阅读说明：本技术 用于对个性化护肤产品制定配方的系统和方法 (System and method for formulating a personalized skin care product ) 是由 S·萨尔维 M·毛平 N·哈希希 于 2019-01-28 设计创作，主要内容包括：用于针对用户对个性化护肤产品制定配方的系统和方法。反映用户的真皮信息的数据输入(例如,水化水平测量结果、油水平测量结果和反映皮肤担忧集合的用户的皮肤的照片)由计算设备采集,且被使用以确定归一化得分集合。基于归一化得分来生成皮肤健康数据集并且将皮肤健康数据集存储在存储器中。基于皮肤健康数据集来确定皮肤健康度量并且将皮肤健康度量存储在存储器中。计算设备使用机器学习框架、基于用户皮肤健康数据集来确定一个或多个第一护肤产品配方。(一个或多个)配方可以用于针对用户制造一个或多个定制化护肤产品,且可以迭代地随时间改善,例如通过随时间采集来自用户的附加数据。(Systems and methods for formulating a formula for a personalized skin care product for a user. Data inputs reflecting dermal information of the user (e.g., hydration level measurements, oil level measurements, and photographs of the user's skin reflecting a set of skin concerns) are captured by a computing device and used to determine a set of normalized scores. A skin health data set is generated based on the normalized scores and stored in a memory. A skin health metric is determined based on the skin health dataset and stored in a memory. The computing device determines one or more first skin care product formulas based on the user skin health data set using a machine learning framework. The formula(s) can be used to manufacture one or more customized skin care products for the user, and can be iteratively improved over time, such as by collecting additional data from the user over time.)

1. A computerized method of formulating a skin care product for a user, the method comprising:

receiving, by a computing device, data input comprising one or more hydration level measurements of a user's skin, one or more oil level measurements of the user's skin, and a photograph of the user's skin reflecting a set of skin concerns;

determining, by the computing device, a normalized hydration index score based on the one or more hydration level measurements;

determining, by the computing device, a normalized oil index score based on the one or more oil level measurements;

determining, by the computing device, a set of normalized severity scores corresponding to a set of skin concerns of a user based on a photograph of the user's skin;

generating, by the computing device, a first skin health data set comprising the normalized hydration index score, the normalized oil index score, and the set of normalized severity scores;

storing, by the computing device, the first skin health data set in a first memory in electronic communication with the computing device;

determining, by the computing device, a first skin health metric based on the first set of skin health data;

storing, by the computing device, the first skin health metric in a second memory in electronic communication with the computing device;

determining, by the computing device, one or more first skin care product formulas based on the first skin health metric and the first skin health dataset using a machine learning framework operating on the computing device; and

storing, by the computing device, the one or more first skin care product formulations in a third memory in electronic communication with the computing device.

2. The method of claim 1, further comprising:

receiving, by the computing device, one or more additional data inputs reflecting a change in at least one of hydration level measurements, oil level measurements, or skin concerns after use of the one or more first skin care product formulas by a user;

generating, by the computing device, a second skin health data set based on the one or more additional data inputs by: (i) calculating, by the computing device, a percentage change in hydration level measurements, oil level measurements, and the normalized severity score; and (ii) calculating, by the computing device, the second skin health data set based on the first skin health data set and the percentage change; and

determining, by the computing device, one or more second skin care product formulas based on the second set of skin health data using a machine learning framework operating on the computing device.

3. The method of claim 1, wherein the data input further comprises at least one of a user's age, gender, race, or occupation.

4. The method of claim 1, wherein the photograph is taken with at least one of visible light or ultraviolet light.

5. The method of claim 1, wherein the one or more data inputs include information reflecting at least one of a temperature, a humidity, or an ambient ultraviolet index of the location of the user.

6. The method of claim 1, wherein the one or more data inputs include information reflecting at least one of user genetics, medical history, diet, water intake, smoking habits, known allergies, alcohol habits, sleep quality, stress levels, time spent in front of an electronic screen, or sun exposure.

7. The method of claim 1, wherein the one or more data inputs include information reflecting at least one of a user-reported skin health assessment, skin care product usage, past skin reactions, skin care goals, skin care concerns, skin care absorption, or texture preferences.

8. The method of claim 1, wherein the one or more data inputs include at least one of an elasticity measurement of the user's skin, a wrinkle measurement of the user's skin, or a surface pH level of the user's skin.

9. The method of claim 1, wherein the first skin health dataset includes information reflecting at least one of wrinkles, dark spots, dark circles, textures, acne, sun damage, pore size, redness, or other skin damage of the user.

10. The method of claim 1, wherein the first skin care product formulation comprises information reflecting active ingredients, preservatives, and dosages.

11. The method of claim 1, further comprising: generating, by the computing device, first formulation instructions for manufacturing a first skin care product by a formulation specialist or machine based on the first skin health data set.

12. The method of claim 1, further comprising: generating, by the computing device, one or more recommendations for adjustments to a lifestyle, diet, or overall health state of a user based on the first skin health dataset to achieve a desired skin result.

13. The method of claim 1, further comprising: generating, by the computing device, a personalized skin care routine based on the first skin health dataset, the personalized skin care routine comprising a recommendation for at least one of a cleanser, a serum, a facial oil, a moisturizer, a dietary supplement, or a sunscreen.

14. The method of claim 1, further comprising: (i) generating, by the computing device, a user display data set for interpretation and display by a user computing device in electronic communication with the computing device; (ii) and sending the user display data set to the user computing device.

15. The method of claim 1, further comprising: receiving, by the computing device, a user attestation of the first skin care product formulation prior to storing the first skin care product formulation in memory.

16. A method of manufacturing a skin care product for a user, the method comprising:

receiving, by a manufacturing system, a product recipe having a unique skin identifier for the user and based on the user's unique skin health data set, the product recipe comprising at least one ingredient;

synthesizing, by the manufacturing system, a customized skin care product according to the product formulation;

bottling, by the manufacturing system, the customized skin care product in a container; and

labeling, by the manufacturing system, the container with a label displaying the at least one ingredient.

17. A computing system for formulating a formula for a skin care product for a user, the system comprising:

a computing device configured to perform operations comprising:

receiving data input comprising one or more hydration level measurements of the user's skin, one or more oil level measurements of the user's skin, and a photograph of the user's skin reflecting a set of skin concerns;

determining a normalized hydration index score based on the one or more hydration level measurements;

determining a normalized oil index score based on the one or more oil level measurements;

determining a set of normalized severity scores corresponding to a set of skin concerns of a user based on a photograph of the user's skin;

generating a first skin health data set comprising the normalized hydration index score, the normalized oil index score, and the set of normalized severity scores;

storing the first skin health data set in a first memory in electronic communication with the computing device;

determining a first skin health metric based on the first skin health dataset;

storing the first skin health metric in a second memory in electronic communication with the computing device;

determining, using a machine learning framework operating on the computing device, one or more first skin care product formulas based on the first skin health metric and the first skin health dataset; and

storing the one or more first skin care product formulations in a third memory in electronic communication with the computing device.

