Systems and methods for producing products

Abstract

Disclosed is a system, device, and / or method for producing a product. Receive the identity of a sample chemical composition comprising ingredients. Receive a value of a property of the sample chemical composition and a feature related to the value of the property of the sample chemical composition. Input the value of the property of the sample chemical composition, the feature related to the value of the property of the sample chemical composition, and the identity of the sample chemical composition into a machine learning model. Via the machine learning model, determine the value of the property of the considered chemical composition based on the feature related to the value of the property of the considered chemical composition and the identity of the considered chemical composition. Produce a product composed of the considered chemical composition.

Description

[0001] Cross - reference to related patent applications

[0002] This application claims the benefit of priority of U.S. Non - provisional application Ser. No. 16 / 672,922, filed on Nov. 4, 2019, which is a continuation of U.S. Non - provisional application Ser. No. 16 / 452,214, filed on Jun. 25, 2019, the content of the foregoing U.S. Non - provisional applications being incorporated herein by reference in its entirety. Background Art

[0003] Many products are formed from compositions, such as chemical compositions. Chemical compositions typically include many different components. Each of the components has a specific value associated with the component, such as a chemical information value. In addition, one or more properties of the chemical composition (e.g., pH, consumer perception) may have a unique value, for example, based on the components within the composition. The value of the property of the chemical composition may change due to the interaction of the components within the composition.

[0004] Some products, such as foods, are formed from compositions in which the components are not necessarily chemicals but are natural complexes and are composites themselves. The attributes of these products (e.g., nutrient profile) can be described in a similar manner and are associated with the components. Their values, whether simple or complex, may be unique and can be derived experimentally or computationally (e.g., measured or calculated). Similar to products formed from chemicals, the value of the property of the composition may change due to the interaction of the components within the composition.

[0005] There are conventional methods for predicting the value of one or more properties of a chemical composition. However, such methods are typically time - consuming and irrelevant. For example, conventional methods for predicting the pH value of a chemical composition include (1) experimentally measuring the chemical composition to determine the pH value; and (2) performing a mathematical prediction calculation to determine the pH value (e.g., using known acidity constants, such as pKa values). However, these methods are flawed due to the time and / or complexity involved in the respective methods. Accordingly, there is a desire for a system and / or method for determining the value of the property of a chemical composition in a manner that requires less time and / or less complexity. Summary of the Invention

[0006] Disclosed is a system, device, and / or method for producing a product. Receive the identity of a sample chemical composition comprising ingredients. Receive a value of a property of the sample chemical composition and a feature related to the value of the property of the sample chemical composition. Input the value of the property of the sample chemical composition, the feature related to the value of the property of the sample chemical composition, and the identity of the sample chemical composition into a machine learning model. Via the machine learning model, determine the value of the property of the considered chemical composition based on the feature related to the value of the property of the considered chemical composition and the identity of the considered chemical composition. Produce a product consisting of the considered chemical composition.

[0007] Disclosed is a system, device, and / or method for producing a product. Receive the identity of a property of interest and the identity of a sample chemical composition. For each of the sample chemical compositions, receive a value of a property. Only for each of the sample chemical compositions having the property of interest, input the value of the property of the sample chemical composition and at least one of (1) the identity of the sample chemical composition or (2) the value of the chemical information property of the ingredients of the sample chemical composition into a model. Via the model, determine the value of the property of the considered chemical composition based on the identity of the considered chemical composition or the value of the chemical information property of the ingredients of the considered chemical composition. Produce a product having the considered chemical composition.

[0008] Disclosed is a system, device, and / or method for determining the value of a property of a considered chemical composition. The identity of a sample chemical composition may be received. The sample chemical composition may comprise ingredients. Each of the ingredients may be associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition. A value of a property of the sample chemical composition may be received. The property of the sample chemical composition may be affected by the interaction of at least two of the ingredients of the sample chemical composition. Input the value of the property of the sample chemical composition and at least one of (1) the identity of the sample chemical composition or (2) the value of the chemical information property of the ingredients of the sample chemical composition into a model. Via the model, determine the value of the property of the considered chemical composition based on at least one of (1) the identity of the considered chemical composition or (2) the value of the chemical information property of the ingredients of the considered chemical composition. The property of the considered chemical composition may be affected by the interaction of at least two of the ingredients of the considered chemical composition.

[0009] On the other hand, values of the properties of the chemical composition under consideration can be determined. The identity of the sample chemical composition can be received. The identity can include components. One or more (e.g., each) of the components can be associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition. Values of the sample physical and chemical properties of the sample chemical composition can be received. The sample physical and chemical properties of the sample chemical composition can be affected by the interaction of at least two of the components of the sample chemical composition. The values of the sample physical and chemical properties of the sample chemical composition can be input into a model. The identity of the sample chemical composition and / or the values of the chemical information properties of the components of the sample chemical composition can be input into the model. The values of the physical and chemical properties under consideration of the chemical composition under consideration can be determined via the model. The values can be based on the identity of the chemical composition under consideration and / or the values of the chemical information properties of the components of the chemical composition under consideration. The physical and chemical properties under consideration of the chemical composition under consideration can be affected by the interaction of at least two of the components of the chemical composition under consideration. The physical and chemical properties under consideration can be different from the sample physical and chemical properties.

[0010] On the other hand, values of the properties of the chemical composition under consideration can be determined. The identity of the property of interest can be received. The identity of the sample chemical composition can be received. Each of the sample chemical compositions can include components each associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition. For each of the sample chemical compositions, values of the properties affected by the interaction of at least two of the components of the sample chemical composition can be received. For each of the sample chemical compositions having the property of interest (e.g., only for each), at least one of the value of the property of the sample chemical composition and (1) the identity of the sample chemical composition or (2) the value of the chemical information property of the components of the sample chemical composition can be input into a model. The values of the properties of the chemical composition under consideration can be determined via the model. The values can be based on at least one of (1) the identity of the chemical composition under consideration or (2) the values of the chemical information properties of the components of the chemical composition under consideration. The properties of the chemical composition under consideration can be affected by the interaction of at least two components of the chemical composition under consideration.

[0011] On the other hand, a product can be produced that consists of a considered chemical composition having a value of a considered chemical property. The identity of a sample chemical composition containing components can be received. Each of the components can be associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition. The value of a training chemical property of the sample chemical composition can be received. The value of the training chemical property can be based on at least one of an experimental measurement of the value of the training chemical property or a mathematical measurement of the value of the training chemical property. A learning model can be constructed using the value of the chemical information property of the sample chemical composition and the value of the training chemical property of the sample chemical composition. The value of the considered chemical property can be input into the learning model. The value of the chemical information property of the considered chemical composition having the value of the considered chemical property can be determined via the learning model and / or based on the value of the considered chemical property. A product can be produced that contains the considered chemical composition having the value of the considered chemical property.

[0012] On the other hand, the value of a considered chemical composition having components can be determined. The identity of a sample chemical composition having a defined value of a chemical property can be received. The sample chemical composition can consist of components different from those of the considered chemical composition. A training set can be generated that contains the identity of the sample chemical composition and the defined value of the chemical property of the sample chemical composition. A model can be constructed based on the training set for determining the value of the chemical property of the considered chemical composition. The value of the chemical property of the considered chemical composition can be determined via the model, e.g., based on the identity of the considered chemical composition and the training set. The value of the chemical property of the considered chemical composition can be received.

[0013] On the other hand, the identity of a sample chemical composition containing components can be received. Each of the components can be associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition. The value of a fitting parameter associated with the value of a property of the sample chemical composition can be received. The property of the sample chemical composition can be affected by the interaction of at least two of the components of the sample chemical composition. The value of the fitting parameter associated with the value of the property of the sample chemical composition and / or at least one of (1) the identity of the sample chemical composition or (2) the value of the chemical information property of the components of the sample chemical composition can be input into a model. The value of the fitting parameter of the considered chemical composition can be determined via the model. The value of the fitting parameter can be based on at least one of (1) the identity of the considered chemical composition or (2) the value of the chemical information property of the components of the considered chemical composition.

[0014] In another aspect, a chemical composition under consideration can be identified. Values of chemical information properties of the components of a sample chemical composition can be received. Values of properties of the sample chemical composition can be received. The properties can be affected by the interaction of at least two of the components. The values of the chemical information properties of the components of the sample chemical composition and the values of the properties of the sample chemical composition can be input into a model. The identity of the chemical composition under consideration can be determined via the model, for example, based on at least one of (1) values of chemical information properties of the components of the chemical composition under consideration or (2) values of properties of the chemical composition under consideration. The properties of the chemical composition under consideration can be affected by the interaction of at least two of the components of the chemical composition under consideration.

[0015] In another aspect, the identities of the components of a first composition can be received. Each of the components can have a value of a certain predefined property among predefined properties. Values of properties of the first composition can be received. The properties can be affected by the interaction of at least two of the components of the first composition. The values of the predefined properties of the components of the first composition and the values of the properties of the first composition can be used to train a learning model. The identities of the second components of a second composition can be provided to the learning model. At least one of the second components can be different from at least one of the first components. Values of properties of the second composition can be determined via the learning model. The properties of the second composition can be affected by the interaction of at least two of the components of the second composition.

[0016] In another aspect, values of properties of a chemical composition under consideration can be determined. The identity of the chemical composition under consideration can be received from a chemical composition associated with a product. The chemical composition under consideration can include components. Values of chemical information properties can be received. Each value can be associated with a respective one of the components of the chemical composition under consideration. The values of the properties of the chemical composition under consideration can be determined based on at least one of (1) the identity of the chemical composition under consideration or (2) the values of the chemical information properties associated with the respective ones of the components of the chemical composition under consideration. The model can be trained based on at least one of (1) the identity of the chemical composition or (2) values of chemical information properties of the components of the chemical composition and values of properties of the chemical composition. The values of the properties of the chemical composition under consideration can be affected by the interaction of at least two of the components of the chemical composition under consideration.

[0017] On the other hand, a model can be created to determine the value of a property of a chemical composition under consideration. The identity of a sample chemical composition containing components can be received. Each of the components can be associated with a value of a chemical information property among the chemical information properties of the sample chemical composition. A value of a property of the sample composition can be received. The property can be affected by the interaction of at least two of the components of the sample chemical composition. The model can be trained to determine the value of the property of the chemical composition under consideration by processing the value of the property of the sample chemical composition and at least one of (1) the identity of the sample composition or (2) the value of the chemical information property of the components of the sample chemical composition. The model can be configured to determine the value of the property of the chemical composition under consideration based on at least one of (1) the identity of the chemical composition under consideration or (2) the value of the chemical information property of the components of the chemical composition under consideration. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The invention will be more fully understood from the detailed description and the drawings, in which:

[0019] Figure 1A is a table of components of an example composition;

[0020] Figure 1B is a table of example properties of a composition where a consumer may have a perception;

[0021] Figure 2A is a block diagram of an example component of a composition, the component including components and substances of the composition;

[0022] Figure 2B is a table of components of another example composition, providing the identity of the components and the percentage of the components;

[0023] Figure 3A is an example process of determining a value of a composition using machine learning rules;

[0024] Figure 3B is an example system for determining a value of a composition;

[0025] Figure 4 is another example process of determining a value of a composition using machine learning rules;

[0026] Figure 5 is a block diagram of an example system including a user device;

[0027] Figure 6 is a block diagram of an example system including training of a property engine;

[0028] Figure 7 is an example functional table of components of a composition;

[0029] Figure 8 It is an example function table of the components of the composition;

[0030] Figure 9A 、 9B 、9C is a block diagram for example training of a machine learning model and receiving values from the machine learning model;

[0031] Figure 10A 、 10B 、10C is an example graphical user interface (GUI) for training a property engine;

[0032] Figure 11A 、 11B 、11C, 11D are example graphical user interfaces (GUI) for receiving determined values via a property engine;

[0033] Figure 12 is an example method for determining the value of a composition as described herein; and

[0034] Figure 13 is another example method for determining the value of a composition as described herein. Detailed Description

[0035] The following description of one or more preferred embodiments is exemplary in nature and should in no way limit the invention. The description of the illustrative embodiments is intended to be read in conjunction with the accompanying drawings, which will be regarded as part of the entire written description. In the description of the exemplary embodiments disclosed herein, any reference to direction or orientation is for convenience of description only and is not intended to limit the scope of the invention in any way. The discussion herein describes and illustrates some possible non-limiting combinations of features that may exist alone or in other combinations of features. Additionally, as used herein, the term "or" is understood to be a logical operator that results in true whenever one or more of its operands is true at any given time. Further, as used herein, the phrase "based on" is understood to mean "at least partially based on" and thus is not limited to an interpretation of "entirely based on".

[0036] The ranges used throughout are used as a shorthand expression for every value within the range. Any value within the range can be selected as an endpoint of the range. Additionally, all references cited herein are incorporated by reference in their entirety. In the event of a conflict between the definitions in this disclosure and those of the cited references, this disclosure shall control.

[0037] The features of the present invention can be implemented in software, hardware, firmware, or a combination thereof. The computer programs described herein are not limited to any specific embodiment and can be implemented in an operating system, application program, foreground or background process, driver, or any combination thereof. The computer program can be executed on a single computer or server processor or multiple computer or server processors.

[0038] The processors described herein can be any central processing unit (CPU), microprocessor, microcontroller, computing or programmable device, or circuitry configured to execute computer program instructions (e.g., code). The various processors can be embodied in any suitable type of computer and / or server hardware (e.g., desktop, laptop, notebook, tablet, cellular phone, etc.) and can include all conventional auxiliary components required to form a functional data processing device, including but not limited to buses, software, and data storage devices (e.g., volatile and non-volatile memories), input / output devices, graphical user interface (GUI), removable data storage devices, and wired and / or wireless communication interface devices including Wi-Fi, Bluetooth, LAN, etc.

