Wearable article system with tension sensor

Abstract

Aspects herein relate to a wearable article system and method for determining, among other things, a fit level associated with a wearable article based on sensor data received from a tensile sensor incorporated into the wearable article. Such wearable articles and associated functionality improve the prior art. In some aspects, the wearable article includes a plurality of electrically conductive wires or traces that act as tensile sensors, as they may change electrical resistance, for example when a stress or strain is applied. The traces may be conductive elements configured to convert the mechanical stimuli to one or more electrical signals. The wearable article is configured to conform to a body part.

Description

Technical Field

[0001] This article relates to systems and methods for determining fit degree, etc., associated with a wearable article based on sensor data received from a stretch sensor bonded to the wearable article. Background Technology

[0002] Some organizations design and manufacture clothing, such as footwear, specifically for particular individuals. This specific design and manufacturing depends on the individual's comfort while wearing the clothing, the size of the body parts that fit the garment, the individual's aesthetic preferences, or other attributes. However, existing technologies for measuring such attributes (such as clothing fit or footwear sizing) are static in design and function. Furthermore, these technologies require the use of bulky equipment, such as cameras, imagers, and other laboratory equipment. Attached Figure Description

[0003] This article describes the technology in detail with reference to the accompanying drawings, which are described below.

[0004] Figure 1A The high-level illustration depicts a sock structure with a stretch sensor, configured to convert mechanical stimuli into electrical signals and transmit corresponding sensor data to one or more networked devices, such as a smartwatch.

[0005] Figure 1B The illustration shows sensor data derived from the sock's structure and data based on the wearer's basketball activity, based on several aspects. Figure 1A Shoe recommendations for the wearer.

[0006] Figure 2 The figure illustrates a fit score presented to the wearer based on sensor data derived from the sock's structure, according to several factors.

[0007] Figure 3 A high-level illustration shows a side view of a sock structure that conforms to the wearer's lower limbs in several aspects.

[0008] Figure 4 The diagram at a high level shows a front view of a head covering that conforms to the wearer's head in several aspects.

[0009] Figure 5 The diagram illustrates the differences between various aspects. Figure 3 A closer view of part of the sock's structure.

[0010] Figure 6 The diagram illustrates the location of traces corresponding to the human foot, based on various factors.

[0011] Figure 7AThe diagram illustrates measurement or sensor data provided by each stitch of the sock structure, based on several aspects.

[0012] Figure 7B The diagram illustrates the basis of several aspects. Figure 5 A three-dimensional model of a human foot based on sensor data from sensor A.

[0013] Figure 8 The illustrations show different sizes and patterns of socks from various perspectives.

[0014] Figure 9A The illustration shows the sock structure relative to the shoe when the heel touches the ground, along with the corresponding capacitive sensor values.

[0015] Figure 9B The diagram illustrates the differences between various aspects. Figure 9A The sock structure relative to the shoe when the heel is off the ground and the corresponding capacitive sensor value.

[0016] Figure 10 This is a schematic diagram illustrating how a neural network generates scores indicating fit, comfort, and / or shoe recommendations based on several aspects.

[0017] Figure 11 These are screenshots of example user interfaces based on some aspects.

[0018] Figure 12 This is a flowchart illustrating an example process for determining and transmitting stretch sensor data, visualizations, and / or scores, based on several aspects.

[0019] Figure 13 It is a flowchart of an example process for causing the presentation of display elements or fractions based on one or more streams of data from a near real-time stretch sensor, according to some aspects.

[0020] Figure 14 It is a flowchart of an example process for determining fit or other properties associated with wearable products based on certain aspects.

[0021] Figure 15 This is a flowchart illustrating an example process for transmitting tensile sensor data representing electrical signals to a network device for further processing, based on several aspects.

[0022] Figure 16 This is a flowchart illustrating an example process for determining the resistance value of each trace based on voltage, according to several aspects.

[0023] Figure 17 This is a flowchart illustrating an example method for manufacturing wearable products based on several aspects.

[0024] Figure 18 This is a block diagram illustrating an example computational environment used to determine the fit or other properties associated with wearable products based on several aspects.

[0025] Figure 19 It is a timing diagram illustrating wearable products, remote devices, and user devices that perform different functions based on various aspects.

[0026] Figure 20 It is a timing diagram illustrating wearable products and remote devices that perform different functions based on some aspects.

[0027] Figure 21 It is a timing diagram illustrating wearable products and user devices that perform different functions based on several aspects.

[0028] Figure 22 This is a block diagram of any wearable electronic device described herein, based on some aspects.

[0029] Figure 23 It is a block diagram based on some aspects of computing devices. Detailed Implementation

[0030] Overview

[0031] Existing solutions require individuals (e.g., high-profile athletes) to travel to a laboratory containing bulky equipment (e.g., cameras and imagers) for footwear sizing or measuring other properties. Alternatively, some solutions require moving such bulky equipment to the individual's location. Both processes are not only costly and time-consuming, but the technologies used in these solutions are static in design and function. For example, some surface imaging systems include a stereo head (for stereoscopic vision) containing multiple cameras and projectors. Such cameras are used to capture images of the human body from different perspectives. Projectors are used to project random speckle patterns onto the body to create an artificial texture for surface reconstruction of the entire body. However, using this technology requires cumbersome setup and configuration (e.g., installing and wiring complex stereo cameras and projectors). Furthermore, these and other technologies (e.g., imagers) only capture a surface-level reconstruction of the body, without indicating, for example, the internal granular-level deformation characteristics of clothing parts based on human movement, such as stretching, compression, pressure, torsion, bending, shearing, or other internal forces, which could indicate comfort levels or fit, etc.

[0032] At a higher level, aspects of this paper relate to a wearable article system and method for determining fit, etc., associated with the wearable article based on sensor data received from a stretch sensor bonded to the wearable article. Such functionality and wearable articles improve upon the aforementioned prior art and other technologies.

[0033] In some aspects, wearable articles (e.g., sock constructions) include multiple conductive wires or traces that act as tensile sensors (e.g., capacitive, resistive, and piezoresistive sensors) because they can change resistance, for example, when stress or strain is applied. A “trace” is any suitable signal carrier and conductive element configured to convert mechanical stimuli (e.g., stress, strain, or deformation) into one or more electrical signals (e.g., resistance value, dielectric value, etc.). The wearable article is configured to conform to a body part (e.g., foot, head, hand, torso).

[0034] In some aspects, a processor (e.g., a microprocessor or microcontroller) is communicatively coupled to a stretch sensor. In some aspects, the processor is configured to perform various operations. For example, the processor may receive first sensor data via the stretch sensor at a first time. The first sensor data indicates a first sensor value (e.g., an ohmic value X) for each trace. The wearable article is in a first position at the first time (e.g., indicating a wearer's heel-to-ground gait). In some aspects, second sensor data is received via the stretch sensor at a second time after the first time. The second sensor data indicates a second sensor value (e.g., an ohmic value Y) for each trace. The wearable article is in a second position at the second time (e.g., indicating a wearer's heel-off gait).

[0035] Based at least in part on the data from the first and second sensors, various aspects can subsequently determine various pieces of information. For example, some aspects determine the degree of fit associated with the wearable article. In an illustrative example, the wearable article may be a sock structure configured to be worn on a person's foot, and the sock structure is configured to be placed within an internal space volume within a shoe. Aspects can determine whether the person's foot fits the shoe based on the deformation characteristics of the corresponding portion of the trace detected by a capacitive sensor (e.g., via a propagating electric field and detecting changes in an oscillator) and another sensor (e.g., a resistive sensor).

[0036] In another example, based on first and second sensor data, aspects determine one or more locations along a trace where the sensor data threshold has been exceeded. For example, each trace may be a long, thin conductor including an external electrode sheath along its length to sense mechanical stimulation and provide a corresponding sensor signal along its length. Each trace may be close together and arranged in a “grid” or mesh configuration, such that they intersect, are perpendicular to each other, or otherwise overlap. In this way, a particular aspect receives granular location information and internal deformation or other mechanical properties, such as the precise location within the trace experiencing resistance exceeding a threshold. This indicates the displacement or other deformation characteristics of the trace or a portion of the trace. The aspects capture this information near real-time as the wearer moves their body parts. In yet another example, some aspects detect the size or dimension of a body part (e.g., the foot) based on first and / or second sensor data.

[0037] Based at least in part on this determination (e.g., the determination of fit), some aspects cause one or more user elements to be presented at the user device. For example, some aspects generate a heatmap that includes a digital model of a body part during a time series corresponding to a first time and a second time. In some aspects, the heatmap also includes elements on the digital model indicating locations where traces have exceeded a sensor data threshold (e.g., “hot spots”). For example, this captures a near real-time indication of which parts of the shoe and / or foot experience pressure points exceeding a threshold during a particular video or time series. In yet another example, aspects may cause one or more user interface elements to be presented indicating the size or dimension of a body part (e.g., the foot).

[0038] In each aspect, the presented elements may additionally or alternatively include any other suitable type of information, such as recommendations for one or more shoe designs or shoe selections for the user based on capacitive and resistive sensor detections. To provide these and other elements, specific aspects map (e.g., via data structures or machine learning models) each sensor data value to one or more characteristics, such as shoe design recommendations, comfort, or the type of force (e.g., torsion, flexing, compression, etc.) experienced by the mesh structure. In response, some aspects provide indications of such characteristics. For example, some aspects cause specific areas of a shoe or wearable to be presented at the user interface that may be uncomfortable for the user based on pressure exceeding a pressure threshold at various traces.

[0039] Example of wearable products

[0040] Now refer to the attached diagram, Figure 1AAt a high level, a sock structure 107 with stretch sensors is illustrated according to some aspects. The stretch sensors are configured to convert mechanical stimuli into electrical signals and then transmit corresponding sensor data to one or more networked devices, such as a smartwatch 105. When the wearer 103 participates in basketball activities, each trace in the sock structure 107 (representing a stretch sensor) converts mechanical stimuli (e.g., stress levels due to movement of the wearer 103's foot) into one or more electrical signals (e.g., resistance values). For example, a trace at the bottom heel portion of the sock structure 107 can serve as a capacitor sensor that detects its distance from the upper surface of the corresponding inner heel portion of the shoe 109 by emitting an electric field from its sensing end (e.g., its electrodes). The electric field disruption characteristics of the trace can then be converted into distance. Such sensor readings indicate the degree of fit between each portion of the inner portion of the shoe 109 and the corresponding area of ​​the sock structure 107. In response, the sock structure 107 transmits sensor data (e.g., via a network communication interface) to one or more network devices, such as smartwatch 105 and / or other network devices (e.g., servers, cloud nodes, etc.).

[0041] Figure 1B The illustration shows data based on sensor data derived from sock structure 107 and basketball activity based on wearer 103, based on several aspects. Figure 1A For wearers of size 103, shoe recommendation number 111 is recommended. Figure 1B The diagram illustrates a point in time after which wearer 103 participated. Figure 1A The basketball activity shown. Responding to network devices from, for example... Figure 1A The sock structure 107 described herein receives sensor data, and the network device determines one or more visualizations and / or scores, as described in more detail herein. For example, a server may generate a low fit score via a neural network based on capacitor sensor values ​​corresponding to some portions of the sock structure 107 exceeding a threshold, indicating that the shoe 109 does not fit the wearer 103's foot properly. In response, such a network device may send a shoe recommendation 107 to a smartwatch 105, stating, "We recommend shoe X based on your sock sensor data for better comfort and fit during basketball." It should be understood that the smartwatch 105 can be any other alternative user device as described herein, such as a smartphone, smart glasses (AR glasses), a television, etc. It should also be understood that the activity can be an alternative to basketball or any suitable activity other than basketball, such as running, tennis, football, rugby, etc.

[0042] Figure 2 The figure illustrates a fit score 211 for wearer 203 based on sensor data derived from sock structure 207, according to several aspects. Figure 2The illustration also depicts a wearer 203 trying on a pair of shoes at a retailer. After the wearer 203 has placed their foot and the corresponding sock structure 207 into the spatial volume representing the interior portion of the shoe 209, each trace in the sock structure 207 converts mechanical stimulation into one or more electrical signals. For example, each trace of the sock structure 207 can act as a resistive sensor, converting the displacement or force experienced into a change in resistance. In response, the sock structure 207 transmits sensor data to one or more networked devices, such as a smartphone 205 and / or other networked devices (e.g., servers, cloud nodes, etc.).

[0043] Continue to refer to Figure 2 In response to receiving sensor data from sock structure 207, the network device determines one or more visualizations and / or scores, such as a fit score. For example, a server may generate a low fit score via a neural network, indicating that shoe 209 does not fit the wearer's foot properly, based on resistance values ​​from one or more traces of sock structure 207 exceeding a threshold. In response, such a network device may send the fit score to smartphone 205, which displays a "Your sock sensor data indicates that this shoe has a fit score X". In response to receiving an instruction from the user that button 211-1 has been selected ("Click here for more details"), any other suitable information may be displayed, such as visualizations (e.g., a heatmap of pressure points on the foot based on sensor data), actual resistance sensor values, a model of the foot, and / or recommended shoes, as described in more detail below. It should be understood that smartphone 205 may be any other alternative user device as described herein, such as a smartwatch, smart glasses (AR glasses), a television, etc.

[0044] Figure 3 A high-level illustration shows a side view of a sock structure 300 conforming to the wearer's lower limbs 302 (including the feet) according to various aspects. In some aspects, the sock structure 300 respectively represents... Figure 1A and Figure 2 The sock structure 300 includes a mesh structure 304 that engages with an outer fabric layer 302 (e.g., via stitches of the mesh structure 304 inserted into the outer fabric layer 302). The mesh structure 304 includes multiple individual stitches, such as horizontal stitches 304-1, illustrated by separate lines. As described in more detail below, the sock structure 300 can be used to determine shoe-related fit, size, or other information.

