System for generating product recommendations using biometric data

Abstract

The present invention relates to systems and methods for facilitating product preferences and / or product recommendations. These systems and methods take into account biometric data of a subject in order to determine product preferences and / or product recommendations. Although other factors of the subject are optional, these factors can also be taken into account when determining product preferences and / or product recommendations for the subject. These product preferences or recommendations can be presented to the subject automatically via a display device or with the assistance of a product consultant. In order to obtain the biometric data, the subject will be exposed to a variety of stimuli, such as a fragrance / aroma stimulus. Biometric data will then be collected from the subject based on the subject's response to this fragrance / aroma stimulus. In some instances, the biometric data collected is related to the subject's event-related potentials (ERPs), i.e., the measured brain responses that are a direct result of a specific sensory, cognitive, or motor event.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefits of U.S. Provisional Application No. 63 / 046440, filed June 30, 2020; U.S. Provisional Application No. 63 / 065220, filed August 13, 2020; and French Application No. 2009180, filed September 10, 2020, the entire disclosures of which are incorporated herein by reference. Background Technology

[0003] Embodiments of this disclosure generally relate to using biometric data to assist in product recommendation and / or selection. In some embodiments, biometric data is used to determine a user's product preferences. In some of these embodiments, product preferences are used to assist in product recommendation and / or selection. Summary of the Invention

[0004] This document discloses systems and methods for facilitating product preferences and / or product recommendations. In the embodiments described below, these systems and methods take into account the biometric data of a subject in order to determine product preferences and / or product recommendations. In some embodiments, these factors may be considered when determining product preferences and / or product recommendations for a subject, although other factors of the subject are optional. These product preferences or recommendations may be presented to the subject automatically via a display device or with the assistance of a product advisor.

[0005] In some implementations, to obtain biometric data, the subject is exposed to multiple stimuli, such as fragrance / olfactory stimuli. Biometric data is then collected from the subject based on their response to these stimuli. In some implementations, the collected biometric data is correlated with the subject's event-related potentials (ERPs), which are measured brain responses that are direct results of specific sensory, cognitive, or motor events.

[0006] For example, in some implementations, these systems and methods detect event-related potentials based on responses to olfactory stimuli. In this respect, these systems and methods detect real-time cognitive processes associated with olfactory stimuli, detect real-time event-related potentials associated with responses to one or more fragrance accords, detect voltage fluctuations representing responses to olfactory stimuli, or detect postsynaptic potentials based on responses to olfactory stimuli.

[0007] According to one aspect of this disclosure, a system is provided. In one embodiment, the system includes: a plurality of sensors configured to sense event-related potentials (ERPs) of an object based on a response to an olfactory stimulus; and one or more engines configured to: receive the EEPs of the object as EEG signals; process the EEG signals to generate EEG data; and generate product recommendations based at least on the EEG data.

[0008] In some implementations, one or more engines are housed in a mobile computing device.

[0009] In some implementations, the generated EEG data is represented as an image.

[0010] In some implementations, the images include electroencephalogram (EEG) images or brain activity maps.

[0011] In some implementations, one or more engines are further configured to generate preference feature parameters for olfactory stimuli based on EEG data, and to generate product recommendations based on these preference feature parameters.

[0012] In some implementations, one or more engines are configured to determine product recommendations by comparing data representing generated preference feature parameters with product data accessible to one or more engines.

[0013] In some implementations, the olfactory stimulus is a fragrance, and the data representing the generated preference characteristics parameters includes a fragrance profile.

[0014] In some implementations, fragrance profiles are presented to the recipients as product recommendations.

[0015] In some implementations, the generated preference feature parameters represent various fragrance notes of a fragrance. In some implementations, product recommendations are generated by comparing a fragrance profile with a set of fragrance profiles that represent a group of fragrances, which can be accessed by one or more engines.

[0016] In some implementations, one or more engines include processing circuitry configured to: detect real-time event-related potentials associated with a response to one or more fragrance blends; detect voltage fluctuations representing a response to an olfactory stimulus; or detect postsynaptic potentials based on a response to an olfactory stimulus.

[0017] In some embodiments, the plurality of sensors and / or one or more engines forming the fragrance response unit include one of the following processing circuits: processing circuits configured to detect real-time cognitive processes associated with olfactory stimuli; processing circuits configured to detect real-time event-related potentials associated with responses to one or more fragrance blends; processing circuits configured to detect postsynaptic potentials based on responses to olfactory stimuli; or processing circuits configured to detect voltage fluctuations representing responses to olfactory stimuli.

[0018] In some embodiments, the olfactory stimulus includes a fragrance. In some of these embodiments, one or more engines form a fragrance selection unit that includes processing circuitry of one or more of the following: processing circuitry configured to generate one or more virtual instances of a subset of fragrances based on at least one input associated with an electroencephalogram; processing circuitry configured to generate one or more instances of a satisfaction rating or preference measurement; processing circuitry configured to generate one or more instances of fragrance intensity; processing circuitry configured to generate one or more instances of an aromatic compound concertation; or processing circuitry configured to generate one or more instances of base notes, top notes, or middle notes in a fragrance combination.

[0019] According to another aspect of the invention, a system is provided that includes a fragrance response unit and a fragrance selection unit. In some embodiments, the fragrance response unit includes circuitry, such as processing circuitry, configured to detect event-related potentials based on a response to an olfactory stimulus. In some embodiments, the fragrance selection unit includes circuitry, such as processing circuitry, configured to generate one or more virtual instances of a subset of fragrances based on at least one input associated with an event-related potential.

[0020] In some embodiments, the fragrance response unit includes one of the following processing circuits: a processing circuit configured to detect real-time cognitive processes associated with olfactory stimuli; a processing circuit configured to detect real-time event-related potentials associated with responses to one or more fragrance blends; a processing circuit configured to detect postsynaptic potentials based on responses to olfactory stimuli; or a processing circuit configured to detect voltage fluctuations representing responses to olfactory stimuli.

[0021] In some embodiments, the fragrance selection unit further includes one of the following processing circuits: processing circuits configured to generate one or more virtual instances of a fragrance subset based on at least one input associated with an electroencephalogram; processing circuits configured to generate one or more instances of a satisfaction rating or preference measurement; processing circuits configured to generate one or more instances of a fragrance intensity; processing circuits configured to generate one or more instances of a blend of aromatic compounds; or processing circuits configured to generate one or more instances of base notes, top notes, or middle notes in a fragrance blend.

[0022] According to another aspect of this disclosure, a method for recommending products to an object is provided. In one embodiment, the method includes: obtaining biometric data of the object based on contact with olfactory stimuli; analyzing the biometric data; and recommending products to the object based at least on the analyzed biometric data.

