Systems and methods for optimizing manufacturing of formulated products

Abstract

Systems and methods for product development and optimized manufacturing of formulated products are provided. Machine learning can be used to optimize performance of controlled physico-chemical parameters in complex multi-component formulations and then a multi-parameter optimization can be carried out to determine and get predictability of overall performance of the products. Machine-leaming-based predictive models for multi-parameter performance optimization can be used, and the models can be developed and / or trained with a robust training set of experimental data for the physico-chemical parameters and / or sensory and functional parameters.

Description

[0001] DESCRIPTION

[0002] SYSTEMS AND METHODS FOR OPTIMIZING MANUFACTURING OF FORMULATED PRODUCTS

[0003] CROSS-REFERENCE TO RELATED APPLICATION

[0004] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 587,762, filed October 4, 2023, the disclosure of which is hereby incorporated by reference in its entirety, including all figures, tables, and drawings.

[0005] BACKGROUND

[0006] Many products across several industrial sectors are formulated products, including those in the cosmetics, consumer goods, home care, pharmaceuticals, biopharmaceuticals, foods, and agro-products industries. These formulated products include several ingredients combined together in specific concentrations. It is difficult and time consuming to attempt to optimize performance of such formulated products within cost constraints.

[0007] BRIEF SUMMARY

[0008] Embodiments of the subject invention provide novel and advantageous systems and methods for product development and optimized manufacturing of formulated products. Machine learning can be used to optimize performance of controlled physico-chemical parameters in complex multi-component formulations and then a multi-parameter optimization can be carried out to determine and get predictability of overall performance of the products. Embodiments of the subject invention can use machine-leaming-based predictive models for multi -parameter performance optimization, and the models can be developed and / or trained with a robust training set of experimental data for the physico-chemical parameters and / or sensory and functional parameters. Validation and / or further optimization (e.g., for additional constraints, such as cost and / or biodegradability) can also be performed.

[0009] In an embodiment, a system for optimizing manufacturing of a formulated product can comprise a processor and a machine-readable medium in operable communication with the processor and having instructions stored thereon that, when executed by the processor, perform the following steps: receiving a list of ingredients for the formulated product; receiving at least one physico-chemical parameter category to be utilized in the optimization; and using a trained machine-leaming-based predictive model on the at least one physico-chemical parameter category while controlling for at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category. The at least one control category can comprise, for example, at least one of cost, biodegradability, and regulatory compliance (e.g., based on geographical location) of at least one ingredient of the list of ingredients. The at least one physico-chemical parameter category can comprise, for example, at least one of viscosity, viscosity variation with shear rate / shear stress, a viscoelastic parameter, viscoelastic parameter variation with frequency, creep compliance, thixotropic index, yield stress, particle size, particle size distribution, zeta potential, electrophoretic mobility, emulsion droplet size, structure (e.g., primary, secondary, and / or tertiary structure) of proteins and / or peptides, surface tension and / or interfacial rheology at an air / water interface, interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface, and deposition on a solid substrate. The instructions when executed can further perform the following step: before using the trained machine-leaming-based predictive model, training the machine-leaming-based predictive model using experimental data for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category. The instructions when executed can further perform the following step: before using the trained machine- leaming-based predictive model, receiving at least one sensory and functional parameter category to be utilized in the optimization. The using of the trained machine-leaming-based predictive model can further comprise using the trained machine-leaming-based predictive model on the at least one sensory and functional parameter category while controlling for the at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each sensory and functional parameter category of the at least one sensory and functional parameter category. The at least one sensory and functional parameter category can comprise, for example, at least one of sensory feel, stability of oil-in-water emulsion and / or water-in-oil emulsion over a period of time (e.g., six months or at least six months), stability of a solid particle containing suspension over the period of time, stability of complex emulsions and / or other multicomponent formulations over a period of time (e.g., six months or at least six months), transport of actives and / or drug molecules, mouthfeel, aerosolization and / or sprayability, and film formation on a solid substrate. The formulated product can be, for example, a polymer, a biopolymer, a surfactant, a biosurfactant, an emulsifier, an emollient, a humectant, a film former, a penetration enhancer, a peptide, a protein, a wetting agent, a rheology modifier, a plasticizer, and / or an oil. The system can further comprise: a display; and a user interface on the display configured to receive input from a user. The input from the user can comprise the list of ingredients for the formulated product, the at least one physico-chemical parameter category, the formulated product, the at least one control category, and / or the at least one sensory and functional parameter category.

