WO2022238894A1

WO2022238894A1 - Automated size and fit determinations

Info

Publication number: WO2022238894A1
Application number: PCT/IB2022/054332
Authority: WO
Inventors: Foluso Omowunmi IMMANUEL; Ufoma IMMANUEL
Original assignee: Chari Holdings Limited
Priority date: 2021-05-10
Filing date: 2022-05-10
Publication date: 2022-11-17

Abstract

Systems and methods for automated and/or intelligent sizing and/or fitting are disclosed. This can include visualization, recommendations, and other aspects or features as presented herein. A silhouette approximating a user's measurements may be generated or created, and one or more recommendations for an item of clothing may be determined and presented to the user based, at least in part, upon the user's measurements and the clothing measurements. An indication of fit may be presented to the user showing how an item may fit at various measurement points.

Description

AUTOMATED SIZE AND FIT DETERMINATIONS

BACKGROUND

[0001] Despite the massive exodus of consumers to online shopping in recent times, consumers who shop for clothing online remain stuck with a traditional size chart system which requires they physically measure themselves with a tape measure and then have to manually analyze their body measurements with clothing’s measurements each time they shop across brands, all in a bid to select their right sizes before buying an item online. With respective brands having their own different measurement standards and the inability to standardize measurement metrices across fashion brands globally, consumer have become fatigued by this lengthy process and 50% of consumers resort to buying three to four of the same clothing item in different sizes to stand a better chance of getting one of the clothing items in their right size, they then return the mis-fitting clothing items to the retailer, in some cases all clothing items purchased do not fit and have to be returned to the retailer leaving the retailer with a high rate of returned items and reverse logistics to deal with.

[0002] In recent times online clothing retailers / e-commerce stores have attempted to solve this problem by adopting solutions such as “True Fit” which compares the users fit in a particular brand with other brands, suggesting the size in that brand is the same size compared to other brands, this solution in itself leaves a lot of room for guessing and errors and is diametrically opposed to an evolving consumer wanting a more automated process.

BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Various embodiments in accordance with the present disclosure will be described with reference to the drawings, in which:

[0004] FIG. 1 illustrates an example user silhouette with body measurements determined and displayed according to an example embodiment.

[0005] FIG. 2 illustrates an example recommendation for an item determined in accordance with one of more example embodiments.

[0006] FIG. 3 illustrates an example display showing how an item of clothing may compare to a user’s body measurements, according to an example embodiment. [0007] FIG. 4 illustrates an example display showing how an item of clothing may fit on a user, according to an example embodiment.

[0008] FIG 5A illustrates an example method for onboarding a user, in accordance with an example embodiment.

[0009] FIG. 5B illustrates an example method for sizing and fitting a product to a user, in accordance with an example embodiment.

[0010] FIG. 5C illustrates an example method for determining one or more sizes for a user, in accordance with an example embodiment.

[0011] FIG. 5D illustrates an example method for training an algorithm that can be utilized in accordance with one or more example embodiments.

[0012] FIG. 6 illustrates components of an example computing resource that can be utilized in accordance with one or more example embodiments.

DETAILED DESCRIPTION

[0013] In the following description, various embodiments will be described. For purposes of explanation, specific configurations and details are set forth in order to provide a thorough understanding of the embodiments. However, it will also be apparent to one skilled in the art that the embodiments may be practiced without the specific details. Furthermore, well-known features may be omitted or simplified in order not to obscure the embodiment being described.

[0014] Approaches described and suggested herein relate to the intelligent and/or automated determination of the size or shape of a user, as well as the fit of one or more articles ( e.g ., clothing) with respect to that user.

[0015] Approaches in accordance with various embodiments can solve these and other such problems by providing an experience, such as a shopping experience, which is personalized to individual consumers and helps these customers automate the sizing and fitting process. In at least one embodiment, this involves the following three steps or stages:

[0016] Precise Data Capture - Capture user measurements in two snaps using the smart phone camera. [0017] Process and Storage - Store and process the data to build a profile that is unique to the user and that can be easily matched to retailer’s offerings thereby eliminating the users need to take time wasting measurements of themselves with a tape measure every time they shop from a different brand and thereby creating a more intimate experience of being able to connect the end user with the brands /retailer in a way that is personal but with aggregate scale.

[0018] Algorithm Simulation & Results - Using artificial intelligence or machine learning, for example, combine with human intelligence to create personalize user timelines which will be driven by user specific body measurements and their personal style preferences with an objective to accurately match the user with available retail options which fit and size them. Somewhat akin to how iTunes generates playlists for its users based on their preferred genre, their historic playlist and its current music offerings.

[0019] A solution in accordance with various embodiments can create a user avatar from one or more photos of that user. This may be part of the solution, or the solution may utilize or leverage an offering from a 3rd party service provider (e.g., 3D Look) to create a user avatar. This may include, for example, generating an avatar from two photos or images of a user from different points of view (e.g., front and side). The image(s) can be analyzed to determine estimates as to the

[0020] This avatar comes with detailed measurements concerning the dimensions of the user’s body. A system can filter and adjust these dimensions from the avatar to a format usable for analyzing retail clothing measurement.

