the desired sensory effect. Generally speaking, these flavoring ingredients belong to various chemical classes, such as alcohols, aldehydes, ketones, esters, ethers, acetates, nitriles, terpenoids, nitrogen- or sulfur-containing heterocyclic compounds, and essential oils, and the flavoring ingredients can be of natural or synthetic origin. Many of these ingredients are in any case listed in references such as the book S. Arctander, Perfume and Flavor Chemicals, 1969, Montclair, New Jersey, USA, or its more recent versions, or other works of a similar nature, as well as the extensive patent literature in the field of flavors. It is also understood that the co-ingredient may also be a compound known to release in a controlled manner various types of flavoring compounds, also called proflavors.

[0062] The term "flavor carrier" refers to a material that is substantially neutral from a flavor standpoint, as long as it does not significantly alter the sensory properties of the flavoring ingredient. The carrier may be liquid or solid.

[0063] Suitable liquid carriers include, for example, emulsifying systems, i.e., solvents and surfactant systems, or solvents commonly used in flavorings.A detailed description of the nature and type of solvents commonly used in flavorings cannot be exhaustive.Suitable solvents used in flavorings include, for example, propylene glycol, triacetin, caprylic / capric triglyceride (Neobee®), triethyl citrate, benzyl alcohol, ethanol, isopropanol, citrus terpenes, vegetable oils such as linseed oil, sunflower oil or coconut oil, and glycerol.

[0064] Suitable solid carriers include, for example, absorbent gums or polymers, or even encapsulating materials. Examples of such materials may include wall-forming and plasticizing materials such as monosaccharides, disaccharides, or polysaccharides, natural or modified starches, hydrocolloids, cellulose derivatives, polyvinyl acetate, polyvinyl alcohol, xanthan gum, gum arabic, gum acacia, or materials cited in references such as H. Scherz, Hydrokolloid: Stabilisatoren, Dickungs-und Geliermittel in Lebensmitteln, Band 2 der Schriftenreihe Lebensmittelchemie, Lebensmittelqualitat, Behr's Verlag GmbH & Co., Hamburg, 1996. Encapsulation is a process well known to those skilled in the art and may be carried out using techniques such as spray drying, coagulation, extrusion, coating, plating, coacervation, etc.

[0065] By "flavor adjuvant" herein is meant an ingredient that may impart additional benefits such as color (e.g., caramel), chemical stability, etc. A detailed description of the nature and types of adjuvants commonly used in flavoring compositions cannot be exhaustive. Nevertheless, such adjuvants are well known to those skilled in the art, who may select them based on their general knowledge and according to the intended use or application. Specific, non-limiting examples include viscosity agents (e.g., emulsifiers, thickeners, gelling and / or rheology modifiers, such as pectin or agar gum), stabilizers (e.g., antioxidants, heat / light and / or buffering agents, such as citric acid), colorants (e.g., natural, synthetic, or natural extract colorants), preservatives (e.g., antibacterial or antimicrobial or antifungal agents, such as benzoic acid), vitamins, and mixtures thereof.

[0066] By "flavor modulator" herein is meant an ingredient that can enhance sweetness, block bitterness, enhance umami, reduce sour or licorice taste, enhance saltiness, enhance cooling effect, or any combination thereof. Flavor modulators are also called trigeminal sensitizers.

[0067] The term "composition" or formulation refers to a liquid, solid or aggregate of at least one volatile component.

[0068] As used herein, "aroma" refers to the olfactory perception resulting from the sum of the activation, enhancement, and inhibition (if present) of odorant receptors by at least one volatile component. Thus, by way of example and not intended to limit the scope of the present disclosure in any way, "aroma" results from the olfactory perception resulting from the sum of a first volatile component that activates odorant receptors associated with coconut tonalities, a second volatile component that activates odorant receptors associated with celery tonalities, and a third volatile component that inhibits odorant receptors associated with hay tonalities.

[0069] As used herein, the term "digital identifier" refers to any computerized representation, such as those used in computer databases, that represents a physical object, such as a flavoring ingredient. A digital identifier may refer to a label that represents the name, chemical structure, or internal reference of the flavoring ingredient.

[0070] As used herein, the term "embodied" is intended to exist outside the digital environment of the present invention. "Embodied" can mean, for example, readily found in nature or synthesized in a laboratory or chemical plant. In either case, an embodied composition exhibits tangible reality. The terms "compounded" or "compounding" refer to the act of materializing a composition, whether by extraction and assembly of components or by synthesis and assembly of components.

[0071] In the present invention, the term "stability" refers to a quantitative measurement of the change in the embodied composition in the base, for example, in terms of solubility, colorimetry, or olfactometry. This change may be measured at various time intervals. Such time intervals may vary depending on the application of the composition and group binding. In a simple embodiment, the stability value may be either true or false, meaning that the change measured for the composition in the base is below a predetermined efficacy threshold. In other embodiments, the stability value may be a numerical value representing the change measured for the composition in the base. Such a value may correspond, for example, to transparency or a chromatic distance value. Such a value may also correspond to a change in the perceived psychophysical intensity or a change in the hedonic experience of the composition. Such a value may also correspond, for example, to the physical solubility of the fragrance in the base, resulting in the formation of a separate phase or precipitate.

