WO2025219997A1 - Digital organoleptic profiles and systems and methods which employ them - Google Patents

Abstract

In some exemplary embodiments of the invention, there is provided a system including: (a) at least one food service terminal presenting an invitation to submit an organoleptic user profile; (b) a communication module configured to receive the organoleptic user profile submitted in response to the invitation; and (c) an analysis module configured to compare the organoleptic user profile to a specific food item organoleptic profile stored in a database and generate a modified recipe for the specific food item based on the analysis.

Description

TITLE: DIGITAL ORGANOLEPTIC PROFILES AND SYSTEMS AND METHODS WHICH EMPLOY THEM

RELATED APPLICATIONS:

This PCT application claims priority under 35 U.S.C §119(e) from US provisional patent application 63/634,493 filed on April 16, 2024 by the same Applicant and entitled "Recommendation of Foods According to User Taste Preference Profiles and Objective Taste, Odor Values and Organoleptic sensations" which is fully incorporated herein by reference for all that it contains including the color content of the figures.

FIELD OF THE INVENTION

The invention is in the field of organoleptic evaluation.

BACKGROUND OF THE INVENTION

The full organoleptic experience of foods, beverages, and cosmetics includes what is known as flavor and is influenced by multiple factors.

Taste is one component of flavor. Taste is sensed by taste buds on the tongue. The sense of taste has traditionally been categorized according to five basic types: sweet, salty, sour, bitter, and umami (savory). More recently the literature has recognized kokumi and fattiness as tastes, although there do not appear to be specific taste receptors for these parameters. In addition, physical sensations such as visual appearance, sound, and mouthfeel contribute to the experience of eating.

Another component of flavor is odor or smell. Odor refers to the impression produced by signals transmitted by olfactory nerves, especially retronasal olfactory nerves, when eating or drinking.

Aroma refers to the overall impression obtained from tastes (gustation) and odor (olfaction) when eating or drinking.

In addition, trigeminal effects, which are experienced by nerves within the mouth, further contribute to the full flavor experience.

In summary, flavor refers to the combination of aroma (taste + odor) and trigeminal effects.

In contrast to sight and hearing, for which intensity of sensations are readily quantified, there is no standard metric for quantifying taste. Taking sweetness as an example, the prevalent approach for measuring sweetness relies on comparison of the sensation of sweetness to referent foods having known sweetness values. In one common type of study, different sugar solutions are prepared with fixed concentrations ("brix") of sucrose by weight, from 0% to 20%. Participants are then offered each of these solutions and learn to recognize the tastes of each of these solutions. The participants then associate the taste of a new food with one of the sample solutions. Although comparison to reference sugar solutions has been used for decades, it has various drawbacks. The main drawback is that the training process for learning the tastes of the solutions is impractical for the average person. A second drawback is that different people experience sweetness differently. As a result of this person- to-person variability evaluations based on comparisons to reference solutions do not lead to universally applicable values.

Recently, various attempts have been made to provide an objective scale for taste. One approach is presented in U.S. Patent Publication 2016/0171728, which introduces the VAL® scale. VAL® is an objective scale for taste based on concentrations of ingredients. For each type of taste, a given concentration of a prevalent tastant contributing to that taste is assigned a value of 1 Vai. Other ingredients that contribute to the same taste are assigned relative values of VAL. A cumulative VAL for each taste is then assigned to each food based on the concentrations of each ingredient, which takes into account synergies between ingredients that have the same impact. For example, in the context of sweetness, the ingredient that forms the baseline for the VAL® scale is sucrose. The scale assigns a VAL® of 1 to a sucrose solution having a concentration of 3.423 g/liter of water, at 20 °C and pH of 7.0. Other ingredients that contribute to sweetness are assigned relative VAL values for the same concentrations, based on their sweetness relative to sucrose. A similar analysis is performed for the other sensations of taste, including saltiness, sourness, bitterness, and umami.

Beyond the objective classification of tastes, a separate challenge relates to automated preparation of foods according to particular taste preferences. Proposals that exist to date are largely impractical. For example, U.S. Patent Publication 2022/0383433 proposes an automated determination of a user's "taste palate profile" in restaurant dishes. The user's taste palate profile is determined based on the user's history of ordering dishes from the restaurant's menu and the user's subsequent feedback regarding how much he or she liked those dishes. Each of the dishes has a "flavor profile," which may characterize the different aspects of taste which are present in the menu item or ingredient. Based on the user's taste palate profile, it is possible to recommend dishes having a flavor profile that would be expected to be pleasing to the user. This approach is highly impractical to implement. The user's taste palate profile is determined over a long period of time, based on the consumption of multiple dishes in the same restaurant. Until such time as the user has generated sufficient feedback on dishes in order to generate a taste palate profile, the system is unable to provide any recommendations.

SUMMARY OF THE INVENTION

A broad aspect of the invention relates standardization of organoleptic profiles. According to various exemplary embodiments of the invention the organoleptic profiles are for products and/or individual user preferences. For purposes of this specification and the accompanying claims, the term "product" indicates a food, beverage, or cosmetic.

One aspect of some embodiments of the invention relates to performance of matching between a product organoleptic profile and a user organoleptic preference profile. In some embodiments a single user has separate organoleptic preference profiles for different categories of products.

In some exemplary embodiments of the invention, a product organoleptic profile is generated by using an expanded version of the VAL scale. Specifically, a system assigns objective values on a scale for tastes, odors, and trigeminal effects of various ingredients in each product and/or for commercially prepared foods.

Alternatively or additionally, in some embodiments each user responds to a questionnaire that is specifically designed to analyze the user's taste and odor preferences in products (e.g. foods). In some embodiments the questionnaire is specific to a particular product. For example, a questionnaire for wine will be different than a questionnaire for ice cream. User responses to the questionnaires are translated into preferences for particular numerical values on the objective scale.

In some exemplary embodiments of the invention, a matching engine pairs user preferences determined by the questionnaire with particular product organoleptic profiles stored in a database, suggestions, and a recommendation engine predicts the likelihood that the user will like particular foods.

One exemplary advantage of this methodology is that since both the product profile and the user profile are based on objective values, the matches are reliable and transferable between different users. Another exemplary advantage of this methodology is that the user taste preference profiles are generated with digital questionnaires which are analyzed nearly instantaneously and without significant investment of time and effort.

According to another aspect of some embodiments of the invention, the VAL® scale is expanded. First, the VAL scale is expanded to quantify odor. The objective scale used for odors is based on the odor impact of each of the ingredients. Odor impact is derived from intrinsic physical and chemical properties of each ingredient that is an odorant. The commonly used odor detection threshold is highly subjective. In contrast, odor impact supplies a universally applicable metric for translating intrinsic properties of an odorant into user experiences. The VAL scale is further expanded to trigeminal effects and to certain physical aspects of the product

In some exemplary embodiments of the invention, determining a product organoleptic profile includes analyzing a chemical composition of the product, determining the concentration of specific compounds within the product having known sensory values, and, on a basis of the concentration of the specific compounds, assigning a sensory value. In another embodiment the sensory values are expressed as numerical values on a relative scale. In some embodiments, the method further comprises displaying a graphic illustration with each of the plurality of tastes in a food represented in a different size in accordance with its relative strength. According to various exemplary embodiments of the invention tastes include instance, sweetness and/or sourness and/or saltiness and/or bitterness and/or umami and/or kokumi and/or fattiness. In some exemplary embodiments of the invention, the sensory values for odor are relative values derived from an odor impact of each of the ingredients of the foods, wherein the odor impact is derived from intrinsic physical and chemical properties of each ingredient that is an odorant. Alternatively or additionally, in some embodiments the intrinsic physical and chemical properties are selected from: molecular mass; boiling point, vapor pressure, molar volume, enthalpy of vaporization, substantivity, molecular geometry, polar surface area, freely rotating bonds, surface tension, and partition coefficient. In some embodiments of the invention, a product organoleptic profile presents a graphic illustration with each of the plurality of odors in a food represented in a different size in accordance with its relative strength.

