AI Personal Fragrance Consultation And Fragrance Selection / Recommendation

Abstract

Data relating to a plurality of individuals is collected, and the data is used to identify whether any of the data is a possible predictor of the individual's preference for one or more fragrances. Data collection may include a passive manner, and may be collected and / or analyzed in real-time. These predictors are then used to provide recommendations of one or more fragrances to one or more individuals on demand or based on real-time data.

Description

[0001] Priority Claim

[0002] This patent application claims the benefit of priority of U.S. Application No. 63 / 385,088, filed on November 28, 2022, which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure generally relates to fragrances, and more particularly to the recommendation of one or more fragrances. Background Art

[0004] How fragrance is perceived and associated is highly subjective and varies greatly among individuals. This makes it particularly difficult to recommend fragrances for products such as perfumes or scented products.

[0005] Complicating the subjective nature of fragrance preference further is that it can be influenced by an individual's mental or emotional state in addition to their own memories and experiences. Fragrance has long been recognized as having a strong associative link with memory.

[0006] Product recommendations are typically generic, such as targeting market demographics based on total sales data or requiring users to provide information on which the recommendation is based. There is a need for a method that passively collects the information needed to make fragrance recommendations and uses real-time data to facilitate fragrance recommendations.

[0007] The difficulty of matching fragrances to individual preferences makes it difficult to market products that use fragrances. Recommending fragrances based on an individual's stated preferences can be difficult, especially when new fragrances need to be discovered, and thus there is a need for methods to obtain additional data, particularly via passive means or via dynamic information sources. The ability to match fragrances to user preferences can help create new or personalized formulations of fragrances, market scented products, and can also prove useful in some therapeutic applications. Real-time data can be used to make recommendations that can facilitate more frequent use of fragrances, allowing individuals to select fragrances for events and situations that can be planned in advance or occur throughout the day, or to help improve their mood. Brief Description of the Drawings

[0008] Figure 1 : A fragrance recommendation is shown according to an embodiment.

[0009] Figure 2 : A fragrance database is shown according to an embodiment.

[0010] Figure 3 : A customer database is shown according to an embodiment.

[0011] Figure 4 : An event database is shown according to an embodiment.

[0012] Figure 5 : According to an embodiment, an associated database is shown.

[0013] Figure 6 : According to an embodiment, a basic module is shown.

[0014] Figure 7 : According to an embodiment, a data collection module is shown.

[0015] Figure 8 : According to an embodiment, an analysis module is shown.

[0016] Figure 9 : According to an embodiment, a parameter selection module is shown.

[0017] Figure 10 : According to an embodiment, a real-time data module is shown.

[0018] Figure 11 : According to an embodiment, a recommendation module is shown.

[0019] Figure 12 : According to an embodiment, an aromatic agent selection module is shown.

[0020] Figure 13 : According to an embodiment, a feedback module is shown.

[0021] Figure 14 is a flowchart of an example of a method for aromatic agent recommendation according to an embodiment.

[0022] Figure 15 is a block diagram showing an example of a machine on which one or more embodiments may be implemented. Detailed Description of the Embodiment

[0023] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which like numerals refer to like elements throughout the several views, and in which exemplary embodiments are shown. However, the embodiments of the claims may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. The examples set forth herein are non-limiting examples and are merely examples among other possible examples.

[0024] This is a system for making fragrance recommendations. Such a system includes an electronic device 102 for a computing device, which may include any one of a mobile device, a phone, a tablet computer, a laptop computer, a desktop computer, a kiosk, etc. The electronic device 102 may include a general computing device or a specially constructed proprietary computing device, such as a kiosk or terminal that may be present in a retail location. The electronic device 102 may include at least one of a sensor 104, a camera 106, a microphone 108, or an input device 110. The electronic device 102 may be configured to receive direct input from a customer via the input device 110, such as personal information and fragrance preferences, or alternatively passively collect data from multiple sources. The electronic device 102 may include a communication interface 112 configured to communicate with the Internet or cloud 114. The communication interface 112 may be connected to one or more electronic devices 102, such as a wearable mobile device including a smartwatch or wearable sensor 104. The communication interface 112 may also be connected to one or more cameras 106 or microphones 108. For the purposes of the present invention, any such sensor 104, camera 106, microphone 108, or input device 110 that may be connected to the electronic device 102 via the communication interface 112 will be referred to as a component of the electronic device 102. However, any such component may alternatively be one or more separate remote devices connected to the electronic device 102 via the communication interface. The sensor 104 is a detection or measurement device configured to collect data. The sensor 104 typically measures and quantifies an analog input and converts it into digital data, although some sensors may themselves collect and monitor digital data. The sensor 104 may be any one of a position sensor (accelerometer, global positioning system, etc.), a pressure sensor (pressure gauge, barometer, etc.), a temperature sensor (radiation thermometer, thermocouple, thermometer, etc.), a force sensor (force transducer), a vibration sensor, a piezoelectric sensor, a fluid property sensor, a humidity sensor, a strain gauge, a photoelectric sensor, a flow switch, a level switch, and may also need to contact the item, substance, or material they are measuring, or may not need to contact. Similarly, some sensors may measure rotational motion and linear motion. Non-contact sensors may additionally include Hall effect sensors, capacitance sensors, eddy current sensors, ultrasonic sensors, laser sensors, or proximity sensors. The sensor 104 may additionally include consumptive or catalytic chemical reactions, including assays. For example, chemical assays may include assessing the lifespan of a fragrance based on its chemical composition, assessing the characteristics of a fragrance based on its chemical composition. Additional embodiments may include biometric monitoring sensors, such as a pulse oximeter, a skin conductance response sensor, blood pressure, an electrocardiogram (EKG), etc. The sensor 104 may be embedded in one or more wearable devices, such as a smartwatch, a smart ring, clothing, shoes, etc., or alternatively directly attached to the customer's skin, for example, via an adhesive patch.Data can be collected from one or more sensors 104 on demand or in real time. In some embodiments, for example, in a home or retail environment, sensor 104 data is continuously collected without interacting with customers. Sensor 104 may additionally be capable of detecting fragrances present in the air, for example, by sampling the air and identifying one or more volatile compounds based on the chemical structure or elemental composition of one or more volatile compounds, such as via mass spectrometry. Camera 106 is an imaging sensor or an array of imaging sensors that typically measures reflected light and then uses it to recreate and image on a display according to the measurements. Each measurement is used to fill a value into a pixel or sub-pixel. Multiple sub-pixels can create a complete pixel, and an array of pixels creates an image. In some embodiments, multiple sensor measurements can be used to fill a single pixel or sub-pixel. Multiple sensor measurements can be obtained from one imaging sensor over a period of time, or simultaneously or also over a period of time from multiple imaging sensors. The multiple measurements can be averaged together, or the multiple measurements can be subjected to a smoothing algorithm to determine the pixel or sub-pixel value. Each pixel or sub-pixel value can be determined independently, or can be determined via image processing of part or the entire image formed by multiple measurements in the array, and one or more algorithms, such as smoothing, edge detection, etc., can be applied to the multiple measurements. Camera 106 can be used to obtain video, including live or pre-recorded video. The camera can be an independent device owned by the customer, integrated into a device worn by the customer, or alternatively one or more devices pointed at the customer. In some embodiments, camera 106 can be a third-party device, such as a security camera feed, or a camera 106 in a device owned by an unrelated party. In such embodiments, face recognition and location tracking can be used to identify the customer. Other examples of camera 106 can include a camera 106 integrated into a smart home device, such as Google Home, an Alexa-enabled device, a doorbell with a camera, etc. Similarly, one or more cameras 106 can be integrated into a kiosk or otherwise present in a retail environment. Microphone 108 is an audio input device that detects sound waves and converts analog signals into digital data. Microphone 108 can be integrated into electronic device 102, a wearable device, or can be an independent microphone wirelessly or via a cable connected to the electronic device. Examples of microphones include capacitive microphones, dynamic microphones, electret microphones, etc. Microphone 108 can include a single audio pick-up, or can include multiple audio pick-ups. The microphone can be integrated into electronic device 102 or connected via a cable or wirelessly via communication interface 112. Data can be obtained from microphone 108 only when the customer directly interacts with electronic device 102, or the data may be continuously active, thus collecting data passively and continuously.In some embodiments, the microphone 108 may be integrated in a smart home device, such as a Google Home or an Alexa-enabled device. The input device 110 is any device for capturing input from a user, such as a keyboard, keypad, mouse, remote control, joystick, or an array of any other switches, dials, etc. arranged to receive input from a user. The input device 110 may additionally be configured to capture a gesture, for example, via a wearable device worn by the user or an image capture system for capturing and analyzing images and / or video to detect a gesture made by the user. The input device 110 may additionally include a touch screen interface, such as a capacitive, resistive, or pressure detection surface, which may or may not cover a screen capable of displaying content to the user, either on or below the screen. The input device 110 may also include a stylus. The input device 110 may be configured to receive direct customer input, such as personal information including demographics, preferences, etc. The input device 110 is typically used in combination with an electronic device 102, such as a mobile device, a desktop computer, a kiosk in a retail environment, etc. Data collected by the input device 110 may be stored in a customer database 118 and used as customer characteristics to train a recommendation model for recommending fragrances. The communication interface 112 provides a connection between one or more electronic devices 102 or components. The communication interface 112 may have a physical interface to accept cable connectors such as Ethernet cables, fiber optic cables, USB cables, etc., or may provide a wireless connection. To provide a wireless connection, the communication interface 112 will include an antenna to transmit and / or receive data via electromagnetic waves. The wireless connection may be established using any communication protocol, which is, for example, Wi-Fi, Bluetooth, infrared (IR), cellular (3G, 4G, 5G, LTE, etc.), near field communication (NFC), radio frequency identification (RFID), global positioning system (GPS), etc. In some embodiments, the communication interface 112 may utilize light to establish a physical connection, such as using a fiber optic cable or wirelessly via visible light communication using one or more lasers, etc. The cloud 114 is a network of distributed computing and data storage resources. The cloud 114 may be a public cloud, such as accessible via the Internet, or may be a private cloud, which may be isolated and not accessible via the Internet. Similarly, the cloud 114 may be widely accessible, or access may be restricted through encryption, authentication, etc. In some embodiments, the cloud 114 may be maintained by a third party, where resources are provided for one or more users and / or organizations. The fragrance database 116 stores data related to the names, descriptions, characteristics, ingredients, and chemical compositions of a variety of fragrances or compounds for adding fragrance and / or odor to products, such as perfumes, colognes, candles, air fresheners, shampoos, body washes, deodorants, personal care products, detergents, etc. The data may additionally include manufacturers and information related to the manufacture of the fragrances. The data may be populated by one or more manufacturers, suppliers, for example, via a third-party database connected through the cloud 114.The customer database 118 stores data about one or more customers. The data can include characteristics that generally describe the user, such as always applicable, or characteristics that conditionally describe the user, such as sometimes only applicable under certain conditions. General characteristics can include the customer's personality, genetic information, allergies, customer-stated preferences, etc., unless indicated as conditional. For example, genetic samples (e.g., DNA, etc.), genetic profiles, or other genetic information can be obtained from the user after the user's consent. The genetic information can be evaluated to identify genetic markers indicating allergies, pheromone preferences, odor preferences, etc. The resulting genetic profile can be used to prevent the presentation of potential allergens for the user or fragrances that the user may be genetically predisposed to dislike. The genetic information can be used in combination with chemical assays to determine the chemical composition of fragrances that can match the user's genetic profile. This can involve observing the decomposition of the fragrance to determine additional chemical substances or chemical reactions present during the lifespan of the fragrance after application. Conditional characteristics can include the customer's mood, occasion, location, or environment, etc. The customer database 118 is populated by the data collection module 126 and the feedback module 138, and can additionally be populated by one or more proprietary or third-party databases and one or more application programming interfaces (APIs). Examples of third-party data can include social media activity feeds from services such as Facebook, Twitter, TikTok, etc., as well as music and video streaming platforms such as Spotify, and dating applications and websites such as Tinder. In some embodiments, customer data can be stored in accordance with privacy and / or customer data retention policies and / or compliance with regulations such as the General Data Protection Regulation (GDPR). The event database 120 stores data related to one or more events, occasions, trigger conditions, etc. The data stored in the event database 120 can include historical data, such as events that have occurred in the past, such as trigger condition logs, one or more trigger condition tables that initiate actions when detected, such as the recommendation module 134. In some embodiments, the actions initiated by the detected trigger conditions can be the analysis module 130 and / or the parameter selection module 132. The event database 120 can additionally store and / or access data related to the schedule or calendar of one or more customers. The schedule or calendar can be obtained through the customer's personal computing device and operating system (e.g., computer or mobile phone), or can be obtained through social media sources such as Facebook. The event database 120 can additionally store data related to the customer's interactions with other individuals, objects, etc., and the data can include trigger conditions. The association database 122 stores data related to the relationship between one or more customer characteristics and one or more fragrances. The association data indicates one or more customer characteristic probabilities that predict the preferences of one or more customers for one or more fragrances. The association database 122 is populated by the analysis module 128 and used by the parameter selection module 130 and the recommendation module 134.The base module 124 activates the data collection module 126. The data collection module collects data from at least one data source including any one of sensors, cameras, microphones, input devices, third-party databases, proprietary databases, surveys, etc., and saves the collected data to the customer database 118. The base module 124 receives the collected data from the data collection module 126 and activates the analysis module 128. The analysis module 128 uses the collected data and the data stored in the customer database 118 and the fragrance database 116 to identify pairings of one or more associations or customer characteristics saved to the association database 122 with fragrances. The base module 124 receives the associations from the analysis module 128 and activates the parameter selection module 130. The parameter selection module 130 evaluates each association to determine whether the association is a strong predictor of preference for one or more fragrances, and the parameter selection is saved to the association database 118. The base module 124 receives the selected parameters from the parameter selection module 130 and activates the recommendation module 134, which creates and / or trains a recommendation model for generating one or more fragrance recommendations. The base module 124 receives one or more fragrance recommendations from the recommendation module 134 and activates the fragrance selection module 136. The fragrance selection module selects one or more fragrances from the recommended fragrances identified by the recommendation module 134. The base module 124 receives the selected fragrances from the fragrance selection module 136 and activates the feedback module 138. The feedback module 138 receives feedback from one or more customers and saves the feedback to the customer database 118. The base module 124 receives the customer feedback from the feedback module 138 and ends the recommendation process. The data collection module 126 collects data from at least one source including any input device 110, such as cameras, sensors, third-party or proprietary databases, etc. The data collection module 126 initializes the input device 110 and receives data from the device, which is then saved to the customer database 118. The analysis module 128 receives data from the customer database 118 and the fragrance database 116. The analysis module 128 selects customer characteristic data from the customer database 118 and fragrance data from the fragrance database 116, and identifies associations of pairings of customer characteristics and fragrances. In some embodiments, the associations are quantifiable, while in other embodiments, the associations are subjective or can be performed by human screeners. The associations are saved to the association database 122, and this process is completed for all combinations of customer characteristics and fragrances. The parameter selection module 130 receives data from the fragrance database 116 and the association database 122, and evaluates the ability of the association data to predict preference for each fragrance, for example, by comparing a quantified correlation coefficient with a threshold and selecting the correlation as a parameter. Alternatively, the association with the highest correlation coefficient can be selected as a parameter. These parameters will be used to create a recommendation model, which will be used to select one or more fragrances to recommend to one or more customers.The real-time data module 132 polls data from one or more sensors 104, cameras 106, microphones 108, or input devices 110 continuously or at regular short intervals, the time range of which can be seconds, minutes, hours, or days, and checks for trigger conditions. The trigger condition can be a specific sensor 104 measurement or set of measurements, one or more inputs from the input device 110, or a specific pattern, object, location, sound, person, etc. via at least one camera 106 and / or microphone 108, or a combination of patterns, objects, sounds, etc. Alternatively, a timeout can be used to end the monitoring performed by the real-time data module 132 after a specified amount of time has elapsed, regardless of whether a trigger condition has been detected. When a trigger condition has been detected, the real-time data module 132 saves the trigger data to the event database 120 and returns the trigger data to the base module 124. The recommendation module 134 receives the selected parameters determined by the parameter selection module 130 and data from the customer database 118 to train a recommendation model. In an embodiment, the recommendation model can be a machine learning model. In an alternative embodiment, the recommendation model can include a lookup table, decision tree, etc. The recommendation model is then used to generate recommendations based on the various available fragrances stored in the fragrance database 116, and the recommendations can include preference scores representing the probability of a customer having a positive reaction to a fragrance. The recommendations can include a set or combination of fragrances, fragrance categories, etc. The fragrance selection module 136 receives the multiple recommendations generated by the recommendation module 134, and also receives data from the fragrance database 116 and the customer database 118 for selecting one or more fragrances. Additionally, customer characteristics, preferences, or other weightings can be considered when selecting one or more fragrances. The feedback module 138 receives the selected fragrances and sends a feedback request to the customer. The feedback request can be included in a sample of the recommended fragrances. Alternatively, the feedback request can include a digital survey request. The feedback module 138 further receives feedback from one or more customers, and the feedback can include completing a survey, or can include behavioral cues such as purchasing a product containing one or more of the recommended fragrances, returning a product containing a fragrance, recommending a fragrance or a product containing a fragrance to a social connection, or performing a facial analysis of the customer's reaction when using or encountering a fragrance or a product containing a fragrance. In an example, one or more fragrances can be recommended based on the identification and recognition of the user's emotional state. The emotional state can be identified based on facial expressions, postures, intonations, message context, biometric information such as heart rate and blood pressure, skin conductance responses, etc.

