Artificial intelligence-based system and method for analyzing user-specific skin or hair data to predict user-specific skin or hair conditions

Abstract

An artificial intelligence based system and method for analyzing user-specific data to predict a user-specific skin or hair condition. The user-specific data of a user is received in a scalp hair analysis application and defines the user's scalp or hair region including the user's last wash data and at least one other factor of the user. An artificial intelligence based learning model is trained with training data for each individual's scalp and hair region and analyzes the user-specific data to generate a scalp or hair prediction corresponding to the user's scalp or hair region. The application generates a user-specific treatment based on the scalp or hair prediction designed to address at least one characteristic based on the scalp or hair prediction of the user's scalp or hair region.

Description

[Technical Field]

[0001] The present disclosure relates generally to artificial intelligence (AI)-based systems and methods, and more particularly to AI-based systems and methods that analyze user-specific skin or hair data to predict a user-specific skin or hair condition. [Background technology]

[0002] Generally, multiple intrinsic factors of human hair and skin, such as sebum and sweat, have real-world effects on the overall condition of a user's scalp, which may include scalp conditions (e.g., sebum residue, scalp skin stress) and hair follicle / hair conditions (e.g., hair stress, acne, scalp plugs). Additional extrinsic factors, such as wind, humidity, and / or the use of various hair-related products, may also affect the condition of a user's scalp. Furthermore, user perception of scalp-related problems typically does not reflect such underlying intrinsic and / or extrinsic factors.

[0003] Therefore, considering the number of intrinsic and / or extrinsic factors, along with the complexity of scalp and hair types, creates problems, especially when considering different users, each of which may be associated with different demographics, races, and ethnicities. This creates problems in diagnosing and treating various human scalp conditions and characteristics. For example, prior art methods that attempt to assist users in self-diagnosing scalp conditions generally lack sufficient information to generate an accurate, user-specific diagnosis, and as a result, provide broad, overly simplified recommendations. Furthermore, users may attempt to empirically experiment with various products or techniques, but do not achieve satisfactory results and / or experience possible negative side effects that affect the condition or otherwise visual appearance of the user's scalp. Summary of the Invention [Problem to be solved by the invention]

[0004] For the foregoing reasons, there is a need for an AI-based system and method that analyzes user-specific skin or hair data to predict a user-specific skin or hair condition. [Means for solving the problem]

[0005] Generally, as described herein, artificial intelligence (AI)-based systems and methods are described that analyze user-specific skin or hair data to predict a user-specific skin or hair condition. In some embodiments, the AI-based systems and methods herein are configured to input user-specific data to train an AI model to predict scalp sebum on the user's scalp. Such AI-based systems provide AI-based solutions to overcome problems arising from the difficulty of identifying and treating various intrinsic and / or extrinsic factors or attributes that affect the condition of a human scalp, skin, and / or hair.

[0006] Generally, an AI-based system as described herein allows a user to submit user-specific data to a server (e.g., including one or more processors thereof) or other computing device (e.g., locally on the user's mobile device), which implements or executes an AI-based learning model trained with training data of potentially thousands (or more) of user-specific data about each individual's scalp and hair region. Based on the scalp or hair predictions, the AI learning model can generate a user-specific treatment designed to address at least one characteristic of the user's scalp or hair region based on the scalp or hair predictions. For example, the user-specific data can include answers or other inputs indicative of dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant odor, itching, unmanageability, hair loss, hair volume, thinning, detangling, oily hair, dryness, hair odor, acne, scalp plugs, and / or other scalp or hair factors of a particular user's scalp or hair region. In some aspects, the user-specific treatment (and / or product-specific recommendation / treatment) may be transmitted over a computer network to the user's user computing device for rendering on a display screen. In some aspects, transmission of user-specific data to the imaging server is not performed, and the user-specific treatment (and / or product-specific recommendation / treatment) may instead be generated by an AI-based learning model, executed and / or implemented locally on the user's mobile device, and rendered on the mobile device's display screen by the mobile device's processor. In various aspects, such rendering may include graphical representations, overlays, annotations, etc. to address scalp or hair prediction-based features of the user's scalp or hair region.

[0007] In certain aspects, an AI-based system as described herein allows a user to submit images of the user to an imaging server (e.g., including one or more processors thereof) or other computing device (e.g., locally on the user's mobile device), which implements or executes an AI-based learning model trained with pixel data from potentially 10,000 (or more) images depicting each individual's scalp or hair region. Based on the scalp or hair predictions, the AI-based learning model can generate a user-specific treatment designed to address at least one feature identifiable in the pixel data comprising the user's scalp or hair region. For example, a portion of a user's scalp or hair region may include pixels or pixel data indicative of whiteheads, dry scalp, oily scalp, dandruff, stiffness, redness / irritation, itchiness, unmanageability, hair loss, hair volume, thinning, detangling, oily hair, dryness, hair odor, acne, scalp plugs, and / or other scalp or hair factors of the particular user's scalp or hair region. In some embodiments, user-specific treatments (and / or product-specific recommendations / treatments) may be transmitted to the user's user computing device via a computer network for rendering on a display screen. In other embodiments, transmission of the user's image to an imaging server is not performed, and user-specific treatments (and / or product-specific recommendations / treatments) may instead be generated by an AI-based learning model, executed and / or implemented locally on the user's mobile device, and rendered on the mobile device's display screen by the mobile device's processor. In various embodiments, such renderings may include graphical representations, overlays, annotations, etc. to address features within the pixel data.

[0008] More specifically, as described herein, an AI-based system is disclosed. The AI-based learning system is configured to analyze user-specific skin or hair data (also referred to herein as "user-specific data") to predict a user-specific skin or hair condition (also referred to herein as a "scalp or hair prediction value" and a "scalp and hair condition value"). The AI-based system includes one or more processors, a scalp and hair analysis application (app) including computing instructions configured to execute on the one or more processors, and an AI-based learning model. The AI-based learning model is accessible by the scalp and hair analysis app and is trained using training data related to each individual's scalp and hair region. The AI-based learning model is configured to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region. The training data related to each individual's scalp and hair region is selected from one or more values corresponding to each individual's last wash data and at least one of one or more scalp factors, one or more hair factors, or wash frequency. The training data includes data generated using a scalp or hair measurement device configured to determine one or more characteristics of the scalp or hair region. The computing instructions of the scalp hair analysis app, when executed by one or more processors, cause the one or more processors to receive user-specific data for a user defining the user's scalp or hair region, including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; analyze the user-specific data with an AI-based learning model to generate scalp or hair predictions corresponding to the user's scalp or hair region; and generate, based on the scalp or hair predictions, a user-specific treatment designed to address the at least one characteristic of the user's scalp or hair region based on the scalp or hair predictions.

[0009] Additionally, as described herein, an artificial intelligence (AI)-based method is disclosed for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition. The AI-based method includes the steps of receiving user-specific data for a user in a scalp and hair analysis application (app) running on one or more processors, the user-specific data defining the user's scalp or hair regions, the user-specific data including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; and analyzing the user-specific data with an artificial intelligence (AI)-based learning model accessible by the scalp and hair analysis app to generate scalp or hair predictions corresponding to the user's scalp or hair regions, the AI-based learning model being trained using training data for each individual's scalp and hair regions. and generating, by the scalp and hair analysis app based on the scalp or hair predictions, a user-specific treatment designed to address the at least one characteristic of the user's scalp or hair region.

[0010] Further disclosed is a tangible, non-transitory computer-readable medium storing instructions for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition as described herein. The instructions, when executed by one or more processors, cause the one or more processors to receive, at a scalp and hair analysis application (app) running on the one or more processors, user-specific data for a user, the user-specific data including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency, defining the user's scalp or hair region; and cause an artificial intelligence (AI)-based learning model accessible by the scalp and hair analysis app to analyze the user-specific data and generate a scalp or hair prediction corresponding to the user's scalp or hair region, the AI-based learning model using training data for each individual's scalp and hair region. the scalp and hair analysis app is trained with data and configured to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region, the training data for each individual's scalp and hair region being selected from each individual's last wash data and one or more values corresponding to at least one of one or more scalp factors, one or more hair factors, or wash frequency, the training data including data generated with a scalp or hair measurement device configured to determine the one or more characteristics of the scalp or hair region; and based on the scalp or hair predictions, the scalp and hair analysis app generates a user-specific treatment designed to address the at least one characteristic based on the scalp or hair predictions of the user's scalp or hair region.

[0011] In accordance with the above and the disclosure herein, the present disclosure includes improvements in computer functionality or improvements to other technologies, at least because the present disclosure describes, for example, an improvement in a server or other computing device (e.g., a user computing device) when its intelligence or predictive capabilities are enhanced by a trained (e.g., machine learning trained) AI-based learning model. The AI-based learning model running on the server or computing device can more accurately identify one or more user-specific scalp or hair region features, scalp or hair predictions, and / or user-specific treatments designed to address at least one feature based on the scalp or hair predictions of the user's scalp or hair region based on the user-specific data of other individuals. That is, the present disclosure describes an improvement in the functionality of the computer itself or "any other technology or technical field" because the server or user computing device is enhanced with multiple training data (e.g., potentially thousands (or more) of user-specific data regarding each individual's scalp and hair region) to accurately predict, detect, or determine a user's skin or hair condition based on user-specific data such as newly provided customer responses / inputs / images. This is an improvement over the prior art at least because existing systems lack such prediction or classification capabilities and are simply unable to accurately analyze user-specific data to output a prediction result to address at least one feature of the user's scalp or hair region based on a scalp or hair prediction value.

[0012] Specifically, the disclosed systems and methods feature improvements over conventional techniques by training an AI-based learning model using multiple clinical data (e.g., scalp sebum and scalp stress data) related to the scalp and hair condition of multiple individuals. The clinical data generally includes the individuals' self-assessments of their scalp and hair condition in the form of text questionnaire responses for each of the multiple individuals, and physical measurements (e.g., collected using a scalp or hair measurement device) corresponding to each individual's scalp and hair. Once trained using the clinical data, the AI-based learning model provides highly accurate scalp and hair condition predictions for a user, without the need for user images, to a degree unattainable using conventional techniques. In fact, the disclosed AI-based system achieves approximately 75% accuracy when predicting a user's scalp and hair condition values based on user-specific data (e.g., questionnaire responses), reflecting a substantial correlation between the AI-based learning model and the user's actual scalp and hair condition that conventional techniques simply cannot achieve. Additionally, in certain embodiments, the clinical data includes user-specific images corresponding to the self-assessment of each individual among the plurality of individuals, and the users further submit the user-specific images as part of the user-specific data. In these embodiments, the accuracy of the AI-based learning model is further enhanced to provide incredibly accurate scalp and hair predictions for the user that conventional techniques cannot provide.

[0013] For similar reasons, the present disclosure relates to improvements over other technologies or technical fields at least because the present disclosure describes or introduces improvements to computing devices in the scalp and hair care field and scalp and hair care product field, whereby a trained AI-based learning model executing on an imaging device or computing device improves the field of scalp and hair area care, and chemical formulations of said scalp and hair care products, using AI and / or digitally based analysis of user-specific data and / or images to output predictive results, addressing at least one feature identifiable within the user-specific data defining the user's scalp or hair area, including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency.

