WO2024074975A1 - Method for manufacturing tailor made skincare products and skincare products so obtained - Google Patents

Abstract

It is disclosed a method of providing a tailor made cosmetic service according to a skin diagnosis for each customer, and more particularly, a method for providing a tailor made cosmetic service by manufacturing and providing tailor made skin care products according to a skin diagnosis for each customer. Skin care products are also disclosed, being obtainable by a computer-based system determining the recipe of said skin care products, based on specific customer data.

Description

“METHOD FOR MANUFACTURING TAILOR MADE SKINCARE PRODUCTS AND SKINCARE PRODUCTS SO OBTAINED”

DESCRIPTION

FIELD OF THE INVENTION

The present invention concerns a method of providing a tailor made cosmetic service according to a skin diagnosis for each customer, and more particularly, to a method for providing a tailor made cosmetic service by manufacturing and providing tailor made skincare products according to a skin diagnosis for each customer.

The present invention also concerns skincare products obtainable by a computer-based system determining the recipe of said skincare products, based on specific customer data. STATE OF THE ART

Many methods are currently used to improve skin quality, health or appearance. To a large extent, the use of skin care products is based on individual preference or when recommended by a professional are generic in nature. In recent years, consumers have tended to place more importance on the user experience of using personalized products. As an example of cosmetic personalization, attention is focused on cosmetics customized for consumers. Customized cosmetics are produced according to the skin condition and demands of the user.

Skin health and appearance focus has shifted in the last couple of years to focus on customizing topical treatments in cosmetology. Skin ageing is a growing concern and aesthetic interventions have been attempted for individual skin concerns.

Various attempts are known to profile an individual’s skin based on biophysical parameters and using genetic profiling techniques.

Dermalogica has implemented a face mapping based on 11 different zones of the face, wherein each zone is analysed for a skin characteristic https://www.dermalogica.com/ blogs/living-skin/face-mapping-skin-analysis. This method discloses a qualitative mapping by a practitioner utilizing a zone based mapping to come to a subjective recommendation and the assessments cannot be tracked or validated and does not create a skin or face profile.

IPSA has implemented a skin analysis system and the IPSALYSER™ skin diagnosis system discloses analysis of 10 categories of Skin Balance, Original Skin Tone Contrast, Translucency, Transparency, Facial Texture Comparison, Moisture Retention Capability, Sebum Secretion, Firmness and Elasticity Test, Keratin Metabolism and Rosiness in order to recommend one of their products based on the skin analysis conducted. The method discloses a system and a self-questionnaire based system for one- or a two- skin characteristic based on patient concerns and is not holistic, quantitative nor reproducible. HelloAva has implemented a 12 question and multiple-choice answer system within a “skin matching app” to make product recommendations of multiple products across multiple brands for a skin care regime (https://www.allure.com/story/hello-ava-app). The system relies on self-directed questionnaire basis by individuals and does not have a systematic skin analysis system to create a skin profile for an individual.

Clinique has implemented a computer aided questionnaire based system for a customer (https://www.clinique.co.uk/Diagnostics) which allows a customer to select up to two skin concerns and directs the individual customer to the company’s product(s) that matches the customer’s skin concern. This system does not take into account a large range of individual skin characteristics based on skin aging or photo damage and is subjective, relies on a few self-identified concerns, lifestyle based only and is not comprehensive in terms of a skin profile for the individual.

Jain et.al., (2017) Journal of Cosmetic Dermatology, 16: 132-143, reveal a global ranking scale (GRS) established by Galderma, for assessing skin and looks at nine aspects of facial appearance with four domains cited as skin quality, wrinkles, morphology and volume and are graded on a four-point scale of 0 denoting none to 4 denoting severe. The method in this disclosure of assessment of skin concerns is subjective, lacks a comprehensive and empirical approach and, is not a validated assessment of potential treatment outcomes. Lakhani et.ai. (2016) IOSR Journal of Dental and Medical Sciences, Vol 15, Issue 7:89- 99, discloses gradings available in prior art for individual skin conditions utilising clinical skin parameters for medical diagnosis and is not directed to creating a skin profile.

The disclosure in Luc Levy et.al., (2004); Medical Laser Application 19(4):223-229, is directed to various state of the art evaluation techniques for individual skin characteristics as is currently available in the field of cosmetic dermatology and the disclosure does not reveal a skin profile creation, based on the evaluation techniques disclosed.

US Patent No. 5622692 discloses a method and system directed to customizing facial foundation products. The system profiles the skin characteristics at a qualitative level and aids in adjusting the colour of premixed foundations for the individual customer and does not address any skin characteristics. PCT Application No. PCT/IB2012/057558 (Publication No. WO2013098531 Al) entitled “Method for delivering cosmetic advice” discloses a method to identify indications of the skin related to skin colour and cosmetic advice related to it. The invention requires that a colour image is captured from a region, or a body of an individual and the image has a colour reference chart in the field of the image, which is then utilised to determine a skin type, a skin colour relating to a pigmentation or a depigmentation process and appropriate photoreaction, or a product that may be applied to temporarily modify the colour of the individual’s skin. This disclosure is narrowly directed to a determination of the skin colour and possible pigmentation or depigmentation, and products related thereto.

It is therefore felt the need of a reliable method for customizing skincare products, which overcome the drawbacks of the prior art and gives significant results that the customers can attest and appreciate.

SUMMARY OF THE INVENTION

This and other objects are achieved through a method of providing a tailor made cosmetic service as defined in the claims.

As it will be apparent from the following detailed description, the method of the invention allows to satisfactorily selected the ingredients for preparing cosmetic skin care products tailored on customer.

Moreover, the method of the invention has resulted in a very rapid and efficient service of a only few steps for the customer, thus making the overall request very convenient under both the economical and personalization points of view.

BRIEF DESCRIPTION OF THE DRAWINGS

The characteristics and advantages of the invention will be clear from the following detailed description of the invention, the working examples provided for illustrative and non-limiting purposes, as well as the accompanying figures, wherein:

Figure 1 depicts a flowchart showing the main steps of the method of the invention, Figure 2 depicts a flowchart showing a preferred embodiment of the method of the invention, and

Figure 3 depicts a flowchart showing the last step of the preferred method of Figure 2, followed by further preferred additional steps. DETAILED DESCRIPTION OF THE INVENTION

The present invention therefore relates to a method of providing tailor made cosmetic skincare products, the method comprising the steps of: a) receiving a picture of a skin test output, the latter being obtained by: i. applying a first sebum indicator on cheek for 3-5 seconds, and a second sebum indicator on forehead for 3-5 seconds, ii. removing the indicators, wherein said indicators show coloured areas corresponding to sebum areas present on cheek and forehead, and iii. taking a picture of the resulting output for cheek and a picture of the resulting output for forehead, b) generating a normalized sebum index for cheek and a normalized sebum index for forehead, by measuring and weighting the coloured areas of each indicator over the initial total area, each index being an number ranging from 0.00 to 100.00, wherein index = 0.00 corresponds to a completely uncoloured indicator (sebum absent), whereas index = 100.00 corresponds to a completely coloured indicator (highest sebum presence), c) generating a main skin metric, which is an number ranging from 0.00 to 100.00, calculated as algebraic average between the normalized sebum index for cheek and the normalized sebum index forehead of step b), d) providing a list comprising 17 skincare products, wherein each skincare product is defined by a composition of active ingredients, as shown in Table 1,

Table 1 :

wherein “wt%” means weight percent based on the skincare product weight, and wherein the wt% of active ingredients reported as a range means that said wt% ranges from the first boundary value (central column) corresponding to the main skin metric = 100.00, up to the second boundary value (right column) corresponding to the main skin metric = 0.00, the remaining single-value wt% being independent of the main skin metric, and e) generating the composition of each skincare product, by proportioning the wt% of the active ingredients to the main skin metric resulted from step c), thus obtaining 17 tailor made skincare products.