[0021] An automated approach can be utilized to make such a size recommendation system (or service, etc.) effective, as may utilize at least one mathematical formula, algorithm, or machine learning model. In at least one embodiment, a Recommended Size is calculated. That can be done by matching the user’s measurement to the products’ measurement values. For each value, the system can calculate the difference in percentage between the two values. For example: take the waist measurement value. Say the user’s waist is 31 inches, and the product (for which the system is are currently calculating its recommended size) is 32 inches. The difference in percentage would be (productValue - userValue) / userValue, which would give around 0.03. [0022] Using this formula, a product size ( e.g ., standard size indicated by the brand) can be selected with the smallest difference in percentage, and use its size (S, M, L..) as a Recommended Size. The system can also use this calculation to display individual tags on a Fitting Silhouette. In at least one embodiment, restriction can be used as may include the following:

• If the percentage difference is between -0.05 and 0.05. It is a Recommended Size, and this is indicated by a Teal colored tab.

• If the percentage difference is between 0.05 and 0.15. It is Slightly Loose, and this is indicated by an Amber colored tab.

• If the percentage difference is greater than 0.15. It is Very Loose, and this is indicated by a Red colored tab.

• If the percentage difference is between -0.05 and -0.15. It is Slightly Tight, and this is indicated by a Yellow colored tab.

• If the percentage difference is smaller than -0.15. It is Very Tight, and this is indicated by a Red tab.

• Everything outside these values is either too small or too large and will automatically be indicated as Too Tight or Too loose.

[0023] Though this example utilizes teal, amber, red, and yellow as indicators, other colors may be utilized. Other types of indicators may be utilized in addition to or alternatively to colors. According to an example, the type of indicator or the colors may be selected or otherwise specified by a user.

[0024] Such a size recommendation system basically automates the traditional size chart system currently used by brands and e- commerce retailers, by analyzing the clothing measurements against the exact key body measurement on the users preselected silhouette, The user can compare their body measurements with product sizes in real time to either obtain an automated recommended size with the app or opt to choose their personal fit preference in any clothing size presenting an automated and intelligent sizing system for the user’s seamless fitting experience.

[0025] An illustration of how the Size and Fit system works in one embodiment is presented below:

[0026] Step 1. Key points of a user’s body measurements are displayed on the app after the user has taken their body measurements using their smart phone camera. [0027] FIG. 1 illustrates an example display screen 100 including a user silhouette 110 with body measurements 120, 130 determined and displayed according to an example embodiment.

In this example, a user silhouette with accurate body measurements may be provided for display. Measurements approximating the sizes of the user’s neck, shoulders, chest, waist, sleeve, hips, inseam, and outseam may be displayed alongside a silhouette of a user, for example.

[0028] Step 2. When a product item is selected, the size and fit system recommends a specific size to the users after matching their key body measurements to the key measurement points on the clothing item, otherwise it alerts the user to specific points where the product item does not fit.

[0029] FIG. 2 illustrates an example recommendation for an item determined in accordance with one of more example embodiments. In this example, a mobile application may be utilized to determine and display one or more recommendations 200, including the clothing item, to the user as a result of the match between the user’s measurements and the product measurements. A user silhouette 210, as determined by one or more processes described herein, may be provided for display. Additionally, one or more measurements corresponding to the clothing and the user may be displayed 220, along with an indication of fit. In this example, the indication of fit may be shown by the circle (e.g., the circles after “M: 100 cm” and “M: 80 cm”), where the circle may be of one or more colors corresponding to a type of fit. For example, a red circle may indicate a bad fit of the clothing to the user. A teal or green circle may be provided in cases with a good fit, as is the case in the present example.

[0030] A user may select one or more sizes 230, and an indication of sizes which are in stock may be provided. A user may select through the various sizes 230 and see how the item looks on the silhouette 210, to get a better visual on how different sizes may fit. For example, a user might have a better fit in the shoulders for a size M instead of a size S, but the size S might be tight around the abdomen area. The user may then consider this information to determine which articles of clothing to purchase. If a user is satisfied with the fit, they may add the article of clothing to their bag 240 for purchase.

[0031] FIG. 3 illustrates an example display 300 of how an item of clothing may compare to a user’s body measurements, according to an example embodiment. Figure 3. When According to this example, when a product item is selected, the size and fit system may enable the user to see how all key areas of the clothing’s dimensions compare to their unique body measurements. For example, a user’s silhouette 310 may be presented with the user’s measurements and clothing measurements 320, 330. The clothing measurements may include an indication of fit, such as through the circles shown (e.g., “M: 80 cm,” “M: 77 cm,” and “M: 170 cm”). In this example, the size difference between the clothing measurement and the chest measurement 320 may be so great that it may be determined that the fit is bad. As such, an indicator associated with a particular color may be provided, such as a red circle to indicate a bad fit at the chest. In areas of good fit where the size difference is not above a determined threshold, an indication of good fit may be provided, such as a teal or green circle. In this example, the length and waist may be classified as a good fit and therefore may have a teal or green circle provided with the clothing measurements 330.