18. The system of claim 17, further comprising a user computing device in electronic communication with the computing device, the user computing device to collect the data input and provide the data input to the computing device.

19. The system of claim 17, wherein the first storage and the second storage are included in a database in electronic communication with the computing device.

20. A computerized method of formulating first and second skin care products for a user, the method comprising:

receiving, by a computing device, one or more first data inputs reflecting dermis information of the user;

generating, by the computing device, a first skin health data set for the user based on the one or more first data inputs, the first skin health data set including one or more normalized scores reflecting the one or more first data inputs;

storing, by the computing device, the first skin health data set in a first storage in electronic communication with the computing device;

determining, by the computing device, a first skin care product formulation based on the first skin health data set;

storing, by the computing device, the first skin care product formulation in a second storage in electronic communication with the computing device;

receiving, by the computing device, one or more second data inputs reflecting a change in the first data input after using a first skin care product based on the first skin care product formulation;

generating, by the computing device, a second skin health data set for the user based on the one or more first data inputs and the one or more second data inputs;

storing, by the computing device, the second set of skin health data in a third storage in electronic communication with the computing device;

determining, by the computing device, a second skin care product formulation based on the second set of skin health data; and

storing, by the computing device, the second skin care product formulation in a fourth memory in electronic communication with the computing device.

Technical Field

The present application relates generally to systems, methods, and apparatus, including computer programs and algorithms, for formulating a skin care product. More particularly, the present application relates to systems and methods for formulating a personalized skin care product and recommending a personalized skin care product routine based on user-specific data.

Background

Many or most skin care products today are targeted to a large number of consumers, but when skin care products are formulated for the mass market, several problems occur. One problem is how to accommodate the largest possible number of diverse skin types for any given product claim made. This may explain the proliferation of skin "type" products in the market (which may include, for example, greasy, dry, combination, dusting prone, sun sensitive, allergy tested, poor texture, or large pores). When targeting the mass market, manufacturers must balance content that is economically viable for them relative to the number of products available in the market with the number of customers they can attract from the market.

Several companies are today creating "customized" products for customers. The methods employed by these companies generally fall into two groups: (1) using self-reported answers related to skin concerns (concern) to recommend existing products; or (2) use self-reported answers related to skin concerns to design customized skin care formulations. One problem with both approaches is: self-reported data may be unreliable, for example, because customers rarely know objectively what their skin is. The first approach also suffers from the constraint of a limited set of potential products, all of which have typically been created for the mass market. The second approach has suffered from limited validity of the results.

Disclosure of Invention

Accordingly, the present invention provides a new framework, comprising a computing system and associated computing methods, algorithms and modules, for: (1) determining skin health and/or problems at one or more points in time; and (2) providing unique skin care product recommendations, formula parameter recommendations, and/or product routines to individual users on a customized, persistent (e.g., iterative) basis. Thus, the present invention enables personal skin care product and regimen creation, recommendation, and improvement over time.

In some embodiments, the invention may be implemented on one or more computerized systems located at a retail location (e.g., by a salesperson or by a consumer self-instructing without assistance), a spa or office (e.g., by a cosmetologist, dermatologist or dermatologist, or by a customer self-instructing without assistance), or at home (e.g., by a consumer without further assistance). In some embodiments, the invention comprises: data specific to an individual user is collected, such as objective dermis data, visual skin data, demographic data, environmental data, genetic data, dietary data, preference data, and other data. In some embodiments, the computer-implemented machine learning algorithm uses data provided to specify unique skin care product formulations, existing products, and ingredient-specific recommendations. In some embodiments, the present invention recommends lifestyle, diet, and/or overall health tips to achieve a desired skin result.

After using the recommended existing product(s), personalized skin care product(s), or implementing lifestyle or dietary changes, the user may provide feedback on the efficacy of the product(s) and update his or her skin data points outlined above. The product recipe(s) can then be improved based on the recommendations generated by the algorithm(s). These reformulations may occur due to, for example, seasonal changes, location or environmental changes, observed changes in the user's skin, and expected changes in the user's skin. In some embodiments, recommendation, use, feedback, and revised feedback loops aid in the success of the invention. In some embodiments, the present invention uses prior feedback and/or aggregated skin data and patterns to make new or revised recommendations.

The present invention overcomes the prior limitations in formulating skin products for the mass market by providing a customized product designed based on unique skin data of an individual. Thus, customized products are created to address an individual's unique skin concerns and/or suit an individual's preferences, and may vary based on the environment, lifestyle, and how an individual's skin changes over time. In some embodiments, aggregated skin data from multiple users allows predictive analytics and machine learning to be used to recommend ingredients that are found to be safest and most effective for a user based on his or her individual skin, and to improve recommendations based on individual responses and preferences. In some embodiments, feedback received from the users is fed back into one or more algorithms to further improve the recommendation and recommend more accurate and effective ingredients tailored to each user.

In some embodiments, the present invention uses user-specific data (e.g., dermal data, visual skin data, demographic data, environmental data, genetic data, dietary data, preference data, and other data) in systems and methods that utilize one or more computerized (e.g., machine learning or deep learning) algorithms to make unique, personal skin care products, other health status products, and personalized recommendations on an ongoing basis (e.g., one process for an in-person setting and another process for a home setting). In some embodiments, creating a feedback loop of recommendations, uses, outcomes, and revisions helps to ensure that each product provides benefits to the user, and that the skin care products, health status products, and personalized recommendations for each user evolve as his or her concerns, environment, and skin change over time.

Examples of possible, but non-limiting, data collection techniques and associated skin properties are listed in the following table:

in one aspect, the invention features a computerized method of formulating a skin care product for a user. The method comprises the following steps: receiving, by a computing device, data input comprising one or more hydration level measurements of a user's skin, one or more oil level measurements of the user's skin, and a photograph of the user's skin reflecting a set of skin concerns. The method further comprises the following steps: determining, by the computing device, a normalized hydration index score based on the one or more hydration level measurements. The method further comprises the following steps: determining, by the computing device, a normalized oil index score based on the one or more oil level measurements. The method further comprises the following steps: determining, by the computing device, a set of normalized severity scores corresponding to a set of skin concerns of a user based on a photograph of the user's skin. The method further comprises the following steps: generating, by the computing device, a first skin health data set comprising the normalized hydration index score, the normalized oil index score, and the set of normalized severity scores. The method further comprises the following steps: storing, by the computing device, the first skin health data set in a first memory in electronic communication with the computing device. The method further comprises the following steps: determining, by the computing device, a first skin health metric based on the first set of skin health data. The method further comprises the following steps: storing, by the computing device, the first skin health metric in a second memory in electronic communication with the computing device. The method further comprises the following steps: determining, by the computing device, one or more first skin care product formulas based on the first skin health metric and the first skin health dataset using a machine learning framework operating on the computing device. The method further comprises the following steps: storing, by the computing device, the one or more first skin care product formulations in a third memory in electronic communication with the computing device.

