Shrinkage prediction, clothing order processing method, system, device and storage medium

Abstract

Embodiments of the present application provide a method, system, device and storage medium for shrinkage prediction and clothing order processing. In the shrinkage prediction method, after obtaining the garment size corresponding to the part of the garment to be processed and the shrinkage of the fabric used in the order, the shrinkage corresponding to the part of the order can be predicted based on a pre-trained shrinkage prediction model. Based on the predicted shrinkage of the part of the garment, the size of the cutting pattern can be quickly determined for generating garment pieces and garment processing. Based on this approach, on the one hand, the dependence of the shrinkage calculation operation of the part of the garment in the garment plate making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation results of the shrinkage of the part of the garment can be improved, thereby improving the plate making efficiency of the garment order.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a shrinkage prediction, clothing order processing method, system, device and storage medium. Background Art

[0002] In the clothing industry, when making design patterns for clothing, it is necessary to determine the sizes corresponding to different parts on the design pattern based on the corresponding garment sizes and the shrinkage rates of different parts. Different parts have different shrinkage rates. For the same part, the shrinkage rates shown on different categories of clothing are also different. Therefore, accurately obtaining the shrinkage rate of the parts is an important part of making design patterns.

[0003] At present, the shrinkage rate of different parts is manually predicted based on the experience of the plate maker, but this prediction method has certain shortcomings in efficiency and accuracy. Therefore, a new solution is needed. Summary of the invention

[0004] Multiple aspects of the present application provide a shrinkage prediction method, system, device and storage medium to improve the prediction accuracy of the shrinkage of clothing parts and reduce labor costs.

[0005] An embodiment of the present application also provides a shrinkage prediction method, comprising: responding to a shrinkage prediction operation, determining the garment sizes of multiple parts corresponding to the garment to be processed and the shrinkage of the fabric used for the garment; inputting the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0006] The embodiment of the present application also provides a method for generating a garment cutting pattern, comprising: in response to a request for generating a cutting pattern corresponding to a garment, determining the garment sizes of multiple parts corresponding to the garment and the shrinkage rate of the fabric used for the garment; inputting the garment sizes of the multiple parts and the shrinkage rate of the fabric into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to each of the multiple parts; determining the cutting piece sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts; marking the cutting piece sizes corresponding to each of the multiple parts on the design pattern corresponding to the garment to obtain the cutting piece pattern corresponding to the garment.

[0007] An embodiment of the present application also provides a method for processing a clothing order, comprising: responding to a processing request for a clothing order, determining the garment sizes of multiple parts corresponding to the clothing order and the shrinkage rates of the fabrics used in the clothing order; inputting the garment sizes of the multiple parts and the shrinkage rates of the fabrics into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to each of the multiple parts; determining the cutting piece pattern corresponding to the clothing order based on the predicted shrinkage rates corresponding to each of the multiple parts; and cutting the fabrics used in the clothing order according to the cutting piece pattern corresponding to the clothing order to obtain clothing pieces for processing the clothing order.

[0008] An embodiment of the present application also provides a method for assisting paper pattern making, comprising: determining attribute information of a garment for which a paper pattern is to be generated; based on the attribute information, predicting a predicted shrinkage rate corresponding to each part of the garment; and displaying the predicted shrinkage rate to a paper pattern making user.

[0009] An embodiment of the present application also provides a method for predicting the deformation amount of clothing, comprising: obtaining attribute information of elastic clothing; inputting the attribute information into a prediction model to obtain a predicted value of the deformation amount of at least one part of the elastic clothing; and displaying the predicted value of the deformation amount of at least one part to a user.

[0010] An embodiment of the present application also provides a shrinkage prediction method, comprising: responding to a size setting operation for a clothing order, determining the garment sizes of multiple parts corresponding to the clothing order; obtaining the shrinkage of the fabric used in the clothing order; sending the garment sizes corresponding to the multiple parts and the shrinkage of the fabric to a server, so that the server predicts the predicted shrinkage corresponding to each of the multiple parts based on a shrinkage prediction model; receiving the predicted shrinkage corresponding to each of the multiple parts returned by the server, and displaying the predicted shrinkage corresponding to each of the multiple parts.

[0011] An embodiment of the present application also provides a shrinkage prediction method, comprising: obtaining the garment sizes corresponding to multiple parts of a clothing order sent by a terminal device and the corresponding fabric shrinkage; inputting the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts; and sending the predicted shrinkage corresponding to each of the multiple parts to the terminal device.

[0012] An embodiment of the present application also provides a terminal device, including: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the reduction rate prediction method provided in the embodiment of the present application.

[0013] An embodiment of the present application also provides a server, comprising: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the reduction rate prediction method provided in the embodiment of the present application.

[0014] The embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the reduction rate prediction method provided in the embodiment of the present application can be implemented.

[0015] In an embodiment of the present application, an automated plate-making auxiliary method is provided, which is suitable for use by clothing plate makers. After obtaining the garment size corresponding to the part of the garment to be processed and the shrinkage of the fabric used in the order, the shrinkage corresponding to the part of the garment can be predicted based on a pre-trained shrinkage prediction model. Based on the predicted shrinkage of the part of the garment, the size of the cutting pattern can be quickly determined for generating garment pieces and garment processing. Based on this method, on the one hand, the dependence of the shrinkage calculation operation of the part of the garment in the garment plate-making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation result of the shrinkage of the part of the garment can be improved, thereby improving the plate-making efficiency of the garment order. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A schematic diagram of the structure of a shrinkage prediction system provided by an exemplary embodiment of the present application;

[0018] Figure 2 A schematic diagram of a page where unfinished orders are located provided for an exemplary embodiment of the present application;

[0019] Figure 3 A schematic diagram of setting the size of a garment provided by an exemplary embodiment of the present application;

[0020] Figure 4 A schematic diagram of setting the shrinkage rate of a fabric provided by an exemplary embodiment of the present application;

[0021] Figure 5 A schematic flow chart of a shrinkage prediction method provided by an exemplary embodiment of the present application;

[0022] Figure 6 A schematic flow chart of a shrinkage prediction method provided for another exemplary embodiment of the present application;

[0023] Figure 7A schematic flow chart of a shrinkage prediction method provided for another exemplary embodiment of the present application;

[0024] Figure 8 A schematic flow chart of a method for generating a garment cutting pattern provided by an exemplary embodiment of the present application;

[0025] Figure 9a A flowchart of a method for processing a clothing order provided by another exemplary embodiment of the present application;

[0026] Figure 9b A flowchart of a method for assisting paper pattern making provided by another exemplary embodiment of the present application;

[0027] Fig.9c A schematic flow chart of a method for predicting clothing deformation provided by another exemplary embodiment of the present application;

[0028] Fig.10 A schematic diagram of the structure of a terminal device provided for an exemplary embodiment of the present application;

[0029] Fig.11 A schematic diagram of the structure of a server provided for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0031] At present, in the process of making clothing patterns, the shrinkage rates of different parts are mostly predicted manually based on the experience of the pattern maker to obtain the size of the cut pieces of the parts. However, this manual prediction method has technical problems of low efficiency and insufficient accuracy. In view of the above technical problems, a solution is provided in some embodiments of the present application. The technical solutions provided in each embodiment of the present application will be described in detail below in conjunction with the accompanying drawings.

[0032] Figure 1 A schematic diagram of the structure of a shrinkage prediction system provided by an exemplary embodiment of the present application is shown in FIG. Figure 1 As shown, the shrinkage prediction system 100 includes: a terminal device 10 and a server 20.

[0033] The shrinkage prediction system 100 is mainly used to provide users with a shrinkage prediction service for parts of clothing.

[0034] Among them, the parts of clothing can be understood as the parts that need to be measured when the clothing is processed. Usually, in the field of clothing plate making, the parts of clothing can also be called measurement positions. For example, the front length, back length, chest circumference, shoulder width, waist circumference, hem circumference, sleeve length and other parts of the top, the waist circumference, upper hip circumference, lower hip circumference, knee circumference, leg circumference and other parts of the trousers. When making clothing pieces, the fabric can be cut according to the piece size corresponding to the part and the design pattern to obtain clothing pieces (clothing pieces). The clothing pieces are processed to obtain finished clothes. After the pieces are processed into finished clothes, the size code of each part measured on the finished clothes can be called the finished clothes size corresponding to the part, that is, the size code of the finished clothes before washing. In the field of clothing plate making, the finished clothes size corresponding to the parts of the clothing can also be called the finished clothes size of the clothing measurement position.

[0035] In the process of processing the cut pieces into garments, the size of the parts will change to a certain extent due to the influence of the fabric characteristics and the processing method. For example, in some cases, the size of the parts will shrink after the cut pieces are processed into garments. The ratio of the size corresponding to the part on the garment to the size corresponding to the part on the cut piece can be called the shrinkage rate of the part. Accurately predicting the shrinkage rate corresponding to the part can effectively ensure that the processed garment has the accurate part size.

[0036] In this embodiment, the users may include various users who have demands for clothing pattern making, such as clothing pattern makers in clothing processing factories, or consumers who have demands for personalized clothing customization, and so on.

[0037] In this embodiment, the terminal device 10 refers to a device that can interact with the user and has a communication function. In different application scenarios, the implementation form of the terminal device 10 will also be different. For example, in some scenarios, the terminal device 10 can be a mobile phone, tablet computer, computer device, smart wearable device, etc. on the user side, and the user can initiate the reduction rate prediction operation of the part through the plug-in, application or browser provided by the above terminal device 10.

[0038] In the shrinkage prediction system 100, the server 20 is a device that can provide data support, storage services, computing services, and some management services. In some embodiments, the server 20 can be implemented as a conventional server, a cloud server, a cloud host, a virtual center, and other servers and other devices, which are not limited in this embodiment. Among them, the composition of the server device mainly includes a processor, a hard disk, a memory, a system bus, etc., which is similar to a general computer architecture and will not be repeated.

