BE1024802B1 - SYSTEM INTEGRATION FOR DESIGN AND PRODUCTION OF CLOTHING - Google Patents

Abstract

Methods and systems for integrating the design, sales and production of garments are specifically described, especially for online ordering of garments, where the customer does not have to take the measurements in advance from a tailor, but the customer can gain access to online sales of high-quality, well-fitting garments via e-commerce platforms, portals and places of sale. The system and working methods can provide the customer with feedback regarding the fitting quality of stock, customized or e-bespoke clothing.

Description

(30) Priority data:

(73) Holder (s):

DOUËLOU NV 3500, HASSELT Belgium (72) Inventor (s):

SUPPLEMENT Michel 3550 ZOLDER Belgium (54) SYSTEM INTEGRATION FOR DESIGN AND PRODUCTION OF CLOTHING (57) Methods and Systems for integration of design, sale and production of garments especially described, especially for online ordering of garments, where the customer by a tailor does not Measurements need to be taken in advance, but the customer can access online sales of well-fitting, high-quality garments through e-commerce platforms, portals and places of sale. The system and practices can provide customer feedback regarding the fitting quality of stock, custom or e-bespoke clothing.

Fig. 1

BELGIAN INVENTION PATENT

FPS Economy, K.M.O., Self-employed & Energy

Publication number: 1024802 Filing number: BE2017 / 5607

Intellectual Property Office International Classification: G06Q 10/08 A41H 1/00 A41H 1/02 A41H 42/00 A41H 3/00 G06Q 30/06 G06Q 50/04 Date of Issue: 03/07/2018

The Minister of Economy,

Having regard to the Paris Convention of 20 March 1883 for the Protection of Industrial Property;

Having regard to the Law of March 28, 1984 on inventive patents, Article 22, for patent applications filed before September 22, 2014;

Having regard to Title 1 Invention Patents of Book XI of the Economic Law Code, Article XI.24, for patent applications filed from September 22, 2014;

Having regard to the Royal Decree of 2 December 1986 on the filing, granting and maintenance of inventive patents, Article 28;

Having regard to the application for an invention patent received by the Intellectual Property Office on 31/08/2017.

Whereas for patent applications that fall within the scope of Title 1, Book XI, of the Code of Economic Law (hereinafter WER), in accordance with Article XI.19, § 4, second paragraph, of the WER, the granted patent will be limited. to the patent claims for which the novelty search report was prepared, when the patent application is the subject of a novelty search report indicating a lack of unity of invention as referred to in paragraph 1, and when the applicant does not limit his filing and does not file a divisional application in accordance with the search report.

Decision:

Article 1

DOUËLOU NV, Kempische Steenweg 303, box 56, 3500 HASSELT Belgium;

represented by

BECK Michaël A.T., Technologielaan 9, 3001, HEVERLEE;

a Belgian invention patent with a term of 20 years, subject to payment of the annual fees as referred to in Article XI.48, § 1 of the Economic Law Code, for: SYSTEM INTEGRATION FOR DESIGN AND PRODUCTION OF CLOTHING.

INVENTOR (S):

PACKAGE Michel, Narcissenlaan 11, 3550, ATTIC;

PRIORITY:

BREAKDOWN:

Split from basic application: Filing date of the basic application:

Article 2. - This patent is granted without prior investigation into the patentability of the invention, without warranty of the Merit of the invention, nor of the accuracy of its description and at the risk of the applicant (s).

Brussels, 03/07/2018,

With special authorization:

BE2017 / 5607

SYSTEM INTEGRATION FOR CLOTHING DESIGN AND PRODUCTION

The present invention relates to methods of system integration of design, sale and production, especially of garments, as well as to the system itself, especially for online ordering of garments, where the customer does not have to take measurements beforehand, but it can access online sales of high quality, well-fitting garments through e-commerce platforms, portals and places of sale.

Background

Consumers are constantly asking for personalized products, for example purchased online and characterized by higher quality or greater functionality instead of standard, “ready-to-use” products. According to a recent study, the percentage of users for fashion products who have tried customer-specific online options is less than 10%. But 25% -30% of the total population is interested in trying it.

The 2017 final report on e-commerce competition investigations conducted by the European Commission states that 64% of responding manufacturers have opened their own online stores in the last 10 years. This means that currently, personalized online fashion is only available through small-scale web shops, which are not integrated with the major B2C (ecommerce) platforms, portals and places of sale and this is a limitation because it is does not allow the large mass of customers to have a good fit and tailoring for clothing purchased via the Internet. Additionally, one of the most frustrating issues with current online B2C platforms is that the menu filter search leads to unsuitable or unavailable Stock Keeping Units 75% of the time and usually no further product or size recommendations are provided to these 'frustrated' customers . For example, when searching / filtering in the category “shirts”, for a 5 cm shorter sleeve for a formal shirt, it may happen that only one shirt is proposed by the system; for an informal XL-shirt - 5 cm longer - tailored model - striped shirt, only 3 shirts are proposed, 2 of which have short sleeves. For a large & long XL shirt with lan§ | 201 7/5607 sleeves, it is said to be out of stock. A main reason for this is that, in order to meet specific customer requirements, suppliers have to make an increasingly fragmented offer for many different target groups. For example large & long, slim / custom / normal / super slim fit, petite / plus, alternative sleeve lengths (eg short / long / extra long / extra short) etc. In addition, there may be a variety of materials used, such as non-iron materials , synthetic fiber, silk or cotton materials, solid and yarn-dyed patterns, with stripes and the check patterns, collars of different shapes and all of these and each in a range of colors. This can easily lead to more than 1000 designs just for shirts.

To keep all these sizes, colors and materials in stock is not economically suitable.

The human form has intricate geometric shapes and presents difficulties in making textile products that fit well. The rate of return of online sales now reaches 50% in most cases and 70% in some cases. Usually "bespoke" tailors emphasize the need for relevant and correct measurements. For example, such measurements are for shirts:

Neck size: the measurement of the neck is taken for making collars and necklines for shirts. The measurement is taken randomly the neck from mid-front to mid-front, keeping a tape measure perpendicular to the neckline with no pulling or folding.

Shoulder: The measurement can be done in two ways: in one measurement, the length of the shoulder is measured by measuring from high shoulder point or neck point to shoulder point at the beginning of the arm. Another method id “crossback” measured from one shoulder point to the other at the back.

Armhole circumference: The armhole measurement is used for making sleeves. The arm hole (the opening in a shirt through which the arm should be allowed to pass) is measured by passing the tape measure under the armpit, starting at the shoulder tip and going round to finish at the starting point with no tensile or folding forces.

Bust or chest size: The measurement of the chest size is used for shirts, blouses, jackets etc .. The measuring tape is randomly let go of most of the chest, starting at the center front and ending there without pulling forces% | 2θ17 / 5607 fold.

Apex or bust point is the highest point or the top of the bust. The apex measurement is carried out to make filament charges. The measurement is taken from the high shoulder point at the neck to apex and the width of the apex is measured by measuring the distance between two apex points.

Front center: is a line that divides the front body into 2 equal halves. The mid front measurement is used to determine the neck depth. The measurement is taken from the pit of the neck at the center front to the waistline, ensuring that the tape measure is free of tensile forces or folds.

Center back: is a line that divides the back body into two equal halves. The mid back measurement is used to determine the neck depth. The measurement is taken from the pit of the neck at the center back to the waistline, ensuring that the tape measure is free of tensile forces or folds.

Side seam: is a line that divides the body into two parts on the side, i.e. front and back. The side seam measurement is used to determine the armhole depth. The measurement is performed from the armpit to the waistline, ensuring that the tape measure is free of tensile forces or folds.

Size of the waist or abdomen: the measurement of the waist is carried out for shirts, blouses, jackets etc. The waist is the narrowest part of the natural waist of the body.

The waist is measured with the person standing in a natural position without stomach retraction or while breathing normally by passing the tape measure over the curvature of the waist starting from the center front and ending there without any pulling or folding.

Hip measurement: the measurement of the hip measurement can be used for shirts, jackets etc. The measurement is carried out by passing the measuring tape over most of the hip, starting at the center front and ending there without pulling forces or folding.

Sleeve Length: The sleeve length measurement is taken from the top of the arm at shoulder point by measuring the length to the wrist or other desired sleeve length. Biceps Circumference: The biceps are measured for sleeves.

The measurement is performed around the upper arm at the largest point without tensile forces or folds.

Elbow Circumference: The elbow measurement is used for manufacturing 2017/5607 sleeves. The bent elbow is measured by randomly letting the tape measure go the elbow without tensile forces or folding.

Wrist size: The measurement of the pois is used for making sleeves. The tape measure is allowed to go randomly the pois without pulling or folding.

Experience shows that the average online customer cannot perform such measurements properly or does not wish to do so.