[0023] In some implementations, recommending products to an object based on the analyzed biometric data includes presenting the object with a fragrance name or a fragrance profile.

[0024] In some embodiments, the method further includes obtaining questionnaire data from the subjects, which represents their preferences for characteristic parameters of the products. In some embodiments, product recommendations for the subjects are based on analyzed biometric data and questionnaire data.

[0025] In some implementations, the olfactory stimulus is a fragrance, where the product is a perfume, and the biometric data represents EEG data.

[0026] In some implementations, product recommendation includes: generating a fragrance profile based on EEG data; and presenting the fragrance profile to the recipient.

[0027] In some implementations, product recommendation includes: generating a fragrance profile based on EEG data; comparing the fragrance profile with a set of fragrance profiles representing a group of fragrances to select a fragrance from the group of fragrances that has a fragrance profile most similar to the generated fragrance profile; and presenting the selected fragrance to the subject.

[0028] In some implementations, obtaining biometric data of an object based on contact with a stimulus includes obtaining biometric data from at least two EEG electrodes associated with the object’s left anterior (F7) lobe and right anterior (F8) lobe.

[0029] This summary is provided to introduce, in a simplified form, some concepts that will be further described in the following detailed description. This summary is not intended to identify key features of the claimed subject matter, nor is it intended to assist in determining the scope of the claimed subject matter. Attached Figure Description

[0030] The foregoing aspects and numerous accompanying advantages of the disclosed subject matter will become more readily and readily understood in conjunction with the following detailed description and the accompanying drawings. In these drawings:

[0031] Figure 1 This is a schematic diagram illustrating a non-limiting example of a system for generating product (e.g., fragrance) recommendations and providing them to an object, according to one aspect of this disclosure;

[0032] Figure 2 Describing applicable Figure 1 An example of a head-mounted device for a system;

[0033] Figure 3 It shows that it is applicable to Figure 1 A block diagram of a non-limiting example of a mobile computing device for a system;

[0034] Figure 4 It shows that it is applicable to Figure 1 A block diagram of a non-limiting instance of a server computing device of a system;

[0035] Figure 5 This is a block diagram illustrating a non-limiting example of a computing device suitable for use as an embodiment of the present disclosure;

[0036] Figure 6 This is a flowchart illustrating a non-limiting example of a method for generating product recommendations and providing them to an object according to one aspect of this disclosure;

[0037] Figure 7 This is a flowchart illustrating another non-limiting example of a method for generating product recommendations and providing them to an object according to one aspect of this disclosure;

[0038] Figure 8 It is an example of a fragrance wheel;

[0039] Figure 9 This is an example of an electroencephalogram generated by processing acquired EEG signals according to this disclosure;

[0040] Figure 10 This is an example of a brain activity map generated by processing acquired EEG signals according to this disclosure;

[0041] Figure 11 It is an example of a fragrance profile generated by the system and presented to an object according to one aspect of this disclosure;

[0042] Figure 12This is an example of an EEG electrode placement diagram according to various aspects of this disclosure; and

[0043] Figure 13 An example of a problem depicting one or more scenarios is shown, which is generated by the user interface engine and presented to an object. Detailed Implementation

[0044] To provide recommendations for cosmetics, most existing technologies simply attempt to directly identify an individual's product preferences. Some technologies may try to determine an individual's product preferences based on their stated preferences for product features (such as scent, color, finish, texture, etc.). However, such technologies produce suboptimal recommendations, at least because they only consider explicitly stated preferences. Even if explicitly stated preferences exist, other factors (e.g., bodily responses (subconscious or conscious), personality traits, etc.) can influence what products a given individual will prefer.

[0045] In this regard, in some embodiments of this disclosure, the subject's biometric data is considered when determining product preferences and / or product recommendations. In other embodiments, these factors may be considered when determining product preferences and / or product recommendations for the subject, although other factors of the subject are optional. These product preferences or recommendations are then presented to the subject automatically via a display device or with the assistance of a product advisor.

[0046] The examples described throughout this disclosure relate to recommendations for fragrances (such as perfumes or colognes). It should be understood that the techniques and methods of this disclosure are not limited to product types and can therefore be used to recommend products to an audience other than fragrances.

[0047] In the examples described below, the subject will be exposed to various stimuli, such as fragrance / olive stimuli. Biometric data will then be collected from the subject based on their responses to these stimuli. In some implementations, the collected biometric data is correlated with the subject's event-related potentials (ERPs), which are measured brain responses that are direct results of specific sensory, cognitive, or motor events. Using this biometric data, a computer-based system can, for example, recommend specific fragrances or generate fragrance profiles from which recommendations can be made with the assistance of, for example, a technician or fragrance consultant. In other implementations, the computer-based system incorporates biometric data in conjunction with optional data (such as data from questionnaires, the subject's historical purchase data, etc.) to present product recommendations to the subject.

[0048] In some embodiments described herein, the fragrance / scent presented to the recipient may include two or more scent notes of a blended fragrance. Typically, a blended fragrance is a scent composed of several perfume scent notes, ingredients, etc., mixed together to form a unique aroma. For example, a blended fragrance usually includes multiple scent notes. Scent notes are perceptible descriptors of aroma, including base notes, middle notes or heart notes, and top notes or initial notes. These scent descriptors or scent notes are well-known and widely used to describe the odor characteristics of a fragrance (e.g., characteristic parameters).

[0049] Fragrance notes are usually selected from fragrance families. Fragrance families can often be visually represented using a fragrance wheel. Figure 8 An example of a fragrance wheel is shown. A fragrance wheel is a circular chart that displays relationships between olfactory groups inferred based on the similarity and difference of scents. Groups adjacent to each other indicate that they share common olfactory characteristics. Fragrance wheels are often used as a classification tool for wines and perfumes.

[0050] Now go to Figure 1 The diagram shown illustrates a non-limiting example of a system 100 according to one aspect of this disclosure. In the illustrated system, in response to a subject's contact with a stimulus (such as an aromatherapy fragrance), the brain electrical activity of the subject 102 is measured in the form of EEG signals using physical acquisition devices 106 (such as EEG sensors). As shown, multiple physical acquisition devices 106 are placed, for example, in various regions of the subject's brain via a suitable head-mounted device 114 to measure the subject's brain electrical activity. In some embodiments, as will be described in more detail below, brain regions associated with, for example, stimulation / relaxation and / or approach / avoidance are measured. Other brain regions may be additionally or alternatively measured to acquire EEG sensor data.