According to another aspect of some embodiments of the invention a recommendation engine issues a recommendation including a percentage likelihood, between 0 and 100%, that a specific user will like a specific product. In some embodiments, the recommendation includes recommending one out of a group of foods to a user on a basis of a predicted likelihood that the user will like the flavor of the one food from the group.

Alternatively or additionally, in some embodiments a computer-implemented system for recommending products adapted to an organoleptic preference of a particular user is provided. In some embodiments the system includes a database storing sensory values for specific products, for each of a plurality of tastes, odors, and trigeminal effects; a user interface configured to administer questionnaires about sensory food preferences to users; and a computer program product configured to analyze user responses to the questionnaires to thereby generate a user taste preference profile, in which the responses are converted to preferred values on a scale, for each of the plurality of tastes, odors, and trigeminal effects, and to recommend foods based on a prediction of a likelihood of the user to like a flavor of the food, in accordance with the user taste preference profile and the database.

According to various exemplary embodiments of the invention the aspects are combined in every possible combination and sub-combination.

According to yet another aspect of some embodiments of the invention comparison of a user organoleptic profile with a product organoleptic profile identifies a set of differences. Each difference is characterized by an amount (defined in weight or volume) and a direction (increase or decrease). In some embodiments small differences are used as the basis for recommendations of specific products. Alternatively or additionally, in some embodiments application of a set of differences to a recipe produces a modified recipe that is custom tailored to the specific user's organoleptic profile.

According to various exemplary embodiments of the invention the aspects set forth above are combined in every possible combination and sub-combination.

It will be appreciated that the various aspects described above relate to solution of technical problems associated with improving the organoleptic experience of users trying new products.

Alternatively or additionally, it will be appreciated that the various aspects described above relate to solution of technical problems related to return of products after delivery due to user dissatisfaction with a product organoleptic profile. According to various exemplary embodiments of the invention the aspects listed above (and their various optional features) are combined in every possible combination and subcombination

In some exemplary embodiments of the invention, there is provided a system including:

(a) at least one food service terminal presenting an invitation to submit an organoleptic user profile;

(b) a communication module configured to receive the organoleptic user profile submitted in response to the invitation; and (c) an analysis module configured to compare the organoleptic user profile to a specific food item organoleptic profile stored in a database and generate a modified recipe for the specific food item based on the analysis. In some exemplary embodiments of the invention the modified recipe for the specific food item is presented in an analog format. Alternatively or additionally, in some embodiments the system includes a food preparation module configured to prepare the specific food item according to the modified recipe provided in digital format by the analysis module. Alternatively or additionally, in some embodiments the food preparation module includes: a plurality of storage containers holding individual ingredients listed in the modified recipe wherein each storage container is equipped with a metered dispenser; robotic food preparation components; and a controller configured to operate the metered dispensers according to the modified recipe and to coordinate operation of the robotic food preparation components.

In some exemplary embodiments of the invention, there is provided a system including: (a) at least one food service terminal presenting an invitation to submit an organoleptic user profile; (b) a communication module configured to receive the organoleptic user profile submitted in response to the invitation; and (c) an analysis module configured to compare the organoleptic user profile to a population of food item organoleptic profiles stored in a database and recommend one or more specific food items based on the analysis.

In some exemplary embodiments of the invention, there is provided a method including: (a) receiving an organoleptic user profile and at least one food item organoleptic profile at a data processing device equipped with an analysis module; and (b) outputting a digital file defining differences between the organoleptic user profile and at least one specific food item organoleptic profile, wherein each difference is defined in terms of direction and amount. In some embodiments the method includes formatting the digital file as a list of recommendations for specific food items, wherein food items with differences characterized by small amounts are presented before food items with differences characterized by larger amounts. Alternatively or additionally, in some embodiments the method includes applying the differences defined in terms of direction and amount for a specific food item to a recipe for that food item using a reformulation module of a data processing device to generate a modified recipe.

In some exemplary embodiments of the invention, there is provided a method for recommending food that is adapted to a taste preference of a user, including: maintaining a database storing sensory values for specific foods, for each of a plurality of tastes, odors, and trigeminal effects; analyzing user responses to questionnaires about sensory food preferences to thereby generate a user taste preference profile; and in accordance with the user taste preference profile and the database, recommending foods based on a prediction of a likelihood of the user to like a flavor of the food. In some embodiments the method includes determining the sensory values for each of the foods. Alternatively or additionally, in some embodiments the determining step includes, for each food, analyzing a chemical composition of the food, determining the concentration of specific compounds within the foods having known sensory values, and, on a basis of the concentration of the specific compounds, assigning a sensory value. In some embodiments the method includes expressing the sensory values as numerical values on a relative scale. Alternatively or additionally, in some embodiments the method includes displaying a graphic illustration with each of the plurality of tastes in a food represented in a different size in accordance with its relative strength. Alternatively or additionally, in some embodiments the plurality of tastes includes sweetness, sourness, saltiness, bitterness, umami, kokumi, and fattiness. Alternatively or additionally, in some embodiments the sensory values for odor are relative values derived from an odor impact of each of the ingredients of the foods, wherein the odor impact is derived from intrinsic physical and chemical properties of each ingredient that is an odorant. Alternatively or additionally, in some embodiments the intrinsic physical and chemical properties are selected from: molecular mass; boiling point, vapor pressure, molar volume, enthalpy of vaporization, substantivity, molecular geometry, polar surface area, freely rotating bonds, surface tension, and partition coefficient. Alternatively or additionally, in some embodiments the method includes displaying a graphic illustration with each of the plurality of odors in a food represented in a different size in accordance with its relative strength. Alternatively or additionally, in some embodiments the recommending step includes issuing a percentage likelihood, between 0 and 100%, that the user will like the flavor of the food. Alternatively or additionally, in some embodiments the method includes recommending one out of a group of foods to a user on a basis of a predicted likelihood that the user will like the flavor of the one food from the group.

In some exemplary embodiments of the invention, there is provided a computer- implemented system for recommending foods adapted to a taste preference of a particular user, including: a database storing sensory values for specific foods, for each of a plurality of tastes, odors, and trigeminal effects; a user interface configured to administer questionnaires about sensory food preferences to users; and a computer program product configured to analyze user responses to the questionnaires to thereby generate a user taste preference profile, in which the responses are converted to preferred values on a scale, for each of the plurality of tastes, odors, and trigeminal effects, and to recommend foods based on a prediction of a likelihood of the user to like a flavor of the food, in accordance with the user taste preference profile and the database.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Although suitable methods and materials are described below, methods and materials similar or equivalent to those described herein can be used in the practice of the present invention. In case of conflict, the patent specification, including definitions, will control. All materials, methods, and examples are illustrative only and are not intended to be limiting.