[0010] In another embodiment, a method for optimizing manufacturing of a formulated product can comprise: receiving (e.g., by a processor) a list of ingredients for the formulated product; receiving (e.g., by the processor) at least one physico-chemical parameter category to be utilized in the optimization; and using (e.g., by the processor) a trained machine-leaming-based predictive model on the at least one physico-chemical parameter category while controlling for at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category. The at least one control category can comprise, for example, at least one of cost, biodegradability, and regulatory compliance (e.g., based on geographical location) of at least one ingredient of the list of ingredients. The at least one physico-chemical parameter category can comprise, for example, at least one of viscosity, viscosity variation with shear rate / shear stress, a viscoelastic parameter, viscoelastic parameter variation with frequency, creep compliance, thixotropic index, yield stress, particle size, particle size distribution, zeta potential, electrophoretic mobility, emulsion droplet size, structure (e.g., primary, secondary, and / or tertiary structure) of proteins and / or peptides, surface tension and / or interfacial rheology at an air / water interface, interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface, and deposition on a solid substrate. The method can further comprise, before using the trained machine-leaming-based predictive model, training (e.g., by the processor) the machine-leaming-based predictive model using experimental data for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category. The method can further comprise, before using the trained machine- leaming-based predictive model, receiving (e.g., by the processor) at least one sensory and functional parameter category to be utilized in the optimization. The using of the trained machine-leaming-based predictive model can further comprise using the trained machine- leaming-based predictive model on the at least one sensory and functional parameter category while controlling for the at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each sensory and functional parameter category of the at least one sensory and functional parameter category. The at least one sensory and functional parameter category can comprise, for example, at least one of sensory feel, stability of oil-in- water emulsion and / or water-in-oil emulsion over a period of time (e.g., six months or at least six months), stability of a solid particle containing suspension over the period of time, stability of complex emulsions and / or other multicomponent formulations over a period of time (e.g., six months or at least six months), transport of actives and / or drug molecules, mouthfeel, aerosolization and / or sprayability, and film formation on a solid substrate. The formulated product can be, for example, a polymer, a biopolymer, a surfactant, a biosurfactant, an emulsifier, an emollient, a humectant, a film former, a penetration enhancer, a peptide, a protein, a wetting agent, a rheology modifier, a plasticizer, and / or an oil. The list of ingredients for the formulated product, the at least one physico-chemical parameter category, the formulated product, the at least one control category, and / or the at least one sensory and functional parameter category can be received as input from a user via a user interface (e.g., displayed on a display).

[0011] BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 shows an overview of an integrated approach for product development and optimized manufacturing of formulated products, according to an embodiment of the subject invention.

[0013] Figure 2 shows a plot of surface tension versus concentration (in grams per milliliter (g / ml)). The (blue) curve with the higher surface tension value at 0.05 g / ml is for predicted; and the (red) curve with the lower surface tension value at 0.05 g / ml is for actual.

[0014] Figure 3 shows a plot of surface tension versus concentration (in g / ml). The (blue) curve with the lower surface tension value at 0.05 g / ml is for predicted; and the (red) curve with the higher surface tension value at 0.05 g / ml is for actual.

[0015] Figure 4 shows a plot of viscosity versus shear rate. The (blue) curve for predicted and the red curve for actual are so close to each other that they appear to be essentially the same curve.

[0016] Figure 5 shows a plot of viscosity versus shear rate. The (blue) curve with the higher viscosity value at a shear rate of 10 (i.e., le+1) is for predicted; and the (red) curve with the lower viscosity value at a shear rate of 10 (i.e., le+1) is for actual. Figure 6 shows a plot of viscosity (in Pascal-seconds (Pa-s)) versus shear rate (in s'1). Images of formulated products are shown below the plot.

