System and method for size setting of image-based disposable articles

Abstract

This invention provides a system and method for recommending the size of disposable garments to be worn by a subject. Images of the subject are analyzed to determine fit parameters. These fit parameters are then applied to various disposable garment size setting models.

Description

Technical Field

[0001] This disclosure relates to systems and methods for determining the recommended size of a disposable article to be worn by a subject, and more particularly, to systems and methods for determining the recommended size of a disposable article to be worn by a subject based on processing of images of the subject. Background Technology

[0002] Absorbent products such as diapers, training pants, etc., are manufactured in a variety of sizes and configurations. To ensure that absorbent products are comfortable and perform properly, wearing the correct size is crucial. Given the numerous product lines available for purchase, and each product line typically offering multiple sizing options, determining which product line and which size is suitable for a particular wearer can be challenging. Furthermore, disposable product sizes are often recommended based on the wearer's weight rather than their physical dimensions. However, a wearer's weight can be a poor predictor of their actual physical dimensions, thus selecting a product size based on weight can lead to an inappropriate fit. Moreover, while knowledge of the wearer's physical dimensions is relevant to an appropriate disposable product fit, these dimensions are often not known and can be difficult to measure manually. Therefore, systems and methods for recommending absorbent products based on the wearer's physical attributes are needed. Summary of the Invention

[0003] In one form, a computer-based method includes: storing multiple disposable product size setting models in a data repository by a disposable product recommendation calculation system, the multiple disposable product size setting models corresponding to a plurality of corresponding pre-made disposable products available for purchase. The method further includes: receiving images collected by at least one camera by the disposable product recommendation calculation system, wherein the images include a representation of a subject, and the subject is a consumer of the pre-made disposable products. The method further includes: determining a scale of the images by the disposable product recommendation calculation system, the scale of which relates the size of the subject's representation in the images to the subject's physical size. The method further includes: determining physical properties of the subject's representation in the images by the disposable product recommendation calculation system. The method further includes: determining multiple fit parameters of the subject by the disposable product recommendation calculation system based on the scale of the images and the physical properties of the subject's representation. The method further includes: applying the multiple fit parameters to one or more of the multiple disposable product size setting models by the disposable product recommendation calculation system. The method further includes: determining recommended pre-made disposable products for the subject by applying a disposable product recommendation calculation system to one or more disposable product size setting models among multiple fit parameters, wherein the recommended pre-made disposable products are selected from multiple pre-made disposable products available for purchase. The method also includes: providing the subject with an indication of recommended pre-made disposable products by the disposable product recommendation calculation system.

[0004] In another form, a computer-based system includes: a data repository storing multiple disposable product size setting models corresponding to prefabricated disposable products of corresponding sizes available for purchase. The system also includes: a disposable product recommendation calculation system comprising a computer-readable medium storing computer-executable instructions. These computer-executable instructions are configured to instruct one or more computer processors to: receive an image of a subject collected by a remote mobile computing device; determine the scale of the image; and process the image to determine the physical attributes of the subject. Based on the scale of the image and the physical attributes of the subject, multiple fit parameters of the subject are determined. The computer-executable instructions are further configured to instruct one or more computer processors to compare the multiple fit parameters with one or more of the multiple disposable product size setting models. Based on the comparison of the multiple fit parameters with one or more of the multiple disposable product size setting models, a recommended prefabricated disposable product for the subject is determined. The computer-executable instructions are configured to instruct one or more computer processors to send an instruction for the recommended prefabricated disposable product to the remote mobile computing device.

[0005] In another form, a computer-based method includes: storing multiple disposable product size setting models corresponding to a plurality of corresponding pre-made disposable products available for purchase. The method further includes: receiving images collected by at least one camera, wherein the images include a representation of a subject, and the subject is a consumer of the pre-made disposable products. The method further includes: determining the scale of the images such that the size of the subject's representation in the images is related to the subject's physical size. The method further includes: determining physical properties of the subject's representation in the images through image processing. The method further includes: determining multiple fit parameters of the subject based on the image scale and the physical properties of the subject's representation. The method further includes: determining recommended pre-made disposable products for the subject by a disposable product recommendation calculation system based on the application of the multiple fit parameters to one or more of the multiple disposable product size setting models, wherein the recommended pre-made disposable products are selected from the plurality of pre-made disposable products available for purchase. The method further includes: providing an indication of recommended pre-made disposable products for the subject by the disposable product recommendation calculation system. Attached Figure Description

[0006] The above and other features and advantages of this disclosure, as well as the ways in which they are obtained, will become more apparent from the following description of non-limiting embodiments of this disclosure, taken in conjunction with the accompanying drawings, and the disclosure itself will be better understood, wherein:

[0007] Figure 1 The text describes a user interacting with an exemplary single-use product recommendation calculation system.

[0008] Figure 2 The text describes a user interacting with another exemplary single-use product recommendation calculation system.

[0009] Figures 3A to 3C An exemplary scale object and subject are depicted placed within the field of view of an image capturing device.

[0010] Figures 4 to 7 Various exemplary operational arrangements for a single-use product recommendation calculation system are described.

[0011] Figure 8 An exemplary process that can be performed by a single-use product recommendation calculation system is described.

[0012] Figure 9 The determination of fit parameters for subjects using proportional objects is described.

[0013] Figure 10 The method of using foot size to determine proportions to determine fit parameters for subjects is described.

[0014] Figure 11 The method of using head circumference to determine proportions for determining fit parameters of subjects is described.

[0015] Figure 12 A simplified size-setting model depicting the lineup of disposable products.

[0016] Figure 13 A series of simplified interfaces for image collection and recommendation display are described.

[0017] Figure 14 A series of simplified interfaces for image collection using a proportional object graphical guide area are described.

[0018] Figures 15 to 16 A simplified interface for displaying exemplary consumption predictions is described.

[0019] Figures 17 to 19 A simplified interface for displaying an exemplary purchase path is depicted.

[0020] Figure 20 A series of simplified interfaces are described for collecting various inputs from users and displaying recommendations.

[0021] Figure 21 This is a flowchart of an exemplary method for recommending pre-made disposable products to subjects. Detailed Implementation

[0022] This disclosure relates to systems and methods for recommending the size of disposable articles based on the determination of the physical attributes of the intended wearer through image processing. Various non-limiting embodiments of this disclosure will now be described to provide a general understanding of the functionality, design, and operational principles of the manufacturing systems and methods. One or more examples of these non-limiting embodiments are illustrated in the accompanying drawings. It will be understood by those skilled in the art that the systems and methods described herein and illustrated in the drawings are non-limiting exemplary embodiments, and that the scope of the various non-limiting embodiments of this disclosure is fully defined by the claims. Features described or illustrated in one non-limiting embodiment may be combined with features of other non-limiting embodiments. Such modifications and variations are intended to be included within the scope of this disclosure.

[0023] As used herein, the term "absorbent article" refers to a disposable device that is worn close to or adjacent to the wearer's body to absorb and contain various excretions from the body, such as baby diapers, children's diapers, adult diapers, trouser diapers, training trousers, feminine hygiene products, and the like. Typically, these articles include a top sheet, a back sheet, an absorbent core, a collection system (which may be referred to as a fluid management system and may consist of one or more layers), and generally other components, wherein the absorbent core is typically at least partially located between the back sheet and the collection system or between the top sheet and the back sheet. The absorbent articles of this disclosure will be further illustrated in the following description and drawings in the form of adhesive diapers. However, this description should not be considered a limitation on the scope of the claims. Rather, this disclosure applies to any suitable form of absorbent article (e.g., training trousers, feminine hygiene products, adult incontinence products, etc.). For example, the systems and methods described herein are applicable to a range of different types of absorbent articles, such as disposable, semi-durable, single-use, reusable, multi-part, fabric, trouser, over-the-knee, or insert-type absorbent articles and products. The absorbent articles according to this disclosure can be prefabricated, such that they are manufactured to a predetermined size configured for wear by a wearer with certain physical properties. In some embodiments, the absorbent articles according to this disclosure are at least partially customizable, for example, certain aspects can be configured based on the physical properties of the intended wearer. By way of example, the leg loop size of the absorbent article to be worn by a particular wearer can be customized to provide a better fit for that particular wearer.

[0024] In some configurations, the systems and methods described herein may receive one or more digital images of a subject and determine the subject's physical attributes using various image processing techniques. The subject may be, for example, an infant, toddler, or other wearer of absorbent articles. Specific physical attributes determined by the systems and methods of this invention may vary based on specific implementations, but in some configurations, image analysis is performed to determine various fit parameters. Examples of fit parameters include the subject's estimated waist circumference, estimated thigh circumference, and estimated crotch measurement, such as from the navel to the lower back. Fit parameters may be applied to various size-setting models of absorbent articles to assess which one or more articles will fit the subject. An absorbent article recommendation can then be provided for the subject. This recommendation may identify, for example, any of the following: article size, article type, and article line. In some configurations, additional information about the subject beyond the images may be used to determine the recommendation. Non-limiting examples of additional information about the subject that may be utilized by the systems and methods described herein include, but are not limited to, the subject's age, gestational age, geographic location, and developmental milestones. Exemplary developmental milestones may include, but are not limited to, crawling, climbing on furniture, walking, initiation of toilet training, etc. Additionally or alternatively, user-provided size information regarding the subject, such as height, weight, and head circumference, can be used by the system when recommending absorbent products. Additionally or alternatively, fit assessments or performance feedback on currently used products, as well as other usage-based parameters such as the number of soiled diapers or wet diapers per day, can also be provided as input. Additionally or alternatively, absorbent product preferences, such as a preference for more natural products, products suitable for more active children, or highly absorbent or overnight products, can be provided by the user and taken into account.

[0025] Other user-provided information may include, for example, whether the wearer is wearing clothes or only diapers, or this information may be determined by, for example, an algorithm. In any of the above examples, data associated with a user profile or other user-provided information may be used to determine recommendations. Additionally or alternatively, data obtained from a public growth chart database may be used to determine recommendations. Furthermore, the type of user-provided information utilized by the system may depend on the type of absorbent product being recommended. By way of example, for recommendations of feminine hygiene products, user-provided information may include, but is not limited to, menstrual frequency, current product used, flow, dates of previous menstrual cycles, typical cycle length, absorbency of the product used, etc. Additionally or alternatively, growth data and charts may be used as the wearer's age and / or weight changes significantly. For incontinence products, user-provided information may include incontinence type, current product used, etc.

[0026] The systems and methods described herein can be used to generate recommendations for a wide variety of absorbent articles, including, for example, products for feminine hygiene or adult incontinence spaces. Therefore, while many of the figures and examples described herein include infants for illustrative purposes, this disclosure is not limited thereto. For example, for products for feminine hygiene or adult incontinence spaces, the user of the system can be a subject, and an image of the subject can be captured using a camera timer feature or a reflector. Images processed according to this disclosure may include the subject, such as a full-body image, or the subject's underwear placed flat on a flat surface. As described in more detail below, if the subject is standing and their entire body is present in the image and the person's height is provided to the system, the scale marker can be the person themselves. Alternatively, any other type of scale marker may be included in the image, such as a handheld scale marker flat against the body, a label on the body or clothing, or other suitable objects of known size. In some embodiments where the subject takes a reflected image in a reflector, the scale marker may be a telephone itself, as shown in the reflection.