[0025] Reference will now be made to Figure 2Explain the functions of the "Fragrance Database". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0026] This figure shows the fragrance database 116. The fragrance database 116 stores data related to one or more fragrances. The data includes at least the fragrance name and a unique identifier or ID. The fragrance database 116 may additionally include descriptions, characteristics, ingredients, and chemical compositions of various fragrances or compounds for adding fragrance and / or odor to products such as perfumes, colognes, candles, air fresheners, shampoos, body washes, deodorants, personal care products, detergents, etc. The data may additionally contain information about manufacturers, brands, and supplier information, as well as information related to the manufacture of fragrances, including manufacturing process steps. The data in the fragrance database 116 can be populated by one or more fragrance manufacturers, suppliers, etc., and used by the analysis module 128, parameter selection module 130, recommendation module 134, and fragrance selection module 136.

[0027] Now refer to Figure 3 Explain the functions of the "Customer Database". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0028] This figure shows customer database 118. Customer database 118 stores data about one or more customers. The data may include identifiable information such as name, phone number, email address, home address, etc., and may include characteristics that describe the user. In addition to regulations such as the General Data Protection Regulation (GDPR), customer data, especially personally identifiable information, should also be stored in accordance with privacy and customer data retention policies. Such policies and regulations may require customer consent before the data is captured, stored, or sent to a server for analysis. In some embodiments, data may be collected and stored locally on the customer's private device without permission, but such permission may still be required before analyzing the data obtained. Without receiving the customer's consent, the data obtained by analyzing the private device (including but not limited to the analysis results) may not be sent outside the device. In some embodiments, consent may be implicit, such that presenting a message to the user that continued use of the device and / or program is considered consent to use their personal information, while in other embodiments, consent is explicit and requires the customer to make a choice to confirm or decline consent. Examples of characteristics may include gender, hobbies, personality traits, fragrance preferences, items purchased, feedback related to the products purchased, etc. The data may additionally include information such as genetic information, allergies, non-fragrance preferences, mood, personality, response to stimuli, occasions of interest, locations, environments, etc. Customer characteristics may additionally depend on the presence of other customers, social media contacts associated with the customer, venues, etc., such that the user's fragrance preference or choice may be influenced by other customers, locations, etc. Customer characteristics may also include innate information about the customer, such as part or all of their genome, genetic code, physical characteristics, etc. Some customer characteristics, such as personality, mood, response, etc., may be determined based on the analysis of other customer characteristics such as facial features, tone of voice, etc. In an example, a user's personality may be analyzed based on preferences and measurable metrics to identify personality types and / or personality traits. Then, the personality trait data may be used to recommend one or more fragrances to the user. These features may be directly used as customer characteristics and / or may be used to derive intermediate customer characteristics such as personality, mood, response, etc. Customer database 118 is populated by data collection module 126 and feedback module 138, and may additionally be populated by one or more proprietary or third-party databases and / or application programming interfaces (APIs). Examples of connected third-party data sources may include social media networks, vendor websites, search engines, web tracking and advertising services, etc. Customer database 118 is used by analysis module 128, recommendation module 128, and fragrance selection module 136. In some embodiments, customer database 118 may additionally be used by feedback module 138 to determine where to send feedback requests, such as customer satisfaction surveys and additional promotions.In an example, one or more samples can be selected for sending to a user based on a plurality of parameters determined according to data collected about the user. The data can be provided by the user, collected from passively monitoring the user, and so on. Then samples are selected from a database and sent to the user for evaluation. The user can additionally provide feedback based on their experience and response to the provided samples. Additional fragrances can be recommended based on the feedback received from the user. In an example, multiple fragrances can be selected with the aim of sending multiple fragrances to a customer rather than a single fragrance. As part of the recommendation, one or more fragrances can be automatically provided to the customer, such as a portion of a sample, to allow the customer to evaluate the one or more fragrances. In an example, the customer can be provided with an opportunity to purchase one or more fragrances. In an example, one or more fragrances can be purchased as a gift. In an example, one or more fragrances can be presented to the user as a notification, such as via an email, SMS message, application notification, etc. The notification or purchase opportunity can additionally include a purchase incentive, such as a discount, rebate, money-back guarantee, etc. In a preferred embodiment, one or more fragrances are selected and provided according to parameters and / or recommendations customized based on the available customer characteristics of the customer.

[0029] Reference will now be made to Figure 4 explain the function of the "event database". Those skilled in the art will understand that for this and other processes and methods disclosed herein, the functions performed in the processes and methods can be implemented in a different order. Additionally, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0030] This figure shows the event database 120. The event database 120 stores data related to one or more events, occasions, trigger conditions, etc. The data stored in the event database 120 may include historical data, such as events that have occurred in the past, such as trigger condition logs, one or more trigger condition tables that initiate actions when detected, such as the recommendation module 134. In some embodiments, the actions initiated by the detected trigger conditions may be the analysis module 130 and / or the parameter selection module 132. The event database 120 may additionally store and / or access data related to the schedules or calendars of one or more customers, including those schedules or calendars provided by third parties. The event database 120 may additionally communicate with social media services to access events, including the time and location of the events. The event database 120 may additionally store data related to the interactions of the customer with other individuals, objects, etc., and the data may include trigger conditions. The event database 120 is populated by the data collection module 126, the real-time data module 132, the analysis module 130, and the parameter selection module 132, and may additionally be populated by the feedback module 138. The event database is used by the real-time data module 132, the analysis module 130, and the parameter selection module 132, and may additionally be used by the fragrance selection module 136.

[0031] Now reference will be made to Figure 5 explain the function of the "association database". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method may be implemented in a different order. Additionally, the steps and operations outlined are provided only as examples, and some of these steps and operations may be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0032] This figure shows the association database 122. The association database 122 stores data related to the relationship between one or more customer characteristics and one or more fragrances. The association data indicates the degree to which one or more customer characteristics are associated with one or more fragrances, such as indicated by a correlation coefficient. Other descriptors of the association may be descriptive rather than quantitative, such as high, medium, or low. Other examples may include unlikely, slightly unlikely, irrelevant, slightly likely, or likely to have a predictive association, such that the customer characteristics may indicate or be used to predict a preference for one or more fragrances. The association may additionally include information indirectly related to the customer's characteristics, preferences, etc., such as the fragrance preferences of one or more additional customers near the first customer. For example, the fragrance preference or selection of the first customer may be influenced by the preferences of other customers in the vicinity. Although described or referred to as customers, the other customers may not be current or potential customers. The association database 122 is generated by the analysis module 128 and used by the parameter selection module 130.

[0033] Now, reference will be made to Figure 6 explain the functions of the "basic module". Those skilled in the art will understand that for this process and method disclosed herein and other processes and methods, the functions performed in the process and method can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0034] This figure shows the base module 124. The process begins with starting the data collection module 126 at step 602. The data collection module 126 initializes the sensors 104, camera 106, microphone 108, and other input devices 110, and polls the initialized devices to obtain data. The data collection module 126 additionally accesses third-party data such as from social media and prompts the user to provide direct input via at least the input device 110. The data is saved to the customer database 118. At step 604, the collected data is received from the data collection module 126. The data can be collected from any one of the one or more sensors 104, camera 106, microphone 108, input devices 110, or third-party sources, which are private or proprietary databases owned and maintained by, for example, social media companies. At step 606, the analysis module 128 is started. The analysis module 128 queries the customer database 118 and the fragrance database 116 and selects a first fragrance and a first customer characteristic. The correlation between the first fragrance and the first customer characteristic is calculated and / or the association therebetween is identified, and the calculated correlation and / or the identified association is saved to the association database 122. It is further determined whether there are more customers, and if there are more customer characteristics available for analysis, a second customer characteristic is selected, otherwise it is determined whether there are more fragrances available. If there are more fragrances available, a second fragrance to be analyzed is selected. At step 608, when all customer characteristic and fragrance combinations have been analyzed, the analyzed data including the correlation and / or the identified association is received from the analysis module 128. The resulting data can be quantitative, such as a correlation coefficient representing the likelihood that one or more customer characteristics are predictors of preference for one or more fragrances, or can be a more general association between a customer characteristic and a fragrance. At step 610, the parameter selection module 130 is started. The parameter selection module 130 queries the fragrance database 116 and the association database 122 and selects a first fragrance and a first association, for example, by comparing the correlation coefficient with a threshold. Alternatively, the association between a customer characteristic and a fragrance can be identified by a method that does not rely on statistical principles involving subjective ratings. The strength of the association can be evaluated, and the context of the association can additionally be considered such that the combination of multiple associations can increase the predictive relevance of the association. If the correlation coefficient is higher than the threshold, or the association is found to be a sufficient predictor of fragrance preference, the correlation or the association is selected as a parameter. If there are more associations, a second association is selected, otherwise if there are more fragrances, a second fragrance is selected. At step 612, the selected parameters are received from the parameter selection module 130. The selected parameters include the correlation and / or the association representing the pairing of a customer characteristic and a fragrance, which has a high likelihood of accurately predicting a customer's preference for one or more fragrances. At step 614, the real-time data module 132 is started.The real-time data module 132 receives the selected parameters from the base module 124 and queries the event database 120 to obtain one or more trigger conditions. The real-time data module 132 polls one or more sensors 104, cameras 106, microphones 108, input devices 110, and external data sources in real time (or at regular intervals) to obtain additional data and determines whether a trigger condition is detected in one or more data streams. Optionally, the real-time data module 132 may check whether a timeout value, such as a predefined amount of time, has elapsed without identifying a trigger condition in the received real-time data and return to the base module 124 in the case of reaching the timeout value, or otherwise continue polling the sensors 104 and accessing external data. If a trigger condition is identified, the trigger data is saved to the event database 120 and the trigger data is returned to the base module 124. At step 616, the trigger data is received from the real-time data module 132. The trigger data includes at least one trigger condition, which may be an event, occasion, detected object, person, odor, environmental attribute, etc., which may represent a change in at least one customer characteristic, which may generate a new fragrance recommendation. For example, a trigger condition is received that includes detecting that a customer plans to attend an upcoming music event based on a Facebook calendar update. At step 618, the recommendation module 134 is launched. The recommendation module 134 queries the customer database 118 and the fragrance database 116 to obtain data related to the selected parameters and uses the data including the relevant customer characteristics and fragrances to train the recommendation model. The recommendation module 134 may additionally receive trigger data. In some embodiments, the recommendation model may be a lookup table or a decision tree. The recommendation model is also used to generate one or more fragrance recommendations. At step 620, one or more fragrance recommendations are received from the recommendation module 134. The recommendations may include one or more fragrances, fragrance series, or fragrance groups that share common characteristics. At step 622, the fragrance selection module 136 is launched. The fragrance selection module 136 queries the fragrance database 116 and the customer database 118 to obtain the recommended fragrance data and additional customer data, such as customer input and feedback, and selects one or more fragrances from the recommended fragrances. At step 624, one or more selected fragrances are received from the fragrance selection module 136. At step 626, the feedback module 138 is launched. The feedback module 138 receives one or more selected fragrances and optionally requests feedback from one or more customers. Customer feedback is received by direct or indirect methods, such as by providing surveys or monitoring sales activities, and the customer feedback is saved to the customer database 118. At step 628, the customer feedback is received from the feedback module 138. The customer feedback includes data that explicitly or implicitly indicates one or more preferences for one or more fragrances. At step 630, the fragrance recommendation process ends.