[0039] In the shrinkage prediction system 100, the terminal device 10 is mainly used to: interact with the user and detect the user's operation of setting the size of the cut piece of the clothing order. In response to the size setting operation for the clothing order, the ready-made clothing sizes of multiple parts corresponding to the clothing order are determined, and the shrinkage of the fabric used in the clothing order is obtained. Next, the ready-made clothing sizes corresponding to the multiple parts of the clothing order and the shrinkage of the fabric used in the clothing order are sent to the server 20.

[0040] The shrinkage of fabric refers to the percentage of shrinkage of fabric after washing or soaking in water. The shrinkage of fabric includes the shrinkage in the warp direction and the shrinkage in the weft direction. Different fabrics have different shrinkages. For example, synthetic fibers and blended fabrics have a smaller shrinkage, wool, linen, and cotton fabrics are in the middle, silk fabrics have a larger shrinkage, and viscose, rayon, and artificial wool fabrics have the largest shrinkage. When the shrinkage of fabrics is different, the impact on the shrinkage of parts is also different.

[0041] After receiving the garment sizes corresponding to the multiple parts and the corresponding fabric shrinkage rates sent by the terminal device 10, the server 20 calculates the garment sizes corresponding to the multiple parts and the shrinkage rates of the fabric based on the pre-trained shrinkage prediction model to obtain the predicted shrinkage rates corresponding to the multiple parts, and sends the calculated predicted shrinkage rates corresponding to the multiple parts to the terminal device 10. The optional implementation method of the server 20 calculating the predicted shrinkage rates of the parts based on the shrinkage prediction model will be exemplarily described in the subsequent embodiments and will not be repeated here.

[0042] After receiving the predicted shrinkage rates corresponding to the multiple parts returned by the server 20, the terminal device 10 can display the predicted shrinkage rates corresponding to the multiple parts for the user to view. The user can make clothing patterns based on the predicted shrinkage rates corresponding to the multiple parts. In the shrinkage prediction system 100, in order to realize the above data interaction process between the terminal device 10 and the server 20, the terminal device 10 and the server 20 can establish a communication connection, and the specific communication connection method can be determined according to the actual application scenario.

[0043] In some exemplary embodiments, the terminal device 10 and the server 20 may communicate with each other by wired communication or wireless communication. The wireless communication includes short-distance communication such as Bluetooth, ZigBee, infrared, WiFi (WIreless-Fidelity), long-distance wireless communication such as LORA, and wireless communication based on mobile network. When the mobile network communication connection is made, the network standard of the mobile network may be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), 5G, WiMax, etc.

[0044] In some exemplary embodiments, the shrinkage prediction function on the server 20 side can be deployed as an online prediction service (Elastic Algorithm Service, EAS) based on the cloud platform. EAS can use Docker (container) for resource management and isolation, support multiple CPU (central processing unit, central processing unit) and GPU (Graphics Processing Unit, graphics processing unit) models on the cloud, and also support in-elastic physical machine access. It also supports user local debugging and stand-alone version of the prediction service, which is more convenient for users to use.

[0045] In this embodiment, after obtaining the garment size corresponding to the part of the clothing order and the shrinkage of the fabric used in the clothing order, the shrinkage prediction system can predict the shrinkage corresponding to the part of the order based on the pre-trained shrinkage prediction model. Based on the predicted shrinkage of the part of the clothing, the size of the cutting pattern can be quickly determined for generating clothing pieces and clothing processing. Based on this method, on the one hand, the dependence of the shrinkage calculation operation of the part of the clothing in the clothing plate making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation results of the shrinkage of the part of the clothing can be improved, thereby improving the plate making efficiency of the clothing order.

[0046] In the above and the following embodiments of the present application, in the above embodiments, the sizes of the garments of the multiple parts corresponding to the clothing order determined by the terminal device 10 may be the sizes of the garments manually entered by the user, or the sizes of the garments queried based on the historical orders. An exemplary description will be given below.

[0047] Optionally, in one case, the terminal device 10 responds to the size setting operation for the clothing order, and can display multiple parts to be set according to the clothing category to which the clothing order belongs, so that the user can set them. The category of clothing refers to the classification item to which the clothing belongs. For example, when clothing is classified according to fabric, the categories of clothing may include jeans, down jackets, T-shirts, shirts, sweaters, etc. For another example, when clothing is classified according to function, the categories of clothing may include: sportswear, casual wear, work clothes, formal wear, etc.

[0048] Different clothing categories correspond to different parts, and each clothing category may correspond to multiple parts. For example, when the clothing category to which the clothing order belongs is shirts, the multiple parts to be set displayed by the terminal device 10 may include: shoulder width, length, collar circumference, hem circumference, waist circumference, sleeve length, collar tip length, collar spacing, etc. For another example, when the clothing category to which the clothing order belongs is jeans, the multiple parts to be set displayed by the terminal device 10 may include: upper hip circumference, lower hip circumference, crotch, leg circumference, knee circumference, waist height, etc.

[0049] For the user, the sample clothes corresponding to the order can be measured to obtain the sizes of multiple parts of the garment. Alternatively, the sizes of multiple parts of the garment can be obtained according to the requirements of the order. Next, the parts to be set displayed by the terminal device 10 can be set according to the obtained sizes of the parts of the garment.

[0050] In response to the user's setting operation, the terminal device 10 can obtain the size data input by the user for the multiple parts to be set as the garment sizes of the multiple parts corresponding to the clothing order.

[0051] The following will be combined Figure 2 An exemplary description is given.

[0052] like Figure 2 As shown in , the user can enter the page where the unfinished orders are located to view the orders for unfinished pattern making. On this page, multiple unfinished orders are displayed, and each order displays the corresponding garment size, quantity and operation button. Figure 2 As shown in the figure, for each order, a "Set Size" button is displayed. Users can click the "Set Size" button to enter Figure 3 The Garment Size Setup page shown.

[0053] like Figure 3 As shown, on the clothing size page, the user can set the clothing category to "short coat", and the terminal device 10 can display multiple parts corresponding to the short coat and the measurement method of the parts. After the user measures the sample clothing, he can enter the clothing size of the part in the corresponding position. Figure 3 The page shown also displays a "Calculate Shrinkage" button, which the user can click to enter the following Figure 4The page shown. Figure 4 On the page shown, the user can enter the warp shrinkage and weft shrinkage of the fabric used in the short coat and click the confirmation button. Figure 3 On the page shown, the corresponding fabric shrinkage of each part can be automatically displayed. For example, the front length and sleeve length are measured longitudinally, so the corresponding fabric shrinkage is the warp shrinkage; the chest circumference, hem, and sleeve width are measured transversely, so the corresponding fabric shrinkage is the weft shrinkage.

[0054] Optionally, in another case, the terminal device 10 responds to the size setting operation for the clothing order and can query whether there is a historical order corresponding to the clothing order; if so, the terminal device 10 can obtain the garment sizes of multiple parts corresponding to the historical order as the garment sizes of multiple parts corresponding to the clothing order. In this case, the user does not need to manually input the historical orders, which further improves the setting efficiency.

[0055] Optionally, if there are changes in a clothing order relative to its corresponding historical order, for example, the values ​​of certain parts increase or decrease, the user can modify the clothing sizes of multiple parts corresponding to the historical orders displayed on the terminal device 10, and use the modified clothing sizes as the clothing sizes of multiple parts corresponding to the clothing order.

[0056] On the basis of the above embodiment, further optionally, the user can update the part displayed by the terminal device 10. The update operation may include at least one of: deleting the existing part displayed by the terminal device, selecting a new part from the parts provided by the clothing category, and adding a custom part. When the terminal device 10 obtains the part updated by the user, it can display the updated part so that the user can set the clothing size of the updated part, which will not be described in detail.

[0057] After confirming the size of the garment and the shrinkage of the fabric for the corresponding part of the clothing order, the user can click Figure 3 The page shown in the figure provides a "Submit" button. At this time, the terminal device 10 can send the garment size of the part shown in the table and the warp shrinkage and weft shrinkage of the fabric to the server 20. After the server 20 calculates the predicted shrinkage of the part based on the garment size of the part and the warp shrinkage and weft shrinkage of the fabric, it can return the shrinkage of the part to the terminal device 10.

[0058] In the above and below embodiments of the present application, optionally, after the terminal device 10 obtains the predicted shrinkage rates corresponding to each of the multiple parts of the clothing order, it can calculate the corresponding piece sizes of each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts. For example, the garment size of the part is divided by the shrinkage rate of the part to obtain the piece size of the part. Next, the terminal device 10 can mark the piece sizes corresponding to each of the multiple parts on the design pattern corresponding to the clothing order to obtain the piece pattern corresponding to the clothing order. Furthermore, the user can cut the fabric based on the piece pattern to obtain pieces. The pieces are sewn together according to certain rules to obtain finished garments.

[0059] Optionally, the design pattern of the clothing order can be provided by the user, or can be drawn by the user in advance using a drawing tool running on the terminal device 10 and saved locally on the terminal device 10 or on the server 20. The drawing tool can be a CAD (Computer Aided Design) tool, or can be other drawing tools such as PhotoShop (a computer graphics software), CorelDraw (a vector drawing software), Painter (a digital sketching and painting tool), etc., which are not limited in this embodiment. Figure 2 An exemplary description is given.

[0060] like Figure 2 As shown, for each order of unfinished plate making in the unfinished page, the terminal device 10 displays a "Modify Pattern" button. After calculating the shrinkage rate of the part, the user can click the "Modify Pattern" button. At this time, the terminal device 10 can call the drawing tool to open the design pattern corresponding to the order, and calculate the cutting piece size corresponding to the part according to the shrinkage rate of the part, and mark the cutting piece size on the design pattern, and no longer illustrate.