[0051] See also Figure 1 Mobile computing device 104 is coupled to physical acquisition device 106 via wired or wireless means to acquire EEG signals generated by physical acquisition device 106. In some embodiments, mobile computing device 104 processes the acquired signals and determines product recommendations to be presented to subject 102 based on the processed signals. In other embodiments, mobile computing device 104 generates a fragrance profile based on the processed signals, which can be used to make recommendations with the assistance of, for example, a technician or fragrance consultant.

[0052] In one implementation, processing the acquired EEG signals includes: generating an electroencephalogram (EEG), such as... Figure 9 The example shown. In other embodiments, processing the acquired EEG signals includes: generating a brain activity map, such as... Figure 10The example shown. The mobile computing device 104 can then use electroencephalography (EEG) and / or brain activity mapping to recommend products to the user, or present fragrance profiles to assist the user in selecting products. Of course, the mobile computing device 104 can also utilize the acquired EEG signals in other ways (including through non-graphics processing techniques) to provide product recommendations to the user.

[0053] In other embodiments, mobile computing device 104 may transmit processed or unprocessed EEG signals as EEG data to an optional server computing device 108 via network 110. In some embodiments, network 110 may include any suitable wireless communication technology (including but not limited to Wi-Fi, WiMAX, Bluetooth, 2G, 3G, 4G, 5G, and LTE), wired communication technology (including but not limited to Ethernet, USB, and FireWire), or combinations thereof.

[0054] By receiving EEG data from mobile computing device 104, server computing device 108 can respond to mobile computing device 104 with product recommendations to be presented to object 102. In other embodiments, server computing device 108 can generate a fragrance profile based on the EEG data. This fragrance profile can then be transmitted to mobile computing device 104. Once mobile computing device 104 receives the fragrance profile, it can make recommendations with the assistance of, for example, a technician or fragrance consultant. Of course, in some embodiments, server computing device 108 can access a cloud-based computer processing system (not shown) via network 110 to enhance its processing, analysis, and generation capabilities.

[0055] In some implementations, server computing device 108 processes EEG data and generates an electroencephalogram (EEG) and / or brain activity map. Server computing device 108 can then use the EEG and / or brain activity map to provide product recommendations to mobile computing device 104 for presentation to subject 102. Alternatively, the generated EEG and / or brain activity map data is transmitted to mobile computing device 104 for use by mobile computing device 104 in providing product recommendations to subject 102.

[0056] In some embodiments, the mobile computing device 104 may also be used to present an optional questionnaire to the subject 102. The questionnaire may include questions that allow the determination of the subject 102's preferences. In some embodiments, the questionnaire may also allow the determination of at least one personality trait. For example, in some embodiments, a personality trait may be associated with one or more fragrance preferences, etc.

[0057] In some implementations, the questionnaire may be provided to the mobile computing device 104 by an optional server computing system 108 for presentation to the subject 102. In other implementations, the mobile computing device 104 may generate the questionnaire and present it to the subject.

[0058] In some embodiments, questionnaire answers are received and processed locally by mobile computing device 104. In other embodiments, the answers received by mobile computing device 104 are transmitted to an optional server computing system 108 for processing. Of course, in some embodiments, server computing device 108 may access a cloud-based computer processing system (not shown) via network 110 to enhance its processing capabilities.

[0059] In any case, the mobile computing device 104 or the server computing device 108 can combine the EEG signals collected from the object with the processed questionnaire answers to provide, for example, product recommendations.

[0060] In some implementations, product recommendations can be provided to subject 102 in a simplified format. For example, the product recommendation could be a specific fragrance, such as one identified by a brand name (e.g., Trade Winds). Other information about subject 102, such as fragrance preferences, personality traits, and previously purchased fragrances, may also be presented to the subject. Additionally or alternatively, the product recommendation can take the form of a fragrance profile. The fragrance profile can be presented as a textual description or visually as a fragrance note diagram. Figure 11 An example of a fragrance profile generated by system 100 and presented to object 102 is shown. A fragrance that the object is likely to like can be selected independently, or with the assistance of a fragrance consultant, through textual descriptions or the fragrance profile.

[0061] Figure 2This is a block diagram illustrating various components of a non-limiting example of a head-mounted device 114 according to one aspect of the present disclosure. The head-mounted device 114 supports multiple physical acquisition devices 106 (“EEG sensors 106”) in the form of EEG sensors, as well as processing and transmission circuitry 118. Typically, voltage changes are caused by ionic currents within and between neurons in the brain. The EEG sensors 106 (sometimes referred to as EEG electrodes) are configured to measure these voltage changes in the subject's brain as EEG signals. The EEG signals measured by the EEG sensors 106 can be appropriately processed for transmission to a mobile computing device 104 for storage, data processing, and / or analysis, etc. For example, in some embodiments, the EEG signals are amplified by an amplifier 120 and digitized by an A / D converter 122 before reaching a transmitter 130. In some embodiments, the EEG signals may be filtered in the analog domain before conversion by the A / D converter 122, or filtered in the digital domain after conversion by the A / D converter 122 through one or more filters 124. In some implementations, the filtered (optional) signal is sent to the multiplexer (MUX) 126 before being transmitted via transmitter 130 to mobile computing device 104.

[0062] EEG electrode 106 is typically formed of a conductive material such as stainless steel or silver / silver chloride (Ag / AgCl). EEG electrode 106 can be wet (e.g., using an electrolytic gel material as a conductor between the skin and the electrode) or dry (e.g., a single metal electrode as a conductor between the skin and the electrode). In some embodiments, a non-gel material such as saline solution can be used as a conductive layer between the skin layer and the electrode.

[0063] In some embodiments, the EEG electrode 106 may be active, wherein these electrodes include preamplifier circuitry immediately following conductive material between the skin and the electrode. This allows the EEG signal to be amplified before additional noise is introduced into the system responsible for capturing, processing, or amplifying the EEG signal. Alternatively, in other embodiments, the EEG electrode may be passive. Passive electrodes do not include preamplifier circuitry. Instead, passive electrodes are simply system components that extend the conductive material from the electrode to the system components that process, amplify, and / or transmit the signal.

[0064] When placed on a subject's head, the EEG electrodes 106 of the head-mounted device 114 are typically aligned with various areas of the brain. Figure 12The diagram shown is an example of an EEG electrode placement diagram according to various aspects of this disclosure. It should be understood that several abbreviations in the diagram relate to the international 10-20 system, including: “N” for nasal root, “F” for frontal lobe (e.g., related to the frontal lobe of the brain, which is the region located at the front of each cerebral hemisphere), “A” for earlobe, “C” for central (e.g., related to the central region of the brain), “T” for temporal lobe (e.g., related to the temporal lobe of the brain, which is located below and behind the frontal lobe of each cerebral hemisphere), “P” for parietal lobe (e.g., related to the parietal lobe of the brain, which is located behind the frontal lobe), “O” for occipital lobe (e.g., related to the occipital lobe of the brain, which is located at the back of the head), “I” for external occipital protuberance, and the subscript “z” for readings taken along the midline of the brain. Figure 11 The chart also includes abbreviations for AF, which lies between Fp and F, and FC, which lies between F and C.