[0032] A user may select one or more sizes 340, and an indication of sizes which are in stock may be provided. A user may select through the various sizes 340 and see how the item looks on the silhouette 310, to get a better visual on how different sizes may fit. For example, a user might have a better fit in the shoulders for a size M instead of a size S, but the size S might be tight around the abdomen area. The user may then consider this information to determine which articles of clothing to purchase. If a user is satisfied with the fit, they may add the article of clothing to their bag 350 for purchase.

[0033] According to one or more embodiments, a color indicator may be utilized to identify sizes which are determined to not be a good fit. In this example, an indicator for size M may be shown in a color such as red to indicate to a user that size M might not be a good fit for the user.

[0034] FIG. 4 illustrates an example display 400 illustrating how an item of clothing may fit on a user, according to an example embodiment. In this example, one or more measurement points 420, 430 on the display may indicate that a dress in size L is a great fit around the chest/bust and around the hips of the silhouette 410, but may be tight and a bad fit around the waist. These measurement points may be presented to the user in a very clear and precise manner, giving the user the opportunity to pick their fit preference. For example, comparisons between the clothing measurement and the silhouette or silhouette measurements may be shown at the measurement points 420, 430, and one or more indicators may be provided at the measurement points 420, 430 to clearly indicate how the clothing will likely fit. In this example, a darker circle may correspond to a better fit, as shown at measurement points 420, and a lighter circle may correspond to a worse fit, as shown at measurement point 430. A user may select one or more sizes 440, and an indication of sizes which are in stock may be provided. A user may select through the various sizes 440 and see how the item looks on the silhouette 410, to get a better visual on how different sizes may fit. If a user is satisfied with the fit, they may add the article of clothing to their bag 450 for purchase.

[0035] According to one or more embodiments, a color indicator may be utilized to identify sizes which are determined to not be a good fit. In this example, an indicator for size L may be shown in a color such as yellow to indicate to a user that size L might not be a perfect fit for the user, but may be an okay fit overall.

[0036] In some embodiments, a user can choose from among a number ( e.g ., 3) of fitting options or preferences, such as, but not limited to: slightly tight, regular and slightly loose.

Using machine learning, for example, the system can, over time, adjust the user’s recommended size based on the choices the user makes.

[0037] In some embodiments, the system can take into consideration the style of specific clothing pieces and warn the user of this. If the user prefers tight fitting clothing but the chosen product is lose-fitting, the system can recommend getting a smaller size.

[0038] In some embodiments, if a user chooses to return a product, the system can determine and/or kick off a flow that asks for the reason for return. If the reason is the size, the system can use the information given by the user to improve the size recommendation. Over time, the data collected will be used for artificial intelligence/machine learning (AI/ML) improvements. Once there is sufficient data available, AI/ML can be used to improve both the individual size recommendation and the system-wide recommendation. The system can be adjusted to make automatic recommendation which are user-specific, brand-specific, product-specific and make similar adjustments to the recommendation algorithm. In some embodiments, such a system can be offered as a service to other parties, such as to brands to help to replace the manual size chart on brand websites and apps.

[0039] In one embodiment, a system can be implemented using solution is built with Java - for the backend (server side), and Flutter - for a cross-platform mobile application, in other embodiments, such solutions can be built with other programming languages or technologies as well. For calculating the body measurements of the user, a third-party service or application programming interface (API) could be used such as "‘3D Look”. However, 3D Look is used only to ease the process, and such solutions would work with other methods of gathering data as well, as discussed and suggested herein.

[0040] The references to the following figures represent example methods that can be utilized in accordance with various embodiments.

[0041] FIG 5 A illustrates an example method 500a for onboarding a user, in accordance with an example embodiment. According to this example, the system may determine whether user measurements are manually input 510a. If the user measurements are manually input, the system may then generate or create a silhouette 550a approximating the user’s body based on the measurements. If the measurements are not manually input, the system may then request photographs of the user 520a. The photographs may be requested via a client device, such as through one or more sensors of a smartphone, tablet, or other device with such capabilities. The user may take photographs directly through an application operating on the client device, or they may use a separate application or apparatus to take the photographs and upload them to the application. An API such as “3DLook” may be utilized to determine the user’s measurements 530a. In some embodiments, the user measurements may be transformed to clothing measurements 540a, and a silhouette approximating a user’s body may be generated or created 550a.

[0042] FIG. 5B illustrates an example method 500b for sizing and fitting a product to a user, in accordance with an example embodiment. According to this example, a product may be selected by or for the user 510b. The product may be an item of clothing, among other options. The system may determine whether the user has a silhouette 520b. If the user does not have a silhouette, then the user may continue shopping without displayed sizing recommendations 530b. If the user does have a silhouette available, the system may compare one or more sizes of the product to the measurements of the user 540b. The system may also apply one or more user experience enhancements 550b. Such enhancements may include clothing fitting style preferences, user style preferences, and other such user preferences. For example, a user may specify that they like a particular style of a dress to be tight-fitting, or a particular type of denim to be loose-fitting. A user may be presented with various size approximations and fit data 560b, such as where an item of clothing may fit tighter or looser at particular positions on the body. A user may proceed with purchasing the product 570b, and may base their decision on the sizing information presented to them.