[0039] Computer-executable instructions or programs (e.g., software or code) and the data described herein can be programmed into and tangibly embodied in a non-transitory computer-readable medium, which can be accessed and retrieved by a corresponding processor as described herein, and the processor is configured and directed to perform the desired functions and processes by executing the instructions encoded in the medium. A device embodying a programmable processor configured with such non-transitory computer-executable instructions or programs can be referred to as a "programmable device" or "device", and a plurality of programmable devices communicating with each other can be referred to as a "programmable system". It should be noted that the non-transitory "computer-readable medium" as described herein can include but is not limited to any suitable volatile or non-volatile memory that can be written to and / or read by a processor operatively connected to the medium, including random access memory (RAM) and its various types, read-only memory (ROM) and its various types, USB flash memory, and magnetic or optical data storage devices (e.g., internal / external hard disks, floppy disks, magnetic tapes, CD-ROMs, DVD-ROMs, optical discs, ZIP TM drives, Blu-ray discs, and other devices).

[0040] In certain embodiments, the present invention may be embodied in the form of computer-implemented processes and apparatuses (e.g., processor-based data processing and communication systems or computer systems for practicing those processes). The present invention may also be embodied in the form of software or computer program code in a non-transitory computer-readable storage medium, which, when downloaded and executed by a data processing and communication system or a computer system, configures a processor to generate specific logic circuitry configured to implement the processes.

[0041] A composition may include one or more ingredients (e.g., components). For example, a composition may include a first, second, third, etc. ingredient. One or more ingredients of a composition may have an effect on one or more other ingredients of the composition. Additionally or alternatively, one or more ingredients may have an effect on the composition (e.g., the composition as a whole).

[0042] A composition may be a chemical composition, but in some embodiments, a composition may be a non-chemical composition. A composition may form a product. A composition (e.g., a product formed from a chemical composition) may be used for one or more purposes. For example, a product formed from a chemical composition may be used for cooking; cleaning; consumer, personal care; treating / testing diseases, disorders, conditions; and one or more other purposes. A composition (e.g., a chemical composition) may be used to perform a task. For example, a chemical composition may be used to perform a test, such as a water purity test.

[0043] A chemical composition may form a product (e.g., a personal care product), but the personal care product is for illustrative purposes only, and a chemical composition may form one or more other products, such as foods, drugs, etc. There may be personal care products to enhance the health, hygiene, appearance, odor, etc. of a user. Such personal care products may contain one or more chemical compositions composed of one or more ingredients. Personal care products may include oral care products containing oral care compositions, skin care products containing skin care compositions, hair care products containing hair care compositions, and other products and / or chemical compositions.

[0044] As used herein, an oral care composition may include a composition whose intended use may include oral care, oral hygiene, oral appearance, or whose intended use may include being applied to the oral cavity. As used herein, a skin care composition may include a composition whose intended use may include promoting or improving the health, cleanliness, odor, appearance, and / or attractiveness of the skin. As used herein, a hair care composition may include a composition whose intended use may include promoting or improving the health, cleanliness, appearance, and / or attractiveness of the hair. The compositions may be used for a variety of purposes, including for enhancing personal health, hygiene, and appearance, and for preventing or treating a variety of diseases and other conditions in humans and animals.

[0045] Figure 1A A table showing example data associated with one or more compositions. The compositions can be chemical compositions, such as Chemical Composition 100. Chemical Composition 100 can form a product, such as a personal care product. As can be seen from Figure 1A it, Chemical Composition 100 can include several ingredients. For example, Chemical Composition 100 can include glycerol, sodium lauryl sulfate, zinc citrate, and one or more other ingredients. Each of the ingredients of Chemical Composition 100 (e.g., the chemical composition forming the personal care product) can be included in the personal care product to provide one or more predefined characteristics. As Figure 1A provided, the characteristics of the ingredients can include providing sweetness to Chemical Composition 100, providing a stabilizing factor to Chemical Composition 100, etc. For example, sodium lauryl sulfate is an ingredient of Chemical Composition 100 and can be used as a solubilizer or a cleaning agent for Chemical Composition 100.

[0046] Figure 1B A table showing additional data associated with an example composition such as Chemical Composition 100. In the example, the chemical composition can form a product, such as a personal care product, a food, a drug, etc. The chemical composition can form a product and / or other materials used, consumed, sold, purchased, etc. by humans, animals, etc. For example, the chemical composition can form a skin care product used by humans or animals, a food consumed by humans or animals, a drug for treating humans and / or animals, etc. In other examples, the composition can be a chemical composition for cleaning one or more surfaces, a composition for absorbing one or more fluids, etc.

[0047] Figure 1B The provided example data can be related to the perception of products such as personal care products, foods, and / or drugs, etc., but other uses can be envisioned. The perception of the product can be determined via consumers of the product, clinical trials of the product, etc. Figure 1B An example showing where consumers can perceive a chemical composition according to several categories and / or characteristics. For example, consumers may have a perception of the color, tackiness, wetness, ease of use, sweetness, etc. of the chemical composition. Based on the perception of one or more characteristics of the chemical composition forming the personal care product, consumers can have a preference for the personal care product. For example, consumers may prefer toothpaste with a specific color, shampoo with a specific smell, deodorant with a specific dispersibility, etc.

[0048] One or more consumers and / or users of a product (e.g., a personal care product) can evaluate the product based on the consumer's one or more perceived values of the personal care product. Consumer perceived values can be obtained in various ways, including surveys (e.g., paper or online surveys), clinical trials (e.g., clinical trials that measure the results of using a chemical composition over a period of time), the storage conditions of the product (e.g., the environment in which the product is stored), the commercial success of the product, etc.

[0049] As provided herein, clinical trials can be used to determine the results of using one or more chemical compositions. Clinical results can be measured over a period of time. For example, with respect to a personal care product, clinical results can be related to a reduction in gingivitis, tooth whitening, allergy relief, wrinkle reduction, etc. over a period of time. Examples can include measuring a reduction in gingivitis within three or six months of using a chemical composition, measuring tooth whitening within a few days / months of using a chemical composition, measuring allergy relief within a few minutes / months of using a chemical composition, and / or measuring wrinkle reduction ninety days after using a chemical composition. Although clinical results and time periods can be related to personal care products, clinical results can be measured for chemical compositions other than personal care products, such as foods (e.g., human or animal foods), drugs, etc. For example, a reduction in animal weight (e.g., the weight of an animal, such as a canine weight) can be measured during a one-month period of using pet food, and a decline in health status (e.g., the health status of a human or animal) can be measured during a six-month period of using a drug, etc.

[0050] Clinical results can be related to formulation properties. Formulation properties can be generated by the chemical interactions of the chemical compositions that form the product. For example, with respect to tooth whitening, the oxidation potential of the product can be a property (e.g., a formulation property) that affects the rate and extent to which the product whitens teeth. With respect to the abrasiveness of the product, the pellicle cleaning ratio (PCR) can be a property that affects the rate and / or extent of the whitening effect. With respect to a dental vehicle, the state (e.g., the desired state) in the chemical composition can be a property related to how fluoride interacts with one or more other components. The desired state in the chemical composition can correspond to minimal interaction of fluoride with excipient components, which can result in more fluoride (e.g., free fluoride). With respect to acne, anti-inflammatory properties can affect the efficacy of the chemical composition.

[0051] Instance data may include user-related information, such as demographic information. Demographic information may include geographical information related to the product user (e.g., current / previous residence information of the product user), the lineage of the product user, the age / height / weight / body mass index of the product user, the body hair coverage rate of the product user, the body sweat production of the product user, the skin sebum production of the product user, biomarkers (e.g., the presence / absence of biomarkers of the product user), genetic status (e.g., defined by a single variant, multiple variants, or a combination thereof, including the entire genome of the user), the hair type / color of the product user, the skin pH value of the product user, the nutrition of the product user, the exercise regimen of the product user, the body flora of the product user, the current / past health condition and / or status of the product user, etc. Biomarkers may include substances (e.g., measurable substances) of a human or animal that indicate phenomena such as diseases, infections, environmental exposures, etc. Additional instance data may include the physical characteristics of the user (e.g., skin type, such as the dryness or oiliness of the user's skin); the effects of chemical compositions on the skin; the presence of tattoos and / or blemishes on the skin; skin elasticity; skin health, skin pigmentation; skin age (actual and / or perceived); the number of visits to a dermatologist; the use of sunscreen; the use of moisturizer; etc. Instance data may include behavioral patterns, such as activities, movements, and one or more other quantifiable behavioral attributes.

[0052] Instance data may include the ways in which the product interacts with the environment. As described herein, the degree and / or manner of the product's interaction with the environment can determine the chemical reaction of the product. For example, the data associated with the product may include whether one or more of the chemical compositions forming the product affect the kinetics of the chemical reaction of the product. Additionally or alternatively, the data associated with the product may include whether one or more of the chemical compositions forming the product affect the kinetics of the phase change of the product, where the phase change may include volatile evaporation, phase transition, etc.

[0053] The data associated with the product may include other environmental attributes of the chemical composition forming the product. The data associated with the product may include the stability of the chemical composition forming the product and / or the attributes related to the storage of the product. For example, the chemical reaction of the product may be affected by storage temperature, storage humidity, etc. For example, when the chemical composition is stored at a higher temperature and / or higher humidity, the chemical reaction of the chemical composition can be accelerated. Instance data may include the packaging of the product. For example, the packaging of the product can determine the degree and / or manner of the product's interaction with the environment. Examples of packaging may include packaging material composition, packaging geometry, packaging opacity, etc. Instance data may include the shape factor of the product having the chemical composition. For example, the data may include whether the chemical composition of the soap is in solid (e.g., bar) form or liquid form.

[0054] Example data can include consumer perceptions of products formed from chemical compositions. The consumer perception of a chemical composition (e.g., a chemical composition forming a personal care product, food, drug, etc.) can be based on one or more of the product ingredients. For example, the consumer perception value may be affected by one or more of the specific ingredients of the product that cause, for example, a personal care product to be whiter or less white, stickier or less sticky, cause more or less burning sensation, etc.

[0055] Figure 2A A depiction showing example data that can be associated with a composition (e.g., a chemical composition). Although many of the examples provided herein describe compositions forming personal care products, such examples are for illustrative purposes only and are non - limiting. The composition can form various products such as personal care product 200, food, drug, etc.

[0056] Data associated with a product, such as personal care product 200, can include an identity (e.g., the name of the personal care product), the ingredients of the personal care product, the chemical information values of the personal care product ingredients, the clinical trial and / or clinical outcome information of the personal care product, the user - related information of the personal care product (e.g., demographic information), the formulation attributes of the personal care product, or one or more other identifiers for identifying the personal care product.

[0057] A product such as personal care product 200 can be associated with a unique number 212a, which can be referenced by a user and / or a computer when referring to the personal care product. Each personal care product 200 can have one or more other values and / or properties, such as property 212b. Property 212b can be a chemical property associated with the chemical composition of the personal care product. For example, property 212b can be a physicochemical property of the chemical composition of the personal care product. The physicochemical properties of the chemical composition can be related to the physical or chemical properties of the chemical composition of the personal care product.

[0058] Property 212b can be the pH value of the personal care product and / or one or more other data, such as the example data provided herein. For example, property 212b can be clinical trial and / or clinical outcome data, user - related data, product form factor and / or packaging data, shelf - life data, biomarker data, formulation attribute data, etc. Property 212b can be the consumer perception of the personal care product, such as Figure 1BPerceptions such as those shown. For example, consumers may have perceptions of the color, tackiness, wetness, ease of use, sweetness, etc. of personal care products. The consumer perception of a personal care product can be based on one or more of the ingredients of the personal care product. For example, an ingredient may cause the personal care product to be whiter or less white, stickier or less sticky, cause more or less of a burning sensation, etc. The value of property 212b may be affected by one or more ingredients of the personal care product.

[0059] As described herein, a composition (e.g., a chemical composition) can form a product, such as a personal care product, a food, a drug, etc. The chemical composition can be composed of one or more ingredients (e.g., ingredient data) such as ingredient 222, 232, etc. Each ingredient can include an identity, such as the name of the ingredient or other identifier used to identify the ingredient. For example, ingredient 222 can include name 222b and / or identifier 222a. Ingredient 222 can include other information, such as the percentage of the personal care product that contains the ingredient. For example, as shown in 222c, ingredient 222 (e.g., sodium lauryl sulfate) can be 1.4999% of personal care product 200. The ingredient data can include one or more other properties and / or values of properties.

[0060] Each ingredient can be composed of one or more substances. As Figure 2A shown, ingredient 222 can be composed of four substances: water 242, sodium sulfate 252, sodium chloride 262, and C12-16 alkyl sulfate 272. Data can be associated with one or more (e.g., each) of the substances. For example, each substance can include an identity such as the name 242a, 252a, 262a, 272a of the substance or other identifier used to identify the substance. For example, substance 242 can have the name 242a of water. The substances (e.g., substances 242, 252, 262, 272) can include one or more other values, such as the percentage 242b that the substance is composed of the ingredient, chemical information properties of the ingredient (e.g., the substance of the ingredient), etc. For example, substance 242 (i.e., water) can contain 70% of ingredient 222 sodium lauryl sulfate, as shown in 242b. Substance 272 can include chemical information properties, such as chemical class, surface area (e.g., topological polar surface area), qualitative class, qualitative sensory attribute, molecular formula, acid dissociation constant, solubility product, structural topology, functional group count, chemical fragment count, hydrophobicity, partition coefficient, steric parameter, association constant, refractive index, or hydrophilic-lipophilic balance (HLB), etc. The qualitative class can include ingredient function or ingredient classification. As Figure 2A shown, the example information can include a chemical class of alkyl sulfate, an HLB value of 40, and / or a topological polar surface area of 74.8 square angstroms. However, in other examples, one or more substances can have one or more (e.g., different) chemical information properties that have one or more different values.