[0014] Furthermore, the present disclosure relates to improvements to other technologies or technical fields, at least because the present disclosure describes or introduces improvements to computing devices in the scalp and hair care and scalp and hair product fields, whereby trained AI-based learning models running on the computing device and / or imaging device improve the underlying computer device (e.g., server and / or user computing device), and such computer device is made more efficient by configuring, adjusting, or adapting a given machine learning network architecture. For example, in some aspects, reducing the machine learning network architecture required to analyze an image, including reducing depth, width, image size, or other machine learning-based dimensional requirements, reduces computational resources, thereby using fewer machine resources (e.g., processing cycles or memory storage). Such reduction frees up computational resources in the underlying computing system, thereby making it more efficient.

[0015] Additionally, the present disclosure includes applying some of the claim elements in conjunction with or by using a particular machine, e.g., a scalp or hair measurement device, to generate training data used to train an AI-based learning model.

[0016] Additionally, the present disclosure includes adding specific characteristics outside of routine, conventional activities well understood in the art, or non-conventional steps that limit the scope of the claims to particular useful applications, such as analyzing user-specific data defining a user's scalp or hair region to generate a scalp or hair prediction and a user-specific treatment designed to address at least one characteristic based on the scalp or hair prediction of the user's scalp or hair region.

[0017] The advantages will become more apparent to those skilled in the art from the following description of the preferred embodiments shown and described by way of illustration. As will be understood, the present embodiments are capable of other and different embodiments, and their details are capable of modification in various respects. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive. [Brief explanation of the drawings]

[0018] The figures described below depict various aspects of the systems and methods disclosed herein. It should be understood that each figure depicts an aspect of a particular aspect of the disclosed systems and methods, and that each of the figures is intended to correspond to possible aspects thereof. Furthermore, wherever possible, the following description will refer to reference numerals contained in the following figures, wherein features depicted in multiple figures will be designated with consistent reference numerals.

[0019] Although the drawings show arrangements that are presently contemplated, it is to be understood that the present aspects are not limited to the precise arrangements and instrumentality shown. [Figure 1]FIG. 1 illustrates an example artificial intelligence (AI)-based system configured to analyze user-specific skin or hair data to predict a user-specific skin or hair condition, according to various aspects disclosed herein. [Figure 2] FIG. 1 illustrates an example survey correlation diagram that may be used to train and / or implement an AI-based learning model in accordance with various aspects disclosed herein. [Figure 3] 1 is an exemplary correlation table having scalp factors and hair factors correlated to the output of an AI-based learning model, according to various aspects disclosed herein. [Figure 4] FIG. 1 illustrates an AI-based method for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition, according to various aspects disclosed herein. [Figure 5A] FIG. 1 illustrates an exemplary user interface rendered on a display screen of a user computing device in accordance with various aspects disclosed herein. [Figure 5B] FIG. 10 illustrates another example user interface rendered on a display screen of a user computing device in accordance with various aspects disclosed herein.

[0020] These figures depict preferred embodiments for purposes of illustration only. Alternative embodiments of the systems and methods illustrated herein may be employed without departing from the inventive principles described herein. DETAILED DESCRIPTION OF THE INVENTION

[0021] 1 illustrates an exemplary AI-based system 100 configured to analyze user-specific skin or hair data to predict a user-specific skin or hair condition according to various aspects disclosed herein. Generally, as referred to herein, the user-specific skin or hair data may include user answers / inputs related to questions / prompts to the user regarding the condition of the user's scalp and / or hair, presented to the user via a display and / or user interface of the user's computing device. For example, the user-specific skin or hair data may include when the user last washed their hair (e.g., 3 hours ago, 1 day ago, 5 days ago, etc.) and a user answer indicating that the user experienced a significant amount of scalp dryness. In certain aspects, the user-specific skin or hair data may also include an image of the user's head, and more particularly, the user's scalp.

[0022] In the exemplary embodiment of FIG. 1 , the AI-based system 100 includes a server 102, which may include one or more computer servers. In various embodiments, the server 102 includes multiple servers, which may include multiple redundant or replicated servers as part of a server farm. In still further embodiments, the server 102 may be implemented as a cloud-based server, such as a cloud-based computing platform. For example, the server 102 may be any one or more cloud-based platforms, such as MICROSOFT AZURE, AMAZON AWS, etc. The server 102 may include one or more processors 104, one or more computer memories 106, and an AI-based learning model 108.

[0023] The memory 106 may include one or more forms of volatile and / or non-volatile fixed and / or removable memory, such as read-only memory (ROM), electronic programmable read-only memory (EPROM), random access memory (RAM), erasable electronic programmable read-only memory (EEPROM), and / or other hard drives, flash memory, MicroSD cards, etc. The memory 106 may store an operating system (OS) (e.g., Microsoft Windows, Linux, UNIX, etc.) that may facilitate functions, apps, methods, or other software as discussed herein. The memory 106 may also store various training data (e.g., potentially thousands (or more) of user-specific data regarding each individual's scalp and hair area) and an AI-based learning model 108, which in certain aspects may be a machine learning model trained on images (e.g., images 114), as described herein. Additionally or alternatively, the AI-based learning model 108 may also be stored in a database 105, which is accessible to or otherwise communicatively coupled to the server 102. In addition, the memory 106 may also store machine-readable instructions, including any of one or more applications (e.g., scalp and hair applications as described herein), one or more software components, and / or one or more application programming interfaces (APIs), which may be implemented to facilitate or perform the features, functions, or other disclosures described herein, such as any methods, processes, elements, or limitations, as illustrated, depicted, or described in the various flow diagrams, illustrations, diagrams, figures, and / or other disclosures herein.For example, at least some of the applications, software components, or APIs may be, include, or otherwise be part of an AI-based machine learning model or component, such as AI-based learning model 108, where each may be configured to facilitate their various functions as discussed herein. It should be understood that one or more other applications may be envisioned and executed by processor 104.

[0024] The processor 104 is connected to the memory 106 via a computer bus that carries electronic data, data packets, or otherwise electronic signals between the processor 104 and the memory 106, and may implement or execute machine-readable instructions, methods, processes, elements, or limitations as illustrated, depicted, or described in the various flow diagrams, illustrations, diagrams, figures, and / or other disclosures herein.

[0025] Processor 104 may interface with memory 106 via a computer bus and execute an operating system (OS). Processor 104 may also interface with memory 106 via the computer bus and may create, read, update, delete, or otherwise access or interact with data stored in memory 106 and / or database 104 (e.g., a relational database such as Oracle, DB2, MySQL, or a NoSQL-based database such as MongoDB). The data stored in memory 106 and / or database 105 may include, for example, training data (e.g., as collected by user computing devices 111c1-111c3 and / or 112c1-112c3 and / or scalp or hair measurement device 111c4); images and / or user images (e.g., including image 114); and / or other information and / or images of users including demographics, age, race, skin type, hair type, hairstyle, etc., or all or a portion of the data or information described herein, including as otherwise described herein.

[0026] Server 102 may further include a communications component configured to communicate (e.g., send and receive) data via one or more external / network ports to one or more network or local terminals, such as computer network 120 and / or terminal 109 (for rendering or visualization) described herein. In some aspects, server 102 may include client-server platform technology, such as ASP.NET, Java J2EE, Ruby on Rails, Node.js, web services, or online APIs, responsible for receiving and responding to electronic requests. Server 102 may implement client-server platform technology that can interact with memory 106 (including applications, components, APIs, data, etc. stored therein) and / or database 105 via a computer bus to implement or perform machine-readable instructions, methods, processes, elements, or limitations as illustrated, depicted, or described in the various flow diagrams, illustrations, diagrams, illustrations, and / or other disclosures herein.

[0027] In various aspects, server 102 may include or interact with one or more transceivers (e.g., WWAN, WLAN, and / or WPAN transceivers) that function according to IEEE, 3GPP, or other standards and that may be used to receive and transmit data via an external / network port connected to computer network 120. In some aspects, computer network 120 may include a private network or a local area network (LAN). Additionally or alternatively, computer network 120 may include a public network, such as the Internet.

[0028] The server 102 may further include or implement an operator interface configured to present information to and / or receive input from an administrator or operator. As shown in FIG. 1 , the operator interface may provide a display screen (e.g., via terminal 109). The server 102 may also provide I / O components (e.g., ports, capacitive or resistive touch-sensitive input panels, keys, buttons, lights, LEDs), which may be directly accessible via or attached to the imaging server 102, or indirectly accessible via or attached to the terminal 109. According to some aspects, an administrator or operator may access the server 102 via terminal 109 to review information, make changes, input training data or images, initiate training of the AI-based learning model 108, and / or perform other functions.

[0029] As described herein, in some aspects, server 102 may perform functions as discussed herein as part of a “cloud” network or may otherwise communicate with other hardware or software components in the cloud to transmit, retrieve, or otherwise analyze data or information as described herein.

[0030] Generally, a computer program or computer-based product, application, or code (e.g., a model such as the AI models described herein or other computing instructions) may be stored on a computer-usable storage medium having such computer-readable program code or computer instructions embodied therein, or on a tangible, non-transitory computer-readable medium (e.g., standard random access memory (RAM), an optical disk, a universal serial bus (USB) drive, etc.), and the computer-readable program code or computer instructions may be installed on or otherwise adapted to be executed by processor 104 (e.g., working in association with a respective operating system in memory 106) to facilitate, implement, or perform the machine-readable instructions, methods, processes, elements, or limitations as illustrated, depicted, or described in the various flow diagrams, illustrative diagrams, schematics, figures, and / or other disclosures herein. In this regard, the program code may be implemented in any desired programming language and may be implemented as machine code, assembly code, bytecode, interpreted source code, or the like (e.g., via Golang, Python, C, C++, C#, Objective-C, Java, Scala, ActionScript, JavaScript, HTML, CSS, XML, etc.).

[0031] 1, server 102 is communicatively coupled to one or more user computing devices 111c1-111c4 via computer network 120 and / or to 112c1-112c4 via base stations 111b and 112b. In some aspects, base stations 111b and 112b may include cellular base stations, such as cell towers, that communicate with one or more user computing devices 111c1-111c4 and 112c1-112c4 via wireless communications 121 based on any one or more of a variety of cellular standards, including NMT, GSM, CDMA, UMMTS, LTE, 5G, etc. Additionally or alternatively, base stations 111b and 112b may include routers, wireless switches, or other such wireless connection points that communicate with one or more user computing devices 111c1-111c4 and 112c1-112c4 via wireless communication 122 based on any one or more of a variety of wireless standards, including, by way of non-limiting example, IEEE 802.11a / b / c / g (WIFI), BLUETOOTH standards, etc.

[0032] Any of one or more of user computing devices 111c1-111c4 and / or 112c1-112c4 may comprise a mobile device and / or client device for accessing and / or communicating with server 102. Such client devices may comprise one or more mobile processors and / or imaging devices for capturing images, such as images (e.g., image 114) as described herein. In various aspects, user computing devices 111c1-111c3 and / or 112c1-112c3 may include mobile phones (e.g., cellular phones), tablet devices, personal data assistance (PDAs), etc., including, by non-limiting example, an APPLE iPhone or iPad device, or a GOOGLE ANDROID-based mobile phone or tablet.