[0027] See now Figure 1 The text depicts a user 122 interacting with an exemplary single-use product recommendation calculation system 100 according to a non-limiting embodiment. Figure 1 In this example, user 122 is seeking a recommendation for an absorbable article for subject 124. User 122 can position subject 124 within the field of view 130 of image capture device 114. In an illustrated embodiment, a scale object 128 is also included in the field of view 130 and captured in image 118. The size of scale object 128 or the size of printed markings on scale object 128 may be known to the disposable article recommendation calculation system 100. In this regard, scale object 128 may be, for example, a standard-sized piece of paper, credit card, playing card, banknote, coin, etc. In some embodiments, the packaging of the disposable article may be sold with scale object 128. Such scale object 128 may be printed or otherwise affixed to the packaging, or may be a separate object included within the packaging. In some embodiments, scale object 128 may be downloaded from a website and printed by user 122. However, as described in more detail below, in other specific embodiments, it is not necessary to include scale object 128 in image 118.

[0028] Once the subject 124 is properly positioned within the field of view 130, an image 118 representing the subject 126 and the scale object 128 can be acquired. In some embodiments, assistance or guidance may be provided to the user 122 to assist in the proper alignment and placement of the subject 124 within the field of view 130 of the image capture device 114. The image 118 may be a single image of the subject 124, multiple still images, or a film or video clip.

[0029] To ensure that image 118 can be used with the image processing techniques described herein, the disposable article recommendation calculation system 100 may execute various routines upon receiving image 118. For example, the disposable article recommendation calculation system 100 may perform perspective correction to account for any trapezoidal distortion that may exist in image 118. The amount of correction required to account for trapezoidal distortion may also be determined, and the image may be rejected if the correction amount exceeds certain preset boundaries.

[0030] The disposable product recommendation calculation system 100 can also execute various error-checking routines to ensure that the subject 124 is properly oriented and positioned within the field of view 130. Real-time feedback can be provided to the user regarding suggested adjustments (such as positional or environmental adjustments), which may need to be made before the process can proceed to the next step. For example, the subject 124 may need to lie supine with the image capture device 114 positioned substantially above the head, and the error-checking routines can confirm this orientation. Additionally, it may be necessary to position the scale object 128 such that all four corners or other attributes of the scale object 128 are visible and properly positioned within the field of view 130. The various error-checking routines can also check whether the subject's eyes are open and viewing the image capture device 114, and other postural or positional aspects of the subject (i.e., limbs that are sufficiently visible and properly oriented for analysis). The error-checking routines can confirm that the subject 128 is properly positioned within the frame, such that the subject 128 is sufficiently distanced from the edge of the frame and properly centered. Various routines can perform, for example, face tracking, pose tracking, object tracking, etc. Initial routines or subroutines can be executed to improve the overall processing speed of image analysis and subsequent recommendations. For example, by first running a routine to detect the face of subject 128, the system can then quickly estimate where the subject's body should be located within the frame. The disposable product recommendation calculation system 100 can also confirm that the lighting level is suitable for image processing, confirm that the subject is in focus, confirm the presence of scale objects, etc. If image 118 does not meet one or more of these checks or other types of preprocessing checks, user 122 can be requested to provide additional image 118 to correct the problem. For example, when subject 124 is positioned in field of view 130, some error checks can be performed locally or remotely in real time on a live preview, depending on the system configuration. In some embodiments, user 122 will not be allowed to collect images with image capture device 114 until certain criteria are met. For example, using live preview, user 122 can reposition subject 128 and / or scale object 128, for example, to meet error check routines or verification processes.

[0031] In some implementations, certain error checking routines or verification processes may be performed locally at the image capture device 114 (e.g., by...). Figure 2The remote computing device 238 associated with the image capture device 114 (shown shown) performs the process, and other processes can be performed by the disposable artifact recommendation computing system 100. For example, one or more routines that can be executed relatively quickly can be performed by the remote computing device. Such high-speed routines may be particularly helpful, for example, in conjunction with a live preview screen on the remote computing device, as described in more detail below. Other routines that may require a higher level of accuracy and may require more time and resources can be performed by the disposable artifact recommendation computing system 100. In addition, to improve processing speed or match the resolution of the images used to train various machine learning models, the image 118 may be downsampled for initial processing. For example, during initial processing, the corners (or other attributes) of the scaled object 128 can be detected using a low-resolution image. It should be understood that the various processes associated with the system can be optimally run at different resolutions, as is the case with various machine learning algorithms. Furthermore, some processes may be too slow to run on a full-resolution image. In some embodiments, after each algorithm has run at its optimal resolution, the data can be remapped to the original image resolution (or, for example, a single downsampled resolution). Various combinations of upsampling, downsampling, cropping, or using portions of the image can be used. Downsampling also reduces file size, which advantageously allows downsampled images to be transmitted faster between various devices compared to full-resolution images. Once a suitable image 118 has been collected and perspective corrected, the disposable article recommendation calculation system 100 can determine the scale of image 118. Although a variety of suitable techniques can be used to determine the scale of image 118, Figure 1 The scale of image 118 can be determined based on the known dimensions of scale object 128. For example, if it is known that scale object 128 is an 8.5-inch by 11-inch piece of paper, disposable product recommendation calculation system 100 can determine the overall scale of image 118. Therefore, the pixel-to-inch conversion or other suitable scale of image 118 can be determined by disposable product recommendation calculation system 100.

[0032] The disposable product recommendation calculation system 100 can perform various processes to identify the physical attributes of the subject 124, as shown in image 118. In some implementations, for example, joint locations such as ankles, hips, shoulders, etc., are identified. Using the scale of image 118, the disposable product recommendation calculation system 100 can then determine various dimensions of the physical attributes of the subject 124. As provided herein, any of a variety of techniques can be used to determine the various dimensions of the physical attributes, such as linear correlation models, machine learning algorithms, etc. Non-limiting examples of the dimensions that can be determined include, but are not limited to, hip width, waist width, torso length, distance between ears, distance between pupils, etc.

[0033] Once the physical properties of subject 124 are determined, multiple fit parameters can be generated. These fit parameters can be correlated with one or more parameters used to generate size-setting models for various absorbent articles. Figure 1 In this context, the fit parameters generated by the disposable product recommendation calculation system 100 include the estimated waist circumference, estimated thigh circumference, and estimated crotch measurement of subject 124. However, it should be understood that any of a variety of different types of fit parameters may be used.

[0034] Multiple size setting models 108 for prefabricated absorbent articles can be stored in a database 106. Generally, each prefabricated absorbent article may have an associated size setting model 108, which includes a range of fit parameters for that particular article. In an illustrated embodiment, for example, each size setting model 108 is a three-dimensional model that includes waist circumference ranges, thigh circumference ranges, and crotch measurement ranges associated with a particular absorbent article. In other embodiments, the size setting models may utilize different fit parameters. When determining the fit parameters of subject 124, the disposable article recommendation calculation system 100 may apply the fit parameters to the size setting models 108 to determine which prefabricated disposable article is appropriately sized for subject 124. In some cases, the fit parameters of subject 124 may fall within the boundaries of multiple different size setting models 108, each associated with a different size of absorbent article. In such cases, the disposable article recommendation calculation system 100 may make recommendations based on which absorbent article is likely to fit better. However, in some configurations, fit parameters or other physical attributes of the wearer can be used to manufacture custom absorbent articles in an on-demand manufacturing process. For example, a custom absorbent article may have a basic design while allowing certain aspects to be modified based on the subject's fit parameters and custom-configured to fit the intended subject. After manufacturing the custom absorbent article, it can be shipped directly to the subject's home or to a retail outlet, for example, near the subject.

[0035] See still Figure 1Recommendations 120 can be provided to user 122 via a suitable user interface 116. The user interface 116 can be any suitable device or method capable of conveying information to user 122, such as a display screen of a computing device, text messages, email messages, in-app messages, etc. The scope of recommendations 120 can vary. In some embodiments, recommendations 120 identify the size of absorbent articles suitable for subject 124, shown as product size recommendations 134. In some embodiments, recommendations 120 may include additional information, such as product type recommendations 132 and product lineup recommendations 136. This additional information can provide recommendations on whether subject 124 should wear, for example, adhesive diapers or training pants diapers. Furthermore, recommendations 120 may indicate the recommended number of products of a specific size to purchase (i.e., based on subject 124's expected growth). Recommendations 120 may also indicate the timeframe for size-up of recommended products. Depending on the type of product, recommendations 120 may indicate, for example, the size of disposable liners or disposable inserts. Recommendation 120 may also provide purchasing information (such as identifying online or brick-and-mortar retailers selling the recommended products) and / or information about the subscription purchasing program. Generally, the subscription purchasing program may routinely send multiple batches of recommended-size disposable products to user 122 over time. In some cases, the size of the batches of disposable products may automatically increase over time to account for the growth of subject 124.

[0036] The disposable article recommendation computing system 100 can be provided using any suitable processor-based device or system, such as a personal computer, mobile communication device, laptop computer, tablet computer, server, host computer, or a collection of multiple computers (e.g., a network). The disposable article recommendation computing system 100 may include one or more processors 104 and one or more computer memory units 102. For convenience, Figure 1 The diagram shows only one processor 104 and only one memory unit 102. Processor 104 executes software instructions stored on memory unit 102. Processor 104 may be implemented as an integrated circuit (IC) having one or more cores. The disposable article recommendation computing system 100 may also utilize one or more graphics processing units (GPUs) to assist various aspects of image processing to execute one or more machine learning models and / or convolutional neural network models suitable for visual imaging analysis. Memory unit 102 may include volatile and / or non-volatile memory units. Volatile memory units may include, for example, random access memory (RAM). Non-volatile memory units may include, for example, read-only memory (ROM) and mechanical non-volatile memory systems, such as, for example, hard disk drives, optical disk drives, etc. RAM and / or ROM memory units may be implemented as, for example, discrete memory ICs.

[0037] Memory unit 102 may store executable software and data for use by the disposable product recommendation calculation system 100 described herein. When the processor 104 of the disposable product recommendation calculation system 100 executes the software, it may cause the processor 104 to perform various operations of the disposable product recommendation calculation system 100, such as analyzing images, determining physical properties and fit parameters, comparing fit parameters with size setting models, and providing recommendations to users.

[0038] The data used by the disposable product recommendation calculation system 100 can come from various sources, such as database 106, which can be, for example, a computer database. Data stored in database 106 can be stored in non-volatile computer memory, such as hard disk drives, read-only memory (e.g., ROM ICs), or other types of non-volatile memory. In some embodiments, one or more databases 106 may be stored, for example, on a remote computer system. It should be understood that various other databases or other types of memory storage structures can be utilized or otherwise associated with the disposable product recommendation calculation system 100.

[0039] According to various implementation schemes, the disposable product recommendation calculation system 100 may include one or more computer servers, which may include one or more web servers, one or more application servers, and / or one or more other types of servers. For convenience, Figure 1 The present invention depicts only one web server 110 and one application server 112, but those skilled in the art will understand that the present disclosure is not limited thereto. Servers 110 and 112 may be composed of processors (e.g., CPUs), memory units (e.g., RAM, ROM), non-volatile storage systems (e.g., hard disk drive systems), and other components.