[0061] As described herein, the property 212b of a personal care product may be affected by the interaction of one or more of the components of the chemical composition forming a product such as a personal care product 200, food, and / or drug. Examples of the property 212b may be related to the pH, fluoride (e.g., fluoride stability), viscosity (e.g., viscosity stability), viscoelasticity, abrasion (e.g., detergency and dentin abrasion), color, turbidity (e.g., measured by NTU), analyte concentration, specific gravity, clinical trial and / or clinical outcome information, consumer usage information (e.g., user-related information such as demographic information), product form factor information, packaging information, biomarker information, consumer perception (e.g., sweetness, tackiness, fragrance), etc. of a product such as a personal care product.

[0062] The value of the property 212b may be based on characteristics related to the property, such as a specific time period. For example, the property 212b may be related to the results of a teeth whitening clinical study over one or more time periods, such as the clinical outcomes at two weeks, four weeks, six weeks, eight weeks, etc. As another example, the efficacy (e.g., clinical efficacy) of fluoride such as bioavailable fluoride may be based on a time period. The time period may be days, weeks, months, years, etc. As another example, over a two-year time period, the bioavailable fluoride in toothpaste may decrease from 1400 parts per million (ppm) to 1100 ppm. The property 212b may include the bioavailable fluoride in toothpaste at the start of the toothpaste's shelf life (e.g., when the fluoride content is 1400 ppm) and / or at the end of the toothpaste's shelf life (e.g., when the fluoride content is 1100 ppm).

[0063] As described herein, the value of the property 212b may be determined via clinical trials, observations (e.g., clinical observations), market data, survey information, etc. The value of the property 212b of the chemical composition of a product (e.g., a personal care product) may be determined by experimentally measuring the value of the property. For example, the actual value of the property may be determined by experimentally measuring the property of the product. The value of the property 212b may be determined via a mathematical (e.g., thermodynamic) calculation of the value of the property. For example, a database of personal care product compositions may be compiled. The compositions may include one or more compositions. A catalog (e.g., a manually evaluated catalog) may contain one or more constants (e.g., metal binding constants, surface acidity constants, etc.), and / or one or more solubility products, for example. Morphological distribution calculations may be performed on the personal care product composition. The morphological distribution calculations may be used to determine the activity of one or more (e.g., each) ions of the personal care product composition. The negative logarithm of the hydrogen ion may correspond to (e.g., the activity corresponds to) the calculated value (e.g., the calculated pH value) of the personal care product composition.

[0064] The value of Property 212b can be determined by performing clinical and / or consumer tests that provide results or perceptions identifying one or more attributes of a personal care product. For example, clinical and / or consumer tests can be used to determine consumer perceptions of a personal care product. The tests can determine how consumers (e.g., potential consumers) may perceive the personal care product. For example, clinical and / or consumer tests can determine a consumer's perception of the color (e.g., whiteness), tackiness, wetness, sweetness, fragrance, bitterness, ease of use, etc. of a personal care product. Consumer perceptions can be determined by other methods, including surveys (e.g., online and paper surveys), commercial success, etc. The value of the property from clinical and / or consumer tests can be based on characteristics related to the property, such as the time period of the clinical / consumer test, user-related information of the participants in the clinical / consumer test, environmental factors in which the clinical and / or consumer test is conducted, etc. Figure 1B Provide a list of example properties of personal care products that a consumer might perceive.

[0065] Figure 2B is an example table of data related to a composition. The composition can be a chemical composition forming products such as personal care products, foods, drugs, etc. As described herein, examples of personal care products can include oral care products (e.g., toothpaste, mouthwash, etc.), hair care products (e.g., shampoo, hairspray, etc.), skin care products (e.g., moisturizer, soap, etc.), etc. Personal care products can include ingredients, such as the example ingredients named in Column 282. For example, the chemical composition forming a personal care product can include ingredients such as sorbitol, water, glycols, etc.

[0066] Ingredients (e.g., each of the ingredients) can be identified in one or more ways. For example, an ingredient can be identified by name. An ingredient can be identified by its chemical information properties. Additionally or alternatively, an ingredient can be identified by an identification number (e.g., a unique identification number), such as the identification number provided in Column 280. The identification number can be used by a user and / or one or more software applications to identify the ingredient. For example, in cases where the identity of an ingredient is confidential, the identification number can be used to hide the true identity of the ingredient. The identification number can be randomly generated, can be generated and / or listed in sequence (e.g., increasing or decreasing order), etc. Although Figure 2B the table in Column 280 shows the identifications as alphanumeric characters, those skilled in the art will understand that the identifications can be represented as any combination of numbers, letters, special characters, etc.

[0067] Figure 2B Further provide values, such as the percentage values shown in Column 284. The percentage values can be related to the percentage in which an ingredient is included in the chemical composition forming a personal care product. For example, as Figure 2BAs shown, demineralized water contains 18.296% of the chemical composition, sodium lauryl sulfate powder contains 1.5% of the chemical composition, and saccharin sodium USP or EP contains 0.3% of the chemical composition.

[0068] As described herein, a product (e.g., a personal care product) can be formed (e.g., formulated) from one or more chemical compositions comprising one or more ingredients. Formulating a personal care product using more than one chemical composition and / or one or more ingredients can present numerous challenges. For example, combining chemical compositions can alter the values of the properties of the chemical composition forming the personal care product. As an example, two or more ingredients in a combined chemical composition can cause a change in the pH value. The pH value can change in an unpredictable manner, for example, based on the interaction of two or more ingredients.

[0069] Since adding, removing, and / or mixing ingredients in a chemical composition can affect the values of the properties of the chemical composition, it can be difficult to produce a personal care product that requires adding, reducing, or mixing ingredients. For example, a personal care product may need to be pharmaceutically and / or cosmetically acceptable for its intended use and / or purpose. The intended use and / or purpose can be based on the values of the properties of the chemical composition (e.g., pH). By combining a new ingredient with a chemical composition or removing an ingredient from a chemical composition, the values of the properties of the chemical composition (e.g., the pH value) can change such that the chemical composition forming the personal care product is no longer suitable for the intended purpose of the personal care product.

[0070] The chemical composition forming a personal care product can contain a therapeutically active material that can (e.g., can only) produce the desired result if the composition does not exhibit chemical degradation. By combining a new ingredient with a chemical composition or removing an ingredient from a chemical composition, the values of the properties of the chemical composition can change such that the chemical composition forming the personal care product causes chemical degradation. Such chemical degradation may render the personal care product no longer suitable for consumer use.

[0071] The chemical composition forming a personal care product can contain a cosmetic functional material that can (e.g., can only) deliver the material to the oral cavity, skin, and / or hair, etc. in an effective amount under the conditions normally used by consumers. By combining a new ingredient with a chemical composition or removing an ingredient from a chemical composition, the values of the properties of the chemical composition can change such that the chemical composition forming the personal care product no longer functions in an effective amount.

[0072] A chemical composition forming a personal care product can (e.g., only can) exhibit an aesthetic appearance for a period of time. This aesthetic of the chemical composition can be important, for example, because this aesthetic can have a significant impact on consumer acceptance and use. By combining new ingredients with the chemical composition or removing ingredients from the chemical composition, the value of the properties of the chemical composition can be changed such that the chemical composition forming the personal care product is no longer aesthetically pleasing. For example, a transparent product can be perceived by consumers as aesthetically pleasing. In some embodiments, the methods described herein can be used to identify the type or amount of ingredients required to produce a transparent product, for example, by matching the refractive index of the product matrix with the refractive index of the particles contained therein. In some embodiments, the methods described herein can be used to identify the refractive index of solid particles using the refractive index of a transparent product matrix.

[0073] A chemical composition forming a personal care product can exhibit one or more properties perceived by consumers. For example, a chemical composition forming a personal care product can exhibit a flavor, sweetness, ease of use, etc. perceived by consumers. By combining new ingredients with the chemical composition or removing ingredients from the chemical composition, the value of the properties of the chemical composition can be changed such that the chemical composition forming the personal care product affects the consumer perception of the personal care product. For example, the value of the properties of the chemical composition may be affected such that the personal care product exhibits more mint flavor, saltier taste, etc.

[0074] A chemical composition forming a food can exhibit one or more properties perceived by consumers. For example, as perceived by consumers, a chemical composition forming a food can exhibit a flavor, sweetness, etc. A chemical composition forming a food can provide weight management, medical benefits, etc. By combining new ingredients with the chemical composition or removing ingredients from the chemical composition, the value of the properties of the chemical composition can be changed such that the chemical composition forming the personal care product affects the weight loss of food users. For example, the value of the properties of the chemical composition may be affected such that the food has additional weight loss or health benefits for the user.

[0075] As described herein, the value of the properties of a chemical composition forming a product such as a personal care product can be determined. For example, the value of the properties of a personal care product composition can be received by experimental measurement, mathematical calculation, and / or via clinical and / or consumer trials. However, such techniques can be time-consuming, non-trivial, and / or impossible because a personal care product composition may include dozens (or more) of ingredients. Machine learning techniques can be used to determine one or more values of the properties of a chemical composition.

[0076] Figure 3AAn example process 300 for determining (e.g., predicting) an attribute using machine learning techniques is shown. The attribute can include the identity of a composition, the ingredients of the composition, the value of a property of the composition, features related to the property of the composition, and the like. For example, the attribute can include the identity of a chemical composition that forms a personal care product, the ingredients of the chemical composition that forms a personal care product, the value of a property of the chemical composition that forms a personal care product (e.g., pH value, fluoride stability value, viscosity value, abrasion value, specific gravity value, consumer perception value), features related to the property (e.g., time period, user-related information, environmental factors), and the like. Although this disclosure may describe determining (e.g., predicting) the identity of a chemical composition that forms a product (e.g., personal care product), the value of a property of the chemical composition that forms a product (e.g., personal care product), and features related to the value of a property of the chemical composition that forms a product, it should be understood that machine learning techniques can also or alternatively be used to determine (e.g., predict) one or more other values, such as other identities of the product, chemical information property values of the product ingredients, features related to the property, and the like. It should also be understood that the machine learning techniques for determining chemical values are for illustrative purposes only, and machine learning techniques can also or alternatively be used to determine one or more values of non-chemical compositions.

[0077] At 302, one or more identities of a chemical composition (e.g., a sample chemical composition of a personal care product) can be stored in, for example, a database. The identity of the chemical composition can include the name of the chemical composition, the ingredients of the chemical composition (e.g., the formulation of the chemical composition), and the like. For example, as Figure 2A shown, the identity of the chemical composition can include the chemical information property (e.g., chemical information value) of each of the ingredients of the chemical composition. The identity of the chemical composition can be received from one or more in the database.

[0078] At 303, one or more perceptions of a chemical composition that forms one or more products (e.g., personal care products) can be determined and / or received. The perception of the chemical composition can be determined and / or identified via clinical trials and / or consumers (e.g., potential consumers). The perception can include the whiteness of a personal care product, the mintiness of a personal care product, the sweetness of a personal care product, and the like. The perception of the chemical composition can be affected by one or more ingredients of the chemical composition that forms the personal care product. For example, one or more ingredients may affect the degree of consumer perception of the mintiness of a personal care product, the degree of consumer perception of the sweetness of a personal care product, the degree of consumer perception of the whiteness of a personal care product, and the like.

[0079] At 304, values of properties of a chemical composition that forms one or more products (e.g., personal care products) can be determined. For example, values of properties of a chemical composition that forms one or more products can be determined via experimental measurements, clinical and / or consumer trials, etc. The values of the properties can be affected by one or more components of the chemical composition. The values of the properties can be affected by one or more characteristics related to the properties, such as the time period for measuring the properties, user-related information of consumers of the chemical composition, environmental factors of the chemical composition, packaging of the chemical composition, etc. The experimental measurement values of the properties of the chemical composition can be identified by performing actual measurements of the values of the properties of the chemical composition. The experimentally measured property values of the chemical composition can be identified, for example, by retrieving the experimentally measured property values from a database after the experimentally measured property values have been stored in the database. The experimentally measured property values of a chemical composition (e.g., a sample chemical composition) can be received.

[0080] At 306, one or more values of a chemical composition that forms a personal care product can be determined and / or stored in, for example, a database. The one or more values of the chemical composition can be related to the physical and chemical properties of the chemical composition. The values of the physical and chemical properties can include values of one or more (e.g., each) components of the chemical composition. The values of the physical and chemical properties can be received, for example, from one or more databases.

[0081] At 308, values of the physical and chemical properties of the chemical composition can be identified and / or determined. The values of the physical and chemical properties of the chemical composition can be determined by measuring the physical and chemical properties of the components of the chemical composition, calculating (e.g., mathematically calculating) predicted values of the physical and chemical properties of the chemical composition, looking up (e.g., via a database, lookup table, etc.) the values of the physical and chemical properties, etc. The values of the physical and chemical properties of the chemical composition can be identified and / or determined via thermodynamic calculations of the physical and chemical properties.

[0082] At 310, data can be input into a machine learning model as described herein. For example, the identity of the chemical composition can be input into the model. The identity of the chemical composition can include the name of one or more of the chemical composition, the identity of the components of the chemical composition, the values of the chemical information properties (components) of the chemical composition, etc. The values of the properties of the chemical composition can be input into the machine learning model. For example, the values of the properties of the chemical composition (e.g., experimentally measured values, mathematically calculated values, consumer perception values) can be input into the model. Characteristics related to the values of the properties of the chemical composition can be input into the machine learning model. For example, the time period, user-related information, and environmental factors of the chemical composition can be input into the model. For example, data related to the chemical composition can be input into the model to train the model. In other instances, data related to the chemical composition can be input into the model to determine values (e.g., other values) of the chemical composition.

[0083] Associations can be input into the model. For example, there can be associations between the identity of a chemical composition (e.g., ingredients), values of properties of the chemical composition, and features related to the values of properties of the chemical composition. Associations between features related to values of properties and the values of properties can be input into the model individually and / or in combination with other associations. The ingredients of a chemical composition (e.g., a sample chemical composition), the associated values of properties of the chemical composition (e.g., the sample chemical composition), and / or features related to the values of properties of the chemical composition can be input into a machine learning model, e.g., to train the machine learning model.