[0061] In some exemplary embodiments, when the terminal device 10 calculates the garment sizes and shrinkage of the fabric corresponding to multiple parts sent by the terminal device 10 based on the shrinkage prediction model, the garment sizes corresponding to the multiple parts and the shrinkage of the fabric can be input into the shrinkage prediction model; in the shrinkage prediction model, the relationship between the shrinkage of the fabric and the garment sizes corresponding to the multiple parts can be calculated according to a pre-trained decision tree to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0062] In the above and below embodiments of the present application, when pre-training the shrinkage prediction model, training samples can be obtained from the processing data of the garment factory. Among them, for different categories, such as knitwear and denim, for some parts, the garment factory usually defines a set of industry standards and rule information. For example, data such as the garment size, piece size, and shrinkage of the fabric used for the parts of clothing under different categories. Based on the above data, the shrinkage prediction model can be preliminarily trained. After the shrinkage prediction model is preliminarily trained, a set of self-learning part prediction models can be further trained based on the mining and cleaning of the garment size data produced by the historical factory and the Internet size big data. An exemplary description will be given below.

[0063] Optionally, based on historical pattern-making data of multiple different categories of clothing, multiple groups of training samples are obtained, wherein each group of training samples includes the ready-made size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing.

[0064] Next, the training sample is input into a regression model based on GBDT (Gradient Boosting Decision Tree). GBDT adds a gradient boosting method on the basis of ordinary decision trees, evolving from one decision tree to multiple decision trees, which can gradually improve the learning accuracy and the accuracy of the shrinkage prediction value. In GBDT, the initial learner can be calculated based on the multiple groups of training samples; according to the initial learner, the prediction residuals of each of the multiple groups of training samples are calculated. The goal of GBDT is to fit the prediction residuals of the samples and construct a decision tree using the prediction residuals as label values. Therefore, the prediction residuals of each of the multiple groups of training samples can be fitted to obtain multiple decision trees; wherein the branch condition of each decision tree is at least one of the garment size of the parts and the shrinkage of the parts contained in the multiple groups of training samples; after obtaining multiple decision trees, a shrinkage prediction model including the initial learner and the multiple decision trees can be output. This will be further explained below.

[0065] An optional implementation of training a decision tree may include the following steps:

[0066] S1. Determine the j-th learner corresponding to each of the multiple groups of training samples.

[0067] S2. Calculate the prediction residuals corresponding to each of the multiple groups of training samples according to the j-th learner and the label values ​​contained in each of the multiple groups of training samples.

[0068] S3. Determine the branching condition of the j-th decision tree from the multiple groups of training samples according to the prediction residuals corresponding to each of the multiple groups of training samples.

[0069] S4. Segment the multiple groups of training samples according to the decision branch conditions of the j-th decision tree, and calculate the prediction values ​​corresponding to the left and right branches of the j-th decision tree based on the segmentation results and the prediction residuals.

[0070] S5. Save the j-th decision tree.

[0071] S6, j=j+1, j is a positive integer.

[0072] The following will provide specific examples for illustration.

[0073] First, multiple groups of training samples are determined. Each group of training samples is composed of: [xi, pi, yi], where xi represents the size of the garment, pi represents the shrinkage of the fabric, and yi represents the shrinkage of the part. i = 1, 2, 3…n, and n is the total number of training samples. The garment size xi of the part and the shrinkage of the fabric pi can be used as features, and the shrinkage of the part yi can be used as a label value. Multiple groups of training samples can be expressed as: [x1, p1, y1], [x2, p2, y2]…[xn, pn, yn].

[0074] The following will describe in detail the training process of the first decision tree with j=1.

[0075] In step S1, the first learner f_1 corresponding to each of the multiple sets of training samples can be determined. Optionally, when j=1, the mean of the label values ​​in the multiple sets of training samples can be taken as f_1, that is, f_1=(y1+y2+…+yn) / n. In this step, the first learners f_1 of the multiple sets of training samples are the same and have a large error. Among them, the learner is equivalent to a prediction result. In the training stage, the learner can be considered as a learning target.

[0076] In step S2, the prediction residual corresponding to each group of training samples can be calculated, wherein the prediction residual corresponding to a group of training samples = the label value of the training sample - the prediction result of the sample, that is, the prediction residual Ri of the i-th group of training samples = yi - f_1.

[0077] The decision tree contains one or more branch conditions. Next, in step S3, the branch conditions in the decision tree may be determined based on the prediction residual of the sample.

[0078] In the n groups of training samples provided in this embodiment, each group of training samples contains two features, namely, the garment size xi of the part and the shrinkage rate pi of the fabric. Each feature has n unique feature values. Therefore, the n groups of training samples correspond to 2n feature values ​​that can be used as branch conditions of the decision tree.

[0079] Next, the 2n eigenvalues ​​may be used as branch conditions respectively, and the losses corresponding to the 2n eigenvalues ​​may be calculated, so as to select a better eigenvalue that can be used as a branch condition from the 2n eigenvalues ​​according to the losses corresponding to the 2n eigenvalues.

[0080] Taking x1 as the branch condition as an example, when making branch judgments on n groups of samples, samples with xi<x1 can be placed in the left branch, and samples with xi≥x1 can be placed in the right branch.

[0081] For any group of samples in the left or right branch, the prediction residual corresponding to the sample can be used as the new label value of the sample. That is, for the i-th group of training samples in n groups of training samples, the prediction residual Ri corresponding to the i-th group of training samples can be used as the new label value of the i-th group of training samples.

[0082] Next, the mean of the new label values ​​corresponding to the samples in the left branch and the right branch can be calculated respectively; and for the left and right branches, the difference between the new label value of the samples in each branch and the mean of the new label value can be calculated, and the sum of the squares of the differences can be calculated as the loss of the branch. The losses corresponding to the left branch and the right branch are added together to obtain the total loss when x1 is used as the judgment condition.

[0083] For example, assuming that when x1 is used as the judgment condition, the first group of training samples and the second group of training samples are divided into the left branch. Then, when calculating the loss of the left branch, the mean of the new label values ​​corresponding to the first group of training samples and the second group of training samples can be calculated, that is: R`(x1) = (R1+R2) / 2; Next, calculate the loss L of the left branch when x1 is used as the judgment condition left (x1) = (R1-R`)^2 + (R2-R`)^2. Similarly, the loss L of the right branch when x1 is used as the judgment condition can be calculated. right (x1); then, the total loss when x1 is used as the judgment condition is L(x1)=L left (x1)+L right (x1).

[0084] Similarly, the left branch loss L can be calculated separately left (xi), right branch loss L right (xi) and the total loss L(xi), i = 2, 3, ... n; when pi is used as the judgment condition, the left branch loss L can be calculated respectively left (pi), right branch loss L right (pi) and total loss L(pi), i=1,2,3…n.

[0085] Based on the above steps, 2n total losses can be calculated for the 2n eigenvalues ​​in the training sample. Next, the eigenvalue corresponding to the minimum loss can be selected from the 2n total losses as the branch condition of the first decision tree. For example, assuming that the minimum value among L(x1), L(x2), L(x3)…L(xn), L(p1), L(p2), L(p3)…and L(pn) is L(x3), then x3 can be used as the branch condition of the first decision tree.

[0086] Next, in step S4, based on the branching conditions of the first decision tree, n groups of training samples can be divided into left leaf nodes and right leaf nodes. In some embodiments, branching conditions can be further added to the left and right leaf nodes of the jth decision tree based on the recursive characteristics of the binary tree, which will not be described in detail. The following embodiments will be exemplified with the maximum number of layers of the decision tree being 2.

[0087] Based on the first decision tree, after n groups of training samples are divided into two branches, the left leaf node and the right leaf node, the prediction values ​​corresponding to the left and right leaf nodes can be calculated based on the mean of the prediction residuals of the samples in the two branches.

[0088] Assume that n=4, the left leaf node contains the first and second training samples, and the right leaf node contains the third and fourth training samples. Then, the prediction value corresponding to the left leaf node is m1=(R1+R2) / 2, and the prediction value corresponding to the right leaf node is m2=(R3+R4) / 2.

[0089] In step S5, the first decision tree after training can be saved. The trained decision tree can include branch conditions, predicted values ​​of leaf nodes, calculation logic of predicted values, and index information of associated samples.

[0090] After the first decision tree is trained, the above steps S1-S6 may be repeated to train the second decision tree.

[0091] When j≥, the j-th learner can be calculated based on the j-1-th learner according to the following formula 1:

[0092] f_j=f_j-1+learning rate*t_j-1 Formula 1

[0093] Where t_j-1 is the predicted value of the leaf node of the j-1th decision tree. The learning rate is used to slow down the learning speed and can be set according to needs, for example, it can be set to 0.1, 0.2, etc.

[0094] Then, when j=2, based on the first learner, the second learner f_2=f_1+learning rate*the leaf node prediction value of the first decision tree. Let's continue with j=2 as an example.

[0095] Next, for each group of training samples, the first decision tree can be traversed to obtain the prediction values ​​of the left and right leaf nodes of the first decision tree and the training samples associated with each leaf node. For example, assuming that the prediction value output by the left leaf node of the first decision tree is m1, and the associated samples are the first group of samples and the second group of samples, and the prediction value of the right leaf is m2, and the associated samples are the third and fourth group of training samples. It can be considered that the prediction value output by the first decision tree for the first group of samples and the second group of samples is m1, and the prediction value output by the first decision tree for the third group of samples and the fourth group of samples is m2.