[0035] Reference will now be made toFigure 7 Explain the functions of the "data collection module". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method can be implemented in a different order. In addition, the outlined steps and operations are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0036] This figure shows the data collection module 126. The process begins with receiving a prompt to start data collection from the base module 124 at step 702. The prompt can be an automated or manual action to initiate data collection from one or more customers. The data collection can be prompted by customer actions such as registering on a website, purchasing a product containing an aromatic, etc. At step 704, one or more sensors 104 are initialized for data collection. Initialization includes powering on the sensor 104 device and can additionally include a handshake where signals are sent to the sensor 104 and a response is received to confirm that the sensor 104 is powered on and ready to collect data. The sensor can additionally refer to the camera 106, microphone 108, or any other input device 110. In an embodiment, a connection is established with the sensor 104 in a mobile phone, which includes the accelerometer, microphone, camera, etc. of the phone. At step 706, one or more of the sensors 104, camera 106, microphone 108, input device 110, etc. are polled to obtain data input. In an embodiment, the accelerometer can collect location and movement data from the customer. In another embodiment, the microphone 108 can collect audio data containing the customer's voice, which can later be analyzed to determine the customer's mood. Similarly, camera 106 data can be collected. Additional embodiments can collect data from the sensor 104, which is configured to detect and analyze the composition of volatile compounds to determine the fragrance present when collecting data about the customer. Similarly, location data can be used to determine the customer's location in a store and to determine near which fragrance products or aromatic samples the customer may be when collecting data that can be used to measure the customer's reaction. In an embodiment, at least one camera 106 oriented towards the customer captures at least one image of the customer when presenting at least one aromatic to the customer, such that the at least one image includes a facial expression in response to the at least one aromatic. In other embodiments, there is no aromatic, but the customer can be prompted to follow instructions to make an expression, which is captured by at least one camera 106. Such image data can later be used to identify reactions, moods, or personalities, which can be evaluated as potential predictors of aromatic preference. In another embodiment, the camera 106 captures the customer's image data for facial feature analysis, such as shape, features, and spacing, etc., which can be correlated with a set of personality traits and further used as a potential predictor of aromatic preference. Similarly, one or more microphones 108 can be used to collect audio samples of the customer's voice, the audio can be processed on the audio samples, and the tone of the customer's voice can be analyzed to indicate reactions, moods, or personalities, which can be evaluated as potential predictors of aromatic preference. In another embodiment, the customer can provide passive data via a wearable device containing at least one sensor 104, which can provide real-time data continuously or at regular intervals.The customer can also submit data via one or more input devices 110, for example, by following prompts and answering questions on a touch screen or by entering data via a keyboard and / or mouse. In some embodiments, the data collected may additionally include data related to one or more customers or individuals near the customer. For example, a customer may be near another individual, and data related to both the customer and the other individual may be collected. This may require prior association, such as sharing contact information between the electronic devices 102 carried by the two individuals, or the individuals being friends or contacts on one or more social media platforms such as Facebook. At step 708, sensor 104 data is received from the sensor 104. The sensor 104 data can be temporarily stored in batches or groups in the sensor 104 device and sent to the electronic device 102, or can be streamed continuously. The method of data transmission may depend on the network connectivity at the time of data collection, such that when the network connection to the electronic device 102, the Internet, or the cloud 114 is poor or there is no network connection, the data is stored on the local sensor 104 device and then sent when the network connection is available. Similarly, when the network connection is available, the data can be streamed in real time. In an embodiment, the electronic device 102 has a reliable connection with at least one sensor 104, such as an accelerometer, and receives data in real time. In an embodiment, image data is received in real time from at least one camera 106 oriented towards the customer's face, thereby capturing facial expressions. A microphone 108 can additionally be used to collect the customer's voice. In some embodiments, the sensor 104 can be used to detect volatile compounds in an aroma, which can allow the determination of the aroma. At step 710, third-party data is accessed from one or more third-party data sources. The third-party data can include connected devices, which include multiple sensors 104, cameras 106, microphones 108, and input devices 110. The third-party data sources can additionally include databases owned and managed by third parties, such as those managed by social media providers. This data is typically available via an application programming interface (API), which allows external applications to access information or services. Alternatively, web scraping can be used to access similar information. In an embodiment, the data collection module 126 accesses social media data from Facebook and Twitter, determines friends, followers, and people the customer follows, and additionally collects public posts that mention or tag the customer made by the customer and the customer's friends, followers, etc. The social media data can additionally include products and services that the customer has liked or otherwise expressed interest in. The social media data can additionally include engagement data for one or more customers, such as likes, posts, shares, comments, etc.It is possible to analyze the sentiment of the published content to determine whether the user's comment is positive or negative, which can be directly related to the fragrance, products containing fragrances, or alternatively related to other data such as interests, hobbies, etc., which can be used independently or to identify the customer's personality. When accessing real-time data, recent social media data can be used to determine the customer's sentiment, and in some embodiments, indicators of more chronic psychological problems such as anxiety, depression, etc. can be identified. Social media data can additionally include data related to the fragrance preferences of the customer's friends or contacts, especially when the customer is close to the customer's friends or contacts compared to when the customer is not close to those individuals, the customer's fragrance preference or selection is different. Data can additionally be obtained from music or video downloads and / or streaming services, dating services, etc. Third-party data can also include sales and return data of fragrances and clothing, cosmetics, personal care products, etc. from one or more suppliers. Such data can be obtained from retailer or manufacturer CRM. Third-party data can include genetic and / or medical data from genetic testing service providers such as 23andMe or from healthcare providers. In some embodiments, genetic data can be utilized such that the gene sequence can be used as a customer characteristic, which can be associated with one or more fragrances. Similarly, the gene sequence or other medical data can reveal medical information such as allergies, which can allow for recommendations to prevent the recommendation of fragrances that may cause allergic reactions and can be used to notify the customer of products that may cause adverse reactions. Access to sensitive data such as genetic information and / or medical health records may require the customer's explicit consent to access such records. Such records may additionally be subject to additional regulations and security protocols. Third-party data can further relate to location, geography, climate, weather, and calendar data, including data from public and private calendars. Examples of geography can include data obtained via the customer's physical location (such as a mall, airport, or retail store) through wireless communication (Wi-Fi, Bluetooth beacons, etc.). Examples of weather can include the weather forecast of the customer's location, which can include temperature, humidity, precipitation, wind, etc. Environmental data that is typically only related to the customer based on the customer's location can be processed similarly to customer characteristics such that the known environment of an individual can at least affect their mood in some cases and can therefore be used with the same capabilities as conditional customer characteristics. Similarly, environmental data such as temperature, humidity, etc. can affect the way fragrances are perceived or made to last in the environment. In an embodiment, environmental data can be used to determine the lifespan of a fragrance, and the user can receive a notification when a fragrance such as perfume should be reapplied. Examples of calendars can include personal or work calendars in mobile device applications, productivity suites such as Google or Office365, or public or social calendars such as those on community web pages, social networks such as Facebook, etc.In an embodiment, a database connected to a retailer is accessed and it is confirmed that a female customer with customer ID 27046 has purchased Her Eau de Parfum. At step 712, the user or customer is prompted for input. The input prompt can include a text message, instructions on a kiosk, a mobile device screen, a website, etc., and user input can be provided via input device 110. User input can alternatively or additionally be provided by one or more sensors 104, cameras 106, microphones 108, etc. For example, the prompt can ask the customer to read text aloud or verbally instruct their response to be received via the microphone. In an alternative embodiment, an image or an aroma can be provided to the user and their reaction can be captured via one or more cameras 106. Further embodiments can include completing a survey via a keyboard input device 110. The input prompt for the user can additionally include a real-time video interaction between the customer and a video recording, or with live or dynamically generated content, or a real-time video interaction using a pre-recorded video feed. In some embodiments, the user input can prompt the customer to provide information about one or more individuals (such as the customer's friends or contacts, or other customers for whom the customer may be purchasing an aroma). This data about individuals other than the customer can be used in situations such as finding gift recommendations, or can be used to determine the aroma preferences of other individuals in order to identify an impact on the customer's preferences when in proximity to or anticipating proximity to the individual. For example, the customer may prefer an aroma that is preferred by both the customer and another individual or the customer when in their proximity, while when not in proximity, the customer may prefer a different aroma. At step 714, the data collected by data collection module 126 is saved to customer database 118. At step 716, the process returns to base module 124.

[0037] Reference will now be made to Figure 8 explain the functionality of the "analysis module". Those skilled in the art will understand that for this and other processes and methods disclosed herein, the functions performed in the processes and methods can be implemented in a different order. Additionally, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or expanded into additional steps and operations without departing from the essence of the disclosed embodiments.