[0033] In certain embodiments, any of user computing devices 111c1-111c3, 112c1-112c3 may include an integrated camera configured to capture image data including one or more sebum images that define an amount of human sebum identifiable in the pixel data of the one or more sebum images. For example, user computing device 111c3 may be a smartphone with an integrated camera that includes a lens that a user can apply (referred to herein as "tapping") to the user's skin surface (e.g., scalp or hair) to distribute sebum on the camera lens and thereby capture image data including one or more sebum images. In these examples, user computing device 111c3 may include instructions that cause a processor of device 111c3 to analyze the captured sebum images and determine the amount and / or type of human sebum represented in the captured sebum images. Further, in these examples, the sebum image may not include a fully resolved visualization, but instead may characterize a sebum pattern that the processor of device 111c3 can analyze and match with known sebum patterns / distributions to determine the amount of sebum distributed across the camera lens. The processor of device 111c3 may thereby extrapolate the amount of sebum distributed across the camera lens to determine the amount of sebum that may have been distributed across the user's scalp / forehead.

[0034] In certain embodiments, the user computing device 111c4 may be a scalp or hair measurement device that a user can use to measure one or more factors of the user's scalp or hair. Specifically, the scalp or hair measurement device 111c4 may include a probe or other device configured to apply a reactive tape or other substrate to the user's skin surface. The reactive tape or other substrate may absorb or otherwise lift oil (e.g., sebum) from the user's skin surface, and then an optical measurement process may be used to quantitatively measure the oil based on the amount and type of residue present on the reactive tape or other substrate. As a specific example, the scalp or hair measurement device 111c4 may be a SEBUMETER SM 815 device developed by COURAGE+KHAZAKA ELECTRONIC GMBH. In this example, a user may apply a probe with matte tape to the user's scalp or hair and apply sebum to the matte tape. The user may then assess the sebum content present on the tape using a grease spot photometer to determine the sebum level on the user's scalp or hair.

[0035] In an additional aspect, user computing device 112c4 may be a portable microscope device that a user can use to capture detailed images of the user's scalp or hair. Specifically, portable microscope device 112c4 may include a microscope camera configured to capture images of the user's scalp or hair region (e.g., any one or more of images 202a, 202b, and / or 202c) at a near-microscopic level. For example, unlike any of user computing devices 111c1-111c4 and 112c1-112c3, portable microscope device 112c4 may capture detailed, high-magnification (e.g., 2 megapixels at 60-200x magnification) images of the user's scalp or hair region while maintaining physical contact with the user's scalp or hair. As a specific example, portable microscope device 112c4 may be an API 202 HAIR SCALP ANALYSIS device developed by ARAM HUVIS. In certain embodiments, the portable microscope device 112c4 may also include a display or user interface configured to display captured images and / or results of image analysis to a user.

[0036] Additionally or alternatively, the scalp or hair measurement device 111c4 and / or the portable microscope device 112c4 may be communicatively coupled to the user computing device 111c1, 112c1 (e.g., the user's mobile phone) via a WiFi connection, a BLUETOOTH connection, and / or any other suitable wireless connection, and the scalp or hair measurement device 111c4 and / or the portable microscope device 112c4 may be compatible with various operating platforms (e.g., Windows, iOS, Android, etc.). Thus, the scalp or hair measurement device 111c4 and / or the portable microscope device 112c4 may transmit the user's scalp or hair factors and / or captured images to the user computing device 111c1, 112c1 for analysis and / or display to the user. Additionally, the portable microscope device 112c4 may be configured to capture high-quality video of the user's scalp and stream the high-quality video of the user's scalp to a display of the portable microscope device 112c4 and / or the communicatively coupled user computing device 112c1 (e.g., the user's mobile phone). In certain additional aspects, the components of each of the scalp or hair measurement device 111c4 and / or the portable microscope device 112c4 and the communicatively connected user computing devices 111c1, 112c1 may be incorporated into a single device.

[0037] In additional aspects, user computing devices 111c1-111c3 and / or 112c1-112c3 may comprise retail computing devices. The retail computing devices may comprise user computing devices configured in the same or similar manner as mobile devices as described herein with respect to user computing devices 111c1-111c3 and 112c1-112c3, for example, including having a processor and memory for implementing AI-based learning model 108 as described herein or for communicating with AI-based learning model 108 (e.g., via server 102). Additionally or alternatively, the retail computing devices may be located, installed, or otherwise positioned within a retail environment to enable users and / or customers of the retail environment to utilize the AI-based systems and methods on-site within the retail environment. For example, the retail computing devices may be installed within a kiosk for access by users. The user may then complete a questionnaire and / or upload or transfer images (e.g., from the user's mobile device) to the kiosk to implement the AI-based systems and methods described herein. Additionally or alternatively, the kiosk may be configured with a camera to allow the user to take new images of themselves (e.g., in a private manner, if warranted) for uploading and transfer. In such aspects, the user or consumer themselves may use the retail computing device to receive and / or render user-specific treatments for the user's scalp or hair region on a display screen of the retail computing device, as described herein.

[0038] Additionally or alternatively, the retail computing device may be a mobile device (as described herein) carried by an employee or other personnel of the retail environment to interact with users or consumers on-site. In such aspects, the user or consumer may be able to interact with the employee or other personnel of the retail environment via the retail computing device (e.g., by providing responses to a questionnaire, by transferring images from the user's mobile device to the retail computing device, or by capturing new images with a camera on the retail computing device) to receive and / or render a user-specific treatment for the user's scalp or hair region on a display screen of the retail computing device, as described herein.

[0039] In various aspects, one or more of user computing devices 111c1-111c3 and / or 112c1-112c4 may implement or execute an operating system (OS) or mobile platform, such as the Apple iOS and / or Google Android operating systems. Any of one or more of user computing devices 111c1-111c3 and / or 112c1-112c3 may include one or more processors and / or one or more memories for storing, implementing, or executing computing instructions or code, such as a mobile application or a home or personal assistant application, as described in various aspects herein. As shown in FIG. 1 , the AI-based learning model 108 and / or imaging application described herein, or at least a portion thereof, may also be stored locally on the memory of a user computing device (e.g., user computing device 111c1).

[0040] User computing devices 111c1-111c4 and / or 112c1-112c4 may comprise wireless transceivers for receiving and transmitting wireless communications 121 and / or 122 to and from base stations 111b and / or 112b. In various aspects, user-specific data (e.g., user responses / inputs to questionnaires presented on user computing device 111c1, measurement data acquired by scalp or hair measurement device 111c4) and / or pixel-based images (e.g., image 114) may be transmitted to server 102 via computer network 120 for training a model (e.g., AI-based learning model 108) and / or analysis as described herein.

[0041] Additionally, one or more of user computing devices 111c1-111c3 and / or 112c1-112c4 may include an imaging device and / or a digital video camera for capturing or filming digital images and / or frames (e.g., image 114). Each digital image may include pixel data for training or implementing a model, such as an AI or machine learning model, as described herein. For example, the imaging device and / or digital video camera of any of user computing devices 111c1-111c3 and / or 112c1-112c4 may be configured to film, capture, or otherwise generate digital images (e.g., pixel-based images 114), and, in at least some aspects, may store such images in memory of the respective user computing device. Additionally or alternatively, such digital images may also be transmitted to and / or stored in memory 106 and / or database 105 of server 102.

[0042] Still further, each of one or more user computing devices 111c1-111c3 and / or 112c1-112c4 may include a display screen for displaying graphics, images, text, products, user-specific actions, data, pixels, features, and / or other visualizations or information as described herein. In various aspects, graphics, images, text, products, user-specific actions, data, pixels, features, and / or other such visualizations or information may be received from server 102 for display on the display screen of any one or more of user computing devices 111c1-111c3 and / or 112c1-112c4. Additionally or alternatively, a user computing device may comprise, implement, have access to, render, or otherwise expose, at least in part, an interface or guided user interface (GUI) for displaying text and / or images on its display screen.

[0043] In some aspects, computing instructions and / or applications executing on a server (e.g., server 102) and / or on a mobile device (e.g., mobile device 111c1) may be communicatively connected to analyze user-specific data defining the user's scalp or hair region, including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency, to generate a user-specific treatment, as described herein. For example, one or more processors (e.g., processor 104) of server 102 may be communicatively coupled to the mobile device via a computer network (e.g., computer network 120). For ease of description, the user-specific data and the last wash data may be collectively referred to herein as "user-specific data."

[0044] 2 illustrates an exemplary questionnaire correlation diagram 200 that may be used to train and / or implement an AI-based learning model according to various aspects disclosed herein. Generally, questionnaire correlation diagram 200 may represent or correspond to user data or information input or used by various correlations determined and / or utilized by the AI-based learning model to associate user-specific data (e.g., each of scalp factor section 202a, hair factor section 202b, and last wash section 202c) with scalp and hair predictions (e.g., each of scalp quality score section 206a, scalp turnover section 206b, scalp stress level section 206c, and hair stress level section 206d). A user may run a scalp hair analysis application (app), which may then display a user interface that may include sections / prompts similar to those provided in sections 202a, 202b, and / or 202c. If the user indicates one or more of the factors included in one or more of the sections, the AI-based learning model may analyze the user-specific data to generate scalp and hair predictions, and the scalp and hair analysis app may render a user interface that may include sections similar to sections 206a, 206b, 206c, and / or 206d.

[0045] The user-specific data may include a scalp factor section 202a that prompts the user to provide user-specific data directed to one or more scalp factors of the user's scalp and provides user-specifiable options. For example, the scalp factor section 202a may query the user whether the user is experiencing any scalp problems and may require the user to select one or more of the options presented as part of the scalp factor section 202a. The one or more options (e.g., scalp factors) may include, for example, dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant scalp odor, itching, unperceived problems, and / or any other suitable scalp factor, or combinations thereof. The user may indicate each applicable scalp factor, for example, through interaction with a user interface of a scalp and hair analysis app running on the user's computing device (e.g., user computing device 111c1). For each scalp factor indicated by the user, the AI-based learning model may incorporate the indicated scalp factor as part of its analysis of the user-specific data to generate a scalp and hair prediction for the user (e.g., each of 206a, 206b, 206c, 206d). That is, scalp factor correlations 204a represent multiple correlations that the AI-based learning model may determine and / or utilize to generate a scalp and hair prediction for the user based in part on the indicated scalp factors.

[0046] Additionally, the user-specific data may include a hair factor section 202b that prompts the user to provide user-specific data directed to one or more hair factors of the user's hair and provides user-specifiable options. For example, the hair factor section 202b may query the user whether the user is experiencing any hair problems and may require the user to select one or more of the options presented as part of the hair factor section 202b. The one or more options (e.g., hair factors) may include, for example, unmanageability, hair loss, hair volume, thinning, detangling, oily hair, dryness, hair odor, unperceived issues, and / or any other suitable hair factor, or combinations thereof. The user may indicate each applicable hair factor, for example, through interaction with a user interface of a scalp hair analysis app running on the user's computing device (e.g., user computing device 111c1). For each hair factor indicated by the user, the AI-based learning model may incorporate the indicated hair factor as part of its analysis of the user-specific data to generate a scalp and hair prediction for the user (e.g., each of 206a, 206b, 206c, 206d). That is, hair factor correlations 204b illustrate multiple correlations that the AI-based learning model may determine and / or utilize to generate a scalp and hair prediction for the user based in part on the indicated hair factors.