[0043] FIG. 5C illustrates an example method 500c for determining one or more sizes for a user, in accordance with an example embodiment. In this example, one or more user measurements may be compared and matched to one or more product measurements 502c. The system may compare names for the measurements such as “waist,” “chest,” etc. The system may then determine or calculate a difference in percentage for each measurement point 504c. Analyzing the various sizes available for the product and associated product size information, the system may determine and/or identify a size accounting for the smallest difference between product measurements and user measurements and provide that size as a recommendation to the user 506c.

[0044] For each measurement, a fit indicator may be displayed 508c. In some embodiments, the fit indicator may be determined based, at least in part, upon the difference percentage between the user’s measurements and the product’s measurements at a given measurement point. A measurement point may correspond to one of the various points of measurement, such as a chest, waist, hip, etc. In some examples, the fit indicator may be displayed by colors, where a red color may correspond to a bad fit, a yellow color may correspond to a moderate fit, and a green or teal color may correspond to a good fit. This example is not intended to be limiting, and other colors may be used. Additionally, other types of indicators providing information about the fit of the product to the silhouette may be displayed.

[0045] The system may determine a difference percentage at the various measurement points between the product’s measurements and the user’s measurements 510c. The difference percentage may be compared to various thresholds to determine how the item fit is to be classified. For example, if the difference percentage is between -0.05 and 0.05, the fit may determined to be “good,” and the size for that analyzed product corresponding to the “good” fit may be displayed to the user as a recommended size 512c. According to another example, if the difference percentage is smaller than -0.15, the system may display the measurement point or size as being significantly different in size, along with an indication that the fit is “tight” 514c. Additionally, an indicator may be provided in a red color to indicate the significantly different and tight fit. According to yet another example, if the difference percentage is between -0.05 and -0.15, then the system may display the measurement point or the size as being slightly different in size, along with an indication that the fit is “tight” 516c. Additionally, an indicator may be provided in a yellow color to indicate the slightly different and tight fit.

[0046] According to another example, if the difference percentage is between 0.05 and

0.15, then the system may display the measurement point or the size as being slightly different in size, along with an indication that the fit is “loose” 518c. Additionally, an indicator may be provided in a yellow color to indicate the slightly different and tight fit. According to yet another example, if the difference percentage is greater than 0.15, then the system may display the measurement point or the size as being significantly different in size, along with an indication that the fit is “loose” 520c. Additionally, an indicator may be provided in a red color to indicate the slightly different and tight fit.

[0047] In some embodiments, a summary of the fit or caption describing the fit may be provided for display on the client device. For example, if a product fits properly on the waist and length but is a poor fit at the chest, a summary or caption may be provided such as “great fit on the waist and length, but won’t fit around the chest.”

[0048] FIG. 5D illustrates an example method 500d for training an algorithm that can be utilized in accordance with one or more example embodiments. According to this example, a user may decide to return a product 510d. A user may indicate to the system that they have selected the wrong size 520d, or the system may make infer that the user returned the product based on a previous determination that the fitting for that size would be bad for the user. Then, based on the user indication and feedback, the system may adjust the silhouette measurements and/or one or more user preferences. [0049] An approach in accordance with at least one embodiment can provide a mobile app clothing store with a fancy youth-attracting application, such as referred to herein as a “Size and Fit” system, which generates a fitting silhouette of the user just by taking two photos of the user and calculating their measurements to offer an automated size recommendation to the user based on the user body measurements versus clothing measurements.

[0050] Users can create an account through email or using several other popular services like Facebook, Google login and Apple login. There are several flows in an example onboarding process designed to interest the user from the very start. These can include first creating a fitting silhouette. An onboarding process can encourage a user to create a fitting silhouette. This process will require two steps. The user will enter their height, weight and shoe size, and then take or provide two photos - front and side. Before taking the photos, the user should choose between two silhouettes: Chelsea (female) and John (male), in order to have a gender specific onboarding process. There are written directions before starting the process, that will help the user take the best photo. The user can also choose if they will like to take the photo by themselves or a friend can help them take a photo. Once the camera opens, there are voice instructions which will guide the user through the process. Once the photos are taken, the fitting silhouette is created, and it is displayed on the screen with the calculated measurements of the user. In some example embodiments, may correspond to a body contour, and may not need to be displayed. Instead, the product or fit recommendations may be provided without displaying an underlying silhouette. In some cases, a user may not have a complete set of measurements that map to the measurements for the product. In such cases, the system may use what measurements are available to determine fit recommendations based on the size of the product, without displaying a physical silhouette.

[0051] To save this fitting silhouette user may need to sign in with an account. To create an account, the user can enter information such as password, name, date of birth, and check the radio button for Terms and Conditions. The user in at least one embodiment will be prompted to the Quick Quiz screens, which for the MVP are represented only by screenshots of few questions concerning their style preferences. These screens can be skipped. After finishing the Onboarding process, the user is taken to a screen to select their shopping preferences: women, men or shop all.

[0052] In a least one embodiment, a homepage or other such user interface may include multiple sections. Once such section can be reserved for promotions and important information to present to the users. This might be personalized information, brand promotion, platform-wide information (like a new feature), etc. Another section, such as a “New for You” section, can include one or more promotions for new clothing in the store. These will be ordered by certain equations which will take into account the user’s preference. The list is horizontally scrollable and gives the users the option to quickly and easily like an item. A trending section can promote actual or seasonal clothing to the user. For the full product, it can also provide direct access to the Discover pages. An interface can present actual items or even whole categories. A “Picked for you” (Personalized) section can present a horizontally scrollable list of items specifically targeting the user preferences from the categories/styles they look at most. These items can also have the option for “like”.