[0038] This figure shows the analysis module 128. The process begins with receiving a cue at step 802 from the base module 124. The cue may contain customer data collected from the data collection module 126. The cue may additionally contain instructions to perform an analysis on all data, only newly collected data, or only data related to a specific customer. At step 804, the customer database 118 is queried to obtain customer characteristic data from at least one customer. The data may additionally include customer feedback data, such as the customer's fragrance preferences, including the fragrances they like and the fragrances they dislike, and may additionally include a quantifiable score, such as the customer rating the fragrance with ID 11 as 7 out of 10. Examples of customer characteristic data may include an image of the customer's face, including when the customer reacts to a specific fragrance. The data may include voice and / or video recordings of the customer's response to the cue. Customer characteristics may additionally include hobbies, personality traits, their gender, location, places visited, purchase history, etc. Any data that can be used to describe the customer, their preferences, behavior, etc. can be used as customer characteristics. The customer data may be aggregated data or may be specific to an individual customer. At step 806, the fragrance database 116 is queried to obtain one or more fragrances. The fragrance data may contain a specific fragrance, but may also contain its characteristics, ingredients, etc., such that the analysis of the customer characteristics paired with the fragrance can alternatively be performed between fragrance characteristics and / or ingredients. This allows for more generalized comparisons and recommendations rather than just explicit comparisons. In some embodiments, both explicit data and general data are used to allow for the identification of a range of related or similar fragrances from which a recommendation can be selected for the customer. At step 808, a fragrance, fragrance characteristic, or fragrance ingredient is selected from the data retrieved from the fragrance database 116. In an embodiment, the fragrance with ID 11, namely Her Eau de Parfum, is selected. In some embodiments, the fragrance may be selected based on environmental data such as volatile compounds in the air (which may be components of the fragrance). These volatile compounds can be detected and used to identify fragrances near the customer. Then, the detected fragrances can be analyzed to identify an association between the detected fragrances and one or more customer characteristics (such as an image from the camera 106 capturing the customer's reaction to the detected fragrance). At step 810, a customer characteristic is selected from the customer data retrieved from the customer database 118. In an embodiment, the customer characteristic is an image of the customer taken when the customer samples the fragrance with ID 11. The customer may have switched to sampling a different fragrance than the selected fragrance. Alternatively, the customer characteristic may be unrelated to the fragrance, such as the user's personality, mood, favorite food, favorite activity, etc. In another embodiment, an adventurous personality is selected as the customer characteristic. In some embodiments, the customer characteristic may include a customer category or group, which may be characterized by one or more customer characteristics.For example, people with an adventurous personality, or a preference for fruity fragrances, or those who like specific activities such as hiking. Other groupings can relate to demographics, habits, music preferences, clothing, hairstyle or cosmetic style preferences, preferred reading types, etc. In some embodiments, customer characteristics can include the mood or emotional state of the customer. The emotional state of the customer can be identified based on facial expressions, posture, tone of voice, message context, or biometric information (such as heart rate, blood pressure, skin conductance response, EKG, etc.). The emotional state can be identified using a method similar to personality through one or more algorithms that include machine learning. In some embodiments, genetic data can be utilized such that the gene sequence can be used as a customer characteristic. Alternatively, medical history data such as allergies, medications, chronic diseases, etc. can be utilized. In other embodiments, social media data can be used as a customer characteristic. Examples can include the activities a customer participates in, such as the pages viewed, the activities and events responded to, customer check-ins, the locations where comments are written, etc., the comments liked by the customer, follows, shares, etc. The content of the customer, including posts, comments, etc., can additionally be analyzed via context analysis to determine the customer's mood, including whether the post or message indicates a positive or negative comment, or a suggestion for a fragrance or a product containing a fragrance. In an embodiment, a Facebook user can share a post about a perfume and can additionally "like" and post a comment that contains positive words indicating a positive emotion that can be a recommendation or support for the product. In some embodiments, multiple customer characteristics can be selected combinatorially. Similarly, the same customer characteristics can be included in multiple different combinations. At step 812, an association between the selected customer characteristics and the selected fragrance is identified. In an embodiment, the association is determined by calculating a correlation coefficient that represents the probability that the selected customer characteristic is a predictor of the customer's preference for the selected fragrance. In some embodiments, such as those utilizing machine learning or another automated algorithm, the correlation coefficient can be a quantifiable statistical relationship, such as the Pearson correlation coefficient, which determines the dependence of one variable (in this case, the selected customer characteristic) on a second variable (in this case, the selected fragrance) by comparing data from a large customer sample. In alternative embodiments, such as those using decision trees or lookup tables, a more generalized association between the selected fragrance and the selected customer characteristics can be identified, such as that people with specific customer characteristics are more likely or less likely to purchase a specific fragrance. In some embodiments, the association can be determined based on manually or digitally collected interviews to determine customer preferences and create an association definition based on subjective or other analysis of the collected data. In an embodiment, the association can include gender (such as the customer being female) and the associated fragrance Her Eau de Parfum. In another embodiment, the customer characteristic preferences for a fruity fragrance are identified and associated with the fragrance My Burberry Eau de Toilette.In some embodiments, multiple customer characteristics may be considered together, such as a woman with a captivating personality who may be associated with the fragrance Her Eau de Parfum. Association represents a potential predictive relationship between one or more customer characteristics and one or more fragrances. Another example of an association may use the customer's genetic sequence, for example to identify an allergy to a component of one or more fragrances, or to aggregate customer preferences associated with one or more genetic sequences. In some embodiments, environmental data may be used as a customer characteristic, such as a factor that may affect the customer's mood. Similarly, an increase in temperature may increase the volatility of a fragrance, which may cause it to be overpowering at warm temperatures, so there may be an association between temperature and the fragrance. In some embodiments, an association may include one or more customer characteristics and may additionally include non-customer data, which may be considered a customer characteristic, such as environmental data. An additional example of non-customer data that may be considered a customer characteristic is an event or occasion. An association may be established between a fragrance and an event, and the association may be further combined with other customer characteristics. The customer characteristics and / or fragrance preferences of one or more friends or contacts identifiable on a social media platform or via other means such as phone or email contacts may be considered customer characteristics when identifying an association, such that when a friend or contact is near the customer, they apply to the customer's own fragrance preferences. For example, an association may include the customer's preference for a fragrance when near a Facebook friend. At step 814, the association is saved to the association database 122. At step 816, it is determined whether there are more customer characteristics to be analyzed. In an embodiment, there are additional customer characteristics to be analyzed, such as the customer's preference for kayaking. Since there are more customer characteristics, return to step 710 and select another customer characteristic. In an alternative embodiment, there are no additional customer characteristics to be analyzed. At step 818, it is determined whether there are more fragrances to be analyzed. In an embodiment, there are additional fragrances, fragrance characteristics, ingredients, etc. to be analyzed, such as the fragrance Brit For Her Eau de Parfum with ID 173. Since there are more fragrances to be analyzed, return to step 708 and select another fragrance. In an alternative embodiment, there are no additional fragrances to be analyzed. At step 820, return to the base module 124.

[0039] Reference will now be made to Figure 9 explain the functionality of the "parameter selection module". Those skilled in the art will understand that for this process and method disclosed herein, as well as other processes and methods, the functions performed in the process and method may be implemented in a different order. Additionally, the steps and operations outlined are provided only as examples, and some of these steps and operations may be optional, combined into fewer steps and operations, or expanded into additional steps and operations without departing from the essence of the disclosed embodiments.

[0040] This figure shows the parameter selection module 130. The process begins with receiving a prompt from the base module 124 at step 902. The prompt can include the associated data created by the analysis module 128. The prompt can additionally include instructions related to the type of recommendation engine to be created, for example, whether it will be used for a related fragrance group or alternatively when a certain type of customer characteristic (such as an interest in outdoor activities) is identified. At step 904, the fragrance database 116 is queried to obtain one or more fragrances, fragrance characteristics, ingredients, etc. At step 906, the association database 122 is queried to obtain at least one correlation or association between one or more fragrances, fragrance characteristics, ingredients, etc. and one or more customer characteristics. The association can be a correlation coefficient or any other number that quantifies the relationship between the fragrance and the customer characteristic or the probability that the customer characteristic is a predictor of the customer's preference for the fragrance. The association can additionally be a non-numeric representation of the relationship between the customer characteristic and the fragrance, fragrance characteristics, ingredients, etc. The association can include feedback from one or more customers, which can increase or decrease the strength of the association. The feedback can be considered via the use of a regression model such that the greater the amount of positive feedback, the more strongly a given customer characteristic can be associated with the fragrance. At step 908, a fragrance, fragrance characteristic, or fragrance ingredient is selected from the data retrieved from the fragrance database 116. In an embodiment, the fragrance with ID 11, i.e., Her Eaude Parfum, is selected. At step 910, a correlation or association is selected from the data retrieved from the association database 122. The association includes at least the customer characteristic and the identified relationship with the selected fragrance. The identified relationship can include an indication of the strength of the relationship, which can be quantitative, for example, in the case of a correlation coefficient, ordinal (such as ranking), or subjective, including descriptors such as low, medium, or high. At step 912, it is determined whether the association is greater than a threshold. In an embodiment, it is determined whether the correlation coefficient is higher than the threshold. The threshold can be selected by the system administrator and then used to determine whether the customer characteristic represented by the correlation coefficient should be selected as a parameter. If the correlation coefficient is higher than the threshold, this association can be selected as a parameter, otherwise it will not be selected as a parameter. In some embodiments, a selected number of associations, for example, up to 100, will be selected. In other embodiments, the maximum percentage, for example, up to 10% of the associations by correlation coefficient, will be selected as parameters. In an alternative embodiment, instead of using the correlation coefficient, a more generalized association can be used. For example, an association can be selected such that customers who like kayaking tend to prefer the fragrance with ID 11, Her Eau de Parfum, while the same group does not tend to prefer the fragrance with ID 174, Brit For Her Eau de Toilette.These associations can be identified by directly observing individual customers, such as by receiving survey responses indicating that they dislike such fragrances and other such feedback, or can be aggregated based on customer input and feedback from a large set of collected data. Data can be collected from first-party sources (such as a mobile device belonging to the customer or a kiosk in a retail environment) or can be obtained from one or more third-party sources. Third-party sources can include databases, APIs, and other sources of stored or streamed data, including social media networks. Social media data can be used to identify customers' interests, such as their liking for kayaking, based on their responses to kayaking activities, having multiple photos of themselves kayaking or multiple photos tagged with them on their profiles, and engagement related to kayaking, including liked, commented on, and shared posts. Social media data can be used to increase or decrease the strength of associations that have already been identified by other means (such as by increasing their relative weight). In the case of aggregated data, an association can be identified if more than half of the relevant customers, such as customers identified as liking kayaking, like the fragrance with ID 11. If less than half of the customers in the same group indicate that they prefer this fragrance, no association is identified. The threshold can be moved, and in some cases, can be subjectively evaluated and assigned by a human screener. Other algorithms can be used to determine such associations. When associations are identified, they can be selected as parameters, otherwise they can be ignored. In some embodiments, associations can include multiple customer characteristics and / or fragrances. At step 914, if the correlation coefficient of a customer characteristic is higher than a threshold, or if there are sufficiently important associations that will be selected by manual selection or other selection algorithms or criteria, then the customer characteristic represented by the correlation or association is selected as a parameter. For example, "likes kayaking" is selected as a parameter, which can be used to identify customers who prefer the fragrance with ID 11. In some embodiments, a single parameter can be used to make recommendations. In other embodiments, multiple parameters can be used, such as in a decision tree or a lookup table. In additional embodiments, parameters can be selected for training a machine learning algorithm or modifying the weighting of a weighting value table or process to generate fragrance recommendations. In some embodiments, parameters can include personality traits, moods, reactions, etc., which can indicate a preference for the selected fragrance. Selecting parameters and fragrances can include adding personality traits, moods, reactions, etc. to a lookup table associated with the selected fragrance, or alternatively can adjust the value weighting for determining whether to recommend the fragrance based on the parameter. Parameters can be identified based on data of a single customer, or alternatively can be identified based on aggregated customer data. In such embodiments, customers can be grouped into multiple categories such that customers in the same group share similar or identical characteristics, such as personality, interests, hobbies, style preferences, etc. It should be noted that parameters can be identified and selected independently or in combination with one or more additional parameters.At step 916, it is determined whether there are more associations to be analyzed. In an embodiment, there are additional associations to be analyzed, so it returns to step 810 and another correlation or association is selected. In an alternative embodiment, there are no additional correlations or associations to be analyzed. At step 918, it is determined whether there are more fragrances to be analyzed. In an embodiment, there are additional fragrances, fragrance characteristics, ingredients, etc. to be analyzed, such as the fragrance Brit For Her Eau de Parfum with ID 173. Since there are more fragrances to be analyzed, it returns to step 808 and another fragrance is selected. In an alternative embodiment, there are no additional fragrances to be analyzed. At step 920, the selected parameters are returned to the base module 124.