[0065] like Figure 12 As illustrated in the examples, the EEG electrodes are positioned to correspond to the AF3, AF4, F3, F4, F7, F8, FC5, FC6, T7, T8, P7, P8, O1, and O2 regions of the subject's brain. In the illustrated embodiment, reference electrodes are located at P3 and P4, but other locations may also be used. In some embodiments, only two electrodes are used, namely the left anterior electrode (F7) and the right anterior electrode (F8), which are respectively associated with proximity (left brain activity) and avoidance (right brain activity). Of course, any other combination of the left anterior electrode (F7) and the right anterior electrode (F8), as well as brain regions, can be practiced using embodiments of this disclosure. In some embodiments, the position of the EEG electrodes may be fixed by a head-mounted device. In other embodiments, the position of the EEG electrodes may be adjustable.

[0066] A non-limiting example of a head-mounted device 114 that outputs suitable signals for use by system 100 is the EPOC+EEG head-mounted device from Emotive. Other head-mounted devices that can be used are available from companies such as Brain Products, EGI, and Cognionics.

[0067] Figure 3 This is a block diagram illustrating various components of a non-limiting example of a mobile computing device 104 according to one aspect of this disclosure. The mobile computing device 104 is configured to acquire information from an object 102 reflecting brain activity based, for example, exposure to one or more aromas in a sequential manner. In particular, the mobile computing device 104 is configured to receive EEG signals from one or more EEG sensors 106 for processing, recording, transmission (optional), and / or analysis (optional). In some embodiments, the mobile computing device 104 is configured to receive EEG signals from a transmitter 130 of a head-mounted device 114 (see [link to relevant documentation]). Figure 2 ).

[0068] In some embodiments, mobile computing device 104 processes EEG signals to determine product recommendations for subject 102. In other embodiments, as will be described in more detail below, processed or unprocessed EEG signals are transmitted as EEG data via network 110 to an optional server computing system 108 for processing and / or generating product recommendations, etc. In either case, mobile computing device 104 may then present the product recommendation to subject 102 or a beauty consultant assisting subject 102. In some embodiments, the generation of product recommendations may be an identifier of a specific product (e.g., a specific perfume / cologne). In other embodiments, the generation of product recommendations may be information assisting in the selection of a specific product or product line, such as a fragrance profile.

[0069] In some embodiments, the mobile computing device 104 may be a smartphone. In some embodiments, the mobile computing device 104 may be any other type of computing device having the illustrated components, including but not limited to tablet computing devices or laptop computing devices. In some embodiments, the mobile computing device 104 may not be mobile, but may be a fixed computing device, such as a desktop computing device or computer kiosk. In some embodiments, the illustrated components of the mobile computing device 104 may be housed in a single housing. In some embodiments, the illustrated components of the mobile computing device 104 may be housed in different housings that are communicatively coupled via wired or wireless connections. The mobile computing device 104 also includes... Figure 3 Other components not shown include, but are not limited to, one or more processor circuits (generally referred to as processors), non-transitory computer-readable media, power supply, and one or more network communication interfaces.

[0070] To implement some (or all) of the techniques and methods described herein, in some embodiments, for example, mobile computing device 104 includes display device 302, EEG engine 306, user interface engine 308, optional questionnaire analysis engine 310, recommendation engine 312, user data repository 314, and product data repository 316. Each of these components will be described in turn.

[0071] In some embodiments, the display device 302 is any suitable type of display device capable of presenting an interface to the object 102, including but not limited to LED displays, OLED displays, or LCD displays. As will be described in more detail below, these interfaces include questionnaires, product recommendations, etc., to be presented to the object 102. In some embodiments, the display device 302 may include an integrated touch-sensitive portion for receiving input from the object 102.

[0072] In some embodiments, the EEG engine 306 is configured to acquire EEG signals from the EEG sensor 106, process these EEG signals, and record these EEG signals in a time-based manner as EEG data in the user data store 314. In some embodiments, EEG signal processing may include, but is not limited to, conversion, filtering, and / or transformation. For example, in some embodiments, the EEG signals may be bandpass filtered to appropriately transmit the signal within, for example, the α and / or β frequency range. In some embodiments, the EEG engine 306 is also configured to process the signal to generate, for example,... Figure 9 The electroencephalogram and / or other similar data of the examples shown Figure 10 Brain activity diagram of the example shown.

[0073] In some embodiments, the user interface engine 308 is configured to present a user interface on the display device 302. In some embodiments, the user interface engine 308 is configured to present product recommendations to the user 102, such as product names or fragrance profiles. In some embodiments, the user interface engine 308 may be configured to present a visual representation of EEG data on the display device 302, such as an electroencephalogram or brain activity map.

[0074] In some implementations, the user interface engine 308 may optionally be configured to present at least one questionnaire to the object 102 on the display device 302 for collecting information from the object 102. In some implementations, the questionnaire is designed to collect information that may relate to characteristic parameters of a fragrance that the object has already encountered or will encounter. For example, the questionnaire may consist of a series of true / false or multiple-choice questions that may elicit preferences for certain top, middle, or base notes. Figure 13 One question in the questionnaire can present participants with multiple images depicting scenes such as beaches and forests, prompting them to answer which depicted scene is associated with their preferred fragrance. Another question can ask participants whether they prefer feminine, masculine, or unisex scents. Yet another question can ask participants whether they prefer perceptible, subtle, strong, or intense fragrances. A third question can ask participants to input their preferred fragrances, including recently purchased ones. Some or all of the collected data can be stored, for example, in a user data repository 314.

[0075] In some implementations, the questionnaire analysis engine 310 can be configured to receive questionnaire answers from the subject 102 via the user interface engine 308, and can determine at least one preference of the subject 102 based on one or more of these answers, such as a fragrance preference, fragrance characteristics, etc. For example, if the subject 102 selects a forest scene as a preference, the questionnaire analysis engine 310 can be configured to determine that the subject 102 prefers woody tones, such as... Figure 8 As shown in the fragrance wheel. In some embodiments, the questionnaire analysis engine 310 may be configured to compare answers with data stored, for example, in a product data repository 316. In one embodiment, the questionnaire analysis engine 310 may be configured to determine at least one personality trait of the subject 102 based on one or more answers.