In some embodiments, the method comprises: receiving, by the computing device, one or more additional data inputs reflecting a change in at least one of hydration level measurements, oil level measurements, or skin concerns after use of the one or more first skin care product formulas by a user; and/or generating, by the computing device, a second skin health data set based on the one or more additional data inputs by: (i) calculating, by the computing device, a percent change in hydration level measurements, oil level measurements, and the normalized severity score (or a precursor to such data, e.g., raw data or pre-processed data, such as a black-to-white ratio described in further detail below); and (ii) calculating, by the computing device, the second skin health data set based on the first skin health data set and the percentage change; and/or determining, by the computing device, one or more second skin care product formulas based on the second skin health data set using a machine learning framework operating on the computing device.

In some embodiments, the data input further comprises at least one of a user's age, gender, race, or occupation. In some embodiments, the photograph is taken with at least one of visible light or ultraviolet light. In some embodiments, the one or more data inputs include information reflecting at least one of a temperature, a humidity, or an ambient uv index of the location of the user. In some embodiments, the one or more data inputs include information reflecting at least one of user genetics, medical history, diet, water intake, smoking habits, known allergies, alcohol habits, sleep quality, stress level, time spent in front of an electronic screen, or sun exposure. In some embodiments, the one or more data inputs include information reflecting at least one of a user-reported skin health assessment, skin care product usage, past skin reactions, skin care goals, skin care concerns, skin care, absorption, or texture preferences. In some embodiments, the one or more data inputs include at least one of an elasticity measurement of the user's skin, a wrinkle measurement of the user's skin, or a surface pH level of the user's skin. In some embodiments, the first skin health data set includes information reflecting at least one of wrinkles, dark spots, dark circles, texture, acne, sun damage, pore size, redness, or other skin damage of the user. In some embodiments, the first skin care product formulation includes information reflecting an active ingredient, a preservative, a dosage, and/or a unique user skin identifier.

In some embodiments, the method further comprises: generating, by the computing device, first formulation instructions for manufacturing a first skin care product by a formulation specialist or machine based on the first skin health data set. In some embodiments, the method further comprises: generating, by the computing device, one or more recommendations for adjustments to a lifestyle, diet, or overall health state of a user based on the first skin health dataset to achieve a desired skin result. In some embodiments, the method further comprises: generating, by the computing device, a personalized skin care routine based on the first skin health dataset, the personalized skin care routine comprising a recommendation for at least one of a cleanser, a serum, a facial oil, a moisturizer, a dietary supplement, or a sunscreen. In some embodiments, the method further comprises: (i) generating, by the computing device, a user display data set for interpretation and display by a user computing device in electronic communication with the computing device; and/or (ii) transmit the user display data set to the user computing device. In some embodiments, the method further comprises: receiving, by the computing device, a user attestation of the first skin care product formulation prior to storing the first skin care product formulation in memory.

In another aspect, the invention features a method of making a skin care product for a user. The method comprises the following steps: receiving, by a manufacturing system, a product recipe having a unique skin identifier for the user and based on the user's unique skin health data set. In some embodiments, the product formulation comprises at least one ingredient. The method further comprises the following steps: synthesizing, by the manufacturing system, a customized skin care product according to the product formulation. The method further comprises the following steps: bottling, by the manufacturing system, the customized skin care product in a container. The method further comprises the following steps: labeling, by the manufacturing system, the container with a label displaying the at least one ingredient.

In another aspect, the invention features a computing system for formulating a skin care product for a user. The system includes a computing device configured to perform the following functions: (i) receiving data input comprising one or more hydration level measurements of the user's skin, one or more oil level measurements of the user's skin, and a photograph of the user's skin reflecting a set of skin concerns; (ii) determining a normalized hydration index score based on the one or more hydration level measurements; (iii) determining a normalized oil index score based on the one or more oil level measurements; (iv) determining a set of normalized severity scores corresponding to a set of skin concerns of a user based on a photograph of the user's skin; (v) generating a first skin health data set comprising the normalized hydration index score, the normalized oil index score, and the set of normalized severity scores; (vi) storing the first skin health data set in a first memory in electronic communication with the computing device; (vii) determining a first skin health metric based on the first skin health dataset; (viii) storing the first skin health metric in a second memory in electronic communication with the computing device; (ix) determining, using a machine learning framework operating on the computing device, one or more first skin care product formulas based on the first skin health metric and the first skin health dataset; and (x) storing the one or more first skin care product formulas in a third memory in electronic communication with the computing device. In some embodiments, the system includes a user computing device in electronic communication with the computing device, the user computing device to collect the data input and provide the data input to the computing device. In some embodiments, the first storage and the second storage are included in a database in electronic communication with the computing device.

In another aspect, the invention features a computerized method of formulating a first and second skin care product for a user. The method comprises the following steps: receiving, by a computing device, one or more first data inputs reflecting dermis information of the user. The method further comprises the following steps: generating, by the computing device, a first skin health data set for the user based on the one or more first data inputs, the first skin health data set including one or more normalized scores reflecting the one or more first data inputs. The method further comprises the following steps: storing, by the computing device, the first skin health data set in a first storage in electronic communication with the computing device. The method further comprises the following steps: determining, by the computing device, a first skin care product formulation based on the first skin health data set. The method further comprises the following steps: storing, by the computing device, the first skin care product formulation in a second memory in electronic communication with the computing device. The method further comprises the following steps: receiving, by the computing device, one or more second data inputs reflecting a change in the first data input after using a first skin care product based on the first skin care product formulation. The method further comprises the following steps: generating, by the computing device, a second skin health data set for the user based on the one or more first data inputs and the one or more second data inputs. The method further comprises the following steps: storing, by the computing device, the second set of skin health data in a third storage in electronic communication with the computing device. The method further comprises the following steps: determining, by the computing device, a second skin care product formulation based on the second set of skin health data. The method further comprises the following steps: storing, by the computing device, the second skin care product formulation in a fourth memory in electronic communication with the computing device.

In another aspect, the invention features a computerized method of training a machine learning framework to generate one or more skin care product formulas. The method comprises the following steps: receiving, by a computing device, first data input for a plurality of users, the first data input including one or more hydration level measurements of each user's skin, one or more oil level measurements of each user's skin, and a photograph of each user's skin reflecting a set of skin concerns. The method further comprises the following steps: determining, by the computing device, for each user, a corresponding first skin health data set and a corresponding first skin health metric based on the first data input. The method further comprises the following steps: determining, by the computing device, one or more recommended first skin care product formulas for each user based on the first skin health metric and/or the first skin health data set. The method further comprises the following steps: receiving, by the computing device, one or more second data inputs reflecting a change in the first data input after using a first skin care product based on the first skin care product formulation. The method further comprises the following steps: combining, by the computing device, the one or more second data inputs with the first data input and the first skin health data set to create a training data set. The method further comprises the following steps: calculating, by the computing device, a second skin health metric based on the one or more second data inputs. The method further comprises the following steps: determining, by the computing device, a machine learning model using the second health data set and a machine learning framework. The method further comprises the following steps: determining, by the computing device, for each user, one or more associations between data inputs for the user and one or more first skin care product formulas for the user, each association based on a corresponding first skin health dataset and a corresponding first skin health metric for each user. The method further comprises the following steps: storing, by the computing device, the model in a memory in electronic communication with the computing device. In some embodiments, other data inputs may be measured, input, transformed, calculated and/or manipulated via algorithms as described above with respect to other aspects of the invention.

