Garment design drawing generation method, garment pattern generation method and garment pattern piece generation method

Abstract

The embodiments of the present application provide a garment design drawing generation method, a garment pattern generation method and a garment pattern piece generation method. The garment design drawing generation method comprises: receiving design intent data and / or a design material; performing initialization processing on the design intent data to obtain a visual design drawing, and / or performing encoding processing on the design material to obtain material feature codes; inputting the material feature codes and / or visual design drawing into a pre-constructed generative network to generate a target design drawing; and outputting the target design drawing. It can be seen that in the garment design drawing generation method, design drawing generation can be automatically performed, without the need for manual editing, thereby facilitating an improvement to the design efficiency.

Description

Clothing design drawings, clothing patterns and clothing pattern generation methods

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202311850815.4, filed with the Patent Office of China on December 28, 2023, entitled “A Method and Apparatus for Generating Clothing Design Drawings,” the entire contents of which are incorporated herein by reference.

[0003] This application claims priority to Chinese Patent Application No. 202410203261.7, filed with the Patent Office of China on February 22, 2024, entitled “Clothing Pattern Generation Method, Device, Electronic Device, and Storage Medium,” the entire contents of which are incorporated herein by reference.

[0004] This application claims priority to Chinese patent application number 202410966265.0 filed with the Patent Office of China on July 18, 2024, entitled “Clothing Pattern Generation Method, Device, Electronic Device and Storage Medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0005] The present application relates to the technical fields of data processing, clothing digitization and clothing design, and in particular provides a method for generating clothing design drawings, clothing patterns and clothing patterns. Background Art

[0006] Fashion design is a creative field that requires a wealth of inspiration, continuous experimentation, and iterative editing to achieve a creative space that better reflects creative possibilities and innovative directions. Existing fashion design methods typically require designers to use visualization tools such as hand-drawing and CAD software to visualize design ideas. However, in practice, existing methods have found that they rely on manual editing by designers, which is time-consuming and reduces design efficiency.

[0007] In the traditional apparel industry, constructing clothing pattern representations has always been a major challenge. While the industry has accumulated a vast amount of digital pattern data, much of this data is unstructured, diverse in format, and lacks unified standards. This unstructured nature often requires designers to create new patterns for new garment designs, increasing design costs and extending the design cycle. Furthermore, because pattern production is closely tied to the pattern maker's habits, each pattern maker typically crafts patterns based on their own personal preferences and experience. While this individualized and fragmented inventory management approach facilitates the work of individual pattern makers to a certain extent, from an enterprise-wide perspective, it hinders the standardization of design standards and the effective management and reuse of digital assets. Furthermore, it also results in relatively low efficiency in knowledge transfer and collaboration.

[0008] On the other hand, a comprehensive digital pattern library often includes garment design drawings, patterns (with sewing information), renderings, or photos of finished garments, aiming to detail the garment's structure, size proportions, and design style. Pattern libraries are often used in conjunction with image retrieval algorithms. During the design iteration process, historical pattern data that most closely matches the current design can be retrieved, and iterative changes can be made to this historical data, accelerating the design process.

[0009] Existing retrieval database construction solutions mainly use the Content-Based Image Retrieval (CBIR) method. It allows users to search based on the actual image content, rather than relying on text descriptions or metadata tags around the image. The main purpose of the CBIR system is to retrieve images that are most similar to the query image content from a large image database. However, CBIR systems usually focus on the global features of the image, such as color distribution, texture, and overall shape. When dealing with local changes to an item in the database, their performance may degrade significantly, that is, they cannot modify the components that make up the clothing.

[0010] In the apparel industry, pattern making has always been a significant challenge. With the advancement of technology, traditional manual production methods are gradually revealing their limitations in the context of rapid digitalization and personalized demands. Market demand for more sophisticated and diverse designs continues to grow, but manual pattern making, due to its time-consuming nature, high error rates, and low efficiency, has become unable to meet the requirements of modern clothing production.

[0011] To address this challenge, pattern-making software such as Richpeace utilizes procedural modeling methods based on symbolic programming. These software transform the garment pattern creation process into symbolic drawing based on points, lines, and surfaces. This offers numerous advantages, including easy-to-understand design parameters, support for random variations, high-quality output, and compact representation. Despite this, the template creation process remains complex, requiring not only in-depth pattern-making knowledge but also mathematical reasoning, geometric intuition, and programming skills. This limits its flexibility and universal applicability. This results in high professional requirements for garment pattern preparation and low pattern-making efficiency.

[0012] Application Contents

[0013] In view of this, the purpose of this application is to provide a method for generating clothing design drawings, clothing patterns and clothing plates, which can automatically generate design drawings without the need for manual editing, thereby improving design efficiency; it can be used to implement clothing pattern design based on component-level matching, avoiding the defects caused by content-based direct image retrieval; it can reduce the requirements for professional capabilities in the clothing plate preparation process while improving plate making efficiency.

[0014] The first aspect of the present application provides a method for generating a clothing design drawing, comprising: receiving design intent data and / or design material; initializing the design intent data to obtain a visual design drawing; and / or encoding the design material to obtain a material feature code; inputting the material feature code and / or the visual design drawing into a pre-constructed generation network to generate a target design drawing; and outputting the target design drawing.

[0015] Furthermore, the design intent data includes one or more of natural language description data, style drawings, and line drawings; the design materials include one or more of text materials, image materials, and graphic materials.

[0016] Furthermore, the encoding processing of the design material to obtain the material feature code includes: determining a target encoder corresponding to each of the design materials; wherein the target encoder is a text encoder, an image encoder or a graphic encoder; encoding the design material based on the target encoder to obtain the material feature code.

[0017] Furthermore, the method also includes: modifying the target design drawing in response to a modification instruction for the target design drawing to obtain a modified design drawing; determining the modified design drawing as design intent data, and performing the initialization processing of the design intent data to obtain a visual design drawing; receiving new design materials, and performing the encoding processing of the design materials to obtain material feature codes.

[0018] The second aspect of the present application provides a clothing design drawing generation device, which includes: a receiving unit for receiving design intent data and / or design materials; an initialization unit for initializing the design intent data to obtain a visual design drawing; an encoding unit for encoding the design material to obtain a material feature code; a generation unit for inputting the material feature code and / or the visual design drawing into a pre-constructed generation network to generate a target design drawing; and an output unit for outputting the target design drawing.

[0019] Furthermore, the design intent data includes one or more of natural language description data, style drawings, and line drawings; the design materials include one or more of text materials, image materials, and graphic materials.

[0020] Furthermore, the encoding unit includes: a determination subunit, used to determine the target encoder corresponding to each of the design materials; wherein the target encoder is a text encoder, an image encoder or a graphic encoder; an encoding subunit, used to encode the design material based on the target encoder to obtain a material feature code.

[0021] Furthermore, the clothing design drawing generation device also includes: a modification unit, used to modify the target design drawing in response to a modification instruction for the target design drawing to obtain a modified design drawing; a determination unit, used to determine the modified design drawing as design intent data, and trigger the initialization unit to initialize the design intent data to obtain a visual design drawing; the receiving unit is also used to receive new design materials, and trigger the encoding unit to encode the design materials to obtain material feature codes.

[0022] A third aspect of the present application provides an electronic device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the clothing design drawing generation method described in any one of the first aspects of the present application.

[0023] A fourth aspect of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the method for generating a clothing design drawing described in any one of the first aspects of the present application is executed.

[0024] The beneficial effects of the above technical solution are: the clothing design drawing generation method and device can automatically generate design drawings without the need for manual editing, which is conducive to improving design efficiency.

[0025] In a fifth aspect, the present invention provides a method for generating a clothing pattern, the method comprising: obtaining a digital information carrier of the target clothing; disassembling the digital information carrier of the target clothing into component units to obtain the component units of the target clothing, and determining the clothing pattern of the target clothing based on the component units of the target clothing.

[0026] The method of the fifth aspect of the present application obtains the digital information carrier of the target garment, and then disassembles the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determines the clothing pattern of the target garment based on the component units of the target garment. Compared with the prior art, and compared with the prior art method of directly searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but instead adds a step of disassembling the component units of the target garment, and then obtains the target garment pattern data through the component units of the target garment. In this way, component-level matching can be achieved, avoiding the defects caused by direct content-based image retrieval.

[0027] In the fifth aspect, as an optional implementation, the determining of the clothing pattern of the target garment based on the component unit of the target garment includes: extracting a first feature vector of the component unit of the target garment; obtaining similar component units based on matching of the first feature vector; obtaining stitching lines of the similar component units and pattern information of the similar component units; and determining the clothing pattern of the target garment based on the pattern information of the similar component units and the stitching lines of the similar component units.

[0028] This optional implementation method extracts the first feature vector of the component unit of the target garment, and then can obtain similar component units based on the first feature vector matching, and then can obtain the stitching lines of the similar component units and the pattern information of the similar component units, so as to determine the clothing pattern of the target garment based on the pattern information of the similar component units and the stitching lines of the similar component units.

[0029] In the fifth aspect, as an optional embodiment, the stitching lines of the similar component units are optimized, wherein the optimization of the stitching lines of the similar component units includes modifying the length of the stitching lines of the similar component units and modifying the curvature of the stitching lines of the similar component units.

