System and method for personalized fragrance recommendation using microbiome-informed inference

The system addresses inconsistent fragrance performance by inferring skin microenvironment states to optimize fragrance recommendations, enhancing accuracy and reliability through microbiome-informed fragrance composition alignment.

WO2026234692A1PCT designated stage Publication Date: 2026-11-12ABDUL GHAFUR KULAKKATTIL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/IN2026/050750
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-07
Filing Date
2026-04-30
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Existing fragrance recommendation systems fail to account for site-specific skin microenvironment variability influenced by microbial ecosystems and pH conditions, leading to inconsistent fragrance performance across different anatomical application sites.

Method used

A computer-implemented method and system that infers a functional skin microenvironment state based on microbial ecosystem variability and pH conditions, evaluating fragrance compositions for alignment with these conditions to generate personalized recommendations.

Benefits of technology

Improves the accuracy, reliability, and consistency of fragrance performance predictions by integrating microbiome-driven pH variability and evaporation characteristics, optimizing fragrance selection without biological sampling.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IN2026050750_12112026_PF_FP_ABST
    Figure IN2026050750_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A computer-implemented system 100 for generating personalized fragrance recommendations is disclosed. The computer-implemented system 100 comprises a user device 102 configured to transmit experiential data via a network 104 to a fragrance recommendation server 106. The fragrance recommendation server 106 includes a processor 108 and a memory 110 storing instructions for processing the experiential data. The processor 108 is configured to receive data including an anatomical application site and perceived fragrance performance patterns, classify the site into a predefined skin microenvironment category based on microbial and pH- related associations, and infer a functional skin microenvironment state without requiring biological sampling. The system 100 evaluates fragrance compositions for performance alignment and generates a personalized recommendation via a recommendation output interface 114.
Need to check novelty before this filing date? Find Prior Art

Description

SYSTEM AND METHOD FOR PERSONALIZED FRAGRANCE RECOMMENDATION USING MICROBIOME-INFORMED INFERENCE BACKGROUNDTechnical Field

[0001] The present invention relates to fragrance personalization systems and computational decision-support mechanisms. More particularly, the invention relates to a microbiome-informed inference -based system and method for generating personalized fragrance recommendations by accounting for site-specific biological and physicochemical characteristics of human skin.Description of the Related Art

[0002] Fragrance compositions may exhibit considerable variability in performance when applied to different individuals or to different anatomical sites of the same individual. Such variability may manifest as differences in longevity, diffusion, tonal evolution, perceptual distortion, or intensity.

[0003] Dermatological and cosmetic science literature establishes that the human skin surface is not uniform across anatomical regions. Distinct skin sites harbor different microbial ecosystems. Microbial metabolic processes contribute to the maintenance of local skin pH and influence the physicochemical environment present at the skin surface.

[0004] Variations in skin pH and associated physicochemical conditions may affect evaporation characteristics, stability, and perceptual behavior of fragrance compounds. Consequently, the same fragrance composition may behave differently depending on the anatomical site at which it is applied.

[0005] Existing fragrance recommendation approaches primarily rely on olfactory preference profiling, demographic segmentation, or historical purchase data. Such approaches do not incorporate structured inference of site-specific skin microenvironment variability influenced by microbial ecosystems and associated pH conditions, and therefore do not address variability in fragrance performance across anatomical application sites.

[0006] Accordingly, there exists a need for a structured computational system capable of translating user-reported fragrance performance patterns into inferred skin microenvironment states and generating fragrance recommendations that improve alignment between fragrancecompositions and anatomical skin conditions.