As used herein, the terms "comprising" and "including" or grammatical variants thereof are to be taken as specifying inclusion of the stated features, integers, actions or components without precluding the addition of one or more additional features, integers, actions, components or groups thereof. This term is broader than and includes the terms "consisting of" and "consisting essentially of" as defined by the Manual of Patent Examination Procedure of the United States Patent and Trademark Office. Thus, any recitation that an embodiment "includes" or "comprises" a feature is a specific statement that sub embodiments "consist essentially of" and/or "consist of" the recited feature.

The phrase "consisting essentially of" or grammatical variants thereof when used herein are to be taken as specifying the stated features, integers, steps or components but do not preclude the addition of one or more additional features, integers, steps, components or groups thereof but only if the additional features, integers, steps, components or groups thereof do not materially alter the basic and novel characteristics of the claimed composition, device or method. The phrase "adapted to" as used in this specification and the accompanying claims imposes additional structural limitations on a previously recited component.

The term "method" refers to manners, means, techniques and procedures for accomplishing a given task including, but not limited to, those manners, means, techniques and procedures either known to, or readily developed from known manners, means, techniques and procedures by practitioners of architecture and/or computer science.

Implementation of the method and system according to embodiments of the invention involves performing or completing selected tasks or steps manually, automatically, or a combination thereof. Moreover, according to actual instrumentation and equipment of exemplary embodiments of methods, apparatus and systems of the invention, several selected steps could be implemented by hardware or by software on any operating system of any firmware or a combination thereof. For example, as hardware, selected steps of the invention could be implemented as a chip or a circuit. As software, selected steps of the invention could be implemented as a plurality of software instructions being executed by a computer using any suitable operating system. In any case, selected steps of the method and system of the invention could be described as being performed by a data processor, such as a computing platform for executing a plurality of instructions.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to understand the invention and to see how it may be carried out in practice, embodiments will now be described, by way of non-limiting example only, with reference to the accompanying figures. In the figures, identical and similar structures, elements or parts thereof that appear in more than one figure are generally labeled with the same or similar references in the figures in which they appear. Dimensions of components and features shown in the figures are chosen primarily for convenience and clarity of presentation and are not necessarily to scale. The attached figures are:

FIG. 1A is a schematic illustration of an input screen of an application programming interface (API) for a program for calculating sweetness of a food based on the food's chemical composition, according to an exemplary embodiment of the invention;

FIG. IB is a schematic illustration of an output screen of an application programming interface (API) for a program for calculating sweetness of a food based on the food's chemical composition, according to the exemplary embodiment of Fig. 1A; FIG. 2 is a schematic illustration of steps in a method of determining a user taste preference profile, according to an exemplary embodiment of the invention;

FIG. 3 schematically illustrates steps in a method of determining a taste profile of a food for multiple tastes, according to embodiments of the present disclosure;

FIG. 4 is a graphic depiction of a taste profile of orange juice, according to an exemplary embodiment of the invention;

FIG. 5 schematically illustrates steps in a method of determining an odor profile of a food, according to an exemplary embodiment of the invention;

FIG. 6 is a graphic depiction of an odor profile of orange juice, according to an exemplary embodiment of the invention;

FIG. 7 is a graphic depiction of the physical sensations of orange juice, according to an exemplary embodiment of the invention;

FIG. 8 is a schematic illustration of a process of matching between a flavor profile of a food and a taste preference profile of a user, according to an exemplary embodiment of the invention;

FIG. 9 is a schematic illustration of a process of recommending particular food items to a user based upon the user's taste preference profile and the flavor profiles of various foods, according to an exemplary embodiment of the invention;

FIG. 10 is a schematic illustration of a system according to some exemplary embodiments of the invention;

FIG. 11 is a schematic illustration of a system according to some exemplary embodiments of the invention;

FIG. 12 is a simplified flow diagram of a method according to some exemplary embodiments of the invention;

FIG. 13 is a simplified flow diagram of a method according to some exemplary embodiments of the invention;

FIG. 14 is a schematic illustration of a system according to some exemplary embodiments of the invention; and

FIG. 15 is a schematic illustration of an exemplary use scenario according to an exemplary embodiment of the invention. DETAILED DESCRIPTION OF EMBODIMENTS

Embodiments of the invention relate to methods of determining organoleptic profiles of products and/or organoleptic preference profiles of individual users, to systems and methods for matching between organoleptic product profiles and organoleptic user profiles, and to systems and methods for adjusting a product profile to more closely match a user profile.

Specifically, some embodiments of the invention can be used to prepare a custom version of a product based upon a user profile.

The principles and operation of profiles and/or systems and/or methods according to exemplary embodiments of the invention may be better understood with reference to the drawings and accompanying descriptions.

Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not limited in its application to the details set forth in the following description or exemplified by the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting.

Various exemplary embodiments of the invention relate to the perception and quantification of taste, and more specifically, but not exclusively, to methods and systems for recommending products (e.g. foods) to a user based objective taste values and odor values of the foods and a user taste preference profile.

Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of the components and/or methods set forth in the following description and/or illustrated in the drawings and/or the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways. In particular, while the invention is exemplified by reference to specific foods, beverage or cosmetic items, the systems and methods described herein are applicable to all types of foods, beverages or cosmetics.

Certain of the systems and methods described herein are implemented on a computer. The computer includes a memory, which is a non-transitory computer-readable medium having instructions stored thereon, and a processor configured to execute the instructions to carry out the methods described herein. According to various exemplary embodiments of the invention the computer is a local computer, a virtualized computer, or a cloud-based computer. Alternatively or additionally, in some embodiments the computer includes a plurality of memories and processors configured to operate together in order to perform the calculations described herein. For example, in some embodiments a single system includes a central database storing information about different types of foods and ingredients. In some embodiments the system further includes a separate computer program or database for storing taste preference profiles of individual users. In some embodiments a software application stored on an individual user's computing device has access to the central database as well as the taste preference profiles of individual users that are authorized to use the program.

For purposes of this specification and the accompanying claims, the term "user taste preference profile" or "user organoleptic profile" refers to a collection of numerical values regarding a particular user's preferences for all aspects of an experience of eating. The profile is not limited to taste, and includes other factors contributing to flavor, such as odor, trigeminal effects, and color and texture attributes of the food.

For purposes of this specification and the accompanying claims, the term "flavor profile" or "product organoleptic profile" refers to a collection of numerical values related to a particular food's flavor. These numerical values relate to all aspects of an experience of eating the food. The profile is not limited to taste, and includes other factors contributing to flavor, such as odor, trigeminal effects, and color and texture attributes of the food. Each numerical value that is entered into the flavor profile is referred to herein as a "sensory value."

For purposes of this specification and the accompanying claims, the term "food" is a general term including any item that is ingested. The term "food" thus encompasses solid foods, liquid foods (beverages), raw foods, prepared foods, and chemical ingredients.