[0040] In some implementations, web server 110 may provide a graphical web user interface, such as user interface 116, through which individual users 122 interact with the disposable product recommendation calculation system 100. The graphical web user interface may also be referred to as a client portal, client interface, graphical client interface, etc. Web server 110 may accept requests from various entities, such as HTTP / HTTPS responses, HTTP / HTTPS requests, and optional data content, such as web pages (e.g., HTML documents) and linked objects (e.g., images, videos, etc.). Application server 112 may provide a user interface, such as interface 116, for users who do not use a web browser to communicate with the disposable product recommendation calculation system 100. Such users may have special software installed on their computing devices to allow them to communicate with application server 112 via a communication network, as described in more detail below. Furthermore, the user interface may include a connection to an automated or human agent via any suitable communication portal, such as chat, voice, or video, to guide the user through the recommendation calculation system.

[0041] Interface 116, such as that generated by disposable product recommendation calculation system 100, can be presented to user 122. User 122 may utilize, for example, a mobile phone, smartphone, tablet computer, laptop computer, desktop computer, kiosk, or other computing device capable of displaying interface 116. As provided above, interface 116 can identify one or more recommendations 120 based on the aforementioned image analysis and processing.

[0042] An alternative implementation scheme for the disposable product recommendation calculation system 200 is in Figure 2 As shown in the examples, and can be used in many ways with Figure 1 The disposable article recommendation calculation system 100 shown is similar to or the same as that shown. For example, the disposable article recommendation calculation system 200 may include a memory unit 202, a processor 204, and a database 206 for storing a size setting model 208. The disposable article recommendation calculation system 100 may include various software programs such as system programs and applications to provide computing power according to the described implementation. System programs may include, but are not limited to, an operating system (OS), device drivers, programming tools, utilities, software libraries, application programming interfaces (APIs), etc. Exemplary operating systems may include a native operating system as well as cloud-based computing services such as Microsoft Azure Server, Amazon Web Services (AWS), Alibaba Cloud, etc.

[0043] The disposable product recommendation calculation system 200 may also include various servers, such as a web server 210 and / or an application server 212. For example... Figure 2As shown, user 222 can interact with disposable product recommendation calculation system 200 via remote computing device 238 having camera 214 and user interface 216. Remote computing device 238 can be any type of computer device suitable for communication over a network, such as wearable computing device, mobile phone, tablet computer, device as a combination of handheld computer and mobile phone (sometimes called "smartphone"), personal computer (such as laptop computer, netbook computer, desktop computer, etc.), or any other suitable networked communication device, such as, for example, personal digital assistant (PDA), mobile gaming device, or media player.

[0044] In some implementations, the remote computing device 238 may provide a variety of applications to allow user 222 to use the disposable product recommendation computing system 200 to perform one or more specific tasks. Applications may include, but are not limited to, web browser applications (e.g., Internet Explorer, Mozilla, Firefox, Safari, Opera, Netscape Navigator), telephone applications (e.g., cellular, VoIP, PTT), networking applications, messaging applications (e.g., email, IM, SMS, MMS, BlackBerry Messenger, WeChat, Xiaohongshu, WhatsApp), etc. The remote computing device 238 may include various software programs such as system programs and applications to provide computing capabilities according to the described implementation. System programs may include, but are not limited to, operating systems (OS), device drivers, programming tools, utilities, software libraries, application programming interfaces (APIs), etc. Exemplary operating systems may include, but are not limited to, PALM OS, MICROSOFT OS, APPLE OS, ANDROID OS, UNIX OS, LINUX OS, SYMBIAN OS, EMBEDIX OS, a binary runtime environment for a wireless (BREW) OS, JavaOS, a wireless application protocol (WAP) OS, and cloud-based computing services such as MICROSOFT AZURE Server, AMAZON WEB Service (AWS), ALIBABA Cloud, and so on.

[0045] The remote computing device 238 may include various components for interacting with the disposable product recommendation computing system 200. The remote computing device 238 may include components used with one or more applications, such as a stylus, a touch-sensitive screen, buttons (e.g., input buttons, preset and programmable hotkeys), buttons (e.g., action buttons, multi-directional navigation buttons, preset and programmable shortcut buttons), switches, microphones, speakers, audio headsets, depth sensors, IR projectors, stereo cameras, gyroscopes, accelerometers, etc. The user 222 may interact with the disposable product recommendation computing system 200 via a variety of other electronic communication technologies, such as, but not limited to, HTTP requests, in-application messaging, and Short Message Service (SMS) messages. Electronic communications may be generated by a dedicated application executing on the remote computing device 238, or may be generated using one or more applications that are generally standardized to the remote computing device 238. Applications may include or be implemented as executable computer program instructions stored on a computer-readable storage medium such as volatile or non-volatile memory, which can be retrieved and executed by a processor to provide operation for the remote computing device 238. The memory may also store various databases and / or other types of data structures (e.g., arrays, files, tables, records) for storing data used by the processor and / or other components of the remote computing device 238.

[0046] Similar to Figure 1 The described process involves user 222 collecting an image 218 of subject 224 by placing subject 224 within the field of view 230 of camera 214. For example, in the context of a mobile phone, camera 214 may be a rear-facing camera that provides a preview of the image on user interface 216. As shown, a scale object 228 may be included in the image 218 for image processing by disposable product recommendation calculation system 200. In an illustrated embodiment, the image 218, including a representation of subject 226, is provided to disposable product recommendation calculation system 200 via electronic communication network 240. The communication network may include multiple computer and / or data networks (including the Internet, LAN, WAN, GPRS network, LTE network, etc.) and may include wired and / or wireless communication links. In some embodiments, a remote computing device 238 may perform various types of preprocessing, such as error checking routines, before providing the image 218 to disposable product recommendation calculation system 200. Furthermore, refer to Figures 3 to 4 below. Figure 6 In more detail, in some embodiments, the remote computing device 238 may perform image processing on the image 218 and provide the output of the image processing to the disposable product recommendation calculation system 200.

[0047] See still Figure 2Upon receiving image 218, the disposable product recommendation calculation system 200 can perform the following: Figure 1 The processing described herein is for generating a recommendation 220 for user 222. Recommendation 220 can then be sent via network 240 for display on user interface 216 of remote computing device 238. The scope, format, and content of recommendation 220 may vary. In an exemplary embodiment, recommendation 220 includes recommended product type 232, recommended product size 234, and recommended product lineup 236, but this disclosure is not limited thereto.

[0048] See now Figures 3A to 3B A side view of an exemplary scale object 328 and a subject 326, each positioned adjacent to an image capturing device 314 with a field of view 330, is shown. Figures 3A to 3B In both cases, the scale object 328 is shown placed on the same plane as the surface on which the subject 326 lies supine; this plane is referred to herein as the scale object focal plane 344. The scale object focal plane 344 may be substantially coplanar with, for example, a floor, bed, crib, or other surface on which the subject 326 is placed. Due to the volume of the subject 326, the hips of the subject 326 are not coplanar with the scale object focal plane 344. Instead, the hips of the subject 326 lie in a hip focal plane 342, which is substantially parallel to the scale object focal plane 344 but closer to the image capture device 314 than the scale object focal plane 344.

[0049] The determination of the scale of the image collected by the image capture device 314 based on the scale object 328 determines the scale of the object coplanar with the scale object focal plane 344. Therefore, based on the distance between the subject 326 and the image capture device 314, this scale may not provide sufficient accuracy to determine the scale of the hip focal plane 342. However, according to various embodiments of this disclosure, the distance between the scale object focal plane 344 and the hip focal plane 342 can be calculated, estimated, or measured, and this distance can then be used to determine the scale of the hip focal plane 342, thereby allowing for a more accurate determination of the size of the subject 326 through image analysis. However, it should be noted that, according to other embodiments, the sizing recommendation process described herein may be based on the scale of the scale object focal plane 344 without considering any possible scale differences between the scale object focal plane 344 and the focal planes where the subject's physical attributes may lie.

[0050] As the image capture device 314 is pulled further away from the subject 326, the difference between the scale of the hip focal plane 342 and the scaled object focal plane 344 will decrease. Figure 3A In the image capture device 314 is relatively close to the subject 336, and the distance between the image capture device 314 and the focal plane 344 of the scale object is shown as distance D. 1AThe distance between the image capturing device 314 and the hip focal plane 342 is shown as distance D. 2A The distance between the hip focal plane 342 and the scale object focal plane 344 is shown as distance D. 3A The distance D 3A equals D 1A Subtract D 2A .exist Figure 3B In this context, the image capturing device 314 is positioned further away, and the distance between the image capturing device 314 and the scale object focal plane 344 is shown as distance D. 1B The distance between the image capturing device 314 and the hip focal plane 342 is shown as distance D. 2B The distance between the hip focal plane 342 and the scale object focal plane 344 is shown as distance D. 3B The distance D 3B Equals D 1B Subtract D 2B As the image capture device 314 is pulled away from the subject 326 (i.e., from...), Figure 3A Move to the position shown Figure 3B (As shown in the image), distance D3 becomes a smaller fraction of distance D1, and the difference in scale between the hip focal plane 342 and the proportional object focal plane 344 decreases. Therefore, if the image capture device 314 is positioned at a sufficiently large distance from the subject 326, the difference in scale between the proportional object 328 and the subject 326 has virtually no impact on the size recommendation and can be considered negligible. However, in cases where the difference in scale is not negligible, the image processing described herein can take into account the distance between the hip focal plane 342 and the proportional object focal plane 344 and compensate for this difference, thereby preventing the calculated size of the subject 326 from being determined to be larger than its actual physical size.

[0051] Various suitable techniques can be used to compensate for the difference in scale between the hip focal plane 342 (as determined by the scale object 328) and the scale object focal plane 344. However, it should be noted that some embodiments of this disclosure do not attempt to compensate for any difference in scale between the hip focal plane 342 and the scale object focal plane 344, regardless of the magnitude of the difference. If compensation for the scale difference is desired, the difference in scale between the hip focal plane 342 and the scale object focal plane 344 is related to the node 332 (where the hip focal plane 342 and the scale object focal plane 344 are connected to the image capture device 314). Figure 3CThe distances between the nodes are linearly proportional. As understood in the art, a node is the point where all the light rays entering the lens of the image capture device 324 converge. Furthermore, the focal length provides the distance between the node and the image sensor of the image capture device 314. The focal length of the image capture device 314 can be provided as metadata in the captured image. Using the focal length of the image capture device 314, the projected size of the subject 326 (as if the projected size of the subject were coplanar with the proportional object focal plane 344), and the distance between the proportional object focal plane 344 and the hip focal plane 342, the scale of the hip focal plane 342 can be determined.