[0047] Additionally, the user-specific data may include a last wash section 202c that prompts the user to provide user-specific data directed to the user's last wash of their hair and provides user-specifiable options. Generally, scalp and hair sebum and other characteristics accumulate and / or change substantially over time based on when the user last washed their hair. Therefore, each scalp or hair prediction output by the AI-based learning model is significantly influenced by the user's responses to the last wash section 202c. For example, the last wash section 202c may query the user regarding the last time the user washed their hair and may require the user to select one or more of the options presented as part of the last wash section 202c. The one or more options (e.g., last wash) may include, for example, less than three hours before providing a survey response / input, less than 24 hours before providing a survey response / input, more than 24 hours before providing a survey response / input, and / or any other suitable last wash data, or a combination thereof. Of course, it should be understood that the one or more options presented in last wash section 202c may include any suitable option for the user to input when they last washed their hair, such as a sliding scale and / or a manually entered number (e.g., by typing on a keyboard or a virtually rendered keyboard on the user's mobile device) indicating the number of hours, days, etc. since the user last washed their hair.

[0048] In either case, the user may indicate an applicable last wash option, for example, through interaction with a user interface of a scalp and hair analysis app executing on the user's computing device (e.g., user computing device 111c1). When the user indicates a last wash option, the AI-based learning model may incorporate the indicated last wash option as part of its analysis of the user-specific data to generate the user's scalp and hair predictions (e.g., each of 206a, 206b, 206c, and 206d). That is, last wash correlation 204c indicates multiple correlations that the AI-based learning model may determine and / or utilize to generate the user's scalp and hair predictions based in part on the indicated last wash of the user's hair.

[0049] The scalp and hair predictions may include a scalp quality score section 206a, which may display the user's scalp quality score. For example, as a result of the AI-based learning model analyzing user-specific data (e.g., derived from each of the scalp factor section 202a, the hair factor section 202b, and / or the last wash section 202c), the AI-based learning model may generate the user's scalp quality score, represented by a graphical score 206a1. The graphical score 206a1 may indicate to the user that the user's scalp quality score is, for example, 3.5 out of a maximum possible score of 4. However, it should be understood that the scalp quality score may be represented to the user as a graphical rendering (e.g., the graphical score 206a1), an alphanumeric value, a color value, and / or any other suitable representation, or a combination thereof.

[0050] Furthermore, the AI-based learning model may also generate a scalp quality score description 206a2 that may inform the user about the received scalp quality score (e.g., represented by the graphical score 206a1) as part of the scalp or hair prediction. The scalp hair analysis app may render the scalp quality score description 206a2 as part of the user interface once the AI-based learning model has completed analyzing the user-specific data. The scalp quality score description 206a2 may include, for example, a description of the predominant scalp / hair factors and / or last wash data that led to the score decrease, the intrinsic / extrinsic factors causing the scalp and / or hair problem, and / or any other information, or a combination thereof. As an example, the scalp quality score description 206a2 may inform the user that their scalp turnover is slightly dysregulated and, as a result, the user may experience unmanageable hair. Further, in this example, scalp quality score description 206a2 may inform the user that irritants such as ultraviolet (UV) radiation, pollution, and oxidants can disrupt and / or otherwise cause the natural scalp turnover cycle to become unregulated. Thus, scalp quality score description 206a2 may indicate to the user that if scalp turnover is unregulated / dysregulated, the scalp may become hard, dry, and oily, which may cause the user's hair to grow in an unmanageable manner.

[0051] Additionally, the scalp and hair predictions may include a scalp turnover section 206b that may display the user's scalp turnover level. For example, as a result of the AI-based learning model analyzing user-specific data (e.g., derived from each of the scalp factor section 202a, hair factor section 202b, and / or last wash section 202c), the AI-based learning model may generate the user's scalp turnover level, represented by a sliding scale and corresponding indicator in the scalp turnover section 206b. Generally, the indicator located on the sliding scale in the scalp turnover section 206b may graphically indicate the user's scalp turnover level to the user, between a fully regulated scalp turnover level and a fully dysregulated scalp turnover level. In the exemplary embodiment shown in FIG. 2, the user's scalp turnover level represented in the scalp turnover section 206b indicates that the user's scalp turnover is slightly dysregulated. The indicator may also provide a numerical representation of the user's scalp turnover, indicating to the user that the user's scalp turnover level is, for example, 4.3 out of a maximum possible score of 5. Of course, the scoring scale may include any suitable minimum and / or maximum values (e.g., 0 to 5, 1 to 6, 0 to 100, etc.). In any event, it should be understood that the scalp turnover level may be represented to the user as a graphical rendering (e.g., a sliding scale and indicator in scalp turnover section 206b), an alphanumeric value, a color value, and / or any other suitable representation, or combination thereof.

[0052] Further, the scalp and hair prediction may include a scalp stress level section 206c that may display the user's scalp stress level. For example, as a result of the AI-based learning model analyzing user-specific data (e.g., derived from each of the scalp factor section 202a, the hair factor section 202b, and / or the last wash section 202c), the AI-based learning model may generate the user's scalp stress level, represented by a sliding scale and corresponding indicator in the scalp stress level section 206c. Generally, the indicator located on the sliding scale in the scalp stress level section 206c may graphically indicate the user's scalp stress level to the user, between low and high scalp stress. In the exemplary embodiment shown in FIG. 2, the user's scalp stress level represented in the scalp stress level section 206c indicates that the user's scalp stress level is relatively low (e.g., within the "ideal" portion of the sliding scale). The indicator may also provide a numerical representation of the user's scalp stress level, indicating to the user that the user's scalp stress level is, for example, 9.2 out of a maximum possible score of 10. Of course, the scoring scale may include any suitable minimum and / or maximum values (e.g., 0 to 5, 1 to 6, 0 to 100, etc.). In any event, it should be understood that the scalp stress level may be represented to the user as a graphical rendering (e.g., a sliding scale and indicator in scalp stress level section 206c), an alphanumeric value, a color value, and / or any other suitable representation, or combination thereof.

[0053] Further, the scalp and hair prediction may include a hair stress level section 206d, which may display the user's hair stress level. For example, as a result of the AI-based learning model analyzing user-specific data (e.g., derived from each of the scalp factor section 202a, hair factor section 202b, and / or last wash section 202c), the AI-based learning model may generate the user's hair stress level, represented by a sliding scale and corresponding indicator in the hair stress level section 206d. Generally, the indicator located on the sliding scale in the hair stress level section 206d may graphically indicate the user's hair stress level to the user, between low and high hair stress. In the exemplary embodiment shown in FIG. 2 , the user's hair stress level represented in the hair stress level section 206d indicates that the user's hair stress level is relatively low. The indicator may also provide a numerical representation of the user's hair stress level, indicating to the user that the user's hair stress level is, for example, 95 out of a maximum possible score of 100. Of course, the scoring scale may include any suitable minimum and / or maximum values (e.g., 0 to 5, 1 to 6, 0 to 100, etc.) In any event, it should be understood that the hair stress level may be represented to the user as a graphical rendering (e.g., a sliding scale and indicator in hair stress level section 206d), an alphanumeric value, a color value, and / or any other suitable representation, or combination thereof.

[0054] Additionally, user-specific data submitted by a user as input to an AI-based learning model may include user image data. Specifically, in certain embodiments, the image data may include one or more sebum images defining the amount of human sebum identifiable within the pixel data of the one or more sebum images. These sebum images may be captured according to the aforementioned tapping techniques, as described herein, and / or via the portable microscope device 112c4 of FIG. 1. Each sebum image may be used to train and / or implement an AI-based learning model for use across a variety of different users with a variety of different scalp or hair region features. For example, as shown in image 114 of FIG. 1, the user's scalp or hair region in this image includes scalp and hair region features of the user's scalp identifiable in the pixel data of image 114. These scalp and hair region features include, for example, white sebum residue and one or more lines / cracks in the scalp, which the AI-based learning model can identify in the image 114 and use to generate a scalp or hair prediction (e.g., any one or more of the scalp quality score section 206a, scalp turnover section 206b, scalp stress level section 206c, and hair stress level section 206d) and / or a user-specific treatment for the user represented in the image 114, as described herein.

[0055] FIG. 3 illustrates an exemplary correlation table 300 having scalp factors and hair factors correlated to the output of an AI-based learning model according to various aspects disclosed herein. Generally, correlation table 300 provides an exemplary representation of correlations drawn between user-specific data (e.g., each of the problems / data included as part of current scalp problems section 302a, current hair problems section 302b, and last hair wash section 302c) and scalp or hair prediction values (e.g., represented by values included in result column 304c). Correlation table 300 includes each of the aforementioned user-specific data types (e.g., current scalp problems, current hair problems, and last wash data) as represented in sections 302a, 302b, and 302c. While FIG. 3 illustrates three user-specific data types for user-specific data, including current scalp problems, current hair problems, and last wash data, it should be understood that additional data types (e.g., user lifestyle / habits, etc.) are similarly contemplated herein.

[0056] Additionally, correlation table 300 includes a user self-selection question column 304 a, a self-reported measure column 304 b, and a results column 304 c. Each column 304 a, 304 b, and 304 c contains values that are correlated to values in other columns through a multiple correlation framework (e.g., as shown in FIG. 2 ) defined by statistical analysis trained / utilized by an AI-based learning model.

[0057] More specifically, training the AI-based learning model may include constructing a multivariate regression analysis using clinical data (e.g., data captured by scalp or hair measurement device 111c4) to correlate each value / answer included as part of the user-specific data to a scalp and hair prediction value. By way of example, the AI-based learning model may include or utilize a multivariate regression analysis of the following form:

[0058]

number

[0059] More generally, each user-specific concern / perception may correspond to a binary (e.g., yes / no) response from the user regarding the corresponding user-specific data value, and / or may correspond to a sliding scale value, an alphanumeric value, a multiple choice response (e.g., yes / no / maybe), and / or any other suitable response type, or combination thereof. Utilizing a regression model similar to the general model provided in Equation (1), as previously described, the AI-based learning model can achieve approximately 75% accuracy when generating a user's scalp or hair prediction value based on user-specific data, reflecting a substantial correlation between the AI-based learning model and the user's actual scalp and hair condition that conventional techniques simply cannot achieve.