[0030] This optional embodiment can adjust the length of the suture line and the curvature of the suture line, thereby optimizing the length of the suture line and the curvature of the suture line.

[0031] In the fifth aspect, as an optional implementation, the method further includes: determining the silhouette of the target garment based on the digital information carrier of the target garment; and determining the clothing pattern of the target garment based on the silhouette of the target garment.

[0032] This optional implementation manner may also determine the silhouette of the target garment based on the digital information carrier of the target garment, thereby determining the clothing version of the target garment based on the silhouette of the target garment.

[0033] In the fifth aspect, as an optional implementation, the method further includes: constructing a pattern library, the pattern library including at least a component unit library, a component relationship library, a component feature library and a silhouette feature library, the component unit library is used to match the similar component units, the component relationship library is used to match the stitching lines of the similar component units, the component feature library is used to match the pattern information of the similar component units, and the silhouette feature library is used to extract the silhouette of the target garment.

[0034] This optional implementation can construct a component unit library for matching similar component units, a component relationship library for matching the seams of similar component units, a component feature library for matching the pattern information of similar component units, and a silhouette feature library for extracting the silhouette of the target garment. By constructing a pattern library, existing clothing design resources can be integrated and digitized, thereby improving the utilization rate of clothing design resources and reducing barriers to sharing clothing design resources. Furthermore, the pattern library can improve pattern design efficiency.

[0035] In the fifth aspect, as an optional implementation, the constructing of the pattern library includes: acquiring clothing pattern data; and constructing the pattern library based on the clothing pattern data.

[0036] This optional implementation manner can obtain clothing pattern data, thereby constructing the pattern library based on the clothing pattern data.

[0037] In the fifth aspect, as an optional implementation, the constructing of the pattern library based on the clothing pattern data includes: extracting clothing stitching relationships based on the clothing pattern data, and constructing the component relationship library based on the clothing stitching relationships; disassembling component units based on the clothing pattern data to obtain component disassembly results and constructing the component unit library based on the component disassembly results.

[0038] This optional implementation can extract the garment stitching relationship based on the garment pattern data and construct the component relationship library based on the garment stitching relationship. On the other hand, it can disassemble the component units based on the garment pattern data to obtain the component disassembly results and construct the component unit library based on the component disassembly results.

[0039] In the fifth aspect, as an optional implementation, the method further includes: extracting a global contour based on clothing pattern data; performing feature encoding on the global contour based on a feature learning algorithm to obtain a second feature encoding result; and constructing the silhouette feature library based on the second feature encoding result.

[0040] This optional implementation can extract the global contour based on the clothing pattern data, and then can perform feature encoding on the global contour based on the feature learning algorithm to obtain a second feature encoding result, and then can construct the silhouette feature library based on the second feature encoding result.

[0041] In the fifth aspect, as an optional implementation, the matching based on the first feature vector to obtain similar component units includes: matching a number of preselected elements in the component feature library based on the first feature vector of the target clothing; calculating the similarity between each of the preselected elements and the first feature vector of the target clothing; determining the highest similarity element based on the similarity between each of the preselected elements and the first feature vector of the target clothing; and determining the similar component unit based on the highest similarity element.

[0042] This optional implementation can match a number of preselected elements in the component feature library based on the first feature vector of the target garment, and then by calculating the similarity between each of the preselected elements and the first feature vector of the target garment, it can determine the highest similarity element based on the similarity between each of the preselected elements and the first feature vector of the target garment, thereby determining the similar component unit based on the highest similarity element.

[0043] In the fifth aspect, as an optional implementation, the method further includes: obtaining modification and editing information of the clothing pattern of the target clothing; and modifying the clothing pattern of the target clothing based on the modification and editing information.

[0044] This optional implementation method obtains modification and editing information of the clothing pattern of the target clothing, and then can modify the clothing pattern of the target clothing based on the modification and editing information, thereby facilitating the designer to perform secondary modifications on the target clothing.

[0045] In a sixth aspect, the present invention provides a clothing pattern generating device, comprising: an acquisition module for acquiring a digital information carrier of the target clothing; a disassembly module for disassembling the digital information carrier of the target clothing into component units to obtain the component units of the target clothing, and determining the clothing pattern of the target clothing based on the component units of the target clothing.

[0046] The device of the sixth aspect of the present application obtains the digital information carrier of the target garment, and then disassembles the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determines the clothing pattern of the target garment based on the component units of the target garment. Compared with the prior art, and compared with the prior art method of directly searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but instead adds a step of disassembling the component units of the target garment, and then obtains the target clothing pattern data through the component units of the target garment. In this way, component-level matching can be achieved, avoiding the defects caused by direct content-based image retrieval.

[0047] In a seventh aspect, the present invention provides an electronic device, comprising: a processor; and

[0048] The memory is configured to store machine-readable instructions, which, when executed by the processor, execute the clothing pattern generation method as described in any one of the aforementioned embodiments.

[0049] The electronic device of the seventh aspect of the present application, by executing the clothing pattern generation method, can obtain the digital information carrier of the target clothing, and then can disassemble the digital information carrier of the target clothing into component units to obtain the component units of the target clothing, and determine the clothing pattern of the target clothing based on the component units of the target clothing. Compared with the prior art, and relative to the prior art method of directly searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but adds a step of disassembling the component units of the target clothing, and then obtains the target clothing pattern data through the component units of the target clothing. In this way, component-level matching can be achieved, avoiding the defects caused by direct image retrieval based on content.

[0050] In an eighth aspect, the present invention provides a storage medium storing a computer program, wherein the computer program is executed by a processor to generate a clothing pattern as described in any one of the aforementioned embodiments.

[0051] The storage medium of the eighth aspect of the present application can obtain the digital information carrier of the target garment by executing the clothing pattern generation method, and then can disassemble the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determine the clothing pattern of the target garment based on the component units of the target garment. Compared with the prior art, and relative to the prior art method of directly searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but adds a step of disassembling the component units of the target garment, and then obtains the target garment pattern data through the component units of the target garment. In this way, component-level matching can be achieved, avoiding the defects caused by direct image retrieval based on content.

[0052] In the ninth aspect, an embodiment of the present application provides a method for generating clothing patterns, including: receiving a clothing design language, converting the clothing design language into a symbolic pattern-making language using a target language parsing model; converting the symbolic pattern-making language into a drawing command corresponding to a target pattern-making software using a target symbol translation model; and determining a target clothing pattern based on the drawing command.

[0053] Compared with the related art, in the clothing pattern generation method provided in the embodiment of the present application, after receiving the clothing design language input by the user, the clothing design language is converted into a drawing command corresponding to the target pattern making software through the target language parsing model and the target symbol translation model, and finally the target clothing pattern is obtained by making a pattern according to the drawing command. The user only needs to input the clothing design language when making the pattern. The clothing design language can be, for example, natural language, design manuscripts, photos, etc., thereby reducing the requirements for professional ability in the clothing pattern preparation process; at the same time, due to the high degree of automation of the entire pattern making process, the user can perform a large amount of clothing pattern making work at the same time, thereby improving the overall pattern making efficiency; in addition, since the conversion logic of converting the clothing design language into the symbolic pattern making language is quite different from the conversion logic of converting the symbolic pattern making language into the drawing command, the target language parsing model is first used to convert the clothing design language into the symbolic pattern making language, and then the target symbol translation model is used to convert the symbolic pattern making language into the drawing command. With the symbolic pattern making language as the intermediary, the operating logic of the target language parsing model and the target symbol translation model can be made clearer, the training process is simpler, and the amount of data required for training is also smaller.

[0054] In an optional embodiment, before using the target symbol translation model to convert the symbolic pattern-making language into drawing commands, the garment pattern-making method further comprises: determining the target symbol translation model based on the target pattern-making software. For different types of target pattern-making software, the corresponding target symbol translation model is selected to generate pattern-making commands. Each target symbol translation model is only used to generate drawing commands corresponding to one type of target pattern-making software, thereby preventing the target symbol translation model from confusing the grammatical rules of different types of pattern-making software, reducing the possibility that the target symbol translation model generates drawing commands that do not comply with the grammatical rules of the target pattern-making software, and making the pattern-making commands generated by the target symbol translation model more compatible with the target pattern-making software used in subsequent steps, thereby improving the pattern-making quality of the target pattern-making software.

[0055] In an optional embodiment, the target symbol translation model is determined based on the target board-making software, including: obtaining the target board-making grammar rules of the target board-making software; obtaining the initial symbol translation model; and performing model training on the initial symbol translation model using the target board-making grammar rules to obtain the target symbol translation model. Real-time acquisition of the target board-making grammar rules of the target board-making software for model training of the target symbol translation model allows the target symbol translation model to be changed accordingly when the target board-making grammar rules change, further making the board-making commands generated by the target symbol translation model more compatible with the target board-making software, thereby improving the board-making quality of the target board-making software.

[0056] In an optional embodiment, determining the target symbol translation model based on the target board-making software includes: obtaining a preset symbol translation model list, the preset symbol translation model list including a plurality of sample symbol translation models and sample board-making software corresponding to each of the sample symbol translation models; and determining the sample symbol translation model corresponding to the target board-making software in the preset symbol translation model list as the target symbol translation model. A symbol translation model list is pre-set, including a plurality of trained sample symbol translation models and sample board-making software corresponding to each of the sample symbol translation models. When determining the target symbol translation model, the sample symbol translation model corresponding to the target board-making software in the symbol translation model list is directly used as the target symbol translation model, eliminating the need to retrain the model and improving the efficiency of determining the target symbol translation model.