Usually “bespoke” tailors have:

a specialist experienced team direct consultation and measurement samples of garments readily available a large number of stock garments to choose from bespoke design and manufacturing service within the company customized service within the company.

Several of them are difficult to integrate into online shopping.

There are currently no system integrators for high quality personalized, ie “bespoke” fashion. The ICT system integrators currently serve only the mass production trade, applying the Made-to-stock (MTS) strategy, which allows brands and retailers to sell their stock products (online) enabled by existing software such as Hybris (SAP), Intershop, AmazonServices, Websphere (IBM), Magento, Prestashop, AmazonServices or Demandware.

Summary of the present invention

An object of embodiments of the present invention is to provide technical support for a creative industry and in particular the fashion industry by using digital processes under the control of the digital processors. The technical means are used for biometric sizing, product configuration, 3D product display and production integration using

APIs. Embodiments of the present invention allow all vendors 07/5607 and consumers to benefit from as-correct-as-technically-standardized fit as possible with means of accessing stock availability. An advantage consists of fewer returns and waste. Resources are provided for ICT integration.

Embodiments of the present invention use a first API to assist in biometric sizing and fit prediction. Means for predicting biometric dimensions and sizes are provided. Size charts, for example e-tailers (webshops), are used to determine fitting criteria in combination with a limited number of measurements performed by the customer. Decision making assistance is provided with regard to whether a standard or custom made or an esspoke product will be the best fit. The decision-making aid can be a derived fit quality value.

Embodiments of the present invention use an API for 3D15 configuration and display of stock garments as well as personalized biometrically tailored garments.

Embodiments of the present invention use an API for production integration, which allows automatic generation of CAD and CAM data sets.

Embodiments of the present invention can be configured as an API microservice architecture, with the APIs accessible for easy integration of new functionalities into existing platforms.

An aspect of the present invention is a method of producing stock and / or custom textile products, which are made of synthetic or natural fibers, characterized by the following steps:

receiving product design data including parameter values related to at least one first textile product and / or a limited set of biometric size data from a customer destined to wear at least one first textile product, the product design data being provided from a first software of a ccrS | 201T5607 seller, mapping these product design data with values from a second software from a textile product manufacturer, mapping by:

A first biometric size data and size prediction API based on a size chart, further comprising means for determining the extent to which the first textile product size matches the biometric size data and enabling input by the customer whether he is stock or custom made product or buy an e-bespoke product.

A second API can be used for 3D configuration of stock or custom or e-bespoke products to enable fully personalized biometrically tailored textile products as an option.

A third API for production integration of textile products with a production process can be provided. This API not only enables CRM and ERP, but also automatic generation of CAD data as well as CAM data to enable production.

The method may include the steps of:

- the receipt by a manufacturer of a digital design specification of a textile product from a design prediction unit through a wide area data network,

obtaining a virtual prototype of the textile product from a processing of the received design specification and

- obtaining a conversion of the virtual prototype to a format compatible with an additive and subtractive machining system,

obtaining a material from which the textile product is to be made, and

- obtaining by molding said textile product using the additive and subtractive treatment system.

The textile product can be selected from woven, knitted or non-woven product ^ ²⁰¹ 7/5607, for example, made from a material selected from natural fibers, synthetic polymer fibers, metal fibers or the like.

The step of obtaining by molding said textile product using the additive and subtractive processing system can be performed by any of the following methods, some of them or all of the following methods, depending on the material selected and the design: cutting, stitching, pleating, folding, sewing, gluing, welding.

The method may comprise the step of after-treatment of said textile product by ironing, starching, washing, pleating or the like.

Said processing step may also take into account any shrinkage of material due to the methods used during the production step.

Embodiments of the present invention provide a method of supplying stock or custom or e-bespoke textile products made from synthetic or natural fibers, comprising the following steps:

receiving a first set of a plurality of body size input variables being biometric size data from a customer to be provided with at least one first textile product, processing said first set of the plurality of body size input variables into a prediction model to predict a second set of at least 2, 4, 6, or 8 estimated body dimensions, each of said estimated body dimensions derived from two or more of said input variables, deriving a fit quality value for the first textile product, being any or all of a stock or custom and e-bespoke textile product as a function of the first set of the plurality of input variables related to body size, the second set of at least 2, 4, 6, or 8 estimated body sizes, rejecting any stock or tailor-made textile product, which does not comply (KS201 7/5607 to the fit quality value and if any stock or custom textile product does not meet the fit quality value, the customer receives this stock or custom textile product, or else the customer receives the e-bespoke product.

The first set of a plurality of body measurement input variables can be provided from a first software from a first vendor.

This first set can be mapped with a third set of values from a second software of the prediction model, mapping being accomplished by transferring the plurality of body size input variables through a first API.

The fit quality value can be derived for any or any of a stock or custom-made and e-bespoke textile product from a size prediction based on a size chart, and this allows a customer to make an entry as to whether a stock or custom or e-bespoke product is acceptable.

A 3D configuration for the stock, custom or e-bespoke product can be provided through a second API.

CAD data as well as CAM data for enabling production can be generated automatically via a third API for production integration of the customized or e-bespoke product with a production process from a manufacturer.

The manufacturer can receive a digital design specification of a textile product from a design unit through a wide area data network.

The received design specification can be processed to obtain a virtual prototype of the textile product.

The virtual prototype can be converted to a format compatible with 7/5607 system for additive subtractive editing,

A material can be obtained from which the textile product is to be manufactured, for example, the customer could specify a particular material, and the textile product can be obtained by molding using the additive and subtractive processing system.

The step of obtaining by molding said textile product using the additive and subtractive processing system can be carried out by one of the following methods, depending on the material selected: cutting, stitching, splitting, seaming ...

A post-treatment of said textile product by ironing, starching, washing, pressing etc. can be carried out.

The plurality of body size input variables can be selected from weight, height, size and additional age and gender input variables.

The second set of at least 2, 4, 6, or 8 approximate body measurements can be selected from BMI, chest circumference, waist circumference, arm circumference, wrist circumference, shoulder length, arm length, back length, and waist or waist circumference.

The customer can be provided with a representation of the virtual prototype displayed in three dimensions.

The customer may be provided with a representation of a virtual person in accordance with said estimated body dimensions wearing the textile product, said virtual person being displayed in three dimensions (3D).

Another aspect of the present invention is a computer-based system for supplying stock or custom or e-bespoke textile products made from synthetic or natural fibers, comprising:

BE2017 / 5607 means for receiving a first set of a plurality of input variables related to body size, being biometric size data from a customer to be provided with at least one first textile product, means for processing said first set of the plurality of body size input variables in a prediction model to predict a second set of at least 2, 4, 6 or 8 estimated body dimensions, each of said estimated body dimensions derived from two or more of said input variables, means for deriving a fit quality value for the first textile product being any of a stock or custom made and e-bespoke textile product as a function of the first set of the plurality of input variables related to body size, the second set of at least 2, 4, 6 or 8 estimated body measurements, means for rejecting and any stock or custom textile product that does not meet the fit quality value, and if any stock or custom textile product does not meet the fit quality value, resources are provided to the customer to receive this stock or custom textile product , while otherwise the customer receives the e-bespoke product.

Another aspect of the present invention is a computer-based system for supplying stock or custom or e-bespoke textile products made from synthetic or natural fibers, comprising:

means for receiving product design data comprising parameter values with respect to at least one textile product and or biometric dimension data from a customer destined for the at least one first textile product, the product design data being provided from a first software of a first product. 7/5607 means for mapping this product data with values from a second software of a textile product prediction system, the means for mapping comprising a first API for biometric size data and size prediction based on a size chart, further comprising means for determining how good the textile product matches the biometric size data and means for allowing a customer to enter whether to purchase a stock or custom or e-bespoke product.

Additional embodiments of the present invention are detailed in the appended claims.

Embodiments of the present invention may utilize an apparatus for the production of made-to-measure clothing or e-bespoke, comprising a controller controlled by a processor and operatively connected to a non-volatile memory and an input means, said input means adapted to provide said control unit input variables personally for a particular customer and said control unit is adapted to process said input variables to provide a range of at least estimated body dimensions, each of the body dimensions derived from one or more of said input variables and used to derive clothing pattern data, wherein one of said input variables includes a display of the age of said customer. The age can be any number of years, but can be any suitable representation, such as the date of birth. These data do not have to be entered by the customer, but could be input from other means, for example the age can be obtained from a delivered date of birth or electronically stored medical records.

Said input variables may further include an input of one or more of said customer's weight, length, collar width, sleeve length and waist, or all of these.

Said predicted body measurements may include at least one, some or all of v @ {j2017 / 5607 (e.g. 2, 4, 6 or 8 of) BMI, chest size, waist size, arm size, shoulder length, arm length and back length (B: BMI, CC: chest size, WC: waist size,

AC: arm circumference, WR: wrist circumference, SL: shoulder length, AL: arm length and BL: back length and optioned also include the BC: abdomen or waist circumference) and any other sizes, which are required for the manufacture of upholstery.