[0053] A “User’s Picked for You” page can be pre-populated with items similar to their wish list, this will be an added parameter to streamline the user’s preference in order to make accurate recommendations. For a Fitting silhouette promotion, if the user hasn’t created a fitting silhouette yet, there is a section that dynamically appears between other sections. This promotion will explain the benefits of creating a silhouette and call to action. For a “Similar to Wishlist Recommendations” section, item can be chosen based on the items in the user’s Wishlist. This section can also be used to promote items on sale or new products. For a “Swipe to Fit” section, this can utilize a swiping input for liking/disliking combinations in different styles that will help nail down the user’s style and prepare better recommendations. The product info is at the top, but as a less relevant content will not be in focus. A separate “view product” link is also available below the product info. If clicked, the user can access the product page and get back immediately using the “back” button. To make the experience more enjoyable, there is an iconography for the like/dislike buttons. The user can also swipe right/left for the same functionality.

[0054] In a “Main Product Info” section, a picture of the product is shown as well as most important information about this product are below the picture, like name, brand, price and information if the item is available in stock. Also, there are user’s actions available (size and fit, add to bag, wish it, etc.) will also be on top to enable easy user action. In a “Product Details” section, which can be next on scroll, can be details about the product, like colors available, composition, care, delivery, etc. A “Shop the Look” section can show other products from the pictures the models are wearing. A “Similar Products Recommendations” section can recommend clothing in a similar style to the product the user is viewing. A “Recently Viewed” section can show the history of the products the user has viewed without overwhelming information.

[0055] A user can then perform multiple actions with respect to this interface. For example, a user can choose a size. If the user has created a fitting silhouette, the ideal size will be chosen automatically. The user can also select an “Add to Bag” option. If the user has chosen size, or size is chosen for the user (has a fitting silhouette), this will add the item to the bag. Otherwise, it will first ask of the user to pick a size.

[0056] A size and fit process in accordance with at least one embodiment can take advantage of the user’s fitting silhouette. The size ideal for the user will be chosen automatically. The user can still browse through the size and see how other sizes would match their body. On the silhouette preview, for each size, the user can see both descriptive notes, and detailed size comparison. Examples include descriptive notes, such as “A bit tight”, “Slightly loose”, “Slightly tight”, etc. Another example is a detailed size comparison, where the user can match the clothing dimensions with the dimensions of each part of his body (chest, length, hips, etc.) to see where exactly the sizes differ.

[0057] If the user has created a fitting silhouette, there can be a small preview of the silhouette on the Profile page, because the users don’t have any benefit seeing it all the time or waiting for it to load. When they want to access the silhouette page, they can click on the “Update Your Silhouette” button. If the user opens the silhouette, they can see the main measurements on it. At the bottom of the silhouette screen, the user can scroll to see all measurements in more details.

[0058] If there is no Fitting Silhouette created, the system can provide a short CTA button on the Profile page to make the users do it. Below the silhouette space, there can be multiple link categories where the users can access specific pages to get information or make adjustments to their profile like:

• Personal info (have the option to update the silhouette)

• Account security (details and password)

• Orders and returns - (Not available for MVP)

• Shipping addresses - (Not available for MVP)

• Payment info - (Not available for MVP)

• Preferred currency- (Not available for MVP)

• Shopping preferences (men/women/all)

• Notifications & email settings- (Not available for MVP)

• Connect social accounts- (Not available for MVP)

• Support pages: About, Terms & conditions, Help, FAQ, etc. (Not available for MVP)

• Log out option

[0059] In at least one embodiment, a “My Bag” or similar page can be accessed from almost all frequently used pages on the app. The number of items placed in the cart is visible, but the page may not be available for the MVP.

[0060] In at least some embodiments, users can access all products they liked on this page and decide if they want to proceed to buy it, keep it, or remove from the list. They can also see information related to product availability. When they click on the “Move to Bag” button the Size & Fit page is being opened with the recommended size, but they still can make adjustments. When they click on “Done” or “Add to Bag”, the product will be moved to Bag.