[0057] In an optional embodiment, determining a target garment pattern according to the drawing command includes: inputting the drawing command into the target pattern-making software, receiving a garment pattern generated by the target pattern-making software; using a quality inspection model to determine whether the garment pattern complies with a preset pattern-making rule; if the garment pattern does not comply with the preset pattern-making rule, adjusting the drawing command according to the preset pattern-making rule, inputting the adjusted drawing command into the target pattern-making software, receiving the target garment pattern generated by the target pattern-making software; if the garment pattern complies with the preset pattern-making rule, using the garment pattern as the target garment pattern. After generating the garment pattern according to the drawing command, using the quality inspection model to inspect the generated garment pattern to determine whether the garment pattern complies with the preset pattern-making rule; if the garment pattern does not comply with the preset pattern-making rule, adjusting the drawing command according to the preset pattern-making rule, and again generating the target garment pattern according to the adjusted drawing command, so that the generated target garment pattern better complies with the preset pattern-making rule, thereby improving the pattern-making quality of the target garment pattern.

[0058] In an optional embodiment, the target language parsing model and the quality inspection model are a multimodal large model. Using the same multimodal large model can reduce the model training process and training requirements, improve board manufacturing efficiency, and reduce board manufacturing costs.

[0059] In an optional embodiment, the garment pattern generation method further includes: receiving a modified garment design language, converting the modified garment design language into a modified garment design language using the target language parsing model; converting the modified symbolic pattern-making language into a modified drawing command using the target symbol translation model; and modifying the target garment pattern according to the modified drawing command. After generating the target garment pattern, the method further includes receiving a modified garment design language input by a user, and generating a modified drawing command according to the modified garment design language to modify the target garment pattern, thereby achieving convenient modification of the target garment pattern.

[0060] In the tenth aspect, an embodiment of the present application provides a clothing pattern generation device, including: a language parsing module, the language parsing module is used to receive a clothing design language, and use a target language parsing model to convert the clothing design language into a symbolic pattern making language; a symbol translation module, the symbol translation module is used to use a target symbol translation model to convert the symbolic pattern making language into a drawing command; a pattern making module, the pattern making module is used to use a target pattern making software to determine a target clothing pattern according to the drawing command.

[0061] Compared with the prior art, in the clothing pattern generation device provided by the embodiment of the present application, after the language parsing module receives the clothing design language input by the user, the clothing design language is converted into a drawing command through the target language parsing model in the language parsing module and the target symbol translation model in the symbol translation module. Finally, the pattern making software in the pattern making module is used to make a pattern according to the drawing command to obtain the target clothing pattern. The user only needs to input the clothing design language when making the pattern. The clothing design language can be, for example, natural language, design manuscripts, photos, etc., thereby reducing the requirements for professional ability in the clothing pattern preparation process; at the same time, due to the high degree of automation of the entire pattern making process, the user can perform a large amount of clothing pattern making work at the same time, thereby improving the overall pattern making efficiency.

[0062] In the eleventh aspect, an embodiment of the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the clothing pattern generation method as described above.

[0063] In a twelfth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the aforementioned garment pattern generation method.

[0064] In a thirteenth aspect, an embodiment of the present application provides a computer program product, which includes a computer program code. When the computer program code is executed by a computer device, the computer device executes the clothing pattern generation method as described above.

[0065] Other features and advantages of the present application will be described in the following description. The purpose and other advantages of the present application can be realized and obtained through the structures specifically pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be considered as limiting the scope. For those skilled in the art, other relevant drawings can be obtained based on these drawings without inventive effort. The above and other purposes, features, and advantages of the present application will be more clearly illustrated through the drawings.

[0067] FIG1 is a flow chart of a method for generating a clothing design drawing according to an embodiment of the present application;

[0068] FIG2 is a flow chart of another method for generating a clothing design drawing according to an embodiment of the present application;

[0069] FIG3 is a schematic diagram of the structure of a clothing design drawing generating device provided in an embodiment of the present application;

[0070] FIG4 is a schematic diagram of the structure of another device for generating clothing design drawings provided in an embodiment of the present application;

[0071] FIG5 is a flow chart of a portion of a method for generating a clothing design drawing provided in an embodiment of the present application;

[0072] FIG6 is a schematic diagram of a process for generating a material feature code based on a design material according to an embodiment of the present application;

[0073] FIG7 is a schematic diagram of a process for generating a clothing design drawing based on a generative model according to an embodiment of the present application;

[0074] FIG8 is a flow chart of a method for generating a garment pattern disclosed in an embodiment of the present application;

[0075] FIG9 is a schematic diagram of constructing a garment pattern disclosed in an embodiment of the present application;

[0076] FIG10 is a flow chart of a feature matching disclosed in an embodiment of the present application;

[0077] FIG11 is a schematic diagram of another embodiment of the present application for constructing a clothing pattern

[0078] FIG12 is a schematic diagram of a construction pattern library disclosed in an embodiment of the present application;

[0079] FIG13 is a schematic structural diagram of a garment pattern generating device disclosed in an embodiment of the present application;

[0080] FIG14 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application;

[0081] FIG15 is a flow chart of a method for generating garment patterns according to the first embodiment of the present application;

[0082] FIG16 is a schematic diagram of design drawings and garment photos in the garment pattern generation method provided in Example 1 of the present application;

[0083] FIG17 is a schematic diagram of the structure of the target language parsing model in the clothing pattern generation method provided in Example 1 of the present application;

[0084] FIG18 is a flow chart of a method for generating garment patterns according to another embodiment of the present application;

[0085] FIG19 is a schematic diagram of a process for determining a target garment pattern in the garment pattern generation method provided in Example 1 of the present application;

[0086] FIG20 is a flow chart of a method for generating garment patterns according to a second embodiment of the present application;

[0087] FIG21 is a schematic diagram of the structure of a garment pattern generating device provided in Example 3 of the present application;

[0088] Figure 22 is a schematic diagram of the structure of the electronic device provided in Example 4 of the present application. DETAILED DESCRIPTION

[0089] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The following embodiments can be used as examples to more clearly illustrate the technical solutions of the present application, and cannot be used to limit the scope of protection of the present application. In addition, if the terms "first", "second", etc. appear, they are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. It will be understood by those skilled in the art that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other.

[0090] Example 1

[0091] Please refer to Figure 1, which is a flow chart of a method for generating a clothing design drawing provided by this embodiment. The method for generating a clothing design drawing includes:

[0092] S101: Receive design intent data and / or design materials.

[0093] In this embodiment, the design intent data includes one or more of natural language description data, style drawings, and line drawings.

[0094] In this embodiment, the design material includes one or more of text material, image material, and graphic material.

[0095] S102: Initialize the design intent data to obtain a visual design drawing; and / or encode the design material to obtain a material feature code.

[0096] S103: Inputting the material feature code and / or the visual design drawing into a pre-built generation network to generate a target design drawing.

[0097] S104: Output the target design drawing.

[0098] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and this is not limited in this embodiment.

[0099] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0100] As can be seen, the method for generating clothing design drawings described in this embodiment can identify the design intent of a designer or user and quickly output a visual design based on that intent, thereby intuitively expressing creative ideas. Furthermore, this method supports multiple sources of material, allowing design details from multiple sources to be integrated, thereby achieving a more diverse, clear, and controllable design creative space and improving the effectiveness of design drawing generation.

[0101] Example 2

[0102] Please refer to Figure 2, which is a flow chart of a method for generating a clothing design drawing provided by this embodiment. The method for generating a clothing design drawing includes:

[0103] S201 , receiving design intent data and / or design materials, and executing steps S202 and / or S203 - S204 .

[0104] In this embodiment, the design intent data includes one or more of natural language description data, style drawings, and line drawings.

[0105] In this embodiment, the design material includes one or more of text material, image material, and graphic material.

[0106] S202: Initialize the design intent data to obtain a visual design drawing, and execute step S205.

[0107] In this embodiment, the method initializes the design intent and converts it into a visual design drawing. Specifically, the method can identify the content in the design intent data and initialize the design based on it through a generative model to obtain a visual design drawing. This process can accept user interaction to achieve interactive initialization effects; alternatively, the visual design drawing can be automatically generated by the generative model.

[0108] In this embodiment, generating a visual design diagram by generating a model is the core step of this application. In a computer system, the unit that executes this process can be regarded as a minimum design unit, and its diagram can be shown in Figure 5.

[0109] By implementing steps S201 to S202, we can initially understand the designer and user's intentions (design ideas, design creativity), and obtain a visual design drawing that can meet the design preview effect, thereby achieving the effect of intuitive expression. Specifically, the specific effects contained in the visual design drawing may include: the design's color, craftsmanship, details, texture, etc.

[0110] S203. Determine a target encoder corresponding to each design material; wherein the target encoder is a text encoder, an image encoder, or a graphic encoder.

[0111] In this embodiment, the target encoder is a model that converts the relevant material into the corresponding code. This model is a model that has been trained using model enhancement data from vertical industries such as fashion, clothing, design, and fabrics. As can be seen, this model is generally more professional and targeted. At the same time, this model can also better keep up with current trends and creativity, achieving stronger feature expression capabilities.