Drawings

The advantages of the invention described above, together with further advantages, may be better understood by reference to the following description taken in conjunction with the accompanying drawings. The figures are not necessarily to scale; instead, emphasis is generally placed upon illustrating the principles of the invention.

FIG. 1 is a schematic diagram of a computing system for formulating a skin care product for a user, according to an illustrative embodiment of the invention.

FIG. 2 is a flowchart illustrating a method of formulating a skin care product for a user according to an illustrative embodiment of the invention.

Fig. 3 is a flowchart illustrating a computerized method of calculating a normalized hydration index score for a user's skin in accordance with an illustrative embodiment of the invention.

FIG. 4 is a flowchart illustrating a computerized method of calculating a normalized oil index score for a user's skin in accordance with an illustrative embodiment of the invention.

FIG. 5 is a flowchart illustrating a computerized method of calculating a set of normalized severity scores for a user's skin in accordance with an illustrative embodiment of the invention.

FIG. 6 is a diagram illustrating exemplary components of a skin health data set, according to an illustrative embodiment of the invention.

Fig. 7 is a schematic diagram illustrating a computerized skin care formulation process according to an illustrative embodiment of the invention.

FIG. 8 is a schematic diagram illustrating a method of manufacturing a personalized skin care product for a user, according to an illustrative embodiment of the invention.

Fig. 9A-9C are screen shots of a user questionnaire eliciting certain dermis data, according to an illustrative embodiment of the invention.

Fig. 10 is a screen shot of a skin care product recommendation according to an illustrative embodiment of the invention.

FIG. 11 is a flowchart of a computerized method of formulating a skin care product for a user, according to an illustrative embodiment of the invention.

FIG. 12 is a flowchart of a method of manufacturing a skin care product for a user, according to an illustrative embodiment of the invention.

Fig. 13 is a flowchart of a computerized method of formulating first and second skin care products for a user, according to an illustrative embodiment of the invention.

Detailed Description

FIG. 1 is a schematic diagram of a computing system 100 for user-formulating a skin care product according to an illustrative embodiment of the invention. The computing system 100 includes a server computing device 104 (or a different back-end computing device) and a user computing device 108 (e.g., a mobile phone, tablet, or a different front-end computing device) in electronic communication (e.g., via the internet) with the server computing device 104. During operation, the user computing device 108 captures a data input 112 that reflects the user's dermis information (e.g., information related to skin characteristics that may be used by the system 100), for example, via an application installed on the user computing device 108. In some embodiments, data input 112 includes one or more dermal measurements (e.g., one or more hydration level measurements of the user's skin and/or one or more oil level measurements of the user's skin) and one or more other data inputs (e.g., one or more photographs of the user's skin taken with visible and/or ultraviolet light using the user's smartphone camera or another camera device) that reflect a set of skin concerns (e.g., wrinkles, dark spots, dark circles, acne, sun damage, redness, or other skin damage). In some embodiments, the data input 112 includes other variables, such as at least one of the user's age, gender, race, or occupation. In some embodiments, the data input 112 includes information reflecting at least one of a temperature, a humidity, or an ambient ultraviolet index of the user's location. In some embodiments, data input 112 includes information reflecting at least one of the additional variables shown and described in more detail below in FIG. 6. In some embodiments, some of the data inputs 112 are captured via a user interface (such as the user interface shown and described below in fig. 9).

After the data inputs 112 are captured, they are sent to the server computing device 104 via electronic communication (e.g., over an electronic transmission medium). The server computing device 104 receives the data input 112 and determines (e.g., calculates) one or more transformed skin health variables, such as a normalized hydration score, a normalized oil index score, and/or a set of normalized severity scores for a set of skin concerns for the user's skin, based on the data input 112. The specific algorithm used may be as shown in more detail below in fig. 3-5. The server computing device 104 then generates a first skin health data set (and potentially other information, e.g., of the type shown below in fig. 6) that includes the calculated score and stores them in a first memory 116A in electronic communication with the server computing device 104. The server computing device 104 then determines one or more first skin care product formulas (and/or skin care routines) based on the first skin health dataset using a machine learning (e.g., deep learning) framework operating on the server computing device 104. In some embodiments, the machine learning framework includes an ensemble of GRU or LSTM recurrent neural networks and optimization algorithms. The server computing device 104 then stores the one or more first skin care product formulas (and/or skin care routines) in a second memory 116B in electronic communication with the server computing device 104.

After performing the above calculations, the server computing device 104 sends the calculated first skin health data set, the recommended skin care product formula, and/or the recommended skin care routine to the user computing device 108 for display to the user in the recommended form. The recommendation includes one or more personalized skin care products in a particular routine for utilization by the user (e.g., on a temporary or permanent basis). The product may have ingredients and other aspects that are specific to the user and optimized to help the user achieve his or her maximum skin health. In some embodiments, the recommendations are displayed for the user via a user interface of the user computing device 108 (e.g., in the form shown and described in more detail below in fig. 10).

After the user has adopted the recommendation for a period of time, it is expected that one or more aspects of the prior data input 112 may change in response to the user adopting the recommendation. The computing system 100 may receive updated data inputs reflecting changes in prior data inputs and generate further skin health data sets over time, and thus iteratively better define optimal skin care recommendations for the user. In some embodiments, the server computing device 104 can receive one or more additional data inputs reflecting a change in at least one of the hydration level measurements, oil level measurements, or skin photography reflecting skin concerns after use of the one or more first skin care product formulas by the user. In some embodiments, the server computing device 104 may generate a second skin health data set based on the one or more additional data inputs, for example by: (i) calculating, by the computing device, a percentage change in the hydration level measurement, the oil level measurement, and the normalized severity score; and (ii) calculating, by the computing device, a second skin health data set based on the first skin health data set and the percentage change. In some embodiments, the server computing device 104 can determine one or more second skin care product formulas based on the second skin health data set using a machine learning framework operating on the server computing device 104. Additional memory (e.g., a third memory, a fourth memory, etc., corresponding to elements 116C, 116D, etc.) may be made available and in electronic communication with the server computing device 104 for storing further information generated and/or received by the server computing device 104. The memory components 116A, 116B, 116C, 116D, etc. may be stored in a single database 116 in electronic communication with the server computing device 104.