[0084] At 312, the machine learning model can determine (e.g., predict) the value of one or more data related to a chemical composition. For example, if the identity of a chemical composition (e.g., the chemical composition under consideration) is input into the machine learning model, the machine learning model can determine (e.g., predict) the value of a property of the chemical composition based on the identity of the chemical composition. Conversely, if the value of a property of a chemical composition (e.g., the chemical composition under consideration) is input into the machine learning model, the machine learning model can determine (e.g., predict) the identity of the chemical composition based on the value of the property of the chemical composition.

[0085] In other instances, if the identity of a chemical composition (e.g., the chemical composition under consideration) and features related to the property are input into the machine learning model, the machine learning model can determine (e.g., predict) the value of a property of the chemical composition based on the identity of the chemical composition and the features related to the property. Conversely, if the value of a property of a chemical composition (e.g., the chemical composition under consideration) is input into the machine learning model, the machine learning model can determine (e.g., predict) the identity of the chemical composition and the features related to the property based on the value of the property of the chemical composition. Although the above provides examples of machine learning attributes, it should be understood that these examples are for illustrative purposes only and are non-limiting. One or more different value arrangements can be input into the machine learning model and / or one or more different value arrangements can be output from the machine learning model.

[0086] Figure 3B is an example diagram of a system 350 for determining information related to a composition such as a chemical composition (e.g., a personal care product) that forms a product. The information can be related to the identity of the chemical composition, the chemical information value of the chemical composition, and one or more other values related to the product. In an example, the system 350 can be a data warehouse. For example, the system 350 can include one or more databases for receiving, storing, and / or providing data and / or one or more processors for processing the data received, stored, and / or provided by the one or more databases.

[0087] System 350 may include element 352, which may include one or more databases. For example, element 352 may include one or more databases that receive, store, and / or provide formulation identifiers, raw materials in one or more (e.g., each) formulations, and / or weight percentages of one or more (e.g., each) raw materials in a formulation. Element 352 may include one or more databases that receive, store, and / or provide formulation identifiers, descriptive sales, and / or logistics information. Element 352 may include one or more databases that receive, store, and / or provide raw material identifiers, costs, manufacturer information, and / or logistics information. Element 352 may include one or more databases that receive, store, and / or provide raw material identifiers, chemicals in one or more (e.g., each) raw materials, and / or weight percentages of one or more (e.g., each) chemicals in a raw material. Element 352 may include one or more databases that receive, store, and / or provide raw material identifiers and / or information (e.g., chemical information) properties of raw materials. Element 352 may include one or more databases that receive, store, and / or provide chemical identifiers and / or information (e.g., chemical information) properties of chemicals. Element 352 may include one or more databases that receive, store, and / or provide thermodynamic and kinetic reaction constants between chemicals, such as all known thermodynamic and kinetic reaction constants between all chemicals.

[0088] At 354, feature selection, representation, and / or engineering may be performed. For example, rules (e.g., algorithms) may perform feature selection, representation, and / or engineering.

[0089] System 350 may include element 356, which may include one or more databases. For example, element 356 may include one or more databases that receive, store, and / or provide formulation identifiers, selected features (e.g., a combination of identifiers, material information, chemical information, etc.) in one or more (e.g., each) formulations, and / or representations of feature abundances (e.g., quantitative representations) in a formulation.

[0090] At 362, chemical speciation distribution calculations may be performed (e.g., based on thermodynamic and / or kinetic constants). For example, rules (e.g., algorithms) may perform chemical speciation distribution calculations (e.g., based on thermodynamic and / or kinetic constants).

[0091] System 350 may include element 364, which may include one or more databases. For example, element 364 may include one or more databases that receive, store, and / or provide formulation identifiers, calculated values of properties of chemical compositions, and / or equilibrium properties (e.g., based on kinetic and thermodynamic constants).

[0092] System 350 may include element 366, which may include one or more databases. For example, element 366 may include one or more databases that receive, store, and / or provide formulation identifiers and / or test values (e.g., analytic test values experimentally determined for properties of a chemical composition). The properties of a sample chemical composition may be affected by the interactions of two or more components of the sample chemical composition. Element 366 may include one or more databases that receive, store, and / or provide formulation identifiers and / or consumer-derived test results. Element 366 may include one or more databases that receive, store, and / or provide formulation identifiers and / or clinical test results.

[0093] At 368, fitting parameters for test results may be determined. For example, rules (e.g., algorithms) may determine fitting parameters for test results.

[0094] System 350 may include element 370, which may include one or more databases. For example, element 370 may include one or more databases that receive, store, and / or provide formulation identifiers, aggregated test results, and / or fitting parameters associated with the test results.

[0095] At 358, machine learning information may be determined. For example, rules (e.g., algorithms) may determine machine learning information.

[0096] System 350 may include element 360, which may include one or more databases. For example, element 360 may include one or more databases that receive, store, and / or provide machine learning model parameters.

[0097] Figure 4 is process 400 showing other example steps of predicting chemical composition information via machine learning rules as described herein. In Figure 4 it, cross-hatching is used to represent relationships within the process.

[0098] At 402, the process begins. At 404, an entity (e.g., a business) may begin to understand and / or improve its understanding of chemical composition information. For example, the entity may begin and / or improve its understanding of the need for a chemical composition to have a certain characteristic, such as a chemical composition having a certain value of pH, emulsifying purpose, sweetness, thickener, etc. Although the entity may understand the need for a chemical composition to have a certain property (e.g., a property value), the entity may not know what the ingredients of the chemical composition will be to produce such a property (e.g., a property value).

[0099] At 406, data related to a chemical composition can be collected. For example, an entity can collect the identity of the chemical composition (e.g., name, ingredients, chemical information properties, etc.), values of the properties of the chemical composition, characteristics related to the values of the properties of the chemical composition, etc. Information about the chemical composition can be collected via experimental measurements, mathematical calculations, clinical and / or consumer trials, one or more data sources (e.g., databases, files, etc.), or other information channels. Associations between the information can be identified and / or determined. For example, an association between the identity of the chemical composition and the values of the properties of the chemical composition can be determined, an association between the characteristics related to the values of the properties of the chemical composition and the values of the properties of the chemical composition can be determined, etc.

[0100] At 408, a machine learning model can be trained and / or used as described herein. For example, information related to a chemical composition (e.g., a sample chemical composition) can be used to train the machine learning model. The information can be the associated values of the identity of the chemical composition and the properties of the chemical composition. The information can be the identity of the chemical composition, the associated values of the properties of the chemical composition, and / or characteristics related to the values of the properties. The trained machine learning model can be used to determine and / or predict the value (e.g., an unknown value) of a chemical composition (e.g., the chemical composition under consideration) based on, for example, the identity of the chemical composition (e.g., the chemical composition) and / or characteristics related to the values of the properties.

[0101] At 410, a machine learning model can be deployed. When deployed, the machine learning model can determine the values of the properties of a chemical composition (e.g., the chemical composition under consideration) based on the identity of the chemical composition and / or characteristics related to the values of the properties. The machine learning model can determine the identity of the chemical composition based on the values of the properties of the chemical composition and / or characteristics related to the values of the properties, etc.

[0102] The determined values of the properties of the chemical composition can be compared with the expected values of the properties of the chemical composition. For example, the pH value returned from the machine learning model can be compared with the expected pH value. The pH value returned from the machine learning model can be compared with the actual (e.g., actually measured) pH value. If it is determined that the value of the property is the same as (e.g., substantially the same as) the expected value, the entity can move towards producing a chemical composition (e.g., a personal care product) having the expected value of the property. The entity can use the ingredients input into the machine learning model to produce a chemical composition having the expected value of the property. For example, the entity can use the ingredients input into the machine learning model to produce a chemical composition that produces the desired determined (e.g., predicted) pH value. A product (e.g., a personal care product) can be produced using the chemical composition such that the product (e.g., a personal care product) will be composed of ingredients that produce the desired value of the property.

[0103] Figure 5 FIG. 500 is a block diagram of an example system 500 for determining (e.g., predicting) data associated with a composition (e.g., a chemical composition) that forms a product such as a personal care product. The data may include the identity of the chemical composition, values of chemical composition properties, characteristics related to the properties of the chemical composition, and / or one or more types of data. The data may be determined based on one or more attributes and / or parameters. For example, system 500 may determine (e.g., predict) data associated with the properties of a chemical composition based on one or more attributes / parameters and machine learning techniques. Although the examples provided herein may relate to determining (e.g., predicting) the identity of a chemical composition, values of the properties of a chemical composition, characteristics related to the properties of a chemical composition, and / or fitting parameters using machine learning techniques, those skilled in the art will understand that one or more other values and / or parameters associated with a chemical composition may be determined (e.g., predicted) using machine learning techniques. For example, chemical information values of the components of a chemical composition may be determined, chemical constants may be determined, clinical and / or consumer outcomes and perceptions may be determined, etc.

[0104] System 500 includes a user device 502 configured to be connected via a network 520 to a property modeling device, such as an example chemical property modeling device 602 (further described in Figure 6 ). Network 520 may include wired and / or wireless communication networks. For example, network 520 may include a local area network (LAN), a metropolitan area network (MAN), and / or a wide area network (WAN). Network 520 may facilitate connection to the Internet. In additional examples, network 520 may include wired telephone and cable hardware, satellites, cellular telephone communication networks, etc.

[0105] User device 502 may include a user interface 504, a memory 506, a central processing unit (CPU) 508, a graphics processing unit (GPU) 510, an image capture device 514, and / or a display 512. User device 502 may be implemented as a user equipment (UE), such as a mobile device, a computer, a laptop, a tablet, a desktop, or any other suitable type of computing device.

[0106] User interface 504 may allow a user to interact with user device 502. For example, user interface 504 may include a user input device, such as an interactive portion of display 512 (e.g., a “soft” keyboard displayed on display 512), an external hardware keyboard configured to communicate with user device 504 via a wired or wireless connection (e.g., a Bluetooth keyboard), an external mouse, or any other user input device. User interface 504 may allow a user to input, view, etc., one or more pieces of information related to a chemical composition that forms a personal care product.

[0107] Memory 506 may store instructions executable on CPU 508 and / or GPU 510. The instructions may include machine-readable instructions that, when executed by CPU 508 and / or GPU 510, cause CPU 508 and / or GPU 510 to perform various actions. Memory 506 may store instructions that, when executed by CPU 508 and / or GPU 510, cause CPU 508 and / or GPU 510 to allow user interface 504 to interact with a user. For example, the executable instructions may allow the user interface (via display 512) to display one or more prompts to the user and / or accept user input. For example, instructions stored in memory 506 may allow the user to input the identity of a chemical composition and / or values of properties of the chemical composition. In other instances, the user may utilize user interface 504 to click, hold, or drag a cursor to define the identity, values, and / or properties of the chemical composition.

[0108] CPU 508 and / or GPU 510 may be configured to communicate with memory 506 to store data in and read data from the memory. For example, memory 506 may be a computer-readable non-transitory storage device that may include any combination of volatile (e.g., random access memory (RAM)) or non-volatile (e.g., RAM with a backup battery, flash memory, etc.) memory.

[0109] Image capture device 514 may be configured to capture images. The images may be two-dimensional images, three-dimensional images, etc. Image capture device 514 may be configured to capture images in digital format having a number of pixels. Although image capture device 514 is shown in Figure 5 as being inside user device 502, in other instances, image capture device 514 may be inside and / or outside user device 502. In an instance, image capture device 514 may be implemented as a camera coupled to user device 502. Image capture device 514 may be implemented as a webcam coupled to user device 502 and configured to communicate with user device 502. Image capture device 514 may be implemented as a digital camera configured to transmit digital images to user device 502 and / or chemical property modeling device 602. For example, such transmission may be via cable, wireless transmission, network 520 / 620, and / or physical memory card device transmission (e.g., SD card, flash card, etc.). Image capture device 514 may be used to capture images of personal care products, chemical compositions forming personal care products, data related to chemical compositions, data related to one or more features of personal care products, etc.

[0110] In an example, a user may input information related to one or more compositions (e.g., chemical compositions) into a user device 502. The chemical composition information may be transmitted to and / or from a chemical property modeling device 602, as Figure 5 shown. In a case where the chemical property modeling device 602 has information related to a chemical composition (e.g., the identity of the chemical composition and / or values of properties of the chemical composition), the chemical property modeling device 602 may return information about the chemical composition. For example, the chemical property modeling device 602 may provide values of properties of the chemical composition (e.g., predicted values).

[0111] The user device 502 may obtain information (e.g., unknown information) about one or more chemical compositions for prediction purposes (e.g., the name of the chemical composition, the ingredients of the chemical composition, the chemical information values of the ingredients of the chemical composition, the values of the properties of the chemical composition, features related to the properties of the chemical composition, etc.). For example, a user (e.g., the user of the user device 502) may desire to know the identity of a chemical composition having a value of a property of a personal care product (e.g., an expected value). The value of the property may be affected by the interaction of one or more ingredients of the chemical composition with each other. The value of the property of the personal care product (e.g., the expected value) may be the value of the personal care product (e.g., pH value), the function of one or more ingredients of the personal care product, the classification of one or more ingredients of the personal care product, the consumer perception of the personal care product, etc.

[0112] The user may input one or more types and / or values of chemical composition information (e.g., name, ingredients, chemical information properties, etc.) into the user device 502, for example, to determine information about the chemical composition (e.g., other information). The user device 502 may transmit the information to the chemical property modeling device 602.

[0113] In an example, all or some of the steps, processes, methods, etc. may be performed by one device or more than one device (e.g., the user device or the chemical property modeling device). For example, in an example, the user device 502 may include a chemical property engine 630. In other examples, the chemical property modeling device 602 may be external to the user device 502. In an example where the chemical property modeling device 602 is separate from the user device 502, the user device 502 may communicate with the chemical property modeling device 602 via one or more wired and / or wireless technologies as described herein. For example, as Figure 5 shown, the user device 502 may communicate with the chemical property modeling device 502 via a network 520. In some examples, the network 520 may be the Internet. In other examples, as described herein, the network 520 may be Wi-Fi, Bluetooth, LAN, etc.