[0096] Then, according to the above learner update formula 1, it can be known that the second learner f_2 of the first group of samples and the second group of samples is f_1+0.1*m1, and the second learner f_2 of the third group and the fourth group of training samples is f_1+0.1*m2.

[0097] After determining the second learner corresponding to each of the multiple groups of samples, step S2 can be repeated to calculate the new prediction residual Ri`=yi-f_2 for each group of training samples, and based on the calculated new prediction residual, determine the branch condition of the second decision tree from the multiple groups of training samples.

[0098] Accordingly, after the second decision tree is trained, the learner f_3 can be updated based on f_2 to construct a new decision tree. In this embodiment, 5 decision trees, 10 decision trees, or any number of decision trees can be trained until the prediction accuracy of the decision tree is no longer improved.

[0099] After completing the training of multiple decision trees based on the above operations, the initial learner f_1 and the relevant information of the multiple decision trees obtained by training can be saved. Then, when there is a set of data to be predicted, multiple prediction values ​​corresponding to the data to be predicted can be obtained based on multiple decision trees, and combined with the initial learner f_1 and the above formula 1, a new learner is calculated, that is, the final shrinkage prediction result.

[0100] In some optional embodiments, further, the shrinkage prediction model may be tested based on Internet size big data to further optimize the shrinkage prediction model.

[0101] Optionally, the garment sizes of multiple parts of the garment product can be obtained from the product details corresponding to the garment product. Next, according to the category to which the garment product belongs, the cut piece sizes of multiple parts of the garment product are queried in a pre-established size comparison library. The garment size comparison library is also called a pattern library, which stores the correspondence between the part sizes and cut piece sizes of garment products of different categories and patterns.

[0102] Based on the garment sizes and cut sizes of multiple parts of the garment product, the shrinkage rates of multiple parts of the garment product can be calculated as the first shrinkage rate. At the same time, the garment sizes corresponding to the multiple parts of the garment product and the shrinkage rates of the fabrics used in the garment product can be input into the shrinkage prediction model to predict the shrinkage rates of multiple parts of the garment product as the second shrinkage rate. Next, the difference between the first shrinkage rate and the second shrinkage rate is used as the prediction loss of the shrinkage prediction model, and the model parameters of the shrinkage prediction model are optimized according to the prediction loss. The following will be illustrated with a specific example.

[0103] Assume that there is a set of test data [x0, p0, y0]. During testing, [x0, p0] can be input into the shrinkage prediction model. Assume that the shrinkage prediction model contains 10 decision trees, and the 10 decision trees calculate the test data prediction value according to the corresponding branch conditions and the calculation logic of the prediction value. Assume that the prediction values ​​output by the 10 decision trees are y1`, y2`…y10` respectively. Then, the first shrinkage calculated by the shrinkage prediction model for the test data can be: y0`=f_1+0.1(y1`+y2`…+y10`).

[0104] Next, the first shrinkage rate y0` is compared with the second shrinkage rate y0 corresponding to the test data. If the difference between y0` and y0 is less than the set threshold, the model accuracy can be considered to be high; conversely, if the difference between y0` and y0 is greater than or equal to the set threshold, the model accuracy can be considered to be low. At this time, the training decision tree can be continued to be added to improve the accuracy of the final learner.

[0105] The training operation of the above-mentioned shrinkage prediction model can be implemented through SMART (short for Scalable Multiple Additive Regression Tree, which is a Gradient boosting decesion tree, scalable multiple additive regression tree) based on the parameter server (Parameter server, PS). Among them, PS is committed to solving offline and online training tasks of large-scale models. SMART is an implementation of (GBDT) on PS. The SMART implementation based on PS can support training tasks of tens of billions of samples and hundreds of thousands of features, can run on thousands of nodes, and has fault translation function and good stability. At the same time, PS-SMART supports multiple data formats, training objectives and evaluation objectives, as well as output feature importance, and includes optimizations such as histogram approximation to accelerate training, which is conducive to quickly and accurately training the shrinkage prediction model provided in this application.

[0106] It should be noted that in the embodiment of the present application, shrinkage prediction models can be trained for different clothing categories. For example, for the jeans category, a model suitable for predicting the shrinkage of each part of the jeans can be trained; for example, for the down jacket category, a model suitable for predicting the shrinkage of each part of the down jacket can be trained; for another example, for the sportswear category, a model suitable for predicting the shrinkage of each category of sportswear can be trained. When a user requests a shrinkage prediction for an order, the data sent by the terminal device 10 can be input into the corresponding shrinkage prediction model for prediction according to the category to which the order belongs, and no further details are given.

[0107] In the embodiment of the training shrinkage prediction model recorded above, optionally, each group of training samples may further include the shrinkage of clothing obtained from the clothing consumer side. In the daily wear and maintenance of clothing, the size of each part of the clothing will usually change due to the influence of external forces. Based on the size change and the size of the finished garments in each part, the shrinkage of the clothing can be calculated. Furthermore, the shrinkage prediction model can learn how to predict the shrinkage of clothing based on the size of the finished garments in each part of the clothing and the shrinkage of the fabric based on the new training samples, so as to provide the plate maker with more abundant plate making reference information.

[0108] In addition to the reduction ratio prediction system described in the above-mentioned embodiment, the embodiment of the present application also provides a reduction ratio prediction method, which will be exemplarily described below with reference to the accompanying drawings.

[0109] Figure 5 is a flow chart of a method for predicting a shrinkage rate provided by an exemplary embodiment of the present application. When the method is executed on the terminal device side, it may include the following steps: Figure 5 Steps shown:

[0110] Step 501: In response to a shrinkage prediction operation, the sizes of multiple parts of the garment to be processed and the shrinkage of the fabric used in the garment are determined.

[0111] Step 502: Input the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0112] The downscaling prediction operation may be initiated by a user, or may be initiated by other upstream devices, which is not limited in this embodiment.

[0113] In some exemplary embodiments, the method further includes: determining the cutting piece sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts; marking the cutting piece sizes corresponding to each of the multiple parts on the design pattern corresponding to the garment to obtain the cutting piece pattern corresponding to the garment.

[0114] In some exemplary embodiments, a method for determining the garment sizes of multiple parts corresponding to a garment to be processed includes: responding to a size setting operation for the garment, and displaying multiple parts to be set according to the garment category to which the garment belongs; and obtaining size data input by a user for the multiple parts to be set as the garment sizes of the multiple parts corresponding to the garment.

[0115] In some exemplary embodiments, it also includes: responding to a part update operation, obtaining an updated part as the part to be set; wherein the part update operation includes at least one of the following: an operation of deleting an existing part from the multiple parts to be set, an operation of selecting a new part from the parts provided by the clothing category, and an operation of adding a custom part.

[0116] In some exemplary embodiments, a method for determining the ready-made garment sizes of multiple parts corresponding to a garment to be processed includes: in response to a size setting operation for the garment, querying whether there is a historical order corresponding to the garment; if so, obtaining the ready-made garment sizes of multiple parts corresponding to the historical order as the ready-made garment sizes of multiple parts corresponding to the garment.

[0117] In some exemplary embodiments, the shrinkage prediction model is: a regression model based on GBDT; a method of inputting the garment sizes of the multiple parts and the shrinkage of the fabric into the shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, including: in the shrinkage prediction model, for any one of the multiple parts, based on multiple pre-trained decision trees, respectively calculating the predicted values ​​of the leaf nodes corresponding to the shrinkage of the fabric and the garment sizes corresponding to the parts, to obtain multiple predicted values; based on a pre-trained initial learner and a preset learning rate, calculating the multiple predicted values ​​to obtain the predicted shrinkage of the parts.

[0118] In some exemplary embodiments, it also includes: obtaining multiple groups of training samples based on historical pattern making data of multiple different categories of clothing, each group of training samples including the ready-made size of a part of the clothing, the shrinkage of the part, and the shrinkage of the fabric used for the clothing; determining an initial learner based on the multiple groups of training samples; calculating the prediction residuals of each of the multiple groups of training samples according to the initial learner; fitting the prediction residuals of each of the multiple groups of training samples to obtain multiple decision trees; wherein the branch condition of each decision tree is at least one of the ready-made size of the part and the shrinkage of the part included in the multiple groups of training samples; and outputting the shrinkage prediction model including the initial learner and the multiple decision trees.

[0119] In some exemplary embodiments, the method further includes: obtaining the garment sizes of multiple parts of the garment product from the product details corresponding to the garment product; querying the cutting sizes of multiple parts of the garment product in a pre-established size comparison library according to the category to which the garment product belongs; calculating the first shrinkage rates of multiple parts of the garment product according to the garment sizes and cutting sizes of multiple parts of the garment product; inputting the garment sizes corresponding to the multiple parts of the garment product and the shrinkage rates of the fabrics used for the garment product into the shrinkage prediction model to obtain the second shrinkage rates of multiple parts of the garment product; using the difference between the first shrinkage rate and the second shrinkage rate as the prediction loss of the shrinkage prediction model, and optimizing the model parameters of the shrinkage prediction model according to the prediction loss.

[0120] In this embodiment, an automated plate-making auxiliary method is provided, which is suitable for use by clothing plate makers. After obtaining the garment size corresponding to the parts of the garment and the shrinkage of the fabric used for the garment, the shrinkage corresponding to the parts can be predicted based on a pre-trained shrinkage prediction model. Based on the predicted shrinkage of the parts of the garment, the size of the cutting pattern can be quickly determined for generating garment cutting pieces and garment processing. Based on this method, on the one hand, the dependence of the shrinkage calculation operation of the parts of the garment in the garment plate-making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation results of the shrinkage of the parts of the garment can be improved, thereby improving the efficiency of garment plate-making.