[0060] For example, assume that an AI-based learning model receives user input regarding each of the user-specific data represented in each of sections 302a, 302b, and 302c, and more particularly, in the user self-selected question column 304a. Assume that the user is concerned about a dry scalp (first entry in column 304a), indicates that the user last washed their hair less than 24 hours ago, and has no concerns regarding any of the other issues included in the user self-selected question column 304a. In this scenario, the AI-based learning model may determine that (1) the user is potentially concerned about having a dry scalp, as indicated by the corresponding first entry in the self-reported measure column 304b; (2) the user likely last washed their hair approximately 12 hours before providing the user input, as indicated by the penultimate entry in the self-reported measure column 304b; and (3) the user does not perceive and / or has no concerns regarding the other issues in column 304a and the corresponding concerns / perceptions in column 304b. Thus, the AI-based learning model may correlate user input to values in the results column 304c by applying a regression model generally described in equation (1) to generate predicted values for the user's scalp or hair (e.g., scalp quality score section 206a, scalp turnover section 206b, scalp stress level section 206c, and hair stress level section 206d of FIG. 2).

[0061] Results column 304c generally includes a representation of the relative strength of correlation between the values included in each of user self-selection question column 304a and self-reported measure column 304b and the scalp or hair prediction values included in results column 304c. For example, as shown in current scalp problem results section 306, the values included in the corresponding sections of columns 304a and 304b are most strongly correlated with scalp quality score and least strongly correlated with hair stress level. In fact, two values (e.g., stiffness and redness) are not correlated with any of the scalp or hair prediction values included in results column 304c. As another example, as shown in last hair wash results section 308, the values included in the corresponding sections of columns 304a and 304b are most strongly correlated with scalp quality score, less strongly correlated with scalp turnover, and not correlated at all with scalp or hair stress level.

[0062] 4 illustrates an AI-based method 400 for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition according to various aspects disclosed herein. The user-specific data used in method 400, and more generally described herein, is user responses / inputs received by a user computing device (e.g., user computing device 111c1). In some aspects, the user-specific data may include or reference multiple responses / inputs, such as multiple user responses collected by the user computing device while running a scalp hair analysis application (app) described herein.

[0063] At block 402, method 400 includes receiving user-specific data for a user at a scalp hair analysis application (app) executing on one or more processors (e.g., one or more processors 104 of server 102 and / or a processor of a computer user device such as a mobile device). The user-specific data may define the user's scalp or hair region and the user's last wash data. Generally, the user-specific data may include non-image data, such as user responses / inputs to a questionnaire presented as part of execution of the scalp hair analysis app. The scalp or hair region defined by the user-specific data may correspond to one of: (1) the user's scalp region, (2) the user's hair region, and / or any other suitable scalp or hair region of the user, or a combination thereof.

[0064] However, in certain aspects, the user-specific data may comprise both image data and non-image data, and the image data may be a digital image captured by an imaging device (e.g., an imaging device of user computing device 111c1 or 112c4). In these aspects, the image data may include pixel data of at least a portion of the user's scalp or hair region. In particular, in certain aspects, the user's scalp or hair region may include at least one of: (i) a frontal scalp region, (ii) a frontal hair region, (iii) a central scalp region, (iv) a central hair region, (v) a custom-defined scalp region, (vi) a custom-defined hair region, (vii) a forehead region, and / or other suitable scalp or hair regions, or combinations thereof.

[0065] In certain aspects, the one or more processors may include a processor of a mobile device, which may include at least one of a handheld device (e.g., user computing device 111c1) and / or a scalp or hair measurement device (e.g., scalp or hair measurement device 111c4). Thus, in these aspects, the handheld device and / or scalp or hair measurement device may independently or collectively receive user-specific data of a user. For example, if the handheld device executes a scalp hair analysis app, the handheld device may receive user input in response to a questionnaire presented as part of the scalp hair analysis app execution. Additionally, the user may apply a scalp or hair measurement device to the user's scalp or hair area and receive sebum data associated with the user. The handheld device and / or scalp or hair measurement device may receive the user input and sebum data (collectively, user-specific data) and process / analyze the user-specific data according to the operations of method 400 described herein.

[0066] Similarly, in certain aspects, the one or more processors may include a processor of a mobile device, which may include at least one of a handheld device (e.g., user computing device 111c1) and / or a portable microscope (e.g., portable microscope device 112c4). Accordingly, in these aspects, the imaging device may comprise a portable microscope, and the mobile device may execute a scalp hair analysis app. For example, if the imaging device is a portable microscope (e.g., portable microscope device 112c4), a user may use a camera of the portable microscope to capture images of the user's scalp or hair region, and the portable microscope may process / analyze the captured images using one or more processors of the portable microscope according to operations of method 400 described herein, and / or transmit the captured images to a connected mobile device (e.g., user computing device 112c1) for processing / analysis.

[0067] At block 404, method 400 includes analyzing the user-specific data with an AI-based learning model (e.g., AI-based learning model 108) accessible by the scalp and hair analysis app to generate scalp or hair predictions corresponding to the user's scalp or hair region. In particular, the scalp or hair predictions may correspond to one or more characteristics of the user's scalp or hair region. In certain aspects, the scalp or hair predictions include a sebum prediction that may correspond to a predicted sebum level associated with the user's scalp or hair region.

[0068] As referred to herein in various aspects, an AI-based learning model (e.g., AI-based learning model 108) is trained using training data related to each individual's scalp and hair region. The AI-based learning model is configured or otherwise operable to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region. The training data includes data (e.g., clinical data) generated using a scalp or hair measurement device (e.g., scalp or hair measurement device 111c4) configured to determine one or more characteristics of the scalp or hair region. In certain aspects, the scalp or hair measurement device is configured to determine the sebum level on the user's skin surface.

[0069] Furthermore, the training data for each individual's scalp and hair region is selected from one or more values corresponding to each individual's last wash data and at least one of one or more scalp factors, one or more hair factors, and / or wash frequency. Therefore, each instance of training data must include at least each individual's last wash data to train the AI-based learning model. This is because, as described above, the scalp or hair predictions output by the AI-based learning model are significantly affected by the user's last wash data. In various embodiments, the one or more scalp factors include dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant odor, or itchiness. In various embodiments, the one or more hair factors include unmanageability, hair loss, hair volume, thinning, detangling, oily hair, dryness, or hair odor.

[0070] For example, a first set of training data corresponding to a first individual may include last wash data indicating that the first individual last washed their hair less than three hours before submitting their answers / inputs, further indicating that the first individual is concerned about dry scalp. Further in this example, a second set of training data corresponding to a second individual may include last wash data indicating that the second individual last washed their hair more than 24 hours before submitting their answers / inputs, further indicating that the second individual is concerned about thinning hair. Finally, in this example, a third set of data corresponding to a third individual may not include last wash data, indicating that the third individual is concerned about scalp dandruff and oily hair. In this example, an AI-based learning model may be trained using the first and second sets of training data, but may not be trained using the third set of data because the first and second sets of training data include last wash data and the third set of data does not.

[0071] Further, in various embodiments, the training data includes image data and non-image data for each individual, and the user-specific data includes image data and non-image data for the user. In these embodiments, the image data of the training data and the image data of the user-specific data each include one or more sebum images that define an amount of human sebum discernible within the pixel data of the one or more sebum images.

[0072] As previously mentioned, as described herein, an AI-based learning model (e.g., AI-based learning model 108) may be trained using a supervised machine learning program or algorithm, such as multivariate regression analysis. Generally, machine learning may involve identifying and recognizing patterns within existing data (e.g., generating scalp or hair predictions corresponding to one or more features of each individual's scalp or hair region) to facilitate prediction or discrimination of subsequent data (e.g., using the model on new user-specific data to determine or generate scalp or hair predictions corresponding to the user's scalp or hair region and / or user-specific treatments to address at least one feature based on the scalp or hair predictions). Machine learning models, such as the AI-based learning models described herein for some embodiments, can be created and trained based on example data (e.g., "training data" and associated user-specific data) inputs or data (which may be referred to as "features" and "labels") to make valid and reliable predictions of new inputs, such as test-level or production-level data or inputs.

[0073] In supervised machine learning, a machine learning program running on a server, computing device, or other processor is provided with example inputs (e.g., "features") and their associated or observed outputs (e.g., "labels"), and the machine learning program or algorithm may determine or discover rules, relationships, patterns, or other machine learning "models" that map such inputs (e.g., "features") to outputs (e.g., labels), for example, by determining and / or assigning weights or other measures for the model across the model's various feature categories. Such rules, relationships, or other models may then be provided with subsequent inputs and the model executed on the server, computing device, or other processor to predict expected outputs based on the discovered rules, relationships, or models.

[0074] However, although described herein as being trained using supervised learning techniques (e.g., multivariate regression analysis), in certain aspects, the AI-based learning model may be trained using multiple supervised machine learning techniques, and may additionally or alternatively be trained using one or more unsupervised machine learning techniques. In unsupervised machine learning, a server, computing device, or other processor may be required to discover its own structure in unlabeled example inputs, in which case, for example, multiple training iterations are performed by the server, computing device, or other processor to train multiple generations of models until a satisfactory model is produced, e.g., a model that provides sufficient predictive accuracy when given test-level or production-level data or inputs.

[0075] For example, in certain embodiments, the AI-based learning model may employ a neural network, which may be a convolutional neural network, a deep learning neural network, or a blended learning module or program that trains two or more features or feature datasets (e.g., user-specific data) within a particular domain of interest. These machine learning programs or algorithms may also include natural language processing, semantic analysis, automated reasoning, support vector machine (SVM) analysis, decision tree analysis, random forest analysis, K-nearest neighbor analysis, naive Bayes analysis, clustering, reinforcement learning, and / or other machine learning algorithms and / or techniques. In some embodiments, the artificial intelligence and / or machine learning-based algorithms may be included as libraries or packages that execute on the server 102. For example, the libraries may include a TENSORFLOW-based library, a PYTORCH library, and / or a SCIKIT-LEARN Python library.

[0076] In any case, training the AI-based learning model may also include retraining, relearning, or otherwise updating the model with new or different information, which may include information received, ingested, generated, or otherwise used over time. Further, in various aspects, the AI-based learning model (e.g., AI-based learning model 108) may be trained by one or more processors (e.g., one or more processors 104 of server 102 and / or a processor of a computer user device, such as a mobile device) using pixel data of multiple training images (e.g., images 114) of each individual's scalp or hair region. In these aspects, the AI-based learning model (e.g., AI-based learning model 108) may be further configured to generate one or more scalp or hair predictions corresponding to one or more features of each individual's scalp or hair region in each of the multiple training images.

[0077] In optional block 406, method 400 includes generating, by the scalp hair analysis app, a quality score based on the scalp or hair predictions for the user's scalp or hair region. The quality score is generated or designed to indicate the quality of the user's scalp or hair region as defined by the user-specific data (e.g., represented by scalp quality score section 206a in FIG. 2). In various aspects, the computing instructions of the hair scalp analysis app, when executed by one or more processors, may cause the one or more processors to generate a quality score determined based on the scalp or hair predictions for the user's scalp or hair region. The quality score may include any suitable scoring system / representation.

[0078] For example, in these aspects, as shown in FIG. 2, the quality score may include a graphical score (e.g., graphical score 206a1) that may indicate to the user that the user's scalp quality score is, for example, 3.5 out of a maximum possible score of 4. The quality score may further include a quality score description (e.g., scalp quality score description 206a20), which may include, for example, a description of the predominant scalp / hair factors and / or last wash data that led to the score decrease, the intrinsic / extrinsic factors causing the scalp and / or hair problem, and / or any other information, or a combination thereof. Additionally, the quality score may include an average / sum value corresponding to each weighted value associated with the user-specific data that was analyzed and correlated to the quality score as part of the AI-based learning model (e.g., AI-based learning model 108).