[0114] It is possible to receive values of properties of a chemical composition (e.g., expected values of properties). A chemical composition that receives a value of a property and whose identity is determined by machine learning rules can be referred to as the chemical composition under consideration. For example, a user can receive values of properties of a chemical composition (e.g., expected values). The user can transmit the values of the properties to the chemical property modeling device 602. The values can be related to properties affected by one or more components of the chemical composition. The values can be related to pH values, fluorine stability values, viscosity values, abrasion values, specific gravity values, clinical trial and / or clinical outcome values, user-specific information (e.g., demographic information) values, time period values, storage information (e.g., storage temperature, storage humidity), biomarker values, consumer perception values, etc. For example, the user can transmit a pH value to the chemical property modeling device 602, transmit a stability value to the chemical property modeling device 602, transmit clinical trial and / or clinical outcome values to the chemical property modeling device 602, transmit user-specific values (e.g., demographic information) to the chemical property modeling device 602, transmit biomarker values to the chemical property modeling device 602, etc.

[0115] The user can transmit one or more values of one or more properties to the chemical property modeling device 602. The user can transmit one or more characteristics related to one or more properties to the chemical property modeling device 602. The values of the properties and the characteristics related to the properties can be transmitted to the chemical property modeling device 602, for example, simultaneously or at different times. An indication of the relationship between the values of the properties and the characteristics related to the properties can be transmitted to the chemical property modeling device 602.

[0116] The values of the properties can correspond to clinical trial and / or clinical outcome data, consumer trial and / or consumer outcome data, etc. The values of the properties corresponding to clinical trial and / or clinical outcome data can be the perceived preference of consumers for a product (e.g., perfume), the clinical whitening efficacy of toothpaste, the moisturizing ability of a skin cream, etc. As described herein, the identity of the chemical composition (e.g., the components of the chemical composition and / or chemical information properties) can be transmitted to the chemical property modeling device 602, the corresponding property values (e.g., clinical trial and / or clinical outcome data) can be transmitted to the chemical property modeling device 602, and / or one or more additional data sets can be transmitted to the chemical property modeling device 602. The additional data sets can be data related to property data, such as clinical trial and / or clinical outcome data.

[0117] A user can transmit the identity of a composition (e.g., the ingredients of the composition) and the properties of the composition (e.g., teeth whitening) to the chemical property modeling device 602. The user can transmit features related to the properties of the chemical composition (e.g., teeth whitening). Features related to properties can be formulation attributes (e.g., the oxidation potential of the chemical composition), time periods (e.g., the teeth whitening values at six weeks of use, at eight weeks of use), user-related data (e.g., the age of the consumer using the chemical composition, geographical data related to the consumer, the user's brushing habits, etc.), and so on.

[0118] Although the above examples may involve user-related information and time period information, other types of information related to properties can also be transmitted to the chemical property modeling device 602, such as information related to product storage. Other information related to properties can include user information of the product, such as ethnic information, physical alterations (e.g., tattoos, piercings, etc.), diet, height, weight, body mass index, body hair coverage, body sweat production, skin sebum production, biomarkers, hair type / color, skin pH value, nutrition, exercise regimens, body flora, health status and / or condition, etc. Environmental characteristics, such as product storage temperature, product storage humidity, product packaging, variables that affect the kinetics of chemical reactions occurring in the product or the kinetics of phase transitions, etc., can be related to properties and can be transmitted to the chemical property modeling device 602.

[0119] A user can transmit the identity of the chemical composition and the value of the property related to the chemical composition such as fluorine to the chemical property modeling device 602. The user can also or alternatively transmit one or more features related to the property, such as time periods, environmental information, user-related information, etc. The time period can include the time of the shelf life of the chemical composition, such as the start of the shelf life of the chemical composition, the end of the shelf life of the chemical composition, and / or one or more time periods therebetween. For example, the user can transmit the identity of the toothpaste formed from the chemical composition, the value of fluorine related to the toothpaste, and the time period of six weeks to the chemical property modeling device 602. Thus, in this example, the value of fluorine of a specific toothpaste at six weeks will be transmitted to the chemical property modeling device 602.

[0120] As another example, the user can transmit the value of the property of fluorine decay rate. The user can transmit the identity of the toothpaste, the value of the property of fluorine decay rate, and one or more time periods and / or one or more storage conditions. For example, the user can transmit the identity of the toothpaste, the value of the property of fluorine decay rate, the time periods at the start and / or end of the product's shelf life, and an indication that the chemical composition is stored at a low temperature with low humidity. In other examples, the user can transmit the value of the property of fluorine decay rate and indicate that the chemical composition is stored at a high temperature with high humidity.

[0121] Environmental characteristics may affect a consumer's perception of a product. For example, a perfume can diffuse a fragrance (e.g., how the consumer perceives a change in the perfume odor). How a consumer perceives the perfume diffusion can depend on one or more environmental characteristics such as environmental conditions, audio conditions, etc. Other properties can be affected by other environmental factors such as temperature, humidity, altitude, environmental composition (e.g., the presence of volatile components in the local atmosphere), etc. The property and the characteristics on which the property depends (e.g., environmental characteristics) can be transmitted to the chemical property modeling device 602. For example, when perfume diffusion is specified as an attribute to be transmitted to the chemical property modeling device 602, information related to the property (e.g., environmental conditions such as atmospheric conditions) can be transmitted to the chemical property modeling device 602.

[0122] Based on the value of the property and / or the characteristics related to the property, the chemical property modeling device 602 can provide the identity of a chemical composition that has (e.g., is predicted to have) the value of the property (e.g., or an approximation thereof) and / or the characteristics related to the property. For example, the chemical property modeling device 602 can provide the name of a composition that has (e.g., is predicted to have) the value and / or the characteristics related to the property, the ingredients of a chemical composition that has (e.g., is predicted to have) the value and / or the characteristics related to the property, and the chemical information values of the ingredients of a chemical composition that has (e.g., is predicted to have) the value and / or the characteristics related to the property, etc.

[0123] The user can also or alternatively provide information related to the chemical composition to determine the value of the property of the chemical composition and / or the characteristics related to the property. For example, the user can input the name of the composition, the ingredients of the chemical composition, the chemical information values of the ingredients of the chemical composition, the consumer perception of the chemical composition, the desired aesthetic of the chemical composition, etc. into the chemical property modeling device 602. Based on the name, ingredients, and / or chemical information, the chemical property modeling device 602 can determine the value of the property of the chemical composition. The chemical property modeling device 602 can determine the value of the property of the chemical composition corresponding to the characteristics related to the property. For example, based on the name, ingredients, and / or chemical information, the chemical property modeling device 602 can determine the pH value, fluoride stability value, viscosity value, refractive index, abrasion value, specific gravity value, clinical trial and / or clinical outcome information, etc. of the chemical composition. According to the name, ingredients, and / or chemical information, the chemical property modeling device 602 can determine the pH value, fluoride stability value, viscosity value, refractive index, abrasion value, specific gravity value, clinical trial and / or clinical outcome information, etc. corresponding to user-related information (e.g., the age of the user), formulation attribute information, packaging information, time period information (e.g., the value of the property at six weeks), storage information, etc.

[0124] Figure 6An example system 600 is shown that trains a property engine, such as a chemical property engine 630. The chemical property engine 630 may be housed in a chemical property modeling device 602, but this configuration is for illustrative purposes only. As Figure 6 shown, a training device 650 may communicate with the chemical property modeling device 602. For example, the training device 650 may communicate with the chemical property modeling device 602 via a network 620. One or more training devices 650 may provide information, as described herein, for training, for example, the chemical property engine 630 of the chemical property modeling device 602.

[0125] The training device 650 may provide information to a modeling device, such as the chemical property modeling device 602. The information provided to the chemical property modeling device 602 may include the identity of a chemical composition, values of properties of the chemical composition, and / or values of characteristics related to properties of the chemical composition. For example, the information provided to the chemical property modeling device 602 may include experimental measurement information related to a chemical composition (e.g., a chemical composition forming a personal care product), mathematical calculation information related to the chemical composition, clinical / consumer trial and / or result information, user-related information, physical characteristics of a user, form factor of the chemical composition, packaging of the chemical composition, biomarker information (e.g., biomarker information related to a user and / or potential user of the product), degree and / or manner of interaction of the product with the environment, environmental characteristics of the chemical composition, consumer perception information related to the chemical composition, etc. The training device 650 may provide values of properties of the chemical composition, such as actual values of properties of the chemical composition and / or mathematically determined values of properties of the chemical composition.

[0126] The training device 650 may provide information related to a chemical composition, which includes the identity of the chemical composition (e.g., name of the chemical composition, ingredients of the chemical composition, chemical information values of the ingredients of the chemical composition, etc.).

[0127] As provided herein, the information provided by the training device 650 may be based on actual (e.g., actually measured information, such as values of a chemical composition that have been actually measured, clinical trial information, etc.) information. Additionally or alternatively, the information provided by the training device 650 may be based on values of a chemical composition determined using mathematical calculations, such as thermodynamic calculations of the chemical composition, to determine values of properties of the chemical composition. As described herein, providing this information (e.g., actual information and / or thermodynamically calculated information) to the chemical property engine 630 may be used to train a model using machine learning techniques. The chemical compositions for which the information is used to train machine learning rules may be referred to as sample chemical compositions.

[0128] The chemical property modeling device 602 may include a CPU 608, a memory 606, a GPU 610, an interface 616, and a chemical property engine 630. The memory 606 may be configured to store instructions executable on the CPU 608 and / or the GPU 610. The instructions may include machine-readable instructions that, when executed by the CPU 608 and / or the GPU 610, cause the CPU 608 and / or the GPU 610 to perform various actions. The CPU 608 and / or the GPU 610 may be configured to communicate with the memory 606 to store data in the memory 606 and read data from the memory. For example, the memory 606 may be a computer-readable non-transitory storage device that may include any combination of volatile (e.g., random access memory (RAM)) or non-volatile memory (e.g., RAM with a backup battery, flash memory, etc.).

[0129] The interface 616 may be configured to interface with one or more devices internal or external to the chemical property modeling device 602. For example, the interface 616 may be configured to interface with a training device 650 and / or a chemical property database 624. The chemical property database 624 may store information about chemical compositions, such as the name of the chemical composition, the components of the chemical composition, the chemical information values of the components of the chemical composition, the values of the chemical composition properties (e.g., pH value, fluorine (e.g., fluorine stability) value, viscosity (e.g., viscosity stability) value, abrasion (e.g., detergency and dentin abrasion) value, refractive index value, specific gravity value, clinical trial and / or clinical outcome data, consumer perception (e.g., sweetness, adhesiveness, fragrance) value), the values of the characteristics related to the properties of the chemical composition (e.g., user-related information, time period information, environmental information), etc. The information stored in the chemical property database 624 may be used to train the chemical property engine 630. The information stored in the chemical property database 624 may also or alternatively be referenced by the chemical property engine 630 to determine (e.g., predict) information about a chemical composition (e.g., the chemical composition under consideration).

[0130] A device (e.g., the user device 502 and / or the chemical property modeling device 602) may receive information about one or more compositions (e.g., chemical compositions) via the training device 650 and / or another device. The information may relate to one or more (e.g., many) different types of compositions, such as chemical compositions, chemical composition families, complete and / or incomplete chemical compositions, chemical compositions with a rich history, relatively unknown chemical compositions, compositions that are not chemical substances in nature, etc.

[0131] One or more types of information of a composition (e.g., a chemical composition) can be provided to the chemical property modeling device 602. For example, one or more types of information of a chemical composition (e.g., a sample chemical composition) can be provided to the chemical property modeling device 602 to train the chemical property modeling device 602 (e.g., the machine learning rules of the chemical property modeling device 602). For example, for each chemical composition, the chemical property modeling device 602 can receive the actual (e.g., actually measured) information of the chemical composition, the calculated (e.g., thermodynamically calculated) information of the composition, the predicted information of the chemical composition, the identity information of the chemical composition, the clinical trial and / or result information of the chemical composition, user-related information, environmental information, time period information, consumer preference information of the chemical composition, etc. The chemical property modeling device 602 can perform information association so that prediction of chemical composition data (e.g., similar chemical composition data) can be performed.

[0132] The chemical property modeling device 602 can use machine learning techniques to develop software applications (e.g., models). For example, the chemical property engine 630 can include machine learning rules for determining (e.g., predicting) information related to a chemical composition. The chemical property engine 630 can include a model (e.g., a machine learning model) for determining (e.g., predicting) information about a chemical composition. The information provided to the model and / or the information provided by the model can be used to train the model. The information for training the model can include the identity of the chemical composition (e.g., name, ingredients, chemical information values of the ingredients, etc.), the values of the properties of the chemical composition, the features related to the values of the properties of the chemical composition, etc. The information for training the model can include clinical / consumer trial and / or result information, user-related information, consumer perception information of the chemical composition, etc. The information provided to the model and / or provided by the model for training the model can be related to a chemical composition (e.g., a sample chemical composition).

[0133] The chemical property engine 630 can include currently known and / or later developed machine learning rules or algorithms. The machine learning rules can be supervised machine learning rules and / or unsupervised machine learning rules. For example, the chemical property engine 630 can include at least one of the following: random forest rules, support vector machine rules, naive Bayes classification rules, boosting rules, variants of boosting rules, alternating decision tree rules, support vector machine rules, perceptron rules, Winnow rules, hedge rules, rules for constructing linear combinations of features or data points, decision tree rules, neural network rules, logistic regression rules, log-linear model rules, perceptron-like rules, Gaussian process rules, Bayesian techniques, probabilistic modeling techniques, regression trees, ranking rules, kernel methods, margin-based rules, linear / quadratic / convex / cone / semidefinite programming techniques, or any modifications of the above.