[0041] Reference will now be made to Figure 10 explain the function of the "real-time data module". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0042] This figure shows the real-time data module 132. The process begins with receiving selected parameters from the base module 124 at step 1002. The selected parameters can include one or more trigger conditions or parameters to monitor changes. At step 1004, the event database 120 is queried to obtain one or more trigger conditions. The trigger conditions can include any of the following: a scheduled event, proximity to a person, location, or object, detection of environmental factors such as temperature, humidity, fragrance, precipitation, etc. The trigger conditions can additionally include activities performed or expected to be performed by the customer or detected personality traits, moods, or changes in personality traits or moods. The trigger conditions indicate that a fragrance should be recommended and / or selected. In an embodiment, the trigger condition can include the contact John Smith of the customer Jane Doe, which is detected within 100 feet of each other based on the locations of their respective mobile devices, and thus the trigger condition is met when the two mobile devices are positioned less than 100 feet apart. In an alternative embodiment, the trigger condition can be a scheduled event. For example, the trigger condition for the customer John Smith can be whether the time is within 30 minutes of the scheduled meeting with Jane Doe. Other trigger conditions can include detection of a sound such as a song, or the customer's posture or facial expression, which can indicate an emotion or mood such as happiness or sadness. At step 1006, one or more sensors 104, cameras 106, microphones 108, input devices 110, etc. are polled to obtain data. The sensors 104 are polled continuously or at regular intervals to collect data about one or more customers. The sensors 104, cameras 106, microphones 108, etc. can be standalone devices, or can be integrated into an electronic device 102 (such as a mobile phone, tablet, wearable device such as a smartwatch or fitness tracker), or can be external to the customer. The sensors 104, cameras 106, microphones 108, etc. can belong to a third party, such as in the case of a security camera or weather station. In some embodiments, third-party data sources can also be polled to obtain data such as calendars, social media feeds, news websites, etc. Similarly, the time can also be monitored to detect proximity to the start time of a scheduled event. At step 1008, data is received from one or more sensors 104, cameras 106, microphones 108, input devices 110 or additional data sources such as calendars, social media services, news feeds, weather updates, etc. The data can include data actively collected, such as providing a prompt or instruction to the customer to provide information, for example, by the input device 110. In an ideal embodiment, the data is mainly collected via passive means, such as monitoring one or more data streams from one or more sensors 104, cameras 106, microphones 108, input devices 110 or connected data sources. The sensor 104 data can include biometrics such as heart rate, blood pressure, respiratory rate, skin conductance response, body temperature, etc.The sensor 104 can additionally detect position and / or movement, for example via the Global Positioning System (GPS), accelerometer, etc., or detect fragrances, for example via assays, mass spectrometry, etc. The camera 106 data can come from one or more cameras 106 belonging to the customer or one or more third parties such as other customers, security cameras, kiosks, etc. The camera 106 can be used to collect information including face tracking, posture, eye tracking, and can additionally be used to infer the customer's personality and / or mood. In some embodiments, the customer's preferences can be inferred based on the demonstrated interest in products containing fragrances, such as can be demonstrated by subtle cues such as their gaze being drawn to such products, and can be further paired with the customer's reactions observed via facial analysis or body language to identify a positive reaction to the fragrance. Additionally, one or more microphones can belong to the customer or one or more third parties. The microphone 108 data can be used to receive voice input, detect personality and / or mood, environmental factors (such as the volume of ambient sound), voice recognition of other customers, the type of ambient sound (such as running water, animal sounds, traffic, music, etc.). The input device 110 can be used to actively collect data from the customer. In some embodiments, the input device 110 can include a wearable device configured to detect posture, which can facilitate the passive collection of postures that can similarly be used to infer personality or mood, such that postures may be unique for excited, happy, angry, or sad customers. Data can be received in real-time or near real-time, such as a live data stream. The data can be processed in real-time or may not be processed in real-time, where the processing time will be minimized to the inherent latency involved in data communication and processing. The sensor data can additionally include temperature data collected from a mobile device or multiple sensors 104. The temperature can be the customer's temperature or the ambient temperature. At step 1010, data from one or more external data sources is accessed. The external data sources can include data sources external to the electronic device 102 and can additionally include third-party data. The third-party data can include connection devices that include multiple sensors 104, cameras 106, microphones 108, and input devices 110. The third-party data sources can additionally include databases and / or data streams or feeds owned and managed by third parties, such as databases and / or data streams or feeds managed by social media providers. In an embodiment, the data collection module 126 accesses social media data from Facebook and Twitter, identifies one or more posts made by the customer's friends, followers, and people the customer follows, and additionally collects public posts that mention or tag the customer in real-time made by the customer and the customer's friends, followers, etc. The third-party data can also include real-time sales and return data for fragrances and clothing, cosmetics, personal care products, etc. from one or more suppliers.Third-party data can further relate to a customer's location, geography, climate, weather, and calendar data, including data from public and private calendars. In an embodiment, a database connected to a retailer is accessed and it is confirmed that a female customer with customer ID 27046 purchased Her Eau de Parfum 30 seconds ago. Real-time means that data is collected and / or processed within a minimal amount of time without an inherent delay or latency. For example, real-time data processing means accessing and processing data immediately after it is available. A social media network may refresh its data feed only every five minutes, so in such examples real-time would refer to updating the data feed every five minutes. Data processing can be, but is not necessarily, performed in real-time. In some embodiments, external data sources can include environmental data, such as real-time updates to weather forecasts. At step 1012, it is determined whether a trigger condition has been detected. If a trigger condition has been detected, then the trigger data is saved to the event database 120. If a trigger condition has not been detected, then it is determined whether a timeout value has been met, or the process returns to step 1006 and continues polling the sensor 104. A trigger condition can be an explicit scenario, such as a detected proximity to a person, location, object, etc., or can be abstract, such as a detected change in the value of a selected parameter. For example, the selected parameter can be a mood, as recognized by a customer's movement, posture, and / or facial expression. If the trigger condition is a mood change, then the trigger condition is met when a customer initially recognized as being in a happy mood is subsequently detected as being in a sad mood. Similarly, when an abstract trigger condition is being monitored, specific conditions may not need to be met. For example, a change in mood may not depend on the initial or final mood, but only require that the detected mood has changed. In additional embodiments, the trigger condition can include a change in weather. In some embodiments, any change can include a trigger condition, while in other embodiments, specific conditions must be met, such as the temperature rising above 80°F, or precipitation being detected or anticipated, or the humidity rising above 70%, etc. For example, John Smith may have a meeting scheduled with Jane Doe at 3:00 PM, and if there is a trigger condition defined as the time being within 30 minutes of the scheduled meeting with Jane Doe, then after 2:30 PM, the trigger condition will be met and detected. At step 1012, it is determined whether the timeout value has been met. The timeout value can indicate the period of time for which one or more sensors 104, cameras 106, microphones 108, input devices 110, or other data sources should be monitored for new data. The timeout value can be optional and is not required to practice the present invention. In some embodiments, a loss of connection to one or more sensors 104, cameras 106, microphones 108, input devices 110, or other data sources can be equivalent to meeting the timeout value. Similarly, each such device or data source can have an independent connection and can have an independent timeout value or termination condition, which can indicate when to stop real-time monitoring of the data source.At step 1016, the trigger data is saved to the event database 120. The trigger data may include only the collected data that matches the trigger condition. In other embodiments, the trigger data may include some or all of the data received from one or more sensors 104, cameras 106, microphones 108, input devices 110, and other data sources that include the trigger condition. At step 1018, return to the base module 124. If a trigger condition is recognized, the trigger data is sent to the base module 124. If a timeout occurs, the timeout condition is returned to the base module 124.

[0043] Reference will now be made to Figure 11 explain the functions of the "recommendation module". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the processes and methods may be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations may be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0044] This figure shows the recommendation module 134. The process begins with receiving selected parameters from the base module 124 at step 1102. The selected parameters have met a quantitative threshold or have been selected due to an identified association with at least one fragrance preference. At step 1104, the customer database 118 is queried to obtain customer characteristics corresponding to the selected parameters. For example, the selected parameters may include an association between a customer's preference for kayaking and their preference for a fragrance with ID 11, and the corresponding customer characteristic is the customer's preference for kayaking. Additionally, data related to the customer of interest for whom recommendations are to be generated is retrieved. The data related to the customer of interest can influence the training of the recommendation model by using only the parameters corresponding to the available data describing the customer. For example, if hobby data for the customer is available, parameters related to hobby preferences will be included in the training data, while if social media data is not available for the customer of interest, social media-related parameters will be excluded from the training data. At step 1106, the fragrance database 116 is queried to obtain available fragrances. Fragrance data can include specific fragrances, but can also include their characteristics, ingredients, etc. Any such data describing the fragrances can be used to generate the recommendation model. For example, a fragrance may ultimately be recommended as a fragrance series rather than a specific fragrance. At step 1108, the recommendation model is trained based on the customer characteristics corresponding to the selected parameters. In a machine learning application, the customer characteristics will correspond to the source data for the features or mappings used to train the machine learning model. Training the machine learning model typically uses regression by applying adjustments or corrections after each successive training test. A number of evolutions can be completed, where a held-out selection of the training data is retained as test data to facilitate assessment of the accuracy of the trained model. The evolution can continue until the prediction accuracy of the model is higher than a threshold, such as 95%. The held-out training data can be varied such that it is randomly reselected between each evolution. In such embodiments, feedback data, such as data obtained by the feedback module 138 and stored in the customer database 118, may be required to demonstrate the association with the fragrance. In one example, based on feedback on the correlation between customer characteristics and customer feedback, the weighting of a given customer characteristic as a parameter for predicting an individual's preference for at least one fragrance is increased or decreased. The recommendation model can alternatively be based on a lookup table or a decision tree. In a lookup table, one or more customer characteristics based on the selected parameters can be used to directly map to one or more fragrances based on customer feedback. In some cases, different combinations of the selected parameters can be used to obtain multiple lookup tables. For example, some tables can use personality traits, while others can use hobbies or interests. Additional tables can include occasions, while others can include combinations of interests and occasions. These tables can be formed by mapping fragrances to customer characteristics using the selected parameters. A decision tree can be created similarly to a lookup table, except that a series of branch decisions can be used instead of lookup matches.For example, one decision tree can include a user's interests, while another decision tree can be the occasion, and another decision can be the fragrance preferences stated by the user. Similar to a lookup table, decision tree branch points can be determined based on the mapping of fragrances to customer characteristics. The selected parameters can be used to modify the weighting in a weighted value method such that a lookup table or algorithm is used where matching customer characteristics can increase or decrease the likelihood of preference or customer feedback for one or more fragrances. At step 1110, one or more fragrance recommendations are generated based on the trained recommendation model and the data collected for the customer. The generated recommendations can include one or more specific fragrances, or alternatively can include one or more fragrance families such that the fragrances in the family have similar qualities. Similarly, the recommendations can be based on specific ingredients or common characteristics in the fragrances. In some embodiments, the recommendations are based on personality types. In other embodiments, the recommendations are based on a customer's stated preference for a particular olfactory component or ingredient (e.g., "I prefer a floral fragrance like peony"), including recommendations based on specific fragrances that the customer has indicated they currently use or prefer. In additional embodiments, the recommendations are based on recommending fragrances with new ingredients that have similar olfactory properties and characteristics. In another embodiment, the recommendations are based on ingredients similar to those in the customer's current or preferred fragrance. In other embodiments, the recommendations can use weighted methods (individually or in combination) such that based on the olfactory properties or ingredient composition of the fragrances that the customer has indicated their preference for or currently uses, more or less influence is given to preferences and characteristics (e.g., personality type, mood, occasion, etc.) in the rating. The fragrance recommendations can include a binary recommendation or non-recommendation decision, or can alternatively provide a score, e.g., each recommended fragrance includes the likelihood of customer preference (total score 10), and a recommended fragrance can be any fragrance with a score above a threshold (e.g., 8 / 10). These scores can also be used to select one or more fragrances from the recommended fragrances. In an embodiment, determining that the customer is female makes them more likely to prefer Her Eau de Parfum. In another embodiment, identifying a customer characteristic preference for fruity fragrances indicates an increased preference for My Burberry Eau de Toilette. In some embodiments, multiple customer characteristics can be considered together, e.g., women with a seductive personality prefer Her Eau de Parfum. Regardless of the type, whether using machine learning, lookup tables, decision trees, or weighted values, the recommendation model can classify customers into multiple categories where customers with similar interests, preferences, characteristics, personalities, etc. can be recommended the same or similar fragrances. In some embodiments, similar fragrances can be recommended based on similar users who like the same fragrance, while in other embodiments, a fragrance can be recommended because it has olfactory properties similar to those preferred by the customer or the customer category to which the customer is identified or determined to belong.Alternatively, fragrances can be recommended based on similar fragrance ingredients. These ingredients can be preferred or taboo, for example in the case of identified allergies or sensitivities. In some embodiments, the recommendation can include one or more fragrance components, which can be combined to create a personalized fragrance. In such embodiments, in the case where a fragrance has been previously defined, the fragrance components can alternatively be used to identify an association or correlation between the fragrance components and customer characteristics to generate one or more combinations of fragrance components that can include a personalized fragrance. Not all recommended fragrance components can be included in the personalized fragrance, and in some embodiments, a pre-formulated fragrance can be selected or recommended based on a combination of multiple recommended fragrance components. At step 1112, one or more fragrance recommendations are sent to the base module 124.

[0045] Reference will now be made to Figure 12 explain the functionality of the "Fragrance Selection Module". Those skilled in the art will understand that for this and other processes and methods disclosed herein, the functions performed in the processes and methods can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or expanded into additional steps and operations without departing from the essence of the disclosed embodiments.

[0046] This figure shows the fragrance selection module 136. The process begins at step 1202 by receiving one or more fragrance recommendations from the base module 124. One or more fragrance recommendations can include specific fragrances or groups of fragrances based on commonalities. At step 1204, the fragrance database 116 is queried to obtain one or more fragrances corresponding to the fragrance recommendations received from the base module 124. For example, if a group of fragrances is recommended, each unique fragrance in the group of fragrances is identified as eligible to be selected. At step 1206, the customer database 118 is queried to obtain specific fragrance preferences or information regarding the current recommendation. For example, if the customer wishes to purchase a new fragrance for an upcoming party and / or prefers a mild fragrance that will not conflict with the smell or flavor of dinner. At step 1208, a fragrance is selected from the fragrance recommendations based on the customer's preferences. In some embodiments, multiple fragrances can be selected. The fragrance can be selected automatically using one or more algorithms or alternatively manually by a contractor or the customer. In some embodiments, multiple fragrances can be selected with the aim of mixing them into a new fragrance. In alternative embodiments, multiple fragrances can be selected with the aim of sending multiple fragrances to the customer rather than a single fragrance. In some embodiments, customer data and a weighted value method, such as a lookup table or an algorithm, can be used to select the fragrance. In other embodiments, it can be based on, for example Figure 9Select a variety of fragrances using the multiple differential decision paths described in []. Can be used based on customer data to make predictions using machine learning algorithms to select a fragrance from the recommended fragrances. Another embodiment can select a fragrance based on characteristics similar to the customer's preferences (including similar olfactory and compositional characteristics). In some embodiments, the fragrance recommendation can include a score indicating the likelihood that the customer prefers the fragrance. A fragrance can be selected based on this score, such as the fragrance with the highest score, or when selecting multiple fragrances, the top "n" fragrances with the highest recommended scores. In some embodiments, selecting a fragrance can include selecting a combination of the recommended fragrance components to create a personalized fragrance. This selection can be fully automated and can additionally include simulations to predict one or more characteristics of the personalized fragrance. Alternatively, the selection can be performed by a professional to create a personalized fragrance. In another embodiment, selecting a fragrance can include creating a plurality of sample personalized fragrances based on the recommended fragrance components, and the samples can be tested before selecting one or more personalized fragrances. In addition to the recommended fragrance components, additional fragrance components can also be used. It should also be noted that the fragrance recommendation is not necessarily a positive recommendation and may alternatively be a negative recommendation to indicate that a fragrance or fragrance component should not be recommended or selected for the customer. At step 1210, send one or more selected fragrances to the base module 124.