[0045] Figure 4A front view of a head cover 400 conforming to the wearer's head 402 is illustrated at a high level. The head cover 400 includes a mesh structure 404 that engages with an outer fabric layer 402 (e.g., via stitches of the mesh structure 404 inserted into the outer fabric layer 402). The mesh structure 404 includes individual stitches, such as horizontal stitches 404-1, illustrated by lines. As described in more detail below, the head cover 400 can be used to determine fit, size, or other information related to sports helmets, hats, or other headwear.

[0046] although Figure 3 and Figure 4 The wearable article is described in light of the sock construction and head covering; however, it should be understood that the wearable article can be any suitable wearable article, such as gloves, footwear (e.g., socks or shoes), any suitable garment (e.g., bras, shirts, headbands, armbands, underwear, trousers, etc.) or gloves. Therefore, for example, mesh construction 404 or any other trace configuration described herein can be incorporated into any suitable wearable article.

[0047] In some respects, footwear includes a sole structure attached to the upper. Footwear (or any footwear) described herein may include running shoes, baseball shoes, basketball shoes, skateboarding shoes, cycling shoes, American football shoes, tennis shoes, soccer shoes, training shoes, walking shoes, hiking shoes, etc. The concepts described herein can also be applied to other types of footwear considered non-athletic, such as dress shoes, loafers, sandals, and work boots. As used herein, footwear can be divided into different general areas. The forefoot area generally includes the portion of the footwear corresponding to the toe and the joints connecting the metatarsals and phalanges. The midfoot area generally includes the portions of the footwear corresponding to the arch and instep areas of the foot. The heel area generally corresponds to the posterior portion of the foot, including the calcaneus. Footwear described herein may include a lateral side (i.e., the surface facing away from the other foot) corresponding to the lateral region or lateral portion of the foot and a medial side (i.e., the surface facing the other foot) corresponding to the medial region of the foot. The different areas and sides described above are intended to represent general areas of footwear to facilitate the discussion below, and are not intended to define precise areas. Different zones and sides can be used as a whole in footwear products, in shoe uppers, and in shoe sole structures.

[0048] Figure 5 The diagram illustrates the various aspects. Figure 3This is an internal view of a portion 502 of the sock structure 300. In various respects, this internal view represents features that are not visible or beneath the outer fabric layer 302, except for the mesh structure 300, which is visible and attached to the outer fabric layer 302. Portion 502 includes a base layer 506 (e.g., a stretchable fabric), a set of vertical stitches 304-1, 304-2, 304-3, and 304-1, a non-conductive layer 504 (e.g., thermoplastic polyurethane (TPU)), and a set of horizontal stitches 304-5, 304-6, 304-7, and 304-8. A "vertical stitch" is a stitch oriented vertically or longitudinally. A "horizontal stitch" is a stitch oriented horizontally or laterally. Figure 5 As shown, the groups of vertical and horizontal traces are perpendicular to each other, so that they form a grid or "grid" pattern.

[0049] The “grid” pattern is practical because it is ideal for use with specific sensors, such as resistive and capacitive sensors, as described in more detail below. When a portion of the grid pattern (or a trace within the grid pattern) is subjected to stress, strain, or force exceeding a threshold, that portion undergoes deformation, resulting in a discernible change in its electrical properties (e.g., resistance) at that particular location. This allows for granular detection of portions of the wearable article undergoing deformation characteristics exceeding a threshold (e.g., corresponding to the metatarsal region). It should be understood that while grid structure 300 illustrates a grid pattern, other suitable patterns exist, such as serpentine, triangular, diamond, or mesh-based patterns. In this way, traces can be positioned and attached to the fabric in any suitable orientation. Regarding the “serpentine” pattern, each trace is arranged along a wavy (sine) line that crosses or passes through the fabric.

[0050] In some respects, base 506 is any suitable stretchable fabric or stretching material that can be stretched beyond a threshold. As used herein, the term "stretching material" refers to a textile or material formed using elastomer yarns. Elastomer yarns typically provide greater than about 200% of their maximum stretch under load before returning to their unstretched state upon removal of the load, and some elastomer yarns provide about 400% of their maximum stretch. Examples of elastomer yarn types include SPANDEX®, Lycra, rubber, etc. Furthermore, examples of stretching materials or textiles can include stretch woven materials, stretch knitted materials, stretch nonwoven materials, etc.

[0051] In some respects, other layers of the wearable article 300 (or any other wearable article described herein), such as non-conductive layer 504, are non-stretchable materials. As used herein, the term "non-stretchable material" refers to a textile or material (e.g., cotton, silk, polyester, conventional denim, and / or other non-elastic polymers) formed using non-elastomeric yarns that are typically stretched to no more than a threshold amount. In other words, a non-stretchable material has a lower tensile strength than a stretchable material. A "non-conductive" layer refers to any layer that cannot or is not typically used as a conductor for carrying electrical signals. For example, a non-conductive layer may include glass, rubber, ceramics, porcelain, plastic, or any fabric. This contrasts with "conductive" layers, which typically include metals (e.g., copper wire) or graphite. As described herein, a trace is an example of a conductive layer or element.

[0052] In some respects, base layer 506 is woven using a "dog-bone" weave (also known as an I-weave or H-weave). In other words, two or more sets of different yarns or threads can be interwoven (e.g., at right angles) to form a fabric or cloth, such as base layer 506. In other respects, base layer may comprise different sets of yarns or threads that are knitted, bonded, nonwoven, or sewn together.

[0053] In some aspects, each trace (such as trace 304-1) has a thickness of approximately 10 micrometers (µm) (e.g., ±5% of 10 µm). In some aspects, each trace has a recommended minimum width of 2 mm (±5% of 2 mm). The length of the trace can be any suitable length corresponding to the length of a particular wearable article. In various aspects, one or more traces extend in three dimensions around the entire wearable article, enabling the detection of a three-dimensional model of a body part, as described in more detail below. For example, in some aspects, the trace may encircle the entire width of the metatarsal region corresponding to the bottom, sides, and top of the foot.

[0054] In some aspects, wearable articles such as sock structure 300 are designed and manufactured in multiple layers. For example, in some aspects, the first or bottom layer is a base layer 506. A second layer on top of the first layer includes vertical traces 304-1 to 304-4. A third layer on top of the second layer includes a non-conductive layer 504. And a fourth layer on top of the third layer includes horizontal traces 304-5 to 304-8. Examples of the manufacture of wearable articles are described in more detail below. In some aspects, the non-conductive layer 504 is combined with the outer fabric layer 302 of FIG. 1 or Figure 4 The outer fabric layer 402 is the same as or represents the outer fabric layer 302 in Figure 1 or Figure 4 The outer fabric layer 402 is such that the non-conductive layer 504 is the outermost layer or visible to the wearer. In other respects, there is another "outer layer" of a fifth layer disposed above the fourth layer of horizontal traces 304-5 to 304-8, which represents the outermost layer or the layer visible to the wearer.

[0055] Figure 6 The illustration shows a set of traces located at a position corresponding to a human foot 602, according to some aspects. The traces are attached to wearable articles (e.g., woven into wearable articles), but in… Figure 6 The diagram is shown in the middle to illustrate the trace associated with the human foot 602. Therefore, in various aspects, the trace is as follows: Figure 6 The locations shown are simply integrated into wearable products, such as... Figure 3 In the sock structure 300, to identify foot-related measurements, such as foot size or any other suitable real-time characteristics, the various aspects use six marker patterns from the trace set – 604, 606, 608, 610, 612, and 614. This allows the various aspects to reconstruct a three-dimensional model of the foot 602 using the associated measurements, as described in more detail below.

[0056] As shown by vertical traces 604, these traces cover (e.g., are disposed thereon) the length of the foot 602 (or stocking structure) from the calcaneal region to the phalanges. Any reference to the foot 602 may be replaced by the term "stocking structure". Horizontal traces 606 cover the width of the foot 602 in the distal metatarsal region. Grid-patterned traces 608 cover the width of the foot 602 in the arch or proximal metatarsal and tarsal (cubic, cuneiform, navicular) region. Horizontal traces 610 cover the width of the foot 602 at the heel or calcaneal region. Inclined traces 612 cover the region from the talus or distal tibia across the ankle or distal fibula region, all the way to the calcaneal region of the foot 602. Horizontal traces 614 cover the distal metatarsal region or metatarsophalangeal joint region, such as the metatarsofibular and metatarsotibial regions of the foot 602.

[0057] Figure 7AFigure 700 illustrates measurement or sensor data provided by each trace of a sock structure according to several aspects. In each aspect, to derive sensor data, the tension sensors are first calibrated. For this purpose, some aspects utilize a shoe last (a solid form around which a shoe is molded). For step 1, a sock structure (e.g., 300) is placed on a shoe last just large enough to fill the sock structure while having minimal or no stretch to serve as a baseline. While each sensing trace is on the shoe last, an impedance value R1 from each sensing trace is measured and stored. The second step is to measure the stretch as the sock structure is worn by a human wearer. In each aspect, the tension sensors have varying impedance (or resistance) as they are stretched or otherwise physically stimulated. The more they are stretched, the higher the impedance. The wearer then puts on the sock structure. The processor then applies an electrical signal of source voltage V1 in parallel to each trace at a first terminal, and then each trace outputs a voltage V2 at a second terminal, which can be interpreted or measured by the processor. Each aspect uses a multiplexer (or "MUX") to reduce the pin count required to measure the impedance of all traces, as described in more detail below. The aspects can then use Ohm's Law to determine the resistance of each trace:

[0058] (V1-V2) = IR

[0059] Where I = current and R = resistance. V1, V2 and I are known, so R ("R2") can be derived for each trace.

[0060] In some aspects, the processor applies an electrical signal V1, and the trace outputs its voltage V2 in a continuous loop to provide near real-time data (e.g., the probability of shoe fit or comfort) based on the wearer's dynamic movements, as described in more detail below. In some aspects, the R1 reading from the last indicates the sock structure at a near real-time initial position based on the wearer's movements. For example, certain aspects derive the baseline from the wearer's first initial (or latest) position, rather than from the last. In these aspects, the R1 value represents only the resistance value from the trace, which corresponds to the previous position of the sock structure based on the wearer's real-time movements.

[0061] Figure 7B The diagram illustrates the basis of various aspects. Figure 7A Figure 700 shows a 3D model of a human foot (702) based on sensor data. Specific aspects are described above regarding... Figure 7A The sensor data described is used as input to generate a 3D model 702 of the foot. To do this, the next step is to form a profile in several aspects. Since R1 is known from the shoe last and R2 is known from the user's foot, changes in resistance are found in specific aspects:

[0062] △R = R2-R1

[0063] Because the tensile-impedance properties of the material are now known, a particular aspect is able to generate distance measurements from ΔR. The aspects then combine all this information into a data structure matrix, which in turn leads to the generation of a contour model of the foot (i.e., a 3D model 702). In other words, to generate the 3D model 702, the particular aspect takes as input the ratio of changes in physical stimuli (e.g., stress, strain, deformation) to corresponding changes in electrical signals (e.g., resistance, capacitance, etc.) for each trace to generate distance measurements. For example, the particular aspect uses the tensile-impedance properties of each trace to create distance measurements based on changes in resistance (e.g., from V1 to V2). In the particular aspect, this data is combined into a data structure, such as a matrix, to generate a 3D model 702 of the foot at its latest position. In the various aspects, this 3D model 702 represents a single instance or frame of a continuous video sequence, allowing multiple frames to be stitched together to form a video sequence. For example, in some aspects, a model reflecting R1 is generated, and then a model 702 representing R2 is generated, which can then be stitched together to generate near-real-time models of the foot for different time series over a period of time.

[0064] Figure 8 The illustrations show different sizes and patterns of socks from various perspectives. Figure 8 The diagram also illustrates that the stretch sensor can surround the entire spatial volume (representing the groove into which the foot enters) in a three-dimensional manner. Specifically, for example, the sock structure 802 and the corresponding trace surround the groove 802-1, such that the trace and the sock structure 802 can wrap around each part of the corresponding foot, as shown in the top, side, and front views of the sock structure 802. Figure 8 The top, side, and front views also illustrate the sock structure 804 for size 2. Figure 8 The top, side, and front views also illustrate the sock structure 806 for size 3.

[0065] Figure 9A The illustration shows the sock structure 904 relative to the shoe 906 when the heel touches the ground, and the corresponding capacitive sensor values. In some respects, the sock structure 904 represents the sock structure 300 of Figure 1. Figure 1A Sock structure 107 and / or Figure 2The sock structure 207. As described herein, in some aspects, one or more stretch sensors in the sock structure 904 include one or more capacitive sensors. Each capacitive sensor embedded in the sock structure 904 detects one or more portions of the interior of the shoe 906 without physical contact with this interior of the shoe 906. To detect one or more portions of the interior of the shoe 906, the capacitive sensor emits an electric field from a sensing end (e.g., a dielectric plate) of the sensor. Any portion of the interior of the shoe 906 that disrupts this electric field is detected by the capacitive sensor. In other words, when a portion of the shoe 906 (such as the inner heel portion) enters within a threshold distance of the sensing end or otherwise interrupts the electric field, this changes the capacitance of the sensor's oscillator by the electric field entering the sensing end.

[0066] In an illustrative example, the traces may be elongated structures (e.g., conductive wires) and include a core and electrodes on the core to cover the entire length of the trace. These electrodes may correspond to the sensing end of a capacitive sensor. Thus, for example, when traces 904-1 and 904-2 of the sock structure 904 emit an electric field (e.g., in response to the transmission of an electrical signal through these traces in the Y direction in the X direction), both traces detect the internal portion 906-1 of the shoe 906 (e.g., corresponding to the upper surface of the heel area). However, both traces 904-1 and 904-2, as well as various other traces, can similarly detect the internal portion of the shoe 906 along their entire length.