[0007] Therefore, there remains a need to address the aforementioned technical drawbacks in existing technologies.SUMMARY

[0008] In view of the foregoing, there is provided a computer-implemented method for generating a site-specific fragrance recommendation. The method includes receiving, via a user device, experiential data comprising an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site. The method includes classifying the identified anatomical application site into a predefined skin microenvironment category by retrieving stored associations between site-specific microbial ecosystem variability and microbially-influenced pH conditions. The method includes inferring, via an inference engine executed on a computing system, a functional skin microenvironment state for the user based on a combination of the skin microenvironment category and the perceived fragrance performance pattern, wherein the functional skin microenvironment state is inferred without requiring biological sampling of the user. The method includes evaluating a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state using a mapping between fragrance composition attributes or chemical structures and predicted stability under inferred pH and microbial conditions. The method includes generating a personalized fragrance recommendation output optimized for the identified anatomical application site.

[0009] In some embodiments, the perceived fragrance performance pattern includes at least one of: fragrance longevity, tonal evolution, or perceptual distortion.

[0010] In some embodiments, the method further includes refining the inferred functional skin microenvironment state by incorporating measured skin pH data as an additional input parameter.

[0011] In some embodiments, the method further includes refining the inferred functional skin microenvironment state by incorporating metagenomic profiling data of the user's skin microbiome at the identified anatomical application site.

[0012] In some embodiments, the method further includes updating the logic set based on an adaptive refinement process that correlates aggregated anonymized user feedback with specific microenvironment categories.

[0013] In some embodiments, the method further includes mapping groups that include at least one of: esters, aldehydes, musks, or terpene derivatives.

[0014] In some embodiments, the method further includes the metagenomic profiling, which comprises sequencing of microbial genetic material associated with the skin microbiome of the user.

[0015] In some embodiments, the output includes a structured formulation report for a fragrance manufacturer to facilitate the design of a composition tailored to the inferred skin microenvironment state.

[0016] In another aspect, a system for generating personalized fragrance recommendations. The system includes a user device that includes an interactive digital interface configured to receive user experiential data and anatomical application-site information. The system includes a fragrance recommendation server that comprises a memory that stores a set of instructions and a processor that executes the set of instructions, when executed by the processor, causes the processor to receive, via the user device, experiential data comprising an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site. The processor classifies the identified anatomical application site into a predefined skin microenvironment category by retrieving stored associations between site-specific microbial ecosystem variability and microbially-influenced pH conditions. The processor infers, via an inference engine executed on the computing system, a functional skin microenvironment state for the user based on a combination of the skin microenvironment category and the perceived fragrance performance pattern. The processor evaluates a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state using a logic set that maps fragrance composition attributes or chemical structures to predicted stability under the inferred pH and microbial conditions and generates a personalized fragrance recommendation output optimized for the identified anatomical application site.

[0017] The term “functional skin microenvironment state” refers to a computed representation comprising at least predicted pH range, evaporation characteristics, and microbiome-induced chemical interaction parameters.

[0018] The term “performance alignment” refers to a quantified compatibility score between fragrance composition attributes and the functional skin microenvironment state.BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:

[0020] FIG. 1 illustrates a system architecture for generating site-specific personalized fragrance recommendations according to some embodiments herein;

[0021] FIG. 2 illustrates an exemplary system view of an adaptive fragrance recommendation and optimization system according to some embodiments herein;

[0022] FIG. 3 illustrates a method flow for generating personalized fragrance recommendations according to some embodiments herein;

[0023] FIG. 4A-B collectively illustrate an extended workflow for generating a personalized fragrance recommendation based on user profile data, inferred skin microenvironment conditions, and fragrance property matching according to some embodiments herein;

[0024] FIG. 5 illustrates an adaptive feedback learning process for improving personalized fragrance recommendations according to some embodiments herein;

[0025] FIG. 6 illustrates a method for generating site-specific personalized fragrance recommendations according to some embodiments herein;

[0026] FIG. 7 is a schematic diagram of a computer architecture in accordance with the embodiments herein.DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

[0027] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0028] FIG. 1 illustrates a system architecture for generating site-specific personalized fragrance recommendations according to some embodiments herein. The system 100 comprises a user device 102, a network 104, and a fragrance recommendation server 106.The network 104 maybe wired or wireless, or a combination of both. The fragrance recommendation server 106 further comprises a processor 108 and a memory 110 and is configured to generate a recommendation output via a recommendation output interface 114. The user device 102 may be, but is not limited to, a tablet, a laptop, a computer device, a customized input device, or a mobile phone.