The method of the invention, as also schematically depicted in Figure 1, is clearly based on the revelation of sebum levels for several reasons:

- the amount of sebum determines the characteristics of the skin (dry or oily). The texture of a cream in relation to the type of skin is very important, in fact the correct correlation between sebum and skin type results in greater customer compliance. Greater compliance results into more constant application of the product, with more significant effects. Furthermore, properly correlated textures and skin types limit undesired phenomena, such as dryness and flaking (typical of dry skin that uses cream with light textures), acne, blackheads, seborrheic skin, skin infections (typical for oily skin that applies cream with rich textures);

- the amount of fat that makes up the skin must be balanced, and this comes from the sebum + fat components in cosmetic products. A correct quantity and quality of fat facilitate the penetration of fat-soluble active ingredients (most of the active ingredients present in a cream).

- the presence (or absence) of sebum can indirectly determine other skin parameters, for example hydration (a skin poor in sebum lacks the natural superficial lipid screen that regulates the evaporation of water and is therefore dehydrated, in contrast to a skin rich in sebum which has an excessive occlusive action, so that water is retained within the epidermis causing maceration of the stratum corneum, and consequently skin infections); - the cleansing phase, very important to prevent skin infections and to prepare the skin to receive functional cosmetics, is calibrated according to the amount of sebum produced, precisely because the cleansing products "degrease" but are not able to distinguish the fat dirt from the naturally occurring skin fat. Often too aggressive detergents degrease the skin excessively, thus decreasing the layer of skin fat which is very important for the skin health. By regulating the quantity of detergent active ingredients with respect to the recorded sebum levels, the method of the invention allows to minimize the collateral damages of the detergents.

According to step a), a picture of a skin test outputs is received, the latter being obtained by: i. applying a first sebum indicator on cheek for 3-5 seconds, and a second sebum indicator on forehead for 3-5 seconds, ii. removing the indicators, wherein said indicators show coloured areas corresponding to sebum areas present on cheek and forehead, and iii. taking a picture of the resulting output for cheek and a picture of the resulting output for forehead.

Said sebum indicator can be a device designed to detect the sebum distribution over a skin region, such as a skin analyser able to detect skin sebum and hydration levels, as well as pores and impurities, and optionally determine the shape and size of wrinkles and facial discoloration and dyschromias. For instance, said device can be a stand-alone station or a portable tester in the form of a remotely connected pen.

However, preferably, the sebum indicator of step a) is a strip or a patch comprising a layer of an opaque porous polymer matrix, having an additive homogenously dispersed therein, the additive being:

- selected from a group consisting of SiCh, AI2O3, CasPC , talc, (Cas PO^OH) and mixtures thereof, and

- crystalline and present in a particle size range of 1-300 pm, wherein said layer is to be applied to cheek and forehead in step a), and wherein, when the layer of an opaque porous polymer matrix comes into contact with sebum, the porous polymer matrix becomes transparent to visible light, thus generating coloured transparent areas throughout the initially opaque matrix.

There are commercially available strips or patches that can be suitably used in step a). In particular, are suitable all those sebum indicators wherein, after contact with skin, areas reacting with sebum change colour or visible light properties. Indeed, for the purposes of the present invention, it is sufficient this change in order to calculate the normalized sebum index in step b).

For example, suitable sebum indicators are commercially available or anyway described in the International patent application n. WO 2012/098166 Al.

Preferably, before performing step a) of the method, the customer is invited to clean the skin with a detergent/de-makeup product, in order to improve the reliability of the skin tests.

According to step b), a normalized sebum index for cheek and a normalized sebum index for forehead are generated, by measuring and weighting the coloured areas of each indicator over the initial total area, each index being an number ranging from 0.00 to 100.00, wherein index = 0.00 corresponds to a completely uncoloured indicator (sebum absent), whereas index = 100.00 corresponds to a completely coloured indicator (highest sebum presence).

Preferably, step b) is performed by running an image processing algorithm, comprising the following sub-steps of:

— recognizing the sebum-reacted areas of the skin tests, preferably both at the same time in a same image. In preferred embodiments, a pattern recognition algorithm is set a priori, such as the Circular Hough Transform (CHT), the most widely used technique for isolating features of a particular shape within an image;

— isolating the above sebum-reacted areas and using them as a sample in pixels to be analysed;

— analysing the pixel population within sebum-reacted areas and establishing a normalized colour scale with respect to all the pixels detected, both in all colour channels and in the grey channel;

— recording all pixels, test by test, with the sebum-reacted areas of the two indicators taken independently;

— selecting the grey channel, with values for example from 0 to 255 in RGB colour mode, and a colour channel chosen automatically as based on the colour content of the image, with the aim of having the greatest contrast within the reacted areas, where 255 represents the skin test with zero reaction and 0 represents the skin test with 100% reaction, thus resulting in two indexes. [RGB uses an 8 bit byte to store colour for each channel, i.e. 8 bits for Red, 8 for Green, and 8 for Blue. This gives 24 total bits to store colour information. Within the 8 bits for each channel, 256 colours are represented, from 00000000 to 11111111. There correspond directly to integers 0 - no colour (black) - to 255 (i.e. 1+2+4+8+16+32+64+128) - full colours (white)].

— calculating a weighted average X for the cheek and a weighted average Y for the forehead of all the values from for example 0 to 255 of all the pixels in the various colour and grey channels, where 255 represents the skin test with zero reaction and 0 represents the skin test with 100% reaction, thus resulting in two indexes; and

— obtaining an index for each of the two skin test on a scale from 0.00 to 100.00, where 0.00 represents the skin test with zero reaction and 100.00 represents the skin test with 100% reaction, for a total of two indexes A and B, i.e. normalized sebum index for cheek and a normalized sebum index for forehead respectively, as a result of the following formulas:

A: 100 = (255-X):255 and B: 100 = (255-Y):255

[Example: X = 127 (approximately in the middle of the scale 0-255) A: 100=(255-X):255

A=100(255-127)/255 =12800/255=50.20 where 50.20 is approximately in the middle of the scale 0.00-100.00]

According to step c), a main skin metric is generated, which is an number ranging from 0.00 to 100.00, calculated as the algebraic average between the normalized sebum index for cheek and the normalized sebum index forehead of step b),

Thus, the main skin metric is merely the algebraic average value between the two indexes A and B deriving from step b).

According to step d), a list comprising 17 skincare products is provided, wherein each skincare product is defined by a composition of active ingredients, as shown in Table 1 above, wherein the wt% of active ingredients reported as a range means that said wt% ranges from the first boundary value (central column) corresponding to the main skin metric = 100.00, up to the second boundary value (right column) corresponding to the main skin metric = 0.00, the remaining single-value wt% being independent of the main skin metric.

Actually, the concentration of some active ingredients is proportionally selected according to the main skin metric resulted from step b) (“variable ingredients”), whereas the concentration of other active ingredients is not dependent on the main skin metric (“constant ingredients”).

As can be seen from Table 1, the concentrations of some of the variable ingredients increase as the main skin metric increases, whereas the concentrations of other variable ingredients decrease, i.e. are inversely proportional to main skin metric. Actually, depending on the main skin metric, i.e. the sebum level on skin, some ingredients have to be added in higher amount and others have to be reduced, to give a balanced and effective action which is suitably tailor made for the customer’s skin.

For the purposes of the present invention, the wt% values reported in Table 1 should be meant to include an acceptable error of ± 0.50%.

The compositions also comprise cosmetic additives and co-formulants to give the listed skincare products, such as solvents, fragrances, and preservatives. However, as such, none of them negatively affects the action of the active ingredients.