[0121] Figure 6 is a flow chart of a method for predicting a reduction ratio provided by another exemplary embodiment of the present application. When the method is executed on the terminal device side, it may include the following steps: Figure 6 Steps shown:

[0122] Step 601: In response to a size setting operation for a clothing order, determine the sizes of multiple parts of the clothing corresponding to the clothing order.

[0123] Step 602: Obtain the shrinkage rate of the fabric used in the clothing order.

[0124] Step 603: Send the garment sizes corresponding to the multiple parts and the shrinkage rate of the fabric to the server, so that the server predicts the predicted shrinkage rates corresponding to the multiple parts based on the shrinkage prediction model.

[0125] Step 604: Receive the predicted reduction ratios corresponding to the multiple parts respectively returned by the server, and display the predicted reduction ratios corresponding to the multiple parts respectively.

[0126] The multiple parts corresponding to the clothing order refer to the multiple parts of the clothing corresponding to the clothing order.

[0127] In some exemplary embodiments, the method further includes: calculating the cutting piece sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts; marking the cutting piece sizes corresponding to each of the multiple parts on the design pattern corresponding to the garment to obtain the cutting piece pattern corresponding to the garment.

[0128] In some exemplary embodiments, a method for determining the garment sizes of multiple parts corresponding to a garment to be processed includes: responding to a size setting operation for the garment, and displaying multiple parts to be set according to the garment category to which the garment belongs; and obtaining size data input by a user for the multiple parts to be set as the garment sizes of the multiple parts corresponding to the garment.

[0129] In some exemplary embodiments, it also includes: responding to a part update operation, obtaining an updated part as the part to be set; wherein the part update operation includes at least one of the following: an operation of deleting an existing part from the multiple parts to be set, an operation of selecting a new part from the parts provided by the clothing category, and an operation of adding a custom part.

[0130] In some exemplary embodiments, a method for determining the ready-made garment sizes of multiple parts corresponding to a garment to be processed includes: in response to a size setting operation for the garment, querying whether there is a historical order corresponding to the garment; if so, obtaining the ready-made garment sizes of multiple parts corresponding to the historical order as the ready-made garment sizes of multiple parts corresponding to the garment.

[0131] In this embodiment, after obtaining the garment size corresponding to the part of the clothing order and the shrinkage rate of the fabric used in the order, the shrinkage rate corresponding to the part of the order can be predicted by the shrinkage rate prediction model pre-trained on the server side. Based on this method, on the one hand, the dependence of the shrinkage rate calculation operation of the part in the clothing plate making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation result of the shrinkage rate of the part can be improved, thereby improving the plate making efficiency of the clothing order.

[0132] Figure 7 is a flow chart of a method for predicting a shrinkage rate provided by another exemplary embodiment of the present application. When the method is executed on the server side, it may include the following steps: Figure 7 Steps shown:

[0133] Step 701: Obtain garment sizes corresponding to multiple parts of a clothing order sent by a terminal device and corresponding fabric shrinkage rates.

[0134] Step 702: Input the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0135] Step 703: Send the predicted shrinkage ratios corresponding to the multiple parts to the terminal device.

[0136] In some exemplary embodiments, the shrinkage prediction model is: a regression model based on GBDT; a method of inputting the garment sizes of the multiple parts and the shrinkage of the fabric into the shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, including: in the shrinkage prediction model, for any one of the multiple parts, based on multiple pre-trained decision trees, respectively calculating the predicted values ​​of the leaf nodes corresponding to the shrinkage of the fabric and the garment sizes corresponding to the parts, to obtain multiple predicted values; based on a pre-trained initial learner and a preset learning rate, calculating the multiple predicted values ​​to obtain the predicted shrinkage of the parts.

[0137] In some exemplary embodiments, it also includes: obtaining multiple groups of training samples based on historical pattern making data of multiple different categories of clothing, each group of training samples including the ready-made size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing; calculating the initial learner based on the multiple groups of training samples; calculating the prediction residuals of each of the multiple groups of training samples according to the initial learner; fitting the prediction residuals of each of the multiple groups of training samples to obtain multiple decision trees; wherein the branch condition of each decision tree is at least one of the ready-made size of the part and the shrinkage rate of the part included in the multiple groups of training samples; and outputting the shrinkage prediction model including the initial learner and the multiple decision trees.

[0138] In some exemplary embodiments, the method further includes: obtaining the garment sizes of multiple parts of the garment product from the product details corresponding to the garment product; querying the cutting sizes of multiple parts of the garment product in a pre-established size comparison library according to the category to which the garment product belongs; calculating the first shrinkage rates of multiple parts of the garment product according to the garment sizes and cutting sizes of multiple parts of the garment product; inputting the garment sizes corresponding to the multiple parts of the garment product and the shrinkage rates of the fabrics used for the garment product into the shrinkage prediction model to obtain the second shrinkage rates of multiple parts of the garment product; using the difference between the first shrinkage rate and the second shrinkage rate as the prediction loss of the shrinkage prediction model, and optimizing the model parameters of the shrinkage prediction model according to the prediction loss.

[0139] In this embodiment, after receiving the garment size corresponding to the part of the order and the shrinkage rate of the fabric used in the order, the shrinkage rate corresponding to the part of the order can be predicted based on the pre-trained shrinkage rate prediction model. On the one hand, the dependence of the shrinkage rate calculation operation of the part in the clothing plate making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation result of the shrinkage rate of the part can be improved, thereby improving the plate making efficiency of the clothing order.

[0140] In addition to the shrinkage prediction method described in the foregoing embodiment, the embodiment of the present application further provides a method for generating a garment cutting pattern, which will be exemplarily described below with reference to the accompanying drawings.

[0141] Figure 8 A schematic diagram of a flow chart of a method for generating a garment pattern according to an exemplary embodiment of the present application is shown in FIG. Figure 8 As shown, the method may include:

[0142] Step 801: respond to a request for generating a cutting pattern corresponding to a garment, and determine garment sizes of a plurality of parts corresponding to the garment and shrinkage rates of fabrics used for the garment.

[0143] Step 802: Input the garment sizes of the multiple parts and the shrinkage rates of the fabric into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to the multiple parts.

[0144] Step 803: Determine the cut piece sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts.

[0145] Step 804: Mark the cutting piece sizes corresponding to the plurality of parts on the design paper pattern corresponding to the garment, and obtain the cutting piece paper pattern corresponding to the garment.

[0146] Among them, based on the ready-made clothing sizes of multiple parts of the clothing and the shrinkage rates of the fabrics used in the clothing, the predicted shrinkage rates corresponding to each of the multiple parts of the clothing are obtained, and the optional implementation method of obtaining the corresponding cutting pattern of the clothing based on the predicted shrinkage rates can be referred to the records of the aforementioned embodiments and will not be repeated here.

[0147] This embodiment can be executed by a terminal device, which may include but is not limited to a mobile phone, a tablet computer, a computer and other devices. Usually, the terminal device may be held by a clothing pattern maker in a clothing factory. Based on the implementation method provided in this embodiment, the pattern maker can quickly generate a cutting pattern corresponding to the clothing based on the terminal device.

[0148] In addition to the shrinkage prediction method described in the foregoing embodiment, the embodiment of the present application also provides a method for processing a clothing order, which will be exemplarily described below with reference to the accompanying drawings.

[0149] Figure 9a A flowchart of a method for processing a clothing order provided by an exemplary embodiment of the present application is shown in FIG. Figure 9a As shown, the method may include:

[0150] Step 901a, responding to a processing request for a clothing order, determining the garment sizes of multiple parts corresponding to the clothing order and the shrinkage rate of the fabric used in the clothing order.

[0151] Step 902a: input the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0152] Step 903a: Determine the cutting pattern corresponding to the clothing order based on the predicted shrinkage rates corresponding to the multiple parts.

[0153] Step 904a: cutting the fabric used in the clothing order according to the cutting piece pattern corresponding to the clothing order to obtain clothing cutting pieces for processing the clothing order.

[0154] Among them, based on the ready-made clothing sizes of multiple parts of the clothing and the shrinkage rates of the fabrics used in the clothing, the predicted shrinkage rates corresponding to each of the multiple parts of the clothing are obtained, and the optional implementation method of obtaining the corresponding cutting pattern of the clothing based on the predicted shrinkage rates can be referred to the records of the aforementioned embodiments and will not be repeated here.

[0155] This embodiment may be executed by a terminal device, or by a specific device or system in a garment processing link in a garment factory, wherein the terminal device may include but is not limited to mobile phones, tablet computers, computers and other devices.

[0156] When this embodiment is executed by a specific device in the garment processing link, the device may integrate multiple functions such as data calculation, pattern drawing, and fabric cutting. Furthermore, based on the steps provided in this embodiment, the shrinkage of each part of the garment corresponding to the garment order can be predicted, and the cutting pattern corresponding to the garment order can be automatically generated based on the predicted shrinkage, and the fabric used in the garment order can be cut based on the cutting pattern.

[0157] Among them, when this implementation is performed by a specific system in the garment processing link, the system can be implemented as a system with a central control function to control other devices to work. For example, the system can control the shrinkage prediction device to predict the shrinkage of each part of the garment corresponding to the garment order, control the pattern drawing device to automatically generate the cutting pattern corresponding to the garment order according to the predicted shrinkage, and control the automatic cutting device to cut the fabric used in the garment order based on the cutting pattern according to the drawn cutting pattern, which will not be repeated.

[0158] Based on this implementation method, automatic processing of clothing orders can be achieved, forming a streamlined automatic operation, further reducing labor costs and improving the efficiency of clothing processing.

[0159] In addition to the methods described in the foregoing embodiments, the embodiments of the present application also provide a method for assisting paper pattern making, which will be exemplarily described below with reference to the accompanying drawings.