[0076] In some embodiments, recommendation engine 312 may be configured to generate at least one product recommendation for object 102 based at least on EEG data. In other embodiments, recommendation engine 312 may be configured to generate at least one product recommendation for object 102 based at least on EEG data and optional questionnaire data. In some embodiments, the product recommendation is in the form of a specific product, such as Trade Winds perfume. In other embodiments, the product recommendation is in the form of a fragrance profile. In these embodiments, the fragrance profile may be presented as a text description or visually depicted as a fragrance note diagram, etc. In some embodiments, recommendation engine 312 provides product recommendations to be presented to object 102 via display device 302.

[0077] For example, Figure 11 This is an instance of a fragrance profile that can be generated by the recommendation engine 312 and presented to object 102. The fragrance profile depicts the characteristic parameters of the fragrances preferred by object 102. For example... Figure 11 As shown, a fragrance note diagram visually depicts the top, heart, or middle notes, and optionally the base notes, preferred by the recipient. These notes are represented by a wheel-like pattern, with bands indicating the intensity of preference. For example, regarding the top notes, aromatic fougères are depicted as five (5) bands, with floral notes being preferred over floral notes, which are depicted as one (1) band. Similarly, regarding the middle notes, fruity notes are depicted as four (4) bands, with fruity notes being preferred over spicy notes, which are depicted as three (3) bands. In addition to the number of bands, or as a substitute for the number of bands, the color of the bands can also indicate the intensity of preference. In some implementations of fragrance note diagrams, the intensity values ​​can be linear (i.e., the preference intensity of two bands is twice that of one band, etc.) or non-linear, such as logarithmic, exponential, etc.

[0078] exist Figure 11In the illustrated chart, the object prefers: a fragrant fougère in the top notes, followed by citrus; green and fruity notes in the middle notes, followed by spicy notes; and balsam notes in the base notes, followed by musk or woody notes. In some embodiments, this fragrance map can be presented on a display device 302 via a user interface engine 308. In some embodiments, a fragrance consultant can use the fragrance map to recommend product types or product lines corresponding to the fragrance profiles in the map. In other embodiments, the object 102 can use the fragrance map to compare with fragrance charts of one or more fragrance products. In still other embodiments, the recommendation engine 312 can analyze, for example, an image of the fragrance map or the underlying data used to generate the fragrance map, and automatically present product recommendations to the object 102 based on this analysis. In this later embodiment, product recommendations can be based on product data, for example, accessed from a product data repository 316.

[0079] In some implementations, the recommendation engine 312 employs one or more algorithms to analyze images generated from biometric data (e.g., electroencephalograms, brain activity maps, etc.). Based on this analysis, one or more characteristic parameters of the fragrance preferred by the subject 102 can be determined. For example, in some implementations, regions associated with the F7 and F8 areas of the brain in the electroencephalogram or brain activity map are analyzed in response to a stronger stimulus. This stronger stimulus may indicate whether the subject 102 likes the fragrance being exposed. Of course, in various implementations, other combinations of brain regions can be analyzed.

[0080] In some implementations, fragrance preference feature parameters are determined based on one or more images of EEG data. For example, in some implementations, image processing techniques are applied to the images to determine the fragrance preference feature parameters. In some implementations, the recommendation engine 312 may include or access an artificial neural network trained to determine feature parameters based on images. Of course, any other suitable type of machine learning techniques and / or classical image processing techniques can be performed to determine the fragrance preference feature parameters that the object 102 is exposed to.

[0081] For example, in some embodiments, the recommendation engine 312 includes a machine learning model for assisting in determining product recommendations. Images such as electroencephalograms (EEGs), brain activity maps, etc., of objects exposed to known fragrances (with known characteristic parameters, such as fragrance profiles) that the objects likely prefer can be used to train the machine learning model. In some embodiments, images from known fragrances are used to create a set of supervised training data, and any suitable technique (including but not limited to gradient descent) can be used to train the machine learning model on the training data, such as an artificial neural network. The resulting machine learning model will take images from the EEG engine 306 as input and will output preference characteristic parameters or product recommendations that object 102 is likely to prefer. In some embodiments, preference characteristic parameters can be used to generate a fragrance profile for object 102, such as... Figure 11 The fragrance notes.

[0082] Therefore, after understanding the fragrance preference characteristics determined based on EEG data and / or optional questionnaire data, the recommendation engine 312 is configured to identify suitable products stored in the product data repository 316 that match or are highly relevant to the preference characteristics determined by the system 100. For example, the recommendation engine 312 can compare the results with product charts, lookup tables, etc., stored in the product data repository 316. This comparison can be based on, for example, a potential match confidence level.

[0083] In some embodiments, the mobile computing device 104 may further include a user data repository 314 configured to store records of each object 102 using the system 100. These records may include, for example, at least one fragrance product, at least one fragrance profile, questionnaire answers, at least one personality trait, at least one product recommendation, and / or other information collected or determined by the system 100. In one embodiment, feedback received from the object 102 after using one or more recommended products may also be stored in the user data repository 322 or forwarded to the product data repository 316 to improve future product recommendations by the system 100.

[0084] The following section provides further details about the actions performed by each of these components.

[0085] "Engine" refers to the logic contained within hardware or software instructions, which can be expressed using programming languages ​​(such as C, C++, COBOL, JAVA). TM , PHP, Perl, HTML, CSS, JavaScript, VBScript, ASPX, Microsoft.NET TMEngines can be written in languages ​​such as Go and / or other programming languages. Engines can be compiled into executable programs or written in interpreted programming languages. Software engines can be invoked from other engines or themselves. Generally, the term "engine" as used herein refers to a logical module that can be merged with other engines or can be divided into sub-engines. Engines can be stored on any type of computer-readable medium or computer storage device and can be stored and executed by one or more general-purpose computers, resulting in a dedicated computer configured to provide the engine or its functionality. In some implementations, the engine can be implemented by one or more circuits, programmable processors, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), and / or field-programmable logic devices (FPLDs).

[0086] "Data repository" refers to any suitable device configured to store data accessible to computing devices. One example of a data repository is a highly reliable, high-speed relational database management system (DBMS) that runs on one or more computing devices and is accessible via a high-speed network. Another example of a data repository is a key-value store. However, any other suitable storage technology and / or device capable of providing stored data quickly and reliably in response to queries can be employed, and the computing device can be accessed locally rather than via a network, or it can be provided as a cloud-based service. A data repository may also include data stored in an organized manner on computer-readable storage media, such as hard disk drives, flash memory, RAM, ROM, or any other type of computer-readable storage media. Those skilled in the art will recognize that the independent data repositories described herein can be combined into a single data repository, and / or the single data storage described herein can be divided into multiple data repositories without departing from the scope of this disclosure.