[0017] Figure 7 shows a plot of shear viscosity (in Pa-s) versus shear rate (in s'1) for a binary surfactant mixture. The (blue) curve, which is for a predicted value, shows a shear viscosity that remains fairly constant across all shear rates.

[0018] Figure 8 shows a plot of shear viscosity (in Pa-s) versus shear rate (in s'1) for a binary surfactant mixture. The (blue) curve, which is for a predicted value, starts with a higher shear viscosity at lower shear rates.

[0019] DETAILED DESCRIPTION

[0020] Embodiments of the subject invention provide novel and advantageous systems and methods for product development and optimized manufacturing of formulated products. Machine learning can be used to optimize performance of controlled physico-chemical parameters in complex multi-component formulations and then a multi-parameter optimization can be carried out to determine and get predictability of overall performance of the products. Embodiments of the subject invention can use machine-leaming-based predictive models for multi-parameter performance optimization, and the models can be developed and / or trained with a robust training set of experimental data for the physico-chemical parameters and / or sensory and functional parameters. Validation and / or further optimization (e.g., for additional constraints, such as cost and / or biodegradability) can also be performed.

[0021] Products in many industries formulated products that include several ingredients combined together in specific concentrations. Optimizing the mixtures can depend upon optimizing certain physico-chemical and other performance and sensory parameters. This can be a very time consuming and labor intensive process. Existing methods for such optimization are not efficient and can miss performance “hot spots”. More efficient methods for optimization are needed in the art, particularly with the desire for sustainability in industry and the increase in ingredient options. Embodiments of the subject invention provide machine-leaming-based predictive models for multi-parameter performance optimization that are much more efficient than the related art and that can allow for the most optimized mixture ingredient selection and concentrations in formulated products.

[0022] Instead of using a black box or brute force method via very large data sets, embodiments of the subject invention can utilize a more knowledge-based approach in optimizing performance by controlling physico-chemical parameters and then carrying out a multiparameter optimization of the physico-chemical parameters with respect to constraints (e.g., cost and / or biodegradability). The physico-chemical parameters can include but are not limited to: viscosity; viscosity variation with shear rate / shear stress; viscoelastic parameters (e.g.; elastic modulus (G’) and / or viscous modulus (G”)); viscoelastic parameter variation with frequency; creep compliance; thixotropic index; yield stress; surface tension and / or interfacial rheology at an air / water interface; interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface; and / or deposition of ingredients on solid substrates. Instead of optimizing using an entirely experimental approach (e.g., via design of experiments (DOE)) and / or high throughput automation platforms, embodiments of the subject invention can perform the optimization much faster using machine-leaming-based predictive models while also allowing for identification of performance “hot spots”.

[0023] Figure 1 shows an overview of an integrated approach for product development and optimized manufacturing of formulated products, according to an embodiment of the subject invention. Referring to Figure 1, artificial intelligence and / or machine learning can be used to optimize formulation automation of materials (e.g., novel and / or sustainable materials and / or chemistries). The performance (e.g., stability, sensory, texture, cleansing efficacy, foam quality, film formation, and / or deposition) can be considered, as can constraints (e.g., cost and / or biodegradability). Physio-chemical insights can be used, such as based on rheology, stability, and / or interface / surface activity. Figure 6 shows a plot of viscosity (in Pascal-seconds (Pa-s)) versus shear rate (in s-1). Images of formulated products are shown below the plot. Viscosity flow curves, such as those in Figure 6, are important for stability and multiple sensory performance aspects of formulated products. Intensive experimental data collection is required to get actual values for such curves. Embodiments of the subject invention can eliminate the need for such data collection by predicting data for these curves, and for other parameters (as discussed herein; see also Example 1).