[0052] See now Figure 3C The diagram shows a cross-sectional end view of the torso of subject 326, with hip 348 schematically shown. Hip 348 is located in the hip focal plane 342. Distance D 1C The size of the image on the image capture device 314 and the focal length of the image capture device 314 (as provided in the image metadata) can be determined because the size of the scale object 328 is known (i.e., 8). 1 / 2 inches by 11 inches, or other suitable size). In some implementations, if the distance to D 1C If a certain threshold is exceeded, the size of the subject 326 can be determined without any adjustment to the distance between the proportional object focal plane 344 and the hip focal plane 342. However, in some embodiments, further processing may be performed to provide such adjustment in order to more accurately determine the various sizes of the subject 326. In one embodiment, the actual hip width (i.e., Figure 3C The size H in A The hip width H can be based on the subject's projection onto the proportional object focal plane 344, as collected by the image capture device 324. P pixel size and distance D 1C To derive, for example, the hip width H projected onto the proportional object focal plane 344 of the subject 326. P The distance (shown as distance D) of the hip focal plane 342 above the scale object focal plane 344 is determined using the hip plane constant. 3C In one exemplary implementation, the thickness T of subject 326 is considered to be the subject's hip size H. A Approximately 90%. Furthermore, in the side view, the subject's hip is considered to be located at the midpoint of the subject's height (i.e., 50% of thickness T). Therefore, the subject's hip can be located in a plane approximately 0.45 times the hip width above the focal plane 344 of the scale object, where the hip plane constant 0.45 is calculated as the product of 0.9 and 0.5. Therefore, the distance D... 3C It can be estimated as hip size H A0.45 times. Once the distance D is determined. 3C The proportion of the hip focal plane 342 can then be linearly extrapolated based on the proportion of the focal plane 344 determined by the proportion object 328. It should be understood that although a hip plane constant of 0.45 is provided herein, other hip plane constants may be used without departing from the scope of this disclosure.

[0053] Furthermore, depending on the specific implementation, other methods can be used to measure the distance between the hip focal plane 342 and the scale object focal plane 344. For example, the distance to the hip focal plane 342 and the scale object focal plane 344 can be directly measured by an instrument associated with the image capture device 314. Such distances can be measured or at least interpolated by stereophotometry, infrared triangulation, laser ranging, infrared time-of-flight, or combinations thereof. In some specific implementations, such as when the telecomputing device has multiple image capture devices 314, multiple images captured simultaneously at multiple locations can be analyzed. In any case, any of a variety of methods can be used according to the system and method described herein to accurately account for the vertical difference between the plane on which the scale object 328 is placed and the plane of the physical feature portion of the subject 326. Figures 4 to 7 Various exemplary operational arrangements of the single-use article recommendation calculation system according to this disclosure are schematically depicted. See first... Figure 4 It shows something similar to Figure 2 The described operational setup involves a remote computing device 438 using a camera 414 to collect an image 418. The image 418 is provided to a disposable product recommendation calculation system 400 via an electronic communication network 440. The disposable product recommendation calculation system 400 is configured to perform image processing 442 to determine fit parameters of the subject in the image 418. The disposable product recommendation calculation system 400 is further configured to perform product fit processing 444 to apply the fit parameters of the subject in the image 418 to a size setting model 408. After image processing 442 and product fit processing 444, the disposable product recommendation calculation system 400 can transmit a recommendation 420 for display on the user interface 416 of the remote computing device 438.

[0054] Figure 5An implementation scheme with an alternative operational arrangement is depicted. As shown, the remote computing device 538 includes a camera 514 and a user interface 516, similar to the previously described implementation. However, in this implementation, the size setting model 508 is stored by the remote computing device 538. Additionally, image processing 542 and product fit processing 544 are performed by the remote computing device 538. Thus, for example, the remote computing device 538 can generally provide the functionality of the disposable product recommendation calculation system 100. As shown, in some implementations, the remote computing device 538 can provide various data to the disposable product recommendation calculation system 500 via a network 540. In the illustrated implementation, performance data 546 is provided to the disposable product recommendation calculation system 500, and various updates 548 can be provided to the remote computing device 538. The performance data 546 can be collected from users of the remote computing device 538 and can be related to the quality of absorbent product recommendations, for example, based on product fit or product performance. Performance data 546 collected from multiple users can be used to change and update various fit parameters over time, such as using a self-learning model. These updated fit parameters can then be provided to a remote computing device 538 in an attempt to continuously improve product fit recommendations over time. Figure 6 Another exemplary alternative operational arrangement is described. In this embodiment, the telecomputing device 638 has a camera 614 and a user interface 616. The telecomputing device 638 is configured to perform image processing 642 on images collected by the camera 614. As a result of this image processing 642, fit parameters 650 can be determined and provided to a disposable product recommendation calculation system 600 via communication through a communication network 640. Upon receiving fit parameters 650, the disposable product recommendation calculation system 600 can perform product fit processing 644 to apply the received fit parameters 650 to a size setting model 608. The disposable product recommendation calculation system 600 can then provide a recommendation 620 to the telecomputing device 638 for display on the user interface 616. Therefore, Figure 6 An exemplary operational arrangement is described, in which processing steps are split between a remote computing device 638 and a disposable product recommendation calculation system 600.

[0055] Figure 7Another embodiment with an alternative operating arrangement is described, which splits the processing between a telecomputing device and a disposable product recommendation calculation system. In this exemplary arrangement, a size setting model 708 is stored by a telecomputing device 738. A camera 714 of the telecomputing device is used to collect images 718, which are provided to the disposable product recommendation calculation system 700 via a communication network 740. The disposable product recommendation calculation system 700 is configured to perform imaging processing 742 to determine fit parameters 750. The fit parameters 750 can then be transmitted to the telecomputing device 738 for product fit processing 744. Product fit processing 744 can apply the fit parameters 750 to the size setting model 708 and generate recommendations for display on a user interface 716.

[0056] As shown in Figure 3 to Figure 6 As shown, some processes can occur locally on a remote computing device, while others can occur at a disposable product recommendation computing system. Therefore, relatively fast algorithms that can be executed on a remote computing device can be separated from relatively slow algorithms that execute on a server. This method allows for real-time preview guidance for users, for example, because such routines supporting real-time preview guidance can be executed locally on the remote computing device. Therefore, regarding the identification of scale objects and the determination of image scale, a combination of processes can be used, including low-resolution object detection algorithms that first determine the region where the scale object is located in the image. For example, such processes can be executed locally on a remote computing device. Such processes can also include high-resolution object detection algorithms that attempt to identify the optimal search neighborhood of specific features of the scale object, such as corners, edges, printed marks, etc. High-resolution algorithms or processes can run on a disposable product recommendation computing system. These processes can also include various refinement algorithms such as edge detection algorithms to accurately locate the features of the scale object. These algorithms can be combined in various ways, including feeding portions of the image from one algorithm to the next (i.e., directional search), weighting the search parameters of another algorithm based on the input of one algorithm, or selecting the result of a single algorithm based on the confidence of that single algorithm in locating the feature of interest.

[0057] Therefore, in some implementations, a set of ultra-low resolution algorithms can run on a remote computing device. More specifically, these algorithms are fast enough to execute on a remote computing device while also providing sufficient guidance and / or error checking. However, these algorithms may not necessarily be accurate enough to determine the subject's body dimensions. The goal of these algorithms is to provide additional error checking while also guiding high-resolution algorithms. For example, a high-resolution algorithm executed by a disposable product recommendation computing system can precisely select points of interest in an image, where the search is guided by low-resolution results. In some cases, this high-resolution algorithm is one that is accurate enough to be used as the basis for a model.

[0058] For illustrative purposes only, the following provides exemplary interactions of various processes according to a non-limiting embodiment. First, a suitable programming function can be performed by a remote computing device to locate a scale object. In some embodiments, an open-source computer vision library such as OpenCV can be used for this process. This process can be used to guide a user to place the scale object in the appropriate position within a bounding box, perform error checking for the presence of the scale object, etc. This process can use simple object detection, such as placing a bounding box around the scale object, although the process is not necessarily designed to find edges or corners or perform image segmentation. Next, at a disposable item recommendation computing system, a first pass with a machine learning algorithm can confirm the presence of an unwrinkled white paper or other suitable scale object (i.e., error checking) and locate a search neighborhood for corners or other attributes, as possible. An edge detection algorithm can then be performed by the disposable item recommendation computing system within the corner search neighborhood to precisely select the corners or other attributes of the scale object. It should be noted that various edges appear throughout the image, which is why it is beneficial for the algorithm to focus on specific areas where scale objects appear. Once identified, these locations can be used to scale the image according to this disclosure.

[0059] In any case, by sharing various image processing algorithms between a local remote computing device and a disposable product recommendation computing system, the overall accuracy and speed of the size recommendation process can be optimized, while also allowing scalability across a large number of simultaneous users. See now. Figure 8The diagram schematically illustrates an exemplary process that can be performed by a disposable product recommendation calculation system 800. The disposable product recommendation calculation system 800 can receive an unprocessed image 818A, which includes a representation of a subject 826 and a scale object 828. During image processing 842, various error checks can be performed on the unprocessed image 818A to ensure the image is suitable for analysis. Image processing 842 can also correct any trapezoidal distortion effects, which are distortions caused by the relative angle between the image capture device and the subject. Any suitable method for trapezoidal distortion correction can be used, including using information collected by sensors associated with the camera (such as accelerometers, gyroscopes, etc.) to assist in correcting the camera angle. Image processing 842 can perform any other image corrections that may be necessary, such as corrections or adjustments to light, color, inherent camera parameters, lens distortion, or other distortions. Furthermore, the amount of correction required for the image can be quantified so that if corrections exceeding a threshold that would affect the accuracy of the recommendation are needed, a new image is requested.

[0060] Specifically, regarding the image processing routines performed on scale objects according to various implementation schemes, multiple error-checking routines can be executed to ensure that the scale objects included in the image are sufficient and usable by the system. For example, confidence levels regarding various aspects of scale object identification can be used. In some implementations, the confidence level of corner detection of paper scraps or paper edges is explored to determine whether the scale objects in the image are acceptable. Additionally or alternatively, various algorithms can be used, for example, to determine whether a suitable scale object exists and to search for other factors besides the edges or corners of the scale object. In one specific implementation, image analysis is performed to determine whether the scale object includes printing or lines in an attempt to determine whether the scale object is actually suitable for processing. Image analysis can also detect the presence of holes in the scale object (such as three-ring adhesive holes or spiral adhesive holes). Image analysis can also check, for example, whether corners may be invisible due to tearing, or look for evidence of folding or bending of the scale object. It can be determined whether the scale object is unusable and another image with a suitable scale object can be requested, or in some cases, images may not be allowed to be collected until the problem with the scale object is resolved. Additionally, the algorithm according to this disclosure can search for linear or otherwise conform the scaled object to a desired shape (e.g., a rectangle or circle) to determine if the scaled object has been folded or otherwise deformed. The algorithm can also search for texture to detect wrinkles on the surface of the scaled object. Based on the results of the algorithm related to the scaled object, the system can determine whether to continue processing the remaining image or reject the image and request a different image from the user. In some embodiments, the user can be notified of the reasoning for rejection (i.e., missing corners, detected wrinkles, incorrect aspect ratio, etc.). In addition to the error checking and verification routines associated with the scaled object, various similar routines can be performed by referring to the analysis of subjects. For example, in some embodiments, the confidence value for each joint location and / or the number of joint locations predicted for a single joint can be used to detect errors and determine whether the image is applicable. Therefore, according to the system and method described herein, multiple error checks can be performed at various points during processing to ensure image applicability.