FIG. 2 is a flowchart 200 illustrating a more detailed method of formulating a skin care product for a user according to an illustrative embodiment of the invention. The method steps may be implemented using the computing system 100 shown and described above in fig. 1. In a first step 201, the user provides the mobile device application with a set of answers to the intake survey questions, one or more photographs of the user's skin and one or more measurements provided via the user device. In a second step 202, the computing device creates a skin health data set, e.g., as described above. In a third step 203, the computing device calculates a skin health metric. The skin health metric may be based on a scorecard dataset having points associated with each component of the skin health metric. For example, consider the following case: wherein the four data points in the score card are the smoking habit, severity score, hydration index and oil index. For example, if one never smokes, this may equate to 100 points; if the person does not smoke very frequently, this may equate to point 0. Similarly, the severity score, hydration index, and oil index are translated into a scale of 0-100, where 0 represents least healthy and 100 represents most healthy. Thus, since a person who is never smoking has one skin problem (e.g., discoloration) with a severity score of 50 and a hydration index and an oil index of 60 each, his or her skin health metric will equal 270. In a fourth step 204, the computing device determines one or more ingredient-dose combinations (see 204A) that will be effective and appropriate (e.g., most effective and appropriate) to improve the skin health of the user given the input data of the user and/or the computing device determines diet and lifestyle changes that will be effective to improve the skin health of the user given the input data of the user (see 204B). In a fifth step 205, the computing device identifies a product type corresponding to the previously determined ingredient-dose combination. In a sixth step 206, the computing device narrows the product-ingredient-dose combination to a complement, e.g., a recommended routine. In a seventh step 207, the computing device displays recommendations for the user, such as routines, diets, and lifestyle changes.

Fig. 3 is a flowchart 300 illustrating a computerized method of calculating a normalized hydration index score for a user's skin in accordance with an illustrative embodiment of the invention. The method may be implemented on a computing device (e.g., the server computing device 104 shown and described above in fig. 1). In a first step 301, hydration measurements are taken at one or more locations on the user's skin (e.g., in area A, B or the like, as shown). The measurements may be taken by performing a keratinocyte test that uses a medical adhesive to measure skin "peeling" or exfoliation of the outer layer of skin. The user may take a picture of the completed test on the medical adhesive. A computer vision algorithm trained on a dataset of keratinocyte test results may estimate hydration level measurement levels (e.g., percent hydration) of the skin. Each hydration level measurement may be converted to a hydration measurement number. In some embodiments, a bioimpedance electrical analysis tool may also be used to collect input measurements. In a second step 302, hydration measurement numbers are averaged. Hydration measurement numbers from several parts of the user's face and body may be weighted based on the relative importance dataset (e.g., for a facial product recipe, a face may have a higher weight than a neck). In a third step 303, the average is compared to a dataset of average hydration levels acquired for a set of reference users (e.g., for comparable regions or skin locations) and a normalized hydration index score (e.g., 1-9 or another suitable numerical scale) is generated. In a fourth step 304, the normalized hydration index score is used as an input into the skin health data set for the user (e.g., the first skin health data set) and/or a component of the skin health data set for the user is recorded.

FIG. 4 is a flowchart 400 illustrating a computerized method of calculating a normalized oil index score for a user's skin in accordance with an illustrative embodiment of the invention. The method may be implemented on a computing device (e.g., the server computing device 104 shown and described above in fig. 1). In a first step 401, oil measurements are taken at one or more locations on the user's skin (e.g., in region A, B or the like, region A, B or the like may correspond to the same region A, B or the like shown and described above). The measurement results may be collected by performing a sebum test. The sebum test may use an oil-absorbing film on a black background-for example, oil or sebum from the skin makes the film on the top layer transparent on contact so that a black gradient appears (the darker the gradient pattern, the more greasy the skin). The user takes a picture of the completed test. A computer vision algorithm trained on the data set of sebum test results estimates the raw oil measurement level (e.g., percent oil) of the skin. Each oil level measurement may be converted to an oil measurement number. In some embodiments, a photometric sensor and/or a bioimpedance electrical analysis tool may also be used to collect input measurements. In a second step 402, the oil measurement numbers are averaged. Raw oil measurements from multiple parts of the user's face and body may be weighted based on the relative importance data sets (e.g., as in the application described above, the face may be weighted higher than the neck). In a third step 403, the average is compared to a dataset of average oil levels collected for a set of reference users (e.g., for comparable regions or skin locations) and a normalized oil index score (e.g., 1-9 or another suitable numerical scale) is generated. In a fourth step 404, the normalized oil index score is used as an input into and/or component of the skin health data set for the user.

FIG. 5 is a flowchart 500 illustrating a computerized method of calculating a set of normalized severity scores for a user's skin in accordance with an illustrative embodiment of the invention. The method may be implemented using a computer vision diagram implemented on a computing device (e.g., server computing device 104 shown and described above in fig. 1). In a first step 501, a picture of the user's skin is taken, for example, on the user's computing device or in a physical storage location. In a second step 502, the computer vision engine determines any skin problems of the user. In one embodiment, the computer vision engine first makes lighting adjustments based on a quadratic model of global lighting. Second, multiple copies of the illumination-adjusted photograph are created, e.g., one copy for each skin issue. Different computer algorithms may be used to evaluate each skin problem. For example, to assess whether a user has wrinkles, one of the image copies may be transformed using a Gabor (Gabor) or blacksen (Hessian) filter and/or image morphology. The algorithm may calculate the ratio of white to black in the image after conversion to grayscale. If the ratio is above a preset threshold, the algorithm determines that the user has wrinkles.

In a third step 503, the photograph is divided into a plurality of regions, e.g., region a, region B, etc. Specific areas of skin may be selected to measure the severity of skin problems (e.g., left cheek, right cheek, forehead, under eye, etc.). An area map may be overlaid on top of the photograph. Using the transformed copies of the photographs, an algorithm may use a region map to divide each transformed image copy into regions. In a fourth step 504, a severity score may be assigned to each region identified in step 503 for each skin issue identified in step 502 (e.g., for a skin photograph having N skin issues divided into M regions, the severity score may occupy an N × M matrix). Different computer algorithms may be used for each skin problem to assess severity. For example, for a user with fading, the image may be transformed into the HSV color space. Using the line fitting thresholding method, the pigmentation appears white in gray. The algorithm calculates the ratio of white to black. After comparison with the data sets of other users, the ratios are normalized to an index. In a fifth step 505, an average severity score is calculated for each skin issue, e.g., a vector representing dimension N of the set of average severity scores for each of the N identified skin issues is generated. In a sixth step 506, the vector is used as an input into the skin health data set for the user and/or components of the skin health data set for the user are recorded.

In some embodiments, the computer vision algorithm makes lighting adjustments based on a quadratic model of global lighting. Computer vision algorithms analyze an area of the user's skin (e.g., the face) to determine whether the user has skin problems (e.g., binary determination of "yes" or "no"), such as wrinkles, blocked pores, rashes (broakout), redness, or discoloration. The computer vision algorithm may be based on a trained machine learning model, such as an anomaly detection model or a convolutional neural network. Different computer algorithms may be used for each skin problem to assess the severity of the problem. As an example, to evaluate wrinkles of a user, a region of a skin image may be transformed using a gabor or blackson filter and image morphology. The algorithm may then calculate a white to black gradient after conversion to grayscale. The gradient score may then be normalized to an index after comparison with the other user's data sets. As another example, to assess skin fading of a user, a region of a skin image may be transformed into HSV color space. The pigmentation in the gray scale can be extracted using a line fitting thresholding method. The algorithm calculates the gradient of white to black after conversion to grey. After comparing the gradient score to the data sets of other users, the gradient score is normalized to an index.