Preferably, said soothing agent is selected from Panthenol, Allantoin, Hamamelis Virginiana (Witch Hazel) flower water, Bisabolol, Bentonite, Chamomilla Recutita flower extract, Malva Sylvestris (Mallow) leaf extract, Glycyrrhetinic Acid, Aloe Barbadensis leaf juice, Althaea Officinalis root extract, and mixtures thereof.

Preferably, said anionic surfactant is selected from Sodium Cocoyl Hydrolyzed Wheat Protein, Laureth-7, Sodium Lauryl Sulfate, Sodium Laureth Sulfate, Disodium Laureth Sulfosuccinate, Sodium Cocoyl Isethionate, Sodium Cocoyl Sarcosinate, Disodium Cocoyl Glutamate, Sodium Methyl Cocoyl Taurate, and mixtures thereof.

Preferably, said amphoteric surfactant is selected from Cocamidopropyl Betaine, Cocamidopropyl Hydroxysultaine, Cocamine Oxide, Cocamidopropylamine Oxide, and mixtures thereof.

Preferably, a non-ionic surfactant is selected from Lauryl Glucoside, Cocamide DEA, Cocamide MEA, and mixtures thereof.

Preferably, said keratolytic agent is selected from Lactobionic Acid, Mandelic Acid, Salicylic Acid, Glycolic Acid, Lactic Acid, Glutathione, Cysteine, Cystine, Methionine, Gluconol atone, and salts, and mixtures thereof.

Preferably, said antioxidant is selected from Tocopheryl Acetate, Superoxide Dismutase, Tocopherol, Ascorbic Acid, Sodium Ascorbyl Phosphate, Ascorbyl Glucoside, Thoictic Acid, and mixtures thereof.

Preferably, said mattifying agent is selected from Amylopectin, Kaolin, Talc, Oryza Sativa Starch, Zea Mays Starch, and mixtures thereof.

Preferably, said moisturizing agent is selected from Sodium Hyaluronate, Hydrolyzed Glycosaminoglycans, Glycine Soja (Soybean) Protein, Hydrogenated Lecithin, Hydrolyzed Soy Protein, Lecithin, Sericin, PCA (Pyrrolidone Carboxylic Acid), Sodium PCA, Urea, Trehalose, Sorbitol, Maltitol, Betaine, and mixtures thereof.

Preferably, said exfoliating agent is selected from Corylus Avellana (Hazel) Shell Powder, Prunus Amygdalus Dulcis (Sweet Almond) Bark Powder, Maranta Arundinacea Root Powder, Olea Europaea (Olive) Seed Powder, and mixtures thereof.

Preferably, said emollient is selected from Oryza Sativa (Rice) Bran Oil, Glycerin, Prunus Amygdalus Dulcis (Sweet Almond) Oil, Hydrogenated Ethylhexyl Olivate, Hydrogenated Olive Oil Unsaponifiables, CIO-18 Triglycerides, C18-70 Isoalkane, CIS- 14 Isoparaffin, Ethylhexylglycerin, Borago Officinalis Seed Oil, Olea Europaea (Olive) Fruit Oil, Argania Spinosa Kernel Oil, Oenothera Biennis Oil, Simmondsia Chinensis Seed Oil, Ribes Nigrum Seed Oil, Therobroma Grandiflorum Seed Butter, and mixtures thereof.

Preferably, said lipid is selected from Ceramide MP, Butyrospermum Parkii (Shea) Butter, Phytosterols, Squalane, Squalene, Ceramide NP, Ceramide AP, Ceramide EOP, and mixtures thereof.

Preferably, said antiaging agent is selected from Aminobutyric Acid, Oligopeptide 4, Caffeine, Retinyl Palmitate, Copper Aspartate, Magnesium Aspartate, Manganese Aspartate, Zinc Aspartate, Azeloyl Bis-Dipeptide-10, Palmitoyl Pentapeptide-3, Dipeptine Dieaminobutyroyl Benzylamide Diacetate, and mixtures thereof.

Preferably, said strong detergent is selected from Dimethicone, Olus Oil (vegetable oil), and mixtures thereof.

Preferably, said soft detergent is selected from Cyclomethicone, Helianthus Annuus (Sunflowers) Seed Oil, and mixtures thereof.

Preferably, said anti-inflammatory agent is selected from Zinc Oxide, Beta-Sitosterol, Boswellia Serrata extract, and mixtures thereof.

Preferably, said sebum normalizing agent is selected from Silica, Potassium Azelaoyl Diglycinate, Sulfur, Resveratrol, Pistacia Lentiscus, Azelaic Acid, and mixtures thereof. Preferably, said vasoprotective agent is selected from Escin, Ruscus Aculeatus extract, Aesculus Hippocastanum Seed extract, Centella Asiatica Leaf extract, and mixtures thereof.

Preferably said anti-oedema agent is selected from Bromelain, Calendula Officinalis flower, and mixtures thereof.

Preferably, said viscosifier is selected from Polyisoprene, Acrylates Copolymer, and mixtures thereof.

Preferably, said depigmenting agent is selected from Kojic Acid, Niacinamide, Hydroquinone, and mixtures thereof. In preferred embodiments, the skincare products of Table 1 comprise the following active ingredients:

According to step e), the composition of each skincare product is generated, by proportioning the wt% of the active ingredients to the main skin metric resulted from step c). To this end, the following formula is adopted for the calculation of each active ingredient, then building up each skincare product:

U = J + (K-J)*S/100 wherein

U = Customer’s tailored wt% to be calculated

J = wt% at main skin metric 0.00 K = wt% at main skin metric 100.00

S = Customer’s main skin metric

The resulting set of 17 tailor made cosmetic skincare products advantageously and suitably fits the peculiar and personal skin characteristics of the customer who performed the initial skin tests. In particular, the products so obtained are specifically formulated to effectively intervene on skin sebum, thus regulating the same and giving a more fresh and balanced skin appearance.

In preferred embodiments, the method of the invention further comprises the step of a’) receiving the output of a questionnaire comprising at least the following closed-ended questions about cosmetic products preferred:

I. Make-up used?

□ heavy make-up (0.05 to 0.20)

□ average make-up (0.02 to 0,15)

□ light make-up (0.01 to 0.10)

□ no make-up (0.00)

II. Texture preferred?

□ rich and full-bodied texture (-0.20 to -0.10)

□ average texture (0.00)

□ light and soft texture (0.10 to 0.20)

□ no preferences (0.00)

III. Preferred effect on skin?

□ strong and active (0.20 to 0.10)

□ average and normal (0.00)

□ soft and pleasant (-0.10 to -0.20)

□ no preferences (0.00)

It would be appreciated that these questions do not involve personal sensitive data, such as name, place of residence/birth, disorders/pathologies, family anamnesis, and so on. Preferably, the questionnaire of step a’) further comprises the following closed-ended questions:

IV. Consumer age?

□ < 24 years (0.05 to 0.10)

□ 25-34 years (0.02 to 0.05)

□ 35-44 years (-0.02 to 0.02)

□ 45-54 years (-0.05 to -0.02)

□ > 55 years (-0.10 to -0.05) V. Specific skin issues? [multiple-choice allowed]

□ skin spots (-0.10 to 0.10)

□ sensitivity/redness (-0.10 to 0.10)

□ eye shadows/bags (-0.10 to 0.10)

□ large pores (-0.10 to 0.10)

□ blackheads and pimples (-0.10 to 0.10)

□ wrinkles (-0.10 to 0.10)

□ none (0.00)

The questionnaire’s output is stored in aNxM matrix, called “matrix Questionnaire”, with N rows for questions and M columns for answers. The number M of answers can be higher than the number N of questions, the latter including multiple choice questions, thus giving a rectangular matrix rather than a square matrix.