[0061] After correcting for any trapezoidal distortion other than any other issues and satisfying any other error checks, the processed image 818B can be analyzed to determine the scale of the image. In some embodiments, the scale of the processed image 818B is determined using the detected scale attribute 852 of the scale object 828. For example, if the scale object 828 is a standard piece of paper measuring 8.5 inches by 11 inches, the disposable article recommendation calculation system 800 can identify the scale object 828 and then measure the corner-to-corner dimensions of the scale object 828 during imaging processing 842. The disposable article recommendation calculation system 800 can also confirm that the two corner-to-corner dimensions are similar, which confirms that the correction for any trapezoidal distortion effect has been successful. The disposable article recommendation calculation system 800 can then determine the scale of the processed image 818B based on the known corner-to-corner dimensions of the paper, which are 13.9 inches. In some implementations, analyzing the aspect ratio of the scale object 828 before and / or after correction, or similarly, analyzing any dimensions of the scale object (e.g., first side length, second side length, width, diagonal, etc.) before and / or after correction, can be used to detect images that are not suitable for processing the recommended scale. In some implementations, the unprocessed image 818A may include more than one scale object 828, such that one scale object in the image is used for perspective correction, and other scale objects in the processed image 818B can be used to confirm that the correct scale has been applied and perspective has been adequately removed. Furthermore, although... Figure 8 The use of conventional paper for scaling object 828 is depicted, but the invention is not limited thereto. Furthermore, other measurements of scaling object 828 can be used to determine the scaling ratio. For example, in some embodiments, scaling attribute 852 may be the measured top and bottom widths of scaling object 828, and the left and right heights of scaling object 828. The top and bottom widths of scaling object 828 can be averaged to determine the scaling ratio in the X direction, and the left and right heights of scaling object 828 can be averaged to determine the scaling ratio in the Y direction. Determining both the X-direction and Y-direction scaling ratios of the processed image 818B increases overall accuracy, especially when the pixels of the processed image 818B are not square, such as in the case of video images.

[0062] The processed image 818B also schematically illustrates exemplary physical attributes 854 of the subject 826 that can be detected during image processing 842. In the illustrated implementation, various joint positions and physical features (i.e., ear positions, eye positions, nose positions, etc.) are determined. This determination may be performed by a disposable product recommendation computing system 800, or it may be performed locally, remotely by a third-party computing system, or by any other suitable resource. In some specific implementations, machine learning-based models are used to identify joint positions or other types of physical features. An exemplary resource for determining joint positions in a subject image is provided by OpenPose, offered by Carnegie Mellon University, Pittsburgh, Pennsylvania. OpenPose is a real-time multi-user system for collaboratively detecting human keypoints, hand keypoints, facial keypoints, and foot keypoints on a single image. Other techniques for detecting the user's physical attributes 854 may include edge detection and object detection algorithms. As an example, or alternative to determining joint location, an algorithm can be used to identify the triangle formed by the nipples and navel of subject 826. Based on the dimensions of this triangle, as determined by the proportions of the image, a model can be applied to determine the appropriate size setting for subject 826.

[0063] Once physical attribute 854 has been identified, the disposable article recommendation calculation system 800 can determine various dimensions of the subject 826 based on proportions. While the determined dimensions may vary based on physical attribute 854, in some implementations, exemplary dimensions include torso measurements, distance between ears, shoulder width, and hip width.

[0064] During the product fit processing 844, the disposable product recommendation calculation system 800 can determine various fit parameters based on the dimensions associated with physical attribute 854. The specific fit parameters utilized by the disposable product recommendation calculation system 800 can then be selected to match the fit parameters of various size setting models 808. For example, size setting models 808 may be defined by certain fit parameters within an acceptable range, such as, but not limited to, waist circumference at the navel, crotch measurement from the navel to the back, and thigh circumference. Therefore, the disposable product recommendation calculation system 800 can estimate fit parameters based on the determined dimensions of physical attribute 854. In some embodiments, for example, a statistical model is used to correlate the various dimensions of physical attribute 854 with various fit parameters or directly with preferred diaper sizes. Furthermore, in some embodiments, in addition to the various dimensions of physical attribute 854 as determined by image analysis, other inputs to the statistical model may include gender and age, as well as other specific dimensions or information entered by the user, as described in more detail below.

[0065] See now Figure 9 An exemplary fit parameter 956 based on physical property 954 is shown. In the illustrated embodiment, fit parameter 956 includes waist circumference at the navel, crotch measurement from the navel to the back, and thigh circumference. Similar to Figure 8 The fit parameter 956 is based on the subject's physical attributes 954, shown as joint position, eye position, etc., and the proportion of the object 928. However, Figures 10 to 11 This demonstrates that other methods can be used to determine the aspect ratio of an image. See also Figure 10 An exemplary process for determining proportion and fit parameters is based on body part dimensions, as provided by the user of the disposable product recommendation calculation system. For example, in an illustrated embodiment, foot size 1054 is provided by the user to the disposable product recommendation calculation system. Foot size 1054 can be provided in any suitable format, such as shoe size or foot length. When the subject's foot is captured within the image at an appropriate angle, the disposable product recommendation calculation system can utilize the known dimensions of the subject's foot to determine the proportion of the image. Based on the subject's proportions and physical attributes, various fit parameters 1056 can be determined. Figure 11 Another configuration is depicted, in which the user provides their head circumference to a disposable product recommendation calculation system. Similar to... Figure 10Using the subject's known dimensions or parameters such as head width 1154 calculated from known head circumference, the disposable product recommendation calculation system can determine the image's proportions. The system can then determine fit parameters 1156. In other embodiments, one or more fit parameters, such as waist size or height, can be additionally or as an alternative provided by the user to scale the image proportionally. For example, regarding height, the subject's height in the image can be calculated from the sum of joint distances. Furthermore, interocular distance or eye diameter can be used to scale the image proportionally because these dimensions vary very little across the population and change only very slowly with age. For example, a newborn's eye diameter is 16 mm + / - 2 mm, and a 3-year-old's eye diameter is 19 mm + / - 2 mm. Therefore, upon receiving the subject's age, the disposable product recommendation calculation system can use an age-to-eye diameter curve to identify eye diameters within a few millimeters of the correct proportion.

[0066] Other techniques, such as photogrammetry, can also be used to determine the scale of an image. Two or more images of the subject can be taken from two or more known locations, where the size of objects within the photographs is calculated by tracking reference points. Alternatively, multiple lenses on a single device can capture images that can be used for the photogrammetric process. Another approach is to utilize a single camera that moves in space and measure the position of the camera's movement. Alternatively, point clouds or structured light can be used. In this method, a known pattern of bars or an array of points can be projected onto the target area / subject. The camera can then read the deformation of the projected light as it falls on different 3D objects. Using algorithms, the 3D shape and size of those objects can be calculated based on the measured deformation of the known light pattern. Structured light can be visible, IR, or other wavelengths, as long as the camera configured for this purpose can detect the deformed light pattern. Alternatively, a depth sensor can be used to calculate the distance to the object and the scale can be calculated based on the number of pixels occupied by a relatively flat object (such as a baby or part of a baby's body) in the image and using triangulation or trigonometric functions to calculate the scale. Alternatively, tilt sensors, position sensors, accelerometers, or other sensors from smartphones or other devices can be incorporated into the method to help calculate the scale in the acquired images or 3D scans.

[0067] See now Figure 12The diagram schematically depicts simplified size-setting models 1208 for sizes 1 to 6 of an exemplary product lineup for disposable articles. While each size-setting model in size-setting models 1208A-1208F is defined based on waist and crotch measurements, this disclosure is not limited thereto. For example, size-setting models 1208A-1208F may include additional dimensions (such as thigh circumference) or may be based on different sizes. In any case, according to this disclosure, a disposable article recommendation calculation system may apply fit parameters of a subject, such as those determined by image analysis, to size-setting model 1208 to determine which one or more sizes of disposable articles are suitable for the subject to wear.

[0068] Figure 12 Exemplary fit parameters for two different subjects (shown as subject 1260 and subject 1262) are illustrated graphically. Referring first to the fit parameters defined by subject 1260, the disposable product recommendation calculation system can determine that subject 1260 falls within size 1 of the disposable product size setting model 1208A and provide this recommendation to the user. However, the fit parameters defined by subject 1262 cause subject 1262 to fall within multiple size setting models (i.e., size 2 size setting model 1208B and size 3 size setting model 1208C). The disposable product recommendation calculation system can use various methods to determine which of these two sizes to recommend to the user. According to the illustrated embodiment, the disposable product recommendation calculation system determines the relative distance from the fit parameters defined by subject 1262 to each boundary of the involved size setting model. In the illustrated implementation, distances 1266a-d are distances to the boundary of size setting model 1208C (size 3), and distances 1264a-d are distances to the boundary of size setting model 1208B (size 2). More specifically, distances 1266a and 1266c are distances to the upper and lower boundaries of the waist fit parameter of size setting model 1208C (size 3). Distances 1266b and 1266d are distances to the upper and lower boundaries of the crotch fit parameter of size setting model 1208C (size 3). Distances 1264a and 1264c are distances to the upper and lower boundaries of the waist fit parameter of size setting model 1208B (size 2). Distances 1264b and 1264d are distances to the upper and lower boundaries of the crotch fit parameter of size setting model 1208B (size 2).

[0069] Once the distances 1266a-d and 1264a-d are determined, the disposable article recommendation calculation system can recommend a disposable article size based on the measured distances. In some implementations, for example, the disposable article recommendation calculation system can identify the minimum dimensions of all boundary dimensions 1266a-d and 1264a-d for each size setting model 1208B and 1208C. The disposable article recommendation calculation system can then compare these two minimum dimensions and recommend a size setting model with the largest of those dimensions.

[0070] Figures 13 to 20 A simplified exemplary user interface display on various computing devices according to a non-limiting embodiment is depicted. The user interface display may be, for example... Figure 1 Recommended calculation system for disposable products 100 or Figure 2 and Figures 4 to 6 Any component of remote computing devices 238, 438, 538, 638, 738. See first. Figure 13 A series of interfaces 1300A-1300B that can be presented on a computing device 1320 are shown. Interface 1300A shows an exemplary image preview pane 1302 during the image acquisition process. The image preview pane 1302 can be used to properly align the subject in the field of view. In some embodiments, the image preview pane 1302 may include a graphical guide area or other types of feedback to assist the user in alignment, such as augmented reality. As shown, an interactive element 1304 may be activated by the user to take a picture or a series of pictures of the subject. Images collected by the computing device 1320 may be processed according to this disclosure and may be presented to the user via interface 1300B. Interface 1300B may present a recommendation 1306 in any suitable format. It should be understood that recommendation 1306 may include various information associated with the recommendation, such as the type of recommended product, the recommended product lineup, etc. In some embodiments, interface 1300B may also include a fit measure 1308. The fit measure 1308 may indicate how the recommended disposable article is expected to fit the subject. The fit measure 1308 can be based on, for example, the subject's fit parameters and their relative position within a size-setting model of a recommended-size disposable item.

[0071] Figure 14Other exemplary simplified interfaces 1400 that can be presented on computing device 1420 by a disposable article recommendation calculation system are depicted. Interface 1400A shows an exemplary image preview pane 1402 during the image collection process. The image preview pane 1402 can be used to properly align the scale object 1428 in the field of view and guide the user to collect images at a sufficient distance from the subject 1426. In this exemplary embodiment, the image preview pane 1402 includes a scale object graphic guide area 1429 for assisting the user in the image collection process. As shown in interface 1400B, interactive elements 1404 can be presented to the user once proper alignment of the scale object 1428 and the scale object graphic guide area 1429 is detected. The user is allowed to collect images only after the scale object 1428 is properly positioned within the boundaries of the scale object graphic guide area 1429. Therefore, the scale object graphic guide area 1429 can provide real-time feedback to the user to assist the image collection process.