[0112] S204: Encode the design material based on the target encoder to obtain the material feature code, and execute step S205.

[0113] S205: Input the material feature code and / or the visual design diagram into the pre-built generation network to generate a target design diagram.

[0114] In this embodiment, for the style design drawing after the design intent is converted, the method can give more inspiration material input (i.e., output design material) so as to integrate more creative elements into the design drawing and generate a target design drawing that better meets the design requirements.

[0115] In this embodiment, the method supports the joint action of single or multiple text, images, graphics and other material carriers, wherein the text, images, graphics and the like are encoded using encoders of different modes to obtain tensorized features.

[0116] Figure 6 shows a schematic diagram of a process for generating feature codes based on design materials. This process demonstrates that this method can unify and integrate information from inspiration materials of different modalities, providing more effective and deterministic prior information for the generative model, thereby facilitating better generation of target design drawings.

[0117] S206: Output the target design drawing.

[0118] Implementing steps S203 to S206 can achieve the fusion of input information from different modalities, different design materials, different inspiration sources, etc., thereby achieving the effect of integrating design elements, and then enabling the generated model to widely absorb the space of design elements, and realize the editing, modification and effect optimization of the overall global effect and local detail effects of the design drawing.

[0119] Specifically, because the generative model can accurately and controllably capture design elements and iteratively edit them with the design drawing, the resulting target design drawing can better meet design requirements and achieve a richer, more intuitive and three-dimensional display effect.

[0120] S207 : Modify the target design drawing in response to the modification instruction for the target design drawing to obtain a modified design drawing.

[0121] S208: Determine the modified design drawing as design intent data, and execute step S202; and / or receive new design material, and execute step S203.

[0122] In this embodiment, the method can realize iterative and repeated modification and editing of style design drawings, thereby realizing the enhanced design of design intent and ultimately obtaining a target design drawing that better meets the needs.

[0123] In this embodiment, since each iteration can incorporate more design intentions and creative ideas, this method can more flexibly achieve design divergence or design convergence. This shows that this method has a wide range of applicable scenarios and strong practicality.

[0124] In addition, this method can also achieve design drawing editing effects of different granularities in the iterative process through global editing, local editing, etc., thereby further improving the implementation freedom and expression accuracy of the method, and thus meeting the design drawing editing needs of designers and users in more different scenarios.

[0125] Please refer to Figure 7, which shows a schematic diagram of a process for generating clothing design drawings based on a generative model. This method enables rapid design, supplementation, improvement, and secondary editing of design drawings, thereby enabling multiple iterations of clothing design drawings and outputting diverse and creative clothing design effects to meet the needs of different design groups, including designers.

[0126] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and this is not limited in this embodiment.

[0127] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0128] It can be seen that the implementation of the clothing design drawing generation method described in this embodiment can identify the design intent of the designer or user, and quickly output the visual style design effect based on the design intent, thereby achieving the effect of intuitively expressing creative ideas. At the same time, the method supports multiple material sources, so that the design details under multiple sources can be integrated together, thereby achieving a more diverse, clear, and controllable design creative space, and improving the generation effect of the design drawing. Finally, the method also supports iterative editing and modification of the design drawing, realizing the progressive editing and improvement of the design drawing, thereby facilitating the targeted understanding of the design intent, thereby improving the expression effectiveness of the design rendering.

[0129] Example 3

[0130] Please refer to Figure 3, which is a schematic diagram of the structure of a clothing design drawing generation device provided by this embodiment. As shown in Figure 3, the clothing design drawing generation device includes:

[0131] Receiving unit 110, for receiving design intent data and / or design materials;

[0132] Initialization unit 120, used to initialize the design intent data to obtain a visual design drawing;

[0133] The encoding unit 130 is used to encode the design material to obtain a material feature code;

[0134] The generation unit 140 is used to input the material feature code and / or the visual design diagram into the pre-built generation network to generate the target design diagram;

[0135] The output unit 150 is used to output the target design drawing.

[0136] In this embodiment, the explanation of the clothing design drawing generating device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0137] As can be seen, the clothing design drawing generation device described in this embodiment can identify the design intent of a designer or user and quickly output a visual style design effect based on the design intent, thereby achieving the effect of intuitively expressing creative ideas. At the same time, the device supports multiple material sources, allowing design details from multiple sources to be integrated, thereby achieving a more diverse, clear, and controllable design creative space, and improving the generation effect of design drawings.

[0138] Example 4

[0139] Please refer to Figure 4, which is a schematic diagram of the structure of a clothing design drawing generation device provided by this embodiment. As shown in Figure 4, the clothing design drawing generation device includes:

[0140] Receiving unit 110, for receiving design intent data and / or design materials;

[0141] Initialization unit 120, used to initialize the design intent data to obtain a visual design drawing;

[0142] The encoding unit 130 is used to encode the design material to obtain a material feature code;

[0143] The generation unit 140 is used to input the material feature code and / or the visual design diagram into the pre-built generation network to generate the target design diagram;

[0144] The output unit 150 is used to output the target design drawing.

[0145] In this embodiment, the design intent data includes one or more of natural language description data, style drawings, and line drawings;

[0146] Design materials include one or more of text materials, image materials, and graphic materials.

[0147] As an optional implementation, the encoding unit 130 includes:

[0148] The determination subunit 131 is used to determine the target encoder corresponding to each design material; wherein the target encoder is a text encoder, an image encoder or a graphic encoder;

[0149] The encoding subunit 132 is used to encode the design material based on the target encoder to obtain material feature code.

[0150] As an optional embodiment, the clothing design drawing generating device further includes:

[0151] A modification unit 160 is configured to modify the target design drawing in response to a modification instruction for the target design drawing to obtain a modified design drawing;

[0152] The determining unit 170 is configured to determine the modified design drawing as the design intent data and trigger the initializing unit 120 to initialize the design intent data to obtain a visual design drawing;

[0153] The receiving unit 110 is further configured to receive new design materials and trigger the encoding unit 130 to encode the design materials to obtain material feature codes.

[0154] In this embodiment, the explanation of the clothing design drawing generating device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0155] It can be seen that the clothing design drawing generation device described in this embodiment can identify the design intent of the designer or user and quickly output the visual style design effect based on the design intent, thereby achieving the effect of intuitively expressing creative ideas. At the same time, the device supports multiple material sources, so that the design details under multiple sources can be integrated together, thereby achieving a more diverse, clear, and controllable design creative space, and improving the generation effect of the design drawing. Finally, the device also supports iterative editing and modification of the design drawing, realizing the progressive editing and improvement of the design drawing, thereby facilitating the targeted understanding of the design intent and thereby improving the effectiveness of the expression of the design rendering.

[0156] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the clothing design drawing generation method in embodiment 1 or embodiment 2 of the present application.

[0157] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the clothing design drawing generation method in embodiment 1 or embodiment 2 of the present application is executed.

[0158] Example 5

[0159] Please refer to FIG8 , which is a flowchart of a method for generating a garment pattern disclosed in an embodiment of the present application. As shown in FIG8 , the method of the embodiment of the present application includes the following steps:

[0160] S301, obtaining a digital information carrier of a target garment;

[0161] S302: Decomposing the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determining the garment pattern of the target garment based on the component units of the target garment.

[0162] The method of the embodiment of the present application obtains the digital information carrier of the target garment, and then disassembles the digital information carrier of the target garment into component units to obtain the component units of the target garment, and then determines the clothing pattern of the target garment based on the component units of the target garment. Compared with the existing technology, and compared with the existing technology that directly searches for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but adds a step of disassembling the component units of the target garment, and then obtains the target clothing pattern data through the component units of the target garment. In this way, it can achieve component-level matching and avoid the defects caused by direct content-based image retrieval.

[0163] In the embodiments of the present application, as an example, assuming that a pattern maker needs to make a pattern for shirt style A, the pattern maker can use the digital information carrier of shirt style A as input to decompose shirt style A into component units, for example, decomposing shirt style A into collar component units, waist component units, etc. Finally, a garment pattern for shirt style A is generated based on the decomposition results.

[0164] Furthermore, in some scenarios, if the clothing pattern of style A shirt is different from the pattern envisioned by the pattern designer, the pattern designer needs to make secondary modifications to the matched clothing pattern of style A shirt. According to the existing technology, the clothing pattern for style A shirt is not obtained through component-level matching, but is obtained through direct image search. In this way, the pattern designer cannot make secondary modifications to the specified component unit. However, for this application, it is assumed that the clothing pattern of style A shirt includes component unit S1 and component unit S2 that constitute style A shirt. At this time, the pattern designer can replace component unit S1 of style A shirt with component unit S3 as needed, without having to redefine the pattern of component unit S2. It can be seen that the existing technology directly obtains the pattern of style A shirt based on the picture, and does not decompose its structure into several component units, so it is difficult to independently make secondary modifications to a certain component unit, while this application can make secondary modifications to a certain component unit.

[0165] In an embodiment of the present application, the clothing pattern of the target garment can be used to construct a three-dimensional model of the target garment, thereby displaying the finished garment of the target garment.

[0166] In the embodiment of the present application, the target clothing may be shirts, cotton-padded jackets and other clothing of different styles.