The systems and methods described herein utilize an objective scale for taste and flavor called VAL®. This scale was introduced in a limited fashion in U.S. Patent Publication 2016/0171728, the contents of which are incorporated by reference as if fully set forth herein. The VAL scale serves as a common medium for both measuring a user's taste preferences and for measuring the flavor profile of a particular food. The present disclosure expands upon the previous disclosure of the VAL scale in several respects. First, the present disclosure applies the VAL scale to all of the sensed tastes. Second, the VAL scale is applied to odor, trigeminal effects, and certain physical attributes.

In order to enable complete understanding of the present disclosure, the principles of the VAL scale are reviewed here, for each of the components of flavor - taste, odor, and trigeminal effects. Following explication of the principles of the scale, application of the scale for creation of personalized recommendations for foods and/or customization of food products, is described.

VAL® is a measurement unit for quantifying sensations. The VAL scale is a ratio scale. In addition, the scale has a sensitivity threshold point— the point that the sense starts to be noticed. Scale units define increasing or decreasing of the intensity of the measured sensation.

Each VAL unit refers to another level of the intensity of the measured sensation. The sensitivity threshold, meaning the point that the intensity of the sense starts, is defined as 1 Vai. Considering that this point can be different from one person to another, 1 VAL is defined as the average sensitivity threshold. The VAL scale is linear, meaning that 2 VAL has a value double of 1 VAL and so on. In addition, the VAL scale is standardized, so that, across different types of taste or sensations, the same VAL level will approximately correspond to the same level of intensity.

Table 1 provides a summary of the five different basic tastes of sweetness, sourness, saltiness, bitterness, and umami. The table includes a reference compound that produces the taste, its threshold molar concentration at which the sensation is first noticeable, and the concentration in grams per liter that is equivalent to 1 Vai.

Table 1: summary of the five different basic tastes

The VAL corresponding to different substances, other than the reference compounds, is determined based on the relative intensity of the sensation generated by that substance, compared to the intensity generated by the reference substance. The relative intensities, including those listed in the present disclosure, are derived from literature publications. A database containing these literature values is maintained and continuously updated. The literature values consider not only individual effects of different compounds, but also synergistic effects caused by combinations of different compounds, when known and available.

The next several paragraphs and tables introduce the reference values and relative values for each of the components that are measured for taste. After that, determination of the objective scales for odors and for trigeminal effects is explained. First, considering sweetness, the reference for defining the VAL units of sweetness is sucrose solutions in water at 25°C and pH 7. 10 millimolar (mM) of sucrose is the threshold point at which sweetness can be sensed. This translates to a weight ratio of 3.423 grams of sucrose per liter. Exemplary substances and their relative sweetness values relative to sucrose, for the same amount of substance, are presented in Table 2:

Table 2 substances and their relative sweetness values relative to sucrose

Sourness is the taste that detects acidity. The reference substance for sourness is citric acid. Table 3 presents the sourness of various substances relative to citric acid. Table 3 sourness of various substances relative to citric acid

Saltiness is imparted by ingredients such as sodium salt, potassium salt, fish sauce, soy sauce, and certain herbs. Table 4 lists the relative values for common salty compounds.

Table 4 relative values for common salty compounds

Bitterness is the most sensitive of the tastes. Many perceive bitterness as unpleasant, sharp, or disagreeable, but it is sometimes desirable and intentionally added via various bittering agents. Common bitter foods and beverages include coffee, unsweetened cocoa, South American mate, bitter gourd, olives, citrus peel, many plants in the Brassicaceae family, dandelion greens, wild chicory, and escarole. Alcoholic beverages generally taste bitter due to ethanol.

Table 5 presents the bitterness of many common substances relative to the reference substance of caffeine.

Table 5 bitterness relative to caffeine.

Umami refers to a Savory taste, which is characteristic of broths and cooked meats. A reference substance for umami is disodium inosinate, which is commonly added to instant noodles, potato chips, and other snacks. Table 6 lists the relative umami values for various contributors to the umami taste.

Table 6 relative umami values

Kokumi means heartiness, mouthfulness, a rich taste, deliciousness, and yumminess. Kokumi may be thought of as a feeling of intensity of the five basic tastes over time; the growth of pleasant, long-lasting taste sensations; and harmony, or the overall feeling of how well- balanced the flavor is. Both the umami and the kokumi taste sensations are activated by amino acids or small peptides (y-glutamyl peptides).

Fat, or Oleogustus, is another taste that may be considered in the present system. Oleogustus is the sensation a user would get from eating oxidized oils, or more specifically non- esterified fatty acids (NEFA). Foods with oleogustus taste have a unique chemical signature and trigger specific receptors on taste buds (the CD36 receptors - fatty acid translocase). Odor is another category of sensation that contributes to the overall feeling generated by food. Often, odors are even more important than taste, when considering the overall flavor of a food. For example, without the contribution of odor, coffee is only bitter, a cookie is only sweet, and a hamburger is only salty and savory. In certain instances, odor contributes approximately 80% of the overall flavor of a food.

Odor is caused by odorants that are emitted by the food or drink. The odorants are generally volatile molecules, insoluble to water, and non-polar. Odorants are transferred by the inhaled air into the olfactory epithelium in the ceiling of the nose. Odor is caused by different molecules than tastants. Tastants are generally non-volatile molecules, water soluble, and polar. Tastants interact with the taste buds of the tongue.

The intensity of an odor is the strength of a signal that is perceived by olfactory receptors in the nose. The intensity of the odor depends both on transport properties of the odorant (e.g., volatility, log P) and the receptor-substrate interaction. For example, the smell of geraniol (a volatile compound present in the rose flower) is a combination of signals from four receptors in the nose which recognize, respectively, the alcohol function, the degree of unsaturation, a specific range of molar volume, and a specific range of polarity.

Historically, the strength of an odor has been quantified with reference to the odor detection threshold. The odor detection threshold is the concentration of an odor in the air at which 50% of a population can distinguish between the odorous sample and an odor-free reference sample. The odor detection threshold is influenced by parameters including molecular mass, molecular geometry, polarity, and partial charges. The concentration corresponding to the odor detection threshold is then assigned a baseline value, and different concentrations are numerically quantified relative to that baseline value.

The present inventors have determined that using the odor detection threshold as a basis for quantifying odor does not produce universally useful results. This is for a number of reasons. First, human olfactory ability is affected by many factors, including genetics, gender, age, environment, and health. Thus, the odor detection threshold varies for different people. In addition, in contrast to taste, in which the relative values of different compounds have a certain degree of scientific consensus, in connection with the odor detection threshold, different sources may cite various values which may differ by several orders of magnitude.

Accordingly, instead of odor detection threshold, the present disclosure uses the concept of "odor impact" to quantify the effect of different ingredients on the sensation of odor. Odor impact is based on the intrinsic physical or chemical properties of each odorant molecule. These intrinsic properties include, for example: molecular mass, boiling point, vapor pressure, molar volume, enthalpy of vaporization (AH), substantivity, molecular geometry, polar surface area, freely rotating bonds, surface tension, and the partition coefficient (log P). Each of the physical properties of any aroma molecule has a different effect on the total odor impact of the fragrance essence. Specific examples of odor impact values will be described further herein.