[0029] The user device 102 receives and transmits user-provided experiential data. The experiential data includes an identified anatomical application site; and at least one perceived fragrance performance pattern associated with the identified anatomical application site. The perceived fragrance performance pattern may include one or more of: fragrance longevity, tonal evolution, and perceptual distortion. In some embodiments, when in operation, a user provides such experiential data via the user device 102. For example, a user may input that a fragrance applied to the wrist exhibits reduced longevity or fades quickly, or that a fragrance applied to the neck undergoes tonal distortion over time. In some embodiments, the user device 102 may provide a structured questionnaire, guided prompts, or conversational interface to capture the experiential data in a standardized format.

[0030] The user device 102 is communicatively coupled to the fragrance recommendation server 106 via the network 104. The network 104 enables transmission of the experiential data from the user device 102 to the fragrance recommendation server 106, and transmission of recommendation outputs from the fragrance recommendation server 106 back to the user device 102.

[0031] The fragrance recommendation server 106 is configured to process the received experiential data and generate a personalized fragrance recommendation output. The processor 108 executes the instructions stored in the memory 110 to perform the following operations.

[0032] The processor 108 receives, via the network 104, experiential data transmitted from the user device 102, including the identified anatomical application site; and the perceived fragrance performance pattern.

[0033] The processor 108 classifies the identified anatomical application site into a predefined skin microenvironment category. The classification is performed by retrieving stored associations between site-specific microbial ecosystem variability; and microbially-influenced pH conditions. The predefined skin microenvironment categories correspond to functional groupings of skin conditions characterized by differences in microbial activity and physicochemical properties. For example, the wrist may be classified into a microenvironment category associatedwith higher volatility sensitivity, while the neck may be classified into a category associated with increased moisture and pH variability.

[0034] The processor 108 infers a functional skin microenvironment state based on the classified skin microenvironment category; and the perceived fragrance performance pattern. The inferred functional skin microenvironment state represents a modeled condition of the skin environment that affects fragrance behavior, including evaporation characteristics and compositional stability. The inference is performed without requiring biological sampling of the user.

[0035] The processor 108 evaluates a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state. The evaluation is performed using a mapping between fragrance composition attributes or chemical structures, and predicted stability under inferred pH and microbial conditions. In some embodiments, the mapping may include fragrance groups such as: esters, aldehydes, musks, and terpene derivatives. For example, if the microenvironment is associated with rapid evaporation, fragrance compositions containing heavier base notes such as musks or resins may be identified as having improved stability.

[0036] Based on the evaluation, processor 108 generates a personalized fragrance recommendation optimised for the identified anatomical application site. The recommendation output is provided via the recommendation output interface 114. The recommendation output may include one or more fragrance suggestions categorized fragrance types or composition-level guidance.

[0037] The recommendation output interface 114 is configured to present the generated recommendation output to the user. The output may be displayed via the user device 102, or any associated display or application interface. In some embodiments, output further comprises a structured formulation report for a fragrance manufacturer to facilitate the design of a composition tailored to the inferred skin microenvironment state.

[0038] In some embodiments, the system 100 may further measure skin pH data as an additional input parameter to refine the inferred functional skin microenvironment state. In some embodiments, metagenomic profiling data of the user’s skin microbiome may be incorporated to enhance classification accuracy. In some embodiments, adaptive refinement processes may be performed based on aggregated anonymized user feedback to update classification or evaluation logic. In some embodiments, structured formulation outputs may be generated for fragrancemanufacturers to facilitate composition design.