[0160] Figure 9bA flow chart of a method for assisting paper sample making provided by an exemplary embodiment of the present application is shown in FIG. Figure 9b As shown, the method may include:

[0161] Step 901b: Determine the attribute information of the garment for which the pattern is to be generated.

[0162] Step 902b: Based on the attribute information, predict the predicted shrinkage corresponding to each part of the clothing.

[0163] Step 903b: display the predicted shrinkage rate to the pattern making user.

[0164] In this embodiment, the attribute information of the clothing includes the size of at least one part of the clothing and the shrinkage rate of the fabric used for the clothing.

[0165] Among them, the optional implementation method of predicting the predicted shrinkage corresponding to each part of the clothing according to the attribute information of the clothing can refer to the description of the above embodiments. For example, the attribute information of the clothing can be input into the shrinkage prediction model described in the above embodiments, and the predicted shrinkage of each part of the clothing can be output by the shrinkage prediction model.

[0166] Based on the predicted shrinkage rate corresponding to each part of the garment, the size of the cut piece of each part of the garment can be determined. For example, in one method of determining the size of the cut piece, the size of the cut piece can be equal to the result of dividing the size of the garment by the predicted shrinkage rate, wherein the size of the garment is known.

[0167] When the predicted shrinkage is displayed to the pattern maker, the size of the cut piece can be directly displayed to the pattern maker, so that the pattern maker can draw the cut piece according to the size of the cut piece. Alternatively, the cut piece size can be used as the size of the pattern making to automatically generate a pattern, and the automatically generated pattern can be displayed to the pattern maker.

[0168] Based on this implementation, an auxiliary tool for pattern making can be provided to pattern making users, which can quickly and accurately generate the cutting piece sizes required for pattern making, or automatically generate patterns for pattern making users, greatly improving the efficiency of clothing pattern making.

[0169] In addition to the methods described in the foregoing embodiments, the embodiments of the present application also provide a method for predicting the deformation amount of clothing, which will be exemplarily described below with reference to the accompanying drawings.

[0170] Fig.9c A flowchart of a method for predicting clothing deformation provided by an exemplary embodiment of the present application is shown in FIG. Fig.9c As shown, the method may include:

[0171] Step 901c: Obtain attribute information of the elastic garment.

[0172] Step 902c: input the attribute information into a prediction model to obtain a prediction value of the deformation amount of at least one part of the elastic garment.

[0173] Step 903c: display the predicted value of the deformation amount of the at least one part to the user.

[0174] In this embodiment, elastic clothing refers to clothing made of elastic fabrics. For example, clothing with a certain degree of elasticity made of artificial elastic fiber fabrics, nylon fabrics, and polyester fabrics. Usually, during the wearing or washing process of the user, the elastic clothing will be subjected to a certain external force, and such external force may cause the elastic clothing to deform. For example, after a certain elastic clothing is worn for a period of time, the cuffs become loose and the neckline becomes enlarged.

[0175] In order to predict the deformation of elastic clothing after wearing, an embodiment of the present application provides a prediction model. The prediction model can be obtained based on a large amount of actual attribute information of elastic clothing and a regression model training of a gradient boosting iterative decision tree.

[0176] The attribute information of the elastic garment may include the garment size of each part of the elastic garment, the shrinkage rate of the fabric of the elastic garment, and the initial elasticity of the fabric.

[0177] When training the prediction model, actual wearing data of the elastic garment can be collected to obtain the deformation of each part of the elastic garment. For example, the deformation of the cuff of the garment can be obtained based on the cuff width when the garment is not worn and the cuff width after being worn for a period of time. For another example, the deformation of the shoulder width of the garment can be obtained based on the shoulder width value when the garment is not worn and the shoulder width value after being worn for a period of time.

[0178] Based on the actual attribute information of the elastic garment and the actual wearing data, multiple sets of training samples can be obtained. Each set of training samples may include: the garment size of the part of the elastic garment, the deformation amount of the part, the shrinkage rate of the fabric used in the elastic garment, and the processed elasticity of the fabric. The optional implementation method of training the regression model of the gradient boosting iterative decision tree based on the training samples can refer to the description of the above-mentioned embodiment, which will not be repeated here.

[0179] Based on this, when users need to predict the deformation rate of elastic clothing, they can quickly predict the deformation of elastic clothing based on the properties of elastic clothing and the prediction model. In some scenarios, clothing pattern makers can use the deformation of elastic clothing as a reference for designing clothing piece sizes when making clothing patterns, so as to avoid serious problems of clothing not fitting properly during subsequent wearing. In other scenarios, clothing consumers can predict the deformation of elastic clothing when purchasing elastic clothing, and use the deformation as a reference for purchase.

[0180] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 601 to 604 can be device A; for another example, the execution subject of steps 601 and 602 can be device A, and the execution subject of step 603 can be device B; and so on.

[0181] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel, and the sequence numbers of the operations, such as 601, 602, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel.

[0182] It should be noted that the descriptions such as “first” and “second” in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit “first” and “second” to different types.

[0183] Fig.10 FIG. 1 is a schematic diagram of the structure of a terminal device provided by an exemplary embodiment of the present application. The terminal device is applicable to the reduction rate prediction system provided by the aforementioned embodiment. Fig.10 As shown, the terminal device includes: a memory 1001, a processor 1002 and a communication component 1003.

[0184] The memory 1001 is used to store computer programs and can be configured to store various other data to support operations on the terminal device. Examples of such data include instructions for any application or method used to operate on the terminal device, contact data, phone book data, messages, pictures, videos, etc.

[0185] The processor 1002 is coupled to the memory 1001 and is used to execute the computer program in the memory 1001, so as to: respond to the shrinkage prediction operation, determine the garment sizes of multiple parts corresponding to the garment to be processed and the shrinkage of the fabric used for the garment; input the garment sizes of the multiple parts and the shrinkage of the fabric into the shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts.

[0186] Further optionally, the processor 1002 is also used to: calculate the cutting piece sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts; mark the cutting piece sizes corresponding to each of the multiple parts on the design pattern corresponding to the garment, and obtain the cutting piece pattern corresponding to the garment.

[0187] Further optionally, when determining the ready-made sizes of multiple parts corresponding to a garment, the processor 1002 is specifically used to: respond to a size setting operation for the garment, and display multiple parts to be set according to the clothing category to which the garment belongs; and obtain size data input by the user for the multiple parts to be set as the ready-made sizes of the multiple parts corresponding to the garment.

[0188] Further optionally, the processor 1002 is also used to: respond to a part update operation, obtain an updated part as the part to be set; wherein the part update operation includes at least one of the following: an operation of deleting an existing part from the multiple parts to be set, an operation of selecting a new part from the parts provided by the clothing category, and an operation of adding a custom part.

[0189] Further optionally, when determining the ready-made clothing sizes of multiple parts corresponding to a garment, the processor 1002 is specifically used to: respond to a size setting operation for the garment, and query whether there is a historical order corresponding to the garment; if so, obtain the ready-made clothing sizes of multiple parts corresponding to the historical order as the ready-made clothing sizes of multiple parts corresponding to the garment.

[0190] In some exemplary embodiments, the shrinkage prediction model is: a regression model based on GBDT; when the processor 1002 inputs the garment sizes of the multiple parts and the shrinkage of the fabric into the pre-trained shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, it is specifically used to: in the shrinkage prediction model, for any part of the multiple parts, based on multiple pre-trained decision trees, respectively calculate the predicted values ​​of the leaf nodes corresponding to the shrinkage of the fabric and the garment size corresponding to the part to obtain multiple predicted values; based on the pre-trained initial learner and the preset learning rate, calculate the multiple predicted values ​​to obtain the predicted shrinkage of the part.

[0191] Further optionally, the processor 1002 is also used to: obtain multiple groups of training samples based on historical pattern making data of multiple different categories of clothing, each group of training samples including the ready-made clothing size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing; calculate the initial learner based on the multiple groups of training samples; calculate the prediction residuals of each of the multiple groups of training samples according to the initial learner; fit the prediction residuals of each of the multiple groups of training samples to obtain multiple decision trees; wherein the branch condition of each decision tree is at least one of the ready-made clothing size of the part and the shrinkage rate of the part included in the multiple groups of training samples; and output the shrinkage prediction model including the initial learner and the multiple decision trees.

[0192] Further optionally, the processor 1002 is also used to: obtain the garment sizes of multiple parts of the garment product from the product details corresponding to the garment product; query the cutting sizes of multiple parts of the garment product in a pre-established size comparison library according to the category to which the garment product belongs; calculate the first shrinkage of multiple parts of the garment product according to the garment sizes and cutting sizes of multiple parts of the garment product; input the garment sizes corresponding to the multiple parts of the garment product and the shrinkage of the fabric used for the garment product into the shrinkage prediction model to obtain the second shrinkage of multiple parts of the garment product; use the difference between the first shrinkage and the second shrinkage as the prediction loss of the shrinkage prediction model, and optimize the model parameters of the shrinkage prediction model according to the prediction loss.

[0193] Further, if Fig.10 As shown, the terminal device also includes: a display component 1004, a power component 1005, an audio component 1006 and other components. Fig.10 Only some components are shown schematically, which does not mean that the terminal equipment only includes Fig.10 Components shown.

[0194] This embodiment provides an automated plate-making auxiliary method suitable for use by clothing plate makers. After obtaining the garment size corresponding to the part of the garment to be processed and the shrinkage rate of the fabric used in the order, the shrinkage rate corresponding to the part of the garment can be predicted based on the pre-trained shrinkage prediction model. Based on the predicted shrinkage rate of the part of the garment, the size of the cutting pattern can be quickly determined for generating garment pieces and garment processing. Based on this method, on the one hand, the dependence of the shrinkage rate calculation operation of the part of the garment in the garment plate-making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation result of the shrinkage rate of the part of the garment can be improved, thereby improving the plate-making efficiency of the garment order.