[0167] In an embodiment of the present application, the digital information carrier of the target garment can be a picture of the target garment, a design sketch of the target garment, or a pattern design drawing of the target garment, wherein the pattern design drawing of the target garment can be incomplete, and then the complete pattern of the target garment can be obtained through the pattern library. Of course, the pattern design drawing of the target garment can be complete, and then the pattern design drawing of the target garment can be represented by digital information through the pattern library.

[0168] In the embodiments of the present application, please refer to Figure 9, which is a schematic diagram of a method for constructing a garment pattern disclosed in the embodiments of the present application. As shown in Figure 9, a pattern designer can use a garment pattern sample or a garment style image as the digital information carrier of the target garment, and then obtain a garment pattern representation of the target garment by disassembling component units or load units, encoding auxiliary components, and matching garment components.

[0169] In the embodiment of the present application, as an optional implementation, step: determining the garment pattern of the target garment based on the component units of the target garment includes the following sub-steps:

[0170] Extracting the first feature vector of the component unit of the target garment;

[0171] Obtaining similar component units based on the first feature vector matching;

[0172] Obtaining stitching lines of similar component units and pattern information of similar component units;

[0173] The garment pattern of the target garment is determined based on pattern information of the similar component units and stitching lines of the similar component units.

[0174] This optional implementation method extracts the first feature vector of the component unit of the target garment, and then can obtain similar component units based on the first feature vector matching, and then can obtain the stitching lines of the similar component units and the pattern information of the similar component units, so as to determine the clothing pattern of the target garment based on the pattern information of the similar component units and the stitching lines of the similar component units.

[0175] For the above optional implementation, please refer to Figure 10 for example, which is a feature matching flow chart disclosed in an embodiment of the present application. As shown in Figure 10, by disassembling the component units, the feature vectors of the collar, body, and sleeves can be extracted based on the disassembly results. The feature vectors of the collar, body, and sleeves are vectors in the first feature vector. Furthermore, the first feature vector can be used to match component units similar to the target garment, i.e., the component matching results.

[0176] In an embodiment of the present application, as an optional implementation, the step is: adjusting the stitching lines of similar component units, wherein the adjustment of the stitching lines of similar component units includes modifying the length of the stitching lines of similar component units and modifying the curvature of the stitching lines of similar component units.

[0177] This optional embodiment can adjust the length of the suture line and the curvature of the suture line, thereby optimizing the length of the suture line and the curvature of the suture line.

[0178] Regarding the above-mentioned optional implementation, please refer to Figure 11, which is a schematic diagram of another method for constructing a garment pattern according to an embodiment of the present application. As shown in Figure 11, after the stitching relationships are synthesized, the component relationships can be optimized, that is, the stitching length and stitching curvature can be adjusted based on the component feature library. The component feature library can record the stitching length and stitching curvature corresponding to each component style.

[0179] In the embodiment of the present application, as an optional implementation manner, the method of the embodiment of the present application further includes the following steps:

[0180] determining a silhouette of the target garment based on the digital information carrier of the target garment;

[0181] A garment pattern of the target garment is determined based on the silhouette of the target garment.

[0182] With respect to the above optional implementation manner, in some scenarios, it may be impossible to disassemble the target garment into component units. In this case, the garment pattern of the target garment can still be determined by the silhouette of the target garment.

[0183] In the embodiment of the present application, as an optional implementation, step: determining the clothing version of the target garment based on the silhouette of the target garment includes the following sub-steps:

[0184] extracting a second feature vector of the target clothing from the silhouette of the target clothing based on the feature extractor;

[0185] The silhouette most similar to the target garment is obtained based on the second feature vector of the target garment and the silhouette feature library;

[0186] A garment pattern of the target garment is determined based on a silhouette most similar to the target garment.

[0187] This optional embodiment may also determine the silhouette of the target garment based on the digital information carrier of the target garment, thereby determining the clothing version of the target garment based on the silhouette of the target garment.

[0188] In the embodiment of the present application, as an optional implementation manner, the method of the embodiment of the present application further includes the following steps:

[0189] Construct a pattern library, which includes at least a component unit library, a component relationship library, a component feature library and a silhouette feature library. The component unit library is used to match similar component units, the component relationship library is used to match the stitching lines of similar component units, the component feature library is used to match the pattern information of similar component units, and the silhouette feature library is used to extract the silhouette of the target garment.

[0190] This optional implementation can construct a component unit library for matching similar component units, a component relationship library for matching the seams of similar component units, a component feature library for matching pattern information of similar component units, and a silhouette feature library for extracting the silhouette of the target garment. Constructing a pattern library also allows for the integration of existing clothing design resources, thereby digitizing them and improving their utilization and reducing barriers to sharing. Furthermore, the pattern library can improve pattern design efficiency.

[0191] For the above optional implementation, for example, suppose that a pattern designer needs to make a pattern for a style B shirt, which is a modified version of a style A shirt. If a pattern library is not built, the designer needs to completely redefine the pattern of the style B shirt. However, if a pattern library is built based on the style A shirt, the pattern designer can first use the pattern of the style A shirt as a similar pattern for the style B shirt based on the pattern library, and then make a secondary modification to the similar pattern of the style B shirt to obtain the final pattern of the style B shirt. In this way, there is no need to completely redefine the pattern of the style B shirt. It can be seen from this that by integrating the existing clothing design resources, namely style A, it is possible to achieve the digitization of clothing design resources, thereby improving the utilization rate of clothing design resources and reducing the barriers to sharing clothing design resources.

[0192] In the embodiment of the present application, as an optional implementation, step: building a template library includes the following sub-steps:

[0193] Get clothing pattern data;

[0194] Build a pattern library based on clothing pattern data.

[0195] This optional implementation can obtain clothing pattern data, thereby building a pattern library based on the clothing pattern data.

[0196] With respect to the above optional implementation manner, the clothing pattern data refers to historical clothing pattern data, wherein the historical clothing pattern data includes digital information carriers such as pattern design sketches, clothing style pictures, and physical pictures of clothing.

[0197] In the above-mentioned optional embodiment, the clothing pattern data includes pattern design sketches for multiple clothing pattern samples, for example, including pattern design sketches for 100 clothing pattern samples. For example, please refer to FIG12 , which is a schematic diagram of a pattern library construction disclosed in an embodiment of the present application. As shown in FIG12 , a component unit library, a component relationship library, a component feature library, and a silhouette feature library can be constructed based on the clothing pattern data and clothing style images.

[0198] In the embodiment of the present application, as an optional implementation, step: constructing a pattern library based on clothing pattern data includes the following sub-steps:

[0199] Extract clothing stitching relationships based on clothing pattern data, and build a component relationship library based on clothing stitching relationships;

[0200] Component units are disassembled based on clothing pattern data to obtain component disassembly results and a component unit library is constructed based on the component disassembly results.

[0201] This optional implementation can extract clothing stitching relationships based on clothing pattern data and build a component relationship library based on clothing stitching relationships. On the other hand, it can disassemble component units based on clothing pattern data to obtain component disassembly results and build a component unit library based on the component disassembly results.

[0202] In the embodiment of the present application, the component unit library records the component names and the feature vectors associated with the component names. On the other hand, the component relationship library records the stitching relationships between components. The component relationship library can record the stitching relationships between components based on a graph network. For example, please refer to Figure 11. As shown in Figure 11, the graph network is a hierarchical representation structure. The hierarchical representation structure includes structural points in each prototype that have a strict correspondence with the human body structure, as well as the connection relationship between the structural points. As shown in Figure 11, the upper garment in Figure 11 has a relationship with the front.

[0203] In the embodiment of the present application, the component feature library records the attributes of the component unit, wherein the attributes of the component unit include information such as the color and size of the component unit. Furthermore, after matching and obtaining the component unit most similar to the target garment, the component feature library can be used to search for the attributes of the component unit most similar to the target garment.

[0204] In the embodiment of the present application, as an optional implementation manner, the method of the embodiment of the present application further includes the following steps:

[0205] Extract global contours based on clothing pattern data;

[0206] Perform feature encoding on the global contour based on a feature learning algorithm to obtain a second feature encoding result;

[0207] A silhouette feature library is constructed based on the second feature encoding result.

[0208] This optional implementation can extract the global contour based on the clothing pattern data, and then can perform feature encoding on the global contour based on the feature learning algorithm to obtain a second feature encoding result, and then can construct a silhouette feature library based on the second feature encoding result.

[0209] In the embodiment of the present application, as an optional implementation, the step of obtaining similar component units based on the first feature vector matching includes the following steps:

[0210] Matching a plurality of preselected elements in a component feature library based on a first feature vector of the target garment;

[0211] Calculate the similarity between each pre-selected element and the first feature vector of the target garment;

[0212] Determine the highest similarity element based on the similarity between each pre-selected element and the first feature vector of the target garment;

[0213] Similar component units are determined based on the highest similarity elements.

[0214] This optional implementation can match several preselected elements in the component feature library based on the first feature vector of the target garment, and then by calculating the similarity between each preselected element and the first feature vector of the target garment, it can determine the highest similarity element based on the similarity between each preselected element and the first feature vector of the target garment, thereby determining similar component units based on the highest similarity element.

[0215] In the embodiment of the present application, as an optional implementation manner, the method of the embodiment of the present application further includes the following steps:

[0216] Obtaining modification and editing information of the clothing pattern of the target clothing;

[0217] The garment pattern of the target garment is modified based on the modified editing information.