[0072] Thus, the methods and systems disclosed below comprise: - a method and system for predicting the colorimetric stability of a fragrance in a base; -methods and systems for predicting the olfactory stability of fragrances in bases; and / or - a method and system for predicting the dissolution stability of a fragrance in a base.

[0073] However, such stability criteria are not limiting when assessing the scope of the present invention.

[0074] The embodiments disclosed below are presented in a general manner.

[0075] Figure 2 depicts a block diagram illustrating an exemplary computer system in which embodiments may be implemented. In the example of Figure 2, computer system 205 and instructions for implementing the disclosed techniques in hardware, software, or a combination of hardware and software are represented schematically, e.g., as boxes and circles, at the same level of detail commonly used by those skilled in the art to which this disclosure pertains to communicate about computer architectures and computer system implementations.

[0076] Computer system 205 includes an input / output (IO) subsystem 220, which may include buses and / or other communication mechanisms for communicating information and / or instructions between components of computer system 205 via electronic signal paths. I / O subsystem 220 may include an I / O controller, a memory controller, and at least one I / O port. Electronic signal paths are represented schematically in the drawings, for example, as lines, single-headed arrows, or double-headed arrows.

[0077] At least one hardware processor 210 is coupled to I / O subsystem 220 for processing information and instructions. Hardware processor 210 may include, for example, a general-purpose microprocessor or microcontroller and / or an embedded system or a special-purpose microprocessor such as a graphics processing unit (GPU) or digital signal processor or ARM processor. Processor 210 may include an integrated arithmetic logic unit (ALU) or may be coupled to a separate ALU.

[0078] Computer system 205 includes one or more units of memory 225, such as main memory coupled to I / O subsystem 220, for electronically and digitally storing data and instructions to be executed by processor 210. Memory 225 may include volatile memory, such as various forms of random access memory (RAM), or other dynamic storage devices. Memory 225 may also be used to store temporary variables or other intermediate information during execution of instructions to be executed by processor 210. Such instructions, when stored on a non-transitory computer-readable storage medium accessible to processor 210, can turn computer system 205 into a special-purpose machine customized to perform the operations specified in the instructions.

[0079] The computer system 205 further includes non-volatile memory, such as read-only memory (ROM) 230 or other static storage device, coupled to the I / O subsystem 220 for storing information and instructions for the processor 210. The ROM 230 may include various forms of programmable ROM (PROM), such as erasable programmable read-only memory (EPROM) or electrically erasable programmable read-only memory (EEPROM). A unit of persistent storage 215, which may include various forms of non-volatile RAM (NVRAM), such as FLASH memory, or solid-state storage, magnetic disks, or optical disks, such as CD-ROMs or DVD-ROMs, may also be coupled to the I / O subsystem 220 for storing information and instructions. The storage 215 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 210, perform computer-implemented methods and cause the techniques herein to perform.

[0080] The instructions in memory 225, ROM 230, or storage 215 may include one or more sets of instructions organized as modules, methods, objects, functions, routines, or calls. The instructions may be organized as one or more computer programs, operating system services, or application programs, including mobile apps. The instructions may include operating system and / or system software; one or more libraries supporting multimedia, programming, or other functionality; data protocol instructions or stacks for implementing TCP / IP, HTTP, or other communications protocols; file formatting instructions for parsing or rendering files encoded using HTML, XML, JPEG, MPEG, or PNG; user interface instructions for rendering or interpreting commands for a graphical user interface (GUI), command line interface, or text user interface; application software such as an office suite, Internet access application, design and manufacturing application, graphics application, audio application, software engineering application, educational application, game, or other application. The instructions may implement a web server, web application server, or web client. The instructions may be organized as a presentation layer, an application layer, and a data storage layer such as a relational database system, object store, graph database, flat file system or other data storage that uses Structured Query Language (SQL) or does not use SQL.

[0081] The computer system 205 may be coupled to at least one output device 235 via the I / O subsystem 220. In one embodiment, the output device 235 is a digital computer display. Examples of displays that may be used in various embodiments include a touchscreen display or a light-emitting diode (LED) display or a liquid crystal display (LCD) or an electronic paper display. The computer system 205 may include other types of output devices 235 instead of or in addition to a display device. Examples of other output devices 235 include a printer, a ticket printer, a plotter, a projector, a sound or video card, a speaker, a buzzer or piezoelectric or other audible device, a lamp or LED or LCD indicator, a tactile device, an actuator, or a servo.

[0082] At least one input device 240 is coupled to the I / O subsystem 220 for communicating signals, data, command selections, or gestures to the processor 210. Examples of input device 240 include a touch screen, a microphone, a still and video digital camera, alphanumeric and other keys, a keypad, a keyboard, a graphics tablet, an image scanner, a joystick, a clock, a switch, a button, a dial, a slide.