[0195] In addition to the above execution logic, Fig.10 The terminal device shown can also execute the following logic: the processor 1002 responds to the size setting operation for the clothing order, determines the garment sizes of multiple parts corresponding to the clothing order; obtains the shrinkage rate of the fabric used in the clothing order; sends the garment sizes corresponding to the multiple parts and the shrinkage rate of the fabric to the server through the communication component 1003, so that the server predicts the predicted shrinkage rates corresponding to each of the multiple parts based on a pre-trained shrinkage prediction model; receives the predicted shrinkage rates corresponding to each of the multiple parts returned by the server through the communication component 1003, and displays the predicted shrinkage rates corresponding to each of the multiple parts.

[0196] In addition to the above execution logic, Fig.10The terminal device shown can also execute the following logic: the processor 1002 responds to a request to generate a cutting pattern corresponding to a garment, determines the garment sizes of multiple parts corresponding to the garment and the shrinkage rate of the fabric used for the garment; inputs the garment sizes of the multiple parts and the shrinkage rate of the fabric into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to each of the multiple parts; determines the cutting sizes corresponding to each of the multiple parts according to the predicted shrinkage rates corresponding to each of the multiple parts and the garment sizes of the multiple parts; marks the cutting sizes corresponding to each of the multiple parts on the design pattern corresponding to the garment, and obtains the cutting pattern corresponding to the garment.

[0197] In addition to the above execution logic, Fig.10 The terminal device shown can also execute the following logic: the processor 1002 responds to a processing request for a clothing order, determines the garment sizes of multiple parts corresponding to the clothing order and the shrinkage rates of the fabrics used in the clothing order; inputs the garment sizes of the multiple parts and the shrinkage rates of the fabrics into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to each of the multiple parts; determines the cutting pattern corresponding to the clothing order based on the predicted shrinkage rates corresponding to each of the multiple parts; and cuts the fabrics used in the clothing order according to the cutting pattern corresponding to the clothing order to obtain clothing pieces for processing the clothing order.

[0198] In addition to the above execution logic, Fig.10 The terminal device shown can also execute the following logic: the processor 1002 determines the attribute information of the garment for which the paper pattern is to be generated; based on the attribute information, predicts the predicted shrinkage corresponding to each part of the garment; and displays the predicted shrinkage to the paper pattern making user.

[0199] Further optionally, the displaying of the predicted shrinkage rate to the pattern making user includes: the processor 1002 determines the piece size of each part of the garment based on the predicted shrinkage rate corresponding to each part of the garment; and displays the piece size to the pattern making user, or, uses the piece size as the size for pattern making to generate a pattern and displays it to the pattern making user.

[0200] In addition to the above execution logic, Fig.10 The terminal device shown can also execute the following logic: obtain attribute information of the elastic garment; input the attribute information into a prediction model to obtain a predicted value of the deformation amount of at least one part of the elastic garment; and display the predicted value of the deformation amount of at least one part to the user.

[0201] Accordingly, an embodiment of the present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps that can be executed by a terminal device in the above method embodiment.

[0202] Fig.11 FIG. 1 is a schematic diagram showing the structure of a server provided by an exemplary embodiment of the present application, and the server is applicable to the shrinkage prediction system provided by the aforementioned embodiment. Fig.11 As shown, the server includes: a memory 1101 , a processor 1102 , and a communication component 1103 .

[0203] The memory 1101 is used to store computer programs and can be configured to store various other data to support operations on the server. Examples of such data include instructions for any application or method operating on the server, contact data, phone book data, messages, pictures, videos, etc.

[0204] The processor 1102 is coupled to the memory 1101 and is used to execute the computer program in the memory 1101, so as to: obtain the garment sizes corresponding to multiple parts of the clothing order sent by the terminal device and the corresponding fabric shrinkage rates through the communication component 1103; input the garment sizes of the multiple parts and the shrinkage rates of the fabric into a pre-trained shrinkage prediction model to obtain the predicted shrinkage rates corresponding to each of the multiple parts; and send the predicted shrinkage rates corresponding to each of the multiple parts to the terminal device through the communication component 1103.

[0205] Further optionally, the shrinkage prediction model is: a regression model based on GBDT; when the processor 1102 inputs the garment sizes of the multiple parts and the shrinkage of the fabric into the pre-trained shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, it is specifically used to: in the shrinkage prediction model, for any part of the multiple parts, based on multiple pre-trained decision trees, respectively calculate the predicted values ​​of the leaf nodes corresponding to the shrinkage of the fabric and the garment size corresponding to the part to obtain multiple predicted values; based on the pre-trained initial learner and the preset learning rate, calculate the multiple predicted values ​​to obtain the predicted shrinkage of the part.

[0206] Further optionally, the processor 1102 is also used to: obtain multiple groups of training samples based on historical pattern making data of multiple different categories of clothing, each group of training samples including the ready-made clothing size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing; calculate the initial learner based on the multiple groups of training samples; calculate the prediction residuals of each of the multiple groups of training samples according to the initial learner; fit the prediction residuals of each of the multiple groups of training samples to obtain multiple decision trees; wherein the branch condition of each decision tree is at least one of the ready-made clothing size of the part and the shrinkage rate of the part included in the multiple groups of training samples; and output the shrinkage prediction model including the initial learner and the multiple decision trees.

[0207] Further optionally, the processor 1102 is also used to: obtain the garment sizes of multiple parts of the garment product from the product details corresponding to the garment product; query the cutting sizes of multiple parts of the garment product in a pre-established size comparison library according to the category to which the garment product belongs; calculate the first shrinkage of multiple parts of the garment product according to the garment sizes and cutting sizes of multiple parts of the garment product; input the garment sizes corresponding to the multiple parts of the garment product and the shrinkage of the fabric used for the garment product into the shrinkage prediction model to obtain the second shrinkage of multiple parts of the garment product; use the difference between the first shrinkage and the second shrinkage as the prediction loss of the shrinkage prediction model, and optimize the model parameters of the shrinkage prediction model according to the prediction loss.

[0208] Further, if Fig.11 As shown, the server also includes: a power supply component 1104 and other components. Fig.11 Only some components are shown schematically, which does not mean that the server only includes Fig.11 Components shown.

[0209] In this embodiment, after receiving the garment size corresponding to the part of the order and the shrinkage rate of the fabric used in the order, the shrinkage rate corresponding to the part of the order can be predicted based on the pre-trained shrinkage rate prediction model. On the one hand, the dependence of the shrinkage rate calculation operation of the part in the clothing plate making process on manual experience can be reduced, which is conducive to reducing labor costs. On the other hand, the accuracy of the calculation result of the shrinkage rate of the part can be improved, thereby improving the plate making efficiency of the clothing order.

[0210] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, each step that can be executed by the server in the above method embodiment can be implemented.

[0211] Above Fig.10 and Fig.11 The memory in can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0212] Above Fig.10 and Fig.11The communication component in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component can be implemented based on near field communication (NFC) technology, radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0213] Above Figure 8 The display component in the display device includes a screen, which may include a liquid crystal display component (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0214] Above Fig.10 and Fig.11 The power supply component in the device provides power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply component is located.

[0215] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0216] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0217] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0218] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0219] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0220] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0221] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0222] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0223] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for predicting shrinkage, characterized in that: include: In response to the shrinkage prediction operation, determining the garment sizes of multiple parts corresponding to the garment to be processed and the shrinkage of the fabric used in the garment order; The garment sizes of the multiple parts and the shrinkage rates of the fabric are input into a shrinkage prediction model to obtain predicted shrinkage rates corresponding to each of the multiple parts. The shrinkage prediction model is trained based on multiple groups of training samples, each group of training samples includes the garment sizes of the parts of the garment products, the shrinkage rates of the parts of the garment products, and the shrinkage rates of the fabrics used for the garment products. The shrinkage rates of the parts of the garment products are calculated based on the garment sizes of the parts of the garment products and the size of the cut pieces.

2. The method according to claim 1, characterized in that Also includes: Determining the sizes of the cut pieces corresponding to the plurality of parts according to the predicted shrinkage rates corresponding to the plurality of parts and the garment sizes of the plurality of parts; The cutting piece sizes corresponding to the plurality of parts are marked on the design paper pattern corresponding to the garment to obtain the cutting piece paper pattern corresponding to the garment.

3. The method according to claim 1, characterized in that Determine the finished garment sizes for multiple parts of the garment to be processed, including: In response to a size setting operation for the garment, a plurality of parts to be set are displayed according to the garment category to which the garment belongs; The size data input by the user for the multiple parts to be set are obtained as the garment sizes of the multiple parts corresponding to the garment.

4. The method according to claim 3, characterized in that Also includes: In response to the part update operation, an updated part is obtained as the part to be set; The part updating operation includes at least one of the following: deleting existing parts from among the multiple parts to be set, selecting new parts from the parts provided by the clothing category, and adding custom parts.

5. The method according to claim 1, characterized in that Determine the finished garment sizes for multiple parts of the garment to be processed, including: In response to the size setting operation for the garment, query whether there is a historical order corresponding to the garment; If so, the garment sizes of the multiple parts corresponding to the historical order are obtained as the garment sizes of the multiple parts corresponding to the garment.

6. The method according to any one of claims 1 to 5, characterized in that: The shrinkage prediction model includes: a regression model based on a gradient boosting iterative decision tree; Inputting the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, including: In the shrinkage prediction model, for any one of the multiple parts, based on multiple pre-trained decision trees, the predicted values ​​of leaf nodes corresponding to the shrinkage of the fabric and the garment size corresponding to the part are calculated respectively to obtain multiple predicted values; Based on a pre-trained initial learner and a preset learning rate, the multiple predicted values ​​are calculated to obtain a predicted shrinkage rate of the part.