Said body measurements can be predicted by reference to a plurality of said input variables and a series of prediction rules applied in combination with said controller under control of the processor.

Said prediction rules may associate said input variables with customer body measurements unknown to said controller and generate said estimated body measurements for use in place of said unknown body measurements.

Said prediction rules may include the use of a regression technique, preferably a multiple linear regression technique.

Said prediction rules can be derived from a database of body measurements of a population sample, said sample preferably being composed of at least twenty times more cases than there are variables to be entered and body measurements to be predicted.

Said prediction rules may be changeable between at least two applications thereof to reflect, for example, changes in said sample over time, between target markets or between geographic areas. A said set of prediction rules can be generated each time an order is placed or each time a reference database of sample body measurements is changed.

Said tailored or e-bespoke clothing may include a shirt or may include a blouse or jacket.

BE2017 / 5607

Said made-to-measure or e-bespoke clothing may include pants, and said input variables may include, for example, one or more of foot size, shoe size, inseam and hem size. In at least this case, said made-to-order or e-bespoke clothing may further comprise a jacket and optionally a vest, in combination with said pants, for example to form a suit.

Said customer may enter an order regarding the structure of at least part of said clothing, such as, for example, a type of material, color, shape or fit, collar, cuff or sleeve design, said order preferably being by said customer changed when assessing a predicted or simulated finished piece of said apparel.

Said input means may comprise an input platform using at least one of a wide area network (WAN), a local area network (LAN), a mobile telecommunication network, an ordering process via the Internet and an interactive mail ordering process, for example carried out interactively by said customer in response to vendor prompts.

The apparatus may further comprise a garment manufacturing facility adapted to receive said control unit from said pattern data and to produce said custom or e-bespoke garments therefrom.

The device may further include a billing and distribution device for billing to customers and transportation to them of said made-to-order or e-bespoke clothing.

Said customer may be provided with a display of said stock, made-to-order or e-bespoke clothing, said virtual display preferably being displayed in three dimensions and movable to show how said clothing could see emit from different angles or viewpoints. Said customer may be provided with a representation of a virtual person, preferably representative of their body shapes in accordance with said estimated body measurements, including a piece of said stock, made-to-order or e-bespoke clothing in accordance with 7 / 5607 carries said pattern data, said virtual person preferably being presented in three dimensions and preferably movable to show by way of overview how said clothing might look emit in use. Said display may be available to customers in a variety of different poses and backgrounds, such as, for example, simulations of poses or movement in urban and rural environments, preferably with the possibility of the accompanying virtual figures being contained therein. Said display may be available to said customer, clothing being worn in addition to said made-to-order or e-bespoke clothing, such as for example in a case where said made-to-order clothing comprises a shirt, said additional clothing comprising a choice of pants, whereby named customer can review said made-to-order clothing in tai of combinations and styles with full dress. The 3D configuration can be provided through an API.

Embodiments of the present invention also provide an apparatus for the production of made-to-measure clothing, comprising a controller operatively connected to a non-volatile memory and an input means, said input means being adapted to provide said control unit with input variables which are personal to a particular customer and said control unit is adapted to process said input variables to predict a range of at least estimated body sizes, each of said body sizes derived from one or more of said input variables and used to display garment pattern data lead, said input variables include only said customer's age, weight, height and gauge.

Embodiments of the present invention also provide an information carrier, such as a CD-ROM, on which at least one program is encoded to enable implementation of an apparatus according to the invention.

For example, said program may include at least one of a website interface, a database of clothing options or dimension information, a web browser, an order / billing system and an image program, to allow display of an image of said made-to-order clothing, include.

BE2017 / 5607

Embodiments of the present invention also provide a method of producing tailor-made clothing, comprising: a) entering into a controller individual input variables for a particular customer, one of said input variables representing the age of said customer b) processing said input variables; and c) predicting a range of at least estimated body measurements from said processing, wherein each of said body measurements is derived from one or more of said input variables and is used in the derivation of clothing pattern data.

Embodiments of the present invention may also provide an apparatus in which a record is made, in, for example, a database, of feedback from orders placed using the invention.

This feedback may take the form of warranty return information or customer feedback and may include either positive and negative results or both. Said record can also be used to record cases where it proves difficult or impossible to satisfy a customer, through which the information thus collected could also be used to a supplier of tailor-made garments produced using protect the invention from customers who are difficult to satisfy, for example, by setting a record of customers who, for whatever reason, usually return goods.

Brief description of the drawings

The present invention will now be described by way of example only and with reference to the accompanying drawings, in which figures:

Figure 1 is a schematic diagram of an apparatus according to an embodiment of the present invention.

Figures 2-5 are graphical representations of information used in the development of the device of Figure 1.

Figures 6 and 7 are additional schematic diagrams of an apparatus according to additional embodiments of the present invention.

BE2017 / 5607

Definitions

1. “Off The Rack” (ready-to-wear) or “Ready To Wear” (ready-to-wear) = stock items ready-to-wear = stock items are factory-finished and standardized sizes and have a wide range of quality standards depending on the manufacturer.

2. "Tailor-made"

Clothing products produced to order from a set block pattern. Usually, a paper pattern is not constructed, instead existing patterns matching those needed are collected and put together. It is distinguished from bespoke in the sense that new patterns are not created. All records can be held for future orders.

3. “e-Bespoke” e-Bespoke clothing refers to using individually cut paper cartridges instead of reusing existing ones.

e-Bespoke clothing can be made from a wide selection of fabrics, styles and accessories.

Preferably, all records are held for future orders.

Description of the illustrative embodiments

Embodiments of the present invention pertain to mainstream fashion, increasing current product diversity by integrating technology related to biometric dimension data and size prediction in multi-channel ecommerce platforms & webshops from manufacturers, e-retailers, emails, sales places , outlets and portals, where options related to customization are embedded in the e-commerce platform software.

Embodiments of the present invention utilize ICT system integration technology, which enables consumers to purchase inline, for example, via the Internet, stock17 items, custom or e-bespoke fashion anywhere, both online alsoifi ^ OI 7/5607 multi-channel, and, for example, from their preferred high volume brands, enabling a seamless flow of information. Embodiments of the present invention provide central access points and avoid a long login process to access the different websites where each platform module is developed. While consumer interest is high, the technical barriers to providing mainstream custom clothing remain a challenge. Embodiments of the present invention utilize an API platform, which will benefit consumers of standardized stock products, while also being able to receive a good fit with technology currently only available in the sub-segment of tailor-made and personalized clothing. Consumers are given the advantage of a standardized fit that is as correct as technically possible. This approach will have a strong impact on the sector that bridges the gap to the right size and allows for the necessary step towards little or hopefully no waste in the fashion sector, specifically improving the rate of return after online sales (which now reaches an unacceptable 50% in most cases and 70% in some cases). Improvement has not been possible due to the lack of technical means. Embodiments of the present invention implement more complex types of garments using biometric sizing (such as shirts, blouses, jackets, etc.), further comprising a sizing prediction for each garment, for example, top and bottom, shirts and pants, respectively, while also stocking online and online tailored and e-bespoke garments are provided as alternatives. Embodiments of the present invention provide a system integration of various APIs. Embodiments of the present invention utilize web platform operations specific to the online bespoke or e Bespoke textile products. In embodiments of the present invention, a manufacturer of online custom textile products or online e-bespoke textile products is integrated into a collaborative API environment. Embodiments of the present invention can achieve currently unavailable degrees of customer satisfaction and waste reduction by ensuring a near-perfect fit for online standardized (e.g., stock) products, online custom or e-bespoke products, eliminating the problem with standardized matxfffj ^ OI 7/5607 which differ between countries with a degree of> 25%.

API means Application Programming Interface and is used to integrate various software applications. A UI (User Interface) is used by a user to interact with the software and tell them what actions to perform, but if one software application is to interact with another, an API can be used . Embodiments of the present invention use parameters to design garments, and also the garments can be designed and manufactured with these parameters. If a multichannel system is to be used, there must be a way for dissimilar systems to communicate with each other. Let's assume that information regarding biometric data to be entered by a customer and stored in a first non-volatile memory under the control of a first processor running Software A must be transferred to another institution and stored in a second non-volatile memory under the control of a second processor running Software B is stored. Since Software B comes from a different vendor, it is very unlikely that the two applications have exactly the same areas and / or that they interpret them in the same way. Therefore, in order to accomplish this integration one must: (a) have a way to get / place the data of A easily and programmably, (b) have a way to get / place the data of B easily, (c ) have a small program in the middle to call A to get the data, set it up as needed and put it in B. A first API program, running on A, will read what is in A (in the particular context that it is stored in A in the first non-volatile memory), transfer it to B and then a second API program running on B enter the second non-volatile memory in B (in the manner that B expects the data to be entered). This is a process called Data Mapping. To accomplish this through APIs (assuming that both A and B and their respective applications have and support APIs), one would use the first API in A to get the data and then the second API in B to get the translate data and write the data in B based on the mapping:

BE2017 / 5607

1) Obtain data from A.