[0067] In some respects, capacitor sensors measure changes in capacitance and translate these changes into distance or position measurements to generate a model of the foot and / or shoe. For example, trace 904-1 can detect the distance or position from its sensing end (e.g., its electrodes) to the upper surface of the inner portion 906-1 of the shoe 906 by translating its electric field disruption characteristics into distance or position. In these respects, the position or distance of an object from the trace (such as portion 906-1) is proportional to the amount of change in the electric field of the capacitor sensor.

[0068] Capacitive sensors measure the capacitance change of a sensing device caused by an external mechanical stimulus. In some aspects, the capacitance of the sensing device is defined as C = εrεoA / d, where εr is the relative permittivity, εo is the vacuum permittivity, A is the effective area of ​​the electrodes (e.g., the outer conductor from which current flows or leaves), and d is the electrode spacing. Therefore, a change in one or more parameters—permittivity, spacing, or effective area—causes a change in the capacitance of the trace, and the magnitude of the mechanical stimulus that causes the parameter change can then be quantified. In some aspects, capacitive sensors comprise two electrode layers and a dielectric layer, where the electrodes require suitable conductivity. In some aspects, the electrodes can be made of materials such as conductive fabrics, metal wires, carbon materials, etc. Although each electrode is typically conductive, the capacitive response is independent of the change in resistance of the electrodes during exposure to mechanical stimuli. Meanwhile, the material used as the dielectric layer typically has a large dielectric constant to reduce leakage current. Commonly used dielectric materials are elastic polymers, fabric gaskets, ionomers, etc. Some aspects use silver-plated composite fibers as electrodes and high-dielectric-constant ionomer films as the dielectric material. In some respects, the composition and film thickness of the ion gel are designed to maximize the change in the contact area between the electrode and the ion gel under external force, which in turn optimizes the sensing performance of the capacitor sensor.

[0069] Continue to refer to Figure 9A At the initial moment, the wearer's lower limbs 902 are in a specific gait phase, such as heel strike. Therefore, this heel strike causes the tracks of the sock structure 904 to experience specific physical stimuli (e.g., stress, strain, or deformation). For example, in the corresponding... Figure 9A The electric field emitted from the first ends (near the heel) of traces 904-1 and 904-2 can indicate whether a portion 906-1 of shoe 906 is adjacent to the trace at its first end, or at a specific close distance from traces 904-1 and 904-2. Furthermore, the electric field emitted from other traces (such as those near the toe area of ​​the trace) can indicate that the corresponding toe portion of shoe 906 is further away from the toe trace relative to the first ends of traces 904-1 and 904-2 of the contact portion 906-1. Therefore, a similar electric field can be generated. Figure 9A A model or diagram indicating the position of each part of the sock structure 904 relative to each corresponding part of the internal part of the shoe 904. Specifically, the model or diagram may illustrate that part 906-1 of the internal part of the shoe 906 is adjacent to or close to corresponding areas of traces 904-1 and 904-2, and other internal parts of the shoe 906 near the toe area are relatively further away from the corresponding traces near the toe area. By detecting changes in capacitance, a capacitive sensor can detect the pressure presented on the corresponding trace segment and the position of the shoe 906 relative to the corresponding trace.

[0070] In some aspects, additional or alternative stretch sensors can be used to generate [the corresponding data]. Figure 9A The same graph is used to make various determinations (e.g., shoe fit). For example, some sensors may include resistive sensors, piezoresistive sensors, etc. These sensors directly convert the mechanical stimuli experienced by the trace (e.g., stress, strain, deformation, or pressure) into corresponding electrical signal sensor values. In other words, the experienced mechanical stimulus is proportional to the electrical signal sensor value.

[0071] In some respects, resistive sensors use piezoresistive materials to convert mechanical stimuli (such as displacement or force) into changes in resistance. Since the resistance of a conductive material is defined as R = ρL / S, a mechanical stimulus will cause a change in the resistivity (ρ), length (L), and / or cross-sectional area (S) of the piezoresistive material, resulting in a change in resistance. The sensing response of a resistive sensor depends on the interaction of: (1) the inherent change in resistance of the sensing element in response to the mechanical stimulus; (2) the geometric changes of the wearable article; and (3) changes in the trace set (e.g., a grid structure). Based on regression curves, the mechanical stimuli and their magnitude can be determined.

[0072] In some aspects, resistive sensors include a flexible substrate and a sensing material. In some aspects, the flexible substrate possesses properties such as elasticity, good flexibility, and long-term stability. These properties can provide an electrical signal carrier for the sensing material and provide piezoresistive properties for the sensing material and subsequent fabric. They can also reduce stress concentration in the sensor when subjected to mechanical stimulation. Example substrates may include silk, cotton, polydimethylsiloxane (PDMS), polyurethane (PU), etc. In some aspects, the sensing element has carbon materials, metallic materials, conductive polymers, etc. In some aspects, the sensing end is fabricated by coating, depositing, winding, or electroplating a functional conductive layer onto fibers, yarns, or fabrics, and they can also be fabricated by wet spinning or 3D printing processes. In some aspects, the resistive trace includes a fiber core electrode wrapped and wound with piezoresistive elastic nanofibers. The yarn can be woven into fabrics (e.g., a base layer 506 or a non-conductive layer 504) to enable multimodal sensing of various mechanical stimuli. The resistive trace can also be designed and fabricated by methods such as coating, deposition, inkjet printing, screen printing, etc. Among these methods, directly coating the sensing end onto ordinary fabric is the simplest and easiest way to achieve large-scale deployment.

[0073] In some applications, piezoelectric sensors are made of flexible materials exhibiting the piezoelectric effect, operating by converting mechanical stimuli into voltage signals. The piezoelectric constant of the piezoelectric material determines the sensor's performance in converting mechanical energy into electrical energy. In some applications, piezoelectric materials include composite materials, polymers, ceramics, and single crystals.

[0074] Piezoelectric traces can generate an internal voltage when subjected to external pressure, allowing them to be self-powered while simultaneously sensing pressure. Furthermore, these sensors typically offer advantages such as fast response times and high sensitivity, making them highly practical for wearable devices. In some cases, piezoelectric traces consist of three layers: a polyvinylidene fluoride (PVDF) film, top and bottom electrode layers of a conductive rGO-PET fabric with self-oriented ZnO nanorods. When subjected to external force, the piezoelectric structure (e.g., a lattice structure) deforms, resulting in a potential difference between the two electrode layers; therefore, the magnitude of the external force can be determined by detecting the voltage change.

[0075] Figure 9B The diagram illustrates the differences between various aspects. Figure 9A The sock structure 904 relative to the shoe 906 when the heel is off the ground, and the corresponding capacitive sensor value. In relation to... Figure 9A At the second moment following the first moment, the wearer's lower limbs 902 are in a specific gait phase – the "heel off the ground" phase, meaning the heel is now off the ground (as opposed to the first moment). Figure 9A (The opposite of heel contact with the ground in the middle). Therefore, this heel lift causes the traces of the sock structure 904 to experience specific physical stimuli (e.g., stress, strain, or deformation). For example, in the corresponding Figure 9B At that time, the electric field emitted from the first ends (near the heel portion) of traces 904-1 and 904-2 can indicate that portion 906-1 of shoe 906 is one inch away from the first ends of traces 904-1 and 904-2. Furthermore, the electric field emitted from other traces (such as those near the toe area of ​​the traces) can indicate that the corresponding toe portion of shoe 906 is closer to or adjacent to the toe trace relative to the first ends of traces 904-1 and 904-2 of contact portion 906-1. Therefore, a similar effect can be generated. Figure 9B A model or map indicating the position of each part of the sock structure 904 relative to each corresponding part of the internal portion of the shoe 906. By detecting changes in capacitance, a capacitive sensor can detect the pressure presented on the corresponding trace segment and the position of the shoe 706 relative to the corresponding trace.

[0076] In response to generating such graphs or models, similar to Figure 9A and Figure 9B Various aspects are then determined, such as the fit and comfort of the 906 shoe. In such aspects, for example, specific aspects can be provided to machine learning models. Figure 9A and Figure 9BThe graph (or corresponding data points, such as capacitance readings at each trace in each time period) is used as input. Additionally or alternatively, some aspects map each reading of each trace to a specific state or characteristic via a data structure. For example, a specific capacitance range can be mapped to a specific “fit” category (e.g., non-fit) in a lookup data structure. In these aspects, each sensor data reading has a predetermined state or category programmed to look up or other data structures. For example, a resistance value A can be mapped to fit fit B or comfort level C by using keywords (i.e., sensor value readings) in a lookup data structure to their corresponding values ​​– their specific states, such as fit or comfort.

[0077] In some respects, wearable footwear does not need to be like... Figure 9A and Figure 9B The shoe 906 is shown. Conversely, in some aspects, shoe 906 can alternatively be any suitable object near or associated with a wearable article. For example, in some aspects, 906 represents a helmet, and sock structure 904 represents... Figure 4 Wearable article 404. In this way, for example, parts of the helmet can be detected via electric field transmission from a capacitor sensor and corresponding interference from the internal parts of the helmet, as described above, to determine properties such as helmet fit. In some aspects, the interior of the shoe 906 additionally or alternatively includes sensors, such as capacitor sensors, rangefinders, miniature cameras, lidar, etc., fastened thereto, to more robustly generate a map of the internal parts of the shoe 906 in order to determine shoe fit, comfort, etc.

[0078] Example Model

[0079] Figure 10This is a schematic diagram illustrating how a neural network 1005 generates scores indicating fit, comfort, and shoe recommendations based on several aspects. In some aspects, the neural network 1005 represents or includes any suitable model functionality, such as supervised learning (e.g., using logistic regression, using backpropagation neural networks, using random forests, decision trees, etc.), unsupervised learning (e.g., using the Apriori algorithm, using K-means clustering), semi-supervised learning, reinforcement learning (e.g., using Q-learning algorithms, using temporal difference learning), regression algorithms (e.g., ordinary least squares, logistic regression, stepwise regression, multivariate adaptive regression splines, local estimation scatter plot smoothing, etc.), instance-based methods (e.g., k-nearest neighbors, learned vector quantization, self-organizing maps, etc.), regularization methods (e.g., ridge regression, minimum absolute shrinkage and selection operators, elastic networks, etc.), decision tree learning methods (e.g., classification and regression trees, iterative dichotomy 3, C4.5, chi-square automatic interaction detection, decision stumps, random forests, multivariate adaptive regression splines, gradient boosting machines, etc.), Bayesian methods (…). Examples of suitable machine learning algorithms include: Naive Bayes, average single dependency estimator, Bayesian belief network, kernel methods (e.g., support vector machine, radial basis function, linear discriminant analysis), clustering methods (e.g., k-means clustering, expectation maximization), association rule learning algorithms (e.g., Apriori algorithm, Eclat algorithm), artificial neural network models (e.g., perceptron method, backpropagation method, Hopfield network method, self-organizing map method, learned vector quantization method, etc.), deep learning algorithms (e.g., restricted Boltzmann machine, deep belief network method, convolutional network method, stacked autoencoder method, etc.), dimensionality reduction methods (e.g., principal component analysis, partial least squares regression, Sammon map, multidimensional scaling, projection tracking, etc.), ensemble methods (e.g., boosting, bootstrap aggregation, adaptive boosting, stacked generalization, gradient boosting machine method, random forest method, etc.), and / or any suitable form of machine learning algorithm.

[0080] Neural network 1005 is modeled as a data flow graph (DFG), where each node in the DFG (e.g., 1021) is an operator with one or more input and output tensors (such as 1020 and 1022). A "tensor" (e.g., a vector) is a data structure containing values ​​representing the inputs, outputs, and / or transformations processed by the operators. Each edge of the DFG depicts the correlation between operators. Neural network 1005 includes an input layer, an output layer, and one or more hidden layers. The input layer is the first layer of neural network 1005. The input layer receives preprocessed input data, represented by 1003 and 1015 (e.g., via preprocessing 1004 or 1016), such as one or more resistance values ​​(derived from resistance traces), one or more capacitance sensor values ​​(derived from capacitor sensors), and / or one or more piezoresistive values. The output layer is the last layer of neural network 1005. The output layer generates one or more inferences in the form of clustering, regression, classification, etc., which can be hard classification (e.g., shoe "fit") or soft probability (e.g., a 50% probability that the shoe fits), represented by predictions 1009 and 1007. The neural network 1005 can include any number of hidden layers. Hidden layers are intermediate layers in the neural network 1005 that perform various operations.

[0081] Figure 10 Each node in the network, such as node 1021, is associated with or includes one or more activation tensors, such as input tensor 1020, output tensor 1022, and / or intermediate tensors. As shown in the data flow from input tensor 1020 to output tensor 1022, an "activation tensor" is a tensor that serves as the input, intermediate, and / or output (e.g., modeled from left to right) of at least one neural network layer. This differs from weight tensors, such as 1024, where weight tensors are modeled as flowing upwards (not as actual inputs or outputs). In other words, activation tensors represent some form of the neural network inputs 1003 and 1015. For example, input tensor 1020 or node 1021 could represent, for a particular set of traces (e.g., ... Figure 6 The presence of specific sensor data values ​​within or outside the threshold of trace group 612 (or in a specific region of trace group) and / or the corresponding wearable article, while the weight tensor represents the weight value indicating the node activation / inhibition value.

[0082] Each node in network 1005 may also be associated with or include one or more weight tensors (e.g., 1024) that include weight values. In the context of machine learning, a “weight” can represent the importance or significance of a feature or feature value used for prediction. For example, each feature (e.g., resistance values ​​within a range at a specific foot location) can be associated with an integer or other real number, where the higher the real number, the more significant the feature is for its prediction. In one or more aspects, weights in a neural network represent the strength of the connection between nodes or neurons from one layer (input layer) to the next layer (hidden layer or output layer). A weight of 0 can mean that the input (e.g., input tensor 1020) will not change the output (e.g., output tensor 1022), while weights higher than 0 will change the output. The higher the input value or the closer the value is to 1, the more the output will change or increase. Similarly, negative weights can exist. Negative weights can proportionally decrease the value of the output. For example, the more the input value increases, the more the output value decreases. Negative weights can result in negative scores. For example, comfort can be highly correlated with the amount of pressure on the lateral metatarsal portion of the foot, and therefore this means that neural network layers or nodes on the lateral metatarsal portion and corresponding sensors can be given higher weights so that this data is activated or considered when making the final predicted score.