[0083] Another type of input device is the control device 245, which may perform cursor control or other automatic control functions, such as navigation within a graphical interface on a display screen, instead of or in addition to input functions. The control device 245 may be a touchpad, mouse, trackball, or cursor direction keys for communicating directional information and command selections to the processor 210 and controlling cursor movement on the display 235. The input device may have at least two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allow the device to specify a position within a plane. Another type of input device is a wired, wireless, or optical control device, such as a joystick, wand, console, steering wheel, pedal, gear shift mechanism, or other type of control device. The input device 240 may include a combination of multiple different input devices, such as a video camera and a depth sensor.

[0084] In another embodiment, computer system 205 may comprise an Internet of Things (IoT) device that omits one or more of output device(s) 235, input device(s) 240, and control device(s) 245. Alternatively, in such an embodiment, input device(s) 240 may comprise one or more cameras, motion detectors, thermometers, microphones, seismic detectors, other sensors or detectors, measuring devices or encoders, and output device(s) 235 may comprise special-purpose display equipment such as a single-line LED or LCD display, one or more indicators, display panels, meters, valves, solenoids, actuators, or servos.

[0085] Computer system 205 may implement the techniques described herein using customized 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 the computer system, cause the computer system to operate as a special-purpose machine or program. According to one embodiment, the techniques herein are performed by computer system 205 in response to processor 210 executing at least one sequence of at least one instruction contained in main memory 225. Such instructions may be read into main memory 225 from another storage medium, such as storage 215. Execution of the sequences of instructions contained in main memory 225 causes processor 210 to perform the process steps described herein. In alternative embodiments, hardwired circuitry may be used in place of or in combination with software instructions.

[0086] As used herein, the term "storage medium" refers to any non-transitory medium that stores data and / or instructions that cause a machine to operate in a specific manner. Such storage media may comprise non-volatile media and / or volatile media. Non-volatile media include, for example, optical or magnetic disks, such as storage 215. Volatile media include dynamic memory, such as memory 225. 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.

[0087] Storage media are distinct from, but may be used in conjunction with, transmission media. Transmission media involves transferring information to and from storage media. For example, transmission media include coaxial cables, copper wire, and fiber optics, including the wires that comprise a bus in I / O subsystem 220. Transmission media can also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0088] Various forms of media may be involved in carrying at least one sequence of at least one instructions to processor 210 for execution. For example, the instructions may initially be carried on a magnetic 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 communications link, such as a fiber optic or coaxial cable or a telephone line, using a modem. A modem or router local to computer system 205 may receive the data on the communications link and convert the data into a format readable by computer system 205. For example, a receiver such as a radio frequency antenna or infrared detector may receive the data carried in a radio or optical signal, and appropriate circuitry can provide the data to I / O subsystem 220, such as placing the data on a bus. I / O subsystem 220 carries the data to memory 225, from which processor 210 retrieves and executes the instructions. The instructions received by memory 225 may optionally be stored in storage 215 either before or after execution by processor 210.

[0089] Computer system 205 also includes a communications interface 260 coupled to bus 220. Communications interface 260 provides a two-way data communication coupling to network link 265, which is directly or indirectly connected to at least one communications network, such as network 270 or a public or private cloud on the Internet. For example, communications interface 260 may be an Ethernet networking interface, an Integrated Services Digital Network (ISDN) card, a cable modem, a satellite modem, or a modem for providing a data communication connection to a corresponding type of communications line, such as an Ethernet cable or any type of metal cable, or an optical fiber line or telephone line. Network 270 broadly represents a local area network (LAN), a wide area network (WAN), a campus network, an internetwork, or any combination thereof. Communications interface 260 may comprise a LAN card for providing a data communication connection to a compatible LAN, or a cellular radiotelephone interface wired to transmit or receive cellular data according to cellular radiotelephone wireless network standards, or a satellite radio interface wired to transmit or receive digital data according to satellite radio network standards. In any such implementation, communication interface 260 sends and receives electrical, electromagnetic or optical signals over signal paths that carry digital data streams representing various types of information.

[0090] Network link 265 typically provides electrical, electromagnetic, or optical data communication to other data devices, directly or through at least one network, for example, using satellite, cellular, Wi-Fi, or Bluetooth technology. For example, network link 265 may provide a connection to host computer 250 through network 270.