2) Set Software B parameter values equal to Software A parameter values

3) Place data in B

Once these translation programs are written, the two software applications will maintain communication. An important advantage of the API approach is that, because a small application-oriented program is written, it has the ability to validate and clean the data from source software A before it is placed in destination software B, causing the general problem of processing bad data is solved. Finally, the API approach also allows any software to communicate with another software, not just the one or two applications the vendor wants to support. This includes software that did not exist when the application was developed.

Therefore, APIs can be used to allow software from one company, such as large B2C (e-commerce) platforms, portals and places of sale, such as Amazon, to communicate with software from another webshop on a small scale. This is important from a technical point of view as the specification data for the manufacture of clothing must be exact. APIs can be used in embodiments of the present invention to collect data from customers shopping through the major B2C (ecommerciej platforms, portals and places of sales to transmit definitions of 3D objects such that they can be viewed by the customer, collect data related to pattern designs, collect data related to inventories, production schedules, provide data for invoicing and billing, etc.

Some APIs that are embodiments of the present invention are:

One or more APIs 22, 26 for transferring biometric dimensions and for size prediction: based on a size table of e-tailers, a customer will have the opportunity to know in advance to what extent a certain size fits his / her own measurements and decide to buy a standard or custom or e-bespoke product.

An API 24 for 3D configuration for custom or e-bespoke products. This ^ iS ² ^ 7/5607 is a technical solution for resellers (e-tailers) of high volume stock to open their platforms to fully customized, biometrically tailored garments as an additional service on their existing platforms, without the necessity of redeveloping already existing implementations. This allows the data required for 3D imaging to be transmitted to the seller's website and / or to a customer for 3D display.

One or more APIs 28, 29 for production integration. This is a technical solution for seamless integration of the design and configuration results for the customized or e-bespoke products with a production process, for example to automatic generation of CAD as well as CAM to enable production.

A microservice API architecture 30 being a total platform, either centralized or distributed with APIs 22, 24, 26, 28, 29 to be accessible to software developers for easy integration of new functionalities into existing platforms (see Figure 6). The microservice can be centralized, localized or distributed.

The API environment of the microservice 30 allows third-party developers to add value to the fashion chain. In addition, embodiments of the present invention exploit historical information regarding sizing (of the products themselves), biometric information (sizing of the customers), configuration systems for online tailor-made products and e-bespoke products, body mass index evaluation system etc. to develop an API SDK (Software Development Kit) for creating a library of interfaces, through which third-party developers can enable fashion producers and consumers to take full advantage of the reduction of ensure time-consuming shopping experiences and better shopping experience at the endpoints.

Embodiments of the present invention provide support to customers during online sales even when: i) personal sense of fit and style of the customer is subjective with increasing variability; (ii) garment collection areas and / or brand sizes under different collections are not the same, causing major problems when choosing the size.

Embodiments of the present invention may be based on the definition of a microservice architecture 30 (see Figures 1, 6 and 7) to integrate new functionalities in the web shop of large e-tailers 32-35, regardless of the platform where they are developed, which overcomes the problem of proprietary software. Embodiments of the present invention provide a configuration and sales process once a sizing predictor 40 has defined the best fit for the particular customer. The system can then check, using ERP and CRM APIs 29, whether the item is in stock at the e-tailer, otherwise the system suggests transferring to a manufacturer a custom textile or e-bespoke product. , for example, using biometric sizing and predicting results from the predictor 40. Embodiments of the present invention utilize ICT technologies in the areas of sizing, product configuration, custom and / or e-bespoke products, and industrialization (i.e., manufacturing) for providing innovative products and services with high commercial potential in a creative industry. Embodiments of the present invention utilize extensive data and semantics for analysis, updating real-time data regarding sizing and biometric formulas with resulting upgraded size chart recommendations. Embodiments of the present invention allow manufacture of standard fashion (MTS) and custom (MtM) and e-bespoke products in a single platform. Embodiments of the present invention allow for the purchase of fashion brands on major e-commerce portals / websites and platforms 32-35 and introduce multi-channel ecommerce (see Figure 6) for standard fashion products (MTS) and tailor-made (MtM) and e-bespoke fashion products using existing platforms 3235.

Embodiments of the present invention use an API 22 for biometric measure prediction. The API 22 allows a limited set of biometric data to be entered on a seller's website 32-35 and this data to be transferred to a size prediction service 40. The size prediction service 40 can input biometric data into a size prediction mode (Rff2017 / 5607).

With reference to Figures 1-7, a custom clothing manufacturing and distribution apparatus comprises an input stage performed by a customer using an interactive interface 10 under the control of a first processor 11, which is online, for example, internet or implement mail order-based scheme by communicating over the Internet with a web server 12, which, under the control of a second processor 12, is an e-commerce portal / website or platform 32 of a stock and / or custom order and / or e-bespoke, billing and distribution terms provided. The e-commerce portal / website or platform terms may be present in various locations in different countries such as Amazion.de, Amazon.us, Amazon.uk etc.

A user of the interface 10 responds to prompts for information and input variables comprising personal information for a particular customer before ordering an item of stock or custom or e-bespoke clothing. In this embodiment, the item of clothing assumed to be ordered is a shirt or blouse 18, for which the input variables provided are the customer's gender (female or male) G, age A, weight W, height H, and cuff width C, wherein the width of the board in the art is also interchangeably referred to as neck circumference.

At this stage, the customer also enters, under the control of the first processor 11, an order regarding his choice of the structure of at least a portion of the clothing being ordered, such as, for example, a type of material, color, shape or fit, collar, cuff or sleeve design.

The web server 12, under the control of a second processor 13, captures the customer-specific input variables and choices and stores them in a first non-volatile memory 15. Using an API system 22 for biometric measurement and size prediction, the customer-specific input variables and choices with any necessary translation, addition, reduction, or correction passed to a control unit 14 of a forecast service provider 30, which selects the customer's choices and input variables G, A, W, H, C in a second non-volatile memory (17) storing on <SSU ^{201 7/5607} the control of a third processor 19 in accordance with a set of rules in a predictor model and processes it.

By applying this set of rules, the controller 14, under the control of the processor 19 and using information stored in non-volatile memory 17, predicts a set of body measurements, which are an estimate of the customer's unknown body measurements. The predicted body measurements include B: BMI, CC: chest circumference, WC: waist circumference, AC: arm circumference, WR: wrist circumference, SL: shoulder length, AL: arm length and BL: back length and optionally also BC: abdomen or waist circumference and any other measurements required to manufacture the clothing.

The controller 14, under the control of the processor 19, can then convert the full set of body measurements into a set of garment pattern data 25. At this stage, under the control of the processor 19, the customer may be provided with a representation 20 of a prototype virtual garment displayed to the customer under the control of the processor 11 in accordance with the model selected by the customer. The prototype virtual clothing representation 20 may preferably be interactively updated with regard to its characteristics to simultaneously reflect changes that could take place in the customer's choices regarding structure and options. It is preferably displayed in three dimensions under the control of the processor 11 and is movable to be viewed from different points of view.

The virtual representation 20 can be extended to provide a virtual person, preferably representative of the customer's predicted body shapes according to the estimated body measurements, which person wears the stock clothing chosen according to the customer's choices . The virtual person is preferably displayed, under the control of the processor 11, in three dimensions (3D) and is preferably movable in order to show what the clothing might look like during use. Such virtual representations are known in the art and a suitable example of this technology can be found in EP0933728. Such a 3D configuration can be embedded in an e-commerce multichannel platform, which offers Confirmation-Sizing-Manufacturing as a service. A

API 24 may allow the advantage of, for example, proprietary 3D configurators to provide details of 3D representations through the use of plugins 36, for example supported by the platform's web services. The customer has the option to reject unwanted clothing, which reduces costs and returns. As explained below, this makes it possible to offer not only current high volume stock products, but also for the customer to choose fully customized biometrically tailored garments as an evolutionary advantage on the existing platforms if the customer is not satisfied with the stock product, without the need to re-develop already existing implementations. This is already made available at the offer stage, thus reducing the supply of badly fitting clothing and reducing the degree of return.

The virtual representation 20 may be available to the customer, under the control of the processor 11, in a variety of different poses and backgrounds, such as, for example, simulations of posing or moving in urban and rural environments, preferably with the possibility of additional virtual figures are present. It may also be of service to the customer, under the control of processor 11, to wear clothing next to the made-to-order shirt 18, such as, for example, a choice of pants. In this way, the customer can judge the shirt in a variety of backgrounds, combinations and styles when fully dressed. At this stage, the customer can change their choices of style or even fit, for example by requesting a looser fit. Once such choices and changes have been processed in the simulation, the customer may be requested to confirm or reject the order.