[0039] FIG. 2 illustrates an exemplary system view of an adaptive fragrance recommendation and optimization system according to some embodiments herein. The system 200 comprises a user input module 202, a microenvironment classification module 204, an inference engine 206, a fragrance performance alignment module 208, a fragrance recommendation module 210, an adaptive refinement module 212, a human skin interface 214, and an output module 216. The user input module 202 is configured to receive experiential data from a user, wherein the experiential data comprises at least an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site. The experiential data may further include prior fragrance usage experiences and optional contextual parameters. The microenvironment classification module 204 is communicatively coupled to the user input module 202 and is configured to classify the identified anatomical application site into a predefined skin microenvironment category. The classification is performed based on stored associations between site-specific microbial ecosystem variability and microbially influenced pH conditions. The inference engine 206 is communicatively coupled to the microenvironment classification module 204 and is configured to generate a functional skin microenvironment state corresponding to the classified skin microenvironment category and the received perceived fragrance performance pattern. The fragrance performance alignment module 208 is communicatively coupled to the inference engine 206 and is configured to evaluate a plurality of fragrance compositions against the inferred functional skin microenvironment state using predefined fragrance selection logic. The evaluation includes determining compatibility of fragrance compositions with respect to predicted stability under microbially influenced pH conditions and evaporation characteristics. The fragrance recommendation module 210 is configured to generate one or more personalized fragrance recommendations based on the evaluation performed by the fragrance performance alignment module 208. The adaptive refinement module 212 is communicatively coupled to the user input module 202, the microenvironment classification module 204, the inference engine 206, the fragrance performance alignment module 208, and the fragrance recommendation module 210. The adaptive refinement module 212 is configured to update classification parameters, inference rules, and fragrance evaluation logic based on aggregated user feedback and interaction data. The human skin interface 214 represents a biological interaction layer corresponding to the application of recommendedfragrance compositions onto the user's skin, wherein the interaction reflects real-world performance of the recommended compositions under the inferred functional skin microenvironment state. The output module 216 is communicatively coupled to the human skin interface 214 and is configured to generate and present a recommendation output to the user, wherein the recommendation output comprises the personalized fragrance recommendations. In some embodiments, the user input module 202 is implemented through an interactive digital interface configured to receive user responses via conversational prompts, structured questionnaires, or guided data entry workflows. In some embodiments, the system dynamically adapts subsequent input queries based on previously received experiential data and generates personalized fragrance recommendations using rule-based logic, machine learning models, or hybrid inference mechanisms.

[0040] In some embodiments, the fragrance performance alignment module 208 applies a rule-based scoring model to evaluate fragrance compositions. Each fragrance composition is associated with one or more classes including esters, aldehydes, musks, and terpenes. Each class is assigned a stability score across predefined pH ranges and microbial activity levels stored in a lookup table. For example, ester-based compositions may be assigned lower stability scores in acidic microenvironments due to increased hydrolysis susceptibility, whereas musk-based compositions may be assigned higher stability scores under the same conditions. The alignment module computes a composite performance score for each fragrance composition based on weighted parameters including predicted evaporation rate, pH stability, and microbiome interaction effects, and selects compositions exceeding a predefined threshold.

[0041] For example, a user reports that a fragrance applied to a wrist dissipates rapidly. The user input module 202 receives the experiential data and identifies the anatomical application site as the wrist. The microenvironment classification module 204 classifies the wrist into a predefined microenvironment category associated with increased volatility sensitivity based on stored microbial and pH-related associations. The inference engine 206 generates a functional skin microenvironment state corresponding to increased evaporation conditions. The fragrance performance alignment module 208 evaluates fragrance compositions and identifies compositions exhibiting improved persistence under such conditions. The fragrance recommendation module 210 generates recommendations including compositions characterized by woody, resinous, or musky structures. For example, a user reports tonal distortion when floral fragrances are appliedto the neck. The user input module 202 receives the experiential data and identifies the anatomical application site as the neck. The microenvironment classification module 204 classifies the neck into a moisture-influenced microenvironment category. The inference engine 206 generates a functional skin microenvironment state associated with increased humidity and microbiome-influenced pH variability. The fragrance performance alignment module 208 evaluates fragrance compositions with improved tonal stability under such conditions, and the fragrance recommendation module 210 generates corresponding recommendations. In some embodiments, the user input module 202 is further configured to receive measured skin pH data associated with the anatomical application site. The inference engine 206 incorporates the measured skin pH data as an input parameter to refine the functional skin microenvironment state. The fragrance performance alignment module 208 evaluates fragrance compositions based on the refined functional skin microenvironment state, and the fragrance recommendation module 210 generates recommendations accordingly. In some embodiments, the inference engine 206 utilizes machine learning models selected from regression models, decision trees, neural networks, or probabilistic models. In other embodiments, rule-based inference or hybrid models combining deterministic rules and learned parameters are employed.