[0083] Each node in a Neural Network 1005 can additionally use activation and weight tensors to perform one or more functions, such as activation functions, matrix multiplication, normalization, etc. In some respects, nodes in a Neural Network 1005 are either fully connected or partially connected. See further reference. Figure 10Each node can process one or more inputs (or portions thereof) in 1003 and 1015 using activation and weight tensors. In some aspects, in response to receiving deployment input 1003 and training data input 1015, neural network 1005 first performs preprocessing 1004 or 1016, such as encoding or converting such inputs into machine-readable notations representing the entire input (e.g., tensors representing sensor values ​​over a specific time span). In response, a node can then receive an input tensor, which may, for example, represent the presence of one or more features in the input (e.g., a specific range of sensor values ​​at a specific location on a trace (e.g., trace 608) or a wearable garment). In some aspects, the input tensor is an N-dimensional tensor, where N can be greater than or equal to one. In some aspects, if the node is in the input layer, the input tensor 1020 represents the input data of neural network 1005. In some aspects, the input tensor 1020 is also the output of another node in the previous layer. In some respects, after a node (such as node 1021) performs an operation using input tensor 1020, it generates output tensor 1022, which is then passed to other neurons in the hidden layer and / or output layer. Output tensor 1022 represents the output processed by node 1021. For example, output tensor 1022 could be a matrix representing the product of matrix multiplication, or a matrix indicating whether a sensor value at a specific location within a set of traces or wearable material has exceeded a threshold (or is within a range). In various respects, output tensor 1022 represents the input to another node in a subsequent layer (i.e., the output layer).

[0084] In some aspects, node 1021 applies weight tensor 1024 to input tensor 820 via linear operations (e.g., matrix multiplication, addition, scaling, biasing, or convolution). All other nodes in the neural network can perform the same function. In some aspects, the results of linear operations are processed by nonlinear activations (such as step functions, sigmoid functions, hyperbolic tangent functions (tan h), and modified linear unit functions (ReLU). The result of activation or other operations is output tensor 1022, which is sent to subsequent connection nodes in the next layer of neural network 1005. Subsequent nodes use output tensor 1022 as input activation tensors to another node.

[0085] Each function in neural network 1005 can be associated with different coefficients (e.g., weights and core coefficients) that can be adjusted during training. For example, after preprocessing 1016 in various aspects (e.g., normalization, feature scaling, and extraction), neural network 1005 is trained using one or more datasets of preprocessed training data input 1015 to train predictions with appropriate weights and acceptable loss to set the weight tensors. This will help make correct inference predictions 1009 at later deployment time. In one or more aspects, learning or training involves minimizing the loss function between the target variable (e.g., an incorrect predicted score indicating shoe fit) and the actual predictor variable (e.g., a correct predicted score indicating shoe misfit). Based on the loss determined by the loss function (e.g., mean squared error loss (MSEL), cross-entropy loss, etc.), the loss function is learned to reduce errors in predictions over multiple epochs or training sessions, such that neural network 1005 learns which features and weights indicate correct inference given the input. Therefore, it is desirable to achieve as close to 100% confidence as possible in a particular classification or inference in order to reduce prediction errors. In an illustrative example, the neural network 1005 learns that for a given set of resistance values ​​A, capacitance sensor values ​​B, and piezoresistive values ​​C at location Z (e.g., within a set of traces or a wearable article), the correct classification is that the shoe does not fit properly.

[0086] After the first round / epoch of training, the neural network 1005 makes predictions using specific weight values, which may or may not be at an acceptable level of the loss function. For example, the neural network 1005 can process the preprocessed training data input 1015 a second time to make another round of predictions. This process can then be repeated over multiple iterations or epochs until the weight values ​​in the weight tensor are learned to be used for the best or correct predictions (e.g., by maximizing the reward and minimizing the loss) and / or the loss function reduces the error in the predictions to an acceptable confidence level.

[0087] In some aspects, the input is preprocessed at 1016 (or 1004) before being fed into the neural network 1005 with the training data input 1015 (or deployment input 1003). This preprocessing may include feature scaling, feature extraction, normalization, etc. Scaling (or “feature scaling”) is the process of changing numerical values ​​(e.g., via normalization or standardization) so that the model can better process the information. For example, normalization may be used to bind numerical values ​​between 0 and 1. Other instances of preprocessing include feature extraction, handling missing data, feature scaling, and feature selection.

[0088] Feature extraction involves computing a simplified set of values ​​from a high-dimensional signal that can summarize most of the information contained within it. Feature extraction techniques develop transformations from the input space to a lower-dimensional subspace, attempting to preserve the most relevant information. In feature selection, the input dimension containing the most relevant information for solving a specific problem is chosen. These methods aim to improve performance, such as the accuracy of estimation, visualization, and interpretability. The advantage of feature selection is that it does not lose important information associated with individual features; however, if a small feature set is required and the original features are highly diverse, information may be lost because some features must be omitted. On the other hand, dimensionality reduction, also known as feature extraction, can typically reduce the size of the feature space without losing information about the original feature space.

[0089] In some respects, the preprocessing of the data at positions 1016 and / or 1004 includes techniques for handling missing data. These techniques include, in some respects, full case analysis, single imputation, log-linear models and estimation using the EM algorithm, propensity score matching, and multiple imputation. This technique limits attention to cases where all variables are observed in a full case analysis. In a single implicit imputation method, missing values ​​are replaced with values ​​from similar response units in the sample. Similarity is determined by examining the variables observed for both responders and non-responders. Multiple imputation replaces each missing value with a vector of at least two imputed values ​​drawn at least twice. These extractions typically come from a random imputation process. In a log-linear model, cell counts in the contingency table are directly modeled. Assumptions may be that, given the expected value for each cell, the cell counts follow an independent multivariate Poisson distribution. These are conditions based on the total sample size, whose counts follow a multinomial distribution.

[0090] In some aspects, preprocessing at 1016 and / or 1004 includes outlier detection and correction techniques for handling outlier data within the input data 1015 / 1003. Unlike other cases, outliers often disproportionately influence substantive conclusions about the relationship between variables. Outliers can be defined as data points that deviate significantly from other data points. For example, error outliers are data points that are far from other data points because they are caused by inaccuracies. More specifically, error outliers include those caused by not being part of the target data group, being outside the possible range of values, errors in observation, errors in recording, errors in data preparation, errors in calculation, errors in encoding, or errors in data manipulation. These error outliers can be handled by adjusting data points to correct their values ​​or by adding more such data points from the dataset. In some implementations, specific aspects define values ​​that are more than three scaled median absolute deviations (“MAD”) from the median as outliers. Once defined as outliers, some aspects replace these values ​​with thresholds used in outlier detection.

[0091] In some aspects, preprocessing at 1016 and / or 1004 includes feature selection at 1015 and / or 1003 of the input data. Feature selection techniques can be performed to reduce dimensionality from the extracted features. Employing feature selection techniques can reduce the computational cost of modeling, resulting in a simpler, more generalized, and higher-performance model. Feature extraction techniques can be performed to reduce the dimensionality of the input data. However, in some implementations, the number of features obtained may still be higher than the number of features in the pre-training data at 1015. Therefore, feature selection techniques can be used to further reduce the dimensionality of the data to identify relevant features for classification and regression. Feature selection techniques can reduce the computational cost of modeling, prevent the generation of complex and overfitted models with high generalization errors, and generate simple and easily understandable high-performance models. In some aspects, the mRmR sequential feature selection algorithm is used to perform feature selection. The mRmR method is designed to discard redundant features, which allows for the design of compact and efficient machine learning-based models.

[0092] In one or more aspects, the neural network 1005 transforms or encodes the deployment input 1003 and training data input 1015 into corresponding feature vectors in the feature space (e.g., via convolutional layers). A “feature vector” (also referred to as a “vector”) as described herein can include one or more real numbers, such as a series of floating-point values ​​or integers representing one or more other real numbers (e.g., [0, 1, 0, 0]), natural language (e.g., English) words and / or other character sequences (e.g., symbols (e.g., @, !, #), phrases and / or sentences, etc.). Such natural language words and / or character sequences correspond to this set of features and are encoded or transformed into corresponding feature vectors, enabling a computer to process the corresponding extracted features. For example, each value or other content in a page can be parsed, tokenized, and encoded into one or more feature vectors.

[0093] Continue to refer to Figure 10In some aspects, annotations or labels are used to train the neural network 1005 in a supervised manner. For example, in some aspects, training includes (or precedes) annotating / labeling training data 1015, causing the neural network 1005 to learn the association between features or weights and corresponding labels, which is used to modify weight / neural node connections for future predictions. For example, a particular aspect captures or samples sensor data from each trace of the wearable garment at a first time and then outputs that information as a report. In response, the wearer, subject matter expert, or programming logic then labels such reports as “comfortable” or “fitting,” indicating whether the shoe or other wearable garment fits or is comfortable at the time corresponding to the first time. Such a process can be repeated for various subsequent times and locations of the traces and the wearable garment, allowing labels to be made for different locations of the traces and the wearable garment to provide, for example, near real-time scores indicative of fit, comfort, or shoe recommendation based on the time series of the wearer wearing the wearable garment. In this way, the neural network 1005 can learn which weights or features and their corresponding sensor data values ​​indicate fit, comfort, or shoe recommendation for different parts of the garment or wearable garment as a whole. Therefore, the neural network 1005 adjusts the weights (weight tensors) or deactivates nodes accordingly, so that some nodes corresponding to certain sensor values ​​at a specific location are activated, while other nodes corresponding to other sensor values ​​at a specific location are disabled from making score predictions.

[0094] In some respects, specific labels represent additional or alternative labels, such as shoe recommendation labels. For example, a report of sensor data could be labeled "basketball shoes," "running shoes," etc., capturing sensor readings and mechanical stimulation characteristics associated with a specific type of shoe. In another instance, the label could be "Design X" or "Activity P," corresponding to a specific wearable design recommended for a particular shoe based on sensor value reading reports. For example, a particular wearer might determine that a particular brand and design fits and is comfortable when performing a particular activity. Thus, the wearer could label the corresponding report as "Brand A, Design X," and "Basketball," indicating that such a design and activity should be performed for a particular sensor value reading. In this way, neural network 1005 can learn at 1009 the weights (e.g., shoe recommendation score or activity recommendation score) indicative of the design and / or activity used for design and / or recommendation.

[0095] In one or more aspects, after training, neural network 1005 (e.g., in a deployment state) receives one or more of the preprocessed deployment inputs 1003. When deploying a machine learning model, it is typically trained, tested, and packaged to process data it has never processed before. In response, in one or more aspects, deployment inputs 1003 (i.e., the resistance sensor value A at position Z (in a set of traces), the capacitance sensor value B at position Z, and the piezoresistive sensor value C at position Z) are fed into neural network 1005, which then uses the same weight tensor (e.g., 1024) learned through training to produce a correct inference prediction 1009. For example, input tensor 1020 may include new values ​​(e.g., sensor readings indicated in 1003) that are then multiplied or otherwise combined with weight tensor 1024 to represent the same weight values ​​learned during training for inference prediction 1009.

[0096] Regarding the interference prediction 1009 and the training prediction 1007, these correspond to fit scores, comfort scores, or shoe recommendation scores. As used herein, a “score” refers to a specific distance (e.g., Euclidean, cosine), a confidence level interval (e.g., .95), and / or a clustering, regression, or classification indicator. For example, a “fit score” could be a score with a .95 confidence level, such as a particular foot being classified as “fitting” or “not fitting.” In another instance regarding distance, deployment inputs 1003 can be combined to form data points, such as a first vector in a vector space. Aspects can then compare or determine distances from the first vector to other vectors, each representing a training data point and other predicted scores (e.g., cluster groups). Thus, for example, aspects can determine that the first vector is closest to a first classification group (“fitting”) based on the distance from the first vector to a second cluster classification group (“not fitting”). Therefore, a particular aspect can responsively generate a score or other label indicating shoe fit at 1009.

[0097] A "comfort score" may include a specific confidence level range of regression scores or categories indicating whether the shoe is "comfortable," "uncomfortable," or "somewhat comfortable." In some aspects, a shoe recommendation score may indicate various categories of shoes or shoe designs recommended for the wearer. For example, based on sensor value readings at deployment input 1003, neural network 1005 generates a score indicating that the shoe should have additional padding in the heel area due to excessive force when the heel strikes the ground. In another instance, if the wearer wears the same shoe for different activities (e.g., running and playing basketball), a particular aspect may recommend a more fitted shoe. For example, a corresponding application may tell the wearer, based on real-time 3D heatmap data, that the recommended shoe is for running rather than for basketball. In some embodiments of these examples, there are additional or alternative scores, such as activity recommendation scores. An activity recommendation score may include a specific confidence range indicating a regression score or category of the most suitable activity (e.g., basketball, football, tennis, etc.) that the wearer should engage in given sensor data.

[0098] Example User Interface

[0099] Figure 11 This is a screenshot 1100 of an example user interface based on some aspects. In some aspects, screenshot 1100 is a neural network 1005 based on data from wearable devices (such as...). Figure 3 The sensor readings (300) are used to perform its function as a result of measurements. Screenshot 1100 includes a three-dimensional heatmap 1102 of pressure points on the foot. "Hot spots" 1104 indicate (e.g., via red pixel values) traces (e.g., Figure 4 The trace 614 (corresponding to the wearable and / or foot) represents a portion of the sensor data that has exceeded a threshold corresponding to pressure. For example, hotspot 1104 may indicate a corresponding portion of the trace, a portion of the wearable, or a portion of the foot that has exceeded a resistance or pressure threshold. In some aspects, other portions of the heatmap 1102 indicate (e.g., via cooler pixel values, such as blue) other corresponding portions of the trace, the wearable, and / or the foot that are associated with sensor data that has not yet exceeded a sensor data threshold. For example, this could be represented in the heatmap 1102 by all non-circular elements or portions of the wearable that are not included in hotspot 1104.