FIG. 6 is a diagram 600 illustrating exemplary components of a skin health data set in accordance with an illustrative embodiment of the present invention. The skin health data set may comprise one or more of the components included in fig. 6. Those skilled in the art will readily appreciate that associations between skin health and/or skin product recommendations may also be plotted using other variables, and that the exemplary data set shown in fig. 6 will be considered to be a significant but not exhaustive list of all possible skin variables. In some embodiments, the skin health data set includes variables that can be categorized in the following groups: (i) in vivo; (ii) vision; (ii) an environment; (iv) a personal history; (v) a lifestyle; and (vi) skin history. Each of the variables may be stored in a single database or in a separate memory, for example in an Excel spreadsheet, in a plain text file, or in HTML form. Each of these variables may represent or provide a basis for input (e.g., 112 as shown and described above in fig. 1).

In one example relating to weather and UV, a computer program enters the user's zip code into a common online weather database and stores in a temporary data set the temperature (Fahrenheit) value, humidity value (percent), and UV index for each of the last thirty days. A computer algorithm calculates the mean and variance of each of these variables. The mean and variance of each of these data inputs, as calculated by the computer algorithm, are stored in the first skin health data set. For several of the personal history (e.g., genetics) and/or lifestyle (e.g., genetics) data inputs, the computer algorithm may compare the data input values to a data table with predetermined buckets (buckets) of variables. The bucket values and raw data inputs may in turn be stored in a first skin health data set. For several of the skin history data entries (e.g., products used), the user input may be matched to the official database (e.g., the current skin care product used may be matched to the official product name by searching through the skin care product database, manually or by barcode). In examples involving user preferences, a user may be assigned to a preference profile based on a response to a preference indicator question or a sample ingredient test. In one embodiment, a data set associated with the response to the profile and a computer matching algorithm may be used to determine the user's preference profile. In another embodiment, a collaborative filtering model trained on ratings of products and ratings of skin care products by users is used to assign users to preference profiles.

Fig. 7 is a schematic diagram 700 illustrating a computerized skin care formulation process according to an illustrative embodiment of the invention. The method may be implemented on a computing device (e.g., the server computing device 104 shown and described above in fig. 1). In a first step 701, a skin health data set is used to assign a user to a preference profile and to calculate a skin health metric. In a second step 702, the skin health metric and skin health dataset are provided to a machine learning model (e.g., the GRU or LSTM recurrent neural network and ensemble of optimization algorithms) and cross-referenced with the ingredient-dose combination dataset 702A. In a third step 703, the machine learning model outputs one or more predicted ingredient-dose combinations, e.g., combinations that would result in an increase in the highest or one of the highest skin health metrics. In a fourth step 704, referring to the skin health dataset and the fields with potential ingredients that may have caused a reaction in the past, the computing device eliminates potential ingredient-dose combinations with those ingredients. In a fifth step 705, the computing device cross-references a preferred profile-ingredient combination data set 705A using a matching algorithm. In a sixth step 706, the computing device cross-references the product type-ingredient-dose combination dataset 706A using a matching algorithm. In a seventh step 707, the computing device generates one or more product-ingredient-dose combinations for providing to the user.

Fig. 8 is a schematic diagram 800 illustrating a method of manufacturing a personalized skin care product for a user according to an illustrative embodiment of the invention. Database 801 provides manufacturing system 802 with product recipes having unique skin identifiers for users and based on unique skin health data sets for users. In a first manufacturing system step 803, manufacturing system 802 synthesizes a customized skin care product according to a product recipe. In a second manufacturing system step 804, manufacturing system 802 bottles the customized skin care product. In a third manufacturing system step 805, manufacturing system 802 labels the container with a label that displays the at least one ingredient. The product is then provided 806 to the user for use. In some embodiments, as described above, the user 806 may provide feedback on the product for reformulating the recipe.

Fig. 9A-9C are screen shots 901, 902, 903 of a user questionnaire eliciting certain dermis data according to an illustrative embodiment of the invention. As shown, the screenshot 901 leads up information related to the user's goals (e.g., "learn more about my skin"; "track my skin progress"; "achieve my skin goal"; and "personalized formula") and skin concerns (e.g., "acne," "blockage/blackhead," "discoloration/spotting," "dryness," "redness/irritation," "sun damage," and "wrinkles/fine lines"). The screenshot 902 brings up information about the user's most important skin concerns, current products, favorite products, and non-favorite products. The screenshot 903 brings up information about the user's skin sensitivity, skin sensitivity to sunlight, and overall well-being about the user's skin. These variables may be in the skin health data set and may be incorporated as factors to be accounted for into a machine learning algorithm that predicts what dose-dose will be most effective in increasing the skin health metric of the user.

Fig. 10 is a screen shot 1000 of a skin care product recommendation according to an illustrative embodiment of the invention. Screenshot 1000 shows a skin care product with a carrier of Jojoba (Jojoba) and active ingredients of marigold (calenula) and Echium (Echium). The screenshot 1000 also shows a more detailed exploded view of the recipe, e.g. stating the characteristics of jojoba, marigold and echium for user references and labels showing the user which condition or target the carrier or active ingredient may be associated with. This screen helps the user understand how the collected skin health data relates to their recommended product-ingredient-dose combination by highlighting the benefits of the combination of the user's specific skin condition and skin concerns.

In some embodiments, one or more user input variables may be automatically determined and input into the algorithms described herein via another application or plug-in installed on the user computing device. For example, data relating to genetics, diet, sleep quality, stress level, and/or time sent in front of an electronic screen may be provided by integration with another application installed on the device. For example, genetic data may be collected from a DNA analysis service. The user's current diet (including meal allergies) and changes in diet may be collected through manual input or from already used diet tracking applications. Sleep habits and quality may be gathered from wearable technology already used by the user. The captured data may include sleep quality, hours of sleep, and/or resting heart rate while sleeping. The computer algorithm may calculate the mean and variance levels for each of these data points from the previous thirty days. The pressure level may be captured from the same wearable technology, and the captured data may include heart rate. The computer algorithm may calculate the mean and variance from, for example, the previous thirty days.

In another example, the time before the screen may be captured by the user's cellular device. The matching algorithm may sort the average number of hours spent each day over the past thirty days into buckets, e.g., high, medium, and low. In some embodiments, the user input of the current skin care product used is matched to the official product name using a database of skin care products (e.g., by hand or bar code). In some embodiments, user selections of sample ingredients in the analysis process are matched to the absorption and sensation preference profiles. In any case, many variables (e.g., those falling under the "personal history", "lifestyle", and/or "skin history" groupings as shown in fig. 6) may be ascertained at a minimum via the user's self-reported answers to intake survey questions. All of these data points may be included in the first skin health data set and are factors used by a machine learning model (e.g., a deep learning framework) to predict which ingredient-dose combinations will be most effective in increasing the skin health metric(s) of the user.