[0072] The use of the proportional object graphic guide area 1429 ensures that the subject 1426 is at a sufficient distance from the computing device 1420. By forcing the user to collect images from a specific distance, interpolation can be reduced or eliminated. Figures 3A to 3C The proportion of the subject 1426 is necessary. In addition, the proportion object graphic guide area 1429 can also ensure that the relative angle between the computing device 1420 and the proportion object 1428 is acceptable for processing, thereby avoiding the need for overcorrection of image trapezoidal distortion due to perspective effects.

[0073] The proportional object graphic guide area 1429 can also guide the user to place the proportional object 1428 in a specific orientation relative to the subject 1426. (Reference) Figure 14 The placement of the scale object graphic guide area 1429 in the image preview pane 1402 ensures that the scale object 1428 is positioned to the upper left of the subject 1426. Guiding the user to place the scale object 1428 in a specific location reduces the overall variability of the collected images. Reduced variability improves overall accuracy because the relative positioning of the scale object 1428 and the subject 1426 in the image can be selected to match the relative positioning of the images used to train the system and develop the model. Additionally or alternatively, graphic guide areas can be used to assist in the alignment and placement of the subject. Such graphic guide areas can instruct the user to place the subject within a specific orientation (i.e., head towards the top of the frame and legs towards the bottom of the frame), which can help reduce, for example, the variability of the collected images.

[0074] Figure 15Another exemplary simplified interface 1500, which can be presented on computing device 1520 by a disposable product recommendation calculation system, is depicted. Interface 1500 provides a disposable product consumption prediction 1510, as determined by the disposable product recommendation calculation system. The disposable product consumption prediction 1510 may include various information, such as the predicted consumption rate (i.e., the number of absorbent products used within a certain time period) and / or the amount of time until the wearer will need to move to a different size and / or product line. In an illustrated embodiment, for example, the disposable product consumption prediction 1510 includes a recommended size 1506, a time period prediction 1512, and a quantity prediction 1514 based on the predicted consumption rate. Thus, the disposable product consumption prediction 1510 informs the user that the subject is expected to wear size 2 disposable products for the next 22 days and will consume 65 products during that time period. The model used to determine such a disposable product consumption prediction 1510 may be based on any number of inputs, including the subject's physical attributes, age, sex, growth history, inferred Centers for Disease Control and Prevention (CDC) growth charts, etc. For example, some inputs may be determined based on image analysis, while others may be based on user-supplied information, such as information provided at the time of image submission or information previously submitted when creating a user profile. In some implementations, a series of images of the subject may be collected over time (i.e., more than 3 days), where the subject's growth pattern is determined based on the subject's growth image-to-image. Various techniques can be used to determine the predicted consumption rate. For example, users may input information about when they purchased absorbent products and the quantity they purchased. This information can be collected using any suitable technology, such as the user manually providing the information through an interface or scanning the UPC code on the absorbent product packaging. For example, providing this information can be incentivized by linking the scanning of the UPC code to a reward program. In some implementations, users provide information about the number of disposable products they change daily. In some implementations, statistical models of the number of absorbent products used by the wearer based on age in a day are utilized. Furthermore, while some consumption predictions are schematically shown as the number of absorbent products consumed, these consumption predictions may also be represented based on the number of absorbent product packages. Packaging configuration can be considered based on consumption forecasts expressed in terms of packaging consumption, as the number of absorbent articles contained in the packaging can vary based on the size of the absorbent articles, product lineup, etc.

[0075] Recommendations provided by the disposable product recommendation calculation system may also include value calculations for users, which combine various recommendation elements (such as the number of disposable products to be consumed, the number of trips to the store, and other consumption metrics) to provide users with the optimal overall value. Regarding automated shipments of products, recommendations may include shipment schedules for various products in the product lineup. The disposable product recommendation calculation system can be configured to receive feedback from users to provide information on how recommendations are received. This feedback can be used to improve or otherwise refine the particular recommendation and / or improve the quality of the overall model over time by collecting feedback across multiple users. Furthermore, based on disposable product consumption predictions, the disposable product recommendation calculation system may schedule notifications to users when it is time to purchase additional disposable products. Such notifications may be in any suitable format and may be scheduled via any suitable communication medium. In some implementations, notifications may be text messages, email messages, in-app messages, scheduled appointments, reminders, smart speaker notifications, pop-up notifications, geofence notifications (e.g., when physically near a store), or combinations thereof. In addition, a subscription purchase program can be offered to users, allowing disposable items to be routinely sent to them, with the recommended size of the disposable items automatically increasing over time. In some configurations, bulk shipments are provided, containing the predicted quantities of all sizes of disposable items that will be used by the wearer over time.

[0076] Figure 16 Another exemplary disposable product consumption forecast 1510 is depicted, which can be displayed on an interface 1500 of a computing device 1520. The disposable product consumption forecast 1510 includes a recommended size 1506, a time period forecast 1514, and a quantity forecast 1516. In this embodiment, the time period forecast 1514 is represented by a date, and the quantity forecast 1516 includes a usage rate. For example, the usage rate can be adjusted as an input such that the associated recommendation changes according to user input regarding the rate.

[0077] Figures 17 to 19 This describes an exemplary indication of a purchase path that can be provided to a user via an interface. The purchase path can be represented in any suitable format. See first. Figure 17 An exemplary interface 1500 of the computing device 1720 illustrates a first example of a recommended size 1706 and a purchase path 1708. In this embodiment, the purchase path 1708 is a retailer map that provides real-time location information based on GPS data provided by the computing device 1720. Therefore, the purchase path 1708 can guide a user to the retailer's aisle to purchase the disposable item of recommended size 1706, and in some embodiments, provides the user with additional information such as available quantity, pricing data, etc. Figure 18An exemplary interface 1800 of a computing device 1820 is depicted, illustrating another exemplary purchase path 1808 and a recommended size 1806. Purchase path 1808 may include one or more web-based links to purchase the recommended size 1806 of the disposable product via an online retailer or online marketplace forum. Figure 19 An exemplary interface 1900 of a computing device 1920 is depicted, illustrating another exemplary purchase path 1908 and a recommended size 1906. The purchase path 1908 in this embodiment may include a map including driving directions to guide the user to a retailer to purchase disposable items. As shown, additional purchase-related information, such as aisle location, available quantities, pricing data, etc., may be provided.

[0078] See now Figure 20 The diagram illustrates an exemplary simplified interface 2000A-C for a computing device 2020. Interface 2000A schematically depicts a collection of various inputs from a user that can be utilized by a disposable product recommendation computing system. For example, providing developmental markers 2002 can assist the disposable product recommendation computing system in recommending appropriate product lines. Exemplary developmental markers 2002 may include, but are not limited to, crawling, climbing on furniture, walking, starting toilet training, sleeping through the night, etc. Additionally or alternatively, user-supplied inputs 2004 may be provided to the disposable product recommendation computing system to help generate recommendations. Exemplary user-supplied inputs 2004 may include, for example, weight, length, head size, date of birth, gestational age at birth, etc. Additional inputs may include geographic location, as different regions have different expectations regarding the fit of disposable products. For example, geographic location may be determined based on the physical location of the user's computer device, or geographic location may be provided by the user as part of the registration process. One or more inputs may be visualized and tracked individually or in conjunction with population growth curves (such as a child's standard CDC growth curve). Interface 2000B schematically depicts a collection of images of the subject. Similar to... Figure 13 Interface 2000B may have an exemplary image preview pane 2006. The image preview pane 2006 can be used to properly align the subject within the field of view. Interactive element 2008 can be activated by the user to capture a single image or a series of images of the subject. Images collected by computing device 2020 can be processed according to this disclosure and presented to the user via interface 2000C. Interface 2000C can present recommendation 2010 in any suitable format. Recommendation 2010 may be based on both image analysis as described herein and additional information provided by the user via interface 2000A. It should be understood that recommendation 2010 may include recommended product type, recommended product lineup, etc. Exemplary interface 2000C also includes a fit measure 2012 to indicate how the recommended disposable article is expected to fit the subject.

[0079] Figure 21 An exemplary flowchart 2100 depicts a method for recommending pre-prepared disposable items to subjects. At 2102, the method includes storing a plurality of disposable item size setting models, which correspond to a plurality of corresponding pre-prepared disposable items available for purchase. The size setting models may be stored by a disposable item recommendation calculation system, such as... Figures 1 to 6 As shown. In this respect, the size setting model can be stored in a centralized storage library or locally stored on the end-user's computer device. At 2104, images collected by at least one camera are received. The images may include representations of the subject. The subject is a consumer of pre-made disposable products, such as an infant, toddler, or toddler. The received images may be, for example, still images, a collection of still images, or video.

[0080] At 2106, the scale of the image relating the size of the subject's representation in the image to the subject's physical dimensions is determined. This scale can be determined by any suitable technique, such as using a scale object in the image or inferring the scale based on known body part dimensions of the subject in the image (such as the subject's height, intrapupillary distance, or head circumference). At 2108, physical properties of the subject's representation in the image are determined. As described above, physical properties may include multiple joint positions of the subject, distances between detected aspects of the subject's representation in the image, and other quantifiable measurements of the subject's area or one aspect of the subject's representation in the image.

[0081] At 2110, multiple fit parameters for the subject are determined based on the image scale and the physical properties of the subject's representation. Fit parameters may include, for example, the subject's estimated waist circumference, estimated thigh circumference, and estimated crotch measurement. At 2112, the multiple fit parameters are applied to one or more disposable article sizing models among multiple disposable article sizing models. For example, it may be determined which sizing model captures each of the subject's estimated waist circumference, estimated thigh circumference, and estimated crotch measurement.

[0082] At 2114, based on the application of multiple fit parameters to one or more disposable product size setting models, a recommended pre-made disposable product is determined for the subject. This recommended pre-made disposable product is selected from a plurality of pre-made disposable products available for purchase. At 2116, the user is provided with instructions regarding the recommended pre-made disposable product for the subject.

[0083] combination

[0084] A. A computer-based method, the method comprising:

[0085] The disposable product recommendation calculation system stores multiple disposable product size setting models in a data repository, which correspond to multiple prefabricated disposable products available for purchase.

[0086] The disposable product recommendation calculation system receives images collected by at least one camera, wherein the images include representations of a subject who is a consumer of pre-made disposable products;

[0087] The scale of the image is determined by the disposable product recommendation calculation system, which makes the size of the representation of the subject in the image related to the physical size of the subject;

[0088] The physical properties of the subject's representation in the image are determined by the disposable product recommendation calculation system;

[0089] The disposable product recommendation calculation system determines multiple fit parameters of the subject based on the proportion of the image and the physical properties of the subject's representation;

[0090] The disposable product recommendation calculation system applies these multiple fit parameters to one or more of the multiple disposable product size setting models.

[0091] The recommended pre-made disposable product for the subject is determined by the disposable product recommendation calculation system based on the application of multiple fit parameters to one or more disposable product size setting models, wherein the recommended pre-made disposable product is selected from the multiple pre-made disposable products available for purchase; and

[0092] The single-use product recommendation calculation system provides an indication of the recommended pre-prepared single-use product for the subject.