7. The method according to any one of claims 1 to 5, characterized in that: Also includes: Based on historical pattern-making data of various types of clothing, multiple groups of training samples are obtained, each group of training samples including the finished garment size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing; Determining an initial learner based on the multiple sets of training samples; Calculating the prediction residuals of each of the plurality of training samples according to the initial learner; Fitting the prediction residuals of the plurality of training samples to obtain a plurality of decision trees; wherein the branching conditions of the decision trees are at least one of the garment sizes and shrinkage rates of the parts included in the plurality of training samples; The output includes the initial learner and the shrinkage prediction model of the multiple decision trees.

8. The method according to claim 7, characterized in that Also includes: Obtain the garment sizes of multiple parts of the garment from the product details corresponding to the garment product; According to the category to which the ready-made clothing product belongs, querying the cutting sizes of multiple parts of the ready-made clothing product in a pre-established size comparison database; Calculating first shrinkage rates of multiple parts of the garment product according to garment sizes and cut piece sizes of multiple parts of the garment product; Inputting the garment sizes corresponding to the multiple parts of the garment product and the shrinkage rates of the fabrics used in the garment product into the shrinkage prediction model to obtain the second shrinkage rates of the multiple parts of the garment product; The difference between the first shrinkage ratio and the second shrinkage ratio is used as the prediction loss of the shrinkage ratio prediction model, and the model parameters of the shrinkage ratio prediction model are optimized according to the prediction loss.

9. A method for generating a garment cutting pattern, characterized in that: include: In response to a request for generating a cutting pattern corresponding to a garment, determining garment sizes of a plurality of parts corresponding to the garment and a shrinkage rate of a fabric used for the garment; Inputting the garment sizes of the multiple parts and the shrinkage rates of the fabric into a shrinkage prediction model to obtain predicted shrinkage rates corresponding to the multiple parts, wherein the shrinkage prediction model is trained based on multiple groups of training samples, each group of training samples includes the garment sizes of the parts of the garment products, the shrinkage rates of the parts of the garment products, and the shrinkage rates of the fabrics used for the garment products, and the shrinkage rates of the parts of the garment products are calculated based on the garment sizes of the parts of the garment products and the sizes of the cut pieces; Determining the sizes of cut pieces corresponding to the plurality of parts according to the predicted shrinkage rates corresponding to the plurality of parts and the sizes of garments corresponding to the plurality of parts; The cutting piece sizes corresponding to the plurality of parts are marked on the design paper pattern corresponding to the garment to obtain the cutting piece paper pattern corresponding to the garment.

10. A method for processing clothing orders, characterized in that: include: In response to a processing request for a clothing order, determine the sizes of multiple parts of the garments corresponding to the clothing order and the shrinkage rate of the fabrics used in the clothing order; Inputting the garment sizes of the multiple parts and the shrinkage rates of the fabric into a shrinkage prediction model to obtain predicted shrinkage rates corresponding to the multiple parts, wherein the shrinkage prediction model is trained based on multiple groups of training samples, each group of training samples includes the garment sizes of the parts of the garment products, the shrinkage rates of the parts of the garment products, and the shrinkage rates of the fabrics used for the garment products, and the shrinkage rates of the parts of the garment products are calculated based on the garment sizes of the parts of the garment products and the sizes of the cut pieces; Determining a cutting pattern corresponding to the clothing order based on the predicted shrinkage rates corresponding to the multiple parts; According to the cutting piece pattern corresponding to the clothing order, the fabric used in the clothing order is cut to obtain the clothing cutting pieces used for processing the clothing order.

11. A method for predicting shrinkage, characterized in that: include: In response to a size setting operation for a clothing order, determining garment sizes of multiple parts corresponding to the clothing order; Obtaining the shrinkage rate of the fabric used in the clothing order; Sending the garment sizes corresponding to the multiple parts and the shrinkage rate of the fabric to a server, so that the server predicts the predicted shrinkage rates corresponding to the multiple parts based on a shrinkage rate prediction model, wherein the shrinkage rate prediction model is trained based on multiple groups of training samples, each group of training samples includes the garment sizes of the parts of the garment commodity, the shrinkage rate of the parts of the garment commodity, and the shrinkage rate of the fabric used for the garment commodity, and the shrinkage rate of the parts of the garment commodity is calculated based on the garment sizes of the parts of the garment commodity and the size of the cut piece; The predicted reduction ratios corresponding to the plurality of parts are received from the server, and the predicted reduction ratios corresponding to the plurality of parts are displayed.

12. A method for assisting paper pattern making, characterized in that: include: Determining attribute information of a garment for which a paper pattern is to be generated, wherein the attribute information of the garment includes a garment size of at least one part of the garment and a shrinkage rate of a fabric used for the garment; Inputting the attribute information into a shrinkage prediction model to predict the predicted shrinkage corresponding to each part of the garment, wherein the shrinkage prediction model is trained based on multiple sets of training samples, each set of training samples includes the garment size of a part of a garment product, the shrinkage of the part of the garment product, and the shrinkage of the fabric used for the garment product, and the shrinkage of the part of the garment product is calculated based on the garment size of the part of the garment product and the size of the cut piece; The predicted shrinkage is displayed to the pattern making user.

13. The method according to claim 12, characterized in that The step of displaying the predicted shrinkage rate to the pattern making user includes: Determining the size of the cut pieces for each part of the garment based on the predicted shrinkage corresponding to each part of the garment; The cutting piece size is displayed to the pattern making user, or the cutting piece size is used as the size of the pattern making to generate a pattern and displayed to the pattern making user.

14. A method for predicting clothing deformation, characterized in that: include: Acquiring attribute information of the elastic garment, wherein the attribute information of the garment includes the garment size of at least one part of the garment and the shrinkage rate of the fabric used in the garment; Inputting the attribute information into a shrinkage prediction model to obtain a predicted shrinkage of at least one part of the elastic garment, wherein the shrinkage prediction model is obtained by training based on multiple sets of training samples, each set of training samples includes the garment size of a part of a garment product, the shrinkage of the part of the garment product, and the shrinkage of fabrics used for the garment product, and the shrinkage of the part of the garment product is calculated based on the garment size of the part of the garment product and the size of the cut piece; The predicted value of the deformation amount of each of the at least one part is presented to the user.

15. A method for predicting shrinkage, characterized in that: include: Obtaining garment sizes corresponding to multiple parts of a clothing order sent by a terminal device and corresponding fabric shrinkage rates; Inputting the garment sizes of the multiple parts and the shrinkage rates of the fabric into a shrinkage prediction model to obtain the predicted shrinkage rates corresponding to the multiple parts, wherein the shrinkage prediction model is trained based on multiple groups of training samples, each group of training samples includes the garment sizes of the parts of the garment products, the shrinkage rates of the parts of the garment products, and the shrinkage rates of the fabrics used for the garment products, and the shrinkage rates of the parts of the garment products are calculated based on the garment sizes of the parts of the garment products and the size of the cut pieces; The predicted reduction ratios corresponding to the multiple parts are sent to the terminal device.

16. The method according to claim 15, characterized in that The shrinkage prediction model is: a regression model based on a gradient boosting iterative decision tree; Inputting the garment sizes of the multiple parts and the shrinkage of the fabric into a shrinkage prediction model to obtain the predicted shrinkage corresponding to each of the multiple parts, including: In the shrinkage prediction model, for any one of the multiple parts, based on multiple pre-trained decision trees, the predicted values ​​of leaf nodes corresponding to the shrinkage of the fabric and the garment size corresponding to the part are calculated respectively to obtain multiple predicted values; Based on a pre-trained initial learner and a preset learning rate, the multiple predicted values ​​are calculated to obtain a predicted shrinkage rate of the part.

17. The method according to claim 16, characterized in that Also includes: Based on historical pattern-making data of various types of clothing, multiple groups of training samples are obtained, each group of training samples including the finished garment size of a part of the clothing, the shrinkage rate of the part, and the shrinkage rate of the fabric used for the clothing; Based on the multiple groups of training samples, calculating the initial learner; Calculating the prediction residuals of each of the plurality of training samples according to the initial learner; Fitting the prediction residuals of each of the plurality of training samples to obtain a plurality of decision trees; wherein the branch condition of each decision tree is at least one of the garment size and the shrinkage rate of the parts included in the plurality of training samples; The output includes the initial learner and the shrinkage prediction model of the multiple decision trees.

18. The method according to claim 17, characterized in that Also includes: Obtain the garment sizes of multiple parts of the garment from the product details corresponding to the garment product; According to the category to which the ready-made clothing product belongs, querying the cutting sizes of multiple parts of the ready-made clothing product in a pre-established size comparison database; Calculating first shrinkage rates of multiple parts of the garment product according to garment sizes and cut piece sizes of multiple parts of the garment product; Inputting the garment sizes corresponding to the multiple parts of the garment product and the shrinkage rates of the fabrics used in the garment product into the shrinkage prediction model to obtain the second shrinkage rates of the multiple parts of the garment product; The difference between the first shrinkage ratio and the second shrinkage ratio is used as the prediction loss of the shrinkage ratio prediction model, and the model parameters of the shrinkage ratio prediction model are optimized according to the prediction loss.

19. A terminal device, characterized in that: include: Memory and processor; The memory is used to store one or more computer instructions; The processor is configured to execute the one or more computer instructions to perform the steps in the method according to any one of claims 1-14.

20. A server, characterized in that: include: Memory and processor; The memory is used to store one or more computer instructions; The processor is configured to execute the one or more computer instructions to: perform the steps in the method of any one of claims 15-18.

21. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 14 or the steps of the method described in any one of claims 15 to 18 can be implemented.

Images