[0091] Further, network link 265 may provide connectivity to other computing devices through network 270 or through internetworking devices and / or computers operated by an Internet Service Provider (ISP) 275. ISP 275 provides data communication services through a worldwide packet data communication network represented as Internet 280. Server computer 255 may be connected to Internet 280. Server 255 broadly represents any computer, data center, virtual machine, or virtual computing instance, with or without a hypervisor, or a computer running a containerized program system such as DOCKER or KUBERNETES. Server 255 may represent an electronic digital service implemented using multiple computers or instances and accessed and used by sending web service requests, uniform resource locator (URL) strings with parameters in HTTP payloads, API calls, application service calls, or other service calls. Computer system 205 and server 255 may form elements of a distributed computing system that includes other computers, processing clusters, server farms, or other organizations of computers that cooperate to perform tasks or run applications or services. The server 255 may comprise one or more sets of instructions organized as modules, methods, objects, functions, routines, or calls. The instructions may be organized as one or more computer programs, operating system services, or application programs, including mobile apps.The instructions may include operating system and / or system software; one or more libraries supporting multimedia, programming, or other functionality; data protocol instructions or stacks for implementing TCP / IP, HTTP, or other communications protocols; file formatting instructions for parsing or rendering files encoded using HTML, XML, JPEG, MPEG, or PNG; user interface instructions for rendering or interpreting commands for a graphical user interface (GUI), a command line interface, or a text user interface; and application software such as an office suite, Internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games, or other applications. Server 255 may comprise a web application server that hosts a presentation layer, an application layer, and a data storage layer such as a relational database system with or without Structured Query Language (SQL), an object store, a graph database, a flat file system, or other data storage.

[0092] Computer system 205 can send messages and receive data and instructions, including program code, through the network(s), network link 265 and communication interface 260. In the Internet example, a server 255 might transmit a requested code for an application program through Internet 280, ISP 275, local network 270 and communication interface 260. The received code may be executed by processor 210 as it is received, and / or stored in storage 215, or other non-volatile storage for later execution.

[0093] Execution of instructions as described in this section may implement a process in the form of an instance of a computer program, consisting 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 simultaneously. In this context, a computer program may be a passive collection of instructions, and a process may be the actual execution of those instructions. Multiple processes may be associated with the same program; for example, opening multiple instances of the same program often means that multiple processes are running. Multitasking may be implemented to allow multiple processes to share the processor 210. Although each processor 210 or processor core executes a single task at a time, the computer system 205 may be programmed to implement multitasking to allow each processor to switch between executing tasks without having to wait for each task to finish. In one embodiment, the switch may be performed when a task performs an input / output operation, when the task indicates that it is available to switch, or upon a hardware interrupt. Time sharing may be implemented to enable fast response to interactive user applications by rapidly executing context switches to provide the appearance of concurrent execution of multiple processes simultaneously. In one embodiment, for security and reliability, the operating system may prevent direct communication between independent processes and provide strictly mediated and controlled inter-process communication facilities.

[0094] FIG. 2 illustrates a system 200 for predicting a stability value for a determined fragrance in a determined fragrance base, which includes: - one or more computer systems 205 comprising one or more hardware processors 210 and storage 215 media; - instructions stored on a storage medium, which instructions, when executed by a computer system, cause the computer system to: - inputting, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients; - inputting, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining, by a computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing, on a computer interface, a value representative of the determined stability value; to carry out the order and The present invention further provides a system comprising:

[0095] 1 and 3 disclose specific embodiments of the above steps.

[0096] 1 shows a schematic representation of a particular sequence of steps of a method 100 that is the subject of the present invention. The method 100 for predicting the stability value of a determined fragrance in a determined fragrance base comprises: - inputting 105, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a fragrance ingredient composition; - inputting 110, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining 115, by the computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing 120, on a computer interface, a value representative of the determined stability value.

[0097] The inputting step 105 is performed manually or automatically on a computer interface, such as, for example, a graphical user interface ("GUI") associated with an I / O subsystem 220 coupled with input devices 240 as shown in FIG. 2. During this inputting step 105, fragrance ingredient digital identifiers may be selected to form a composition. Such fragrance ingredient digital identifiers may be represented as buttons, items in a list, or items that can be searched via a search engine. The user may add any number of ingredients represented by corresponding digital identifiers. This step 105 corresponds to a potential or intended composition to be assembled and associated with a particular fragrance base.

[0098] In certain embodiments, the relative or absolute amounts of the fragrance ingredient digital identifiers in the composition may be entered.

[0099] At the start of this step 105 of the input, the composition is defined.

[0100] The inputting step 110 is performed manually or automatically on a computer interface, such as, for example, a graphical user interface ("GUI") associated with an I / O subsystem 220 coupled with input devices 240 as shown in FIG. 2. During this inputting step 110, a base digital identifier may be selected. Such a base digital identifier may be represented as a button, an item in a list, or an item that can be searched via a search engine. The user may add any number of bases, represented by corresponding digital identifiers. This step 110 corresponds to potential or intended bases to be associated with the input composition.

[0101] In certain embodiments, the inputting step 110 is performed by selecting base components, e.g., molecules or compounds that make up the base, represented by corresponding base component digital identifiers, the selection of which forms the base composition.