The questionnaire further refines the skin test output with variations depending on the sensory and preferred personal aspect to improve the customer’s product compliance and subjective preferences. Additionally, the questionnaire can be used to select a sub-list of products that can be offered as “highly recommended” in consideration of the answers given in the questionnaire itself, as it will be further disclosed in the following, also with reference to Figure 2.

A second matrix MxN is provided for each skincare product obtained in step e), shortly called “matrix Cursor”, where the latter confers percentage variations to the indexes obtained as skin test outputs, thus further personalizing the proposed skincare products. The matrix Cursor for each skincare product is built up with the values falling within the ranges associated to each questionnaire’s answer, as reported there alongside by brackets. A merely exemplary and illustrative representation of a matrix Cursor could be the following:

Actually, the values in the matrix Cursor represent the percentage variations to be inferred to the calculated main skin metric, as measured by skin tests.

By making a matrix product between the matrix Questionnaire and matrix Cursor, for each skincare product, a “matrix Index” NxN can be obtained, for each skincare product. The values useful for the subsequent calculation are those found on the main diagonal, highlighted in bold in the merely exemplary and illustrative representation of a possible matrix Index:

Each value present in the main diagonal of matrix Index indicates a percentage variation value useful for the fine tuning, whereas the other values are ignored. Each diagonal value thus represents a percentage variation of the main skin metric, thus a fine tuning of the wt% of each active ingredient in each skincare product resulting from step e).

These percentage variation values are then weighted based on the distance they have with respect to the boundary values of the main skin metric scale towards which the variation leads. A negative value leads to 0 on the scale, a positive value leads to 100.00 on the scale.

If the diagonal value is > 0, then: the weighted main skin metric = value*(l - main skin metric)

If the diagonal value is < 0, then: the weighted main skin metric = value*(main skin metric)

The percentage variation value in each position will therefore be the more influential the further the main skin metric value is from the boundary of the scale towards which the variation leads.

The sum of the values in the main diagonal of the matrix Index, downstream of the weighting calculation just described, represents the "theoretical index variation".

A final skin metric is generated by algebraically summing the main skin metric calculated at step c) with the “theoretical index variation” above, for each product generated at step e), thus obtaining 17 tailor made and personalized cosmetic skincare products. In fact, with the results of the questionnaire, it is possible a fine tuning of the tailor made skincare products obtained in step e), by further personalizing the latter in accordance with the customer’s preferences.

To this end, the method of the invention can further comprise the step of: f) fine tuning the final wt% of each active ingredient in each skincare product of step e), by

- generating a NxM matrix Questionnaire, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), built up with binary values, i.e. 1 or 0, where 1 indicates that an answer is given to the corresponding question, whereas 0 indicates no answer,

- generating a MxN matrix Cursor for each skincare product, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), the matrix Cursor containing values falling within the ranges associated to each questionnaire’s answer,

- making a matrix product between the matrix Questionnaire and matrix Cursor, for each skincare product, thus obtaining 17 “matrixes Index” NxN,

- summing the values in the main diagonal for each matrix Index, thus obtaining 17 "theoretical index variations",

- generating a final skin metric by algebraically summing the main skin metric calculated at step c) with the respective “theoretical index variation” for each product, which is used as percentage to further weight the main skin metric values, thus the final wt% of each active ingredient in each skincare product of step e), so obtaining 17 tailor made and personalized skincare products.

A third matrix MxN is provided for each skincare product obtained in step e), shortly called “matrix Exclusion”, where the latter allows to tag each skincare product as “highly recommend” or “optional”.

The matrix Exclusion for each skincare product is built up with binary values, i.e. 1 or 0, depending on whether the questionnaire’s answers, i.e. the Customer’s needs and preferences, match or not the skincare product.

A merely exemplary and illustrative representation of a matrix Exclusion could be the following:

As said, “1” indicates, with respect to the questionnaire’s answers, a match between the

Customer’s needs and the product, whereas “0” indicates a mismatch.

By making a matrix product between the matrix Questionnaire and matrix Exclusion, for each skincare product, a “matrix Recommendation” NxN can be obtained, for each skincare product.

The values useful for the subsequent calculation are those found on the main diagonal, highlighted in bold in the merely exemplary and illustrative representation of a possible matrix Recommendation:

The sum of the values in the main diagonal of the matrix Recommendation gives a number, and

- if the resulting number is equal to zero (=0), then the skincare product corresponding to that matrix Exclusion is tagged and shown as “optional” to the Customer, whereas

- if the resulting number is different from zero (^0), then the skincare product corresponding to that matrix Exclusion is tagged and shown as “highly recommended” to the Customer.

In this way, the set of 17 skincare products resulted from step e) can be further classified in “highly recommended” products and “optional” to the Customer, as also shown in Figure 2. To this end, the method of the invention can further comprise the step of: g) classifying the 17 skincare products resulted from step e) in “highly recommended” products and “optional” products, by

- generating a NxM matrix Questionnaire, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), built up with binary values, i.e. 1 or 0, where 1 indicates that an answer is given to the corresponding question, whereas 0 indicates no answer,

- generating a MxN matrix Exclusion for each skincare product, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), the matrix Exclusion containing values of 1 or 0, depending on whether the questionnaire’s answers match or not the skincare product,

- making a matrix product between the matrix Questionnaire and matrix Exclusion, for each skincare product, thus obtaining 17 “matrixes Recommendations” NxN,

- summing the values in the main diagonal for each matrix Recommendation, thus obtaining 17 numbers, wherein when the number is equal to zero, the corresponding product is tagged and shown as “optional”, whereas when the number is different from zero, the corresponding product is tagged and shown as “highly recommended” to the Customer.

It should be appreciated that this classification step can be performed directly after step e), or preferably after step f). In other words, the 17 skincare products can be classified downstream the method of the invention comprising step a’), directly after step e), i.e. on the 17 tailor made skincare products resulting from step e), or preferably after step f), i.e. on the 17 tailor made and personalized skincare products resulting from step f).

If the step g) is performed after the step f), the matrix Questionnaire is already provided in step f) itself, as also schematically depicted in Figure 2.

In preferred embodiments, the method of the invention comprises the steps a) to e), as well as the steps a’), f) and g), wherein the step g) is performed on the 17 tailor made and personalized skincare products resulting from the step f).

Preferably, a list of fragrances is proposed to the Customer in order to actually make unique the set of skincare products, so that the Customer can choose which one is to be added to the skincare products’ compositions.

The fragrance choice can be offered: - after the 17 tailor made skincare products have resulted from step e),

- after the 17 tailor made and personalized skincare products have resulted from step f), or

- after the 17 classified, tailor made and personalized skincare products have resulted from step g).

Preferably, the fragrance choice is offered after the 17 classified, tailor made and personalized skincare products have resulted from step g), as also shown in Figure 3.

It should be also understood that all the combinations of preferred aspects of the method steps and cosmetic skincare products above described are likewise preferred and deemed to be hereby disclosed.

It should be also understood that all the combinations of preferred aspects of the method steps, as above reported, are likewise preferred and deemed to be hereby disclosed also for the and cosmetic skincare products tailor made by said method.

Below are working examples of the present invention provided for illustrative purposes.

EXAMPLES

Example 1.

Customer’s data

Age: 18

Sex: female

Skin characteristics: skin in good condition, no particular signs, slight sebum production.

Skin test outputs:

Both skin patches react in a moderately marked way — normal skin tending to oily Product processing:

From the skin test outputs, the algorithm generates the composition of 17 skincare products with medium textures tending to lean, with moderate dosage sebum-regulating active ingredients.