[0100] Figure 11The illustration also depicts recommendations that can be made when sensor data thresholds are exceeded and / or not exceeded at one or more parts of the trace, wearable article, and / or foot. For example, as shown in screenshot 1100, different natural language recommendations can be presented in response to receiving an indication that button 1107 has been selected. For instance, a label such as "Current shoe does not fit the wearer" can be presented (e.g., based on neural network 1005 performing its function). Alternatively or additionally, other labels can be presented, such as "Based on sensor data, we recommend the wearer wear size A." In some of these aspects, computational logic can, for example, generate and use data structures, such as lookup tables, to map user shoe size information derived from sensor data to shoe sizes for recommendation. For example, each row or key in the data structure can correspond to a range of sensor data values ​​(e.g., resistance value A to resistance value C) and / or a corresponding location in the wearable article or foot. And the value of each corresponding key can be the recommended shoe size.

[0101] As further illustrated in screenshot 1100, some aspects provide user interface elements indicating that "running is the most suitable activity for this shoe" (e.g., based on determining an activity recommendation score, as described herein). In some of these aspects, for example, the wearer can wear the same shoe for different activities (e.g., running, soccer, basketball, tennis). In response, traces within the shoe's wearable material can convert physical stimuli (e.g., deformation) into electrical signals during such different activities to determine whether any of the signals exceeds a threshold, which can be set by the programmer based on the activity being performed (or fed into a model, such as neural network 1005). For example, for sprinting, since the runner can be expected to apply force to the metatarsal and toe areas of the foot, and less force to the heel or calcaneal portion, a force threshold can be set accordingly to determine the activity recommendation score. However, this force distribution may differ from, for example, walking activities, in which the wearer can be expected to apply more force to the heel portion, such as during heel strike. Therefore, each threshold (e.g., the expected range of sensor data readings) can be set via programming logic or an activity-specific machine learning model. Thus, for example, if any sensor reading falls outside or exceeds such a threshold, different activities can be recommended based on an activity-specific recommendation score, where the threshold more closely matches the wearer's sensor data readings. Subsequently, for example, a corresponding computer application page or webpage (e.g., screenshot 1100) can recommend to the wearer that the shoe is recommended for activity A rather than activity B based on real-time sensor data or 3D heatmap data (such as the data indicated in heatmap 1102).

[0102] Example Method

[0103] Figure 12This is a flowchart of an example process 1200 for determining and transmitting stretch sensor data, visualizations, and / or scores, based on some aspects. Process 1200 (and / or any of the functionalities described herein) may be executed by processing logic including hardware (e.g., circuitry, hardware accelerators (e.g., AI accelerators), dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions running on a processor to perform hardware simulations), firmware, or combinations thereof. Although specific boxes described in this disclosure are referenced in a specific number and order, it should be understood that any box may occur substantially in parallel with any other box, or before or after any other box. Furthermore, more (or fewer) boxes may exist than those shown. The added boxes may include any functionality embodied herein (e.g., as per Figures 1 to 1). Figure 23 The box described herein. The computer-implemented method, system (including a wearable article and a processor) and / or computer-readable medium associated with the processor may perform or be caused to perform process 1200 or any other function described herein.

[0104] According to box 1202, some embodiments receive first stretch sensor data at a first time via at least two sets of overlapping traces on a wearable article located in a first position. For example, return to reference Figure 5 In a particular embodiment, first tensile sensor data (e.g., resistance values) is received from traces 304-1 to 304-8, wherein traces 304-1 to 304-4 and 304-5 to 304-8 overlap each other. The first position can be any suitable position (e.g., heel strike). In some aspects, traces 304-1 to 304-8 (or a processor within the wearable article) generate the first sensor data, and the wearable article then transmits the first sensor data via a network (e.g., via a network interface card), such that a network device receives such data and executes block 1202 (and the remainder of process 1200).

[0105] According to block 1204, some embodiments receive second stretch sensor data at a second time via at least two sets of overlapping traces on the wearable article in the second position. For example, using the above description, when the wearable article 300 is in the second position (e.g., heel off the ground), the same stretch sensors 304-1 to 304-8 generate additional stretch sensor data and transmit the data over a network for further processing.

[0106] According to box 1206, some embodiments determine at least one of the visualization content or score based at least in part on received first stretch sensor data and second stretch sensor data. As used herein, "visual content" refers to any data representing a displayed element, such as one or more letters, symbols, words, images, etc. For example, visualization content may include... Figure 1B Shoe recommendations: any part of 111. Figure 2 Any marker in 211 (e.g., fit score), Figure 7B The model of foot 702 in the middle, or Figure 11 This refers to any part of the screenshot 1100, data points, etc. As used herein, a “score” refers to a specific distance (e.g., Euclidean, cosine), confidence level interval (e.g., .95), and / or clustering, regression, or classification decision statistics. For example, a “fit score” could be a score with a .95 confidence level, such as a particular foot being classified as “fitting” or “non-fitting.” In another instance regarding distance, deployment inputs 1003 can be combined to form data points, such as a first vector in a vector space. Such scores can include any scores described herein, such as those in… Figure 10 The inference prediction 1009 describes the "fit score", "comfort score" or "shoe recommendation score".

[0107] Such scores and visualizations can be determined using any of the methods described in this article. For example, they can be determined via... Figure 10 The neural network 1005 or any programmed data structure that maps specific stretch sensor data (or ranges) to corresponding scores determines the scores. For example, the lookup data structure could include resistance value ranges A to C as keywords in records, where the same records include values ​​for a specific fit score D for a particular resistance value range. Regarding the determination of the visualization content, specific embodiments use any suitable method, such as using a matrix of stretch sensor data (e.g., data representing the visualization content), to generate model 702, as per [reference to...]. Figure 7B As described. In some aspects, identifying visualization content includes identifying "hotspots" (e.g., Figure 11 (1104) will be based on which sensor data exceeds the threshold location, as described herein. In some embodiments, determining the visualization content includes, for example, regarding... Figure 9A and Figure 9B The described functionality.

[0108] According to box 1208, some embodiments send at least one of the following to the user equipment for presentation: received first stretch sensor data, received second stretch sensor data, visualization content, and / or scores. For example, refer to Figure 18 The wearable product handling system 1808 can transmit data 1805 to the user equipment 1802 via network 1806. In response, the user equipment 1802 presents or displays first tensile sensor data, second tensile sensor data, visualizations, and / or scores.

[0109] Figure 13This is a flowchart of an example process 1300 for causing the presentation of display elements or scores based on one or more streams of near-real-time stretch sensor data, according to some aspects. According to block 1303, some embodiments receive one or more streams of stretch sensor data in near real-time via a set of traces on a wearable article. The data streams comprise a series of data elements typically ordered by time. Streaming data refers to data that flows continuously from a source system (e.g., wearable article 300) to a target (e.g., wearable article processing system 1808). When streaming data is generated by the wearable article, the streaming data architecture allows aspects to receive, store, enrich, and / or analyze the streaming data in near real-time. For example, each time a mechanical stimulus is applied to a trace on the wearable article over a time series, the trace generates a corresponding stretch sensor value, and the wearable article simultaneously (or responsively) transmits this stretch sensor value (e.g., via an antenna) to the wearable article processing system 1808 within that time series. In this way, the wearable article processing system 1808 receives the stretch sensor data "near real-time" relative to the time when the trace has generated such stretch sensor data.

[0110] According to block 1305, based at least in part on stretch sensor data, some embodiments generate at least one of the following: display elements or scores. For example, based on a portion of the stretch sensor data stream exceeding a threshold, some embodiments determine a fit score of X. In some embodiments, block 1305 includes information about... Figure 12 All the functions described in 1206. According to box 1307, based at least in part on this generation, certain embodiments cause at least one of the following to be presented: display elements or scores. For example, display elements may include Figure 1B Shoe recommendations: any part of 111. Figure 2 Any marker in 211 (e.g., fit score), Figure 7B The model of foot 702 in the middle, or Figure 11 Any part of the screenshot 1100.

[0111] In some embodiments, a data flow management system (DSMS) is responsible for at least part of performing process 1300. For example, the DSMS includes a data ingestion layer that processes the flow or stream of stretch sensor data by controlling, buffering, and routing the data. In another instance, the DSMS may include a query layer that generates queries for querying and analyzing the stored data stream.

[0112] Figure 14This is a flowchart of an example process 1400 for determining fit or whether sensor data has exceeded a threshold, based on several aspects. According to block 1402, some aspects receive first sensor data at a first time via a plurality of stretch sensors including at least a first trace and a second trace. The first sensor data indicates a first data value of the first trace and the second trace. For example, a microcontroller may receive digital sensor values ​​from an analog-to-digital converter, which indicate the amount of resistance experienced by one or more portions of the trace. The first trace and the second trace are included in a wearable article. For example, the first trace and the second trace may include... Figure 3 The wearable article has a trace 304-1 and another trace incorporated into the base layer 502 or non-conductive layer 504 of the sock structure 300. The wearable article is in a first position at the first moment. For example, the sock structure 300 may be in the heel-touching position, such as... Figure 9A As shown, this indicates that the corresponding part of the trace is measuring the corresponding sensor data, such as resistance.

[0113] In some respects, the first trace (or group of traces) and the second trace (or group of traces) overlap each other, such as Figure 5 As shown herein, “overlap” means, as used herein, an intersection at any suitable angle in position or orientation, regardless of whether the traces are in contact with or adjacent to each other. For example, the group (i.e., one or more) of traces 304-1 to 304-4 overlaps with the group of traces 304-5 to 304-8 even if a non-conductive layer 504 exists between these groups of traces so that they are not in contact. In some respects, such traces overlap each other in any suitable orientation, such as at 90 degrees relative to each other, or have a perpendicular orientation, to create a “grid” structure or pattern, as shown by traces 304-1 to 304-8. In other respects, such traces overlap at a 45-degree angle (±5 degrees) to create a “fishnet,” diamond, or triangular pattern.

[0114] In some respects, each trace is configured to convert a mechanical stimulus into one or more electrical signals. A “mechanical” or “physical” stimulus refers to any suitable mechanical-physical stimulus that the trace is experiencing through direct contact with an object that causes a physical stimulus (e.g., the ground, a helmet, or a shoe) or indirect contact with an object that causes a physical stimulus (e.g., via an electric field propagated by a capacitor sensor). For example, in response to the trace experiencing a specific stress, strain, deformation, or force due to the trace (and suggestive wearable articles) being pressed against a ground surface, each trace may output a directly proportional sensor value, such as a resistance value, pressure value, etc., indicating the degree to which the trace experiences a specific stimulus. In various respects, the wearable articles are configured to conform to body parts, such as the hand, torso, head, or foot. “Conform” means at least partially attached to or conforming to. For example, a person’s foot is configured to conform to a sock structure. In another example, a wristband or knee brace is configured to fasten or attach to the wrist or knee.

[0115] In some aspects, to receive sensor data, as described with respect to boxes 1404 and 1406, a processor is communicatively coupled to multiple tension sensors. A processor “communicably coupled” to a tension sensor means that the processor can communicate with the tension sensor via a wireless protocol (e.g., Bluetooth) or a wired protocol. For example, the processor may be external to or outside the wearable article, and the tension sensor may provide data to a network interface corresponding to the Bluetooth protocol via an on-chip bus, allowing the network interface to wirelessly transmit the sensor data via an antenna to another antenna included in a computing device housing the processor. In another instance, the processor is connected to the tension sensor via a bus and is included in the wearable article for local communication. In yet another instance, external leads or signal carriers of a processor external to or outside the wearable article but physically connected to the outside of the wearable device may be physically connected to traces, allowing the traces to provide their sensor data to the processor via the external leads.

[0116] As used herein, a “tension sensor” refers to any suitable sensor that converts, represents, or indicates a mechanical stimulus as an electrical signal (e.g., an ohmic signal). These sensors are not necessarily limited to measuring “tension,” or may not even require measuring tension at all. For example, one or more tension sensors may include at least one of the following: a capacitive sensor, a resistive sensor, and a piezoresistive sensor. The first sensor data value and the second sensor data value include one or more of the following: a resistance value detected by a resistive sensor, a capacitance value detected by a capacitive sensor, and a dielectric value detected by a piezoresistive sensor. Dielectrics are typically insulators that do not allow the flow of current, or are not conductors. Piezoelectricity is the property of certain dielectric materials to generate an electric charge when physically deformed in the presence of an electric field or conversely, when mechanically deformed.

[0117] According to box 1404, some aspects receive second sensor data indicating second sensor values ​​of the first and second traces at a second time after the first time. The wearable article (e.g., and the corresponding traces and body parts) is in a second position at the second time. For example, the wearable article may be in a position corresponding to a swing phase, heel off the ground, intermediate posture, or any other gait posture. In an illustrative example, the processor can receive a second resistance value, such as that measured by a resistance sensor, from each trace fastened to the wearable article. In a higher-level illustrative example, when the wearable article 904 is in its... Figure 9A When the wearable article 904 is in the position shown, the first sensor value can be included in the sensor value. Figure 9B At the position shown, the second sensor value can be included in the sensor value.