[0024] Embodiments of the subject invention provide systems and methods for prediction and optimization of product performance, controlling physico-chemical parameters, for multicomponent mixtures. The physico-chemical parameters can include, for example, viscosity, viscosity variation with shear rate / shear stress, viscoelastic parameters (e.g., G’ and / or G”), viscoelastic parameter variation with frequency, creep compliance, thixotropic index, yield stress, particle size, particle size distribution, zeta potential, electrophoretic mobility, emulsion droplet size, structure (e.g., primary, secondary, and / or tertiary structure) of proteins and / or peptides, surface tension and / or interfacial rheology at an air / water interface, interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface, and / or deposition of ingredients on solid substrates. The product performance parameters that can be considered and / or utilized can include, for example: sensory feel of products (e.g., on skin and / or hair); stability of oil-in-water emulsions, water-in-oil emulsions, complex emulsions, suspensions, and / or other multicomponent formulations over a period of time (e.g., six months or at least six months); transport of actives and / or drug molecules (e.g., across skin and / or hair); mouthfeel of food products and / or beverages; aerosolization and / or sprayability; and / or film formation on solid substrates. Further optimization and / or ingredient selection can be performed, and this can be based on, for example, cost of ingredient(s), biodegradability of ingredient(s), and / or regulatory compliance of ingredient(s) (e.g., based on geographic region). Optimization of material selection and / or mixture concentration can be performed based on some or all of these factors. This can be done for many different material classes, including but not limited to: polymers; biopolymers; surfactants; biosurfactants; emulsifiers; emollients; humectants; film formers; penetration enhancers; peptides; proteins; wetting agents; rheology modifiers; plasticizers; and / or oils (natural oils and / or silicones).

[0025] In many embodiments, data (e.g., available data from another source or experimentally gathered data) can be used to train one or more predictive models (e.g., ensemble learning methods and / or deep learning predictive models). These techniques enable the prediction of properties across any combination of chemicals and chemical ratios. The values from the predictive models can be utilized by an optimization algorithm, which aids in the formulation process for complex multicomponent chemical mixtures. An algorithm can search for the optimal composition that minimizes surface tension while maximizing viscosity, all while keeping costs as low as possible. An intuitive user interface can enable users to effortlessly modify model parameters while simultaneously displaying visualizations of both the predicted results and optimal configurations. In some further embodiments, the results can be used to fabricate one or more formulated products based on the optimized mixture ingredient selection and concentrations.

[0026] Embodiments of the subject invention provide a focused technical solution to the focused technical problem of how to optimize ingredient selection and concentrations for formulated products. The solution is provided by machine-leaming-based predictive models for multi-parameter performance optimization, which can be developed and / or trained with a robust training set of experimental data for physico-chemical parameters and / or sensory and functional parameters. Embodiments of the subject invention can improve the computer system performing the optimization by performing an algorithm-based optimization more efficiently (which can free up memory and / or processor usage).

[0027] The methods and processes described herein can be embodied as code and / or data. The software code and data described herein can be stored on one or more machine-readable media (e.g., computer-readable media), which may include any device or medium that can store code and / or data for use by a computer system. When a computer system and / or processor reads and executes the code and / or data stored on a computer-readable medium, the computer system and / or processor performs the methods and processes embodied as data structures and code stored within the computer-readable storage medium.

[0028] It should be appreciated by those skilled in the art that computer-readable media include removable and non-removable structures / devices that can be used for storage of information, such as computer-readable instructions, data structures, program modules, and other data used by a computing system / environment. A computer-readable medium includes, but is not limited to, volatile memory such as random access memories (RAM, DRAM, SRAM); and nonvolatile memory such as flash memory, various read-only-memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM), and magnetic and optical storage devices (hard drives, magnetic tape, CDs, DVDs); network devices; or other media now known or later developed that are capable of storing computer- readable information / data. Computer-readable media should not be construed or interpreted to include any propagating signals. A computer-readable medium of embodiments of the subject invention can be, for example, a compact disc (CD), digital video disc (DVD), flash memory device, volatile memory, or a hard disk drive (HDD), such as an external HDD or the HDD of a computing device, though embodiments are not limited thereto. A computing device can be, for example, a laptop computer, desktop computer, server, cell phone, or tablet, though embodiments are not limited thereto.