[0087] Figure 4 This is a block diagram illustrating various components of an alternative server computing system 108 according to one aspect of this disclosure. In these embodiments, one or more functions of the mobile computing device described above may be additionally or alternatively performed by the server computing device 108. For example, fragrance preference information collected by the mobile computing device 104 (e.g., fragrance preferences from fragrance exposure of subject 102 and / or biometric data (e.g., brain activity) from optional questionnaires) may be transmitted to the server computing system 108 via network 110 with or without additional processing (e.g., filtering, transformation, etc.) and / or storage. In this regard, the server computing system 108 may include, for example, an EEG engine 306 ( Figure 3 ), used to process and store EEG signals, and optionally generate such as Figure 9 The electroencephalogram and / or other similar data of the examples shown Figure 10 Brain activity diagram of the example shown.

[0088] In some embodiments, server computing system 108 uses information received from mobile computing device 104 to determine product recommendations for object 102 and transmits these recommendations back to mobile computing device 104 for presentation to object 102. In this regard, server computing system 108 may additionally or alternatively include a questionnaire analysis engine 310, a recommendation engine 312, and / or a product data repository 316, the functions of which have been described in detail above. In some embodiments, server computing system 108 may also include a user data repository 314.

[0089] Figure 5 This is a block diagram illustrating various aspects of a representative computing device 400 suitable for use as a computing device in this disclosure. Although many different types of computing devices have been discussed above, the representative computing device 400 describes various elements common to many different types of computing devices (such as mobile computing device 104 and / or server computing device 108). Although Figure 5 This description is intended in conjunction with computing devices implemented as devices on a network; however, the following description applies to servers, personal computers, mobile phones, smartphones, tablets, computer kiosks, embedded computing devices, and other devices that can be used to implement various parts of the embodiments of this disclosure. Furthermore, those skilled in the art and others will recognize that computing device 400 can be any of any number of currently available or under-development devices.

[0090] In its most basic configuration, computing device 400 includes at least one processor 402 and system memory 404 connected via a communication bus 406. Depending on the exact configuration and type of the device, system memory 404 may be volatile or non-volatile memory, such as read-only memory (“ROM”), random access memory (“RAM”), EEPROM, flash memory, or similar memory technologies. Those skilled in the art and others will recognize that system memory 404 typically stores data and / or program modules that are readily accessible and / or currently being operated by processor 402. In this respect, processor 402 can act as the computing center of computing device 400 by supporting instruction execution.

[0091] like Figure 5As further shown, computing device 400 may include a network interface 410, which includes one or more components for communicating with other devices via a network. Embodiments of this disclosure can access basic services for performing communication via public network protocols using network interface 410. Network interface 410 may also include a wireless network interface configured to communicate via one or more wireless communication protocols (such as WiFi, 2G, 3G, LTE, WiMAX, Bluetooth, Bluetooth Low Energy, and / or similar protocols). As will be understood by those skilled in the art, Figure 5 The network interface 410 shown may represent one or more wireless interfaces or physical communication interfaces described and shown above with respect to specific components of computing device 400.

[0092] In some embodiments of the head-mounted device that include a multiplexer for combining multiple signal channels (one channel per electrode), the network interface of the computing device (such as mobile computing device 104) includes, for example, a demultiplexer implemented in hardware or software to distribute the received EEG signals into their respective channels. Alternatively, the EEG engine 306 may include such a demultiplexer. In these embodiments, the acquired (e.g., received) EEG signals are passed through the demultiplexer so that the mobile computing device 104 processes the EEG signal from each channel as EEG data.

[0093] exist Figure 5 In the exemplary embodiment shown, computing device 400 also includes storage medium 408. However, computing devices that do not include means for saving data to local storage media can be used to access the service. Therefore, Figure 5 The storage medium 408 shown is indicated by a dashed line to show that the storage medium 408 is optional. In any case, the storage medium 408 may be volatile or non-volatile and removable or non-removable, and may be implemented using any technology capable of storing information, such as, but not limited to, hard disk drives, solid-state drives, CD-ROMs, DVDs or other disc storage devices, cassette tapes, magnetic tapes, disk storage, etc.

[0094] As used herein, the term "computer-readable medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology capable of storing information (such as computer-readable instructions, data structures, program modules or other data). In this respect, Figure 5 The system memory 404 and storage medium 408 depicted are merely examples of computer-readable media.

[0095] Suitable implementations of a computing device, including processor circuitry or processor 402, system memory 404, communication bus 406, storage medium 408, and network interface 410, are known and commercially available. For ease of explanation, and because they are not essential for understanding the claimed subject matter, therefore... Figure 5 Many typical components of computing devices are not shown. In this respect, computing device 400 may include input devices such as a keyboard, keypad, mouse, microphone, touch input device, touchscreen, tablet computer, and / or similar devices. Such input devices may be coupled to computing device 400 via wired or wireless connections, including RF (radio frequency) connections, infrared connections, serial connections, parallel connections, Bluetooth connections, Bluetooth Low Energy connections, USB connections, or other suitable connection protocols employing wireless or physical connections. Similarly, computing device 400 may also include output devices such as a display, speakers, printer, etc. Since these devices are well known in the art, they will not be further described or illustrated herein.

[0096] In some embodiments, multiple sensors and / or one or more engines form a fragrance response unit. In some embodiments, the fragrance response unit includes one of the following processing circuitry: processing circuitry configured to detect real-time cognitive processes associated with olfactory stimuli; processing circuitry configured to detect real-time event-related potentials associated with responses to one or more fragrance blends; processing circuitry configured to detect postsynaptic potentials based on responses to olfactory stimuli; or processing circuitry configured to detect voltage fluctuations representing responses to olfactory stimuli.

[0097] In some implementations, one or more engines form a fragrance selection unit comprising one of the following processing circuits: processing circuits configured to generate one or more virtual instances of a subset of fragrances based on at least one input associated with an electroencephalogram; processing circuits configured to generate one or more instances of a satisfaction rating or preference measurement; processing circuits configured to generate one or more instances of a fragrance intensity; processing circuits configured to generate one or more instances of a blend of aromatic compounds; or processing circuits configured to generate one or more instances of base notes, top notes, or middle notes in a fragrance blend.

[0098] Figure 6 This is a flowchart illustrating a non-limiting example of a method for generating product recommendations and / or providing them to an object according to one or more aspects of this disclosure. (The last sentence appears to be incomplete and possibly refers to a separate topic.) Figures 1 to 5 The system 100 described herein is used to describe one or more components of a representative method, typically labeled 600.