[0079] At block 408, method 400 includes generating, by the scalp hair analysis app, a user-specific treatment based on the scalp or hair predictions, designed to address at least one scalp or hair prediction-based characteristic of the user's scalp or hair region. In various aspects, the user-specific treatment is displayed on a display screen of a computing device (e.g., user computing device 111c1) to instruct the user on how to treat the at least one scalp or hair prediction-based characteristic of the user's scalp or hair region.

[0080] The user-specific treatment may be generated by a user computing device (e.g., user computing device 111c1) and / or by a server (e.g., server 102). For example, in some aspects, server 102 may analyze user-specific data remote from the user computing device, as described herein with respect to FIG. 1, to determine a user-specific treatment designed to address a scalp or hair prediction value corresponding to the user's scalp or hair region, a quality score, and / or at least one characteristic based on the scalp or hair prediction value of the user's scalp or hair region. For example, in such aspects, a server or cloud-based computing platform (e.g., server 102) receives, via computer network 120, user-specific data defining the user's scalp or hair region, including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency. The server or cloud-based computing platform may then execute an AI-based learning model (e.g., AI-based learning model 108) and generate a scalp or hair prediction, a quality score, and / or a user-specific treatment based on the output of the AI-based learning model. The server or cloud-based computing platform may then transmit the scalp or hair prediction, the quality score, and / or the user-specific treatment to the user computing device via a computer network (e.g., computer network 120) for rendering on a display screen of the user computing device. For example, in various aspects, the scalp or hair prediction, the quality score, and / or the user-specific treatment may be rendered on a display screen of the user computing device in real time or near real time while or after receiving user-specific data defining the user's scalp or hair region and the user's last wash data.

[0081] By way of example, in various aspects, the user-specific treatment may include a user-specific recommended washing frequency. The recommended washing frequency may include the number of washes, one or more washes or durations over a day, a week, etc., suggestions regarding washing methods, etc. Further, in various aspects, the user-specific treatment may include, for example, text-based treatments, visual / image-based treatments, and / or virtual renderings of the user's scalp or hair region displayed on a display screen of a user computing device (e.g., user computing device 111c1). Such user-specific treatments may include a graphical representation of the user's scalp or hair region annotated with one or more graphic or textual renderings corresponding to user-specific characteristics (e.g., excessive scalp sebum, dandruff, dryness, etc.).

[0082] Further, in certain embodiments, the scalp hair analysis app can receive an image of a user, where the image can depict the user's scalp or hair region. In these embodiments, the scalp hair analysis app can generate a photorealistic representation of the user after virtually applying a user-specific treatment to the user's scalp or hair region. Furthermore, the scalp hair analysis app can generate the photorealistic representation by manipulating one or more pixels of the user's image based on the scalp or hair predictions. For example, the scalp hair analysis app can graphically render a user-specific treatment for display to the user, where the user-specific treatment can include a treatment option to increase hair / scalp washing frequency to reduce scalp sebum accumulation present on the user's scalp or hair region, determined by an AI-based learning model based on user-specific data and last wash data. In this example, the scalp hair analysis app may generate a photorealistic representation of the user's scalp or hair region free of (or with reduced amounts of) scalp sebum by manipulating (e.g., updating, smoothing, changing color) pixel values of one or more pixels of the user's image to change pixel values of pixels identified as containing pixel data representative of scalp sebum present on the user's scalp or hair region to pixel values representative of the user's scalp or hair follicles in the user's scalp or hair region. For example, in some aspects, the graphical representation of the user's scalp or hair region 506 is a photorealistic representation of the user.

[0083] In additional aspects, the user-specific treatment may include a product recommendation for the manufactured product. Additionally or alternatively, in some aspects, the user-specific treatment may be displayed on a display screen of a computing device (e.g., user computing device 111c1) along with instructions (e.g., a message) for treating at least one feature of the user's scalp or hair region based on the scalp or hair prediction with the manufactured product. In still further aspects, computing instructions executing on a processor of the user computing device (e.g., user computing device 111c1) and / or server may initiate shipment of the manufactured product to the user based on the user-specific treatment. With respect to the manufactured product recommendation, in some aspects, one or more processors (e.g., server 102 and / or a user computing device such as user computing device 111c1) may generate and render a modified image, as described above, based on how the user's scalp or hair region is predicted to look after treating at least one feature with the manufactured product.

[0084] FIG. 5A illustrates an exemplary user interface 504a rendered on a display screen 500 of a user computing device (e.g., user computing device 111c1) in accordance with various aspects disclosed herein. For example, as shown in the example of FIG. 5A, user interface 504a may be implemented or rendered via an application (app) running on user computing device 111c1. For example, as shown in the example of FIG. 5A, user interface 504a may be implemented or rendered via a native app running on user computing device 111c1. In the example of FIG. 5A, user computing device 111c1 is the user computing device described with respect to FIG. 1; for example, 111c1 is illustrated as an APPLE iPhone implementing the APPLE iOS operating system and having display screen 500. User computing device 111c1 may run one or more native applications (apps) on its operating system, including, for example, a scalp hair analysis app described herein. Such native apps may be implemented or coded (e.g., as computing instructions) in a computing language (e.g., SWIFT) executable by the processor of the user computing device 111c1 and by the user computing device operating system (e.g., APPLE iOS).

[0085] Additionally or alternatively, user interface 504a may be implemented or rendered via a web interface, such as via a web browser application, such as the Safari and / or Google Chrome app, or other such web browser.

[0086] 5A, the user interface 504a includes a graphical representation of the scalp or hair predictions, including the scalp quality score section 206a, the graphical score 206a1, the scalp quality score description 206a2, the scalp turnover section 206b, the scalp stress level section 206c, and the hair stress level section 206d of FIG. 2. Thus, the scalp hair analysis app can directly communicate each of the scalp or hair predictions to the user by rendering the scalp or hair predictions on the user interface 504a. In certain embodiments, the scalp hair analysis app can initially render the user interface 504a in a series of graphical displays intended to provide the user with a comprehensive assessment of the user's scalp or hair region defined by user-specific data and last wash data.

[0087] For example, FIG. 5B shows another exemplary user interface 504b rendered on a display screen 502 of a user computing device (e.g., user computing device 111c1), where in certain aspects user interface 504b may be a subsequent graphical rendering to user interface 504a of FIG. 5A. User interface 504b includes a graphical representation (e.g., image 114) of a user's scalp or hair region 506. Image 114 may include an image of the user (or its graphical representation 506) including pixel data (e.g., pixel data 114ap) of at least a portion of the user's scalp or hair region, as described herein. In the example of FIG. 5B, the graphical representation (e.g., image 114) of the user's scalp or hair region is annotated with one or more graphics (e.g., areas of pixel data 114ap) or textual renderings (e.g., text 114at) corresponding to various features identifiable within the pixel data including the portion of the user's scalp or hair region 506. For example, areas of pixel data 114ap may be annotated or overlaid on a user's image (e.g., image 114) to highlight areas or features identified in the pixel data (e.g., feature data and / or raw pixel data) by an AI-based learning model (e.g., AI-based learning model 108). In the example of FIG. 5B , the areas of pixel data 114ap indicate features including scalp sebum (e.g., pixels 114ap1-3) as defined in pixel data 114ap, and may indicate other features indicated in the areas of pixel data 114ap as described herein (e.g., dry scalp, oily scalp, dandruff, unmanageable hair, dry hair, etc.). In various aspects, pixels (e.g., pixels 114ap1-3) identified as unique features may be highlighted or otherwise annotated when rendered on display screen 502.

[0088] The text rendering (e.g., text 114at) indicates a user-specific attribute or characteristic (e.g., 80 for pixels 114ap1-3) that may indicate that the user has a high scalp quality score (of 80) for scalp sebum. A score of 80 indicates that the user has a large amount of sebum present on the user's scalp or hair region (and thus, likely the user's entire scalp), thereby indicating that the user would likely benefit from washing the scalp with a cleansing shampoo and increasing washing frequency to improve scalp health / quality / condition (e.g., reduce the amount of scalp sebum). It should be understood that other text rendering types or values are contemplated herein, and text rendering types or values, such as a scalp quality score, a scalp turnover score, a scalp stress level score, a hair stress level score, etc., may be rendered. Additionally or alternatively, the color values may be used and / or overlaid on a graphical representation shown on the user interface 504b (e.g., a graphical representation of the user's scalp or hair region 506) to indicate the degree or quality of a given score, e.g., a high score of 80 or a low score of 5. Scores may be provided as raw scores, absolute scores, percentage-based scores, and / or any other suitable presentation style. Additionally or alternatively, such scores may be presented along with a text or graphic indicator indicating whether the score represents a positive result (good scalp washing frequency), a negative result (poor scalp washing frequency), or an acceptable result (average or acceptable scalp washing frequency).

[0089] User interface 502 may also include or render a scalp or hair prediction 510. In the embodiment of FIG. 5B, scalp or hair prediction 510 comprises a message 510m to the user designed to indicate to the user the scalp or hair prediction along with a brief explanation of any reasons that result in the scalp or hair prediction. As shown in the example of FIG. 5B, message 510m indicates to the user that the scalp or hair prediction is "80" and further indicates to the user that the scalp or hair prediction results from areas of the user's scalp or hair that contain "high scalp sebum."

[0090] The user interface 504b may also include or render user-specific treatment recommendations 512. In the embodiment of FIG. 5B, the user-specific treatment recommendations 512 include a message 512m to the user designed to address at least one feature identifiable within the user-specific data defining the user's scalp or hair region and the user's last wash data. As shown in the example of FIG. 5B, the message 512m recommends that the user wash their scalp more frequently to improve scalp health / quality / condition by reducing excess sebum buildup.

[0091] Message 512m further recommends the use of a cleansing shampoo to help reduce excess sebum buildup. The cleansing shampoo recommendation can be made based on a high scalp quality score (e.g., 80) for scalp sebum, suggesting that the user's image depicts a large amount of scalp sebum, and a cleansing shampoo product designed to address the scalp sebum detected or classified in the pixel data of image 114 or otherwise predicted based on the user's user-specific data and last wash data. The product recommendation can be correlated with identified features within the user-specific data and / or pixel data, and user computing device 111c1 and / or server 102 can be instructed to output a product recommendation when a feature (e.g., excessive scalp (or hair) sebum) is identified.

[0092] User interface 504b may also include or render a section for product recommendation 522 for manufactured product 524r (e.g., a cleansing shampoo, as described above). Product recommendation 522 may correspond to user-specific treatment recommendation 512, as described above. For example, in the example of FIG. 5B, user-specific treatment recommendation 512 may be displayed on display screen 502 of user computing device 111c1 along with instructions (e.g., message 512m) for processing at least one predicted and / or identifiable feature (e.g., a high scalp quality score of 80 associated with scalp sebum at pixels 114ap1-3) in manufactured product (manufactured product 524r (e.g., a cleansing shampoo)) based on user-specific data and last wash data, and / or pixel data (pixel data 114ap) including, in certain embodiments, pixel data of at least a portion of the user's scalp or hair region. The predicted or identified feature is shown and annotated (524p) on user interface 504b.