[0118] According to box 1406, based at least in part on first sensor data and second sensor data, some aspects determine at least one of the following: fit degree associated with the wearable article, and one or more locations within the wearable article that have exceeded (or fallen outside or satisfied) a sensor data threshold (e.g., resistance or capacitance value Y). For example, regarding "fit degree," the wearable article may be a sock structure configured to be worn on a person's foot, and the sock structure is configured to be placed in a shoe. In some aspects, the plurality of stretch sensors include capacitive sensors and another second sensor (e.g., a resistive sensor). Thus, determining the fit degree associated with the wearable article includes determining whether a person's foot fits the shoe based on the detection of the inner portion of the shoe by the capacitive sensor (e.g., detection of the inner surface of the shoe via a propagating electric field), and the second sensor may detect deformation characteristics of corresponding portions of the first and second traces. (Reference) Figure 9A and Figure 9B An example of this situation is described, and some aspects are combined with references. Figure 9A and Figure 9B The described function.

[0119] In some aspects, determining one or more locations within the first or second trace (or implying a wearable article) that have exceeded a sensor data threshold includes determining that corresponding portions of the first and second traces have exceeded a pressure threshold. In this way, for example, aspects can make it possible to present thermal image elements indicating the corresponding portions exceeding the pressure threshold and other portions of the first or second trace that have not exceeded the pressure threshold (e.g., “cold spots” indicated in blue). Figure 11 Hot topic 1104).

[0120] Based at least in part on first sensor data and second data from a first trace and a second trace (and / or other sets of traces), certain aspects generate three-dimensional models of human body parts during a time series corresponding to a first time and a second time. For example, a particular aspect may generate a 3D model of a human foot 702, as per [the context of the previous sentence]. Figure 7B The illustrations and descriptions are as follows. However, in some aspects, a “time series” corresponds to a sequence of video or model frames of various videos or models, such that the 3D model represents a continuous frame-by-frame model between two timestamps (a first time and a second time), allowing the 3D model to illustrate the motion of a wearable article over time (e.g., near real-time relative to human motion). For example, a 3D model can illustrate various gait phases in a model sequence, such as heel strike, mid-pose, toe lift, and heel lift, and the corresponding “hot spots” during such sequences, indicating which areas or traces of the foot are associated with sensor data values ​​that have exceeded a threshold. In some aspects, such 3D models are included in user interfaces or other display elements, such as Figure 11 Screenshot 1100.

[0121] In some aspects, frame 1406 includes detecting the size (e.g., according to a US or international shoe size conversion table, such as size 10) or dimensions (e.g., length, width, and height) of the foot (or each part of the foot) based on at least one of first sensor data and second sensor data. For example, this could include, as about Figure 7A and Figure 6 The described functionality. Such size indications can be presented at presentation elements such as user interface markers. For example, such indications can include... Figure 11 The image shows "The current shoe does not fit the wearer".

[0122] In some aspects, box 1406 may additionally or alternatively include other determinations, such as shoe design recommendations or activity recommendations. For example, based on traces indicating that pressure exceeds a threshold only at the sock construction or heel portion of the shoe, a particular aspect may recommend that the heel portion of the shoe be reinforced with more cushioning, rubber, or actually recommend a specific predetermined shoe design. In some aspects, such design recommendations are based on the use of a machine learning model, such as neural network 805, wherein, for example, training sensor data is labeled with specific design choices, and the model can learn weights corresponding to features or sensor data values ​​associated with that label. In an illustrative example of activity recommendation, since a specific stretch sensor reading is close to a basketball profile (which includes a threshold associated with such readings), a particular aspect may recommend a specific shoe for basketball rather than football. In some aspects, as described above, such activity recommendations are based on the use of a machine learning model, such as neural network 1005, wherein, for example, training sensor data is labeled with specific activities, and the model can learn weights corresponding to features or sensor data values ​​associated with that label.

[0123] According to box 1408, based at least in part on this determination, some aspects cause one or more elements to be presented (e.g., displaying and / or playing audio data via a voice assistant). For example, the one or more elements may include one or more user interface elements of a user interface. In an illustrative example, based at least in part on first sensor data and second sensor data, some aspects generate a heatmap that includes a digital model of a human body part during a time series corresponding to the first and second times (e.g., Figure 7B The heatmap also includes elements (e.g., hotspot 1104) on a portion of the digital model indicating corresponding locations within the first or second trace that have exceeded a sensor data threshold. For example, "one or more elements" could include heatmap 1102 or... Figure 11 Any other element in it.

[0124] In some respects, one or more elements include recommendations for one or more shoes for a user to wear, based on sensor data. For example, shoe recommendations could be recommendations for shoe brands and models (or product lines / categories within a shoe brand). In some respects, such shoe recommendations are based on machine learning models, such as Neural Network 1005, where, for example, sensor data is trained to be labeled with specific brands and models, and Neural Network 1005 can learn weights corresponding to features or sensor data values ​​associated with the labels.

[0125] Figure 15 This is a flowchart of an example process 1500 for transmitting tensile sensor data representing electrical signals to a network device for further processing, based on some aspects. In some embodiments, process 1500 represents a process involving a wearable article (such as...) Figure 3 The wearable article 300 performs the function. According to box 1503, the wearable article receives mechanical stimulation at the track assembly. “Mechanical” stimulation refers to any suitable mechanical physical stimulation that the track is experiencing through direct contact with an object that causes physical stimulation (e.g., the ground, helmet, or shoe) or indirect contact with an object that causes physical stimulation (e.g., via an electric field propagated by a capacitor sensor). For example, mechanical stimulation could be a simple finger touch on the track or holding a specific object at a distance from the track (e.g., inside or outside the emitting electric field of the capacitor sensor).

[0126] According to box 1508, the wearable article determines whether the stimulus exceeds a threshold (e.g., a resistance or capacitance threshold). If not, process 1500 stops. If yes, the wearable article converts the mechanical stimulus into one or more electrical signals. For example, in response to the traces experiencing specific stress, strain, deformation, or force due to the traces (and the suggestive wearable article) being pressed against a ground surface, each trace may output a directly proportional electrical signal, such as a resistance signal, a pressure signal, etc., indicating the degree to which the trace has experienced a specific stimulus.

[0127] According to box 1509, the wearable product is transmitted via a network (e.g., Figure 18 Network 1806 transmits the tensile sensor data representing the one or more electrical signals to a network device for further processing. For example, in response to the transition at block 1502, a processor within the wearable article can first cause an analog-to-digital converter in the wearable article to convert the raw one or more electrical signals into digital data (i.e., tensile sensor data). The processor can then transmit such tensile sensor data to a network interface via an on-chip bus, the network interface including an antenna for transmitting the tensile sensor data over the network to a network device (such as a cloud node or server) for further processing. Such a cloud node or server can perform, for example, [actions related to...]. Figure 12 Process 1200 Figure 13 1300 and / or Figure 14 The functions described in 1400.

[0128] Figure 16 This is a flowchart of an example process 1600 for determining the resistance value of each trace based on voltage, based on several aspects. In some aspects, process 1600 represents acquiring measurement data from a static wearable article to determine attributes such as foot geometry, size, etc., to build a model, as per [the relevant information]. Figure 7A and 7B As described. According to box 1602, the wearable article applies an electrical signal at the first end of each trace of the wearable article. For example, a processor within the wearable article can apply electrical signals in parallel with a first voltage (V1) through each trace.

[0129] According to box 1604, the wearable article measures the voltage (V2) of an electrical signal at the second end of each trace. For example, each trace may output an electrical signal at the second end, which is at a second voltage, and a coupling bus may transmit such outputs to a processor of the wearable article.

[0130] According to box 1606, the wearable article determines the resistance value for each trace based on the voltage of the electrical signal. For example, the processor can determine the resistance value via the following formula:

[0131] (V1-V2) = IR

[0132] Where I = current and R = resistance. V1, V2 and I are known, so R ("R2") can be derived for each trace.

[0133] According to box 1608, in response to the determination at box 1606, a particular aspect performs at least one of the following: transmitting each resistance value to the network device for further processing, determining a score, determining visualization content, or presenting display elements. In some aspects, box 1608 includes, as per [reference to box 1608], [details about the determination at box 1606]. Figure 12 The functionality described in Figure 1206.

[0134] Figure 17 This is a flowchart illustrating an example method for manufacturing wearable products based on several aspects. In some aspects, Figure 17 Indicates manufacturing, such as Figure 5 The wearable article 500 is shown. According to step 1703, some aspects (e.g., a knitting machine or sewing machine) join a first set of stitches (e.g., stitches 304-1 to 304-4) to the base layer of the wearable article (e.g., ...). Figure 5 (Base layer 506). The wearable article is configured to conform to a part of the human body. The first set of traces is a conductive material configured to convert mechanical stimulation into one or more electrical signals. As used herein, “joining” means sewing, fastening, or otherwise connecting two articles together. For example, joining may include or mean sewing, knitting, weaving, bonding, nonwoven joining, etc.

[0135] According to step 1705, the parties may position a non-conductive layer (e.g., non-conductive layer 504) of the wearable article on the first set of traces. In these cases, the non-conductive layer is placed on top of and adjacent to the first set of traces. According to step 1707, the parties may position a second set of traces (e.g., horizontal traces 304-5 to 304-8) on the non-conductive layer such that the second set of traces is substantially perpendicular (±5% of a 90-degree angle) to the first set of traces. In these cases, the second set of traces is placed on top of and adjacent to the non-conductive layer. In some aspects, the second set of traces does not need to be positioned substantially perpendicularly, but can be positioned at any suitable angle, such as 45 degrees (±5%) relative to each other or any other suitable angle.

[0136] According to step 1709, some aspects bond the second set of traces at least to the non-conductive layer. Some aspects additionally or alternatively bond the second set of traces to the first set of traces and / or the base layer. Some aspects alternatively or additionally bond the non-conductive layer to the first set of traces and / or the base layer. In some aspects, the wearable article includes an outer layer positioned on top of the second set of traces, wherein this outer layer is the outermost layer visible to the wearer or the environment, such that the traces are not visible to the wearer. In these cases, the outer layer may be bonded to the second set of traces, the non-conductive layer, the first set of traces, and / or the base layer.

[0137] In some cases, such as Figure 17 The “joining” is performed by an article-making machine and / or in conjunction with a human. In some aspects, the article-making machine is an automatic knitting machine or any other machine capable of producing wearable articles. In the aspect where the article-making machine is a knitting machine, the knitting machine can be a plain knitting machine, for example, a plain V-shaped knitting machine such as one with a front needle bed and a back needle bed. A knitting machine can form knitted parts using needles from a single needle bed or using needles from two needle beds. The knitting machine may include and / or be coupled to one or more computing devices. The computing devices may accept computerized knitting instructions, and the knitting machine may automatically form knitted parts based on these computerized knitting instructions.

[0138] Example computing environment

[0139] Figure 18This is a block diagram illustrating an example computational environment 1800 for determining fit or other properties associated with wearable articles based on several aspects. It should be understood that this and other arrangements described herein are merely illustrative examples. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, and functional groupings, etc.) may be used in addition to or in place of the arrangements and elements shown, and some elements may be omitted entirely. Furthermore, many of the elements described herein are functional entities that can be implemented as separate or distributed components or combined with other components, and implemented in any suitable combination and location. The various functions performed by one or more entities as described herein can be performed by hardware, firmware, and / or software. For example, various functions can be performed by a processor executing instructions stored in memory.

[0140] The computing environment 1800 is an example of a suitable architecture or operating environment for implementing certain aspects of this disclosure. In addition to other components not shown, the computing environment 1800 includes a user device 1802, a wearable article 1804, and a wearable article processing system 1808. Each of the user device 1802, the wearable article 1804, and the wearable article processing system 1808 may include one or more computer devices, such as those discussed below. Figure 23 The computing device 2300. For example... Figure 18 As shown, user equipment 1802, wearable device 1804, and wearable device processing system 1808 can communicate via network 1806, which may include, but is not limited to, one or more local area networks (LANs) and / or wide area networks (WANs). Such network environments are common in offices, enterprise-wide computer networks, intranets, and the Internet. It should be understood that, within the scope of this technology, any number of client devices and server devices can be used within computing environment 1800. Each device may include a single device or multiple devices cooperating in a distributed environment. For example, wearable device processing system 1808 may be provided by multiple server devices or cloud nodes that collectively provide the functionality of wearable device processing system 1808 as described herein. Additionally, other components not shown may also be included in the network environment. In some aspects, wearable device processing system 1808 is included in user equipment 1802.

[0141] User device 1802 may be a client device on the client side of computing environment 1800, while wearable artifact processing system 1808 may be on the server side of computing environment 1800. Wearable artifact processing system 1808 may include server-side software designed to work in conjunction with client-side software on user device 1802 to implement any combination of features and functions discussed in this disclosure. For example, user device 1802 may include an application for interacting with wearable artifact processing system 1808. This application may be, for example, a web browser or a dedicated application for providing functionality, such as information about... Figure 11 The division of computing environment 1800 is provided to illustrate an example of a suitable environment, and for each implementation, it is not required that any combination of user equipment 1802 and wearable artifact processing system 1808 remain as separate entities. While computing environment 1800 illustrates a configuration in a networked environment with separate user equipment and wearable artifact processing system, it should be understood that other configurations in which components are combined may be employed. For example, in some configurations, the user equipment may also provide the capabilities of the techniques described herein.

[0142] User equipment 1802 may include any type of computing device that can be used by a user. For example, in one aspect, the user equipment may be what is described herein as... Figure 23 The computing device 2300 described is of a certain type. By way of example and not limitation, user device 1802 can be embodied as a personal computer (PC), laptop computer, mobile device, smartphone, tablet computer, smartwatch, wearable computer, handheld communication device, gaming device or system, entertainment system, vehicle computer system, embedded system controller, electrical appliance, consumer electronics device, workstation, or any combination of these depicted devices, or any other suitable device. A user can associate with user device 1802 and can interact with wearable article handling system 1808 via user device 1802.