Trigeminal effects also contribute to the overall flavor of foods. Trigeminal effects are caused by sensations at the trigeminal nerve, which is responsible for sensation in the face and mouth. These effects include spiciness; heat; cooling; tingling, astringency, and metallic feeling. Examples of compounds that cause trigeminal effects include Lachrimating agents found in garlic and onion, and pungent compounds such as allyl isothiocyanate, found in mustard.

Compounds that generate a hot or spicy sensation, such as black pepper, have been classified for over 100 years, according to the Scoville heat index. The relative values for spicy- hot foods, using Piperine (found in black pepper) as a reference value, are summarized in Table 7.

Table 7 Scoville heat index values relative to Piperine

The trigeminal effect of cooling is induced principally by menthols. Menthols are common ingredients in chewing gum and toothpaste. Table 8 introduces the relative cooling values of various compounds.

In sum, using the reference and relative values for each of the sensations described herein, including for the different tastes, odors, and trigeminal effects, it is possible to quantify the effect on flavor for each of the components of a recipe. In addition, considering the synergies generated by each of the ingredients, it is possible to quantify a total flavor profile of a given food beverage or cosmetic product.

In practice, ingredients are typically composed of multiple compounds that are not readily separable from each other. Thus, rather than calculating the flavor values of particular compounds, a flavor profile may be calculated based on particular ingredients to a dish. A database may include the data values relevant to the ingredients. For example, hot peppers contain capsaicin and dihydrocapsaicin, which give rise to trigeminal effects, and various hydrocarbons, alcohols, esters, ketones, aldehydes, and terpenes, which together constitute capsicum extract, and give rise to odor. Of course, the hot peppers also are sensed by the taste buds.

Table 8 relative cooling values

In view of the principles described above, a database may be created with VAL values for common ingredients. In addition to items that may be entered into a global database, such as fruits, vegetables, and packaged foods, specially prepared items may also be entered into the database, based on their ingredients.

FIG. 1A illustrates an application programming interface (API) 100 for a computer program for calculating the VAL® of a food item. The API is accessed, for example, via a web browser. The user inputs into data fields the total volume of the food, and the masses of three common sugar ingredients: fructose, glucose, and sucrose. The program determines the concentrations of the three sugars in grams per liter, and calculates, on a basis of these concentrations, the VAL of the beverage. The API of the interface communicating the VAL is shown in FIG. IB. As seen in FIG. IB, VAL values are provided both for sweetness (VAL of 11) and for bitterness (VAL of 2). These parameters are merely examples, and the VAL values for other tastes, odors, and trigeminal effects may also be provided, if desired.

With this framework now in place, the uses of the VAL scale for recommending foods are considered. FIG. 2 schematically illustrates steps in a method 200 for recommending foods on a basis of the VAL scale, according to embodiments of the present disclosure.

At step 201, a user completes a questionnaire. Questionnaires of this type are commonly used in the art and an illustrative example can be found at https://www.ncbi.nlm.nih.gov/pmc/articles/PI\/IC6682919/pdf/nutrients-ll-01453.pdf. The questionnaire contains various questions regarding a user's preferences regarding taste of food. For example, the questionnaire may present pictures of different food items to users. The user is requested to rank his or her preference for each of these foods on the scale, or otherwise state that he or she is unfamiliar with the food. The preferences may be ranked on a Likert scale (for example, a rating from a scale of 1 to 5). The questionnaires may be adapted from questionnaires that are currently in use, for example by nutritionists. One widely used example is the Leeds Food Preference Questionnaire. The Leeds Food Preference Questionnaire (LFPQ), which is well known in the art, is a computer-based task, designed to measure both a user's liking and wanting for food. The traditional LFPQ shows a user 16 images of foods that are either high-fat savory, low-fat savory, high-fat sweet or low-fat sweet, and asks the users how much they like, and want, those foods. The LFPQ has been adapted to various cultures and geographic locations, in recognition of differences in availability of different foods and patterns of food consumption.

The questionnaires may also include textual questions regarding specific user preferences. For example, a question may ask whether a user drinks coffee black, with milk, with sugar, with sweetener, with any combination of the above, or with none of the above. Another question may ask which type of dessert a user prefers (e.g., chocolate, cake, ice cream, pie), when some of the desserts are sweeter than the others, or more savory than the others. A question may further ask a user to identify his favorite smell from a list of smells.

At step 202, the system scores the questionnaire. Based on the user's answers, the system determines a user's overall preference for different types of tastes, odors, and trigeminal effects.

At step 203 the system optionally outputs a graphical depiction of the user's preferred VAL® values for each of the flavor components. In the illustrated embodiment, the depiction is that of a circle or flower. The circle is subdivided into sections having relative sizes corresponding to the VAL values for each of the components. In this case, spicy has a VAL of 65; umami, 38; bitter, 10; salty, 30; sour, 25; and sweet, 31. Because the VAL® scales are standardized, the relative values approximately indicate the relative degree of preference for each taste type. In other words, in general, this user prefers a balance of tastes that is more spicy than sweet or savory.

FIG. 3 illustrates how the VAL® scale is used to analyze and categorize various food products. In the illustrated embodiment, a can of COCA COLA, containing 355 ml, is analyzed. Chemical analysis of the COCA COLA shows presence of 37.6 g of sucrose, 34.0 mg of caffeine, and 50 mg of phosphoric acid. These values are entered into the algorithm and resulting VAL values are output. In this case, the can of COCA COLA has a VAL of 31 for sweetness, 2 for bitterness, and 25 for sourness.

FIG. 4 illustrates the results of a similar analysis performed on orange juice. In this case, the results are presented in the form of a color palette. Different rectangles are placed on the color palette, with the size of the rectangle corresponding to the VAL value.

FIG. 5 illustrates how a similar mode of analysis may be performed with respect to the odor impact determination. In FIG. 5, a IL bottle of orange-flavored soft drink is analyzed for the presence of particular odorants. The results of the chemical analysis indicate the presence of 50 mg of limonene, which produces a citrus odor; 5 mg of linalool, which produces a floral odor, and 1 mg of valencene, which produces a fresh odor. The concentration of each of the odorants is input into the algorithm, and a graphic display is output indicating the VAL values of each of the measurable odors. In this case, the VAL for citrus odor is 31, the VAL for fresh odor is 25, and the VAL for floral odor is 2.

FIG. 6 illustrates a color palette display for the odors of orange juice. In this instance, approximately 40 odors are listed. Many of these odors are in relatively small weights. The number of odors that are displayed, or the threshold of the relative weight of the odor that is to be displayed, may be adjusted in accordance with user preferences.

Referring to FIG. 7, as discussed above, the overall flavor of a food is also influenced by physical sensations, including the appearance, texture and mouthfeel of the food. In order to quantify the effect of these physical sensations, a scale is also introduced for them. Color may be measured by a colorimeter. In exemplary embodiments, color is expressed using the L*A*B* color scale, in which the L* value refers to lightness, the A* value refers to the red/green coordinate, and the B* value refers to the blue/yellow coordinate. When the criterion of interest is only one particular color component (for example, in the case of orange juice, only the blue/yellow component), the display may reference only that component, for example as an RGB attribute in the format #F4B627, for example. The percentage of pulp in a volume (floating and sinking) may be measured using a centrifuge and a sieve. Cloud stability is detected by measuring the transmittance of the orange juice in a spectrophotometer.