The controller 14, under the control of the processor 19, then examines whether the shirt 18 can be delivered from stock, or can be supplied as a custom over an e-bespoke shirt. The controller 14, under the control of the processor 19, includes the array of body data such as A, W, H, C, B, CC, WC, AC, WR, SL, AL and BL and also optioned the BC and optioned any other sizes used to manufacture the stock apparel depending on whether the customer is either male or female, as well as any choices made available by the customer for the stock products offered by the e-commerce portal / website or platform with the predicted values of body data such as A, W, H, C, B, CC, WC, AC, WR, SL, AL and

BL and optionally also the BC prepared by the control unit 14. This equation also uses woßfi ^ OI 7/5607 to see if the stock product is good enough and the values generated by the control unit 14, under the control of the processor 19, are used as a reference. To do this, standard stock size charts 38 and pattern blocks can be used to obtain the necessary data for this comparison. This data, which includes the size tables 38, can be obtained by an API 26 between the controller 14 of the e-commerce portal / website or platform 32-35 if that data is stored there. For example, British standard BS3666 has established the sizing system for the British clothing industry. All shops or vendors selling garments or manufacturers of garments for the UK market adhere to BS3666. The measure with suffix S or T indicates whether it applies to a small or tall person.

The equation can be used to generate an incorrect or "mismatched" estimate, which may be a function of the differences between the predicted values and the stock measure values, depending on whether the customer is either male or female that is, that is

E = / (AA, AW, ΔΗ, AC, ΔΒ, ACC, AWC, AAC, AWR, ASL, AAL, ABL and optional ABC) where E is an incorrect estimate and Δ refers to a difference between the predicted values and the biometric dimensions used for the stock sizes. An example would be a simple total of the absolute values of the deviations for either male or female:

E = wi | AA | + W2 | AW | + W3 | AH | + W4 | AC | + w ₅ | AB | + wô | ACC | + w ₇ | AWC | + wg | AAC | wpA | WR | + wio | AS | wn | AAL | + wi2 | ABL | and optional + wi3 | AB |.

where w _{n is} a weighting. The weight may be higher if the measured value of any of the differences is negative, since a garment, which is small, is a bigger problem than a little more space in a garment.

Instead of obtaining the relevant stock sizes from the sellers, alternatively the values for a female or male customer from A, W, H, C, B, CC,

WC, AC, WR, SL, AL and BL and optionally BC are available from the manufacturers of the stock article 7/5607, which are supplied to the e-commerce portal / website or platform 32-35. If the stock products are also designed by the forecast service provider and / or are manufactured according to these designs by a third party, the details for the control unit 14 will then be made available.

Instead of E or a function of E, the inverse of E (1 / E) can be used as a measure of how good a fit is. Whether E or an inverse of E is used, the result is a fit quality value. The present invention includes a function that provides a fit quality value, such as E, 1 / E, E, 1 / E.

If a stock item cannot be recommended due to the fit quality value, for example when E exceeds a threshold value, in that case the control unit 14 under the control of the professor 19 examines the custom products that can be manufactured with existing patterns from a manufacturer 16 If there are existing patterns that are suitable, the controller 14, under the control of the processor 19, changes the full set of body measurements and the known pattern data into a set of garment pattern data 25. The known patterns can be obtained by API 28. The customer can , under the control of the processor 19, optionally be provided with a second representation 20 of a prototype virtual garment displayed under the control of the processor 11 in accordance with the model selected by the customer and as manufactured with standard patterns. As before, the prototype virtual apparel representation 20 can preferably be interactively updated with regard to its characteristics to reflect simultaneously changes that could take place in the customer's choices regarding structure and options. It is preferably presented under the control of the processor 11 in three dimensions and is movable to be viewed from different points of view.

The virtual representation 20 may be extended to provide a virtual person, preferably representing the predicted body shape of the customer in accordance with the estimated body measurements, which person wears the made-to-order clothing chosen in accordance with the pattern data generated by the control unit 14. The virtual person is preferably presented, under the control of the processor 11, in three dimensions (3D) and is preferably movable in order to show, as an overview, how the clothing might emit. See 7/5607 when used. Such virtual representations are known in the art and a suitable example of this technology can be found in EP0933728.

The virtual representation 20 can be made available to the customer, under the control of the processor 11, in a variety of different poses and backgrounds, such as, for example, simulations of positioning or movement in urban and rural environments, preferably with the option of being present are of additional virtual figures. It may also be made available to the customer, under the control of the processor 11, while this person wears clothing in addition to the made-to-order shirt 18, such as, for example, a choice of pants. In this way, the customer can judge the shirt in various styles, combinations and styles when fully dressed. At this stage, the customer can change their choices of style or even fit, for example by requesting a looser fit. Once such choices and changes have been factored into the simulation, the customer can be moved to confirm that the new prototype is preferred or rejected.

As previously described, a fit quality value such as E, which represents a flaw or wrong fit, can be calculated for the custom article by any of the methods indicated above. The incorrect or “mismatched” estimate may be a function of the differences between the predicted values and the measure values relevant to the tailoring, depending on whether the customer is either male or female, ie

E = / (AA, AW, ΔΗ, AC, ΔΒ, ACC, AWC, AAC, AWR, ASL, AAL, ABL and optioned ABC) where E is an incorrect estimate and Δ refers to a difference between the predicted values and the biometric dimensions used for the stock sizes. An example would be a simple total of the absolute values of the deviations for either male or female:

E = wi | AA | + W2 | AW | + W3 | AH | + WzJACI + w ₅ | AB | + wô | ACC | + w ₇ | AWC | + wg | AAC | wpAlWRj + wio | AS | wn | AAL | + wi2 | ABL | and optionee! + wi3 | AB |.

where w _{n is} a weighting. The weight may be higher if the measured value of the differences of the differences is negative, since a garment which is too small is a bigger problem than a little more space in a garment.

If a custom item cannot be recommended due to the fit quality value, for example when E exceeds a threshold value, in that case the control unit 14 under the control of the professor 19 examines the e Bespoke products that can be manufactured with new cartridges or a combination of new ones. and existing patterns from a manufacturer 16. Any rules or size data regarding how to design new patterns can be obtained from the manufacturer 16 through API 28. In this case, the controller 14, under the control of the processor 19, changes the full body size range into a sequence of new garment pattern data 25 or a combination of new and existing garment pattern data 25. Under the control of the processor 19, the customer may, be provided with a third representation 20 of a prototype virtual garment displayed under the control of the processor 11 in accordance with the model chosen by the customer and as manufactured with new patterns. As before, the prototype virtual apparel representation 20 can preferably be interactively updated with regard to its characteristics to reflect simultaneously changes that could take place in the customer's choices regarding structure and options. It is preferably presented under the control of the processor 11 in three dimensions and movable to be viewed from different points of view.

The virtual representation 20 may be extended to provide a virtual person, preferably representing the predicted body shape of the customer in accordance with the estimated body measurements, which person wears the made-to-order clothing chosen in accordance with the pattern data generated by the control unit 14. The virtual person is preferably presented, under the control of the processor 11, in three dimensions (3D) and is preferably movable to show, by way of overview, how the clothing might look emit in use. Such virtual representations are known in the art and a suitable example of this technology can be found in EP0933728.

The virtual representation 20 can be made available to the customer, under control of the processor 11, in a variety of different poses and backgrounds, such as, for example, simulations of positioning or movement in urban and rural environments, preferably with the option of of the presence of additional virtual figures. It may also be made available to the customer, under the control of the processor 11, while this person wears clothing in addition to the made-to-order shirt 18, such as, for example, a choice of pants. In this way, the customer can judge the shirt in many different backgrounds, combinations and styles when fully dressed. At this stage, the customer can change their choices of style or even fit, for example by requesting a looser fit. Once such choices and changes have been factored into the simulation, the customer can be moved to confirm that the new prototype is preferred or rejected.

If an order is confirmed and preferably meets the fit quality value, such as when the error requirement E is less than a threshold value, the customer is allowed to go through an online billing schedule. It will be understood, of course, that customer accounts, credit cards and other similar systems can be used for billing and provided to the e-commerce portaaE website or platform through back office APIs 29 for Enterprise resource planning (ERP) and Customer relationship management (CRM). ERP is the integrated management of core business processes, often in real time and mediated by software and technology.

These business activities may include product planning, purchase production planning, manufacture or service, marketing and sales, materials management, inventory management, transportation and payment, and finance.

CRM compiles data from a range of different communication channels, including a company-specific website, telephone, email, live chat, marketing materials, and social media. By facilitating the CRM approach and the Systems used, things learn more about their customers and partners and how to best meet their needs.