Among the 17 products, the Customer has chosen the following:

Impure skin cream

• Average texture tending to dry

• pH < 5.5

• main moderately dosed functional sebum -regulating active ingredients: o Salicylic acid o Mandelic acid o Hamamelis virginiana o Amylopectin o Azeloglycine

Moisturizing cream

• Average texture tending to dry

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Cl 3- 14 Isoparaffin o Ceramide Mp o Polyisoprene

Detergent gel

• pH < 5.5

• main functional sebum-regulating and moisturizing active ingredients moderately dosed o Salicylic acid o Mandelic acid o Cocamidopropyl betaine o Lauryl glucoside

The skin test is performed 30 and 60 days after the initial measurement: the daily use of the chosen products has resulted in significant improvements in skin parameters:

Based on the subsequent skin test outputs, the algorithm can modulate the composition of the products, thus adapting them to the improved characteristics of the skin, for example the composition of the Impure skin cream is modified as follows:

Mandelic acid and salicylic acid, as well as amylopectin, follow the trend of the values found through the tests: in fact, owing to the daily application of the product, the amount of sebum has decreased. Consequently, the necessary dose of acids and amylopectin (sebum-regulating active ingredients) decreases: this entails a decreased risk of skin irritation (side effect of acidic active ingredients).

Active ingredients such as allantoin and potassium azelate remain at an unchanged concentration: this decreases the risk of excessive sebum production as a response to the decrease in the aforementioned sebum -regulating active ingredients (i.e. mandelic acid, salicylic acid, amylopectin).

Similarly, the composition of the moisturizing cream is modified as follows:

The concentration of some lipids increases (Ceramide MP, Oryza sativa bran oil and CIS- 14 Isoparaffin). Actually, these substances are responsible for a partially occlusive action on the skin, in order to ensure indirect hydration (i.e. they slow down the evaporation of the water present in the deep skin layers). In fact, they mimic the action of sebum. For this reason, a decreased production of sebum (detected by skin tests on day 30 and day 60) corresponds to a modification of the composition with an increased concentration of the lipids described above.

On the other hand, the concentration of Polyisoprene decreases, being an active ingredient that acts on the viscosity of the skincare product, so as to balance the increased concentration of lipids.

With respect to the detergent gel, the composition changes as follows:

Mandelic acid and salicylic acid follow the trend of the values found through the tests: in fact, owing to the daily application of the product, the amount of sebum has decreased. Consequently, the necessary dose of acids (sebum-regulating active ingredients) decreases: this entails a decreased risk of skin irritation (side effect of acidic active ingredients).

Similarly, the concentration of Cocamidopropyl betaine and Lauryl Glucoside, surfactants responsible for the degreasing power of the detergent, decreases accordingly to the trend of the values found through the tests: in fact, owing to the daily application of the product, the amount of sebum has decreased.

Consequently, the necessary dose of surfactants (degreasing active ingredients) decreases: this involves a decreased risk of skin irritation and dryness (side effect of surfactants that deplete the lipid layer of the skin, thus causing greater evaporation of water from the deep skin layers, which can result in skin irritation and dryness).

Customer’s satisfaction survey:

1. Evaluate the overall process from the skin tests to the tailor made skincare products’ delivery (from 1 : very complex, to 5: very easy): 5 2. Evaluate the skincare products’ suitability and fittingness for your skin (from 1 : totally unsuitable, to 5: very appropriate): 4

3. Impure skin cream:

3.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

3.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 4

3.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

4. Moisturizing cream:

4.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

4.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 4

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

5. Detergent gel:

5.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

5.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 3

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

Example 2.

Customer’s data

Age: 35 Sex: male

Skin characteristics: skin very dry, with local skin flaking.

Skin test outputs:

Both skin patches react in a moderately marked way — skin very dry

Product processing:

From the skin test outputs, the algorithm generates the composition of 17 skincare products with enriched textures, and moisturizing and lipo-restorative ingredients.

Among the 17 products, the Customer has chosen the following:

Moisturizing cream

• Enriched texture

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Cl 3- 14 Isoparaffin o Ceramide Mp o Polyisoprene

Soothing Moisturizing Mask

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Amylopectin o Sodium hyaluronate o Prunus Amygdalus Dulcis (Sweet Almond) Oil

Moisturizing serum

• Enriched texture

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Amylopectin o Sodium hyaluronate o Prunus Amygdalus Dulcis (Sweet Almond) Oil The skin test is performed 30 and 60 days after the initial measurement: the daily use of the chosen products has resulted in significant improvements in skin parameters:

Based on the subsequent skin test outputs, the algorithm can modulate the composition of the products, thus adapting them to the improved characteristics of the skin, for example the composition of the Moisturizing cream is modified as follows:

The concentration of some lipids decreases (Ceramide MP, Oryza sativabran oil and CIS- 14 Isoparaffin). In fact, these substances are responsible for a partially occlusive action on the skin, in order to ensure indirect hydration (i.e. they slow down the evaporation of the water present in the deep skin layers). In fact, they mimic the action of sebum. For this reason, an increased production of sebum (detected by skin tests on day 30 and day 60) corresponds to a modification of the composition with an increased concentration of the lipids described above. On the other hand, the concentration of Polyisoprene decreases, being an active ingredient that acts on the viscosity of the skincare product, so as to balance the increased concentration of lipids.

Similarly, the composition of the Soothing Moisturizing Mask is modified as follows:

The concentration of some lipids decreases (Prunus amygdalus dulcis oil and Oryza sativa bran oil). In fact, these substances are responsible for a partially occlusive action on the skin, in order to ensure indirect hydration (i.e. they slow down the evaporation of the water present in the deep skin layers). In fact, they mimic the action of sebum. For this reason, an increased production of sebum (detected by skin tests on day 30 and day 60) corresponds to a modification of the composition with an increased concentration of the lipids described above.

On the other hand, the concentration of amylopectin, an opacifying and sebum-regulating active ingredient, increases to balance the increased production of the amount of sebum detected by skin tests at 30 and 60 days.

Sodium hyaluronate, a direct moisturizing active ingredient, carries and releases a proper amount of water to the skin. To this end, its concentration remains unchanged at the maximum level.

With respect to the Moisturizing gel, the composition changes as follows:

The concentration of some lipids decreases (Prunus amygdalus dulcis oil and Oryza sativa bran oil). In fact, these substances are responsible for a partially occlusive action on the skin, in order to ensure indirect hydration (i.e. they slow down the evaporation of the water present in the deep skin layers). In fact, they mimic the action of sebum. For this reason, an increased production of sebum (detected by skin tests on day 30 and day 60) corresponds to a modification of the composition with an increased concentration of the lipids described above.

On the other hand, the concentration of amylopectin, an opacifying and sebum-regulating active ingredient, increases to balance the increased production of the amount of sebum detected by skin tests at 30 and 60 days.

Sodium hyaluronate, a direct moisturizing active ingredient, carries and releases a proper amount of water to the skin. To this end, its concentration remains unchanged at the maximum level.

Customer’s satisfaction survey:

1. Evaluate the overall process from the skin tests to the tailor made skincare products’ delivery (from 1 : very complex, to 5: very easy): 5

2. Evaluate the skincare products’ suitability and fittingness for your skin (from 1 : totally unsuitable, to 5: very appropriate): 4

3. Moisturizing cream:

3.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

3.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 3

3.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

4. Soothing Moisturizing Mask:

4.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

4.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 4

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

5. Moisturizing serum: 5.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 4

5.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 3

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 4

Example 3.

Customer’s data

Age: 20

Sex: female

Skin characteristics: skin in good condition, no particular signs, slight sebum production.