[0061] Computing resources, such as servers or personal computers, can be used to build, implement, execute, and/or access systems, services, processes, and data discussed herein. Such resources will generally include at least a set of standard components configured for general purpose operation, although various proprietary components and configurations can be used as well within the scope of the various embodiments. One example of such a computing resource is illustrated in FIG. 6. [0062] FIG. 6 illustrates components of an example computing resource 600 that can be utilized in accordance with various embodiments. It should be understood that there can be many such compute resources and many such components provided in various arrangements, such as in a local network or across the Internet or “cloud,” to provide compute resource capacity as discussed elsewhere herein. The computing resource 600 ( e.g ., a desktop or network server) will have one or more processors 602, such as central processing units (CPUs), graphics processing units (GPUs), and the like, that are electronically and/or communicatively coupled with various components using various buses, traces, and other such mechanisms. A processor 602 can include memory registers 606 and cache memory 604 for holding instructions, data, and the like. In this example, a chipset 614, which can include a northbridge and southbridge in some embodiments, can work with the various system buses to connect the processor 602 to components such as system memory 616, in the form or physical RAM or ROM, which can include the code for the operating system as well as various other instructions and data utilized for operation of the computing device. The computing device can also contain, or communicate with, one or more storage devices 620, such as hard drives, flash drives, optical storage, and the like, for persisting data and instructions similar, or in addition to, those stored in the processor and memory. The processor 602 can also communicate with various other components via the chipset 614 and an interface bus (or graphics bus, etc.), where those components can include communications devices 624 such as cellular modems or network cards, media components 626, such as graphics cards and audio components, and peripheral interfaces 630 for connecting peripheral devices, such as printers, keyboards, and the like. At least one cooling fan 632 or other such temperature regulating or reduction component can also be included as well, which can be driven by the processor or triggered by various other sensors or components on, or remote from, the device. Various other or alternative components and configurations can be utilized as well as known in the art for computing devices.

[0063] At least one processor 602 can obtain data from physical memory 616, such as a dynamic random access memory (DRAM) module, via a coherency fabric in some embodiments. It should be understood that various architectures can be utilized for such a computing device, that may include varying selections, numbers, and arguments of buses and bridges within the scope of the various embodiments. The data in memory may be managed and accessed by a memory controller, such as a DDR controller, through the coherency fabric. The data may be temporarily stored in a processor cache 604 in at least some embodiments. The computing device 600 can also support multiple I/O devices using a set of I/O controllers connected via an I/O bus. There may be I/O controllers to support respective types of I/O devices, such as a universal serial bus (USB) device, data storage (e.g., flash or disk storage), a network card, a peripheral component interconnect express (PCIe) card or interface 630, a communication device 624, a graphics or audio card 626, and a direct memory access (DMA) card, among other such options. In some embodiments, components such as the processor, controllers, and caches can be configured on a single card, board, or chip (i.e., a system-on-chip implementation), while in other embodiments at least some of the components may be located in different locations, etc.

[0064] An operating system (OS) running on the processor 602 can help to manage the various devices that may be utilized to provide input to be processed. This can include, for example, utilizing relevant device drivers to enable interaction with various I/O devices, where those devices may relate to data storage, device communications, user interfaces, and the like. The various I/O devices will typically connect via various device ports and communicate with the processor and other device components over one or more buses. There can be specific types of buses that provide for communications according to specific protocols, as may include peripheral component interconnect) PCI or small computer system interface (SCSI) communications, among other such options. Communications can occur using registers associated with the respective ports, including registers such as data-in and data-out registers. Communications can also occur using memory-mapped I/O, where a portion of the address space of a processor is mapped to a specific device, and data is written directly to, and from, that portion of the address space.

[0065] Such a device may be used, for example, as a server in a server farm or data warehouse. Server computers often have a need to perform tasks outside the environment of the CPU and main memory (i.e., RAM). For example, the server may need to communicate with external entities (e.g., other servers) or process data using an external processor (e.g., a General Purpose Graphical Processing Unit (GPGPU)). In such cases, the CPU may interface with one or more I/O devices. In some cases, these I/O devices may be special-purpose hardware designed to perform a specific role. For example, an Ethernet network interface controller (NIC) may be implemented as an application specific integrated circuit (ASIC) comprising digital logic operable to send and receive packets.

[0066] As discussed, different approaches can be implemented in various environments in accordance with the described embodiments. As will be appreciated, although a network- or Web-based environment is used for purposes of explanation in several examples presented herein, different environments may be used, as appropriate, to implement various embodiments. Such a system can include at least one electronic client device, which can include any appropriate device operable to send and receive requests, messages or information over an appropriate network and convey information back to a user of the device. Examples of such client devices include personal computers, cell phones, handheld messaging devices, laptop computers, set-top boxes, personal data assistants, electronic book readers and the like. The network can include any appropriate network, including an intranet, the Internet, a cellular network, a local area network or any other such network or combination thereof. Components used for such a system can depend at least in part upon the type of network and/or environment selected. Protocols and components for communicating via such a network are well known and will not be discussed herein in detail. Communication over the network can be enabled via wired or wireless connections and combinations thereof. In this example, the network includes the Internet, as the environment includes a Web server for receiving requests and serving content in response thereto, although for other networks, an alternative device serving a similar purpose could be used, as would be apparent to one of ordinary skill in the art.

[0067] The illustrative environment includes at least one application server and a data store. It should be understood that there can be several application servers, layers or other elements, processes or components, which may be chained or otherwise configured, which can interact to perform tasks such as obtaining data from an appropriate data store. As used herein, the term "data store" refers to any device or combination of devices capable of storing, accessing and retrieving data, which may include any combination and number of data servers, databases, data storage devices and data storage media, in any standard, distributed or clustered environment. The application server can include any appropriate hardware and software for integrating with the data store as needed to execute aspects of one or more applications for the client device and handling a majority of the data access and business logic for an application. The application server provides access control services in cooperation with the data store and is able to generate content such as text, graphics, audio and/or video to be transferred to the user, which may be served to the user by the Web server in the form of HTML, XML or another appropriate structured language in this example. The handling of all requests and responses, as well as the delivery of content between the client device and the application server, can be handled by the Web server. It should be understood that the Web and application servers are not required and are merely example components, as structured code discussed herein can be executed on any appropriate device or host machine as discussed elsewhere herein.