[0134] The chemical property engine 630 can improve its ability to perform tasks when analyzing more data related to the tasks. As described herein, the task can be to determine (e.g., predict) unknown information related to the chemical composition for forming a personal care product. The unknown information can be, for example, an unknown value of the properties of a chemical composition from known information. The task can be to predict the value of the properties of a chemical composition based on the identity information of the chemical composition. The task can be to predict the value of the properties of a chemical composition based on the identity information and / or characteristics related to the properties. The task can be to predict the identity of a chemical composition based on the value of the properties of the chemical composition and / or characteristics related to the properties. In such instances, the more information (related to one or more chemical compositions) provided to the model, the better the results of the model. For example, the model can provide a more accurate determination of the value of the properties of a chemical composition based on the numerous information the model receives about the chemical composition and the information related to the identity of the chemical composition.

[0135] As described herein, a set of training instances can be used to train a machine learning model. Each training instance can include an instance of an object, and the value of the properties of the object and / or characteristics related to the value of the properties of the object. By processing a set of training instances including the object, the value of the properties of the object, and / or characteristics related to the properties, the model can determine (e.g., learn) the attributes or characteristics of the object associated with a specific value of the properties. This learning can then be used to predict the properties or predict the classification of other objects. As described herein, machine learning techniques (e.g., rules, algorithms, etc.) can be used to develop a model for one or more chemical compositions.

[0136] The chemical composition (and / or one or more components of the chemical composition) for forming a personal care product can be identified and / or classified based on the product, function, classification, clinical / consumer trial, and / or outcome information, user-related information, shape factor information of the chemical composition, packaging of the chemical composition, biomarker information, degree and / or manner of interaction between the product and the environment, environmental characteristics of the chemical composition, consumer perception, etc. The one or more chemical compositions (and / or one or more components in the chemical composition) can be identified and / or classified before being input into the machine learning rules. The one or more chemical compositions (and / or one or more components in the chemical composition) can be identified and / or classified by the machine learning rules. For example, the machine learning rules can identify and / or classify the chemical composition (and / or one or more components in the chemical composition) based on the product, function, classification, clinical / consumer trial, consumer perception, etc.

[0137] Models (e.g., machine learning models) can be developed to receive information related to a chemical composition, e.g., to determine (e.g., predict) information about the chemical composition. Training instances (e.g., a training set or training data) can be used to train the chemical property engine 630. For example, the training data can include the name of a sample chemical composition, the ingredients of the sample chemical composition, the chemical information values of the ingredients of the sample chemical composition, the fitting parameters of the sample chemical composition, the function of the sample chemical composition, the classification of the sample chemical composition, the values of the properties of the sample chemical composition, etc. The values of the properties of the sample chemical composition can be determined via calculations, e.g., via thermodynamic calculations. The values of the properties of the sample chemical composition can be determined via experimental measurements. As described herein, the properties of the sample chemical composition can include the pH of the sample chemical composition, fluoride stability, viscosity stability, abrasion, specific gravity, clinical / consumer trial and / or outcome information, user-related information, shape factor information of the chemical composition, the packaging of the chemical composition, biomarker information, the degree and / or manner of interaction of the product with the environment, environmental characteristics of the chemical composition, consumer-perceived properties, etc.

[0138] After training the chemical property engine 630 (e.g., the machine learning model of the chemical property engine 630) using the training data, the chemical property engine 630 can be used to determine (e.g., predict) data. For example, the chemical property engine 630 can be used to determine (e.g., predict) parameters similar to those used to train the chemical property engine 630. For example, the identity (e.g., ingredients) of a chemical composition and the value of the pH property of the chemical composition can be used to train the chemical property engine 630. The chemical property engine 630 can be used to determine an unknown value of the pH property, e.g., based on the identity (e.g., ingredients) of the chemical composition. In another example, the identity (e.g., ingredients) of a chemical composition, the value of the result of a teeth whitening clinical study, and one or more characteristics related to the teeth whitening clinical study, e.g., a time period related to the result of the teeth whitening clinical study, can be used to train the chemical property engine 630. Based on the identity (e.g., ingredients) of the chemical composition, the chemical property engine 630 can be used to determine an unknown value of the result of the teeth whitening clinical study over one or more time periods.

[0139] In other instances, after training the chemical property engine 630 (e.g., the machine learning model of the chemical property engine 630) using training data, the chemical property engine 630 can be used to determine parameters different from the parameters used to train the chemical property engine 630. For example, the chemical property engine 630 can be trained using the identity of a chemical composition (e.g., ingredients) and the value of the pH property of the chemical composition. The chemical property engine 630 can be used to determine an unknown value of the soluble zinc property. The chemical property engine 630 can be used to determine the unknown value of the soluble zinc property based on the identity of the chemical composition (e.g., ingredients). Different parameters can have relationships with each other. The relationships between different parameters can allow the chemical property engine 630 to predict different parameters. Using the above example, although the pH property and the soluble zinc property are different properties, the relationship between the pH property and the soluble zinc property can allow the chemical property engine 630 to predict soluble zinc data based on pH training data.

[0140] Other data related to the chemical composition can be used to train the chemical property engine 630. For example, features (e.g., data) related to the property can be used to train the chemical property engine 630. For example, data related to the property can be user-related information associated with the value of the property, environmental data associated with the value of the property, time period data associated with the value of the property, fitting parameters associated with the value of the property, but other types of data can also be used to train the chemical property engine 630. For example, the training data can include the identity of a sample chemical composition (e.g., name, ingredients, and / or chemical information values of the ingredients) and the fitting parameters of the sample chemical composition.

[0141] The fitting parameters can be used to determine the value of a parameter in a defined instance. For example, the fitting parameter can be related to the rate at which the value changes over time. The fitting parameters can be used to determine the value of a parameter at a future date, number of days, time, time period, etc. The fitting parameters can be used to define a continuous function. The fitting parameters can be used to determine the value of a property at one or more (e.g., any) time points. For example, if the value of the fluorine stability has been measured at 4, 8, and 13 weeks, a fitting parameter can be derived, which can provide the value of the fluorine stability at intermediate time points between 4, 8, and 13 weeks and / or at extended points after 13 weeks (e.g., expected values).

[0142] Fitting parameters can be used to determine values of characteristics related to the properties of a composition. For example, fitting parameters can be derived that provide values of clinical outcomes (e.g., expected values) over one or more time periods. Clinical outcomes can be related to products such as personal care products, foods, drugs, etc. For example, fitting parameters can be derived that can provide clinical outcomes of gingivitis reduction over a three - month or six - month period, clinical outcomes of teeth whitening over a period of days to months, clinical outcomes of allergy relief over a period of minutes to months, and / or clinical outcomes of wrinkle reduction over ninety days. In other instances, fitting parameters can be derived that provide clinical outcomes of weight loss over a six - week period (e.g., of a human or an animal), reduction of a medical condition (e.g., elevated blood pressure) over an eight - week period, etc.

[0143] Determining values of properties at future dates, days, times, time periods, etc. can be useful because manufacturers of products (e.g., personal care products) may need to demonstrate that the product (e.g., personal care product) maintains a minimum threshold quantity of a property throughout the product's shelf life. For example, since the shelf life of a product may be several years, it may be impractical to test the product (e.g., a new product) over certain time periods (e.g., several months, years, etc.) to determine the viability of the product. It can be advantageous to collect data (e.g., collect data over a short time period) and use fitting parameters to infer values of properties over a longer time period. Such models (e.g., models that predict fitting parameters) can predict properties at time points where experimental data may not exist. Characteristics related to the property can include data corresponding to the time period (e.g., time points) of the product's shelf life, but the characteristics can be data other than the time - period data in the examples.

[0144] Data related to a chemical composition can be used to train a chemical property engine 630. As described herein, the data can be the identity of the chemical composition (e.g., ingredients) and other data. For example, the ingredients of the chemical composition, the molecular weight of the ingredients (e.g., each ingredient), the weight percentage of the ingredients (e.g., each ingredient), etc. can be used to train the chemical property engine 630. The weight percentage of the ingredients (e.g., each ingredient) can be converted to molar concentration. The molar concentration, the theoretical total fluoride content, and / or the soluble fluoride can be used to train the chemical property engine 630 after the chemical composition has aged (e.g., after the chemical composition has aged for 13 weeks at 40 degrees Celsius). After training the chemical property engine 630 (e.g., the machine - learning model of the chemical property engine 630) using the training data, the chemical property engine 630 can be used to determine (e.g., predict) data. For example, the chemical property engine 630 can be used to determine (e.g., predict) the value of soluble fluoride after aging based on the identity of the chemical composition (e.g., ingredients) and / or based on molecular concentration data related to the chemical composition.

[0145] The values of the parameters can be determined for a future time period using the fitting parameters. The future time period can be a characteristic related to the property. For example, the chemical property engine 630 can be trained using the components of a chemical composition, the molecular weight of the components (e.g., each component), the weight percentage of the components (e.g., each component), and / or the fitting parameters. After training the chemical property engine 630 (e.g., the machine learning model of the chemical property engine 630) using the components of a chemical composition, the molecular weight of the components (e.g., each component), the weight percentage of the components (e.g., each component), and / or the fitting parameters, the chemical property engine 630 can be used to determine the fitting parameters. The fitting parameters can be used with a fitting function to determine defined instances, as described herein. For example, the chemical property engine 630 can be used to determine (e.g., predict) the value of a fitting parameter that can be used with a fitting function to determine the theoretical total fluoride content and / or soluble fluoride content measured after the chemical composition has aged (e.g., after the chemical composition has aged at 40 degrees Celsius for 4, 8, and / or 13 weeks). Example fitting functions can include exponential functions, polynomial functions, power functions, trigonometric functions, but other fitting functions can also be used.

[0146] The information included in the training data can be selected based on function and / or classification and / or input into the model of the chemical property engine 630. For example, a chemical composition and / or the components of a chemical composition can have a defined function and / or classification, such as components in a chemical composition having a binding function, a retention function, a whitening function, an alcohol classification, an ether classification, etc. The function can relate to how one or more components of the chemical composition are used in a product form. The function can relate to the plaque cleaning ratio (PCR) and / or the relative dentin abrasion (RDA).

[0147] The PCR is a measure of detergency and can represent the cleaning efficacy of a personal care product such as toothpaste. The RDA is a measure of the abrasion rate (e.g., the pure abrasion rate) and can represent the erosive ability of a personal care product such as toothpaste. Example functions 700 of a chemical composition and / or the components in a chemical composition can be found in Figure 7 . Example classifications 800 of a chemical composition and / or the components in a chemical composition can be found in Figure 8 . Although Figure 7 and Figure 8 provide lists of functions and classifications respectively, those skilled in the art should understand that the functions provided in Figure 7 and the classifications provided in Figure 8 are provided for illustrative purposes only and are not restrictive.

[0148] In an example, one or more chemical compositions may (e.g., only may) be input into the model if the chemical composition has a function (e.g., a desired function). For example, the set may consist of eighty chemical compositions. Among the eighty chemical compositions, fourteen chemical compositions may include ingredients that provide a whitening function. A user may desire to determine the value of a property of a chemical composition where the chemical composition (e.g., the ingredients of the chemical composition) may have a whitening function. In such examples, the model may be trained using (e.g., only using) the chemical compositions (e.g., the ingredients of the chemical composition) having a whitening function, such as the fourteen chemical compositions in the above example. Additionally or alternatively, the model may classify the chemical compositions based on the function of the chemical compositions (e.g., automatically classify, dynamically classify, etc.).

[0149] In cases where the model includes (e.g., only includes) chemical compositions having a defined function or the model classifies chemical compositions based on a defined function, the chemical property engine 630 may provide information on the chemical compositions having (e.g., only having) the function. For example, the chemical property engine 630 may determine the value of the property of a chemical composition having a function (e.g., a flavor function, a binding function, etc.) based on the identity of the chemical composition. Conversely, the chemical property engine 630 may determine the identity of a chemical composition having a certain function based on the value of the property of the chemical composition.

[0150] In other examples, one or more chemical compositions may (e.g., only may) be input into the model if the chemical composition has a certain classification (e.g., a chemical classification). The classification may be related to the molecular properties of the ingredients of the chemical composition, such as chemical compositions forming personal care products. The chemical composition may (e.g., only may) be input into the model if the chemical composition has a desired classification. Example chemical classifications may include alcohol classification, amino acid classification, enzyme classification, fatty acid classification, ketone classification, peptide classification, and Figure 8 other classifications provided in

[0151] For example, the set may consist of forty chemical compositions. Among the forty chemical compositions, ten chemical compositions may include ingredients classified as ethers. A user may desire to determine the value of a property of a chemical composition where the chemical composition (e.g., the ingredients of the chemical composition) may have an ether classification. In this example, the model may be trained using (e.g., only using) the chemical compositions (e.g., the ingredients of the chemical composition) having an ether classification. Additionally or alternatively, the model may classify the chemical compositions based on the classification of the chemical compositions (e.g., automatically classify, dynamically classify, etc.).

[0152] In cases where the model includes (e.g., consists only of) defined classifications of chemical compositions or the model classifies chemical compositions based on defined classifications, the chemical property engine 630 can provide information on chemical compositions having (e.g., consisting only of) the classifications. For example, the chemical property engine 630 can determine the values of properties of chemical compositions having a classification (e.g., alcohol classification, fatty acid classification, etc.) based on the identity of the chemical composition. Conversely, the chemical property engine 630 can determine the identity of a chemical composition having a certain classification based on the values of the properties of the chemical composition.

[0153] As described herein, information related to one or more chemical compositions can be input into the model based on the function, classification, clinical / consumer trials, consumer perception, etc. of the chemical composition and / or the components of the chemical composition. Information on chemical compositions (e.g., identity, values of properties, etc.) can be identified based on experiments, simulations, mathematical calculations, analysis, clinical / consumer trials, and / or assumptions about the property being modeled. For example, the actual (e.g., actually measured) values of the properties of a chemical composition can be identified and input into the model.