[0218] This optional implementation method obtains modification and editing information of the clothing pattern of the target clothing, and then can modify the clothing pattern of the target clothing based on the modification and editing information, thereby facilitating the designer to perform secondary modifications on the target clothing.

[0219] For the above optional implementation, for example, if the designer needs to adjust the collar of style B shirt, he only needs to modify the collar in the clothing pattern.

[0220] Example 6

[0221] Please refer to FIG13, which is a schematic diagram of the structure of a clothing pattern generation device disclosed in an embodiment of the present application. As shown in FIG13, the device of the embodiment of the present application includes the following functional modules:

[0222] An acquisition module 201 is used to acquire a digital information carrier of a target garment;

[0223] The disassembly module 202 is configured to disassemble the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determine the garment pattern of the target garment based on the component units of the target garment.

[0224] The device of the embodiment of the present application obtains the digital information carrier of the target garment, and then disassembles the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determines the clothing pattern of the target garment based on the component units of the target garment. Compared with the existing technology, and compared with the existing technology that searches for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but obtains the target clothing pattern data through the component units of the target garment, thereby achieving component-level matching.

[0225] It should be noted that for other detailed descriptions of the device in the embodiment of the present application, please refer to the relevant description of Example 5 of the present application, and the embodiment of the present application will not go into details thereon.

[0226] Example 7

[0227] Please refer to FIG14 , which is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. As shown in FIG14 , the electronic device in the embodiment of the present application includes:

[0228] Processor 301; and

[0229] The memory 302 is configured to store machine-readable instructions. When the instructions are executed by the processor 301, the method for generating a garment pattern according to any one of the aforementioned embodiments is executed.

[0230] The electronic device of the embodiment of the present application can obtain the digital information carrier of the target garment by executing the clothing pattern generation method, and then can disassemble the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determine the clothing pattern of the target garment based on the component units of the target garment. Compared with the prior art, and compared with the prior art method of searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but obtains the target clothing pattern data through the component units of the target garment, thereby achieving component-level matching.

[0231] Example 8

[0232] An embodiment of the present application provides a storage medium storing a computer program, and the computer program is executed by a processor as a method for generating a clothing pattern according to any of the aforementioned embodiments.

[0233] The storage medium of the embodiment of the present application can obtain the digital information carrier of the target garment by executing the clothing pattern generation method, and then can disassemble the digital information carrier of the target garment into component units to obtain the component units of the target garment, and determine the clothing pattern of the target garment based on the component units of the target garment. Compared with the prior art, and compared with the prior art method of searching for clothing pattern data based on images, the present application does not directly search for clothing pattern data, but obtains the target clothing pattern data through the component units of the target garment, thereby achieving component-level matching.

[0234] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0235] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0236] Example 9 of the present application provides a clothing pattern generation method, which is applied to a clothing pattern generation device. As shown in FIG15 , the clothing pattern generation method specifically includes:

[0237] Step S401: receiving clothing design language, and converting the clothing design language into a symbolic pattern-making language using a target language parsing model.

[0238] Step S402: using the target symbol translation model to convert the symbolic drawing language into drawing commands.

[0239] Step S403: Determine the target garment pattern according to the drawing command.

[0240] Compared with the prior art, in the clothing pattern generation method provided in Example 9 of the present application, after receiving the clothing design language input by the user, the clothing design language is converted into a drawing command through the target language parsing model and the target symbol translation model, and finally the target clothing pattern is obtained by making a pattern according to the drawing command. The user only needs to input the clothing design language when making the pattern. The clothing design language can be, for example, a natural language, a design manuscript, a photo, etc., thereby reducing the requirements for professional ability in the clothing pattern preparation process; at the same time, due to the high degree of automation of the entire pattern making process, the user can perform a large amount of clothing pattern making work at the same time, thereby improving the overall pattern making efficiency; in addition, since the conversion logic of converting the clothing design language into the symbolic pattern making language is quite different from the conversion logic of converting the symbolic pattern making language into the drawing command, the target language parsing model is first used to convert the clothing design language into the symbolic pattern making language, and then the target symbol translation model is used to convert the symbolic pattern making language into the drawing command. With the symbolic pattern making language as the intermediary, the operating logic of the target language parsing model and the target symbol translation model can be made clearer, the training process is simpler, and the amount of data required for training is smaller.

[0241] In step S401, the clothing design language can be a natural language input by the user, or an image language such as a design drawing or photo uploaded by the user. For example, the clothing design language can be a natural language description sentence such as "A black, A-line dress with a fitted bodice and flaring skirt" input by the user when making a pattern; or the clothing design language can be an image such as a design drawing or a photo of a finished garment uploaded by the user to the clothing pattern generation device when making a pattern, as shown in FIG. 16 . The specific language can be obtained according to actual design needs.

[0242] Furthermore, in step S401, as shown in FIG17 , the target language parsing model may include an encoder 601 and a decoder 602. The encoder 601 may be, for example, a neural network encoder, configured to convert natural language, design drawings, photos, and other clothing design languages ​​into feature space vector representations. The decoder 602 may be, for example, a neural network decoder, configured to parse the feature space vectors into a symbolic pattern-making language. As shown in FIG17 , the symbolic pattern-making language may include, for example, structural commands, symbolic programs, and program parameters. Symbolic programs may include, for example, functions such as "make a top (_make_top_bodice)" and "make a skirt (_make_skirt)." Structural commands may include, for example, "stitching," a set of functions that define the combined relationships and logical order of different symbolic program quality checks, such as "stitch a top and skirt." Program parameters may include, for example, parameters related to the execution of each function in the structural commands, such as the size parameters for a top or skirt.

[0243] It is understood that the symbolic pattern-making language, including structural commands, symbolic programs, and program parameters, is merely a specific example in the embodiments of this application and is merely a specific, general, logical abstraction of pattern-making rules. It defines the garment objects and operations involved in the pattern-making process using the structure of structural commands, symbolic programs, and program parameters, and is not specific to the specific syntax of any industrial pattern-making language. Because the symbolic pattern-making language is independent of the specific syntax of the pattern-making software, the same target language parsing model can be used for different pattern-making software, eliminating the need to replace the target language parsing model based on changes in the pattern-making software. This reduces the demand for the target language parsing model and simplifies the training process of the target language parsing model.

[0244] Specifically, the target language parsing model can be a large multimodal model (LMM). The training process for the target language parsing model in the form of a large multimodal model can be based on the constructed standard large multimodal model as the initial language parsing model, and the initial language parsing model of the standard large multimodal model is fine-tuned (finetune) using a pre-collected training dataset. The training dataset can include multiple training data, and the training data can be, for example, data in the format of "style description-symbol program-plate".

[0245] Furthermore, in different embodiments of the present application, the target pattern-making software can be a pre-set pattern-making software, or it can be a pattern-making software included in the clothing design language, such as "using A pattern-making software to generate patterns for a black A-line dress, corset and flared skirt", etc., and can be specifically set according to actual needs.

[0246] Furthermore, in step S402, the drawing command is a code segment for generating a plate, which can be applied to CAD plate-making software such as ET, Assyst, etc. CAD plate-making software such as ET, Assyst, etc. can generate corresponding plates according to the drawing command.

[0247] In step S402, the target symbol translation model can be, for example, a neural network model that adopts a "text-to-text" conversion architecture. The input of the target symbol translation model is the symbolic pattern-making language generated in step S401, and the output is the corresponding drawing command. In the process of training the target symbol translation model, an initial neural network model can be first constructed based on the "text-to-text" conversion architecture, and then the initial neural network model can be trained using a large amount of training data, wherein the training data can be a large amount of data pairs including mutually corresponding symbolic pattern-making languages ​​and sample drawing commands. The initial neural network model is trained based on the training data to obtain the target symbol translation model.

[0248] In step S402, determining the target garment pattern based on the drawing command may specifically include inputting the drawing command into target pattern-making software and using the output of the target pattern-making software as the target garment pattern. The target pattern-making software may be running in the garment pattern generating apparatus or in an external device connected to the garment pattern generating apparatus, and may be used flexibly according to actual needs.

[0249] Furthermore, in different embodiments of the present application, when the target pattern-making software is running in the garment pattern generation device, the target pattern-making software used in step S403 may be different. Different target pattern-making software corresponds to pattern-making commands in different grammatical formats. Therefore, corresponding to the training process of the target symbol translation model in step S402, the sample drawing commands used for model training may also be different. Specifically, the sample drawing commands used to train the target symbol translation model are pattern-making commands in the grammatical format based on the target pattern-making software.

[0250] Based on this, in some embodiments of the present application, as shown in FIG18 , in addition to the aforementioned steps S401 to S403, before using the target symbol translation model to convert the symbolic pattern language into drawing commands and drawing parameters in step S403, the garment pattern generation method may further include:

[0251] Step S404: determining a target symbol translation model according to the target board making software.

[0252] Compared with the related art, in the embodiments of the present application, for different types of target board-making software, the corresponding target symbol translation model is selected to generate board-making commands. Each target symbol translation model is only used to generate drawing commands corresponding to one target board-making software, so as to avoid the target symbol translation model confusing the grammatical rules of different types of board-making software, and reduce the possibility of the target symbol translation model generating drawing commands that do not comply with the grammatical rules of the target board-making software, so that the board-making commands generated by the target symbol translation model are more matched with the target board-making software used in subsequent steps, thereby improving the board-making quality of the target board-making software.