[0047] Now refer to Figure 13 Explain the function of the "feedback module". Those skilled in the art will understand that for this process and method and other processes and methods disclosed herein, the functions performed in the process and method can be implemented in a different order. In addition, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0048] This figure shows feedback module 138. The process begins with receiving an aroma selection from base module 124 at step 1302. In some embodiments, multiple aromas may be selected. Receiving an aroma may include providing one or more aromas to a customer, such as a sample portion, to allow the customer to rate one or more aromas. In other embodiments, receiving an aroma may include presenting the customer with an opportunity to purchase one or more aromas. In another embodiment, one or more aromas may be purchased as a gift. In some embodiments, one or more aromas may be presented to the user as a notification, such as via email, SMS message, app notification, etc. The notification or opportunity to purchase may additionally include a purchase incentive, such as a discount, rebate, money-back guarantee, etc. In a preferred embodiment, one or more aromas are selected and provided based on parameters and / or recommendations customized based on available customer characteristics of the customer. At step 1304, a feedback request is sent to the customer. The feedback request may relate to the selected aroma or alternatively may be a general query. An example of a feedback request may be a customer satisfaction survey delivered by mail or email. The feedback request is optional and not required to practice the present invention. Alternatively, customers may voluntarily share their feedback by actions such as returning a product or purchasing a product again or by voluntarily submitting comments, complaints, etc. At step 1306, feedback is received from the customer. The feedback may be explicit, such as from a survey response, comment, complaint, etc., or may be obtained passively by observing the actions taken by the customer, such as whether they purchase a product containing the aroma, which would indicate a positive response or preference, especially if they repeatedly purchase one or more products with the same aroma, while a customer returning a product with a particular aroma may indicate a negative response or preference. Customer feedback may also be obtained via social media posts, containing mentions, shares, recommendations, and critical comments. In some embodiments, multiple aromas may be presented to the customer and the customer provides feedback on their preferences. The feedback may include ranking the provided aromas from most preferred to least preferred. The feedback may alternatively consist of two parts, such as preferred or not preferred, liked or disliked, etc. The feedback may alternatively be an independent rating, such as 8 / 10, where 10 / 10 represents the highest possible preference and 0 / 10 represents the worst or lowest possible preference. At step 1308, the customer feedback is saved to customer database 118. The information accumulated in customer database 118 may be used to further refine Figures 6 to 10 any of the activities described in

[0049] The functions performed in these processes and methods can be implemented in a different order. Additionally, the steps and operations outlined are provided only as examples, and some of these steps and operations can be optional, combined into fewer steps and operations, or extended into additional steps and operations without departing from the essence of the disclosed embodiments.

[0050] Figure 14 is a flowchart of an example of a method 1500 for fragrance recommendation according to an embodiment. Method 1400 can provide features as Figures 1 to 13 described therein.

[0051] At operation 1405, a fragrance database is queried to obtain one or more fragrances. At operation 1410, a customer database is queried to obtain one or more characteristics related to at least one individual. In an example, mood state data including at least facial expressions, postures, intonation, message context, or biometric data elements can be obtained from at least one sensor, camera, input device, or data stream, and the mood state data can be evaluated to determine the current mood state of the user. The characteristic can be the mood state, and the current mood state of the user is used to partially predict the user's preferences. In an example, at least one characteristic can include facial features. One or more images of the user's face can be captured from a camera. User facial features can be identified in the one or more images, and the user facial features can be used to partially predict the user's preferences. In an example, at least one characteristic can be a demographic parameter, a user preference parameter, or a user action parameter. In an example, at least one characteristic can include at least one human parameter and at least one non - human parameter.

[0052] At operation 1415, a correlation coefficient between at least one fragrance and at least one characteristic is calculated. At operation 1420, it is determined that at least one characteristic is a predictor of an individual's preference for at least one fragrance. In an example, it can be determined that at least one characteristic is a predictor of an individual's preference for at least one fragrance based on the correlation coefficient exceeding a threshold. In an example, it can be determined that at least one characteristic is a predictor of an individual's preference for at least one fragrance based on the correlation coefficient of at least one characteristic having a higher value than a second correlation coefficient of another characteristic.

[0053] At operation 1425, an aroma recommendation model is created using at least one characteristic. At operation 1430, user data is received from at least one sensor, camera, input device, or data stream. In an example, user personality data including user activity metrics and user preferences can be obtained. The personality data can be evaluated to determine the user's personality type. User personality characteristics can be determined based on the personality type and added to the user data. In an example, the user's social media profile can be identified. User social network engagement data can be obtained based on the social media profile. The social network engagement data can be evaluated to determine user characteristics of the user, and the user characteristics can be added to the user data. In an example, at least one characteristic can include volatile organic compound (VOC) attributes. A VOC sensor can be used to collect air samples. The air samples can be evaluated to identify the concentration of a set of VOCs. The concentration of the set of VOCs can be used to query an aroma database to identify a current aroma. Aroma attributes of the current aroma can be obtained from the aroma database and added to the user data. In an example, the user's social proximity data can be obtained. The social proximity data can be evaluated to identify connections between the user and connections. Connection data of the connections can be collected. Connection characteristics can be extracted from the connection data and added to the user data.

[0054] At operation 1435, after detecting a trigger condition in the user data, an aroma recommendation model is used to evaluate the user data to predict the user's preference for at least one aroma. In an example, data provided by the user can be obtained via an input device of the user computing device, and the aroma recommendation model can be used in combination with the user data to evaluate the data provided by the user. In an example, a stimulus can be presented via an output device of the user computing device. User biometric data can be obtained from a biometric sensor, and the user biometric data can be evaluated to determine a physical response to the stimulus. The preference can be predicted in part based on the physical response. In an example, a genetic sample of the user can be obtained. The genetic sample can be sequenced to determine the user's allergen profile and the user's predicted pheromone preference, and the preference can be predicted in part using the allergen profile and the predicted pheromone preference. In an example, the aroma recommendation model can include environmental-aroma chemical composition characteristics. Environmental data of the user's nearby area can be obtained from an environmental sensor. The environmental data can be added to the user data, and the preference can be predicted in part based on a prediction of the suitability of at least one aroma for the nearby area, the prediction of the suitability being based on an evaluation of the environmental data and the chemical composition of at least one aroma. In an example, at least one characteristic can include user type. The user data can be evaluated to assign a user type to the user, and the preference can be predicted in part using the user type. In an example, a video feed can be obtained from an image sensor. The video feed can be processed using an artificial intelligence processor to identify the user's emotional response to a stimulus present in the video feed. An emotional response attribute of the user can be generated based on the identified emotional response. The aroma recommendation model can include emotional response characteristics, and the preference can be predicted in part using the emotional response attribute. In an example, the aroma recommendation model can include aroma ingredient-characteristic characteristics. A list of ingredients of at least one aroma can be obtained, and the preference can be predicted in part based on an evaluation of the list of ingredients in combination with the user data. In an example, an event in the user data can be identified. The user data can be evaluated to collect event data. Event attributes can be extracted from the event data, and the event attributes can be evaluated using the aroma recommendation model in combination with the user data.

[0055] At operation 1440, a recommendation message including an identification of at least one aroma is transmitted to the user's user computing device. In an example, a visual stimulus associated with at least one aroma can be presented to a display of the user computing device. An image of the user's eyes can be obtained from a camera. The image can be evaluated to determine a vector of the user's gaze, and an aroma of interest can be determined based on the vector of the gaze. The recommendation message can include the identity of the aroma of interest.

[0056] In an example, characteristics of multiple individuals can be obtained from a customer database. An association between a characteristic and an aroma from an aroma database can be determined based on and in response to an evaluation of the customer data of the multiple individuals. The association between the characteristic and the aroma can be stored in an association database, and it can be determined that at least one characteristic is a predictor of an individual's preference based on an assessment of the association database.

[0057] In an example, at least one aroma sample can be selected based on the identification of at least one aroma, and a fulfillment request including a request for the at least one aroma sample and a recipient address of a user can be transmitted electronically to an enterprise resource planning system.

[0058] In an example, a personality aroma prediction model can be trained using a training data corpus that includes personality traits and corresponding aroma preferences. The personality aroma prediction model can be used to evaluate aroma attributes of aromas from an aroma database to predict one or more personality traits associated with the aroma attributes, and the predicted one or more personality traits associated with the aroma attributes can be stored in the aroma database.

[0059] Figure 15 A block diagram of an exemplary machine 1500 is shown, on which any one or more of the techniques (e.g., methods) discussed herein can be executed. In alternative embodiments, the machine 1500 can be used as a stand-alone device or can be connected (e.g., networked) to other machines. In a networked deployment, the machine 1500 can operate as a server machine, a client machine, or both in a server-client network environment. In an example, the machine 1500 can act as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. The machine 1500 can be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a network appliance, a network router, a switch or bridge, or any machine capable of executing instructions (sequentially or otherwise) that specify actions to be taken by the machine. Further, although only a single machine is shown, the term "machine" shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methods discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations.

[0060] As described herein, an example can include logic or multiple components or mechanisms, or can be operated by logic or multiple components or mechanisms. A circuit set is a collection of circuits implemented in a tangible entity that includes hardware (e.g., simple circuits, gates, logic, etc.). Circuit set membership can be flexible over time and with underlying hardware variability. A circuit set includes components that can perform specified operations individually or in combination when operated. In an example, the hardware of a circuit set can be immutably designed to perform a particular operation (e.g., hardwired). In an example, the hardware of a circuit set can include physically configurable components (e.g., execution units, transistors, simple circuits, etc.) that include a computer-readable medium encoding instructions for a particular operation in a physical modification (e.g., magnetically, electrically, movable placement of invariant mass particles, etc.). When physically configuring the components, the underlying electrical properties of the hardware configuration change, for example, from an insulator to a conductor, and vice versa. The instructions enable the embedded hardware (e.g., an execution unit or a loading mechanism) to create components of the circuit set in the hardware via the physical configuration to perform portions of a particular operation when operated. Thus, when the device is operating, the computer-readable medium is communicatively coupled to other components of the circuit set components. In an example, any of the physical components can be used in more than one component in more than one circuit set. For example, in operation, an execution unit can be used in a first circuit of a first circuit set at one point in time and reused by a second circuit in the first circuit set or by a third circuit in a second circuit set at a different time.

[0061] A machine (e.g., a computer system) 1500 can include a hardware processor 1502 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 1504, and a static memory 1506, some or all of which can communicate with each other via an interconnector (e.g., a bus) 1508. The machine 1500 can further include a display unit 1510, an alphanumeric input device 1512 (e.g., a keyboard), and a user interface (UI) navigation device 1514 (e.g., a mouse). In an example, the display unit 1510, the input device 1512, and the UI navigation device 1514 can be a touch screen display. The machine 1500 can additionally include a storage device (e.g., a drive unit) 1516, a signal generation device 1518 (e.g., a speaker), a network interface device 1520, and one or more sensors 1521, such as a global positioning system (GPS) sensor, a compass, an accelerometer, or other sensors. The machine 1500 can include an output controller 1528, such as a serial (e.g., universal serial bus (USB), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection to communicate with or control one or more peripheral devices (e.g., a printer, a card reader, etc.).

[0062] The storage device 1516 may include a machine-readable medium 1522, on which is stored a set or sets of data structures or instructions 1524 (e.g., software) embodying any one or more of the techniques or functions described herein or utilized by any one or more of the techniques or functions described herein. The instructions 1524 may also reside, completely or at least partially, within the main memory 1504, within the static memory 1506, or within the hardware processor 1502 during execution thereof by the machine 1500. In an example, one or any combination of the hardware processor 1502, the main memory 1504, the static memory 1506, or the storage device 1516 may constitute a machine-readable medium.

[0063] Although the machine-readable medium 1522 is shown as a single medium, the term "machine-readable medium" may include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) configured to store one or more instructions 1524.

[0064] The term "machine-readable medium" may include any medium that can store, encode, or carry instructions for execution by the machine 1500 and that cause the machine 1500 to perform any one or more of the techniques of the present disclosure, or that can store, encode, or carry data structures used by or associated with such instructions. Non-limiting examples of machine-readable media may include solid-state memory and optical and magnetic media. In an example, the machine-readable medium may exclude transitory propagating signals (e.g., non-transitory machine-readable storage media). Specific examples of non-transitory machine-readable storage media may include non-volatile memory, such as semiconductor memory devices (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)), and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

[0065] The instructions 1524 may further be transmitted or received over the communication network 1526 via the network interface device 1520 using a transmission medium by way of any one of a plurality of transmission protocols (e.g., Frame Relay, Internet Protocol (IP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), etc.). Exemplary communication networks may include local area networks (LANs), wide area networks (WANs), packet data networks (e.g., the Internet), mobile telephone networks (e.g., cellular networks), plain old telephone (POTS) networks, and wireless data networks (e.g., the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard series, known as Wi-Fi 、LoRa / LoRaWAN LPWAN standards (such as LoRaWAN), the IEEE 802.15.4 standard series, peer-to-peer (P2P) networks, and the 3rd Generation Partnership Project (3GPP) standards for 4G and 5G wireless communications, including: the 3GPP Long Term Evolution (LTE) standard series, the 3GPP LTE-Advanced standard series, the 3GPP LTE Advanced Pro standard series, the 3GPP New Radio (NR) standard series, etc. In an example, the network interface device 1520 may include one or more physical jacks (e.g., Ethernet, coaxial, or telephone jacks) or one or more antennas to connect to the communication network 1526. In an example, the network interface device 1520 may include multiple antennas to perform wireless communication using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) technologies. The term "transmission medium" shall be regarded as including any non-tangible medium capable of storing, encoding, or carrying instructions for execution by the machine 1500, and including digital or analog communication signals or other non-tangible media to facilitate the communication of such software.

[0066] Additional Examples

[0067] Example 1 is a method executable by a computing circuit system, including: querying an aroma database to obtain one or more aromas; querying a customer database to obtain one or more characteristics related to at least one individual; calculating a correlation coefficient between at least one aroma and at least one characteristic; determining that the at least one characteristic is a predictor of an individual's preference for the at least one aroma; using the at least one characteristic to create an aroma recommendation model; receiving user data from at least one sensor, camera, input device, or data stream; after detecting a trigger condition in the user data, using the aroma recommendation model to evaluate the user data to predict the user's preference for the at least one aroma; and transmitting a recommendation message including an identification of the at least one aroma to the user's user computing device.