[0099] Prior to starting method 600, one or more EEG sensors 106 are coupled to the head of the subject 102. In some embodiments, with or without a reference electrode, only two EEG sensors 106 are placed in the F7 and F8 regions of the subject's brain. In other embodiments, a head-mounted device 114 consisting of multiple EEG sensors 106 is placed on the head of the subject 102. In some of these embodiments, the sensors 106 are also located in the F7 and F8 regions in addition to other regions of the subject's brain. In some embodiments, a reference electrode may be positioned on the subject's head.

[0100] Once the sensor has been properly associated with the head of object 102, the method can begin. Method 600 proceeds from the start step to step 602, in which object 102 is exposed to one or more fragrances. For example, the object is exposed to a series of fragrances. Object 102 is exposed to each fragrance for a period of time. In one embodiment, this period of time is approximately 45 seconds. Of course, shorter or longer periods of time can be used. In other embodiments, this period of time is approximately five (5) minutes or longer. In some embodiments, the fragrances exposed to the object include at least two fragrance notes, such as top notes and middle notes.

[0101] The object's response to one or more fragrances is captured by EEG sensor 106 and transmitted as an EEG signal to mobile computing device 104. At this point, in step 604, mobile device 104 is communicatively coupled to EEG sensor 106 and receives EEG (e.g., biometric) signals from object 102.

[0102] Then, in step 606, the EEG signal can be processed by the EEG engine 306 to generate, for example, EEG data. In some embodiments, the EEG signal is processed by the EEG engine 306 residing on the mobile computing device 104. In other embodiments, the EEG signal is processed by the EEG engine 306 residing on the server computing device 108. In these or other embodiments, the EEG data is stored in the user data repository 314, or locally on the mobile computing device 104, or remotely on the server computing system 108.

[0103] In some embodiments, the actions performed in steps 602, 604, and 606 are repeated for each fragrance that the object 102 is to come into contact with. In other embodiments, the actions performed in steps 602 and 604 may be performed for each fragrance before the actions performed in step 606. In one embodiment, the object comes into contact with four fragrances. Of course, four or more fragrances may be used in embodiments of the present invention.

[0104] In one implementation, object 102 is exposed to a pre-selected set of fragrances. For example, the pre-selected set of fragrances could be the four best-selling fragrances from a company's fragrance line. In other implementations, such as combining... Figure 7 In more detail, system 100 can influence the selection of one or more subsequent fragrances to be applied to the object 102 by utilizing the object 102's reaction to the aforementioned fragrance. For example, EEG data generated by EEG engine 306 based on fragrance application can be displayed on display device 302 as an electroencephalogram or brain activity map. With the assistance of a fragrance consultant, the next fragrance to be applied to the object 102 can be selected. Alternatively, the system can be configured to automatically select the next fragrance to be presented to the object based on the object's reaction to one or more previous fragrances.

[0105] In some embodiments, each fragrance contacted by object 102 includes at least two fragrance notes (e.g., top and middle notes, two middle notes, top and base notes, etc.). In some embodiments, each fragrance contacted by object 102 includes at least three fragrance notes (e.g., top, middle, and base notes (vertical blend), three middle notes (horizontal blend), etc.). In any case, the characteristic parameters of the fragrance contacted by object 102 (e.g., top, middle, and / or base notes) are known and stored in product data repository 316. In some embodiments, the characteristic parameters are stored as, for example, a fragrance profile.

[0106] In some embodiments, in step 608, the user interface engine 308 of the mobile computing device 104 optionally presents a questionnaire to the subject 102. In some embodiments, the questionnaire may include questions that directly express values ​​for the subject 102. For example, the questionnaire may explicitly ask the subject 102 to input fragrance preferences, including specific product names, preferred fragrance notes, or other fragrance characteristics (e.g., whether the subject prefers masculine, feminine, or unisex fragrances). In other embodiments, the user interface engine 308 asks the subject 102 one or more questions, the answers of which can be used to infer the aforementioned or other subject preferences.

[0107] In step 610, the user interface engine 308 receives the questionnaire answers and sends them to the questionnaire analysis engine 310 for processing. In step 612, the questionnaire analysis engine 310 determines one or more fragrance preferences based on the questionnaire answers. In some embodiments, these answers are processed by the questionnaire analysis engine 310 residing on the mobile computing device 104. In some embodiments, these answers are processed by the questionnaire analysis engine 310 residing on the server computing device 108. The user interface engine 308 can receive responses via input on a user interface presented on the display device 302. The questionnaire answers and the results of the answer processing can be stored in the user data repository 314. It should be understood that the actions performed in steps 610 and 612 are also optional.

[0108] In step 614, recommendation engine 312 determines product recommendations based at least on EEG data and optionally on object preferences determined by questionnaire analysis engine 310. For this purpose, recommendation engine 312 can access data in product data repository 316. In some embodiments, the product recommendation is a specific product. In other embodiments, the product recommendation is a fragrance profile. In some embodiments, product recommendations are determined by recommendation engine 312 residing on mobile computing device 104. In other embodiments, product recommendations are determined by recommendation engine 312 residing on server computing device 108.

[0109] In step 616, product recommendations are presented to the recipient. For example, in one embodiment where a specific product is presented, the product recommendation may be displayed on display device 302 along with, for example, a product description (e.g., a fragrance profile), product price, where to purchase the product, etc. In other embodiments where the product recommendation is in the form of a fragrance profile, the fragrance profile may be displayed to a fragrance consultant via display device 302. With the assistance of a fragrance consultant, one or more products may be presented to the recipient based on the fragrance profile.

[0110] Next, this method proceeds to the end step and terminates.

[0111] Figure 7 This is a flowchart illustrating another non-limiting example of a method for generating product recommendations and / or providing them to an object according to one or more aspects of this disclosure. (The last sentence appears to be incomplete and possibly refers to a separate, unrelated statement.) Figures 1 to 5 The system 100 described herein is used to describe one or more components of a representative method, typically labeled 700. Method 700 is essentially similar to the combination described above. Figure 6 The method 600 differs from what will now be described.

[0112] exist Figure 7In one implementation, steps 702, 704, and 706 are performed sequentially for each fragrance the subject will be exposed to. In this implementation, the recommendation engine 312 or other engines in the system determine the next fragrance to be presented to the subject 102 based on the biometric data generated from the fragrance exposure, rather than pre-selecting a fragrance. In some implementations, the recommendation engine 312 determines the next fragrance to be presented to the subject 102 based on the biometric data generated from the fragrance exposure and one or more answers to the questionnaire in step 708. Once all fragrances have been presented to the subject 102, method 700 proceeds to step 716, where the recommendation engine 312 determines a product recommendation.