In some embodiments, calculating the formulation instructions for manufacturing the first skin care product by a formulation specialist or machine comprises: the following are calculated based on the problems found from the skin image analysis, severity score, oil and moisture index: (i) skin health metrics based on a trained logistic regression model and a separate scorecard dataset (e.g., similar to what a FICO does for a person's credit score); and (ii) comparing the skin health metric with prior inputs using a trained machine learning model to predict an optimal product-ingredient-dose combination. The training data set may include a longitudinal data set of changes in one or more skin health metrics, individual skin issue determinations, severity scores, oil and moisture indices, product-ingredient-dose recommendations, and/or composite scores. In such a dataset, the computer may calculate whether a change in the composite score represents a statistically significant improvement (e.g., by making a binary decision). Possible calculation modes include, but are not limited to: time series, logical model; a collaborative filtering model for predicting complementary product-ingredient-dose combinations; a neural network having a circuit.

In some embodiments, where the data input further includes information reflecting at least one of a temperature, humidity, or ambient ultraviolet index of the user's location, the user may enter his or her zip code during the ingestion process, and the computing device may enter the zip code into a weather database and store in a temporary data set, for example, temperature values, humidity values, and UV indices for each of the past thirty days. The computer algorithm may then calculate the mean and variance of each of these variables. These numbers may then be stored in the first skin health data set.

In some embodiments, where the one or more data inputs include information reflecting at least one of the user reported assessments of skin health, the user may provide a self-reported assessment of skin health (e.g., on a scale of 1 to 5). Where the user input includes care product usage, during intake, the user may scan or type in the product they have used, and the computing device may match the product to the full product name in a separate product database. The user can identify how many days of the week he or she uses each product during intake. The user may select his or her particular skin worry from a predetermined list. The user may type in the name of the product or ingredient to which he or she has reacted and may match that name with the full product name in a separate product database. The computer algorithm may identify the major active, preserved or potentially harmful ingredients from the products to which the user responds. In some embodiments, the user identifies favorite products used in the past and provides data related to absorption and texture preferences. Currently used products, frequency of use, favorite past products, absorption and texture preferences, and potential ingredients that may have caused prior reactions may be stored in the first skin health data set.

In some embodiments, where the one or more data inputs include at least one elasticity measurement of the user's skin, an elasticity measurement device (e.g., a frequency oscillation sensor and/or a suction pressure measurement device) may be used. The user may take a contract value measurement (e.g., in newtons). These contract values may be averaged and normalized to produce a normalized elasticity index. Where the data input includes the pH of the skin, litmus paper and/or an activating solution may be used to measure the pH. The normalized elasticity index and pH value may be input into the first skin health data set.

In some embodiments, with reference to the skin health dataset and fields with potential ingredients that may have caused a reaction in the past, the computer algorithm creates a rule that does not include those ingredients in the product recipe. Incorporating this rule, the computer algorithm predicts that the ingredient-dose combination will result in the highest increase in the skin health metric for the user. In some embodiments, using the input of the first skin health data set and the data set of dietary and lifestyle changes, the computer algorithm recommends specific dietary and lifestyle habits that will augment the skin health metric of the user. The computer algorithm utilizes a machine learning model that has been trained on longitudinal datasets including diet, lifestyle habits, skin concerns, severity scores, and skin health metrics. In some embodiments in which a recommended personalized skin care routine is generated that includes a recommendation for at least one of a cleanser, a serum, a facial oil, a moisturizer, a dietary supplement, or a sunscreen, the input of the recommended ingredient-dose combination and the product dataset of ingredient-doses are matched to the product type, and the computer algorithm compares the recommended ingredient-dose combination for the user and pulls the associated product type appropriate for the recommended ingredient-dose combination from the product dataset.

In some embodiments, the invention may be implemented in a number of settings, such as in a physical location or at home. In a physical location, the process may be directed through a kiosk or an in-location device and follow the same process as described above. In addition, the user may receive their personalized product and personalization routine in the same visit as the analysis is completed. In a home setting, the user may receive the personalized skin care product(s) via mail after completing the analysis.

Example implementation

Main body A

Environment + background data

Female, 27 years old, asian, 5 feet 5 inches, 135 pounds, located in boston, ma

Without known allergies, prior reactions to skin care products, daily sunscreen, regularly experienced dry and itchy skin, no recent acne

The daily passenger and non-smoker drink 6 cups of water and vegetarian food in one day, and the high pressure is applied for 2 times in one week

The first diagnosis (fall) occurred during the month of October

Raw vision + physical skin data

Technical measurement

Visible light imaging recognizes dryness of skin on forehead and chin, discoloration on forehead associated with dry spots of skin, redness on forehead, wrinkles, rashes recognized on forehead and around mouth, not to be a concern

Oil measurement results forehead-15%, nose-18%, cheek-21%

Moisture measurements forehead-12%, nose-15%, cheek-17%

Absorption preference "non-oily" was identified as preference, and "quick absorption" was selected "

Transformed skin health variables

Oil classification 4 index score, not greasy (average of 15%, 18%, 21% less than 35% threshold)

Moisture class 3 index score, dehydration (average of 12%, 15%, 17% less than 30% threshold)

Fade score 40/100

Redness and swelling score 50/100

Wrinkle score 60/100

Skin health metric: rash (100) + fading (40) + redness and swelling (50) + wrinkles (50) + non-smoking (100) + water intake (50) + high pressure (25) + frequent traveler (20) + vegetarian person (70) + exercise (40) = 545)

Preference profile: "non-oily" match to Profile 3 ("non-severe, moderate basis")

Ingredient-dose matching

Potential ingredients:

potential basis: aqua (water), rose water, aloe water, evening primrose and squalane

Potential active ingredients: hyaluronic acid, ascorbic acid (vitamin C), ascorbyl glucoside

(vitamin C derivative) Nicotinamide, Retinol

Potential conflict (elimination of use of both): nicotinamide and ascorbic acid (used together to create niacin in the case of the red and reddish side effects)

The recommended ingredient-dose combination:

formulation (A-1): aqueous solution (water) + ascorbic acid glucoside 8%

Formulation (A-2): squalane + hyaluronic acid

Preference profile matching:

formulation (A-1): compatible with preference profile 3 ("non-severe, moderate")

Formulation (A-2): compatible with preference profile 3 ("non-severe, moderate")

Product-ingredient-dose matching:

recommended products for addressing fading, redness, dryness of the user: morning essence (A-1), night essence (A-2)

And (3) selecting by the user:

formulation (A-1): the user does not change the recommended formula and product recommendations.