[0068] In Example 2, the subject matter of Example 1 includes: obtaining characteristics of a plurality of individuals from the customer database; determining an association between the characteristics and an aroma from the aroma database based on and in response to an evaluation of the customer data of the plurality of individuals; storing the association between the characteristics and the aroma in an association database; and determining that the at least one characteristic is a predictor of the individual's preference based on an assessment of the association database.

[0069] In Example 3, the subject matter of Examples 1 to 2 includes: obtaining emotion state data including at least facial expressions, postures, intonations, message contexts, or biometric data elements from the at least one sensor, camera, input device, or data stream; and evaluating the emotion state data to determine the current emotion state of the user, where the characteristic is the emotion state, and the preference of the user is predicted in part using the current emotion state of the user.

[0070] In Example 4, the subject matter of Examples 1 to 3 includes: presenting a visual stimulus associated with the at least one fragrance to a display of the user computing device; obtaining an image of the user's eyes from a camera; evaluating the image to determine a vector of the user's gaze; and determining a fragrance of interest based on the vector of the gaze, where the recommendation message includes the identity of the fragrance of interest.

[0071] In Example 5, the subject matter of Examples 1 to 4 includes: obtaining data provided by the user via an input device of the user computing device; and evaluating the data provided by the user using the fragrance recommendation model in combination with the user data.

[0072] In Example 6, the subject matter of Examples 1 to 5 includes: presenting a stimulus via an output device of the user computing device; obtaining user biometric data from a biometric sensor; and evaluating the user biometric data to determine a physical response to the stimulus, where the preference is predicted in part based on the physical response.

[0073] In Example 7, the subject matter of Examples 1 to 6 includes: obtaining user personality data including user activity metrics and user preferences; evaluating the personality data to determine the user's personality type; determining the user's personality characteristics based on the personality type; and adding the personality characteristics to the user data.

[0074] In Example 8, the subject matter of Examples 1 to 7 includes: where the at least one characteristic includes facial features, and the subject matter further includes: capturing one or more images of the user's face from a camera; and identifying user facial features in the one or more images, where the preference of the user is predicted in part using the user facial features.

[0075] In Example 9, the subject matter of Examples 1 to 8 includes: selecting at least one fragrance sample based on the identification of the at least one fragrance; and electronically transmitting a fulfillment request to an enterprise resource planning system, the fulfillment request including a request for the at least one fragrance sample and the user's delivery address.

[0076] In Example 10, the subject matter of Examples 1 to 9 includes: obtaining a genetic sample of the user; and sequencing the genetic sample to determine the user's allergen profile and the user's predicted pheromone preference, wherein the preference is predicted in part using the allergen profile and the predicted pheromone preference.

[0077] In Example 11, the subject matter of Examples 1 to 10 includes: identifying the user's social media profile; obtaining the user's social network engagement data based on the social media profile; evaluating the social network engagement data to determine the user's user characteristics; and adding the user characteristics to the user data.

[0078] In Example 12, the subject matter of Examples 1 to 11 includes: wherein the fragrance recommendation model includes environmental-fragrance chemical composition characteristics, and the subject matter further includes: obtaining environmental data of the vicinity of the user from an environmental sensor; and adding the environmental data to the user data, wherein the preference is predicted in part based on a prediction of the suitability of the at least one fragrance for the vicinity, the prediction of the suitability being based on an evaluation of the environmental data and the chemical composition of the at least one fragrance.

[0079] In Example 13, the subject matter of Examples 1 to 12 includes: wherein the at least one characteristic includes user type and further includes evaluating the user data to assign a user type to the user, wherein the preference is predicted in part using the user type.

[0080] In Example 14, the subject matter of Examples 1 to 13 includes: obtaining a video feed from an image sensor; processing the video feed using an artificial intelligence processor to identify the user's emotional response to stimuli present in the video feed; and generating an emotional response attribute of the user based on the identified emotional response, wherein the fragrance recommendation model includes emotional response characteristics, and wherein the preference is predicted in part using the emotional response attribute.

[0081] In Example 15, the subject matter of Examples 1 to 14 includes: wherein the at least one characteristic includes volatile organic compound (VOC) attributes, and the subject matter further includes: using a VOC sensor to collect an air sample; evaluating the air sample to identify the concentration of a set of VOCs; querying a fragrance database using the concentration of the set of VOCs to identify a current fragrance; obtaining fragrance attributes of the current fragrance from the fragrance database; and adding the fragrance attributes to the user data.

[0082] In Example 16, the subject matter of Examples 1 to 15 includes: obtaining social proximity data of the user; evaluating the social proximity data to identify a connection between the user and a connection; collecting connection data of the connection; extracting connection characteristics from the connection data; and adding the connection characteristics to the user data.

[0083] In Example 17, the subject matter of Examples 1 to 16 includes: wherein the at least one characteristic is a demographic parameter, a user preference parameter, or a user action parameter.

[0084] In Example 18, the subject matter of Examples 1 to 17 includes: wherein the fragrance recommendation model includes fragrance ingredient-characteristic features, and the subject matter further includes obtaining a list of ingredients of the at least one fragrance, wherein the preference is predicted based at least in part on an evaluation of the list of ingredients in combination with the user data.

[0085] In Example 19, the subject matter of Examples 1 to 18 includes: wherein the at least one characteristic includes at least one human parameter and at least one non-human parameter.

[0086] In Example 20, the subject matter of Examples 1 to 19 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient exceeding a threshold.

[0087] In Example 21, the subject matter of Examples 1 to 20 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient of the at least one characteristic having a higher value than a second correlation coefficient of another characteristic.

[0088] In Example 22, the subject matter of Examples 1 to 21 includes: identifying an event in the user data; evaluating the user data to collect event data; extracting event attributes from the event data; and using the fragrance recommendation model in combination with the user data to evaluate the event attributes.

[0089] In Example 23, the subject matter of Examples 1 to 22 includes: using a training data corpus including personality traits and corresponding fragrance preferences to train a personality fragrance prediction model; using the personality fragrance prediction model to evaluate fragrance attributes of fragrances from the fragrance database to predict one or more personality traits associated with the fragrance attributes; and storing the predicted one or more personality traits associated with the fragrance attributes in the fragrance database.

[0090] Example 24 is a system that includes components for performing the method according to any one of Examples 1 to 23.

[0091] Example 25 is at least one machine-readable medium comprising instructions that, when executed by a machine, cause the machine to perform the method of any one of Examples 1 to 23.

[0092] Example 26 is a system comprising: at least one processor; and a memory comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: query an aroma database to obtain one or more aromas; query a customer database to obtain one or more characteristics related to at least one individual; calculate a correlation coefficient between at least one aroma and at least one characteristic; determine that the at least one characteristic is a predictor of an individual's preference for the at least one aroma; use the at least one characteristic to create an aroma recommendation model; receive user data from at least one sensor, camera, input device, or data stream; after detecting a trigger condition in the user data, use the aroma recommendation model to evaluate the user data to predict the user's preference for the at least one aroma; and transmit a recommendation message identifying the at least one aroma to the user's user computing device.

[0093] In Example 27, the subject matter of Example 26 comprises: the memory further comprises instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain characteristics of a plurality of individuals from the customer database; determine an association between the characteristics and aromas from the aroma database based on and in evaluation of the customer data of the plurality of individuals; store the association between the characteristics and the aromas in an association database; and determine that the at least one characteristic is a predictor of the individual's preference based on an assessment of the association database.

[0094] In Example 28, the subject matter of Examples 26 to 27 comprises: the memory further comprises instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain emotion state data comprising at least facial expression, posture, tone of voice, message context, or biometric data elements from the at least one sensor, camera, input device, or data stream; and evaluate the emotion state data to determine the user's current emotion state, wherein the characteristic is the emotion state and the user's preference is predicted in part using the user's current emotion state.

[0095] In Example 29, the subject matter of Examples 26 to 28 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: presenting a visual stimulus associated with the at least one fragrance to a display of the user computing device; obtaining an image of the user's eyes from a camera; evaluating the image to determine a vector of the user's gaze; and determining a fragrance of interest based on the vector of the gaze, wherein the recommendation message includes an identity of the fragrance of interest.

[0096] In Example 30, the subject matter of Examples 26 to 29 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtaining data provided by a user via an input device of the user computing device; and evaluating the data provided by the user using the fragrance recommendation model in combination with the user data.

[0097] In Example 31, the subject matter of Examples 26 to 30 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: presenting a stimulus via an output device of the user computing device; obtaining user biometric data from a biometric sensor; and evaluating the user biometric data to determine a physical response to the stimulus, wherein the preference is predicted at least in part based on the physical response.

[0098] In Example 32, the subject matter of Examples 26 to 31 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtaining user personality data including user activity metrics and user preferences; evaluating the personality data to determine a personality type of the user; determining personality characteristics of the user based on the personality type; and adding the personality characteristics to the user data.

[0099] In Example 33, the subject matter of Examples 26 to 32 includes: wherein the at least one characteristic includes facial features, and the memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: capturing one or more images of the user's face from a camera; and identifying user facial features in the one or more images, wherein the user's preference is predicted at least in part using the user facial features.

[0100] In Example 34, the subject matter of Examples 26 to 33 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: select at least one fragrance sample based on the identification of the at least one fragrance; and electronically transmit a fulfillment request to an enterprise resource planning system, the fulfillment request including a request for the at least one fragrance sample and the user's shipping address.

[0101] In Example 35, the subject matter of Examples 26 to 34 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a genetic sample of the user; and sequence the genetic sample to determine the user's allergen profile and the user's predicted pheromone preference, wherein the preference is predicted at least in part using the allergen profile and the predicted pheromone preference.

[0102] In Example 36, the subject matter of Examples 26 to 35 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: identify the user's social media profile; obtain the user's social network engagement data based on the social media profile; evaluate the social network engagement data to determine the user's user characteristics; and add the user characteristics to the user data.

[0103] In Example 37, the subject matter of Examples 26 to 36 includes: wherein the fragrance recommendation model includes environmental-fragrance chemical composition characteristics, and the memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain environmental data of the user's nearby area from an environmental sensor; and add the environmental data to the user data, wherein the preference is predicted at least in part based on a prediction of the suitability of the at least one fragrance for the nearby area, the prediction of the suitability being based on an evaluation of the environmental data and the chemical composition of the at least one fragrance.

[0104] In Example 38, the subject matter of Examples 26 to 37 includes: wherein the at least one characteristic includes a user type, and the memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: evaluate the user data to assign a user type to the user, wherein the preference is predicted at least in part using the user type.

[0105] In Example 39, the subject matter of Examples 26 to 38 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a video feed from an image sensor; process the video feed using an artificial intelligence processor to identify the user's emotional response to a stimulus present in the video feed; and generate the user's emotional response attributes based on the identified emotional response, wherein the fragrance recommendation model includes emotional response characteristics, and wherein the preference is predicted using the emotional response attributes in part.

[0106] In Example 40, the subject matter of Examples 26 to 39 includes: wherein the at least one characteristic includes a volatile organic compound (VOC) attribute, and the memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: use a VOC sensor to collect an air sample; evaluate the air sample to identify the concentration of a set of VOCs; query the fragrance database using the concentration of the set of VOCs to identify the current fragrance; obtain the fragrance attributes of the current fragrance from the fragrance database; and add the fragrance attributes to the user data.

[0107] In Example 41, the subject matter of Examples 26 to 40 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain the user's social proximity data; evaluate the social proximity data to identify the connection between the user and a connection; collect the connection data of the connection; extract connection characteristics from the connection data; and add the connection characteristics to the user data.

[0108] In Example 42, the subject matter of Examples 26 to 41 includes: wherein the at least one characteristic is a demographic parameter, a user preference parameter, or a user action parameter.

[0109] In Example 43, the subject matter of Examples 26 to 42 includes: wherein the fragrance recommendation model includes fragrance ingredient-characteristic features, and the memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a list of ingredients of the at least one fragrance, wherein the preference is predicted based on an evaluation of the list of ingredients in combination with the user data in part.

[0110] In Example 44, the subject matter of Examples 26 to 43 includes: wherein the at least one characteristic includes at least one human parameter and at least one non-human parameter.

[0111] In Example 45, the subject matter of Examples 26 to 44 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient exceeding a threshold value.

[0112] In Example 46, the subject matter of Examples 26 to 45 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient of the at least one characteristic having a higher value than a second correlation coefficient of another characteristic.

[0113] In Example 47, the subject matter of Examples 26 to 46 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: identify an event in the user data; evaluate the user data to collect event data; extract event attributes from the event data; and evaluate the event attributes using the fragrance recommendation model in combination with the user data.

[0114] In Example 48, the subject matter of Examples 26 to 47 includes: The memory further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: train a personality fragrance prediction model using a training data corpus containing personality traits and corresponding fragrance preferences; use the personality fragrance prediction model to evaluate the fragrance attributes of fragrances from the fragrance database to predict one or more personality traits associated with the fragrance attributes; and store the predicted one or more personality traits associated with the fragrance attributes in the fragrance database.