[0113] In some implementations, the first fragrance to be selected is determined based on one or more answers to a questionnaire. Therefore, the questionnaire can be presented to the subject before any fragrance is introduced.

[0114] The detailed description above, taken in conjunction with the accompanying drawings (where like reference numerals denote like elements), is intended as a description of various embodiments of the present disclosure and is not intended to represent only those embodiments. Each embodiment described in this disclosure is provided by way of example or illustration only and should not be construed as preferred or superior to other embodiments. The illustrative examples provided herein are not exhaustive or limit the disclosure to the exact forms disclosed. Similarly, any step described herein may be interchanged with other steps or combinations thereof to achieve the same or substantially similar results. Furthermore, some method steps may be performed sequentially, simultaneously, or in any order unless specifically stated or understood in the context of the other method steps.

[0115] In the foregoing description, specific details have been set forth to provide a full understanding of exemplary embodiments of the present disclosure. However, it will be apparent to those skilled in the art that embodiments disclosed herein can be practiced without including all of these specific details. In some cases, well-known process steps have not been described in detail to avoid unnecessarily obscuring various aspects of the present disclosure. Furthermore, it should be understood that embodiments of the present disclosure may employ any combination of the features described herein.

[0116] This application may also refer to quantities and numbers. Unless otherwise specified, these quantities and numbers should not be considered limiting, but rather examples of possible quantities or numbers relating to this application. Also in this respect, this application may use the term "multiple" to refer to a quantity or number. In this context, the term "multiple" means any number more than one, such as two, three, four, or five, etc. The terms "approximately," "about," etc., indicate plus or minus 5% of the specified value.

[0117] Technical terms may be used throughout this specification. These terms will take their ordinary meaning in the art to which they pertain, unless specifically defined herein or otherwise expressly implied in the context in which they are used.

[0118] The principles, representative embodiments, and operating modes of this disclosure have been described above. However, the aspects of this disclosure intended to be protected should not be construed as limited to the specific embodiments disclosed. Furthermore, the embodiments described herein should be considered illustrative rather than restrictive. It should be understood that others may make changes and modifications, and may employ equivalents, without departing from the spirit of this disclosure. Therefore, all such changes, modifications, and equivalents are expressly intended to fall within the spirit and scope of this disclosure as claimed.

Claims

1. A system comprising: Multiple EEG electrodes are configured to sense the event-related potential of the object based on its response to a series of fragrances it comes into contact with; and One or more engines, configured as follows: The event-related potential generated by the EEG electrode of the object is received as an EEG signal; The EEG signal is processed to generate EEG data; as well as Product recommendations are generated based at least on the EEG data, wherein the product recommendations are generated by a recommendation engine, the recommendation engine including a machine learning model trained on a set of supervised training data, the supervised training data including EEG images or brain activity maps of objects exposed to known fragrances, and The recommendation engine is configured to determine the next fragrance to be presented to the object from the series of fragrances based on the EEG data generated by the object's contact with previous fragrances in the series of fragrances.

2. The system of claim 1, wherein the one or more engines are housed in a mobile computing device.

3. The system of claim 1, wherein the generated EEG data is represented as an image.

4. The system of claim 3, wherein the image comprises an EEG image or a brain activity map.

5. The system of claim 1, wherein the one or more engines are further configured to generate preference feature parameters of the series of fragrances based on the EEG data, and to generate the product recommendations based on the preference feature parameters.

6. The system of claim 5, wherein the one or more engines are configured to determine product recommendations by comparing data representing the generated preference feature parameters with product data accessible to the one or more engines.

7. The system of claim 5, wherein the data representing the generated preference feature parameters includes a fragrance profile.

8. The system of claim 7, wherein the fragrance profile is presented to the subject as a product recommendation.

9. The system of claim 7, wherein the generated preference feature parameters represent various fragrance notes of the series of fragrances, and wherein the product recommendation is generated by comparing the fragrance profile with a set of fragrance profiles representing the series of fragrances, the set of fragrance profiles being accessible by the one or more engines.

10. The system of claim 1, wherein the one or more engines are configured to detect the event-related potential based on the response to the series of fragrances, the one or more engines including processing circuitry configured to: Detect real-time cognitive processes associated with olfactory stimuli; Detect real-time event-related potentials associated with responses to one or more fragrance blends; The detection measures voltage fluctuations in response to olfactory stimuli; or Postsynaptic potentials are detected based on responses to olfactory stimuli.

11. The system according to claim 1, further comprising: A fragrance selection unit includes processing circuitry configured to generate one or more virtual instances of a subset of fragrances based on at least one input associated with the event-related potential.

12. The system of claim 11, wherein the perfume selection unit further comprises one of the following processing circuits: A processing circuit configured to generate one or more virtual instances of a fragrance subset based on at least one input associated with EEG; Processing circuitry configured to generate one or more instances of the degree of desirability rating or liking measurement; Processing circuitry configured to generate one or more instances of fragrance intensity; Processing circuitry configured to generate one or more instances of aromatic compound blends; or A processing circuit configured to generate one or more instances of base notes, top notes, or middle notes in a fragrance blend.

13. A method for recommending products to an object, comprising: Obtain biometric data in the form of event-related potentials of an object, wherein the biometric data is EEG signals generated by multiple EEG electrodes based on contact with a series of fragrances that the object has come into contact with; The EEG signal is processed to generate EEG data; as well as Product recommendations are generated based at least on the EEG data, wherein the product recommendations are generated by a recommendation engine, the recommendation engine including a machine learning model trained with a set of supervised training data, the supervised training data including EEG images or brain activity maps of objects exposed to known fragrances, and wherein the recommendation engine is configured to determine the next fragrance to be presented to the object in the series of fragrances based on the EEG data generated by the object's exposure to previous fragrances in the series of fragrances.

14. The method according to claim 13, wherein, Generating the product recommendations includes: Present the fragrance name to the object; or Present a fragrance profile to the object.

15. The method of claim 13, further comprising: Obtain questionnaire data from the subjects, the questionnaire data representing preferences for product characteristic parameters. The product recommendations mentioned therein are also based on the questionnaire data.

16. The method according to claim 13, wherein, The product recommendations mentioned are for perfumes.

17. The method according to claim 16, wherein, The product recommendations include: fragrance profiles based on the EEG data.

18. The method of claim 17, further comprising: The fragrance profile is compared with a set of fragrance profiles representing the series of fragrances to select a fragrance from the series of fragrances that has a fragrance profile most similar to the generated fragrance profile.

19. The method according to claim 13, wherein, The EEG electrodes are located in the left and right anterior lobes of the subject and are configured to detect brain activity associated with approach and avoidance in response to exposure to the series of fragrances.

Images