[0154] A training set (e.g., the identity of chemical compositions and the associated values of the properties of the chemical compositions) can be used to train a machine learning model (e.g., the chemical property engine 630). As described herein, the machine learning model (e.g., the chemical property engine 630) can use the training set to execute selected machine learning rules or algorithms. Once trained, the model can be used to determine (e.g., predict) the identity and / or the values of the properties of chemical compositions with respect to the property of interest.

[0155] Figure 9A A block diagram showing example data for training the chemical property engine 630. The data 902 can be related to one or more chemical compositions (e.g., sample chemical compositions). The data 902 can be known and / or determined. For example, the data 902 can be known through experimental measurement data, mathematical calculations (e.g., via thermodynamic calculations) data, data received from a storage device (e.g., from a database, such as the chemical property database 624), data received from clinical trials, etc. The data 902 can include the values of one or more parameters. For example, the data 902 can include the identity of the chemical composition. The identity can include the name of the chemical composition, the components of the chemical composition, the chemical information values / properties of the components of the chemical composition, the values of the properties of the chemical composition, the values of the characteristics related to the properties of the chemical composition, the consumer perception of the chemical composition, etc. The data can be input into the chemical property engine 630, e.g., to train the model to predict one or more values of the chemical composition.

[0156] As Figure 9AAs shown, the data 902 may include one or more components 912 of one or more chemical compositions. The components may include a first component 912a, a second component 912b, etc. Example components are provided in Figure 1A , 1B and 2A, 2B. For example, the chemical composition may include water, glycerin, propylene glycol, and flavor components. In such examples, the data 902 may include data for water, glycerin, propylene glycol, and flavor components. Each component 912a, 912b, etc. may include the identity of the component and / or the chemical information value of the component. For example, the data 902 may include chemical information values 914a, 914b, etc. In an example chemical composition including glycerin, propylene glycol, and flavor components, each of glycerin, propylene glycol, and flavor will have a corresponding chemical information value within the data 902.

[0157] The data 902 may include values 904 of properties of the chemical composition. The values 904 of the properties may be affected by one or more components. For example, the values 904 of the properties may be affected by one or more components that interact with one or more other components of the chemical composition. The properties may be pH, fluoride stability, viscosity stability, abrasion, specific gravity, clinical / consumer outcomes and / or tests, user-related information, environmental characteristics, consumer perception of the chemical composition, etc. The data 902 may include values of properties, such as the value of the pH property. As described herein, the value of a property (e.g., the pH property) may be affected by one or more components of the chemical composition.

[0158] The data 902 may include values 906 of characteristics related to one or more properties of the chemical composition. For example, the values 904 of the properties may be related to clinical / consumer tests and / or outcome data, etc. The values 904 of the properties related to clinical trials and / or clinical outcome data may be the consumer's perceived preference for a product (e.g., perfume), the clinical whitening efficacy of toothpaste, the moisturizing ability of a skin cream, etc. The values 906 of the characteristics related to the properties may be formulation attributes (e.g., the oxidation potential of the chemical composition), time periods (e.g., the tooth whitening value at six weeks of use, at eight weeks of use), user-related data (e.g., the age of the consumer using the chemical composition, geographical data related to the consumer, the consumer's brushing habits, etc.), etc.

[0159] One or more values of data 902 can be input into the chemical property engine 630, e.g., to train the chemical property engine 630. The identity of a chemical composition, associated values of properties of the chemical composition (e.g., other properties), and / or features related to the properties can be input into the chemical property engine 630. For example, associated values of the components and properties of a chemical composition (e.g., a sample chemical composition) can be input into the chemical property engine 630. The chemical property engine 630 can provide an association between the components of the chemical composition and the values of the properties of the chemical composition. In another example, the components, associated values of the properties, and features related to the properties of a chemical composition (e.g., a sample chemical composition) can be input into the chemical property engine 630. The chemical property engine 630 can provide an association between the components of the chemical composition, the values of the properties of the chemical composition, and the features related to the properties of the chemical composition.

[0160] Figure 9B A block diagram showing example data 920 for using the chemical property engine 630 to determine information related to a chemical composition. For example, Figure 9B A block diagram showing example data 920 for determining a value 904 of a property and / or a value 906 of a feature related to the property via the chemical property engine 630. The data 920 can be related to one or more compositions (e.g., chemical compositions, e.g., the chemical composition under consideration). The data 920 can be known and / or determined. For example, the data 920 can be known and / or determined by receiving data from a memory (e.g., from a database, e.g., the chemical property database 624), experimental measurement data, mathematical calculation (e.g., via thermodynamic calculation) data, receiving data via a survey or clinical trial, etc.

[0161] The data 920 can include values of one or more parameters. The data 920 can include the identity of a chemical composition, e.g., the name of the chemical composition, the components 912 of the chemical composition, chemical information values / properties of the components of the chemical composition, values of the properties of the chemical composition, values of features related to the properties of the chemical composition, etc. The data 920 can be input into the chemical property engine 630, e.g., to determine one or more values 904 of the properties of the chemical composition and / or a value 906 of a feature related to the properties of the chemical composition from the chemical property engine 630 (e.g., the machine learning model of the chemical property engine 630).

[0162] As Figure 9BAs shown, the data 920 may include one or more components 912 of one or more chemical compositions. The components 912 may include a first component 912a, a second component 912b, and so on. For example, the chemical composition may include water, glycerin, propylene glycol, and flavor components. In such examples, the data 920 may include data on water, glycerin, propylene glycol, and flavor components. Each component 912a, 912b, etc. may include chemical information values for the component. For example, the data 902 may include chemical information values 914a, 914b, and so on. In an example chemical composition including glycerin, propylene glycol, and flavor components, each of glycerin, propylene glycol, and flavor will have a corresponding chemical information value within the data 920.

[0163] One or more values of the data 920 may be input into the chemical property engine 630, for example, to determine (e.g., determine from the chemical property engine 630) a value 904 of a property of the chemical composition and / or a value 906 of a characteristic related to the property of the chemical composition. For example, the components 912 of a chemical composition (e.g., a sample chemical composition) may be input into the chemical property engine 630. The chemical property engine 630 may run (e.g., process) one or more machine learning rules to determine a value 904 of a property of the chemical composition. The chemical property engine 630 may provide a value 904 of a property of the chemical composition after determining the value.

[0164] In another example, the components 912 of a chemical composition (e.g., a sample chemical composition) may be input into the chemical property engine 630, and one or more characteristics related to one or more properties of the chemical composition may be input into the chemical property engine 630. The chemical property engine 630 may run (e.g., process) one or more machine learning rules to determine a value 904 of a property of the chemical composition. The value of the property may be associated with the characteristic (e.g., the value of the clinical whitening efficacy may be associated with the characteristic that the clinical participants are below a predetermined age). The chemical property engine 630 may provide a value 904 of a property of the chemical composition after determining the value.

[0165] The chemical property engine 630 (e.g., the model of the chemical property engine 630) can be configured to predict the value of the property of a chemical composition, for example, based on the identity of the components of the received chemical composition and / or characteristics related to the value of the property of the chemical composition, etc. In one example, the value of the property of a chemical composition can be affected by the components of the chemical composition (e.g., can be affected by the interaction of one or more components of the chemical composition) and / or by the value of the characteristics related to the property of the chemical composition. When information related to the chemical composition is supplied to the trained model, the output can include predictions regarding the value of the property of the chemical composition, characteristics related to the property, fitting parameters associated with the chemical composition, the identity of the chemical composition, etc. The property can be related to the pH of the chemical composition, the viscosity stability of the chemical composition, the abrasion of the chemical composition, the specific gravity of the chemical composition, clinical / consumer trials and / or results, the consumer perception of the chemical composition, etc. The characteristics related to the property can involve user-related values, environmental factors, etc. For example, the prediction can take the form of a value from a continuous value range or a value from discrete values.

[0166] Figure 9C A block diagram showing example data 930 for determining the identity of a chemical composition via the chemical property engine 630. The data 930 can be related to one or more chemical compositions (e.g., the chemical composition under consideration). The data 930 can be known. For example, as described herein, the data 930 can be known data such as experimentally measured data, data from mathematical calculations (e.g., via thermodynamic calculations), data received via clinical / consumer trials, data received from a storage device (e.g., from a database, such as the chemical property database 624), etc. As Figure 9C shown, the data 930 can include the value 904 of the property of the chemical composition, the value 906 of the characteristics related to the property of the chemical composition, etc. The data 930 can be input into the chemical property engine 630, for example, to determine information about the chemical composition (e.g., associated information). For example, the data 930 (e.g., the value 904) can be input into the chemical property engine 630 to determine the components 912 of the chemical composition according to the model, and the components are determined (e.g., predicted) to be related to the value 904 of the property input into the chemical property engine 630.

[0167] As described herein, the data 930 can include values 904 of properties, values 906 of characteristics related to the properties, and the like. The values 904 of the properties and / or the values 906 of the characteristics related to the properties can be input into the chemical property engine 630, for example, to predict (e.g., determine) the name of a chemical composition, one or more components 912 of the chemical composition, chemical information values 914a, 914b, ..., 914n of the chemical composition, and the like. The components can include a first component 912a, a second component 912b, and the like. For example, the chemical composition can include water, glycerin, propylene glycol, and flavor components. The chemical information values can be associated with (e.g., each) component 912a, 912b, and the like. For example, the component 912a can include the chemical information value 914a.

[0168] For example, the values 904 of the properties of the chemical composition and / or the values 906 of the characteristics related to the properties can be input into the chemical property engine 630. Based on the values 904 of the properties of the chemical composition and / or the values 906 of the characteristics related to the properties, the chemical property engine 630 (e.g., the model of the chemical property engine 630) can be configured to predict the identity (e.g., name, components, chemical information values, etc.) of the chemical composition forming a personal care product. When information related to the chemical composition is supplied to the chemical property engine 630, the output can include a determination (e.g., prediction) of the identity (e.g., name, chemical information values, etc.) of the chemical composition forming the personal care product, the fitting parameters associated with the chemical composition, the values of the properties of the chemical composition (e.g., another value), and the characteristics related to the properties, and the like. The chemical property engine 630 can provide the name, components, chemical information values, etc. of the chemical composition to the user, for example, via the user device 502.

[0169] Figure 10A - 10C An example graphical user interface (GUI) for training the chemical property modeling device 602 (e.g., the chemical property engine 630 within the chemical property modeling device 602) is shown. The GUI can be displayed on one or more devices. For example, the GUI can be displayed on a training device, such as the training device 650, the user device, and the like.

[0170] As Figure 10AAs shown, the GUI can request information from the user. For example, the GUI can request information from the user via prompt request 1010. The prompt request 1010 can ask the user what data the user wants to use to train the chemical property engine 630 (e.g., the model of the chemical property engine 630). The data used to train the model can be referred to as sample data. The data can include the identity of the chemical composition forming the personal care product (e.g., name, ingredients, chemical information values of the ingredients), the values of the properties of the personal care product, the values of the characteristics related to the properties, etc. The GUI can provide an input mechanism 1012 for the user to provide a response to the prompt request 1010. For example, the GUI can have a text box for receiving text from the user, radio buttons for selection, etc. As Figure 10A shown, a checkbox 1012 can be provided. In the instance where a text box is provided, the user can check one or more data in the input mechanism 1012 for training the chemical property engine 630.

[0171] After the user selects the data expected to be input into the chemical property engine 630 (e.g., for training the chemical property engine 630), the user can input such data. The user can input the data manually (e.g., by manually typing or speaking the data). The user can input a single piece of data, or the user can input multiple pieces of data. For example, the user can input the identity of the chemical composition (e.g., ingredients), the properties of the chemical composition, and / or the characteristics related to the properties. As Figure 10B shown, the GUI can provide an indication to the user to select the data to be input into the chemical property engine 630. The GUI can display the data to be input into the chemical property engine 630. For example, the GUI can display the data to be input into the chemical property engine 630 based on the input provided on Figure 10A the input mechanism 1012.

[0172] In one instance, the user may expect to input the ingredients 1016a of the chemical composition forming the product (e.g., personal care product, food, drug, etc.), the values 1016b of the properties of the chemical composition, and / or the values 10616c of the characteristics related to the properties. As Figure 10B shown, the user can select a file to provide ingredient information (via browsing 1017a), property value information (via browsing 1017b), and / or value information related to the properties (via browsing 1017c). Although Figure 10B browse buttons for inputting data are shown, those skilled in the art will understand that there are other methods for selecting data and inputting data into the chemical property engine 630, such as via a database (e.g., a database located on a server such as a cloud server), via one or more hard disk drives, via an external device (e.g., the user device 502), etc.

[0173] A user can input data into a chemical property engine 630 for one or more chemical compositions. For example, the user can train the chemical property engine 630 with data related to dozens, hundreds, thousands, etc. of chemical compositions. The user can train the chemical property engine 630 with the same data for one or more chemical compositions. For example, the user can train the chemical property engine 630 with the ingredients and property values of dozens of chemical compositions.

[0174] The user can train the chemical property engine 630 with different data (e.g., different types of data) for one or more chemical compositions. For example, the user can use the ingredients, property values, and / or values of features related to property values of certain chemical compositions; use chemical information values, property values, and / or values of features related to properties of certain chemical compositions; use chemical composition names, property values, and / or values of features related to property values of certain chemical compositions, etc. to train the chemical property engine 630.

[0175] The user can train the chemical property engine 630 with property values that include pH, fluorine stability, viscosity stability, abrasion, specific gravity, clinical / consumer trials and results, user-related data, consumer perception, etc. If the user desires to input additional data, the training device 650 (e.g., the GUI of the training device) can make a request. For example, as Figure 10C shown, the GUI can provide an additional data prompt 1018 to ask the user whether the user desires to input any additional data into the chemical property engine 630 (e.g., the model of the chemical property engine 630). If the user desires to further train the chemical property engine 630, the user may desire to input additional data into the chemical property engine 630. If the user desires to input additional data into the chemical property engine 630, the user can select the yes prompt in region 1020, otherwise the user can select the no prompt in region 1020. If the user selects the yes prompt in region 1020, the GUI shown in Figure 10B and described herein can be provided to the user. If the user selects the no prompt in region 1020, the user can exit the GUI.