[0042] FIG. 3 illustrates a method 300 for generating a personalized fragrance recommendation based on a site-specific skin microenvironment, according to some embodiments herein. At step 302, the method comprises receiving user input and microenvironment data. The receiving includes obtaining experiential data associated with a user, wherein the experiential data comprises at least an identified anatomical application site and at least one perceived fragrance performance pattern corresponding to the identified anatomical application site. The perceived fragrance performance pattern may include fragrance longevity, tonal evolution, or perceptual distortion. In some embodiments, the receiving is performed via a user device through structured input interfaces, conversational prompts, or guided workflows. At step 304, the method comprises classifying the anatomical application site into a predefined skin microenvironment category. The classification is performed based on stored associations between site-specific microbial ecosystem variability and microbially influenced pH conditions. The predefined skin microenvironment categories represent distinct functional groupings of skin environments characterized by differences in microbial composition and physicochemical properties. At step 306, the method comprises generating initial fragrance recommendations. The generation includes identifying oneor more candidate fragrance compositions based on the classified skin microenvironment category. In some embodiments, the initial recommendations are generated using predefined mapping rules between microenvironment categories and fragrance composition attributes. At step 308, the method comprises aligning fragrance performance with the skin microenvironment. The aligning includes evaluating the candidate fragrance compositions against an inferred functional skin microenvironment state derived from the classified category and the perceived fragrance performance pattern. The evaluation determines compatibility of the fragrance compositions with respect to predicted stability under microbially influenced pH conditions and evaporation characteristics. At step 310, the method comprises refining the fragrance recommendations using feedback data. The refining includes updating the candidate fragrance compositions based on user feedback, historical interaction data, or aggregated system-level learning. In some embodiments, the refining further includes adjusting classification parameters, inference logic, or fragrance evaluation criteria. At step 312, the method comprises outputting a personalized fragrance recommendation. The output includes generating a final recommendation comprising one or more fragrance compositions optimized for the identified anatomical application site and the inferred functional skin microenvironment state. The recommendation may be presented via a user interface associated with a user device.

[0043] FIG. 4A-B collectively illustrate an extended workflow for generating a personalized fragrance recommendation based on user profile data, inferred skin microenvironment conditions, and fragrance property matching. The process begins with receiving user profile and context data 402. The user profile and context data 402 may include parameters such as age category, gender, environment type, fragrance preferences, and past fragrance performance. The process proceeds to microenvironment inference 403, wherein a probable skin microenvironment is determined based on the received user profile and contextual data. The inference includes identifying a likely skin pH range and application site characteristics. At fragrance property matching 404, fragrance attributes are matched with the inferred microenvironment. The attributes include volatility, scent family, persistence, and projection. At candidate fragrance selection 406, suitable fragrance profiles are selected from a fragrance database based on the matched properties. The selected candidates represent fragrance compositions likely to perform well under the inferred skin conditions. At ranking and optimization 408, the selected candidate fragrance profiles are ranked based on predictedperformance within the inferred skin microenvironment. The ranking may consider factors such as stability, longevity, and user preference alignment. At step 410, a personalized fragrance recommendation is generated. The recommendation includes one or more optimized fragrance options tailored to the user’s profile and skin microenvironment. In some embodiments, the ranking and optimization step further refines the recommendations using feedback data, historical usage patterns, or adaptive learning techniques to improve recommendation accuracy. For example, a user with preference for fresh fragrances and exposure to humid environments may receive recommendations of fragrance compositions exhibiting moderate volatility and high persistence to ensure stable performance under such conditions.