[0029] When ranges are used herein, combinations and subcombinations of ranges (including any value or subrange contained therein) are intended to be explicitly included. When the term “about” is used herein, in conjunction with a numerical value, it is understood that the value can be in a range of 95% of the value to 105% of the value, i.e. the value can be + / - 5% of the stated value. For example, “about 1 kg” means from 0.95 kg to 1.05 kg.

[0030] EXAMPLE 1

[0031] A machine-learning -based predictive model, according to an embodiment of the subject invention, was used to predict the chemical properties of surfactant and polymer mixtures and other ingredients of formulated products. Experimentally gathered data on surface tension and viscosity was used to train an ensemble of predictive models using machine learning and deep learning techniques. These techniques enable the prediction of properties across any combination of chemicals and chemical ratios. The values from the predictive models were utilized by an optimization algorithm, which aids in the formulation process for complex multicomponent chemical mixtures. One of the algorithms can search for the optimal composition that minimizes surface tension while maximizing viscosity, all while keeping costs as low as possible. An intuitive user interface can enables users to effortlessly modify model parameters while simultaneously displaying visualizations of both the predicted results and optimal configurations. The actual surface tension and viscosity were measured for the formulated products, for comparison.

[0032] Figures 2 and 3 show results for the predicted surface tension compared to actual, measured surface tension. Figures 4 and 5 show results for the predicted surface tension compared to actual, measured viscosity. Figures 7 and 8 show results for shear viscosity for two different binary surfactant mixture ratios, respectively. Referring to Figures 2-5, 7, and 8, it can be seen that the values predicted by the model were extremely accurate, with only minimal differences compared to the actual values.

[0033] It should be understood that the examples and embodiments described herein are for illustrative purposes only and that various modifications or changes in light thereof will be suggested to persons skilled in the art and are to be included within the spirit and purview of this application.

[0034] All patents, patent applications, provisional applications, and publications referred to or cited herein (including in the “References” section, if present) are incorporated by reference in their entirety, including all figures and tables, to the extent they are not inconsistent with the explicit teachings of this specification. REFERENCES

[0035] [1] A.R Davies, S.Amin, A.Kane Happi 5-54, May 2021

[0036] [2] P.S Kang, J.S.Lim, C.Huy, Appl Sei. 6, 188, 2016

Claims

CLAIMSWhat is claimed is:

1. A system for optimizing manufacturing of a formulated product, the system comprising: a processor; and a machine-readable medium in operable communication with the processor and having instructions stored thereon that, when executed by the processor, perform the following steps: receiving a list of ingredients for the formulated product; receiving at least one physico-chemical parameter category to be utilized in the optimization; and using a trained machine-leaming-based predictive model on the at least one physicochemical parameter category while controlling for at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category, the at least one control category comprising at least one of cost and biodegradability, and the at least one physico-chemical parameter category comprising at least one of viscosity, viscosity variation with shear rate / shear stress, a viscoelastic parameter, viscoelastic parameter variation with frequency, creep compliance, thixotropic index, yield stress, particle size, particle size distribution, zeta potential, electrophoretic mobility, emulsion droplet size, primary / secondary / tertiary structure of proteins and / or peptides, surface tension and / or interfacial rheology at an air / water interface, interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface, and deposition on a solid substrate.

2. The system according to claim 1, the instructions when executed further performing the following step: before using the trained machine-learning-based predictive model, training the machine- leaming-based predictive model using experimental data for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category.

3. The system according to any of claims 1 -2, the instructions when executed further performing the following step: before using the trained machine-leaming-based predictive model, receiving at least one sensory and functional parameter category to be utilized in the optimization, the using of the trained machine-leaming-based predictive model further comprising using the trained machine-leaming-based predictive model on the at least one sensory and functional parameter category while controlling for the at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each sensory and functional parameter category of the at least one sensory and functional parameter category.

4. The system according to claim 3, the at least one sensory and functional parameter category comprising at least one of sensory feel, stability of oil-in-water emulsion and / or water-in-oil emulsion over a period of time, stability of a solid particle containing suspension over the period of time, stability of complex emulsions and / or other multicomponent formulations over the period of time, transport of actives and / or drug molecules, mouthfeel, aerosolization and / or sprayability, and film formation on a solid substrate.