[0093] As shown in FIG. 5B , the user interface 504b recommends a product (e.g., a manufactured product 524r (e.g., a wash shampoo)) based on the user-specific treatment recommendation 512. In the example of FIG. 5B , the output or analysis of the image (e.g., image 114), e.g., scalp or hair prediction value 510, and / or its associated values (e.g., scalp sebum quality score) or associated pixel data (e.g., 114ap1, 114ap2, and / or 114ap3), and / or the user-specific treatment recommendation 512 by the user-specific data and the AI-based learning model (e.g., AI-based learning model 108) can be used to generate or identify a corresponding product recommendation. Such recommendations can include products such as shampoo, conditioner, hair gel, moisturizing treatment, etc., to address user-specific issues detected or predicted from the user-specific data and last wash data and / or, in certain aspects, within the pixel data by the AI-based learning model (e.g., AI-based learning model 108).

[0094] The user interface 504b may further include selectable UI buttons 524s that allow a user (e.g., a user of the image 114) to select a corresponding product (e.g., a manufactured product 524r) for purchase or shipment. In some aspects, selection of the selectable UI button 524s may cause the recommended product to be shipped to the user and / or may notify a third party that the individual is interested in the product. For example, either the user computing device 111c1 and / or the server 102 may initiate shipment of the manufactured product 524r (e.g., a cleansing shampoo) to the user based on the scalp or hair prediction value 510 and / or the user-specific treatment recommendation 512. In such aspects, the product may be packaged and shipped to the user.

[0095] In various aspects, the graphical annotations (e.g., areas of pixel data 114ap), text annotations (e.g., text 114at), and the graphical representation (e.g., a graphical representation of the user's scalp or hair region 506) having the scalp or hair predictions 510 and user-specific treatment recommendations 512 may be transmitted over a computer network (e.g., from the server 102 and / or one or more processors) to the user computing device 111c1 for rendering on the display screen 500, 502. In other aspects, transmission of the user-specific images to a server is not performed, and the scalp or hair predictions 510 and user-specific treatment recommendations 512 (and / or product-specific recommendations) may instead be generated locally by an AI-based learning model (e.g., AI-based learning model 108) running and / or implemented on the user's mobile device (e.g., user computing device 111c1) and rendered on the display screen 500, 502 of the mobile device (e.g., user computing device 111c1) by a processor of the mobile device.

[0096] In some embodiments, any one or more of the graphical annotations (e.g., areas of pixel data 114ap), text annotations (e.g., text 114at), scalp or hair predictions 510, user-specific treatment recommendations 512, and / or product recommendations 522 (e.g., graphical representations of the user's scalp or hair region 506) may be rendered (e.g., rendered locally on the display screens 500, 502) during or after receiving, in real time or near real time, the user-specific data and last wash data and / or, in certain embodiments, images of the user's scalp or hair region. In embodiments where the user-specific data and last wash data and images are analyzed by the server 102, the user-specific data and last wash data and images may be transmitted and analyzed by the server 102 in real time or near real time.

[0097] In some aspects, a user may provide new user-specific data, new last wash data, and / or new images that may be transmitted to server 102 for updating, retraining, or reanalysis by AI-based learning model 108. In other aspects, new user-specific data, new last wash data, and / or new images may be received locally on computing device 111c1 and analyzed on computing device 111c1 by AI-based learning model 108.

[0098] Additionally, as shown in the example of FIG. 5B , a user may select selectable button 512i to reanalyze new user-specific data, new last wash data, and / or new images (e.g., locally at computing device 111c1 or remotely at server 102). Selectable button 512i may prompt the user to input / attach new user-specific data, new last wash data, and / or new images to user interface 504b for analysis. A user computing device, such as server 102 and / or user computing device 111c1, may receive new user-specific data, new last wash data, and / or new images including data defining the user's scalp or hair region. The new user-specific data, new last wash data, and / or new images may be received / captured by the user computing device. The new images (e.g., similar to image 114) may include pixel data of a portion of the user's scalp or hair region. An AI-based learning model (e.g., AI-based learning model 108) executing on the memory of the computing device (e.g., server 102) may analyze new user-specific data, new last-wash data, and / or new images received / captured by the user computing device to generate a new scalp or hair prediction. The computing device (e.g., server 102) may generate a new scalp or hair prediction based on a comparison of the new user-specific data to the user-specific data, the new last-wash data to the last-wash data, and / or the new image to the image. For example, the new scalp or hair prediction may include a new graphical representation including graphics and / or text (e.g., indicating a new quality score value, e.g., 1, after the user washed their hair). The new scalp or hair prediction may include, for example, an additional quality score that the user successfully washed their hair to reduce scalp dandruff and / or hair oiliness, as detected using the new user-specific data, the new last-wash data, and / or the new images.The comments may include that the user needs to correct new user-specific data, new last wash data, and / or additional features detected in the new image, such as dry hair, by applying additional products, such as moisturizing shampoo or coconut oil.

[0099] In various aspects, the new scalp or hair prediction values and / or new user-specific treatment recommendations may be transmitted over a computer network from the server 102 to the user's user computing device (e.g., user computing device 111c1) for rendering on a display screen 502 of the user computing device.

[0100] In other aspects, new user-specific data, new last wash data, and / or new images of the user are not transmitted to the server, and new scalp or hair predictions and / or new user-specific treatment recommendations (and / or product-specific recommendations) may instead be generated locally by an AI-based learning model (e.g., AI-based learning model 108), executed and / or implemented on the user's mobile device (e.g., user computing device 111c1), and rendered on a display screen of the mobile device (e.g., user computing device 111c1) by a processor of the mobile device.

[0101] Of course, it should be understood that any graphical / textual rendering present on user interface 504a, 504b may be rendered on either user interface 504a, 504b. For example, scalp quality score section 206a present in user interface 504a may be rendered as part of the display in user interface 504b. Similarly, scalp or hair prediction value 510 and user-specific treatment recommendation 512 and corresponding messages 510m, 512m may be rendered as part of the display in user interface 504a.

[0102] Aspects of the Disclosure The following aspects are provided as examples according to the disclosure herein and are not intended to limit the scope of the disclosure. 1. An artificial intelligence (AI)-based system configured to analyze user-specific skin or hair data to predict a user-specific skin or hair condition, the system comprising: a scalp hair analysis application (app) including: one or more processors; computing instructions configured to execute on the one or more processors; and an AI-based learning model accessible by the scalp hair analysis app, the AI-based learning model trained with training data regarding each individual's scalp and hair region, the AI-based learning model configured to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region, the training data regarding each individual's scalp and hair region being selected from each individual's last wash data and one or more values corresponding to at least one of: one or more scalp factors, one or more hair factors, or wash frequency. the training data includes data generated by a scalp or hair measurement device configured to determine one or more characteristics of the scalp or hair region; and the computing instructions of the scalp hair analysis app, when executed by the one or more processors, cause the one or more processors to receive user-specific data for a user defining the user's scalp or hair region, including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; analyze the user-specific data with an AI-based learning model to generate a scalp or hair prediction corresponding to the user's scalp or hair region; and generate, based on the scalp or hair prediction, a user-specific treatment designed to address the at least one characteristic of the user's scalp or hair region based on the scalp or hair prediction. 2. The AI-based system of aspect 1, wherein the one or more scalp factors include dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant odor, or itchiness. 3. The AI-based system of aspect 2, wherein the scalp or hair prediction value comprises a sebum prediction value. 4. The AI-based system of any one of aspects 1-3, wherein the user's scalp or hair region corresponds to one of: (1) the user's scalp region; or (2) the user's hair region. 5. The AI-based system of any one of aspects 1-4, wherein the one or more hair factors include unmanageability, hair loss, hair volume, thinning, detangling, hair oiliness, dryness, or hair odor. 6. The AI-based system of any one of aspects 1-5, wherein the computing instructions of the scalp hair analysis app, when executed by the one or more processors, further cause the one or more processors to generate a quality score based on the scalp or hair predictions for the user's scalp or hair region. 7. The AI-based system of any one of aspects 1-6, wherein the training data includes image data and non-image data for each individual, and the user-specific data includes image data and non-image data for the user. 8. The AI-based system of aspect 7, wherein the image data of the training data and the image data of the user-specific data each include one or more sebum images that define an amount of human sebum identifiable within the pixel data of the one or more sebum images. 9. The AI-based system of any one of aspects 1-8, wherein the computing instructions of the scalp hair analysis app, when executed by the one or more processors, further cause the one or more processors to receive an image of the user depicting the user's scalp or hair region and generate a photorealistic representation of the user after virtual application of the user-specific treatment to the user's scalp or hair region, wherein the photorealistic representation is generated by manipulating one or more pixels of the image of the user based on the scalp or hair prediction. 10. The AI-based system of any one of aspects 1-9, wherein the scalp or hair measurement device is configured to determine the sebum level on the user's skin surface. 11. An artificial intelligence (AI)-based method for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition, the AI-based method comprising: receiving, in a scalp hair analysis application (app) executing on one or more processors, user-specific data for a user, the user-specific data defining the user's scalp or hair region, the user-specific data including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; analyzing the user-specific data with an artificial intelligence (AI)-based learning model accessible by the scalp hair analysis app to generate a scalp or hair prediction corresponding to the user's scalp or hair region, the AI-based learning model the model is trained using training data for each individual's scalp and hair region and is configured to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region, the training data for each individual's scalp and hair region being selected from each individual's last wash data and one or more values corresponding to at least one of one or more scalp factors, one or more hair factors, or wash frequency, the training data including data generated with a scalp or hair measurement device configured to determine the one or more characteristics of the scalp or hair region; and generating, by a scalp hair analysis app based on the scalp or hair predictions, a user-specific treatment designed to address the at least one characteristic based on the scalp or hair predictions of the user's scalp or hair region. 12. The AI-based method of aspect 11, wherein the one or more scalp factors comprise dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant odor, or itching. 13. The AI-based method of aspect 12, wherein the scalp or hair predictor comprises a sebum predictor. 14. The AI-based method of any one of aspects 11-13, wherein the user's scalp or hair region corresponds to one of: (1) the user's scalp region; or (2) the user's hair region. 15. The AI-based method of any one of aspects 11-14, wherein the one or more hair factors comprise unmanageability, hair loss, hair volume, thinning, detangling, hair oiliness, dryness, or hair odor. 16. The AI-based method of any one of aspects 11-15, further comprising generating, by a scalp hair analysis app, a quality score based on the scalp or hair predictions for the user's scalp or hair region. 17. The AI-based method of any one of aspects 11-16, wherein the training data includes image data and non-image data for each individual, and the user-specific data includes image data and non-image data for the user. 18. The AI-based method of any one of aspects 11-17, wherein the image data of the training data and the image data of the user-specific data each include one or more sebum images that define an amount of human sebum discernible within the pixel data of the one or more sebum images. 19. The AI-based method of any one of aspects 11-18, further comprising: receiving, in the scalp hair analysis app, an image of a user depicting the user's scalp or hair region; and generating, by the scalp hair analysis app, a photorealistic representation of the user after virtual application of a user-specific treatment to the user's scalp or hair region, wherein the photorealistic representation is generated by manipulating one or more pixels of the image of the user based on the scalp or hair prediction. 20. The AI-based method of any one of aspects 11-19, wherein the scalp or hair measurement device is configured to determine the sebum level on the user's skin surface. 21. A tangible, non-transitory computer-readable medium storing instructions for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition, the instructions, when executed by one or more processors, causing the one or more processors to receive, in a scalp hair analysis application (app) executing on the one or more processors, user-specific data of a user, the user-specific data defining the user's scalp or hair region, the user-specific data including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; and analyzing the user-specific data with an artificial intelligence (AI)-based learning model accessible by the scalp hair analysis app to generate a scalp or hair prediction corresponding to the user's scalp or hair region, wherein the AI-based a learning model for each individual's scalp and hair region that is trained using training data for each individual's scalp and hair region and configured to output one or more scalp or hair predictions corresponding to one or more characteristics of each individual's scalp or hair region, the training data for each individual's scalp and hair region being selected from each individual's last wash data and one or more values corresponding to at least one of one or more scalp factors, one or more hair factors, or wash frequency, the training data including data generated with a scalp or hair measurement device configured to determine the one or more characteristics of the scalp or hair region; and generating, based on the scalp or hair predictions, a user-specific treatment designed to address the at least one characteristic of the user's scalp or hair region based on the scalp or hair predictions.