Fig. 11 is a flowchart 1100 of a computerized method of formulating a skin care product for a user, according to an illustrative embodiment of the invention. The illustrated steps may be implemented by a computing device (e.g., computing device 104 shown and described above in fig. 1). In a first step 1101, a data input is received that includes one or more hydration level measurements of a user's skin, one or more oil level measurements of the user's skin, and a photograph of the user's skin reflecting a set of skin concerns. In a second step 1102, a normalized hydration index score is determined based on the one or more hydration level measurements. In a third step 1103, a normalized oil index score is determined based on the one or more oil level measurements. In a fourth step 1104, a set of normalized severity scores corresponding to the set of skin concerns of the user is determined based on the photograph of the user's skin. In a fifth step 1105, a first skin health data set is generated that includes a set of normalized hydration index scores, normalized oil index scores, and normalized severity scores. In a sixth step 1106, the first skin health data set is stored in a first memory in electronic communication with the computing device. In a seventh step 1107, a first skin health metric is determined based on the first skin health data set. In an eighth step 1108, the first skin health metric is stored in a second memory in electronic communication with the computing device. In a ninth step 1109, one or more first skin care product formulas are determined based on the first skin health metric and the first skin health data set using a machine learning framework operating on the computing device. In a tenth step 1110, the one or more first skin care product formulas are stored in a third memory in electronic communication with the computing device.

Fig. 12 is a flowchart 1200 of a method of manufacturing a skin care product for a user according to an illustrative embodiment of the invention. The steps shown may be performed by a manufacturing system (e.g., an in-house manufacturing facility or another facility). In a first step 1201, a manufacturing system receives a product recipe (e.g., as generated according to one or more methods described herein) having a unique skin identifier for a user and based on the user's unique skin health data set. In a second step 1202, the manufacturing system synthesizes a customized skin care product according to a product recipe. In a third step 1203, the manufacturing system bottles the customized skin care product in a container. In a fourth step 1204, the manufacturing system labels the container with a label that displays the ingredients.

Fig. 13 is a flowchart 1300 of a computerized method of formulating first and second skin care products for a user according to an illustrative embodiment of the invention. The steps shown may be implemented by a computing device (e.g., computing device 104 shown and described above in fig. 1). In a first step 1301, one or more first data inputs reflecting dermis information of a user are received. In a second step 1302, a first skin health data set is generated for the user based on the one or more first data inputs, the first skin health data set comprising one or more normalized scores reflecting the one or more first data inputs. In a third step 1303, the first skin health data set is stored in a first storage in electronic communication with the computing device. In a fourth step 1304, a first skin care product formulation is determined based on the first skin health data set. In a fifth step 1305, the first skin care product formulation is stored in a second storage in electronic communication with the computing device. In a sixth step 1306, one or more second data inputs are received that reflect a change in the first data input after the first skin care product is used based on the first skin care product formulation. In a seventh step 1307, a second set of skin health data for the user is generated based on the one or more first data inputs and the one or more second data inputs. In an eighth step 1308, the second set of skin health data is stored in a third storage in electronic communication with the computing device. In a ninth step 1309, a second skin care product formulation is determined based on the second skin health data set. In a tenth step 1310, the second skin care product formulation is stored in a fourth memory in electronic communication with the computing device.

The techniques described above may be implemented in digital and/or analog electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. The implementations may be implemented as a computer program product (i.e., a computer program tangibly embodied in a machine-readable storage medium) for execution by, or to control the operation of, data processing apparatus (e.g., a programmable processor, a computer, and/or multiple computers). The computer programs may be deployed in a Cloud computing environment (e.g., Amazon AWS, Google Cloud Platform, Microsoft Aztre, etc.). Method steps may be performed by one or more processors executing the computer program to: which performs the functions of the invention by operating on input data and/or generating output data.

To provide for interaction with a user, the techniques described above can be implemented on a computing device that communicates with a display device (e.g., a plasma or LCD (liquid crystal display) monitor or mobile computing device display or screen for displaying information to the user) and a keyboard and pointing device (e.g., a mouse, touchpad, or motion sensor) by which the user can provide input to the computer (e.g., interact with user interface elements). Other kinds of devices may also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, voice, and/or tactile input.

The techniques described above can be implemented in a distributed computing system that includes a back-end component. The back-end component can be, for example, a data server, a middleware component, and/or an application server. The techniques described above can be implemented in a distributed computing system that includes a front-end component. The front-end component can be, for example, a client computer having a graphical user interface, a web browser through which a user can interact with the example implementations, and/or other graphical user interfaces for a transmitting device. The techniques described above can be implemented in a distributed computing system that includes any combination of such back-end, middleware, or front-end components.

The components of the computing system may be interconnected by a transmission medium that may include any form or medium of digital or analog data communication (e.g., a communication network). The transmission medium may include one or more packet-based networks and/or one or more circuit-based networks, in any configuration. The packet-based network may include, for example, the internet, a carrier Internet Protocol (IP) network (e.g., Local Area Network (LAN), Wide Area Network (WAN), Campus Area Network (CAN), Metropolitan Area Network (MAN), Home Area Network (HAN)), a private IP network, an IP private branch exchange (IPBX), a wireless network (e.g., Radio Access Network (RAN), bluetooth, Near Field Communication (NFC) network, Wi-Fi, WiMAX, General Packet Radio Service (GPRS) network, HiperLAN), and/or other packet-based networks. The circuit-based network may include, for example, a Public Switched Telephone Network (PSTN), a conventional private branch exchange (PBX), a wireless network (e.g., RAN, Code Division Multiple Access (CDMA) network, Time Division Multiple Access (TDMA) network, global system for mobile communications (GSM) network), and/or other circuit-based networks.

The transfer of information over the transmission medium may be based on one or more communication protocols. The communication protocols may include, for example, an ethernet protocol, an Internet Protocol (IP), a Voice Over IP (VOIP), a peer-to-peer (P2P) protocol, a hypertext transfer protocol (HTTP), a Session Initiation Protocol (SIP), h.323, a Media Gateway Control Protocol (MGCP), a signaling system #7 (SS 7), a global system for mobile communications (GSM) protocol, a push-to-talk (PTT) protocol, a cellular PTT (poc) protocol, a Universal Mobile Telecommunications System (UMTS), a 3GPP Long Term Evolution (LTE), and/or other communication protocols.

Devices of a computing system may include, for example, computers with browser devices, telephones, IP phones, mobile computing devices (e.g., cellular phones, Personal Digital Assistant (PDA) devices, smart phones, tablets, laptops, email devices), and/or other communication devices. The browser devices include, for example, computers (e.g., desktop and/or laptop computers) having a web browser (e.g., Chrome @, available from Google, Inc., Microsoft Internet Explorer @ available from Microsoft Corporation, and/or Mozilla Firefox available from Mozilla Corporation). The mobile computing devices comprise, for example, Black berry from Research in Motion, iPhone from Apple Corporation and/or an Android based device. The IP phones comprise, for example, Cisco ® Unifield IP Phone 7985G and/or Cisco @ Unifield Wireless Phone 7920 available from Cisco System, Inc.

It should also be understood that the various aspects and embodiments of the invention may be combined in various ways. Based on the teachings of this specification, one of ordinary skill in the art can readily determine how to combine these various embodiments. In addition, modifications may occur to those skilled in the art upon reading the specification.