[0093] B. According to the computer-based method described in paragraph A, wherein the recommended prefabricated disposable article for the subject includes any one of a recommended standard-size prefabricated disposable article, a recommended product series of prefabricated disposable articles, and a recommended style of prefabricated disposable article.

[0094] C. The computer-based method according to any one of paragraphs A to B, wherein the image includes a scale object that is adjacent to the representational location of the subject.

[0095] D. According to the computer-based method described in paragraph C, wherein the physical dimensions of the proportional object in the image are known for the disposable product recommendation calculation system.

[0096] E. The computer-based method according to any one of paragraphs A to D, wherein determining the scale of the image comprises: determining the scale in the X direction and the scale in the Y direction.

[0097] F. The computer-based method according to any one of paragraphs A to E, further comprising:

[0098] Before determining the multiple fit parameters, the image is processed by the disposable product recommendation calculation system to take into account the viewing angle between the subject and the at least one camera.

[0099] G. The computer-based method according to any one of paragraphs A to F, wherein these physical properties include multiple joint positions of the subject.

[0100] H. According to the computer-based method described in paragraph G, the positions of the subject's multiple joints are determined at least in part based on a machine learning model.

[0101] I. The computer-based method according to any one of paragraphs A to H, wherein the physical properties include the distance between the detected aspects of the representation of the subject in the image.

[0102] J. The computer-based method according to any one of paragraphs A to I, wherein the physical properties include any one of the length, width, area, and volume of an aspect of the representation of the subject in the image.

[0103] K. The computer-based method according to any one of paragraphs A to J, wherein the plurality of fit parameters are based on their correlation with one or more of the physical attributes of the subject.

[0104] L. The computer-based method according to any one of paragraphs A to K, wherein the physical properties include any one of head width, interocular distance, torso length, hip width, and shoulder width.

[0105] M. The computer-based method according to any one of paragraphs A to L, wherein the fit parameters include any one of the subject's estimated waist circumference, the subject's estimated thigh circumference, and the subject's estimated crotch measurement.

[0106] N. According to the computer-based method described in paragraph M, each of the plurality of disposable product size setting models includes a waist circumference range, a thigh circumference range, and a crotch measurement result range.

[0107] O. According to the computer-based method described in paragraph N, applying the plurality of fit parameters to one or more of the plurality of disposable product size setting models includes: determining for each corresponding disposable product size setting model: whether the estimated waist circumference is within the waist circumference range, whether the estimated thigh circumference is within the thigh circumference range, and whether the estimated crotch measurement result is within the crotch measurement result range.

[0108] P. According to the computer-based method described in paragraph O, the recommended pre-made disposable item for the subject is one of a plurality of different pre-made disposable items of a set size for the subject.

[0109] Q. The computer-based method according to any one of paragraphs A to P, further comprising:

[0110] The disposable product recommendation calculation system receives one or more user supply values.

[0111] R. According to the computer-based method described in paragraph Q, the user-provided values ​​include any one of the subject's age, weight, sex, height, gestational age at birth, and head circumference.

[0112] S. The computer-based method according to any one of paragraphs A to R, further comprising:

[0113] The consumption forecast for disposable products is determined by this disposable product recommendation calculation system; and

[0114] The consumption forecast for this disposable product is provided by the disposable product recommendation calculation system.

[0115] T. According to the computer-based method described in paragraph S, the disposable product consumption forecast is based on one or more of these user supply values.

[0116] U. According to the computer-based method described in paragraph T, the disposable product consumption forecast is based on one or more user supply values ​​and one or more physical attributes among the determined physical attributes.

[0117] V. The computer-based method according to any one of paragraphs R to U, wherein the disposable product consumption prediction includes an estimated number of these recommended pre-prepared disposable products to be used by the subject.

[0118] W. The computer-based method according to any one of paragraphs R to V, wherein the single-use product consumption forecast is associated with any one of the product, product size, and product lineup.

[0119] X. The computer-based method according to any one of paragraphs R to W, wherein the disposable product consumption prediction includes the estimated time during which the recommended pre-made disposable product will fit the subject.

[0120] Y. The computer-based method according to any one of paragraphs R to X, further comprising:

[0121] The disposable product recommendation calculation system sends purchase reminder notifications to remote computing devices based on the consumption forecast of the disposable products.

[0122] Z. The computer-based method according to any one of paragraphs R to Y, further comprising:

[0123] The disposable product recommendation calculation system registers users into a subscription purchase program for prefabricated disposable products.

[0124] AA. The computer-based method according to any one of paragraphs R to Z, further comprising:

[0125] After a certain period of time, the recommended size of these prefabricated disposable products will be automatically increased.

[0126] AB. The computer-based method according to any one of paragraphs A to AA, wherein the image is one or more still images of the subject collected by a mobile computing device.

[0127] AC. According to the computer-based method described in paragraph AB, the one or more still images of the subject are collected by a rear-facing camera of the mobile computing device.

[0128] AD. The computer-based method according to any one of paragraphs A to AC, the method further comprising:

[0129] The disposable product recommendation calculation system receives multiple images of subjects collected over a certain period of time, where the period is longer than three days; and

[0130] The disposable product recommendation calculation system predicts disposable product consumption based on the subject's growth pattern determined from the multiple images.

[0131] AE. According to the computer-based method described in paragraph AD, the method further includes:

[0132] The disposable product recommendation calculation system predicts the size change of the recommended prefabricated disposable products over time based on the growth pattern of the subject determined from the multiple images.

[0133] AF. The computer-based method according to any one of paragraphs A to AE, the method further comprising:

[0134] The disposable product recommendation calculation system provides at least one image collection guidance tool.

[0135] AG. According to the computer-based method described in paragraph AF, wherein the at least one image

[0136] The collection guidance tool includes a graphical overlay for presentation to the user during image collection. AH. According to the computer-based method described in paragraph AF, wherein the at least one image...

[0137] The collection guide tool includes a proportional object graphic guide area.

[0138] AI. A computer-based method according to any one of paragraphs A to AH, wherein processing the image to determine the proportions of the image includes: utilizing the known body part sizes of the subject.

[0139] AJ. According to the computer-based method described in paragraph AI, the known body part size of the subject is any one of the subject's height, the subject's intrapupillary distance, and the subject's head circumference.

[0140] AK. A computer-based method according to any one of paragraphs A to AJ, wherein processing the image to determine the proportion of the image comprises: utilizing multiple images of the subject during photogrammetry.

[0141] AL. A computer-based method according to any one of paragraphs A to AK, wherein processing the image to determine the scale of the image comprises: analyzing the deformation of the structured light projected onto the subject.

[0142] AM. The computer-based method according to any one of paragraphs A to A1, the method further comprising:

[0143] The subject's geographical location is determined by the single-use product recommendation calculation system, and the recommended pre-made single-use product for the subject is based on that geographical location.

[0144] AN. A computer-based method according to any one of paragraphs A to AM, wherein the image is a full-body top view of the subject, and wherein the subject is any one of an infant, toddler, or toddler.

[0145] AO. According to the computer-based method described in paragraph AN, the subject is lying supine in the image.

[0146] AP. According to the computer-based method described in paragraph AO, the method further includes:

[0147] The error checking module of the disposable product recommendation calculation system verifies one or more verification parameters of the image.

[0148] AQ. According to the computer-based method described in paragraph AP, verifying these verification parameters includes verifying any one of the following: the presence of an infant, the infant's posture, the presence of a scale object, the camera's orientation and viewing angle relative to the scale object, and the camera's orientation and viewing angle relative to the subject.

[0149] AR. According to the computer-based method described in paragraph AO, verifying these verification parameters includes verifying any of the physical properties of the scaled object.

[0150] AS. According to the computer-based method described in paragraph AR, the method further includes: downsampling the image before verifying the physical properties of the scaled object.

[0151] AT. The computer-based method according to any one of paragraphs A to AS, the method further comprising:

[0152] The disposable product recommendation calculation system provides the subject with instructions on the purchase path of the recommended pre-made disposable products.

[0153] AU. A computer-based method according to any one of paragraphs A to AT, wherein the prefabricated disposable article is either a disposable diaper or a disposable training trouser.

[0154] AV. A computer-based method according to any one of paragraphs A to A, wherein the image collected by the at least one camera is a single image.

[0155] AW. A computer-based system comprising:

[0156] A data repository containing multiple disposable product size setting models, each corresponding to a prefabricated disposable product of a specific size available for purchase; and

[0157] A disposable product recommendation calculation system includes a computer-readable medium storing computer-executable instructions configured to instruct one or more computers to process...

[0158] The device performs the following operations:

[0159] Receive images of the subject collected by a remote mobile computing device;

[0160] Determine the aspect ratio of the image;

[0161] Process the image to determine the physical properties of the object;

[0162] Based on the proportions of the image and these physical properties of the subject, several fit parameters of the subject were determined;

[0163] The fit parameters are compared with one or more disposable product size setting models from among the multiple disposable product size setting models.

[0164] Based on a comparison of these multiple fit parameters with one or more disposable product size setting models, the recommended pre-made disposable product for the subject is determined; and

[0165] Instructions for the recommended prefabricated disposable product will be sent to the remote mobile computing device.

[0166] AX. According to the computer-based system described in paragraph AW, the recommended pre-made disposable article for the subject includes any one of the recommended standard-size pre-made disposable articles, the recommended product series of pre-made disposable articles, and the recommended style of pre-made disposable articles.

[0167] AY. A computer-based system according to any one of paragraphs AW to AX, wherein,

[0168] The image includes a scale object that is adjacent to the representation location of the subject. AZ. According to the computer-based system described in paragraph AY, the scale object in the image...

[0169] These physical dimensions of the example object are known for the recommended calculation system for this disposable product.

[0170] BA. According to the computer-based system described in paragraph AZ, the physical dimensions of the proportional object in the image known to the recommended calculation system for the disposable article include any one of corner-to-corner dimensions, height dimensions, width dimensions, and radius dimensions.

[0171] BB. A computer-based system according to any one of paragraphs AW to BA, wherein,

[0172] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0173] Before determining the multiple fit parameters, the image is processed to take into account the viewing angle between the subject and the at least one camera.

[0174] BC. A computer-based system according to any one of paragraphs AW to BB, wherein,

[0175] These physical properties include the subject's multiple joint positions.

[0176] BD. According to the computer-based system described in paragraph BC, the positions of the subject's multiple joints are determined at least in part based on a machine learning model.

[0177] BE. A computer-based system according to any one of paragraphs AW to BD, wherein,

[0178] These physical properties include the distance between the detected aspects of the subject's representation in the image.

[0179] BF. A computer-based system according to any one of paragraphs AW to BE, wherein,

[0180] These physical properties include any one of the circumference, area, and volume of one aspect of the representation of the subject in the image.

[0181] BG. A computer-based system according to any one of paragraphs AW to BF, wherein,

[0182] These multiple fit parameters are based on their correlation with one or more of the subject's physical attributes.

[0183] BH. A computer-based system according to any one of paragraphs AW to BG, wherein,

[0184] These physical properties include any one of the following: head width, interocular distance, torso length, hip width, and shoulder width.

[0185] BI. A computer-based system according to any one of paragraphs AW to BH, wherein,

[0186] These fit parameters include any one of the subject's estimated waist circumference, estimated thigh circumference, and estimated crotch measurement.

[0187] BJ. According to the computer-based system described in paragraph BI, each of the plurality of disposable product size setting models includes a waist circumference range, a thigh circumference range, and a crotch measurement result range.