If a stock item is to be delivered, the ecommerce portal / website or platform is instructed to deliver it.

If a custom or e-bespoke item is selected, once 1/2017/5607 billing has been processed, the garment pattern data 25 is sent to a garment manufacturing facility 16, for example, via API 28. This may include a computer-aided manufacturing company 16, which selects the material under the control of the processor 27 from the passed choices (e.g., via API 28) from the non-volatile memory 17 of the controller 14.3 which is the customer input / change save. The computer aided manufacturing company 16, under the control of the processor 27, cuts the material or materials according to pattern data 25 for the ordering customer. The cut material is then put together and finished.

Company 16 output is a shirt 18 made to order for the specific customer and then sent to a distribution center (not shown separately) and then shipped to the customer.

More detailed consideration will now be given regarding the development and application of the prediction rules and the significance of the particular requested input variables as set forth in WO0235952, which is hereby incorporated in its entirety.

The fundamental consideration on which the calculation of the rules is based is that, in a given population, there is some correlation between certain body measurements. For example, there is a proven correlation between body height and arm length. Another fundamental consideration is that there is some correlation between age and certain body measurements such as height or waist size. The identification of correlation between known variables, for example the input variables A, W, H, C for a male or female person and the unknown predictable body measurements B, CC, WC, AC, WR,

SL, AL and BL and optionally also the BC for a male or female person allows the construction of a prediction model and its use for the purpose of its estimation.

With reference to Figure 2, it can be seen that an estimate of the breast size using only one particular input variable is rather inaccurate.

In this case, the input variable is the border width C and the body measurements represent a sample of potential customers. Chest circumference is plotted against collar width C / neck circumference and a “good fit zone” is developed at random a best-fit line across the population. The graph represents the principle of a basic ready-to-use sizing system in industry. In this system, it is believed that chest circumference is proportional to neck circumference, which can be seen to some extent true, but can leave many potential customers with fitting problems and is not accurate enough for tailored clothing.

Figure 3 shows an estimate of the chest size, where two personal measurements, weight and height plotted on the x-axis in the form of the square root of (weight / height) are known. In this graph, we insert two body measurements instead of one to estimate the chest circumference. It can be seen that the correlation between available data and the estimate is clearer. Fewer potential customers are left with fitting problems.

From Figures 2 and 3 it can be seen that increasing the number of input variables increases the accuracy of estimated body measurements and it is believed that those chosen in the present invention produce a good compromise between accuracy and ease of use for customers. The requested input variables are often known by heart or at least easily determined without specialist help. In Figure 4, it can be seen that the effects of including age A in a prediction rule improve the results of the prediction of Figure 3.

After choosing the input variables A, W, H, C, the next step in developing the present invention is to build the prediction model and associated rules and the value of B, CC, WC, AC, WR, SF, AF and BF and optionally also the BC depending on whether the customer is a male person or a female person.

The prediction model is based on regression techniques. Such regression techniques aim to establish mathematical relationships between predictor target variables, thereby collecting a significant sample of cases. The relationships are formalized as functions that describe how one dependent variable responds when an independent variable is changed.

The functions chosen are those that best describe the relationship between variables on average.

Of course, the functions only approximate the average behavior of the population ^ 2017/5607, although the forecast is generally satisfactory in most cases, an error can often be noticed when comparing the forecast with the actual value. The functions selected are those that minimize the absolute error between actual sample values and values calculated using the regression function. The techniques should be “multiple regression”, because it is necessary to process several variables, for example four independent variables (age A, weight W, height H and width C) and several dependent variables, ie the predicted body measurements of chest size , waist circumference, arm circumference, wrist circumference, shoulder length, arm length; back length plus optional abdominal girth (e.g. B, CC, WC, AC, WR, SL, AL and BL and optionally also the BC for a male or female person).

Many multiple regression techniques would provide close results in the present application. However, a linear multiple regression generally gives robust models and should preferably be chosen if the relationships between variables are generally linear. In order to say whether the relationship is linear or not, it is appropriate to use standard statistical software packages available commercially, such as SAS, SPSS, STATISTICA or others, which provide interactive graphical exploration of data facilities. In the case of the present invention, the software used was WINIDAMS. Using this software, obtaining the relationships between couples of variables gives graphs similar to those shown in Figure 5.

On these graphs the dependent variables are plotted against the independent variables. Obviously, while these graphs are very useful, they provide only a partial overview of population behavior, since they are only two-dimensional. In fact, we are interested in the multidimensional relationships between independent and dependent variables. In Figure 5, it can be seen in some cases that there are linear relationships (arm circumference to weight), non-linear relationships (arm circumference to age, looking like banana) and some fairly undefined bandages (wrist circumference to body length, which is a very inaccurate correlation or none at all). correlation) appear to be.

BE2017 / 5607

In order to convert non-linear relationships into linear relationships, it is necessary to introduce some variable changes. It can be seen that all dressings seemed to belong to the linear or undefined type, except when age A was included. This makes sense, as some body measurements may increase with age up to a certain number of years and then decrease with age. For example, height and related body measurements such as leg length often fall into this category. For example, to handle a curve-shaped relationship, such as that between arm size and age, the prediction rules introduce age squared as a dependent variable. This allows the approximation of the curve by a second degree polynomial curve.

Some other relationships can also be found to be non-linear. By assuming that there is an analogy between body parts such as the chest or arm and a cylinder, it is possible to identify the relationship between body size in size and the information given in weight and height.

v ~ => r Jl ^1iz - (v / h) ^1ß

C = 2i1r “> c = 2ff ^ß fv / b) ¹ⁱ² c proportional to (vZh) ^1ia and if it is assumed that w is proportional to v, then we have:

1/2 c proportional to (w / h)

1/2

As a result, (w / h) is entered into the model as an additional independent variable.

At the end of this step, we are left with a series of independent variables that are gender-dependent: age, weight, height, collar width / neck circumference, age squared, square root of weight divided by square root of height. It is likely that these variables will fit the multiple linear regression model.

The next step, then, is to formalize the relationships between variables by means of a series of equations. This step is the actual “modeling” step, in which all parameters of the regression are established and the prediction rules are made final. Again, an application-specific statistical package is useful here, such as WINIDAMS, which preferably characterizes a stepwise regression application.

Developing stepwise regression provides for the simultaneous identification of the relationships between variables (i.e. to obtain a series of equations / prediction rules) and to check the significance of the enhancement that each independent variable adds to the model. In other words, if the standard error of the prediction does not decrease significantly by using a particular independent variable, this variable can be discarded.

At the end of the stepwise regression process, an exemplary model can generally be obtained in the direction of the following:

Assuming that: a = age (years), w = weight (kg), h = length (cm), and c = waist / neck circumference (cm).

The prediction rules in this case were calculated from a representative sample of approximately 1400 Belgian males over 18 years of age using the IS08559 body size definitions and read as follows (all results in cm) chest circumference = - 4.87 +0.229 a- 0.019a ² + 0.361c + 130.4 (w / h) ^1/2 waist circumference = -70.7 + 0.232a + 0.802c + 185 (w / h) ^1/2 waist circumference = 86.2 + 0, 2 la-0.423h + 0246c + 0.742w arm circumference = -1.5-0.00043a ² -0.0432h + 0.089c + 57.6 (w / h) ^1/2 wrist circumference = 4.2 + 0.00019a ² + 0.02h + 15.3 (w / h) ^1/2 shoulder length = 12.4 -0.00012a ² + 0.013h -0.065c + 0.045w arm length = 6.1 + 0.047a + 0.326h -0.165c + 0.058w back length = 7.9 + 0.02a + 0.3h + 0.149c + 0.072w

BE2017 / 5607

It should be noted that this model is derived from one special sample from one special population. Using a different sample or even changing the threshold level of significance in the stepwise regression, or obtaining only strictly linear relationships or also changing the linear adjustment method can result in very different looking equations. But the predicted values of the dependent variables will remain close to each other.

Once the prediction rules have been constructed, they are tested, preferably on a different sample of the population, to calculate the standard deviation of the resulting estimates compared to the actual body measurements. It should be found that this standard deviation is close to the standard deviation of the regression model.

Once the entire process is completed, a robust body size prediction model is obtained, which can be used in the design of patterns from previous personalized custom shirts 18 and other apparel.

By using statistical terms, the uncertainty of pattern conformity has been reduced compared to the ready-to-wear industry.

If there were changes in the morphological characteristics of the population over time, for example, if the average human body becomes longer or heavier, the prediction model will become less accurate. However, it is possible to change the model to reflect the evolution of the population. The regression simply needs to be done again in exactly the same way, but using a new, updated sample of individual variables. If an updated sample is continuously available, the rules can also develop continuously. In this case, every time an order is placed or every time the sample is changed, the regression could be performed to generate new lines.