[0102] In certain embodiments, the subject method 100 of the present invention comprises: - a step 101 of constructing a database of fragrance ingredient digital identifiers, in which physical fragrance ingredients are associated with fragrance ingredient digital identifiers according to a one-to-one relationship; and / or - a step 102 of configuring a database of fragrance-based digital identifiers, in which physical base components are associated with fragrance-based digital identifiers according to a one-to-one relationship; At least one of the databases is used during input steps 105 and / or 110 .

[0103] During the configuring step 101, a user or a computer system may introduce into the database a set of fragrance ingredient digital identifiers that represent physical fragrance ingredients. Such identifiers may correspond to identification numbers or labels.

[0104] During the configuring step 102, a user or computer system may introduce into the database a series of base component digital identifiers that represent the physical base components. Such identifiers may correspond to identification numbers or labels.

[0105] In certain embodiments, such as the one depicted in FIG. 1, the method 100 of the present invention includes a step 125 of inputting, on a computer interface, a fragrance application digital identifier representing the use of the input fragrance and the input base.

[0106] The inputting step 125 may be performed manually or automatically on a computer interface, such as a graphical user interface ("GUI") associated with an I / O subsystem 220 coupled with input devices 240 as shown in FIG. 2. During this inputting step 125, an application identifier may be selected. Such application digital identifiers may be represented as buttons, items in a list, or items that can be searched via a search engine. The user may add any number of applications represented by corresponding digital identifiers. This step 110 corresponds to a potential or intended use associated with at least one binding formed between a composition digital identifier and a base digital identifier.

[0107] An application digital identifier may correspond to an application or class of applications at any level of abstraction that results from the process of classification.

[0108] The step 115 of decision-making may be implemented, for example, by computer software represented by instructions stored in a storage 215 medium and executed by the hardware processor 210 of the computer system 205. During this step 115 of decision-making, two main types of algorithms are used: The first type corresponds to expert system modeling, in which a deterministic (and programmed) equation or system of equations links the presence and / or amount of fragrance components and bases to stability values, and The second type may be used, which corresponds to the implementation of a machine learning algorithm based on known data to infer or predict the stability of a combination of a composition and a fragrance base.

[0109] In the first type, the presence of a particular ingredient above a determined threshold may, for example, automatically set the stability value to a value corresponding to a lack of stability. While such an approach is possible, the combinability in a large fragrance ingredient palette combined with a large fragrance base palette requires significant manual effort.

[0110] In the second type, a supervised machine learning algorithm may be implemented, in which training data corresponding to a set of compositions and fragrance bases associated with values ​​representing the stability of the compositions and fragrances is fed to a training algorithm to generate a trained machine learning device.

[0111] In certain embodiments, such as that depicted in FIG. 1, the method 100 of the present invention comprises: a step 135 of providing a set of example data to a classifier machine learning device, composition digital identifiers, each composition digital identifier being associated with a fragrance ingredient digital identifier; - for at least a portion of the exemplary composition digital identifiers, a fragrance-based digital identifier; - for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the stability of the exemplary composition; - a step 140 of operating a classifier machine learning device based on a set of example data; - obtaining a trained classifier machine learning device 145.

[0112] The providing step 135 may be performed by using the I / O subsystem 220 of the computer system 205 coupled with a storage 215 medium or an API that provides input example data.

[0113] A specific embodiment of exemplary data is shown in Figure 3. This schematic shows that such inputs include: compositions 301, each composition represented as a sum of components 302, the components varying in number and nature between different compositions, and such components represented by digital identifiers, such as alphanumeric labels, that represent a reference in a database of component digital representations; - fragrance bases 303, where each fragrance base is represented as a sum of base components 304, where the base components vary in number and nature between different fragrance bases, and where such base components are represented by digital identifiers such as alphanumeric labels that represent references in a database of base component digital representations; - alternatively, fragrance bases 303 may be considered as complete entities (i.e. not broken down to component level) that are represented by digital identifiers that represent digital representations of that fragrance base; - Attributes 306 that are linked to the composition and fragrance-based association, such as the time period since association with a stability measurement, or the associated application.

[0114] In certain embodiments, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the duration since assembly of the bond.

[0115] In certain embodiments, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the concentration of the composition within the base of that bond.

[0116] In certain embodiments, the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing the application of the bond.

[0117] FIG. 3 depicts step 135 of providing this input as an arrow 305 that feeds the machine learning device being trained.

[0118] The step 140 of operating the machine learning device is performed, for example, by one or more hardware processors 210 configured to execute a set of instructions representing a machine learning device. Such a machine learning device corresponds, for example, to the gradient boosting decision tree device referenced 305 in Figure 3. This step 140 of operating is represented by the reference numeral 310 in Figure 3. Preferentially, the gradient boosting decision trees are constructed sequentially such that each new tree minimizes the classification loss.