[0068] The data store can include several separate data tables, databases or other data storage mechanisms and media for storing data relating to a particular aspect. For example, the data store illustrated includes mechanisms for storing content ( e.g ., production data) and user information, which can be used to serve content for the production side. The data store is also shown to include a mechanism for storing log or session data. It should be understood that there can be many other aspects that may need to be stored in the data store, such as page image information and access rights information, which can be stored in any of the above listed mechanisms as appropriate or in additional mechanisms in the data store. The data store is operable, through logic associated therewith, to receive instructions from the application server and obtain, update or otherwise process data in response thereto. In one example, a user might submit a search request for a certain type of item. In this case, the data store might access the user information to verify the identity of the user and can access the catalog detail information to obtain information about items of that type. The information can then be returned to the user, such as in a results listing on a Web page that the user is able to view via a browser on the user device. Information for a particular item of interest can be viewed in a dedicated page or window of the browser.

[0069] Each server typically will include an operating system that provides executable program instructions for the general administration and operation of that server and typically will include computer-readable medium storing instructions that, when executed by a processor of the server, allow the server to perform its intended functions. Suitable implementations for the operating system and general functionality of the servers are known or commercially available and are readily implemented by persons having ordinary skill in the art, particularly in light of the disclosure herein.

[0070] The environment in one embodiment is a distributed computing environment utilizing several computer systems and components that are interconnected via communication links, using one or more computer networks or direct connections. However, it will be appreciated by those of ordinary skill in the art that such a system could operate equally well in a system having fewer or a greater number of components than are illustrated. Thus, the depiction of the systems herein should be taken as being illustrative in nature and not limiting to the scope of the disclosure.

[0071] The various embodiments can be further implemented in a wide variety of operating environments, which in some cases can include one or more user computers or computing devices which can be used to operate any of a number of applications. User or client devices can include any of a number of general purpose personal computers, such as desktop or laptop computers running a standard operating system, as well as cellular, wireless and handheld devices running mobile software and capable of supporting a number of networking and messaging protocols. Such a system can also include a number of workstations running any of a variety of commercially-available operating systems and other known applications for purposes such as development and database management. These devices can also include other electronic devices, such as dummy terminals, thin-clients, gaming systems and other devices capable of communicating via a network.

[0072] Most embodiments utilize at least one network that would be familiar to those skilled in the art for supporting communications using any of a variety of commercially-available protocols, such as TCP/IP, FTP, UPnP, NFS, and CIFS. The network can be, for example, a local area network, a wide-area network, a virtual private network, the Internet, an intranet, an extranet, a public switched telephone network, an infrared network, a wireless network and any combination thereof. [0073] In embodiments utilizing a Web server, the Web server can run any of a variety of server or mid-tier applications, including HTTP servers, FTP servers, CGI servers, data servers, Java servers and business application servers. The server(s) may also be capable of executing programs or scripts in response requests from user devices, such as by executing one or more Web applications that may be implemented as one or more scripts or programs written in any programming language, such as Java^®, C, C# or C++ or any scripting language, such as Perl, Python or TCL, as well as combinations thereof. The server(s) may also include database servers, including without limitation those commercially available from Oracle^®, Microsoft^®, Sybase^® and IBM^® as well as open-source servers such as MySQL, Postgres, SQLite,

MongoDB, and any other server capable of storing, retrieving and accessing structured or unstructured data. Database servers may include table -based servers, document-based servers, unstructured servers, relational servers, non-relational servers or combinations of these and/or other database servers.

[0074] The environment can include a variety of data stores and other memory and storage media as discussed above. These can reside in a variety of locations, such as on a storage medium local to (and/or resident in) one or more of the computers or remote from any or all of the computers across the network. In a particular set of embodiments, the information may reside in a storage-area network (SAN) familiar to those skilled in the art. Similarly, any necessary files for performing the functions attributed to the computers, servers or other network devices may be stored locally and/or remotely, as appropriate. Where a system includes computerized devices, each such device can include hardware elements that may be electrically coupled via a bus, the elements including, for example, at least one central processing unit (CPU), at least one input device (e.g., a mouse, keyboard, controller, touch-sensitive display element or keypad) and at least one output device (e.g., a display device, printer or speaker). Such a system may also include one or more storage devices, such as disk drives, magnetic tape drives, optical storage devices and solid-state storage devices such as random access memory (RAM) or read-only memory (ROM), as well as removable media devices, memory cards, flash cards, etc. [0075] Such devices can also include a computer-readable storage media reader, a communications device (e.g., a modem, a network card (wireless or wired), an infrared communication device) and working memory as described above. The computer-readable storage media reader can be connected with, or configured to receive, a computer-readable storage medium representing remote, local, fixed and/or removable storage devices as well as storage media for temporarily and/or more permanently containing, storing, transmitting and retrieving computer-readable information. The system and various devices also typically will include a number of software applications, modules, services or other elements located within at least one working memory device, including an operating system and application programs such as a client application or Web browser. It should be appreciated that alternate embodiments may have numerous variations from that described above. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, software (including portable software, such as applets) or both. Further, connection to other computing devices such as network input/output devices may be employed.