More generally, if the invention is to be applied to a population that gives significant morphological differences compared to the original sample, the model can be recalculated based on a new sample extracted from the considered different population. Such morphological differences may, for example, reflect specificities in the geographic or ethnic origins of the newly targeted population. Yet another improvement step in the same direction would be to add new personal variables to the model, representing the geographic or ethnic origin of the customer. Introducing the new variables into the regression would result in a single model that could be applied to different morphological types.

The use of age A as an independent input variable and within the prediction rules is particularly noteworthy. It has been found that their use in some cases leads experimentally to the following reduction of error of the estimates. The figures can be read as the improvement in terms of prediction accuracy resulting from the use of the age variable A.

While the present invention has been particularly shown and described with reference to a preferred embodiment, those skilled in the art will understand that changes in shape and detail can be made without departing from the scope and spirit of the invention.

For example, it will be preferable to also obtain an input variable indicating arm or sleeve length and also an input variable waist, since this would further increase accuracy. Should the above-described embodiment be varied to provide a blouse, it would prove useful to obtain additional input variables specific to the feminine shape and well known to the customer, such as, for example, the bust size.

The invention can also be varied to produce other articles of tailor-made clothing, such as, for example, trousers, the use of age also being useful in predicting changes over time in, for example, the size of thighs. Since height is in fact already 'known' in the model, the effect of height and its shrinkage due to age can already be generally taken into account. The prediction of the back length is generally unaffected by the insertion of age into the model, although in absolute terms the back length can be quite influenced by age as space between vertebrae decreases. Under such circumstances, it would also be preferable to request input variables indicative of foot length 2017/5607 leg length, for example shoe size and the inner seam. By using the invention to make a jacket and pants, full suits can also be considered, with or without accompanying vests.

To facilitate the implementation of the invention, an information carrier such as a CD-ROM could be provided, for example, given away as a promotional donation or exchangeable against later purchases. At least one program would be encoded to enable implementation of the invention, including, for example, at least one of a website interface, a database of clothing options or sizing information, a web browser, an order / billing system, and an image program for enabling of displaying an image as discussed above.

It will be understood that the results of the samples taken, while the databases are being built, could be used to further develop the invention such that the limits can be determined as to whether or not a particular customer can be met with regarding the use of the automated body size estimation procedure.

When the graph of Figure 4 is currently taken, a boundary is placed randomly the area of the results with the highest density of data, and that boundary may include, for example, an ellipse or an oval extending beyond the limits of the proper fit zone . If the import variables supplied by a potential customer place them outside the border, they are defined as impractical for delivery. This may be due to the delivery by customers of extraordinary or very inaccurate input variables that could result in a message being sent to them, interactively recommending that they check their input variables or even measure them professionally.

A database could also be built in which details of extraordinary customers are maintained, together with records of the dimensions used on any orders that are returned or listed as badly fitting, for example warranty returns. Furthermore, records in this order database, where no complaint was lodged, could be maintained. The data collected in this way is then used to update the population sample records and even ² ^ 7/5607 prediction rules to protect against trends toward inaccuracy due to negative input or tolerance input data, or to build confidence in robustness. support positive results, as may be the case. The database can be integrated with the records of the original / updated sample or separately, as would prove necessary in the event that a third party database was purchased. The information collected in this way could also be used to protect against customers who are difficult to satisfy, for example by creating a record of customers who usually return goods for whatever reason.

For example, a customer answers 4 simple questions and software components translate this data into a fully biometric profile of the client's human body. When all these measures are stored, an endpoint can use one of the backbone implementation functions to match those biometric values to the chosen product and return the most appropriate standard measure. The algorithm then provides a percentage of the fit of the standard measure. An acceptable percentage as a decision threshold can be derived before directing the consumer to another garment or to the platform's full bespoke process.

With reference to Figures 1-7, embodiments of the present invention use APIs 22, 24, 26 for personalization and custom software 3D configuration embedded in the multi-channel platform. A prediction service 40, after receiving input variables such as A, W, H, C, can use a prediction model and its associated rules to calculate the values of B, CC, WC, AC, WR, SL,

AL and BL and optionally also use the BC, depending on whether the customer is a male or female person. Configuration-Sizing-Manufacturing is provided as a service, using size charts to provide the stock, custom or e Bespoke products. The API 24 enables benefits for 3D configurators 37 to deliver through the use of plug-ins 36 (e.g. supported by platform web services) as a way to get started quickly and cheaply. This allows access to platforms 32 for fully personalized biometrically tailored garments.

Embodiments of the present invention may utilize an API 2017/5607, for example, as a web service for CAD / CAM interfaces 39: fabric cut files to join fabrication systems 16, which will cut, manufacture and distribute fashion products.

Embodiments of the present invention utilize an API-powered platform 30, which allows all vendors and consumers to benefit from high-tech sizing and tailor-made solutions that are not currently available. This platform can be located, centralized or distributed. Consumers can benefit from a so-correct-as-standardized fit, and a correct overview regarding stock availability.

Advantages of the present invention include (i) easy size prediction implementation reduction of 50% time to implement this service;

(ii) matching the product with the customer's measure 50% reduction of returned products;

(iii) spreading the bespoke paradigm 40% increase in custom products;

(iv) Integration of product concentration and production reduction of 30% delivery time of customized products;

(v) a direct impact on the environment by the fact that the amount of wrong online sales will be drastically reduced by using the size prediction or the choice of bespoke products. There will be a reduction in waste by reducing the total number of online returns, by linking customer sizes and fashion products with a size predictor with other functionality such as the inclusion of custom garments;

(vi) custom-made and configurable Made-to-Measure (MtM) and e-bespoke solution based on open standards;

(vii) reduction of product rejections and returns mainly as a result of online commerce associated with discomfort and ill-fitting of garments;

(viii) Being able to create open and interoperable platforms that any company can use the fashion sector to produce its products, processes and services.

Processors described with respect to the embodiments of the present invention, such as for use with non-volatile memories, may be operated with a standalone digital processing device or may be embedded in another device. The processor preferably has processing power as provided by one or more microprocessors, FPGAs, or a central processing unit (CPU) and / or a Graphics Processing Unit (GPU), and is adapted to perform the respective functions by being programmed with software that is, one or more computer programs. References to software can include any type of program in any language that is directly or indirectly executable by a processor, either in a compiled or interpretative language, such as Java. The implementation of any of the methods of the present invention may be performed by or supported by logic circuits, electronic hardware, processors or circuits that may include any kind of logic or analog circuit integrated to an extent, and not limited to, general purpose processors purpose, digital signal processors, ASICs, FPGAs, discrete components or transistor logic gates and the like.

Such devices may have a memory (such as a non-volatile memory, non-transitory computer readable medium, RAM and / or ROM), an operating system, optionally a display such as a fixed format display, ports for data input devices such as a keyboard, a pointing device such as a “mouse”, serial or parallel ports to communicate with other devices, network cards, and connections to connect to any of the networks.

The software may be embodied in a computer program product adapted to perform functions specified below when the software is loaded on the controller and on one or more processors such as microprocessors, ASICs, FPGAs. Devices for use with any of the embodiments of the present invention may incorporate a computer system capable of running one or more computer applications in the form of Computer software.

BE2017 / 5607

The methods for embodiments of the present invention can be performed by one or more computer application programs running on the computer system by being loaded into memory and on or in combination with an operating system such as Windows ™ supplied by Microsoft Corp, USA, Linux,

Android or the like are running. The computer system may include a main memory, preferably random access memory (RAM), and may also include a non-transistor hard disk drive and / or a removable non-transistor memory and / or a non-transistor solid state memory. Non-transitory removable memory may be an optical disc such as a compact disc (CD-ROM or DVD-ROM), a magnetic tape read by and described by a suitable reader. The removable non-transitory memory may be a computer-readable medium containing Computer software and / or data stored thereon. The non-volatile storage memory can be used to store persistent information, which should not be lost if the computer system is turned off. The application programs can use and store information in non-volatile memory.

The software embodied in the computer program product is adapted to perform the following functions of one of the method steps of the embodiments of the present invention when the software is loaded on the respective device or devices and on one or more processors such as microprocessors, ASICs, FPGAs etc. is performed.

Any of the above software can be implemented as a computer program product, which is compiled for a processor in each of the servers or nodes of the network or written in the interpretative language such as Java running on a virtual machine such as the Java virtual machine . The computer program product can be stored on a non-transistor signal storage medium such as an optical disk (CD-ROM or DVD-ROM), a digital magnetic tape, a magnetic disk, a solid-state memory such as a USB flash memory, a ROM, etc. saved.