[0143] The wearable article processing system 1808 is configured to receive sensor data input 1818 from the wearable article 1808 (or more precisely, a stretch sensor of the wearable article), in order to interpret the sensor input data 1818 (via the fit detection component 1810) and provide a corresponding output 1805 to the user equipment 1802 (via the model generation component 1812). In some aspects, the wearable article processing system 1808 performs actions such as... Figure 12 , Figure 13 and Figure 14 The processes 1200, 1300, and / or 1400 are described. In some aspects, wearable article 1804 refers to any wearable article described herein, such as... Figure 3 Sock structure 300 or Figure 4 The head cover 400. In some respects, the sensor data input 1818 represents any suitable sensor data value, such as resistance, capacitance, or piezoelectric value.

[0144] The fit detection component 1810 is typically responsible for interpreting the sensor data input 1818 in any suitable manner; one example is determining whether the shoe fits the foot. In some aspects, the fit detection component 1810 includes, as described above... Figure 12 , Figure 13 and / or Figure 14 Any of the functions described herein. For example, as described herein, fit detection component 1810 may determine fit degree associated with wearable article 1804, one or more locations within wearable article 1804 that have exceeded sensor data thresholds, comfort score, shoe design recommendation, shoe brand / model recommendation, and / or activity recommendation. To interpret such sensor data, in some aspects, fit detection component 1810 includes or uses neural network 1005, as per [the relevant documentation / concept]. Figure 10 As described.

[0145] The model generation component 1812 is typically responsible for generating or determining one or more elements (e.g., visual content) for presentation at the user device 1202. For example, in some aspects, the model generation component 1812 generates a 3D model of a foot, such as... Figure 7B The model 702 represents the foot. In another instance, the model generation component 1812 enables presentation (e.g., by sending communication signals to user equipment 1802 via network 1806). Figure 11 The screenshot of 1100 shows one or more user interface elements, such as Figure 11 Hotspot 1104. Model generation component 1812 can enable the presentation of any other user interface elements as described herein, and may include, as per [the relevant information]... Figure 14 The functions described in 1408.

[0146] The wearable artifact handling system 1808 can be implemented using one or more server devices, one or more platforms with corresponding application programming interfaces, cloud infrastructure, etc. Although the wearable artifact handling system 1808... Figure 18 In this configuration, it is shown separately from the user equipment 1802 and the wearable article 1804; however, it should be understood that in other configurations, some or all of the functions of the wearable article processing system 1808 may be provided in the user equipment 1802 and / or the wearable article 1804. For example, in some aspects, the fit detection component 1810 and / or the model generation component 1812 are logic included on-chip or within the wearable article 1804.

[0147] In one aspect, the functions performed by the components of the wearable article handling system 1808 are associated with one or more applications, services, or routines. In particular, such applications, services, or routines may operate on one or more user devices or servers, be distributed across one or more user devices and servers, or be implemented in the cloud.

[0148] Furthermore, in some aspects, these components of the wearable artifact handling system 1808 may be distributed across a network in the cloud (including one or more server and client devices) and / or may reside on user devices. Additionally, these components, the functions performed by these components, or the services performed by these components may be implemented at an appropriate abstraction layer of the computing system (such as the operating system layer, application layer, hardware layer, etc.). Alternatively or additionally, the functions of these components and / or aspects of the techniques described herein may be performed at least in part by one or more hardware logic components. Illustrative types of hardware logic components that may be used, such as but not limited to, include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), etc. Furthermore, although the functionality is described herein with reference to specific components shown in the example computing environment 1200, it is conceivable that, in some aspects, the functionality of these components may be shared or distributed across other components.

[0149] Figure 19 This is a timing diagram illustrating wearable articles, remote devices, and user devices that perform different functions according to various aspects. At the first moment, wearable article 1902 (e.g., Figure 3 The wearable article 300 transmits sensor data (e.g., via an antenna and an on-chip network interface card) to the remote device 1904. The remote device 1904, or any “remote device” as used herein, refers to any external device that is outside or not part of the wearable article 1902 or user equipment 1906. For example, the remote device 1904 can be any suitable network device or host, such as a cloud node, server, switch, gateway device, base station, or any associated component, router, etc. In some aspects, the remote device 1904, or any other remote device as used herein, includes... Figure 18 Wearable product handling system 1808.

[0150] In response to the remote device 1904 receiving the transmitted sensor data, according to step 2, the remote device 1904 determines at least one of the score or the visualization content. In some aspects, this includes, for example, regarding... Figure 6The function described in box 1206. According to step 3, the remote device 1904 then transmits the score, visualization content, and / or sensor data to the user device 1906. According to step 4, the user device 1906 then presents (e.g., displays) the score, visualization content, and / or sensor data.

[0151] Figure 20 This is a timing diagram illustrating wearable articles and remote devices performing different functions according to some aspects. In step 1, wearable article 2002 first transmits sensor data to remote device 2004. For example, wearable article 2002 may convert mechanical stimulation into one or more electrical signals indicating one or more stretch sensor data (such as resistance values). Wearable article 2002 may then transmit such stretch sensor data to remote device 2004 according to step 1.

[0152] According to step 2, the remote device 2004 then determines at least one of the score, the visualization content, and / or the control signal. In some aspects, step 2 includes, as per […]. Figure 12 The function described in box 1206. To determine the control signal, remote device 2004 can determine what control signal to send to wearable article 2002 to elicit some specific tangible output at wearable article 2002. For example, remote device 2004 can determine that it needs to send a control signal to activate a light-emitting diode (LED) at wearable article 2002. According to step 3, remote device 2004 transmits a score, visualization content, and / or control signal to wearable article 200. For example, the control signal may cause the LED to output a specific color or lighting pattern, indicate that sensor data has exceeded a threshold, or any other indicator associated with the score, such as shoe fit, etc. In another instance, the control signal may be audio feedback indicating a control signal.

[0153] Figure 21 This is a timing diagram illustrating wearable articles and user devices performing different functions according to various aspects. At step 1, wearable article 2102 determines sensor data, visualization content, and / or scores. In some aspects, step 1 includes, as per [reference to...] Figure 12 The function described in box 1206. According to step 2, the wearable article 2102 then transmits the sensor data, visualizations, and / or scores to the user device 2104. At step 3, the user device 2104 then responsively presents (e.g., displays or provides its audio feedback) the sensor data, visualizations, and / or scores.

[0154] In terms of alternatives, wearable articles 2102 perform all functions, eliminating the need for user equipment 2104, such as Figure 21As shown. For example, according to step 1, wearable article 2102 can determine sensor data, visualization content, and / or scores. And at step 2, wearable article 2102 can additionally present sensor data, visualization content, and / or scores. In these respects, for example, wearable article 2102 may include display devices (e.g., LCD screens) and / or audio devices to present such information.

[0155] Example computing device

[0156] Figure 22 It is any wearable article described in this document in accordance with certain aspects (e.g., Figure 3 Block diagram 2200 of wearable devices (300). Although Figure 22 The illustrations depict various components included within a wearable article, but in some respects, some or every component is not part of the wearable article. For example, in some respects, the electronics of the wearable article may only include the stretch sensor 2230 and / or the wireless communication block 2206, while other components are hosted at a remote device, such as... Figure 18 The wearable article handling system 2808. Block diagram 2200 includes wireless communication block 2206, control block 2204, power supply 2202, multiplexer (MUX) 2220 and a set of traces 2230 (e.g., a set of stretch sensors).

[0157] Power block 2202 includes a DC power source, such as a battery, supercapacitor, etc., which is sufficient to provide power to a variety of other electronic devices. The battery may be a rechargeable battery or may be replaceable. Additionally or alternatively, power block 2202 may include any of a variety of other power sources, including a piezoelectric generator or other power sources that can generate electricity through movement or regular use of wearable articles. Power block 2202 may optionally include additional components to boost or otherwise convert the power output of the DC power source, such as a boost converter in the example, power block 2202 includes a lithium-ion battery configured to deliver between 3.0 and 4.2 volts and a charged (5) volt boost converter.

[0158] Control block 2204 receives power from power block 2202 and controls the operation of wireless communication block 206, as well as signals transmitted and received from trace 2230 (or stretch sensor). Control block 2204 includes processor 2208 (such as a microcontroller), electronic memory 2210 (such as random access memory (RAM) or flash memory or any suitable electronic memory known in the art), and input / output block 212, as well as various other components that may be required or utilized. In some instances, control block 2204 is a single system or a system-on-a-chip (e.g., a PCB substrate with circuitry). In some instances, control block 2204 includes an Atmel Corporation ATmega32U4 microcontroller as processor 2208 and associated circuitry, and / or an Arduino Leonardo microcontroller board, or any suitable controller or controller system. In some aspects, processor 2208 performs… Figure 12 , Figure 13 , Figure 14 , Figure 15 and / or Figure 16 The process is 1200, 1300, 1400, 1500 and / or 1600.

[0159] When the stretch sensor (an individual trace or group of traces 2230 of 2230) outputs a signal to the input / output block 2212 of the control block 1304, the input / output block 2212 formats the signal received from the trace and forwards the signal to the processor 2208. The processor 2208 evaluates various characteristics of the signal from the input / output block 2212 as needed, including but not limited to the time of sensing the output signal and the duration of the output signal. The processor 2208 may store such characteristics in the electronic memory 2210 and / or apply these characteristics appropriately.

[0160] The wireless communication block 2206 (e.g., a network interface) includes one or more wireless antennas 2214 and a wireless controller 2216. The wireless antennas 2214 can each be configured to communicate according to different wireless modes, such as various versions of Bluetooth, Near Field Communication (NEC), Ultra High Frequency (UHF), etc. Each wireless antenna 2214 can be configured to communicate within one frequency band or across multiple frequency bands. The wireless controller 2216 is configured to communicate according to various wireless modes corresponding to the one or more antennas 2214. The wireless controller 2216 can be a single device or multiple separate controllers, each configured to communicate according to the different modes supported by the various antennas. In a non-limiting example, the wireless communication block 2206 includes a single antenna 2214 configured to transmit sensor data to an external device, such as Bluetooth or any other standard. Figure 18Wearable product handling system 1808.

[0161] Wireless communication block 2206 is configured to communicate via various modes with one or more external devices that are not themselves part of the wearable article. The external device may be a mobile device, such as a mobile phone (e.g., user equipment 2802), a smartphone, a personal digital assistant (PDA), a mobile music or media player, etc. The external device may additionally or alternatively be fixed or typically fixed, such as a race tracker or base station. Wireless communication block 2206 may pair with a given external device according to a conventional pairing mechanism associated with that external device to establish a communication link between the wearable article and the external device.

[0162] In various instances, control block 2204 includes, as a standalone component or together with processor 2208 and / or input / output block 2212, the implementation of an analog-to-digital converter (ADC) and rate smoothing and / or filtering of the signal from trace 2230. In various instances, the ADC converts the input analog signal from approximately zero (0) volts to approximately five (5) volts and, at sampling rates from approximately ten (10) Hz to fifty (50) Hz, to an eight-bit digital signal. In one instance, the sampling rate is thirty (30) Hz.

[0163] In various instances, the input / output block 2212 and / or processor 2208 utilizes a rolling weighted average of the digital output from the ADC for each sensor data value received from the trace. In one instance, processor 2208 applies a rolling weighted average of 0.2 to the current output of the pressure sensor from the ADC and applies an average of 0.8 to the previous rolling weighted average of the pressure sensor output. Thus, the current rolling weighted average of the output of a given pressure sensor is based on eighty percent (80) of the previous average, and the current output of the ADC based on that pressure sensor is twenty percent (20). It should be noted and emphasized that the rolling weighted average of each tension sensor can be evaluated individually and independently.

[0164] Block diagram 2200 also includes a mux 2220. Various aspects utilize a multiplexer (or “MUX”) 2220 to reduce the pin count required to measure the impedance or other physical stimuli of each trace. In some aspects, processor 2208 applies an electrical signal of source voltage V1 in parallel at the first end of each trace in trace group 2230 by first transmitting a signal to the first end of each trace via bus 2218. Then, each trace outputs a voltage V2 at the second end, which is then forwarded to MUX 2220 and then to processor 2208 via bus 2219 (and / or wireless communication block 2206, for transmission to wearable article processing system 1808) for processing and interpretation. For example, as described above, processor 2208 can determine the resistance of each trace using Ohm's law based on voltage. Additionally or alternatively, the processor 2208 may then convert or interpret the resistance or other sensor data into other determinations, such as fit associated with the wearable article, wearable article comfort, wearable article design recommendations, and / or as per [the relevant information]. Figure 14 The appropriate determination described in box 1406. Additionally or alternatively, in some aspects, in response to determining the resistance (e.g., via Ohm's law) or other sensor value, processor 2208 sends a signal along bus 2211 to wireless communication block 2206 for transmission to wearable article processing system 1808 for further processing. For example, antenna 2214 may send a request via a wireless computer network to an external remote device requesting the interpretation or mapping of the resistance value to a specific score. Such a remote device may, for example, include neural network 1005, such that the resistance value is provided as input to the model to generate different inference prediction scores.

[0165] Looking at it now Figure 23 The computing device 2300 includes a bus 10 that is directly or indirectly coupled to the following devices: memory 12, one or more processors 14, one or more presentation units 16, input / output (I / O) ports 18, input / output units 20, and an exemplary power supply 22. Bus 10 can represent one or more buses (such as an address bus, a data bus, or a combination thereof). Although lines are shown for clarity... Figure 23 The various blocks are depicted, but in reality, the individual components are not clearly defined, and metaphorically, these lines will be more accurately described as gray and blurry. For example, the presentation components such as those of a display device can be considered as I / O components. Furthermore, the processor has memory. The inventors recognize this as the nature of the art and reiterate... Figure 23 The figures are merely illustrations of exemplary computing devices that may be used in conjunction with one or more aspects of the present invention. No distinction is made between categories such as “workstation,” “server,” “laptop,” “handheld device,” etc., as all of these categories are... Figure 23Within the scope and refer to "Computing Devices".