[0115] Example 49 is at least one non - transitory machine - readable medium that includes instructions that, when executed by at least one processor, cause the at least one processor to perform the following operations: query a fragrance database to obtain one or more fragrances; query a customer database to obtain one or more characteristics related to at least one individual; calculate a correlation coefficient between at least one fragrance and at least one characteristic; determine that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance; create a fragrance recommendation model using the at least one characteristic; receive user data from at least one sensor, camera, input device, or data stream; after detecting a trigger condition in the user data, use the fragrance recommendation model to evaluate the user data to predict the user's preference for the at least one fragrance; and transmit a recommendation message containing an identification of the at least one fragrance to the user's user computing device.

[0116] In Example 50, the subject matter of Example 49 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain characteristics of a plurality of individuals from the customer database; determine an association between the characteristics and an aroma from the aroma database based on and in response to an evaluation of the customer data of the plurality of individuals; store the association between the characteristics and the aroma in an association database; and determine that the at least one characteristic is a predictor of the preference of the individual based on an assessment of the association database.

[0117] In Example 51, the subject matter of Examples 49 to 50 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain mood state data including at least facial expression, posture, tone of voice, message context, or biometric data elements from the at least one sensor, camera, input device, or data stream; and evaluate the mood state data to determine the current mood state of the user, wherein the characteristic is the mood state and the preference of the user is predicted in part using the current mood state of the user.

[0118] In Example 52, the subject matter of Examples 49 to 51 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: present a visual stimulus associated with the at least one aroma to a display of the user computing device; obtain an image of the user's eyes from a camera; evaluate the image to determine a vector of the user's gaze; and determine an aroma of interest based on the vector of the gaze, wherein the recommendation message includes an identity of the aroma of interest.

[0119] In Example 53, the subject matter of Examples 49 to 52 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain data provided by a user via an input device of the user computing device; and evaluate the data provided by the user using the aroma recommendation model in combination with the user data.

[0120] In Example 54, the subject matter of Examples 49 to 53 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: present a stimulus via an output device of the user computing device; obtain user biometric data from a biometric sensor; and evaluate the user biometric data to determine a physical response to the stimulus, wherein the preference is predicted in part based on the physical response.

[0121] In Example 55, the subject matter of Examples 49 to 54 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain user personality data including user activity metrics and user preferences; evaluate the personality data to determine the user's personality type; determine the user's personality characteristics based on the personality type; and add the personality characteristics to the user data.

[0122] In Example 56, the subject matter of Examples 49 to 55 includes where the at least one characteristic includes facial features, and the subject matter further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: capture one or more images of the user's face from a camera; and identify the user facial features in the one or more images, wherein the user's preferences are predicted in part using the user facial features.

[0123] In Example 57, the subject matter of Embodiments 49 to 56 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: select at least one fragrance sample based on the identification of the at least one fragrance; and electronically transmit a fulfillment request to an enterprise resource planning at least one non - transitory machine - readable medium, the fulfillment request including a request for the at least one fragrance sample and the user's shipping address.

[0124] In Example 58, the subject matter of Examples 49 to 57 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a genetic sample of the user; and sequence the genetic sample to determine the user's allergen profile and the user's predicted pheromone preferences, wherein the preferences are predicted in part using the allergen profile and the predicted pheromone preferences.

[0125] In Example 59, the subject matter of Examples 49 to 58 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: identify the user's social media profile; obtain the user's social network engagement data based on the social media profile; evaluate the social network engagement data to determine the user's user characteristics; and add the user characteristics to the user data.

[0126] In Example 60, the subject matter of Examples 49 to 59 includes where the fragrance recommendation model includes environmental-fragrance chemical composition characteristics, and the subject matter further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain environmental data of the vicinity of the user from an environmental sensor; and add the environmental data to the user data, where the preference is predicted at least in part based on a prediction of the suitability of the at least one fragrance for the vicinity, the prediction of the suitability being based on an evaluation of the environmental data and the chemical composition of the at least one fragrance.

[0127] In Example 61, the subject matter of Examples 49 to 60 includes where the at least one characteristic includes user type, and the subject matter further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: evaluate the user data to assign a user type to the user, where the preference is predicted at least in part using the user type.

[0128] In Example 62, the subject matter of Examples 49 to 61 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a video feed from an image sensor; process the video feed using an artificial intelligence processor to identify the user's emotional response to stimuli present in the video feed; and generate an emotional response attribute of the user based on the identified emotional response, where the fragrance recommendation model includes emotional response characteristics, and where the preference is predicted at least in part using the emotional response attribute.

[0129] In Example 63, the subject matter of Examples 49 to 62 includes where the at least one characteristic includes volatile organic compound (VOC) attributes, and the subject matter further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: use a VOC sensor to collect an air sample; evaluate the air sample to identify the concentration of a set of VOCs; query the fragrance database using the concentration of the set of VOCs to identify a current fragrance; obtain the fragrance attributes of the current fragrance from the fragrance database; and add the fragrance attributes to the user data.

[0130] In Example 64, the subject matter of Examples 49 to 63 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain the user's social proximity data; evaluate the social proximity data to identify a connection between the user and a connection; collect connection data of the connection; extract connection characteristics from the connection data; and add the connection characteristics to the user data.

[0131] In Example 65, the subject matter of Examples 49 to 64 includes: wherein the at least one characteristic is a demographic parameter, a user preference parameter, or a user action parameter.

[0132] In Example 66, the subject matter of Examples 49 to 65 includes wherein the fragrance recommendation model includes fragrance ingredient - characteristic features, and the subject matter further includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: obtain a list of ingredients of the at least one fragrance, wherein the preference is predicted based at least in part on an evaluation of the list of ingredients in combination with the user data.

[0133] In Example 67, the subject matter of Examples 49 to 66 includes: wherein the at least one characteristic includes at least one human parameter and at least one non - human parameter.

[0134] In Example 68, the subject matter of Examples 49 to 67 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient exceeding a threshold.

[0135] In Example 69, the subject matter of Examples 49 to 68 includes: wherein it is determined that the at least one characteristic is a predictor of the individual's preference for the at least one fragrance based on the correlation coefficient of the at least one characteristic having a higher value than a second correlation coefficient of another characteristic.

[0136] In Example 70, the subject matter of Examples 49 to 69 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: identify an event in the user data; evaluate the user data to collect event data; extract event attributes from the event data; and use the fragrance recommendation model in combination with the user data to evaluate the event attributes.

[0137] In Example 71, the subject matter of Examples 49 to 70 includes instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: use a training data corpus containing personality traits and corresponding fragrance preferences to train a personality fragrance prediction model; use the personality fragrance prediction model to evaluate fragrance attributes of fragrances from the fragrance database to predict one or more personality traits associated with the fragrance attributes; and store the predicted one or more personality traits associated with the fragrance attributes in the fragrance database.

[0138] Example 72 is at least one machine - readable medium that includes instructions that, when executed by a processing circuitry, cause the processing circuitry to perform the operations for implementing any one of Examples 1 to 71.

[0139] Example 73 is an apparatus including components for implementing any one of Examples 1 to 71.

[0140] Example 74 is a system for implementing any one of Examples 1 to 71.

[0141] Example 75 is a method for implementing any one of Examples 1 to 71.

Claims

1. A method executable by a computing circuitry, comprising: Querying an aroma database to obtain one or more aromas; Querying a customer database to obtain one or more characteristics related to at least one individual; Calculating a correlation coefficient between at least one aroma and at least one characteristic; Determining that the at least one characteristic is a predictor of an individual's preference for the at least one aroma; Using the at least one characteristic to create an aroma recommendation model; Receiving user data from at least one sensor, camera, input device, or data stream; After detecting a trigger condition in the user data, using the aroma recommendation model to evaluate the user data to predict the user's preference for the at least one aroma; And Transmitting a recommendation message including an identification of the at least one aroma to the user's user computing device.

2. The method according to claim 1, further comprising: Obtaining characteristics of a plurality of individuals from the customer database; Determining an association between the characteristics and aromas from the aroma database based on and in evaluation of the customer data of the plurality of individuals; Storing the association between the characteristics and the aromas in an association database; And Determining that the at least one characteristic is a predictor of the individual's preference based on an assessment of the association database.

3. The method according to claim 1, further comprising: Obtaining emotion state data including at least facial expression, posture, intonation, message context, or biometric data elements from the at least one sensor, camera, input device, or data stream; And Evaluating the emotion state data to determine the user's current emotion state, wherein the characteristic is the emotion state, and the user's preference is predicted in part using the user's current emotion state.

4. The method according to claim 1, further comprising: Presenting a visual stimulus associated with the at least one aroma to a display of the user computing device; Obtaining an image of the user's eyes from a camera; Evaluating the image to determine a vector of the user's gaze; And Determining an aroma of interest based on the vector of the gaze, wherein the recommendation message includes an identity of the aroma of interest.

5. The method according to claim 1, further comprising: Obtaining data provided by a user via an input device of the user computing device; And Evaluating the data provided by the user using the aroma recommendation model in combination with the user data.

6. The method according to claim 1, further comprising: Presenting a stimulus via an output device of the user computing device; Obtaining user biometric data from a biometric sensor; And Evaluating the user biometric data to determine a physical response to the stimulus, wherein the preference is predicted in part based on the physical response.

7. The method according to claim 1, further comprising: Obtaining user personality data including user activity metrics and user preferences; Evaluating the personality data to determine the user's personality type; Determining the user's personality characteristics based on the personality type; And Adding the personality characteristics to the user data.

8. The method according to claim 1, wherein the at least one characteristic includes facial features, and the method further comprises: Capturing one or more images of the user's face from a camera; And Identifying the user's facial features in the one or more images, wherein the user's preferences are predicted in part using the user's facial features.

9. The method according to claim 1, further comprising: Selecting at least one fragrance sample based on the identification of the at least one fragrance; And Transmitting a fulfillment request electronically to an enterprise resource planning system, the fulfillment request including a request for the at least one fragrance sample and the user's shipping address.

10. The method according to claim 1, further comprising: Obtaining a genetic sample of the user; And Sequencing the genetic sample to determine the user's allergen profile and the user's predicted pheromone preference, wherein the preferences are predicted in part using the allergen profile and the predicted pheromone preference.

11. The method according to claim 1, further comprising: Identifying the user's social media profile; Obtaining the user's social network engagement data based on the social media profile; Evaluating the social network engagement data to determine the user's user characteristics; And Adding the user characteristics to the user data.

12. The method according to claim 1, wherein the fragrance recommendation model includes environmental-fragrance chemical composition characteristics, and the method further comprises: Obtaining environmental data of the user's nearby area from an environmental sensor; And Adding the environmental data to the user data, wherein the preferences are predicted in part based on a prediction of the suitability of the at least one fragrance for the nearby area, the prediction of the suitability being based on an evaluation of the environmental data and the chemical composition of the at least one fragrance.

13. The method according to claim 1, wherein the at least one characteristic includes user type and further comprises evaluating the user data to assign a user type to the user, wherein the preferences are predicted in part using the user type.

14. The method according to claim 1, further comprising: Obtaining a video feed from an image sensor; Processing the video feed using an artificial intelligence processor to identify the user's emotional response to stimuli present in the video feed; And Generating an emotional response attribute of the user based on the identified emotional response, wherein the fragrance recommendation model includes emotional response characteristics, and wherein the preferences are predicted in part using the emotional response attribute.

15. The method according to claim 1, wherein the at least one characteristic includes volatile organic compound (VOC) attributes, and the method further comprises: Collecting an air sample using a VOC sensor; Evaluating the air sample to identify the concentration of a group of VOCs; Querying a fragrance database using the concentration of the group of VOCs to identify a current fragrance; Obtaining the fragrance attributes of the current fragrance from the fragrance database; And Adding the fragrance attributes to the user data.

16. The method according to claim 1 further comprises: obtaining social proximity data of the user; evaluating the social proximity data to identify a connection between the user and a connection; collecting connection data of the connection; extracting connection characteristics from the connection data; and adding the connection characteristics to the user data.

17. The method according to claim 1, wherein the at least one characteristic is a demographic parameter, a user preference parameter, or a user action parameter.

18. The method according to claim 1, wherein the fragrance recommendation model comprises fragrance ingredient-characteristic features, and the method further comprises obtaining a list of ingredients of the at least one fragrance, wherein the preference is predicted based at least in part on an evaluation of the list of ingredients in combination with the user data.

19. The method according to claim 1, wherein the at least one characteristic comprises at least one human parameter and at least one non-human parameter.

20. The method according to claim 1, wherein it is determined that the at least one characteristic is a predictor of the preference of the individual for the at least one fragrance based on the correlation coefficient exceeding a threshold.

21. The method according to claim 1, wherein it is determined that the at least one characteristic is a predictor of the preference of the individual for the at least one fragrance based on the correlation coefficient of the at least one characteristic having a higher value than a second correlation coefficient of another characteristic.

22. The method according to claim 1 further comprises: identifying an event in the user data; evaluating the user data to collect event data; extracting event attributes from the event data; and evaluating the event attributes using the fragrance recommendation model in combination with the user data.

23. The method according to claim 1 further comprises: training a personality fragrance prediction model using a training data corpus comprising personality traits and corresponding fragrance preferences; using the personality fragrance prediction model to evaluate fragrance attributes of fragrances from the fragrance database to predict one or more personality traits associated with the fragrance attributes; and storing the predicted one or more personality traits associated with the fragrance attributes in the fragrance database.

24. A system comprising components for performing the method according to any one of claims 1 to 23.

25. At least one machine-readable medium comprising instructions that, when executed by a machine, cause the machine to perform the method according to any one of claims 1 to 23.

Images