Skin test outputs:

Both skin patches react in a moderately marked way — normal skin tending to oily Product processing:

Answers from the questionnaire:

I. Make-up used? 0 heavy make-up; > average make-up; > light make-up; > no makeup

II. Texture preferred? > rich and full-bodied texture; > average texture; 0 light and soft texture; > no preferences

III. Preferred effect on skin? 0 strong and active; > average and normal; > soft and pleasant; > no preferences,

Optional questions:

IV. Consumer age? 0 < 24 years; > 25-34 years; > 35-44 years; > 45-54 years; > > 55 years

V. Specific skin issues? > skin spots; > sensitivity / redness; > eye shadows/bags; 0 large pores; 0 blackheads and pimples; > wrinkles; > none [multiple-choice allowed] Resulting matrix Questionnaire:

From the skin test outputs, the algorithm generates the composition of 17 skincare products with medium textures tending to lean, with moderate dosage sebum-regulating active ingredients.

Among the 17 products, the algorithm has tagged as “highly recommended” the following:

• Impure skin cream

• Moisturizing cream

• Detergent gel

• Impure skin serum

• Skin tonic

• Moisturizing serum

• Scrub

• Purifying mask

• Soothing moisturizing mask

• Night cream

• Make-up remover

Among the above 11 highly recommended skincare products, only the following 3 products are selected and prosecuted herein below for sake of conciseness: Impure skin cream

• Average texture tending to dry

• pH < 5.5

• main moderately dosed functional sebum -regulating active ingredients: o Salicylic acid o Mandelic acid o Hamamelis virginiana o Amylopectin o Azeloglycine

Moisturizing cream

• Average texture tending to dry

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Cl 3- 14 Isoparaffin o Ceramide Mp o Polyisoprene

Detergent gel

• pH < 5.5

• main functional sebum-regulating and moisturizing active ingredients moderately dosed o Salicylic acid o Mandelic acid o Cocamidopropyl betaine o Lauryl glucoside

The basal skin test is performed 0 days after the initial measurement:

The resulting algebraic average is 67.89, which is the main skin metric.

Impure skin cream

The matrixes characterizing the product are:

Matrix Cursor

Matrix Exclusion

By making the matrix product between the matrix Questionnaire and the matrix Cursor, the matrix Index is obtained as follows:

By weighting the values on the diagonal (in bold), 5 values are obtained:

These values, once multiplied by 100, are added to the main skin metric, thus obtaining the final skin metric for this skincare product: 80.73

On this percentage, the wt% of the ingredients will be weighted, to give a skincare product tailor made and personalized.

This product has been indicated as “highly recommended” according to the following procedure. By making the matrix product between the matrix Questionnaire and the matrix Exclusion, it is obtained:

By summating the values on the diagonal, the total is 2; as 2>0, this product is tagged as

“highly recommended”.

Moisturizing cream

The matrixes characterizing the product are: Matrix Cursor

By making the matrix product between the matrix Questionnaire and the matrix Cursor, the matrix Index is obtained as follows:

By weighting the values on the diagonal (in bold), 5 values are obtained:

These values, once multiplied by 100, are added to the main skin metric, thus obtaining the final skin metric for this skincare product: 74.31

On this percentage, the wt% of the ingredients will be weighted, to give a skincare product tailor made and personalized.

This product has been indicated as “highly recommended” according to the following procedure.

By making the matrix product between the matrix Questionnaire and the matrix

Exclusion, it is obtained:

By summating the values on the diagonal, the total is 1; as l>0, this product is tagged as “highly recommended”. Detergent gel

The matrixes characterizing the product are:

Matrix Cursor

By making the matrix product between the matrix Questionnaire and the matrix Cursor, the matrix Index is obtained as follows:

By weighting the values on the diagonal (in bold), 5 values are obtained:

These values, once multiplied by 100, are added to the main skin metric, thus obtaining the final skin metric for this skincare product: 87.16 On this percentage, the wt% of the ingredients will be weighted, to give a skincare product tailor made and personalized.

This product has been indicated as “highly recommended” according to the following procedure.

By making the matrix product between the matrix Questionnaire and the matrix Exclusion, it is obtained:

By summating the values on the diagonal, the total is 1; as l>0, this product is tagged as

“highly recommended”.

The skin test is performed 30 and 60 days after the initial measurement: the daily use of the chosen products has resulted in significant improvements in skin parameters:

The same matrix calculation procedure is carried out for each product reformulation, on day 30 and day 60. The calculations are carried out respectively starting from the main skin metric on day 30 and day 60, which are modified by the following percentage values, multiplied by 100:

Impure skin cream

Moisturizing cream

Detergent gel

These values are obtained as shown above for the products at day 0. The main skin metric and the final skin metrics for the 3 exemplary products above are:

As a result, the final skin metrics of the products are based on the starting scientific data (coming from the elaboration of skin test output), then weighted on the personal preferences of the customer deriving form the questionnaire, as so to maximize the compliance and results on skin.

Based on the subsequent skin test and questionnaire outputs, the algorithm can modulate the composition of the products, thus adapting them to the improved characteristics of the skin; for example, in this case, the composition of the Impure skin cream is modified as follows:

Similarly, the composition of the moisturizing cream is modified as follows:

With respect to the detergent gel, the composition changes as follows:

Customer’s satisfaction survey:

1. Evaluate the overall process from the skin tests to the tailor made skincare products’ delivery (from 1 : very complex, to 5: very easy): 5

2. Evaluate the skincare products’ suitability and fittingness for your skin (from 1 : totally unsuitable, to 5: very appropriate): 5

3. Impure skin cream:

3.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

3.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5

3.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

4. Moisturizing cream:

4.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

4.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

5. Detergent gel: 5.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

5.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

Example 4.

Customer’s data

Age: 40

Sex: male

Skin characteristics: skin very dry, with local skin flaking.

Skin test outputs:

Both skin patches react in a moderately marked way — skin very dry

Product processing:

Answers from the questionnaire:

I. Make-up used? > heavy make-up; > average make-up; > light make-up; 0 no makeup

II. Texture preferred? 0 rich and full-bodied texture; > average texture; > light and soft texture; > no preferences

III. Preferred effect on skin? > strong and active; > average and normal; 0 soft and pleasant; > no preferences,

Optional questions:

IV. Consumer age? > < 24 years; > 25-34 years; 0 35-44 years; > 45-54 years; > > 55 years

V. Specific skin issues? 0 skin spots; > sensitivity / redness; 0 eye shadows/bags; > large pores; > blackheads and pimples; 0 wrinkles; > none [multiple-choice allowed] Resulting matrix Questionnaire:

From the skin test outputs, the algorithm generates the composition of 17 skincare products with medium textures tending to lean, with moderate dosage sebum-regulating active ingredients.

Among the 17 products, the algorithm has tagged as “highly recommended” the following:

• Moisturizing cream

• Soothing moisturizing mask

• Moisturizing serum

• Detergent gel

• Skin tonic

• Antiaging cream

• Night cream

• Antiaging serum

• Antiaging eye contour

• Scrub

• Eye Contour Cream, Bags and Dark Circles

• Depigmenting cream

Among the above 12 highly recommended skincare products, only the following 3 products are selected and prosecuted herein below for sake of conciseness: Moisturizing cream

• Enriched texture

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Cl 3- 14 Isoparaffin o Ceramide Mp o Polyisoprene Soothing Moisturizing Mask

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Amylopectin o Sodium hyaluronate o Prunus Amygdalus Dulcis (Sweet Almond) Oil Moisturizing serum

• Enriched texture

• pH ~ 5.5

• main functional moisturizing active ingredients o Oryza Sativa (Rice) Bran Oil o Amylopectin o Sodium hyaluronate o Prunus Amygdalus Dulcis (Sweet Almond) Oil

The basal skin test is performed 0 days after the initial measurement:

The resulting algebraic average is 28.50, which is the main skin metric.

Moisturizing cream

The matrixes characterizing the product are:

Matrix Cursor

Matrix Exclusion

Similar calculations and procedure as per Example 3 are carried out.