Referring to FIG. 8, once a database is generated with taste profiles for different foods and beverages, and a user taste preference profile is generated with preferred VAL values for a particular user, the user taste preference profile and each product's taste profile may be compared in order to generate food recommendations. A few methods may be applied to profile users' preferences. By using questionnaires, based on preferred product usage, digital media, and others. The results are converted into a number, on an interval scale and converted into VAL scale (0 no sensation, 40 average max sensation threshold) The number describes the impact of the sensation. For example, Product digital sweetness = 20val. The user preference score is 20val. There is 100% that the user will like the product. Product digital sweetness = 30val. The user preference score is 20val. There is 75% that the user will like the product. According to various exemplary embodiments of the invention the recommendations are expressed as yes/no, or as a percentage of likelihood that a particular user will like a particular food. In the illustrated example, the can of COCA COLA that was previously discussed in connection with FIG. 3 is considered, with respect to the user whose taste preference profile was charted in FIG. 2. Here, the can of COCA COLA is reasonably close to the user's preferences for sweetness, bitterness, and sourness, but does not have any taste of umami, spiciness, and saltiness. The algorithm predicts a 75% probability that the user will like the can of soda.

Referring now to FIG. 9, in addition to considering whether a particular user will like a particular product, the system may also be used to compare similar products and recommend to the user which of two products to purchase. FIG. 9 illustrates the operation of a software application running on a mobile phone. The software application has access to the product database with VAL values for each of the products. In addition, the user has completed the questionnaire and thus has generated a user taste preference profile.

At step 901, the user scans a QR code 911 on packaging of each of the products. The QR code links to the entry in the database for that particular product.

At step 902, the user requests for the software program to compare the scanned product and his or her user taste preference profile. For example, the user may engage the icon 912 labeled "Pair." At steps 903a and 903b, the software program issues recommendations regarding whether the particular user 913 will like either one of the selected products. The recommendations are based on a comparison of the user's taste preference profile and the flavor profile of the product, as discussed. In the illustrated examples, at step 903a, the system determines a 78% likelihood, presented graphically as text 914a, that user 913 will like the first pictured beer. In step 903b, the system determines a 92% likelihood, presented graphically as text 914b, that the user will like the second pictured beer. If the user follows the recommendations of the application, he will choose the second beer.

Exemplary product customization system

FIG. 10 is a schematic illustration of a system for product customization, indicated generally as 1000, according to some exemplary embodiments of the invention. The system is defined in the context of food, but the principles are equally applicable to other products with sensory characteristics such as cosmetics or perfumes.

Depicted exemplary system 1000 includes at least one food service terminal 1010 presenting an invitation to submit an organoleptic user profile. In some embodiments machine readable symbol 1020 encodes the invitation. In other exemplary embodiments of the invention, the invitation is provided as part of a user interface, for example as an icon or hypertext link. In the depicted embodiment, machine readable symbol 1020 is depicted as a QR code but could be in another format, such as a bar code. According to various exemplary embodiments of the invention food service terminal 1010 takes different forms including, but not limited to, a vending machine, a self-service kiosk in a restaurant, a digital menu provided on a tablet, an application or website for a food delivery service, and a tangible media (e.g. a card or tabletop) bearing machine readable symbol 1020.

In some exemplary embodiments of the invention, a user has pre-prepared profile 1040 and simply submits the profile to system 1000. In other exemplary embodiments of the invention, the user prepares profile 1040 by responding to a series of questions provided by system 1000.

In the depicted embodiment, system 1000 includes a communication module 1030 configured to receive the organoleptic user profile 1040 submitted in response to the invitation and an analysis module 1050 configured to compare organoleptic user profile 1040 to a specific food item organoleptic profile 1062 stored in a database 1060 and generate a modified recipe 1070 for the specific food item based on the analysis. In some embodiments analysis module 1050 selects specific food item organoleptic profile 1062 based on a menu selection made by the user in parallel to submission of profile 1040.

In some exemplary embodiments of the invention, modified recipe 1070 for the specific food item is presented in analog format. For purposes of this specification and the accompanying claims, the term "analog format" means readable by a human, and includes text displayed on a screen as well as text printed on paper. In those embodiments where modified recipe 1070 is provided in an analog format, a human chef or cook prepares the selected food item according to recipe 1070. According to these analog embodiments analysis module 1050 outputs recipe 1070 to a printer or display screen.

In the depicted embodiment, system 1000 includes a food preparation module 1080 configured to prepare the specific food item according to modified recipe 1070 provided in digital format by analysis module 1050. For purposes of this specification and the accompanying claims, the term "digital format" means machine readable.

In some exemplary embodiments of the invention, food preparation module 1080 includes a plurality of storage containers (e.g. 1090a; 1090b; and 1090c) holding individual ingredients listed in modified recipe 1070. In some embodiments each of these storage containers is equipped with a metered dispenser (e.g. 1092a; 1092b; and 1092c). In the depicted embodiment, food preparation module 1080 includes robotic food preparation components 1094. According to various exemplary embodiments of the invention robotic food preparation components 1094 include mixers, stirrers, blenders, grinders, heat sources, utensils (e.g. pots, pans, and bowls) and wrapping equipment.

In the depicted embodiment, system 1000 includes a computerized controller 1096 configured to operate the metered dispensers 1092a; 1092b; and 1092c according to modified recipe 1070 and to coordinate operation of robotic food preparation components 1094.

Preparation of the food item according to modified recipe 1070 makes it more palatable to the user that supplied profile 1040.

Additional exemplary system

FIG. 11 is a schematic illustration of a system for product recommendation, indicated generally as 1100, according to some exemplary embodiments of the invention. The system is defined in the context of food, but the principles are equally applicable to other products with sensory characteristics such as cosmetics or perfumes. Depicted exemplary system 1100 includes at least one food service terminal 1110 presenting an invitation 1120 to submit an organoleptic user profile.

Food service terminal 1110 presenting an invitation 1120 are as described hereinabove in the context of Fig 10 (items 1010 and 1020).

In the depicted embodiment, system 1100 includes a communication module 1130 configured to receive the organoleptic user profile 1140 submitted in response to the invitation. Considerations in preparation and submission of organoleptic user profile 1140 are as described hereinabove for organoleptic user profile 1040.

In the depicted embodiment, system 1100 includes an analysis module 1150 configured to compare organoleptic user profile 1140 to a population of food item organoleptic profiles (e.g. 1162a; 1162b; and 1162c) stored in a database 1160 and recommend 1170 one or more specific food items based on the analysis. Three food item organoleptic profiles are depicted in database 1160 for clarity although in actual practice a much larger number of food item organoleptic profiles would typically be present.

Recommendation 1170 makes it more likely that the user submitting profile 1140 will find the food item they select palatable (provided they select according to the recommendation).

Exemplary method

FIG. 12 is a simplified flow diagram of a method that compares an organoleptic user profile to at least one food item organoleptic profile, indicated generally as 1200, according to some exemplary embodiments of the invention.

Depicted exemplary method 1200 includes receiving 1210 an organoleptic user profile and at least one food item organoleptic profile at a data processing device equipped with an analysis module and outputting 1220 a digital file defining differences between the organoleptic user profile and at least one specific food item organoleptic profile, wherein each difference is defined in terms of direction and amount.