[0044] FIG. 5 illustrates an adaptive feedback learning process for improving personalized fragrance recommendations according to some embodiments herein. The process begins with a personalized fragrance recommendation 502 generated for a user. The recommendation is provided based on previously inferred skin microenvironment conditions and fragrance evaluation processes. The personalized fragrance recommendation 502 is provided to an adaptive refinement module 504. The adaptive refinement module 504 is configured to improve recommendation accuracy based on feedback and observed performance. Context-specific skin response observations 506 are collected following application of the recommended fragrance. The observations may include parameters such as fragrance longevity, projection, and scent transformation over time on the user’s skin. In parallel, feedback data collection 508 is performed. The feedback data may include user satisfaction, performance ratings, and environmental context associated with fragrance usage. The adaptive refinement module 504 processes the contextspecific skin response observations 506 and the feedback data collection 508 to generate refinement updates 510. The refinement updates 510 represent adjustments to system parameters based on real-world performance and user feedback. The refinement updates 510 are applied to perform model adjustments 512. The model adjustments 512 may include updating classification parameters, inference logic, and fragrance evaluation criteria used in generating future recommendations. The model adjustments 512 are fed back into the adaptive refinement module 504, thereby enabling a continuous learning loop that progressively improves the accuracy and personalization of fragrance recommendations. In some embodiments, the adaptive refinement module 504 utilizes machine learning techniques, statistical models, or rule-based logic to process feedback data and generate refinement updates. In some embodiments, the environmental contextincludes parameters such as temperature, humidity, and activity level, which influence fragrance performance and are incorporated into the refinement process. For example, a user may report that a recommended fragrance exhibits low longevity in a high-temperature environment. The system captures the feedback and updates the model to prioritize fragrance compositions with higher persistence under similar environmental conditions in subsequent recommendations.

[0045] FIG. 6 illustrates a method for generating site-specific personalized fragrance recommendations according to some embodiments herein. At step 602, the method includes receiving, via a user device, experiential data comprising an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site. At step 604, the method includes classifying the identified anatomical application site into a predefined skin microenvironment category by retrieving stored associations between site-specific microbial ecosystem variability and microbially influenced pH conditions. At step 606, the method includes inferring, via an inference engine executed on a computing system, a functional skin microenvironment state for the user based on a combination of the skin microenvironment category and the perceived fragrance performance pattern, wherein the functional skin microenvironment state is inferred without requiring biological sampling of the user. At step 608, the method includes evaluating a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state using a mapping between fragrance composition attributes or chemical structures and predicted stability under inferred pH and microbial conditions; and at step 610, the method includes generating a personalized fragrance recommendation output optimized for the identified anatomical application site.

[0046] The computer-implemented system provides a technical improvement over conventional fragrance recommendation systems by introducing a structured computational framework that models the interaction between site-specific skin microenvironment conditions and fragrance chemical stability. Unlike existing systems that rely primarily on user preferences or demographic data, the disclosed system transforms experiential input data into a quantified functional skin microenvironment state incorporating microbiome-driven pH variability and evaporation characteristics. This transformation enables the system to algorithmically evaluate fragrance compositions based on predicted chemical behavior, including degradation susceptibility and persistence under specific skin conditions. As a result, the invention improves the accuracy,reliability, and consistency of fragrance performance prediction across different anatomical application sites. Additionally, the system reduces variability in user experience, optimizes fragrance selection without requiring direct biological sampling, and enhances the functional capability of recommendation engines by integrating biochemical interaction modeling into the decision-making process.