5. The system according to claim 4, the period of time being at least six months.

6. The system according to any of claims 1-5, the at least one physico-chemical parameter category comprising viscosity.

7. The system according to any of claims 1-6, the at least one physico-chemical parameter category comprising surface tension.

8. The system according to any of claims 1-7, the at least one control category comprising both cost and biodegradability.

9. The system according to any of claims 1-8, the at least one control category comprising regulatory compliance of at least one ingredient of the list of ingredients.

10. The system according to any of claims 1-9, the formulated product being a polymer, a biopolymer, a surfactant, a biosurfactant, an emulsifier, an emollient, a humectant, a film former, a penetration enhancer, a peptide, a protein, a wetting agent, a rheology modifier, a plasticizer, and / or an oil.11 . The system according to any of claims 1-10, further comprising: a display; and a user interface on the display configured to receive input from a user, the input from the user comprising the list of ingredients for the formulated product and the at least one physicochemical parameter category.

12. A method for optimizing manufacturing of a formulated product, the method comprising: receiving a list of ingredients for the formulated product; receiving at least one physico-chemical parameter category to be utilized in the optimization; and using a trained machine-leaming-based predictive model on the at least one physicochemical parameter category while controlling for at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category, the at least one control category comprising at least one of cost and biodegradability, and the at least one physico-chemical parameter category comprising at least one of viscosity, viscosity variation with shear rate / shear stress, a viscoelastic parameter, viscoelastic parameter variation with frequency, creep compliance, thixotropic index, yield stress, particle size, particle size distribution, zeta potential, electrophoretic mobility, emulsion droplet size, primary / secondary / tertiary structure of proteins and / or peptides, surface tension and / or interfacial rheology at an air / water interface, interfacial tension and / or interfacial rheology at an oil / water interface and / or an oil / oil interface, and deposition on a solid substrate.

13. The method according to claim 12, further comprising: before using the trained machine-leaming-based predictive model, training the machine- leaming-based predictive model using experimental data for each ingredient of the list ofingredients for each physico-chemical parameter category of the at least one physico-chemical parameter category.

14. The method according to any of claims 12-13, further comprising: before using the trained machine-leaming-based predictive model, receiving at least one sensory and functional parameter category to be utilized in the optimization, the using of the trained machine-leaming-based predictive model further comprising using the trained machine-leaming-based predictive model on the at least one sensory and functional parameter category while controlling for the at least one control category to obtain an optimized value for each ingredient of the list of ingredients for each sensory and functional parameter category of the at least one sensory and functional parameter category.

15. The method according to claim 14, the at least one sensory and functional parameter category comprising at least one of sensory feel, stability of oil-in-water emulsion and / or water-in-oil emulsion over a period of time, stability of a solid particle containing suspension over the period of time, stability of complex emulsions and / or other multicomponent formulations over the period of time, transport of actives and / or drug molecules, mouthfeel, aerosolization and / or sprayability, and film formation on a solid substrate.

16. The method according to claim 15, the period of time being at least six months.

17. The method according to any of claims 12-16, the at least one physico-chemical parameter category comprising viscosity.

18. The method according to any of claims 12-17, the at least one physico-chemical parameter category comprising surface tension.

19. The method according to any of claims 12-18, the at least one control category comprising both cost and biodegradability.

20. The method according to any of claims 12-19, the at least one control category comprising regulatory compliance of at least one ingredient of the list of ingredients.

21. The method according to any of claims 12-20 the formulated product being a polymer, a biopolymer, a surfactant, a biosurfactant, an emulsifier, an emollient, a humectant, a film former, a penetration enhancer, a peptide, a protein, a wetting agent, a rheology modifier, a plasticizer, and / or an oil.

22. The method according to any of claims 12-21, the list of ingredients for the formulated product and the at least one physico-chemical parameter category being received as input from a user via a user interface displayed on a display.

Images