[0119] In a particular example, it is formed of over 100,000 pass / fail observations (meaning "stable / unstable") for over 30,000 formulations, and -Formulation upn defines the chemical formula identifier of the fragrance, -Fragrance dosage measures the concentration (%) of the formula in the tested product; -Segment names define product usage at a high level: Body and Personal Care, Home and Fabric Care, Fine Fragrances, -Sub-segment names define product usage in a more specific way than the segment name:13 attribute, - the application name defines the use of the product in a more specific way than the subsegment name, and corresponds to a leaf in the tree structure defined by the Segment Name, Subsegment Name, and Application Name: 158 attributes; A dataset may be used that includes explanatory variables such as -matcode, which defines the base used in the stability study.

[0120] The formula identifier upn can be associated with a sparse matrix called the composition matrix that stores a weighted partition of the ingredients used, with the weighted sum of each formula being 1. The composition matrix has approximately 1 million formulas (rows) and 6000 ingredients (columns), where the weight corresponds to the amount of a given ingredient (column) within a given formula (row). This allows for the replacement of formula identifiers with the corresponding ingredient compositions.

[0121] In certain embodiments, a grid search algorithm may be used to select the best parameter set for each stability prediction, thus maximizing the outcome of each stability prediction, namely: - Encapsulation name: presence or absence depending on the use of encapsulation technology to capture the fragrance, and / or Olfactory list: a set of olfactory descriptors, such as labels, that describe the perceived description of the fragrance's smell, used as features.

[0122] An olfactory descriptor, or olfactory description, describes how something smells. In other words, an olfactory descriptor corresponds to the organoleptic properties imparted by a fragrance composition, or a composition of fragrance ingredients, or a fragrance ingredient, or ingredient. Such an olfactory descriptor may correspond to items that a particular fragrance smells similar to, for example, "citrus," "aromatic," "red fruit," "rose," etc. Several olfactory descriptors may be used in one fragrance composition or one fragrance ingredient.

[0123] Taste descriptors, or taste descriptions, are similar in scope only for taste, not smell.

[0124] To maximize the information gain provided by using target coding, it is possible to calculate the most important features for stability: a feature is considered most important if the accuracy score difference between adding and removing the feature is maximized.

[0125] The step of obtaining 145 the trained machine learning device is performed by one or more hardware processors 210 configured to execute a set of instructions representing storage, for example, in a storage 215 medium, of the results of the operating step 140. This obtaining step 145 is represented in Figure 3 by reference numeral 315.

[0126] This trained machine learning device or model is configured to receive the input composition, fragrance base, and optionally application, and predict as output the associated stability of this input, which corresponds to step 130 of operating the machine learning device or model.

[0127] In certain embodiments, such as that depicted in FIG. 1 , the determining step 115 includes a step 130 of operating a trained classifier machine learning device, where the input composition and the input fragrance base are used as inputs to a classifier machine learning model, and the output is a stability class identifier representing the stability of the input composition in the input fragrance base.

[0128] The providing step 120 may be performed on a computer interface, such as, for example, a graphical user interface ("GUI") associated with an I / O subsystem 220 coupled to an output device 235, as shown in Figure 2. During this providing step 120, the predicted stability may be expressed as a numeric or alphanumeric value.

[0129] In a particular embodiment, as shown in FIG. 1 , the method 100 of the present invention includes, downstream of the step 130 of operating the trained gradient boosting decision tree device, a step 150 of determining, by a computer device, a numerical value representing a stability impact for at least one input fragrance ingredient digital identifier, and a step 155 of providing the determined stability impact numerical value on a computer interface.

[0130] The determining step 150 is performed, for example, by one or more hardware processors 210 configured to execute a set of instructions representing software.

[0131] To determine which set of ingredients will have the most impact on stability, it is important to remember that stability scores are affected by application and base. Therefore, ingredient recommendations are provided for application-based combinations.

[0132] Recognized as the state-of-the-art method in machine learning explainability, Shapley Additive Explanations (SHAP) was published by Lundberg and Lee in 2017. SHAP assigns an importance value for each feature in an input dataset to a particular prediction.

[0133] Considering that components with a positive or negative relationship between SHAP importance score and component dosage must be treated separately, selecting the most influential components is not a trivial task. Linear relationships may be determined via Spearman correlation, allowing for the separation of positive from negative relationships.

[0134] This allows us to find the component with the most positive impact on stability, which can be related to the boundary dosage given by the minimum and / or maximum amount of a particular component. The minimum amount of a particular component should indicate the starting amount at which that component becomes a stability enhancer. Exceeding the minimum amount can increase the stability of a given fragrance until the maximum amount is reached, which is defined as the breakpoint. Adding more than the amount indicated by the maximum amount results in a slow increase, saturation, or decrease in the component's effect. The component with the most negative effect also provides important additional information to the perfumer. Adding a large amount of a negative component can significantly reduce stability. Therefore, it is possible to calculate only the maximum dosage, which determines the limit of the amount a perfumer can add before the component's contribution becomes negative and therefore interferes with stability.

[0135] A final importance score for each component is calculated by taking the median of the positive or negative SHAP scores for each component with more than 50 positive or negative samples, taking into account positive or negative relationships. In this way, the component with the most positive or negative contribution is the component with the highest or lowest median. However, the most influential component is expected to be the one that maximizes both the correlation score and the median SHAP, in order to maximize this contribution while having a discernible separation between positive and negative contributions.