[0047] A representative hardware environment for practicing the embodiments herein is depicted in FIG. 7, with reference to FIGS. 1 through 6. This schematic drawing illustrates a hardware configuration of a computer system in accordance with the embodiments herein. The computer includes at least one processing device 10 and a cryptographic processor 11. The specialpurpose CPU 10 and the cryptographic processor (CP) 11 may be interconnected via system bus 14 to various devices such as a random-access memory (RAM) 15, read-only memory (ROM) 16, and an input / output (RO) adapter 17. The RO adapter 17 can connect to peripheral devices, such as disk units 12 and tape drives 13, or other program storage devices that are readable by the system. The computer can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments herein. The system further includes a user interface adapter 20 that connects a keyboard 18, mouse 19, speaker 25, microphone 23, and / or other user interface devices such as a touch screen device (not shown) to the bus 14 to gather user input. Additionally, a communication adapter 21 connects the bus 14 to a data processing network 26, and a display adapter 22 connects the bus 14 to a display device 24, which provides a graphical user interface (GUI) 30 of the output data in accordance with the embodiments herein, or which may be embodied as an output device such as a monitor, printer, or transmitter, for example. Further, a transceiver 27, a signal comparator 28, and a signal converter 29 may be connected with the bus 14 for processing, transmission, receipt, comparison, and conversion of electric or electronic signals.

[0048] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described interms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the appended claims.

Claims

CLAIMSI / WE CLAIM:

1. A computer-implemented method for generating a site-specific fragrance recommendation, the method comprising:receiving, via a user device (102), experiential data comprising an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site;classifying the identified anatomical application site into a predefined skin microenvironment category by retrieving stored associations between site-specific microbial ecosystem variability and microbially influenced pH conditions;inferring, via an inference engine executed on a computing system, a functional skin microenvironment state for the user based on a combination of the skin microenvironment category and the perceived fragrance performance pattern, wherein the functional skin microenvironment state is inferred without requiring biological sampling of the user;evaluating a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state using a mapping between fragrance composition attributes or chemical structures and predicted stability under inferred pH and microbial conditions; andgenerating, via a recommendation output interface, a personalized fragrance recommendation output optimized for the identified anatomical application site.

2. The method as claimed in claim 1 , wherein the perceived fragrance performance pattern includes at least one of: fragrance longevity, tonal evolution, or perceptual distortion.

3. The method as claimed in claim 1, further comprising refining the inferred functional skin microenvironment state by incorporating measured skin pH data as an additional input parameter.

4. The method as claimed in claim 1 , further comprising refining the inferred functional skin microenvironment state by incorporating metagenomic profiling data of the user's skin microbiome at the identified anatomical application site.

5. The method as claimed in claim 1, further comprising updating the logic set based on an adaptive refinement process that correlates aggregated anonymized user feedback with specific microenvironment categories.

6. The method as claimed in claim 1, wherein the mapping groups include at least one of:esters, aldehydes, musks, or terpene derivatives.

7. The method as claimed in claim 4, wherein the metagenomic profiling comprises sequencing of microbial genetic material associated with the skin microbiome of the user.

8. The method as claimed in claim 1, wherein the output further comprises a structured formulation report for a fragrance manufacturer to facilitate the design of a composition tailored to the inferred skin microenvironment state.

9. A system for generating personalized fragrance recommendations, wherein the system comprises:a user device (102) comprising an interactive digital interface configured to receive user experiential data and anatomical application-site information;a fragrance recommendation server (106) that comprises:a memory that stores a set of instructions; anda processor (108), wherein execution of the set of instructions causes the processor (108) to:receive, via the user device (102), experiential data comprising an identified anatomical application site and at least one perceived fragrance performance pattern associated with the identified anatomical application site;classify the identified anatomical application site into a predefined skin microenvironment category by retrieving stored associations between site-specific microbial ecosystem variability and microbially-influenced pH conditions;infer, via an inference engine executed on the computing system, a functional skin microenvironment state for the user based on a combination of the skin microenvironment category and the perceived fragrance performance pattern;evaluate a plurality of fragrance compositions for performance alignment with the inferred functional skin microenvironment state using a logic set that maps fragrance composition attributes or chemical structures to predicted stability under the inferred pH and microbial conditions; and generate, via a recommendation output interface, a personalized fragrance recommendation output optimized for the identified anatomical application site.