Soothing Moisturizing Mask The matrixes characterizing the product are:

Matrix Cursor

Matrix Exclusion

Moisturizing serum

The matrixes characterizing the product are: Matrix Cursor

The skin test is performed 30 and 60 days after the initial measurement: the daily use of the chosen products has resulted in significant improvements in skin parameters:

The same matrix calculation procedure is carried out for each product reformulation, on day 30 and day 60. The calculations are carried out respectively starting from the main skin metric on day 30 and day 60 (complete calculation procedure similar to Example 3)

The main skin metric and the final skin metrics for the 3 exemplary products above are:

As a result, the final skin metrics of the products are based on the starting scientific data (coming from the elaboration of skin test output), then weighted on the personal preferences of the customer deriving form the questionnaire, as so to maximize the compliance and results on skin.

Based on the subsequent skin test outputs and questionnaire , the algorithm can modulate the composition of the products, thus adapting them to the improved characteristics of the skin, for example the composition of the Moisturizing cream is modified as follows:

Similarly, the composition of the Soothing Moisturizing Mask is modified as follows:

With respect to the Moisturizing gel, the composition changes as follows:

Customer’s satisfaction survey:

1. Evaluate the overall process from the skin tests to the tailor made skincare products’ delivery (from 1 : very complex, to 5: very easy): 5

2. Evaluate the skincare products’ suitability and fittingness for your skin (from 1 : totally unsuitable, to 5: very appropriate): 5

3. Moisturizing cream:

3.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

3.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5

3.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

4. Soothing Moisturizing Mask:

4.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

4.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5

4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

5. Moisturizing serum: 5.1 Evaluate the texture of the products you tested (from 1 : very unpleasant, to 5: very pleasant): 5

5.2 Evaluate the effect on skin after one week of application (from 1 : very unsatisfied, to 5: very satisfied): 5 4.3 Evaluate the effect on skin after 60 days of application, including the changes in composition provided along the way, in accordance with intermediate skin tests (from 1 : very unsatisfied, no improvements, to 5: very satisfied, visible improvements): 5

Claims

1. A method of providing tailor made cosmetic skincare products, the method comprising the steps of: a) receiving a picture of a skin test output, the latter being obtained by: i. applying a first sebum indicator on cheek for 3-5 seconds, and a second sebum indicator on forehead for 3-5 seconds, ii. removing the indicators, wherein said indicators show coloured areas corresponding to sebum areas present on cheek and forehead, and iii. taking a picture of the resulting output for cheek and a picture of the resulting output for forehead, b) generating a normalized sebum index for cheek and a normalized sebum index for forehead, by measuring and weighting the coloured areas of each indicator over the initial total area, each index being an number ranging from 0.00 to 100.00, wherein index = 0.00 corresponds to a completely uncoloured indicator (sebum absent), whereas index = 100.00 corresponds to a completely coloured indicator (highest sebum presence), c) generating a main skin metric, which is an number ranging from 0.00 to 100.00, calculated as algebraic average between the normalized sebum index for cheek and the normalized sebum index forehead of step b), d) providing a list comprising 17 skincare products, wherein each skincare product is defined by a composition of active ingredients, as shown in Table 1,

Table 1 :

wherein “wt%” means weight percent based on the skincare product weight, and wherein the wt% of active ingredients reported as a range means that said wt% ranges from the first boundary value (central column) corresponding to the main skin metric = 100.00, up to the second boundary value (right column) corresponding to the main skin metric = 0.00, the remaining single-value wt% being independent of the main skin metric, and e) generating the composition of each skincare product, by proportioning the wt% of the active ingredients to the main skin metric resulted from step c), thus obtaining 17 tailor made skincare products.

2. The method of claim 1, wherein the sebum indicator of step a) is a strip or a patch comprising a layer of an opaque porous polymer matrix, having an additive homogenously dispersed therein, the additive being:

- selected from a group consisting of SiCh, AI2O3, CasPC , talc, (Ca5(PO4)3OH) and mixtures thereof, and

- crystalline and present in a particle size range of 1-300 pm, wherein said layer is to be applied to cheek and forehead in step a), and wherein, when the layer of an opaque porous polymer matrix comes into contact with sebum, the porous polymer matrix becomes transparent to visible light, thus generating coloured transparent areas throughout the initially opaque matrix.

3. The method of claim 1 or 2, wherein step b) is performed by running an image processing algorithm, comprising the following sub-steps of:

— recognizing the sebum-reacted areas of the skin tests, preferably both at the same time in a same image. In preferred embodiments, a pattern recognition algorithm is set a priori, such as the Circular Hough Transform (CHT), the most widely used technique for isolating features of a particular shape within an image;

— isolating the above sebum-reacted areas and using them as a sample in pixels to be analysed;

— analysing the pixel population within sebum-reacted areas and establishing a normalized colour scale with respect to all the pixels detected, both in all colour channels and in the grey channel;

— recording all pixels, test by test, with the sebum-reacted areas of the two indicators taken independently;

— selecting the grey channel, with values for example from 0 to 255 in RGB colour mode, and a colour channel chosen automatically as based on the colour content of the image, with the aim of having the greatest contrast within the reacted areas, where 255 represents the skin test with zero reaction and 0 represents the skin test with 100% reaction, thus resulting in two indexes;

— calculating a weighted average X for the cheek and a weighted average Y for the forehead of all the values from for example 0 to 255 of all the pixels in the various colour and grey channels, where 255 represents the skin test with zero reaction and 0 represents the skin test with 100% reaction, thus resulting in two indexes; and

— obtaining an index for each of the two skin test on a scale from 0.00 to 100.00, where 0.00 represents the skin test with zero reaction and 100.00 represents the skin test with 100% reaction, for a total of two indexes A and B, i.e. normalized sebum index for cheek and a normalized sebum index for forehead respectively, as a result of the following formulas:

A: 100 = (255-X):255 and B: 100 = (255-Y):255

4. The method of any one of claims 1-3, wherein, with respect to the active ingredients shown in Table 1 :

- said soothing agent is selected from Panthenol, Allantoin, Hamamelis Virginiana (Witch Hazel) flower water, Bisabolol, Bentonite, Chamomilla Recutita flower extract, Malva Sylvestris (Mallow) leaf extract, Glycyrrhetinic Acid, Aloe Barbadensis leaf juice, Althaea Officinalis root extract, and mixtures thereof;

- said anionic surfactant is selected from Sodium Cocoyl Hydrolyzed Wheat Protein, Laureth-7, Sodium Lauryl Sulfate, Sodium Laureth Sulfate, Disodium Laureth Sulfosuccinate, Sodium Cocoyl Isethionate, Sodium Cocoyl Sarcosinate, Disodium Cocoyl Glutamate, Sodium Methyl Cocoyl Taurate, and mixtures thereof; - said amphoteric surfactant is selected from Cocamidopropyl Betaine, Cocamidopropyl Hydroxysultaine, Cocamine Oxide, Cocamidopropylamine Oxide, and mixtures thereof; a non-ionic surfactant is selected from Lauryl Glucoside, Cocamide DEA, Cocamide MEA, and mixtures thereof;

- said keratolytic agent is selected from Lactobionic Acid, Mandelic Acid, Salicylic Acid, Glycolic Acid, Lactic Acid, Glutathione, Cysteine, Cystine, Methionine, Gluconolatone, and salts, and mixtures thereof;

- said antioxidant is selected from Tocopheryl Acetate, Superoxide Dismutase, Tocopherol, Ascorbic Acid, Sodium Ascorbyl Phosphate, Ascorbyl Glucoside, Thoictic Acid, and mixtures thereof;

- said mattifying agent is selected from Amylopectin, Kaolin, Talc, Oryza Sativa Starch, Zea Mays Starch, and mixtures thereof;