In some embodiments, method 1200 includes formatting 1230 the digital file as a list of recommendations for specific food items. According to these embodiments food items with differences characterized by small amounts (relative to the organoleptic user profile) are presented before food items with differences characterized by larger amounts. Differences characterized by small amounts contribute to a likelihood that the user providing the organoleptic user profile will find the specific food item palatable. In some embodiments, method 1200 includes applying 1240 the differences defined in terms of direction and amount for a specific food item to a recipe for that food item using a reformulation module of a data processing device to generate a modified recipe.

The advantages of these methods are the same as those described hereinabove for exemplary systems 1100 and 1000 (Fig. 11 and Fig. 10).

Additional Exemplary method

FIG. 13 is a simplified flow diagram of a method for matching user organoleptic preferences to specific foods, indicated generally as 1300, according to some exemplary embodiments of the invention.

The depicted exemplary method 1300 includes maintaining 1310 a database storing sensory values for specific foods, for each of a plurality of tastes, odors, and trigeminal effects and analyzing 1320 user responses to questionnaires about sensory food preferences. In some embodiments the responses to the questions in the questionnaire are used to generate a user taste preference profile. In some embodiments the responses are converted to preferred values on a scale, for each of the plurality of tastes, odors, and trigeminal effects.

In some embodiments the method includes recommending 1330 foods based on a prediction of a likelihood of the user to like a flavor of the food in accordance with the user taste preference profile and data stored in the database.

In some exemplary embodiments of the invention, method 1300 includes determining 1340 the sensory values for each of the foods. In some embodiments determining 1340 includes, for each food, analyzing 1342 a chemical composition of the food, determining 1344 the concentration of specific compounds within the food(s) having known sensory values, and, on a basis of the concentration of the specific compounds, assigning 1346 a sensory value.

In some embodiments method 1300 includes expressing 1348 the sensory values as numerical values on a relative scale.

In some exemplary embodiments of the invention, method 1300 includes displaying a graphic illustration with each of the plurality of tastes in a food represented in a different size in accordance with its relative strength. In some embodiments the plurality of tastes include sweetness, sourness, saltiness, bitterness, umami, kokumi, and fattiness.

In some embodiments the sensory values for odor are relative values derived from an odor impact of each of the ingredients of the foods, wherein the odor impact is derived from intrinsic physical and chemical properties of each ingredient that is an odorant. In some embodiments the intrinsic physical and chemical properties are selected from: molecular mass; boiling point, vapor pressure, molar volume, enthalpy of vaporization, substantivity, molecular geometry, polar surface area, freely rotating bonds, surface tension, and partition coefficient.

In some exemplary embodiments of the invention, method 1300 includes displaying a graphic illustration with each of the plurality of odors in a food represented in a different size in accordance with its relative strength.

In some embodiments recommending 1300 includes issuing a percentage likelihood, between 0 and 100%, that the user will like the flavor of the food. In some exemplary embodiments of the invention, method 1300 includes recommending one out of a group of foods to a user on a basis of a predicted likelihood that the user will like the flavor of the one food from the group.

Additional exemplary recommendation system

FIG. 14 is a schematic illustration of a system for recommending foods adapted to a taste preference of a particular user, indicated generally a 1400, according to some exemplary embodiments of the invention; and

Depicted exemplary method 1300 includes a database 1410 storing sensory values for specific foods. The sensory values are for each of a plurality of tastes, odors, and trigeminal effects.

In the depicted embodiment, system 1300 includes a user interface 1420 configured to administer questionnaires 1422 about sensory food preferences to users.

In the depicted embodiment, system 1300 includes a computer program product 1430 configured to analyze user responses 1424 to questionnaires 1422 to generate a user taste preference profile 1432. In profile 1432 the responses are converted to preferred values on a scale, for each of the plurality of tastes, odors, and trigeminal effects. Using profile 1432 computer program product 1430 recommends foods 1434 based on a prediction of a likelihood of the user to like a flavor of the food, in accordance with user taste preference profile 1432 and database 1410.

Exemplary use scenario

FIG. 15 is a schematic illustration of an exemplary use scenario according to an exemplary embodiment of the invention indicated generally as 1500. The depicted configuration is a specific embodiment of system 1000 (Fig. 10) and reference is made here to certain features in Fig. 10.

The depicted exemplary use scenario is deployed, for example, in a coffee vending machine deployed in a public area accessible to many people with different taste preferences. Three types of fresh coffee are stored in separate containers 1590a; 1590b; and 1590c. Sugar is stored in a fourth container 1590d. Water is stored in a fifth container 1590e. Milk is stored in a sixth container 1590f. Each container is equipped with a corresponding metered dispensing mechanism 1592a; 1592b; 1592c; 1592d; 1592e; and 1592f respectively. All of the metered dispensing mechanisms are controlled electronically by controller 1596. Controller 1596 also controls robotic components of the system: mixer 1594a and heaters 1594b and 1594c for milk and water respectively.

Prior to use, an organoleptic profile is established for each of the coffees in containers 1590a; 1590b; and 1590c. The profile is established by performing quantitative HPLC (High Precision Liquid Chromatography) & GCMS (Gas Chromatographic Mass Spectroscopy) Analyses to evaluate bitterness, acidity, sweetness, sourness, umami, and odor. The result of this analysis is a list of compounds and their concentration. The list is then translated to a product digital organoleptic sensation profile expressed (quantitatively) in terms of bitterness, acidity, sweetness, sourness, umami, and odor. The product digital organoleptic sensation profile for each of the coffees in containers 1590a; 1590b; and 1590c is stored in a database 1060 (see Fig. 10).

When a user approaches the vending machine for the first time, they scan barcode 1020 (Fig. 10) with their phone and are presented with a questionnaire containing four or more questions relating to their preferences for bitterness, acidity, sweetness, sourness, umami, and odor in coffee. There is a tradeoff between convenience and accuracy. A larger number of questions contributes to a more accurate user organoleptic preference profile, but a smaller number of questions is preferred by many users. Answers to the questions are translated into a user organoleptic preference profile which is used to generate a modified recipe 1070 (Fig. 10) which is sent to controller 1596. Controller 1596 operates valves 1592a; 1592b; and 1592c to dispense custom amounts of coffee from containers 1590a; 1590b; and 1590c into mixer 1594a. This produces a user specific blend custom tailored to the individual palette of the user as defined in user organoleptic profile 1040. Controller 1596 then dispenses an appropriate amount of water via valve 1592e through heater 1594c to mixer 1594a where it comes into contact with the ground coffee. In some embodiments the contact time between the water and thew coffee is controlled in accord with user profile 1040. Depending on the user's beverage choice, controller 1596 then dispenses an appropriate amount of milk via valve 1592f through heater 1594b to mixer 1594a and/or dispenses an appropriate amount of sugar via valve 1592d to mixer 1594a.

The finished beverage is then dispensed via an additional valve (bot depicted) in mixer 1594 into a waiting cup.

Exemplary advantages

In some embodiments the matches are reliable and transferable between different users because both the product profile and the user profile are based on objective values.

Alternatively or additionally, in some the user taste preference profiles are generated with digital questionnaires which are custom tailored to the relevant product. These digital questionnaires are delivered at point of use and analyzed in a short time with little effort.