[0103] Additional Considerations While this disclosure provides detailed descriptions of many different embodiments, it should be understood that the legal scope of such descriptions is defined by the terms of the claims at the end of this patent and any equivalents. This detailed description should be construed as exemplary only and does not describe every possible embodiment, as describing every possible embodiment would be impractical. Many alternative embodiments may be implemented using either current technology or technology developed after the filing date of this patent, and such embodiments would still fall within the scope of the claims.

[0104] The following additional considerations apply to the foregoing discussion: Throughout this specification, multiple examples may implement components, operations, or structures that are described as a single example. While individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed simultaneously, and the operations need not be performed in the order illustrated. Structures and functions presented as separate components in example configurations may be implemented as combined structures or components. Similarly, structures and functions presented as a single component may also be implemented as separate components. These and other variations, modifications, additions, and improvements are included within the scope of the present subject matter herein.

[0105] Additionally, certain aspects are described herein as including logic or certain routines, subroutines, applications, or instructions. These may be constructed as either software (e.g., code embodied on a machine-readable medium or in a transmission signal) or hardware. In hardware, routines, etc., are tangible units capable of performing certain operations and may be configured or arranged in a particular manner. In exemplary aspects, one or more computer systems (e.g., standalone, client, or server computer systems) or one or more hardware modules (e.g., processors or groups of processors) of a computer system may be configured by software (e.g., applications or application portions) as hardware modules that operate to perform certain operations as described herein.

[0106] Various operations of the example methods described herein may be performed, at least in part, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the associated operations. Whether temporarily or permanently configured, such processors may form processor-implemented modules that operate to perform one or more operations or functions. Modules referred to herein may, in some example aspects, include processor-implemented modules.

[0107] Similarly, the methods or routines described herein may be at least partially processor-implemented. For example, at least some of the operations of a method may be performed by one or more processors or processor-implemented hardware modules. Certain performance of those operations may be distributed to one or more processors and may reside within a single machine as well as spread across multiple machines. In some exemplary aspects, the processor(s) may be located in a single location, whereas in other aspects, the processor(s) may be distributed across several locations.

[0108] Certain performance of those operations may be distributed across one or more processors and may reside within a single machine as well as be spread across multiple machines. In some exemplary aspects, one or more processors or processor-implemented modules may be located in a single geographic location (e.g., in a home environment, an office environment, or a server farm). In other aspects, one or more processors or processor-implemented modules may be distributed across multiple geographic locations.

[0109] This detailed description should be construed as illustrative only and does not describe every possible embodiment, as describing every possible embodiment would be impractical, if not impossible. Those skilled in the art will be able to implement numerous alternative embodiments using either current technology or technology developed after the filing date of this application.

[0110] Those skilled in the art will recognize that numerous modifications, variations, and combinations can be made with respect to the above-described aspects without departing from the scope of the present invention, and that such modifications, variations, and combinations can be considered to be within the circumstance of the inventive concept.

[0111] The claims at the end of this patent application are not intended to be construed under 35 U.S.C. § 112(f) unless conventional means-plus-function language, such as "means for" or "step for," is expressly recited. The systems and methods described herein are directed to improving computer functionality and improve upon the functionality of conventional computers.

[0112] Dimensions and values disclosed herein should not be understood as being strictly limited to the exact numerical values recited. Instead, unless otherwise indicated, each such dimension is intended to mean both the recited value and a functionally equivalent range surrounding that value. For example, a dimension disclosed as "40 mm" is intended to mean "about 40 mm."

[0113] All documents cited herein, including any cross-referenced or related patents or patent applications, and any patent applications or patents to which this application claims priority or benefit, are incorporated herein by reference in their entirety, unless expressly stated to the contrary. The citation of any document shall not be deemed to be prior art to any invention disclosed or claimed herein, or to teach, suggest, or disclose any such invention, either alone or in combination with any other reference(s). Furthermore, to the extent that any meaning or definition of a term in this document conflicts with any meaning or definition of the same term in a document incorporated by reference, the meaning or definition assigned to that term in this document shall govern.

[0114] While particular embodiments of the present invention have been illustrated and described, it would be obvious to those skilled in the art that various other changes and modifications can be made without departing from the spirit and scope of the invention. It is therefore intended to cover in the appended claims all such changes and modifications that are within the scope of this invention.

Claims

1. 1. An artificial intelligence (AI)-based method for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition, the computer-implemented AI-based method comprising: receiving user-specific data for a user in a scalp and hair analysis application (app) executing on one or more processors, the user-specific data defining the user's scalp or hair region including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; and analyzing the user-specific data with an artificial intelligence (AI)-based learning model accessible by the scalp and hair analysis app to generate a scalp or hair prediction corresponding to the user's scalp or hair region, the AI-based method comprising: wherein the learning model is trained using training data for each individual's scalp and hair region and is configured to output one or more scalp or hair predictions corresponding to one or more characteristics of the scalp or hair region of each individual, the training data for each individual's scalp and hair region being selected from each individual's last wash data and one or more values corresponding to at least one of one or more scalp factors, one or more hair factors, or wash frequency, and the training data includes data generated with a scalp or hair measurement device configured to determine the one or more characteristics of the scalp or hair region; and generating, by the scalp and hair analysis app based on the scalp or hair predictions, a user-specific treatment designed to address at least one characteristic of the user's scalp or hair region based on the scalp or hair predictions.

2. 10. The AI-based method of claim 1, wherein the one or more scalp factors include dry scalp, oily scalp, dandruff, stiffness, redness, unpleasant odor, or itchiness.

3. 2. The AI-based method of claim 1, wherein the scalp or hair predictor comprises a sebum predictor.

4. 2. The AI-based method of claim 1, wherein the scalp or hair region of the user corresponds to one of: (1) the scalp region of the user; or (2) the hair region of the user.

5. 10. The AI-based method of claim 1, wherein the one or more hair factors comprise unmanageability, hair loss, hair volume, thinning, detangling, hair oiliness, dryness, or hair odor.

6. 2. The AI-based method of claim 1, further comprising generating, by the scalp hair analysis app, a quality score based on the scalp or hair predictions for the user's scalp or hair region.

7. 2. The AI-based method of claim 1, wherein the training data includes image data and non-image data for each of the individuals, and the user-specific data includes image data and non-image data for the user, and preferably the image data of the training data and the image data of the user-specific data each include one or more sebum images that define the amount of identifiable human sebum within pixel data of the one or more sebum images.

8. 2. The AI-based method of claim 1, further comprising: receiving, in the scalp hair analysis app, an image of the user depicting the scalp or hair region of the user; and generating, by the scalp hair analysis app, a photorealistic representation of the user after virtual application of the user-specific treatment to the scalp or hair region of the user, wherein the photorealistic representation is generated by manipulating one or more pixels of the image of the user based on the scalp or hair prediction.

9. 10. The AI-based method of claim 1, wherein the scalp or hair measurement device is configured to determine a sebum level on the user's skin surface.

10. 10. An artificial intelligence (AI) based system configured to perform the method of any one of claims 1 to 9, the system comprising: one or more processors; computing instructions configured to execute on the one or more processors; and a scalp hair analysis application (app) accessible by the scalp hair analysis app, the AI based learning model being trained with training data relating to the scalp and hair region of each individual, the AI based learning model being configured to output one or more scalp or hair predictions corresponding to one or more characteristics of the scalp or hair region of each individual, wherein the training data relating to the scalp and hair region of each individual is selected from each individual's last wash data and one or more values corresponding to at least one of one or more scalp factors, one or more hair factors, or wash frequency, the scalp or hair analysis app includes data generated by a scalp or hair measurement device configured to determine the one or more characteristics of a scalp or hair area, and the computing instructions of the scalp hair analysis app, when executed by the one or more processors, cause the one or more processors to receive user-specific data of a user defining the user's scalp or hair area, including (1) the user's last wash data and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; analyze the user-specific data with the AI-based learning model to generate a scalp or hair prediction corresponding to the user's scalp or hair area; and generate, based on the scalp or hair prediction, a user-specific treatment designed to address at least one characteristic of the user's scalp or hair area based on the scalp or hair prediction.

11. 11. The AI-based system of claim 10, wherein the computing instructions of the scalp hair analysis app, when executed by the one or more processors, further cause the one or more processors to generate a quality score based on the scalp or hair predictions for the user's scalp or hair region.

12. 11. The AI-based system of claim 10, wherein the computing instructions of the scalp or hair analysis app, when executed by the one or more processors, further cause the one or more processors to receive an image of the user depicting the scalp or hair region of the user and generate a photorealistic representation of the user after virtual application of the user-specific treatment to the scalp or hair region of the user, the photorealistic representation being generated by manipulating one or more pixels of the image of the user based on the scalp or hair prediction.

13. 11. The system of claim 10, comprising a non-transitory computer-readable medium storing instructions for performing the method for analyzing user-specific skin or hair data to predict a user-specific skin or hair condition.

14. 10. A tangible, non-transitory computer-readable medium storing instructions for performing the method of any one of claims 1 to 9, wherein the instructions, when executed by one or more processors, cause the one or more processors to receive, at a scalp hair analysis application (app) executing on the one or more processors, user-specific data for a user, the user-specific data defining the user's scalp or hair region including (1) the user's last wash data, and (2) at least one of the user's one or more scalp factors, the user's one or more hair factors, or the user's wash frequency; and cause an artificial intelligence (AI)-based learning model accessible by the scalp hair analysis app to analyze the user-specific data to generate scalp or hair predictions corresponding to the user's scalp or hair region, wherein the AI-based learning model a scalp and hair analysis app configured to generate, based on the scalp or hair predictions, a user-specific treatment designed to address at least one characteristic of the user's scalp or hair region based on the scalp or hair predictions.

Images