[0136] With the goal of maximizing both parameters, the correlation and SHAP scores can be normalized between 0 and 1 so that both scores have equal weight. A final impact score assessing the influence of a component is finally obtained by summing these normalized scores, with 2 being the maximum value and 0 being the minimum value. Once the most influential components (also called manipulable components) have been calculated, the calculation of quantity boundaries requires the detection and removal of outlier data samples to maximize their reliability.

[0137] In certain embodiments, the method 100 of the present invention, such as that shown in FIG. 1, downstream of step 150 of determining the numerical value representing the stability impact, comprises step 160 of providing at least one alternative fragrance ingredient digital identifier for at least one fragrance ingredient digital identifier input and forming a composition in response to the numerical value representing the stability impact of that input and of that alternative fragrance ingredient digital identifier.

[0138] The providing step 160 is performed, for example, by one or more hardware processors 210 configured to execute a set of instructions representing software. During this providing step 160, other alternative fragrance ingredient digital identifiers not originally entered, or variations in the concentrations of fragrance ingredient digital identifiers, are used in place of at least one originally entered fragrance ingredient digital identifier, and the stability performance of the composition-based combination is re-evaluated. If performance improves, the alternative fragrance ingredient digital identifiers or alternative concentrations are provided to the user, for example, on a GUI.

[0139] In certain embodiments, such as that shown in FIG. 1, step 160 of providing at least one alternative fragrance ingredient digital identifier is configured to further provide at least one value representing the concentration of the at least one alternative fragrance ingredient digital identifier.

[0140] For each operable component, a piecewise linear function can be used to approximate the plot of data points versus quantity in SHAP, with the intent of determining quantity ranges and boundaries. The optimal number of linear functions may be set to 3, providing a major trend while allowing for easy analysis to determine quantity boundaries.

[0141] Graphing ingredient usage may show that the number of uses decreases as the amount of ingredient increases. Beyond a certain amount, the density of data points may become so small that the fit line is no longer reliable relative to its reliability. In certain cases, the density of points may become so low that a single data point can completely change the slope of the linear function. To counter this effect, it is possible to develop a method to find a threshold amount at which the fit line can no longer be considered reliable. To count the number of data points contained in each bucket, a range of amounts in buckets of the same size is separated. The threshold for the number of data points per bucket is: thresholdbucket=1 / |bucket|·2 Σb∈bucket Σx∈b 1(xquantity>0) It is defined as where x represents a data point contained in bucket b, 1(xquantity>0) represents an indicator function with the condition that the input quantity of data point x must be strictly greater than 0, and the quantity threshold is defined as the maximum quantity of the last bucket that satisfies the condition defined above.

[0142] The three piecewise linear functions are useful for evaluating different boundary quantities depending on the positive or negative contribution of the selected component. The minimum quantity can be calculated by projecting a 0 SHAP score onto the fitted line. Selecting a piecewise linear function is necessary to calculate the maximum quantity of the positive contributor. Breakpoints can be called the two extreme points of the gradient line, as well as the points where the slope changes, giving a total of four breakpoints for most components. The maximum quantity can be obtained by selecting breakpoints through the analysis of the three slopes, and similarly through the analysis of the three gradients. Let grad 0, grad 1, and grad 2 be the gradients calculated for the three linear functions, respectively, and break 0, break 1, break 2, and break 3 be the breakpoints. The following pseudocode shows the analysis performed to obtain the maximum quantity of the positive contributor. #Condition 1: The gradient becomes smaller if grad_0>grad_1>grad_2 and grad_1>0 return break_2 #Condition 2: The gradient becomes larger elif grad_2>grad_1>grad_0 and grad_1>0 return break_3 #Condition 3: The last gradient is greater than the second gradient elif grad_2>grad_1 return break_1 #Condition 4: The first gradient is greater than the first gradient elif grad_1>grad_0 return break_2 #others else return break_1

[0143] For disturbing components, an outlier removal process can be applied, and the maximum amount can be obtained by projecting a zero SHAP score onto the fitted line. Since the linear correlation between SHAP score and amount is negative, a 0 SHAP score indicates the maximum amount of that component that can be added before the contribution becomes negative with a negative SHAP score.

[0144] In certain embodiments, step 160 of providing at least one alternative fragrance ingredient digital identifier, such as that shown in FIG. 1, is configured to further provide minimum and / or maximum values ​​representing the concentration of the at least one alternative fragrance ingredient digital identifier.

[0145] In certain embodiments, the method 100 of the present invention, such as that shown in FIG. 1, includes a step 165 of physically assembling an input composition in an input fragrance base.

[0146] This step of physically assembling 165 is configured to embody the composition. Such a step of physically assembling 165 may be performed in a variety of ways, for example, in a laboratory, a chemical plant, etc.