[0176] Figure 11A - 11D An example graphical user interface (GUI) for determining (e.g., predicting) data from a chemical property modeling device 602 (e.g., the chemical property engine 630 within the chemical property modeling device 602) is shown. The GUI can be displayed on one or more devices. For example, the GUI can be displayed on a user device, such as user device 502.

[0177] As Figure 11AAs shown, the GUI can request information from the user via, for example, a prompt request 1110. The prompt request 1110 can ask the user which data the user wants the model to determine (e.g., predict). The GUI can provide an input mechanism 1112 for the user to provide a response to the prompt request 1110. For example, the GUI can have a text box for receiving text from the user, radio buttons for selection, etc. As Figure 11A shown, check boxes 1112 can be provided. The user can check one or more data in the input mechanism 1112 such that the chemical property engine 630 can determine one or more data related to the chemical composition. The input mechanism can allow selection of additional information, including sub-categories of information for determination. The sub-categories of information can include values of characteristics related to the properties of the chemical composition. The input mechanism 1112 can allow the user to define the values of the properties to be determined as pH, fluorine stability, viscosity stability, abrasion, specific gravity, clinical trials and / or results, consumer perception, etc.

[0178] After the user selects the data that the user expects the chemical property engine 630 to determine, the user can input data associated with the expected data, as Figure 11B shown. For example, the prompt 1116 indicates that the user expects to determine the value of the property of the chemical composition (based on Figure 11A the user input 1112 in). As Figure 11B shown, the GUI can provide an input 1118 that allows the user to select the data that the user expects to input into the chemical property engine 630, for example, to determine the value of the property of the chemical composition. Examples of the data to be input into the chemical property engine 630 include the identity of the chemical composition (e.g., name, ingredients, chemical information values of the ingredients) forming the product (e.g., personal care product), the value of the property of the personal care product, etc. Additional data, such as one or more values of characteristics related to the property, can be input into the chemical property engine 630 to determine one or more values of the property of the product.

[0179] After the user selects the data (1112) that the user expects to determine and the data (1118) that the user wants to use to determine the value of the personal care product, the user can provide the associated data. Figure 11C An example GUI is shown where the user can input data at 1122. The prompt 1120 indicates that the user has selected to input the ingredients of the chemical composition (to determine the value of the property of the chemical composition), however such indication is for illustrative purposes only and the user can provide other types of data to determine information related to the chemical composition.

[0180] The user can input data manually (e.g., by manually typing or speaking the data). For example, the user can manually input the ingredients of the chemical composition, as Figure 11CAs shown. A user can input a single piece of data, or a user can input multiple pieces of data. For example, as Figure 11C shown, the GUI can provide an indication to the user to select the data to be input into the chemical property engine 630. The user can select a file to provide composition information (via the browse button 1122). Although Figure 11C the browse button 1122 for inputting data is shown, those skilled in the art will understand that there are other methods for selecting data and / or inputting data into the chemical property engine 630, such as via a database (e.g., a database located in the cloud), via an external hard drive, via an external device (e.g., the user device 502), etc.

[0181] The GUI can provide determined (e.g., predicted) data. For example, the GUI can provide the value of a parameter, as Figure 11D shown. The value of the parameter can be related to the chemical composition forming the personal care product. The hint 1130 can display the associated data provided by the user. For example, the hint 1130 can display that the determined data is based on the composition information (e.g., the composition information provided by the user). The hint 1130 can indicate which data has been determined. For example, the hint 1130 indicates that the value of the property of the personal care product has been determined. The output 1132 provides the determined value. As Figure 11D shown, the determined value can be 1.7. In an example, the GUI can provide further information about the information, such as the property being pH, fluoride stability, viscosity stability, abrasion, specific gravity, and / or consumer perception.

[0182] Figure 12 is an example process 1200 for determining (e.g., predicting) the value of a chemical composition. The value can be the identity of the chemical composition, such as the name of the chemical composition, the components of the chemical composition, the chemical information value of the components of the chemical composition, the value of the property of the chemical composition, etc.

[0183] At 1202, the identity of the chemical composition (e.g., the sample chemical composition) can be received. The identity can be received from the database described herein or another storage device. As described above, the identity of the chemical composition can be the name of the chemical composition, the components of the chemical composition, the chemical information value of the components of the chemical composition, etc.

[0184] At 1204, the value of the parameter of the chemical composition (e.g., the sample chemical composition) can be received. The value of the property may be affected by one or more components of the chemical composition. For example, the property can be the pH of the chemical composition, and the value of the property can be the value of the pH of the chemical composition.

[0185] As described herein, the identity and / or values of parameters of a chemical composition (e.g., a sample chemical composition) can be used to train a machine learning model. For example, at 1206, values of properties of a chemical composition (e.g., a sample chemical composition) can be input into the machine learning model to train the machine learning model. The identity of the chemical composition can be input into the machine learning model to train the machine learning model. The identity of the chemical composition can be one or more of the name of the chemical composition, the components of the chemical composition, the chemical information values of the components of the chemical composition, etc. The machine learning model can correlate the values of the properties of the chemical composition with the identity of the chemical composition.

[0186] After training the machine learning model, the machine learning model can determine one or more values of a chemical composition. The machine learning model can determine one or more values of a chemical composition in response to receiving a piece of associated data. For example, the machine learning model can determine the value of a property of a chemical composition based on the identity of the chemical composition, such as the components of the chemical composition or the name of the chemical composition. The properties of the chemical composition can be the pH value of the chemical composition, the fluoride stability value of the chemical composition, the viscosity value of the chemical composition, the abrasion value of the chemical composition, the specific gravity value of the chemical composition, the consumer perception value of the chemical composition, etc.

[0187] For example, at 1208, the machine learning model can receive one or more values of a chemical composition (e.g., the chemical composition under consideration). As described herein, the chemical composition under consideration can be a chemical composition for which one or more values are unknown and it is desired to know them. For example, the identity of the chemical composition under consideration can be known, the components of the chemical composition under consideration can be known, and / or the chemical information values of the chemical composition under consideration can be known. The values of the properties of the chemical composition under consideration can be unknown.

[0188] Figure 13 Is an example process 1300 for determining (e.g., predicting) the value of a chemical composition based on the identity of the chemical composition and / or characteristics related to the properties.

[0189] At 1302, the identity of a chemical composition (e.g., a sample chemical composition) can be received. The identity can be received from the database described herein or another storage device. As described above, the identity of the chemical composition can be the name of the chemical composition, the components of the chemical composition, the chemical information values of the components of the chemical composition, etc.

[0190] At 1304, the value of a parameter of a chemical composition (e.g., a sample chemical composition) can be received. The value of the property can be affected by one or more components of the chemical composition. For example, the property can be gingivitis reduction, whitening efficacy, consumer perceived preference for a perfume, etc. The value of the property can be a value identified via measurement, etc. in a clinical / consumer trial.

[0191] At 1305, values of characteristics related to values of a chemical composition can be received. Characteristics related to values of properties can include, for example, the time period for conducting a clinical trial for reducing gingivitis, the age of a person for determining clinical whitening efficacy, demographic data of a user providing consumer perceived preference for a perfume, and the like. Although these examples describe characteristics determined during a clinical trial, such characteristics of properties can be determined via clinical and / or non-clinical methods, such as via experiments, measurements, and the like.

[0192] At 1306, values of properties of a chemical composition (e.g., a sample chemical composition) and values of characteristics related to the properties can be input into a machine learning model to train the machine learning model. The identity of the chemical composition can be input into the machine learning model to train the machine learning model. The machine learning model can associate values of one or more properties of the chemical composition, values of one or more characteristics related to the properties, and the identity of one or more chemical compositions.

[0193] After training the machine learning model, the machine learning model can determine one or more values of properties of the chemical composition and / or one or more values of characteristics related to the properties. The machine learning model can determine one or more values of properties of the chemical composition in response to receiving one or more associated data. For example, the machine learning model can determine the value of a property of the chemical composition based on the identity of the chemical composition and / or characteristics related to the property. In an example, the property of the chemical composition can be reduction of gingivitis, whitening efficacy, consumer perceived preference for a perfume, and the like. In other examples, the property of the chemical composition can be the pH value of the chemical composition, the fluoride stability value of the chemical composition, the viscosity value of the chemical composition, the abrasion value of the chemical composition, the specific gravity value of the chemical composition, clinical / consumer trials, the consumer perceived value of the chemical composition, and the like.

[0194] For example, at 1308, the machine learning model can receive one or more values of properties of a chemical composition (e.g., the chemical composition under consideration) and / or one or more values of characteristics related to the properties of the chemical composition. As described herein, the chemical composition under consideration can be a chemical composition for which one or more values are unknown and it is desired to know. For example, the identity of the chemical composition under consideration can be known, the ingredients of the chemical composition under consideration can be known, the chemical information value of the chemical composition under consideration can be known, the value of the characteristic related to the value of the property can be known, and the like. The value of the property of the chemical composition under consideration can be unknown.

[0195] Known values (e.g., the identity of the chemical composition under consideration, the components of the chemical composition under consideration, the chemical information value of the chemical composition under consideration, etc.) can be input into a machine learning model. Values of features related to properties (e.g., time period, user-related information, etc.) can be input into the machine learning model. Based on the known values and / or features input into the machine learning model, the machine learning model can determine the value of the property of the chemical composition under consideration. The value of the chemical composition under consideration can be displayed to the user or otherwise provided.

[0196] In an example, the user can determine whether the value of the property corresponds to the expected value of the property. For example, it may be desirable (e.g., required) for a personal care product to have a defined value for a property of the personal care product. The value may be related to a pH value or one or more other properties described herein. If the machine learning model determines that the chemical composition has a property value that matches the expected value of the property, the user can perform an action, such as producing a personal care product having the components associated with the determined value. The value of the feature related to the expected value of the property can be modified, e.g., to make the value of the property match the expected property. For example, the time period can be adjusted such that (e.g., until) the value of the property of the chemical composition matches the expected value. The user can perform an action, such as by performing a measurement of the property value, performing a mathematical calculation of the value, to confirm that the result provided by the machine learning model is accurate. The user can confirm that the result provided by the machine learning model is accurate before producing a personal care product having the components associated with the determined value.

[0197] The systems described herein can be implemented using any available computer systems and adaptations contemplated for known and later-developed computing platforms and hardware. Additionally, the methods described herein can be performed by a software application configured to execute on a computer system, which can range from a single-user workstation, a client-server network, a large distributed system employing peer-to-peer technology, or a cluster grid system. In one example, a high-speed computing cluster can be used. The computer systems for practicing the methods described herein can be geographically dispersed across local or national boundaries using a data communication network such as the Internet. Additionally, well-known data storage and transmission techniques can be used to transmit predictions generated at one location to other locations and the predictions can be experimentally verified at other locations.

[0198] Although the invention has been described with respect to specific examples, including the presently preferred mode of carrying out the invention, those skilled in the art will appreciate that there are many variations and permutations of the systems and techniques described above. It should be understood that other embodiments can be utilized and structural and functional modifications can be made without departing from the scope of the invention. Accordingly, the spirit and scope of the invention should be broadly construed as set forth in the appended claims.

Claims

1. A computer-implemented method for determining a value of a property of a chemical composition under consideration, the chemical composition under consideration forming a toothpaste, the method comprising: (a) receiving an identity of a sample chemical composition, the sample chemical composition comprising components, each of the components being associated with a value of a certain chemical information property among the chemical information properties of the sample chemical composition; (b) receiving a value of a property of the sample chemical composition, the property of the sample chemical composition being affected by an interaction of at least two of the components of the sample chemical composition, wherein the value of the property of the sample chemical composition is identified via at least one of an experimental measurement of the sample chemical composition or a thermodynamic calculation of the sample chemical composition; (c) inputting the value of the property of the sample chemical composition and the values of the chemical information properties of the components of the sample chemical composition into a machine learning model; repeating steps (a)-(c) for a plurality of sample chemical compositions, wherein the machine learning model comprises a supervised learning method; and (d) via the model, determining the value of the property of the chemical composition under consideration based on the values of the chemical information properties of the components of the chemical composition under consideration, the value of the property of the chemical composition under consideration being determined via the rules of the machine learning model; wherein the property of the chemical composition under consideration is the same as the property of the sample chemical composition, and wherein the property of the chemical composition under consideration is affected by an interaction of at least two of the components of the chemical composition under consideration; and wherein for each of the sample chemical composition and the chemical composition under consideration, the value of the property is related to at least one of pH, rheology, abrasiveness, chemical degradation, phase change, turbidity, component solubility, volatile loss, or consumer perception.

2. The method according to claim 1, wherein the identity comprises the identities of the components of the sample chemical composition.

3. The method according to claim 1, wherein the supervised learning method includes at least one of decision tree rules, random forest rules, support vector machine rules, Naive Bayes Bayes classification rules, or logistic regression rules.

4. The method according to claim 1, wherein the value of the property of the chemical composition under consideration is related to the physicochemical properties of the chemical composition under consideration, the physicochemical properties being related to the physical properties or chemical properties of the chemical composition under consideration.

5. The method according to claim 2, wherein the identities of the components of the sample chemical composition and the values of the chemical information properties of the components of the sample chemical composition are stored in a database.

6. The method according to claim 1, wherein for each of the sample chemical composition and the chemical composition under consideration, the chemical information property is related to at least one of a qualitative category, a qualitative sensory attribute, a molecular formula, an acid dissociation constant, a solubility product, a structural topology, a functional group count, a chemical fragment count, hydrophobicity, a partition coefficient, a steric parameter, an association constant, or a hydrophilic-lipophilic balance (HLB).

7. The method according to claim 6, wherein the qualitative category comprises at least one of a component function or a component classification.

8. The method according to claim 6 or 7, wherein the qualitative sensory attribute comprises at least one of an odor, a taste, or a tactile attribute.

Images