[0253] Specifically, in some embodiments of the present application, step S404 may specifically include: obtaining the target board making grammar rules of the target board making software; obtaining the initial symbol translation model; using the target board making grammar rules to perform model training on the initial symbol translation model to obtain the target symbol translation model.

[0254] Among them, the target board grammar rules are used to perform model training on the initial symbol translation model. For example, a large number of sample board languages ​​can be generated according to the target board grammar rules, and then the generated sample board languages ​​are used to perform model training on the constructed initialized initial symbol translation model. After the model training is completed, the target symbol translation model is obtained.

[0255] Acquiring the target board-making grammar rules of the target board-making software in real time to perform model training of the target symbol translation model can enable the target symbol translation model to make corresponding changes when the target board-making grammar rules change, and further make the board-making commands generated by the target symbol translation model more compatible with the target board-making software used in step S403, thereby improving the board-making quality of the target board-making software.

[0256] Furthermore, in some other embodiments of the present application, a preset symbol translation model list can also be obtained, the preset symbol translation model list including multiple sample symbol translation models and sample board making software corresponding one-to-one to each sample symbol translation model; and the sample symbol translation model corresponding to the target board making software in the preset symbol translation model list is determined as the target symbol translation model.

[0257] A symbol translation model list is set in advance, and the symbol translation model list includes multiple trained sample symbol translation models and sample board-making software corresponding to each sample symbol translation model. When determining the target symbol translation model, the sample symbol translation model corresponding to the target board-making software in the symbol translation model list is directly used as the target symbol translation model. This eliminates the need to perform the model training process again, thereby improving the efficiency of determining the target symbol translation model.

[0258] Furthermore, in step S403, as shown in FIG19 , the target pattern making software is used to determine the target garment pattern according to the drawing command and drawing parameters, which may specifically include:

[0259] Step S501: Input the drawing command into the target pattern making software and receive the garment pattern generated by the target pattern making software;

[0260] Step S502: Use the quality inspection model to determine whether the garment pattern meets the preset pattern making rules. If the garment pattern does not meet the preset pattern making rules, execute step S503; if the garment pattern meets the preset pattern making rules, execute step S504.

[0261] Step S503: Adjust the drawing command according to the preset pattern making rules, input the adjusted drawing command into the target pattern making software, and receive the target garment pattern generated by the target pattern making software.

[0262] Step S504: If the garment pattern meets the preset pattern making rules, the garment pattern is used as the target garment pattern.

[0263] After receiving the clothing pattern generated by the target pattern-making software according to the drawing command, the quality inspection model is used to detect the generated clothing pattern to determine whether the clothing pattern complies with the preset pattern-making rules. If the clothing pattern does not comply with the preset pattern-making rules, the drawing command is adjusted according to the preset pattern-making rules, and the target clothing pattern generated by the target pattern-making software according to the adjusted drawing command is received, so that the generated target clothing pattern is more consistent with the preset pattern-making rules, thereby improving the pattern-making quality of the target clothing pattern.

[0264] Among them, the quality inspection model is a mathematical model trained according to the preset board making rules. The preset board making rules can be, for example, standardized board making rules in the board making industry, or board making rules set according to one's own needs. They can be flexibly set according to actual application needs.

[0265] In some embodiments of the present application, the quality inspection model can also be a large multimodal model (LMM). Furthermore, in some embodiments of the present application, the target language parsing model and the quality inspection model can be the same large multimodal model trained using preset template rules.

[0266] The target language parsing model and the quality inspection model are the same large multimodal model, which can reduce the model training process and training requirements, improve board manufacturing efficiency and reduce board manufacturing costs.

[0267] Embodiment 10 of the present application provides a method for generating a garment pattern, which is applied to a garment pattern generating device. As shown in FIG20 , the method specifically includes:

[0268] Step S601: receiving clothing design language, and converting the clothing design language into a symbolic pattern-making language using a target language parsing model.

[0269] Step S602: using the target symbol translation model to convert the symbolic drawing language into drawing commands.

[0270] Step S603: Determine the target garment pattern according to the drawing command.

[0271] Step S604: receiving the modified clothing design language, and converting the modified clothing design language into the modified clothing design language using the target language parsing model.

[0272] Step S605: using the target symbol translation model to convert the modified symbolic pattern making language into modified drawing commands.

[0273] Step S606: Modify the target garment pattern according to the modification drawing command.

[0274] Compared with the prior art, in the clothing pattern generation method provided in Example 10 of the present application, after generating the target clothing pattern, it continues to receive the modified clothing design language input by the user, and generates a modified drawing command based on the modified clothing design language to modify the target clothing pattern, thereby realizing convenient modification of the target clothing pattern.

[0275] It can be understood that steps S601 to S603 in the clothing pattern generation method provided in Example 10 of the present application are roughly the same as steps S401 to S403 in the aforementioned embodiment, and specific details can be referred to the specific description in the aforementioned embodiment.

[0276] Furthermore, in step S604, the language type of the modified clothing design language and the clothing design language in the aforementioned step S401 can be the same or different. For example, both can be natural languages, or the clothing design language in step S401 can be an image language such as a design drawing, while the modified clothing design language can be a natural language, etc.

[0277] Example 11 of the present application provides a clothing pattern generation device, as shown in Figure 21, including: a language parsing module 401, the language parsing module 401 is used to receive clothing design language, and use the target language parsing model to convert the clothing design language into a symbolic pattern making language; a symbol translation module 402, the symbol translation module 402 is used to use the target symbol translation model to convert the symbolic pattern making language into a drawing command; and a pattern making module 403, the pattern making module 403 is used to determine the target clothing pattern according to the drawing command.

[0278] Compared with the prior art, in the clothing pattern generation device provided in Example 11 of the present application, after the language parsing module 401 receives the clothing design language input by the user, the clothing design language is converted into a drawing command through the target language parsing model in the language parsing module 401 and the target symbol translation model in the symbol translation module 402, and finally the pattern making software in the pattern making module 403 is used to make a pattern according to the drawing command to obtain the target clothing pattern. The user only needs to input the clothing design language when making the pattern. The clothing design language can be, for example, natural language, design manuscripts, photos, etc., thereby reducing the requirements for professional ability in the clothing pattern preparation process; at the same time, due to the high degree of automation of the entire pattern making process, the user can perform a large amount of clothing pattern making work at the same time, thereby improving the overall pattern making efficiency.

[0279] The symbol translation module 402 is further configured to determine a target symbol translation model according to a target board-making software before using the target symbol translation model to convert the symbolic board-making language into a drawing command.

[0280] The symbol translation module 402 is also used to obtain the target board making grammar rules of the target board making software; obtain the initial symbol translation model; use the target board making grammar rules to perform model training on the initial symbol translation model to obtain the target symbol translation model.

[0281] The symbol translation module 402 is also used to obtain a preset symbol translation model list, which includes multiple sample symbol translation models and sample board making software corresponding to each sample symbol translation model; and determine that the sample symbol translation model corresponding to the target board making software in the preset symbol translation model list is the target symbol translation model.

[0282] The pattern making module 403 is also used to input the drawing command into the target pattern making software and receive the clothing pattern generated by the target pattern making software; use the quality inspection model to determine whether the clothing pattern meets the preset pattern making rules; if the clothing pattern does not meet the preset pattern making rules, adjust the drawing command according to the preset pattern making rules, input the adjusted drawing command into the target pattern making software, and receive the target clothing pattern generated by the target pattern making software; if the clothing pattern meets the preset pattern making rules, use the clothing pattern as the target clothing pattern. In different embodiments of the present application, the target pattern making software can be directly run in the pattern making module 403, and the pattern making module 403 directly uses the target pattern making software running therein to generate the target clothing pattern; or the target pattern making software can be run in other external devices connected to the pattern making module 403, and the pattern making module 403 sends the drawing command to the external device and receives the target clothing pattern fed back by the external device.

[0283] In addition, the language parsing module 401 is also used to receive the modified clothing design language and convert the modified clothing design language into the modified clothing design language using the target language parsing model; the symbol translation module 402 is also used to convert the modified symbolic pattern making language into the modified drawing command using the target symbol translation model; the pattern making module 403 is also used to modify the target clothing pattern according to the modified drawing command.

[0284] Embodiment 12 of the present application provides an electronic device, as shown in FIG22 , comprising: at least one processor 501; and a memory 502 communicatively connected to the at least one processor 501; wherein the memory 502 stores instructions that can be executed by the at least one processor 501, and the instructions are executed by the at least one processor 501 so that the at least one processor 501 can execute the methods in the above-mentioned embodiments.

[0285] The memory and processor are connected using a bus, which can include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are therefore not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor.

[0286] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0287] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a portion of code, and the module, program segment or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified functions or actions, or can be implemented with a combination of dedicated hardware and computer instructions.

[0288] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0289] In the above embodiments, they can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the device, the process or function described in the embodiment of the present application is generated in whole or in part. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by the device or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, and a tape, etc.), an optical medium (e.g., a digital video disk (DVD), etc.), or a semiconductor medium (e.g., a solid-state drive, etc.).