[0166] Computing device 2300 typically includes a variety of computer-readable media. Computer-readable media can be any available medium accessible by computing device 2300, and includes volatile and non-volatile media, as well as removable and non-removable media. By way of example and not limitation, computer-readable media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile media, removable and non-removable media, of any method or technical fact for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, cassette tape, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by computing device 2300. Computer storage media itself does not include signals. Communication media typically embody computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals such as carrier waves or other transmission mechanisms, and includes any information delivery medium. The term "modulated data signal" means a signal whose characteristics are set or altered in a manner that encodes information in the signal. As an example, and not a limitation, communication media includes wired media such as wired networks or direct wired connections, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination of the foregoing should also be included within the scope of computer-readable media. In various respects, computing device 2300 refers to... Figure 18 The physical architecture of the user equipment 1802 or wearable product handling system 1808.

[0167] Memory 12 includes computer storage media in the form of volatile memory and / or non-volatile memory. The memory can be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. Computing device 2300 includes one or more processors that read data from various entities such as memory 12 or I / O components 20. Presentation component 16 presents data indications to a user or other device. Exemplary presentation components include display devices, speakers, printing components, vibrating components, etc. In some aspects, the memory contains program instructions that, when executed by one or more processors, cause one or more processors to perform any of the operations described herein, such as... Figure 12 , Figure 13 , Figure 14 , Figure 15 and / or Figure 16 Processes 1200, 1300, 1400, 1500 and / or 1600 or about Figure 1 to Figure 13Any functionality described.

[0168] I / O port 18 allows computing device 2300 to be logically coupled to other devices including I / O component 20, some of which may be built-in. Illustrative components include microphones, joysticks, game controllers, satellite receivers, scanners, printers, wireless devices, etc. I / O component 20 can provide a natural user interface (NUI) that processes user-generated air gestures, voice, or other physiological input. In some cases, the input can be sent to appropriate network elements for further processing. The NUI can implement any combination of voice recognition, stylus recognition, facial recognition, biometric recognition, on-screen and near-screen gesture recognition, air gestures, head and eye tracking, and touch recognition (described in more detail below) associated with the display of computing device 1400. Computing device 2300 may be equipped with depth cameras, such as stereo camera systems, infrared camera systems, RGB camera systems, touchscreen technology, and combinations thereof, for gesture detection and recognition. Additionally, computing device 2300 may be equipped with accelerometers or gyroscopes capable of detecting motion. The output of the accelerometer or gyroscope can be provided to the display of computing device 1400 to present immersive augmented reality or virtual reality.

[0169] As will be understood, aspects of the invention particularly provide for generating proof and proof service notifications corresponding to the veracity of the established claims. The invention has been described with respect to specific aspects, which are intended in all respects to be illustrative rather than restrictive. Alternative aspects will become apparent to those skilled in the art to which this invention pertains without departing from the scope of the invention.

[0170] As can be seen from the foregoing, the present invention is well adapted to achieve all the objects and objectives listed above, as well as other advantages that are obvious and inherent to the system and method. It should be understood that certain features and sub-combinations are practical and can be used without reference to other features and sub-combinations. This is contemplated by the claims and is within the scope of the claims.

[0171] The subject matter of this invention is specifically described herein to satisfy legal requirements. However, the specification itself is not intended to limit the scope of this patent. Rather, the inventors have envisioned that the claimed subject matter may be embodied in other ways, in conjunction with other prior or future techniques, to include different steps or combinations of steps similar to those described in this document. Furthermore, although the terms “step” and / or “box” may be used herein to refer to different elements of the method employed, these terms should not be construed as implying any particular order among or between the various steps disclosed herein, unless and only if the order of individual steps is explicitly described.

[0172] The following clauses represent exemplary aspects of the concepts envisioned herein. Any of the following clauses may be combined in a multi-dependent manner to be subordinate to one or more other clauses. Furthermore, any combination of subordinate clauses (clauses that explicitly depend on preceding clauses) may be combined while remaining within the scope of the aspects envisioned herein. The following clauses are illustrative and not restrictive.

[0173] The present invention has been described in conjunction with specific aspects, which are intended in all respects to be illustrative and not restrictive. Alternative aspects will become apparent to those skilled in the art without departing from its scope.

[0174] Various components used herein have been identified, and it should be understood that any number of components and arrangements can be employed to achieve the desired functionality within the scope of this disclosure. For example, for clarity of concept, components in aspects depicted in the figures are shown by lines. Other arrangements of these and other components may also be implemented. For example, although some components are depicted as single components, many elements described herein can be implemented as separate or distributed components or combined with other components, and implemented in any suitable combination and location. Some elements may be omitted entirely. Furthermore, the various functions performed by one or more entities as described herein can be performed by hardware, firmware, and / or software, as described below. For example, various functions can be performed by a processor executing instructions stored in memory. Therefore, other arrangements and elements (e.g., machines, interfaces, functions, sequences, and functional groups) may be used in addition to or in place of the arrangements and elements shown.

[0175] The aspects described herein may be combined with one or more of the specifically described alternatives. In particular, in the alternatives, the claimed aspect may include references to more than one other aspect. The claimed aspect may specify further limitations on the claimed subject matter.

[0176] This document describes in detail the subject matter of various aspects of the technology to meet legal requirements. However, the specification itself is not intended to limit the scope of this patent. Rather, the inventors have envisioned that the claimed subject matter may be embodied in other ways, in conjunction with other existing or future technologies, to include different steps or combinations of steps similar to those described in this document. Furthermore, although the terms “step” and / or “box” may be used herein to refer to different elements of the method employed, these terms should not be construed as implying any particular order among or between the various steps disclosed herein, unless and only if the order of individual steps is explicitly described.

[0177] For the purposes of this disclosure, the word "including" has the same broad meaning as the word "comprising," and the word "access" includes "receiving," "quoting," or "retrieval." Furthermore, the word "communication" has the same broad meaning as the words "receiving" or "transmitting," which are implemented by a software- or hardware-based bus, receiver, or transmitter using the communication medium described herein. Additionally, unless otherwise indicated, words such as "a" and "an" include both plural and singular forms. Thus, for example, the constraint of "feature" is satisfied when one or more features are present. Furthermore, the term "or" includes conjunctions, disjuncts, and both (a or b therefore includes a or b, and a and b).

[0178] For the purposes of the detailed discussion above, aspects of this technology are described with reference to a distributed computing environment; however, the distributed computing environment depicted herein is merely exemplary. Components can be configured to perform novel aspects of these aspects, wherein the term "configured for" can mean "programmed to" perform a specific task or implement a specific abstract data type using code. Furthermore, while aspects of this technology may generally refer to the technical solution environment and illustrations described herein, it should be understood that the technology can be extended to other implementation contexts.

[0179] As can be seen from the foregoing, this technology is well adapted to achieve all the aforementioned objectives and purposes, as well as other obvious advantages inherent to this system and method. It should be understood that certain features and sub-combinations are practical and can be used without reference to other features and sub-combinations. This is contemplated by the claims and is within the scope of the claims.

Claims

1. A computer-implemented method, comprising: At the first moment, first stretch sensor data is received via at least two sets of overlapping traces on the wearable garment located in the first position; At a second time, second stretch sensor data is received via the at least two sets of overlapping traces on the wearable article located at the second position; Determine at least one of the visual content or score based on the received first stretch sensor data and second stretch sensor data; and send at least one of the following to the user equipment for presentation: the received first stretch sensor data, the received second stretch sensor data, the indication of the visual content or the score.

2. The method of claim 1, wherein the determination includes determining the visualization content, the visualization content including data representing a heatmap, the heatmap including a digital model of a human body part during a time series corresponding to the first time and the second time, and wherein the heatmap also includes elements on a portion of the digital model indicating corresponding positions within the at least two sets of overlapping traces that have exceeded a sensor data threshold.

3. The method of claim 1, wherein the determination includes determining the score, the score including at least one of the following: fit score, comfort score, shoe recommendation score, or activity recommendation score.

4. The method of claim 1, wherein the at least two sets of overlapping traces comprise at least one of the following: a capacitive sensor, a resistive sensor, and a piezoresistive sensor, and wherein the first sensor data value and the second sensor data value comprise one or more of the following: a resistance value detected by the resistive sensor, a capacitance value detected by the capacitive sensor, and a dielectric value detected by the piezoresistive sensor.

5. The method of claim 1, wherein the determination of the score is based on: determining whether the human foot fits the shoe by detecting the inner portion of the shoe using a capacitive sensor included in the at least two sets of overlapping traces.

6. The method of claim 1, wherein the determination of the score is based on determining that at least a portion of the at least two sets of overlapping traces has exceeded a pressure threshold, and wherein the determination of the visualization content includes determining data representing heatmap elements indicating the portion exceeding the pressure threshold and another portion of the at least two sets of overlapping traces that has not exceeded the pressure threshold.

7. The method of claim 1, wherein determining the visualization content includes determining data representing three-dimensional models of human body parts during a time series corresponding to the first and second times.

8. The method of claim 1, wherein the determination of the score is based on: detecting the foot size or dimension based on at least one of the first stretch sensor data and the second stretch sensor data.

9. A system comprising: A wearable article comprising a plurality of stretch sensors, the plurality of stretch sensors including a first set of traces overlapping a second set of traces, each trace being configured to convert mechanical stimulation into one or more electrical signals, wherein the wearable article is configured to conform to a human body part. And a processor communicatively coupled to the plurality of tensile sensors, wherein the processor is configured to perform operations including: receiving first sensor data via the plurality of tensile sensors at a first time, the first sensor data indicating a first sensor value for each trace, wherein the wearable article is in a first position at the first time; At a second time following the first time, second sensor data is received via the plurality of stretch sensors, the second sensor data indicating a second sensor value for each trace, wherein the wearable article is in a second position at the second time; at least one of the following is determined, based at least in part on the first sensor data and the second sensor data: fit degree associated with the wearable article, or one or more positions of the first set of traces and the second set of traces that have exceeded a sensor data threshold; and at least in part on the determination, one or more user interface elements are presented at the user interface of the user device.

10. The system of claim 9, wherein the processor is configured to perform further operations, the further operations including: A heatmap is generated based at least in part on the first sensor data and the second set of data. The heatmap includes a digital model of the human body part during a time series corresponding to the first and second times. The heatmap also includes elements on a portion of the digital model indicating corresponding locations within the first and second sets of traces that have exceeded the sensor data threshold. The heatmap is included in one or more user interface elements of the user interface.

11. The system of claim 9, wherein the wearable article comprises one of the following: footwear, head covering, clothing, or gloves.

12. The system of claim 9, wherein the plurality of tensile sensors comprises at least one of the following: a capacitive sensor, a resistive sensor, and a piezoresistive sensor, and wherein the first sensor data value and the second sensor data value comprise one or more of the following: a resistance value detected by the resistive sensor, a capacitance value detected by the capacitive sensor, or a dielectric value detected by the piezoresistive sensor.

13. The system of claim 9, wherein the wearable article is a sock structure configured to be worn on a person's foot, and the sock structure is configured to be placed in a shoe, and wherein the plurality of stretch sensors include a capacitive sensor and a second sensor, and wherein determining the fit degree associated with the wearable article includes determining whether the person's foot fits the shoe based on deformation characteristics detected by the capacitive sensor on the inner portion of the shoe and by the second sensor on corresponding portions of the first set of traces and the second set of traces.

14. The system of claim 9, wherein determining the one or more locations within the first set of traces and the second set of traces that have exceeded the sensor data threshold comprises determining that corresponding portions of the first set of traces and the second set of traces have exceeded a pressure threshold, and wherein the one or more user interface elements include heat map elements indicating the corresponding portions that have exceeded the pressure threshold and other portions of the first set of traces and the second set of traces that have not exceeded the pressure threshold.

15. The system of claim 13, wherein the one or more user interface elements include recommendations for one or more shoes to be worn by the user based on capacitive sensor detection and second sensor detection.

16. The system of claim 9, wherein the processor is configured to perform further operations, the further operations including: A three-dimensional model of the human body part is generated, at least in part, based on the first sensor data and the second sensor data of the first set of traces and the second set of traces, during a time series corresponding to the first time and the second time, and wherein one or more user interface elements include the three-dimensional model of the human body part.

17. The system of claim 9, wherein the human body part is a foot, and wherein the processor is configured to perform further operations, the further operations including: The size or dimension of the foot is detected based on at least one of the first sensor data and the second sensor data, and wherein the one or more user interface elements include an indication of the size or dimension of the foot.

18. A wearable article comprising a plurality of stretch sensors, the plurality of stretch sensors including a first set of traces overlapping a second set of traces, each trace being configured to convert mechanical stimulation into one or more electrical signals, wherein the wearable article is configured to conform to a human body part. And a processor communicatively coupled to the plurality of tensile sensors, wherein the processor is configured to perform operations including: receiving first sensor data via the plurality of tensile sensors at a first time, the first sensor data indicating a first sensor value for each trace, wherein the wearable article is in a first position at the first time; At a second time following the first time, second sensor data is received via the plurality of stretch sensors, the second sensor data indicating a second sensor value for each trace, wherein the wearable article is in a second position at the second time; Based at least in part on the first sensor data and the second sensor data, determine one or more locations where the first set of traces and the second set of traces have exceeded the sensor data threshold; And based at least in part on the determination, one or more user interface elements are presented at the user interface of the user device.

19. The wearable article of claim 18, wherein the wearable article comprises one of the following: footwear, head covering, clothing, or gloves.

20. The wearable article of claim 18, wherein the plurality of stretch sensors comprises at least one of the following: a capacitive sensor, a resistive sensor, and a piezoresistive sensor, and wherein the first sensor data value and the second sensor data value comprise one or more of the following: a resistance value detected by the resistive sensor, a capacitance value detected by the capacitive sensor, or a dielectric value detected by the piezoresistive sensor.

Images