[0147] 2 shows a schematic representation of a particular embodiment of a system 200 that is the subject of the present invention. This system 200 for predicting the stability value of a determined fragrance in a determined fragrance base comprises: - one or more computer systems 205 comprising one or more hardware processors 210 and storage 215 media; - instructions stored on a storage medium, which instructions, when executed by a computer system, cause the computer system to: - inputting, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients; - inputting, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining, by a computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing, on a computer interface, a value representative of the determined stability value; to carry out the order and Equipped with.

[0148] A description of optional embodiments of the corresponding means and steps has been disclosed above.

Claims

1. 1. A method (100) for predicting a stability value of a determined fragrance in a determined fragrance base, said method (100) comprising: - inputting (105) on a computer interface at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a fragrance ingredient composition; - inputting (110) on a computer interface a fragrance base digital identifier representing a material fragrance base; - determining (115) by a computing device a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing (120) on a computer interface a value representative of said determined stability value; A method (100) comprising:

2. The method includes inputting (125) on a computer interface a fragrance application digital identifier representing the use of an input fragrance and an input base; The method (100) of claim 1.

3. the determining step (115) includes operating (130) a trained classifier machine learning device, wherein an input composition and the input fragrance base are used as inputs to a classifier machine learning model, and the output is a stability class identifier representing the stability of the input composition in the input fragrance base. The method (100) according to claim 1 or 2.

4. The method further comprises, upstream of the step (130) of operating a trained classifier machine learning device, - providing a set of example data to a classifier machine learning device (135); - operating (140) said classifier machine learning device based on said set of example data; - obtaining (145) said trained classifier machine learning device; Including, The exemplary data set includes: composition digital identifiers, each composition digital identifier being associated with a fragrance ingredient digital identifier; - fragrance-based digital identifiers for at least some of the exemplary composition digital identifiers; and - a value representing the stability of the exemplary composition for at least one bond formed between the exemplary composition and a base digital identifier; Including, The method (100) of claim 3.

5. the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing a duration since the establishment of the bond; The method (100) of claim 4.

6. the exemplary data further includes, for at least one bond formed with an exemplary composition and a base digital identifier, a value representing the concentration of the composition within the base of the bond; The method (100) of any one of claims 4 or 5.

7. the exemplary data further includes, for at least one bond formed with the exemplary composition and the base digital identifier, a value representing application of the bond; The method (100) of any one of claims 4 to 6.

8. the trained classifier machine learning model is a classifier gradient boosting decision tree device; The method (100) of any one of claims 3 to 7.

9. The method further comprises, downstream of the step (130) of operating the trained gradient boosting decision tree device, determining (150) by the computing device a numerical value representing a stability impact for at least one input fragrance ingredient digital identifier; providing (155) the determined stability impact numbers on a computer interface; Including, The method (100) of any one of claims 3 to 8.

10. downstream of the step (150) of determining a numerical value representative of a stability impact, the method comprises a step (160) of providing at least one alternative fragrance ingredient digital identifier for at least one fragrance ingredient digital identifier input, and forming the composition in response to the numerical value representative of the stability impact of the input and of the alternative fragrance ingredient digital identifier; 10. The method (100) of claim 9.

11. wherein said step (160) of providing at least one alternative fragrance ingredient digital identifier is further configured to provide at least one value representing a concentration of said at least one alternative fragrance ingredient digital identifier. The method (100) of claim 10.

12. wherein said step (160) of providing at least one alternative fragrance ingredient digital identifier is further configured to provide a minimum value and / or a maximum value representing a concentration of said at least one alternative fragrance ingredient digital identifier. The method (100) according to claim 9 or 10.

13. The method includes a step (165) of physically assembling the input composition in the input fragrance base. The method (100) of any one of claims 1 to 12.

14. The method comprises: - constructing (101) a database of fragrance ingredient digital identifiers, in which physical fragrance ingredients are associated with fragrance ingredient digital identifiers according to a one-to-one relationship (101); and / or - constructing (102) a database of fragrance-based digital identifiers, in which physical base components are associated with fragrance-based digital identifiers according to a one-to-one relationship; and At least one of said databases is used during the input step (105, 110). The method (100) of any one of claims 1 to 13.

15. 1. A system (200) for predicting a stability value for a determined fragrance in a determined fragrance base, said system (200) comprising: - one or more computer systems (205) comprising one or more hardware processors (210) and storage (215) media; - instructions stored on said storage medium; wherein the instructions, when executed by the computer system, cause the computer system to: - inputting, on a computer interface, at least two fragrance ingredient digital identifiers representing ingredient fragrance ingredients, the resulting input corresponding to a fragrance ingredient composition; - inputting, on a computer interface, a fragrance base digital identifier representing the material fragrance base; - determining, by a computing device, a stability value of the input composition in the input fragrance base as a function of the input composition and the input fragrance base; - providing, on a computer interface, a value representative of said determined stability value; A system (200) for implementing the above.

Images