[0290] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0291] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0292] The above are merely embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0293] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A method for generating a clothing design drawing, characterized in that, Including: Receiving design intent data and / or design materials; Performing initialization processing on the design intent data to obtain a visualized design drawing; And / or performing encoding processing on the design materials to obtain material feature encodings; Inputting the material feature encodings and / or the visualized design drawing into a pre-constructed generation network to generate a target design drawing; Outputting the target design drawing.

2. The method for generating a clothing design drawing according to claim 1, wherein The design intent data includes one or more of natural language description data, style drawings, and line drawings; The design materials include one or more of text materials, image materials, and graphic materials.

3. The method for generating a clothing design drawing according to claim 1, wherein The performing encoding processing on the design materials to obtain material feature encodings includes: Determining a target encoder corresponding to each of the design materials; wherein the target encoder is a text encoder, an image encoder, or a graphic encoder; Performing encoding processing on the design materials based on the target encoder to obtain material feature encodings.

4. The method for generating a clothing design drawing according to claim 1, characterized in that, The method further includes: Modifying the target design drawing in response to a modification instruction for the target design drawing to obtain a modified design drawing; Determining the modified design drawing as design intent data and performing the initialization processing on the design intent data to obtain a visualized design drawing; Receiving new design materials and performing the encoding processing on the design materials to obtain material feature encodings.

5. A clothing design drawing generation device, characterized in that, The clothing design drawing generation device includes: A receiving unit, configured to receive design intent data and / or design materials; An initialization unit, configured to perform initialization processing on the design intent data to obtain a visualized design drawing; An encoding unit, configured to perform encoding processing on the design materials to obtain material feature encodings; A generation unit, configured to input the material feature encodings and / or the visualized design drawing into a pre-constructed generation network to generate a target design drawing; An output unit, configured to output the target design drawing.

6. The device for generating a clothing design drawing according to claim 5, wherein The design intent data includes one or more of natural language description data, style drawings, and line drawings; The design materials include one or more of text materials, image materials, and graphic materials.

7. The device for generating a clothing design drawing according to claim 6, wherein The encoding unit includes: A determination subunit, configured to determine a target encoder corresponding to each of the design materials; wherein the target encoder is a text encoder, an image encoder, or a graphic encoder; An encoding subunit, configured to perform encoding processing on the design materials based on the target encoder to obtain material feature encodings.

8. The device for generating a clothing design drawing according to claim 6, characterized in that, The clothing design drawing generation device further includes: A modification unit, configured to modify the target design drawing in response to a modification instruction for the target design drawing to obtain a modified design drawing; A determination unit, configured to determine the modified design drawing as design intent data and trigger the initialization unit to perform initialization processing on the design intent data to obtain a visualized design drawing; The receiving unit is further configured to receive new design materials and trigger the encoding unit to perform encoding processing on the design materials to obtain material feature encodings.

9. An electronic device, characterized in that, The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the clothing design drawing generation method according to any one of claims 1 to 4.

10. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the clothing design drawing generation method according to any one of claims 1 to 4 is executed.

11. A method for generating a clothing pattern, characterized in that, The method comprises: Acquire digital information carrier of target clothing; The digital information carrier of the target garment is disassembled into component units to obtain the component units of the target garment, and the garment pattern of the target garment is determined based on the component units of the target garment.

12. The method according to claim 11, wherein The determining of the clothing pattern of the target clothing based on the component unit of the target clothing comprises: Extracting a first feature vector of a component unit of the target garment; Obtaining similar component units based on the first feature vector matching; Acquire the stitching lines of the similar component units and the pattern information of the similar component units; Based on the pattern information of the similar component units and the sewing lines of the similar component units, the clothing pattern of the target clothing is determined.

13. The method according to claim 12, wherein The method further comprises: The stitching lines of the similar component units are tuned, wherein the tuning of the stitching lines of the similar component units includes modifying the length of the stitching lines of the similar component units and modifying the curvature of the stitching lines of the similar component units.

14. The method according to claim 12, wherein The method further comprises: Determining the silhouette of the target garment based on the digital information carrier of the target garment; A clothing pattern of the target garment is determined based on the silhouette of the target garment.

15. The method according to claim 14, wherein The method further comprises: A pattern library is constructed, the pattern library comprising at least a component unit library, a component relationship library, a component feature library and a silhouette feature library, the component unit library is used to match the similar component units, the component relationship library is used to match the seams of the similar component units, the component feature library is used to match the pattern information of the similar component units, and the silhouette feature library is used to extract the silhouette of the target garment.

16. The method according to claim 15, wherein The construction template library includes: Get clothing pattern data; The pattern library is constructed based on the clothing pattern data.

17. The method according to claim 16, wherein The step of constructing the pattern library based on the clothing pattern data comprises: Extracting garment sewing relationships based on the garment pattern data, and constructing the component relationship library based on the garment sewing relationships; Component units are disassembled based on the clothing pattern data to obtain component disassembly results, and the component unit library is constructed based on the component disassembly results.

18. The method according to claim 16, wherein The method further comprises: Extract global contours based on clothing pattern data; Performing feature encoding on the global contour based on a feature learning algorithm to obtain a second feature encoding result; The silhouette feature library is constructed based on the second feature encoding result.

19. The method according to claim 15, wherein The obtaining of similar component units based on the matching of the first feature vectors includes: Matching a plurality of preselected elements in the component feature library based on the first feature vector of the target garment; Calculating the similarity between each of the pre-selected elements and the first feature vector of the target garment; Determine the element with the highest similarity based on the similarity between each of the preselected elements and the first feature vector of the target clothing; Determine the similar component unit based on the element with the highest similarity.

20. The method according to claim 11, wherein The method further includes: Obtain modification and editing information for the clothing pattern of the target clothing; Modify the clothing pattern of the target clothing based on the modification and editing information.

21. A clothing pattern generation device, characterized in that, The apparatus includes: An acquisition module, configured to acquire a digital information carrier of the target clothing; A disassembly module, configured to disassemble the digital information carrier of the target clothing into component units of the target clothing, obtain the component units of the target clothing, and determine the clothing pattern of the target clothing based on the component units of the target clothing.

22. An electronic device, characterized in that, Includes: A processor; And A memory, configured to store machine-readable instructions that, when executed by the processor, execute the clothing pattern generation method according to any one of claims 11-20.

23. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, executes the clothing pattern generation method according to any one of claims 11-20.

24. A method for generating a clothing panel, characterized in that, Includes: Receive a clothing design language, and use a target language parsing model to convert the clothing design language into a symbolic pattern-making language; Use a target symbol translation model to convert the symbolic pattern-making language into drawing commands corresponding to a target pattern-making software; Determine the target clothing pattern pieces according to the drawing commands.

25. The method for generating a clothing panel according to claim 24, wherein Before using the target symbol translation model to convert the symbolic pattern-making language into drawing commands, the clothing pattern piece generation method further includes: Determine the target symbol translation model according to the target pattern-making software.

26. The method for generating a clothing panel according to claim 25, wherein The determining the target symbol translation model according to the target pattern-making software includes: Obtain the target pattern-making syntax rules of the target pattern-making software; Obtain an initial symbol translation model; Use the target pattern-making syntax rules to perform model training on the initial symbol translation model to obtain the target symbol translation model.

27. The method for generating a clothing panel according to claim 25, wherein The determining the target symbol translation model according to the target pattern-making software includes: Obtain a preset symbol translation model list, where the preset symbol translation model list includes multiple sample symbol translation models and sample pattern-making software corresponding to each of the sample symbol translation models; Determine the sample symbol translation model corresponding to the target pattern-making software in the preset symbol translation model list as the target symbol translation model.

28. The method for generating a clothing panel according to claim 24, wherein The determining the target clothing pattern pieces according to the drawing commands includes: Input the drawing commands into the target pattern-making software, and receive the clothing pattern pieces generated by the target pattern-making software; Use a quality inspection model to determine whether the clothing pattern pieces conform to preset pattern-making rules; If the clothing pattern pieces do not conform to the preset pattern-making rules, adjust the drawing commands according to the preset pattern-making rules, input the adjusted drawing commands into the target pattern-making software, and receive the target clothing pattern pieces generated by the target pattern-making software; If the clothing pattern pieces conform to the preset pattern-making rules, use the clothing pattern pieces as the target clothing pattern pieces.

29. The method for generating a clothing panel according to claim 28, wherein The target language parsing model and the quality inspection model are multimodal large models.

30. The method for generating a clothing panel according to claim 24, wherein The clothing pattern piece generation method further includes: Receive the modified fashion design language, and use the target language parsing model to convert the modified fashion design language into a modified fashion design language; Use the target symbol translation model to convert the modified symbolic pattern-making language into a modified drawing command; Modify the target garment pattern according to the modified drawing command.

31. A garment panel generating device, characterized in that, Comprising: A language parsing module for receiving a fashion design language and using a target language parsing model to convert the fashion design language into a symbolic pattern-making language; A symbol translation module for using a target symbol translation model to convert the symbolic pattern-making language into a drawing command corresponding to a target pattern-making software; A pattern-making module for determining a target garment pattern according to the drawing command.

32. An electronic device, characterized in that, Comprising: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the garment pattern generation method according to any one of claims 24 to 30.

33. A computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by a processor to implement the garment pattern generation method according to any one of claims 24 to 30.

34. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code is executed by a computer device, the computer device executes the garment pattern generation method according to any one of claims 24 to 30 above.

Images