[0076] Storage media and other non-transitory computer readable media for containing code, or portions of code, can include any appropriate media known or used in the art, such as but not limited to volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, including RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other medium which can be used to store the desired information and which can be accessed by a system device. Based on the disclosure and teachings provided herein, a person of ordinary skill in the art will appreciate other ways and/or methods to implement the various embodiments.

[0077] The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. It will, however, be evident that various modifications and changes may be made thereunto without departing from the broader spirit and scope of the invention as set forth in the claims.

Claims

1. A computer-implemented method, comprising: obtaining one or more images of a user; determining, based at least in part upon the one or more images, one or more measurements of the user; generating, based at least in part upon the one or more measurements of the user, a silhouette of the user for display on a client device; receiving a selection of at least one item of clothing; comparing one or more measurements of the item of clothing to the silhouette of the user; and providing for display on the client device one or more recommendations associated with the item of clothing, based at least in part upon the comparison.

2. The computer-implemented method of claim 1, further comprising: calculating a difference in percentage between the one or more measurements of the item of clothing and the one or more measurements of the user; providing for display a recommended size of the item of clothing corresponding to a smallest difference in percentage.

3. The computer-implemented method of claim 2, wherein the recommended size of the item of clothing is determined based, at least in part, upon the difference in percentage being within one or more determined thresholds.

4. The computer-implemented method of any of the preceding claims, wherein the one or more recommendations correspond to a size of the item of clothing.

5. The computer-implemented method of any of the preceding claims, further comprising: updating the silhouette based, at least in part, upon user feedback; and updating one or more user preferences based, at least in part, upon the user feedback.

6. A computer-implemented method, comprising: determining, based at least in part upon one or more images of a user, one or more measurements of the user; generating, based at least in part upon the one or more measurements of the user, a silhouette of the user; receiving a selection of at least one item of clothing; and providing for presentation on a display of a client device one or more recommendations associated with the at least one item of clothing based, at least in part, upon the silhouette of the user.

7. The computer-implemented method of claim 6, further comprising: calculating a difference in percentage between the one or more measurements of the item of clothing and the one or more measurements of the user; and providing for display a recommended size of the item of clothing corresponding to a smallest difference in percentage.

8. The computer-implemented method of claim 7, wherein the recommended size of the item of clothing is determined based, at least in part, upon the difference in percentage being within one or more determined thresholds.

9. The computer-implemented method of any of claims 6-8, wherein the one or more recommendations correspond to a size of the item of clothing.

10. The computer-implemented method of any of claims 6-9, further comprising: providing for display one or more indicators indicating a level of fit of the item of clothing on the user.

11. The computer-implemented method of any of claims 6-10, further comprising: generating, based at least in part upon the one or more measurements of the user, a silhouette of the user for display on a client device; and presenting the at least one item of clothing on the generated silhouette.

12. The computer-implemented method of claim 11, further comprising: updating the silhouette based, at least in part, upon user feedback; and updating one or more user preferences based, at least in part, upon the user feedback.

13. The computer-implemented method of any of claims 6-12, wherein the one or more measurements of the user are determined using an application programming interface (API) running on the client device.

14. A non-transitory computer-readable medium storing instructions that when executed by one or more processors, cause the one or more processors to: determine, based at least in part upon one or more images of a user, one or more measurements of the user; generate, based at least in part upon the one or more measurements of the user, a silhouette of the user; receive a selection of at least one item of clothing; and provide for presentation on a display of a client device one or more recommendations associated with the at least one item of clothing based, at least in part, upon the silhouette of the user.

15. The non-transitory computer-readable medium of claim 14, wherein the instructions when executed by the one or more processors cause the one or more processors to: calculate a difference in percentage between the one or more measurements of the item of clothing and the one or more measurements of the user; and provide for display a recommended size of the item of clothing corresponding to a smallest difference in percentage.

16. The non-transitory computer-readable medium of any of claims 14-15, wherein the recommended size of the item of clothing is determined based, at least in part, upon the difference in percentage being within one or more determined thresholds.

17. The non-transitory computer-readable medium of any of claims 14-16, wherein the instructions when executed by the one or more processors cause the one or more processors to: provide for display one or more indicators indicating a level of fit of the item of clothing on the user.

18. The non-transitory computer-readable medium of any of claims 14-17, wherein the instructions when executed by the one or more processors cause the one or more processors to: generate, based at least in part upon the one or more measurements of the user, a silhouette of the user for display on a client device; and present the at least one item of clothing on the generated silhouette.

19. The non-transitory computer-readable medium of claim 18, wherein the instructions when executed by the one or more processors cause the one or more processors to: update the silhouette based, at least in part, upon user feedback; and update one or more user preferences based, at least in part, upon the user feedback.

20. The non-transitory computer-readable medium of any of claims 14-19, wherein the one or more measurements of the user are determined using an application programming interface (API) running on the client device.