BE2017 / 5607

Claims (32)

Conclusions A computer system-based method of supplying stock or custom or e-bespoke textile products made from synthetic or natural fibers, comprising the following steps: the computer system receives a first set of a plurality of input variables being biometric size data from a customer to be provided with at least one first textile product, the computer system processes said first set of the plurality of input variables regarding body size into a prediction model at least to predict 2, 4, 6 or 8 body dimensions, each of said body dimensions being derived from two or more of said input variables, the computer system derives a fit quality value for the first textile product, which is any or all of a stock - or custom and e-bespoke textile product, as a function of the first series of the plurality of input variables regarding body size, the second series of at least 2, 4, 6 or 8 suitable body dimensions, the computer system rejects any stock or custom textile product that is not full does the fit quality value and if any stock or custom textile product does not meet the fit quality value, the customer will receive this stock or custom textile product under the control of the computer system, otherwise the customer will receive the e-bespoke product. The method of claim 1, wherein the first set of a plurality of body size input variables is provided from a first software from a first vendor, the computer system mapping this first set with a third set of values from a second software from the first vendor. prediction model, where mapping is accomplished by transferring the plurality of body size input variables by a first API, wherein the computer system derives the fit quality value for any or each of a stock or custom and e-bespoke textile product from a size prediction based on a size chart, and the computer system allows a customer input whether a stock or custom or an e-bespoke product is acceptable. The method of claim 1 or 2, wherein: the computer system, which provides a 3D configuration for the stock, custom or e-bespoke product, is provided via a second API. The method of claim 1 or 2 or 3, wherein: CAD data as well as CAM data for enabling production are automatically created by the computer system via a third API for production integration of the custom or e-bespoke product with a production process from a manufacturer. The method of claim 4, further comprising - receiving by the manufacturer, from the computer system, a digital design specification of a textile product from a design unit through a wide area data network, - processing by the computer system of the received design specification in order to obtain a virtual prototype of the textile product, - computer conversion of the virtual prototype into a format compatible with an additive and subtractive editing system, obtaining a material from which the textile product is to be made, and - obtaining by molding said textile product using the additive and subtractive treatment system. A method according to claim 5, wherein the step of obtaining said textile product by molding using the additive and subtractive processing system is performed by one of the following methods, depending on the material selected: cutting, stitching, pleating, folding , sewing, gluing, welding. A method according to claim 5 or 6, further comprising a step of an after-treatment of said textile product by ironing, starching, washing-pressing. A method according to any one of the preceding claims, wherein the plurality of body size input variables are selected from weight, height, size and additional age and gender input variables. The method of any preceding claim, wherein the second set of at least 2, 4, 6, or 8 estimated body sizes is selected from BMI, chest size, waist size, arm size, wrist size, shoulder length, arm length, back length, and waist or waist size . The method of any one of claims 5 to 9, wherein the computer system provides said client with a representation of the virtual prototype displayed in three dimensions. A method according to any one of claims 5 to 10, wherein the computer system provides said customer with a representation of a virtual person in accordance with said estimated body size wearing the textile product, said virtual person being displayed in three dimensions (3D). 12. Computer system-based methods of supplying stock or mSS ^ OI 7/5607 made or e-bespoke textile products made from synthetic or natural fibers, comprising the following steps: the computer system receives product design data including parameter values related to at least one textile product and or biometric size data from a customer destined to wear the at least one first textile product, the product design data being provided from a first software from a first vendor, the computer system submitting these product data to mapping with values from a second software of a textile product prediction system, where mapping is accomplished by: a first API for biometric size data and size prediction based on a size chart, further comprising determining how well the size of the textile product matches the biometric size data and having a customer enter a stock or a custom or e- bespoke product. The method of claim 12, further comprising the computer system that provides a 3D configuration for the stock, custom or e-bespoke product. The method of claim 12 or 13, further comprising generating CAD data as well as CAM data to enable production through a third API for production integration of the custom or e-bespoke product with a manufacturer's production process. The method of claim 14, further comprising - receiving by the manufacturer from a computer system a digital design specification of the custom or e-bespoke product from a design unit through a wide area data network, - processing by the computer system of the received design specification in order to obtain a virtual prototype of the customized or e-bespoke product, - conversion by the computer system of the virtual prototype into a format compatible with an additive and subtractive processing system, - obtaining a material from which the textile product is to be made, & Ε ² θ ¹ 7/5607 - obtaining by molding said textile product using the additive and subtractive treatment system. The method of claim 15, wherein the computer system provides said client with a virtual representation of said virtual prototype, wherein said virtual representation is displayed in three dimensions. The method of any one of claims 12 to 16, wherein said input variables include an age, weight, height of said customer. 18. Computer-based system for supplying stock or custom or e Bespoke products made from synthetic or natural fibers, comprising: means for receiving a first set of a plurality of body size input variables, which are biometric measurement data from a customer to be provided with at least one first textile product, means for processing said first set of the plurality of body size input variables in a prediction model to predict a second set of at least 2, 4, 6, or 8 appropriate body dimensions, wherein each of said appropriate body dimensions is derived from two or more of said input variables, being means for deriving a fit quality value for the first textile item any or any of a stock or custom and e-bespoke product as a function of the first series of the plurality of body size input variables and the second series of at least 2, 4, 6 or 8 body sizes, means for rejecting a stock or custom textile product, that does not meet the fit quality value, and, if any stock or custom textile product does not meet the fit quality value, funds are provided to the customer prior to receiving 1 ^ 2017/5607 of this stock or custom textile product, where the customer otherwise receive the e-bespoke product. The system of claim 18, wherein a first set of a plurality of body size input variables are provided from a first software of a first vendor, the system further comprising: means for subjecting this first set to mapping with a third set of values from a second software of the prediction model, mapping being accomplished by transmitting the plurality of body size input variables by a first API, means for deriving the fit quality value for any or any of a stock or custom and e-bespoke product from a size prediction based on a size chart, and means for a customer to enter either a stock or a custom or an e- bespoke product is acceptable. The system of claim 18 or 19, wherein: a second API for a 3D configuration for the stock, custom or esspoke product is provided. The system of claim 18 or 19 or 20, further comprising: means for generating CAD data as well as CAM data for enabling production via a third API for production integration of the custom or e-bespoke product with a manufacturer's production process. The system of claim 21, further comprising: - the manufacturer is arranged to receive a digital design specification of a textile product from a design unit through a wide area data network, - means for processing the received design specification to obtain a virtual prototype of the textile product, - means for converting the virtual prototype into a format compatible with 7/5607 with an additive and subtractive processing system, means for obtaining a material from which the textile product is to be made, and - means for obtaining said textile product by molding using the additive and subtractive processing system. The system of claim 22, wherein the means for obtaining said textile product by molding using the additive and subtractive processing system comprises one of the following depending on the material selected: cutting means, stitching means, means for pleating, means for folding, means for sewing, means for lines, means for welding. The system of any one of claims 18 to 23, wherein the plurality of body size input variables are selected from weight, height, size, and additional age and gender input variables. The system of any one of claims 18 to 24, wherein the second set of at least 2, 4, 6, or 8 estimated body sizes is selected from BMI, chest size, waist size, arm size, wrist size, shoulder length, arm length, back length, and abdominal size or waist. The system of any one of claims 22 to 25, further comprising means for said client to be provided with a representation of the virtual prototype displayed in three dimensions. 27. Computer-based system for supplying stock or custom or e Bespoke textile products, which are manufactured from synthetic or natural fibers, comprising means for receiving product design data including parameter values related to at least one textile product and / or biomettic dimension data from a customer destined to wear the at least one first textile product, the product design data being provided from a first software of a first seller, BE2017 / 5607 means for mapping this product data with values from a second software of a textile product prediction system, the means for mapping comprising a first API for biometric size data and size prediction based on a size chart, means for determining how well the textile product size matches the biometric dimension data and means for a customer to enter whether he wants to buy a stock or a custom or e-bespoke product. The system of claim 27, further comprising means for providing a 3D configuration for the stock, custom or e-bespoke product. The system of claim 27 or 28, further comprising means for generating CAD data as well as CAM data for enabling production via a third API for production integration of the custom or e-bespoke product with a production process from a manufacturer. The system of claim 29, further comprising - being in possession of the manufacturer with means for receiving a digital design specification of the custom or e-bespoke product from a design unit through a wide area data network, - means for processing the received design specification in order to obtain a virtual prototype of the custom or e-bespoke product, - means for converting the virtual prototype into a format compatible with an additive and subtractive processing system, means for obtaining a material from which the textile product is to be made, and - means for obtaining by forming said textile product using the additive and subtractive treatment system. The system of claim 30, wherein said customer is provided with means for displaying a virtual representation of said virtual prototype, said virtual representation being displayed in three dimensions. BE2017 / 5607 32. Non-transitional signal storage device, on which at least one program is encoded to execute any one of claims 1 to 17, when it is on the processor 5 is performed. BE2017 / 5607 Web server 1 qyb ^ls BE2017 / 5607 Chest size ~ T1 Chest size (Weight / Height) BE2017 / 5607