- said moisturizing agent is selected from Sodium Hyaluronate, Hydrolyzed Glycosaminoglycans, Glycine Soja (Soybean) Protein, Hydrogenated Lecithin, Hydrolyzed Soy Protein, Lecithin, Sericin, PCA (Pyrrolidone Carboxylic Acid), Sodium PCA, Urea, Trehalose, Sorbitol, Maltitol, Betaine, and mixtures thereof;

- said exfoliating agent is selected from Corylus Avellana (Hazel) Shell Powder, Prunus Amygdalus Dulcis (Sweet Almond) Bark Powder, Maranta Arundinacea Root Powder, Olea Europaea (Olive) Seed Powder, and mixtures thereof;

- said emollient is selected from Oryza Sativa (Rice) Bran Oil, Glycerin, Prunus Amygdalus Dulcis (Sweet Almond) Oil, Hydrogenated Ethylhexyl Olivate, Hydrogenated Olive Oil Unsaponifiables, CIO-18 Triglycerides, C18-70 Isoalkane, CIS- 14 Isoparaffin, Ethylhexylglycerin, Borago Officinalis Seed Oil, Olea Europaea (Olive) Fruit Oil, Argania Spinosa Kernel Oil, Oenothera Biennis Oil, Simmondsia Chinensis Seed Oil, Ribes Nigrum Seed Oil, Therobroma Grandiflorum Seed Butter, and mixtures thereof;

- said lipid is selected from Ceramide MP, Butyrospermum Parkii (Shea) Butter, Phytosterols, Squalane, Squalene, Ceramide NP, Ceramide AP, Ceramide EOP, and mixtures thereof;

- said antiaging agent is selected from Aminobutyric Acid, Oligopeptide 4, Caffeine, Retinyl Palmitate, Copper Aspartate, Magnesium Aspartate, Manganese Aspartate, Zinc Aspartate, Azeloyl Bis-Dipeptide-10, Palmitoyl Pentapeptide-3, Dipeptine Dieaminobutyroyl Benzylamide Diacetate, and mixtures thereof;

- said strong detergent is selected from Dimethicone, Olus Oil (vegetable oil), and mixtures thereof;

- said soft detergent is selected from Cyclomethicone, Helianthus Annuus (Sunflowers) Seed Oil, and mixtures thereof;

- said anti-inflammatory agent is selected from Zinc Oxide, Beta-Sitosterol, Boswellia Serrata extract, and mixtures thereof;

- said sebum normalizing agent is selected from Silica, Potassium Azelaoyl Diglycinate, Sulfur, Resveratrol, Pistacia Lentiscus, Azelaic Acid, and mixtures thereof;

- said vasoprotective agent is selected from Escin, Ruscus Aculeatus extract, Aesculus Hippocastanum Seed extract, Centella Asiatica Leaf extract, and mixtures thereof;

- said anti-oedema agent is selected from Bromelain, Calendula Officinalis flower, and mixtures thereof;

- said viscosifier is selected from Polyisoprene, Acrylates Copolymer, and mixtures thereof; and

- said depigmenting agent is selected from Kojic Acid, Niacinamide, Hydroquinone, and mixtures thereof.

5. The method of any one of claims 1-4, wherein, in step e), said proportioning of the wt% of the active ingredients is performed by adopting the following formula for the calculation of each active ingredient, then building up each skincare product:

U = J + (K-J)*S/100 where

U = Customer’s tailored wt% to be calculated

J = wt% at main skin metric 0.00

K = wt% at main skin metric 100.00

S = Customer’s main skin metric

6. The method of any one of claims 1-5, further comprising the step of: a’) receiving the output of a questionnaire comprising at least the following closed-ended questions about cosmetic products preferred:

I. Make-up used? □ heavy make-up (0.05 to 0.20)

□ average make-up (0.02 to 0,15)

□ light make-up (0.01 to 0.10)

□ no make-up (0.00)

II. Texture preferred?

□ rich and full-bodied texture (-0.20 to -0.10)

□ average texture (0.00)

□ light and soft texture (0.10 to 0.20)

□ no preferences (0.00)

III. Preferred effect on skin?

□ strong and active (0.20 to 0.10)

□ average and normal (0.00)

□ soft and pleasant (-0.10 to -0.20)

□ no preferences (0.00)

7. The method of claim 6, wherein the questionnaire of step a’) further comprises the following closed-ended questions:

IV. Consumer age?

□ < 24 years (0.05 to 0.10)

□ 25-34 years (0.02 to 0.05)

□ 35-44 years (-0.02 to 0.02)

□ 45-54 years (-0.05 to -0.02)

□ > 55 years (-0.10 to -0.05)

V. Specific skin issues? [multiple-choice allowed]

□ skin spots (-0.10 to 0.10)

□ sensitivity/redness (-0.10 to 0.10)

□ eye shadows/bags (-0.10 to 0.10)

□ large pores (-0.10 to 0.10)

□ blackheads and pimples (-0.10 to 0.10)

□ wrinkles (-0.10 to 0.10)

□ none (0.00) method of claim 6 or 7, further comprising the step of: f) fine tuning the final wt% of each active ingredient in each skincare product of step e), by

- generating a NxM matrix Questionnaire, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), built up with binary values, i.e. 1 or 0, where 1 indicates that an answer is given to the corresponding question, whereas 0 indicates no answer,

- generating a MxN matrix Cursor for each skincare product, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), the matrix Cursor containing values falling within the ranges associated to each questionnaire’s answer,

- making a matrix product between the matrix Questionnaire and matrix Cursor, for each skincare product, thus obtaining 17 “matrixes Index” NxN,

- summing the values in the main diagonal for each matrix Index, thus obtaining 17 "theoretical index variations",

- generating a final skin metric by algebraically summing the main skin metric calculated at step c) with the respective “theoretical index variation” for each product, which is used as percentage to further weight the main skin metric values, thus the final wt% of each active ingredient in each skincare product of step e), so obtaining 17 tailor made and personalized skincare products. method of any one of claims 6-8, further comprising the step of: g) classifying the 17 skincare products resulted from step e) in “highly recommended” products and “optional” products, by

- generating a NxM matrix Questionnaire, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), built up with binary values, i.e. 1 or 0, where 1 indicates that an answer is given to the corresponding question, whereas 0 indicates no answer,

- generating a MxN matrix Exclusion for each skincare product, with N rows for questions and M columns for answers of the questionnaire’s output of step a’), the matrix Exclusion containing values of 1 or 0, depending on whether the questionnaire’s answers match or not the skincare product, - making a matrix product between the matrix Questionnaire and matrix Exclusion, for each skincare product, thus obtaining 17 “matrixes Recommendations” NxN,

- summing the values in the main diagonal for each matrix Recommendation, thus obtaining 17 numbers, wherein when the number is equal to zero, the corresponding product is tagged and shown as “optional”, whereas when the number is different from zero, the corresponding product is tagged and shown as “highly recommended” to the Customer.

10. The method of claim 9, wherein step g) is performed directly after step e), i.e. on the 17 tailor made skincare products resulting from step e), or preferably after step f), i.e. on the 17 tailor made and personalized skincare products resulting from step f).

11. The method of any one of claims 6-9, comprising the steps a) to e), as well as the steps a’), f) and g), wherein the step g) is performed on the 17 tailor made and personalized skincare products resulting from the step f).

12. The method of any one of claims 6-11, wherein a list of fragrances is proposed to the Customer, to choose which one is to be added to the skincare products’ compositions, the fragrance choice being offered:

- after the 17 tailor made skincare products have resulted from step e),

- after the 17 tailor made and personalized skincare products have resulted from step f), or

- after the 17 classified, tailor made and personalized skincare products have resulted from step g).