In general, the various embodiments described hereinabove contribute to a reduction in risk that a user will encounter a product that they find organoleptically disagreeable.

Additional exemplary use scenarios

In addition to the preparation of custom coffee as described hereinabove, it is envisioned that the described systems and methods can be applied to customization of soups (e.g. Ramen), stir fried dishes, cocktails, wine, beer, pizza, sauces, cooked meat, and salads.

Other considerations

Olfactory perceptions differ from user to user due to genetic and/or experience and/or olfactory memory. The described systems and methods address this user-to-user variability by creating an objective scale to measure sensations (e.g., "sweetness 20") and selecting/tailoring products to individual olfactory preferences.

Experiencing new olfactory sensations involves firsthand trial, sometimes augmented by external information (e.g. descriptions or recommendations provided by another person). In some cases, memory plays a role in categorizing new olfactory experiences relative to previous olfactory experiences (e.g. "This wine reminds me of the chianti we drank on the train from Venice to Rome.")

Olfactory perceptions also fluctuate over time due to hydration and/or emotions and/or environment and/or physiological changes. The described methods and systems consider the dynamic and context-dependent nature of the user's olfactory experience and provide personalized and meaningful sensory experiences.

It is expected that during the life of this patent many robotic components will be developed and the scope of the invention includes all such new technologies a priori.

Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims.

Specifically, a variety of numerical indicators have been utilized. It should be understood that these numerical indicators could vary even further based upon a variety of engineering principles, materials, intended use and designs incorporated into the various embodiments of the invention. Additionally, components and/or actions ascribed to exemplary embodiments of the invention and depicted as a single unit may be divided into subunits. Conversely, components and/or actions ascribed to exemplary embodiments of the invention and depicted as sub-units/individual actions may be combined into a single unit/action with the described/depicted function.

Alternatively, or additionally, features used to describe a method can be used to characterize an apparatus or system and features used to describe an apparatus or system can be used to characterize a method.

It should be further understood that the individual features described hereinabove can be combined in all possible combinations and sub-combinations to produce additional embodiments of the invention. The examples given above are purely illustrative and do not limit the scope of the invention, which is defined solely by the following claims.

Each recitation of an embodiment of the invention that includes a specific feature, part, component, module or process is an explicit statement that additional embodiments of the invention not including the recited feature, part, component, module or process exist.

Alternatively or additionally, various exemplary embodiments of the invention exclude any specific feature, part, component, module, process or element which is not specifically disclosed herein.

Specifically, the invention has been described in the context of food but might also be used in the context of other product types such as cosmetics or toiletries. All publications, references, patents and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such a reference is available as prior art to the present invention.

The terms "include", and "have" and their conjugates as used herein mean "including but not necessarily limited to".

Claims

CLAIMS:

1. A system comprising:

(a) at least one food service terminal presenting an invitation to submit an organoleptic user profile;

(b) a communication module configured to receive said organoleptic user profile submitted in response to said invitation; and

(c) an analysis module configured to compare said organoleptic user profile to a specific food item organoleptic profile stored in a database and generate a modified recipe for said specific food item based on said analysis.

2. A system according to claim 1, wherein said modified recipe for said specific food item is presented in analog format.

3. A system according to claim 1, comprising a food preparation module configured to prepare said specific food item according to said modified recipe provided in digital format by said analysis module.

4. A system according to claim 3, wherein said food preparation module includes: a plurality of storage containers holding individual ingredients listed in said modified recipe wherein each storage container is equipped with a metered dispenser; robotic food preparation components; and a controller configured to operate said metered dispensers according to said modified recipe and to coordinate operation of said robotic food preparation components.

5. A system comprising:

(a) at least one food service terminal presenting an invitation to submit an organoleptic user profile;

(b) a communication module configured to receive said organoleptic user profile submitted in response to said invitation; and

(c) an analysis module configured to compare said organoleptic user profile to a population of food item organoleptic profiles stored in a database and recommend one or more specific food items based on said analysis.

6. A method comprising:

(a) receiving an organoleptic user profile and at least one food item organoleptic profile at a data processing device equipped with an analysis module; and

(b) outputting a digital file defining differences between said organoleptic user profile and at least one specific food item organoleptic profile, wherein each difference is defined in terms of direction and amount.

7. A method according to claim 6, comprising formatting said digital file as a list of recommendations for specific food items, wherein food items with differences characterized by small amounts are presented before food items with differences characterized by larger amounts.

8. A method according to claim 6, comprising applying said differences defined in terms of direction and amount for a specific food item to a recipe for that food item using a reformulation module of a data processing device to generate a modified recipe.

9. A method for recommending food that is adapted to a taste preference of a user, comprising: maintaining a database storing sensory values for specific foods, for each of a plurality of tastes, odors, and trigeminal effects; analyzing user responses to questionnaires about sensory food preferences to thereby generate a user taste preference profile; and in accordance with the user taste preference profile and the database, recommending foods based on a prediction of a likelihood of the user to like a flavor of the food.

10. The method of claim 9, further comprising determining the sensory values for each of the foods.

11. The method of claim 10, wherein the determining step comprises, for each food, analyzing a chemical composition of the food, determining the concentration of specific compounds within the foods having known sensory values, and, on a basis of the concentration of the specific compounds, assigning a sensory value.

12. The method of any one of claims 9 to 11, further comprising expressing the sensory values as numerical values on a relative scale.

13. The method of claim 12, further comprising displaying a graphic illustration with each of the plurality of tastes in a food represented in a different size in accordance with its relative strength.

14. The method of any one of claims 9 to 13, wherein the plurality of tastes comprises sweetness, sourness, saltiness, bitterness, umami, kokumi, and fattiness.

15. The method of any one of claims 9 to 14, wherein the sensory values for odor are relative values derived from an odor impact of each of the ingredients of the foods, wherein the odor impact is derived from intrinsic physical and chemical properties of each ingredient that is an odorant.

16. The method of claim 15, wherein the intrinsic physical and chemical properties are selected from: molecular mass; boiling point, vapor pressure, molar volume, enthalpy of vaporization, substantivity, molecular geometry, polar surface area, freely rotating bonds, surface tension, and partition coefficient.

17. The method of any one of claims 9 to 16, further comprising displaying a graphic illustration with each of the plurality of odors in a food represented in a different size in accordance with its relative strength.

18. The method of any one of claims 9 to 17, wherein the recommending step comprises issuing a percentage likelihood, between 0 and 100%, that the user will like the flavor of the food.

19. The method of claim 18, further comprising recommending one out of a group of foods to a user on a basis of a predicted likelihood that the user will like the flavor of the one food from the group.

20. A computer-implemented system for recommending foods adapted to a taste preference of a particular user, comprising: a database storing sensory values for specific foods, for each of a plurality of tastes, odors, and trigeminal effects; a user interface configured to administer questionnaires about sensory food preferences to users; and a computer program product configured to analyze user responses to the questionnaires to thereby generate a user taste preference profile, in which the responses are converted to preferred values on a scale, for each of the plurality of tastes, odors, and trigeminal effects, and to recommend foods based on a prediction of a likelihood of the user to like a flavor of the food, in accordance with the user taste preference profile and the database.