[0188] BK. According to the computer-based system described in paragraph BJ, the comparison of the plurality of fit parameters with one or more of the plurality of disposable product size setting models includes: determining for each corresponding disposable product size setting model: whether the estimated waist circumference is within the waist circumference range, whether the estimated thigh circumference is within the thigh circumference range, and whether the estimated crotch measurement result is within the crotch measurement result range.

[0189] BL. According to the computer-based system described in paragraph BK, the recommended pre-made disposable item for the subject is one of several different pre-made disposable items of a set size for the subject.

[0190] BM. A computer-based system according to any one of paragraphs AW to BL, wherein,

[0191] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0192] Receive one or more user-supplied values, such as those typed into the remote computing device. BN. According to paragraph BM, in the computer-based system, these user-supplied values...

[0193] This includes any one of the following: the subject's age, weight, sex, height, gestational age at birth, and head circumference.

[0194] BO. A computer-based system according to any one of paragraphs BM to BN, wherein,

[0195] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0196] Determine the consumption forecast for disposable products; and

[0197] Provide the remote mobile computing device with a consumption forecast of the disposable product.

[0198] BP. According to paragraph BO, the computer-based system wherein the disposable product consumption forecast is based on one or more of these user supply values.

[0199] BQ. According to the computer-based system described in paragraph BP, the disposable product consumption forecast is based on one or more user supply values ​​and one or more physical properties determined.

[0200] BR. A computer-based system according to any one of paragraphs BO to BQ, wherein,

[0201] The disposable product consumption forecast includes an estimated number of these recommended pre-made disposable products to be used by the subject.

[0202] BS. A computer-based system according to any one of paragraphs BO to BR, wherein,

[0203] This disposable product consumption forecast is associated with any of the following: product, product size, and product lineup.

[0204] BT. A computer-based system according to any one of paragraphs BO to BS, wherein the disposable product consumption prediction includes the estimated time that the recommended pre-made disposable product will fit the subject.

[0205] BU. A computer-based system according to any one of paragraphs BO to BT, wherein,

[0206] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0207] Purchase reminders are sent to the remote computing device based on the consumption forecast of disposable products.

[0208] BV. A computer-based system according to any one of paragraphs BO to BU, wherein...

[0209] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0210] Users are registered into a subscription-based purchasing program for pre-made disposable products. BW. A computer-based system according to any one of paragraphs BO to BV, wherein,

[0211] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0212] After a certain period of time, the recommended size of these prefabricated disposable products will be automatically increased.

[0213] BX. A computer-based system according to any one of paragraphs AW to BW, wherein,

[0214] The image is one or more still images of the subject collected by the remote mobile computing device.

[0215] BY. According to paragraph BX, the computer-based system wherein the one or more still images of the subject are collected by a rear-facing camera of the remotely mobile computing device. BZ. According to any one of paragraphs AW to BY, the computer-based system wherein...

[0216] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0217] Receive multiple images of the subject collected over a period of time, where the period is longer than three days; and

[0218] Based on the subject's growth pattern determined from these multiple images, a prediction of disposable product consumption is made.

[0219] CA. According to the computer-based system described in paragraph BZ, wherein these computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0220] Based on the growth pattern of the subject determined from these multiple images, a prediction of the size change of prefabricated disposable products over time is recommended.

[0221] CB. A computer-based system according to any one of paragraphs AW to CA, wherein,

[0222] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0223] Provide at least one image collection guide tool.

[0224] CC. According to paragraph CB, the computer-based system wherein at least one image

[0225] The collection guidance tool includes a graphical overlay for presentation to the user during image collection. CD. A computer-based system according to any one of paragraphs AW to CC, wherein,

[0226] Processing the image to determine its proportions includes utilizing the known body part sizes of the subject.

[0227] CE. According to the computer-based system described in paragraph CD, the known body part size of the subject is either the subject's height or the subject's head circumference.

[0228] CF. A computer-based system according to any one of paragraphs AW to CE, wherein,

[0229] Processing the image to determine its proportions involves using multiple images of the subject during photogrammetry.

[0230] CG. A computer-based system according to any one of paragraphs AW to CF, wherein,

[0231] Processing the image to determine its scale includes considering the vertical distance between the plane of the object and the plane containing the physical properties of the subject.

[0232] CH. A computer-based system according to any one of paragraphs AW to CG, wherein,

[0233] Processing the image to determine its scale includes analyzing the deformation of the structured light projected onto the subject.

[0234] CI. A computer-based system according to any one of paragraphs AW to CH, wherein,

[0235] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0236] The subject's geographic location is determined, and the recommended pre-made disposable product for the subject is based on that geographic location.

[0237] CJ. A computer-based system according to any one of paragraphs AW to CI, wherein,

[0238] The image is a full-body top view of the subject, who is either an infant, toddler, or a toddler.

[0239] CK. According to paragraph CJ, the computer-based system in which the subject is lying supine in the image.

[0240] CL. According to the computer-based system described in paragraph CK, wherein these computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0241] Verify one or more verification parameters for the image.

[0242] CM. According to the computer-based system described in paragraph CL, verifying these verification parameters includes: verifying the presence of an infant, the infant's posture, the presence of a scale object, the camera's orientation and viewing angle relative to the scale object, and any one of the camera's orientation and viewing angle relative to the subject.

[0243] CN. A computer-based system according to any one of paragraphs AW to CM, wherein,

[0244] These computer-executable instructions are further configured to instruct one or more computer processors to perform the following operations:

[0245] Instructions are provided on the purchase pathway for the recommended pre-made disposable products for this subject.

[0246] CO. A computer-based system according to any one of paragraphs AW to CN, wherein,

[0247] Pre-made disposable products are either disposable diapers or disposable training pants.

[0248] CP. A computer-based system according to any one of paragraphs AW to CO, wherein,

[0249] The image received from the remote mobile computing device is a single image.

[0250] CQ. A computer-based method comprising:

[0251] Store multiple disposable product size setting models, which correspond to multiple prefabricated disposable products available for purchase;

[0252] Receive images collected by at least one camera, wherein the images include representations of a subject who is a consumer of a pre-made disposable product;

[0253] Determine the scale of the image such that the size of the representation of the subject in the image is related to the physical size of the subject;

[0254] Image processing is used to determine the physical properties of the subject's representation in the image;

[0255] Based on the proportion of the image and the physical properties of the subject's representation, multiple fit parameters of the subject are determined;

[0256] The disposable product recommendation calculation system determines the recommended pre-made disposable product for the subject based on the application of multiple fit parameters to one or more disposable product size setting models, wherein the recommended pre-made disposable product is selected from the multiple pre-made disposable products available for purchase; and

[0257] and

[0258] The single-use product recommendation calculation system provides an indication of the recommended pre-prepared single-use product for the subject.

[0259] The dimensions and values ​​disclosed herein should not be construed as strictly limited to the precise numerical values ​​cited. Rather, unless otherwise specified, each such dimension is intended to represent the stated value and a range around which it is functionally equivalent. For example, a dimension disclosed as “40 mm” is intended to represent “approximately 40 mm”.

[0260] Unless expressly excluded or otherwise limited, every reference cited herein, including any cross-references or related patents or patent applications, and any patent application or patent claiming priority to or benefiting from it, is incorporated herein by reference in its entirety. Reference to any reference is not an endorsement of it as prior art to any disclosed or protected art herein, nor is it an endorsement of any such invention, either on its own or in combination with any one or more references. Furthermore, where any meaning or definition of a term in this invention conflicts with any meaning or definition of the same term in referenced documents, the meaning or definition given to that term in this invention shall prevail.

[0261] While specific embodiments of the invention have been illustrated and described by way of example, it will be apparent 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. Therefore, it is intended that all such changes and modifications falling within the scope of the invention be covered by the appended claims.

Claims

1. A computer-based method, the method comprising: The disposable product recommendation calculation system stores multiple disposable product size setting models in a data repository, and the multiple disposable product size setting models correspond to multiple prefabricated disposable products available for purchase. The disposable product size setting model includes the range of fit parameters for the disposable product; The disposable product recommendation calculation system receives images collected by at least one camera, wherein the images include representations of subjects who are consumers of pre-made disposable products; The proportion of the image is determined by the disposable product recommendation calculation system, the proportion being such that the size of the representation of the subject in the image is related to the physical size of the subject; The physical attributes of the subject represented in the image are determined by the disposable product recommendation calculation system; wherein the physical attributes include any one of head width, interocular distance, torso length, hip width, and shoulder width; The disposable product recommendation calculation system determines multiple fit parameters of the subject based on the proportion of the image and the physical attributes represented by the subject; wherein the fit parameters include any one of the subject's estimated waist circumference, the subject's estimated thigh circumference, and the subject's estimated crotch measurement. The disposable product recommendation calculation system applies the multiple fit parameters to one or more of the multiple disposable product size setting models. The disposable product recommendation calculation system determines the recommended pre-made disposable products for the subject based on the application of the plurality of fit parameters to one or more disposable product size setting models among the plurality of disposable product size setting models, wherein the recommended pre-made disposable products are selected from the plurality of pre-made disposable products available for purchase; and The disposable product recommendation calculation system provides instructions for the recommended pre-made disposable products for the subject.

2. The computer-based method according to claim 1, wherein, The recommended prefabricated disposable products for the subjects include any one of the following: prefabricated disposable products of the recommended standard size, prefabricated disposable products of the recommended product series, and prefabricated disposable products of the recommended style.

3. The computer-based method according to claim 1, wherein, The image includes a scale object that is adjacent to the representation location of the subject.

4. The computer-based method according to any one of claims 1-3, further comprising: Before determining the plurality of fit parameters, the image is processed by the disposable product recommendation calculation system to take into account the viewing angle between the subject and the at least one camera.

5. The computer-based method according to claim 1, wherein, Each of the multiple disposable product size setting models includes a waist circumference range, a thigh circumference range, and a crotch measurement result range.

6. The computer-based method according to claim 5, wherein, Applying the plurality of fit parameters to one or more of the plurality of disposable product size setting models includes: determining for each corresponding disposable product size setting model whether the estimated waist circumference is within the waist circumference range, whether the estimated thigh circumference is within the thigh circumference range, and whether the estimated crotch measurement result is within the crotch measurement result range.

7. The computer-based method according to claim 6, wherein, The recommended pre-made disposable item for the subject is one of several different pre-made disposable items that are determined to be the size specified for the subject.

8. The computer-based method according to claim 1, further comprising: The disposable product recommendation calculation system receives one or more user supply values.

9. The computer-based method according to claim 8, wherein, The user-supplied values ​​include any one of the subject's age, weight, gender, height, gestational age at birth, and head circumference.

10. The computer-based method according to claim 8, further comprising: The disposable product recommendation calculation system determines the consumption forecast for disposable products; and The consumption forecast for disposable products is provided by the disposable product recommendation calculation system.

11. The computer-based method according to claim 10, wherein, The disposable product consumption forecast is based on one or more user supply values ​​from the user supply values.

12. The computer-based method according to claim 11, wherein, The disposable product consumption forecast is based on one or more user supply values ​​and one or more physical attributes among the determined physical attributes.

13. The computer-based method according to claim 10, further comprising: The disposable product recommendation calculation system sends a purchase reminder notification to a remote computing device based on the disposable product consumption prediction.

Images