Garment editing generation method and system based on semantic guidance

Abstract

The invention relates to the technical field of image data processing, in particular to a clothing editing generation method and system based on semantic guidance, and the clothing editing generation system based on semantic guidance comprises a semantic guidance module, a clothing editing module, a material storage module and a material preview module. The material preview module displays various selectable garment materials to the consumer for the consumer to select independently; the semantic guiding module captures a voice instruction of a consumer, converts the voice instruction of the consumer into a text to be output, extracts keywords in the text, understands the intention of the consumer and generates a clothing editing command; and the clothing editing module extracts corresponding clothing materials from the material storage module according to the clothing editing command, and edits and generates a clothing style required by the consumer. Therefore, the clothes can be used by consumers by themselves, and the edition, fabric, pattern and color of the clothes are edited and matched and then provided for merchants.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a clothing editing generation method and system based on semantic guidance. Background Art

[0002] With the development of the national economy, the living standards of residents are gradually improving. With the popularization of the Internet, online shopping has become a major trend. More and more people are getting used to online shopping, and the traditional shopping model has been gradually abandoned. Compared with the traditional shopping model, online shopping can purchase goods from various regions, enriching shopping options, and there are more types to choose from. In addition, the prices of some goods on the online shopping platform are more affordable; and clothing is a product that people buy more frequently.

[0003] As people continue to pursue quality of life, when the existing clothing materials, patterns and colors cannot meet the needs of consumers, consumers' demand for personalized clothing customization will increase. However, professional clothing editing systems are not suitable for consumers to use. It is unrealistic for merchants to provide personalized customization services to each consumer, which will increase labor costs. Therefore, a simple and easy-to-use clothing editing generation system is needed for consumers to use. Summary of the invention

[0004] The purpose of the present invention is to provide a semantically guided clothing editing generation method and system, which can be used by consumers themselves to edit and match the clothing style, fabric, pattern and color and then provide them to merchants.

[0005] To achieve the above-mentioned purpose, in a first aspect, the present invention provides a clothing editing generation system based on semantic guidance, comprising a semantic guidance module, a clothing editing module, a material storage module and a material preview module; the clothing editing module is connected to the semantic guidance module; the material storage module is connected to the clothing editing module; the material preview module is connected to the material storage module;

[0006] The semantic guidance module is used to capture the consumer's voice instructions, convert the consumer's voice instructions into text output, extract keywords therein, understand the consumer's intention, generate clothing editing commands and send them to the clothing editing module;

[0007] The clothing editing module is used to receive the clothing editing command sent by the semantic guidance module, extract the corresponding clothing material from the material storage module according to the clothing editing command, and edit and generate the clothing style required by the consumer;

[0008] The material storage module is used to store various types of clothing materials.

[0009] The material preview module is used to display various types of clothing materials stored in the material storage module to consumers.

[0010] The semantic guidance module includes a speech capture unit, a preprocessing unit, a conversion unit, a keyword extraction unit, an intention recognition unit and a command generation unit; the speech capture unit, the preprocessing unit, the conversion unit, the keyword extraction unit, the intention recognition unit and the command generation unit are connected in sequence;

[0011] The voice capturing unit is used to capture the voice of the consumer;

[0012] The pre-processing unit is used to clean and standardize speech;

[0013] The conversion unit is used to convert speech into text;

[0014] The keyword extraction unit is used to extract keywords from the text;

[0015] The intention identification unit is used to combine the extracted keywords to determine the consumer intention;

[0016] The command generation unit is used to generate a clothing editing command according to the consumer's intention and send it to the clothing editing module.

[0017] Wherein, the clothing editing module includes a command execution unit, an image generation unit and an image preview unit; the image generation unit is connected to the command execution unit; the image preview unit is connected to the image generation unit;

[0018] The command execution unit is used to receive the clothing editing command sent by the semantic guidance module, extract the corresponding clothing material from the material storage module and send it to the image generation unit, and guide the image generation unit to perform editing;

[0019] The image generation unit is used to receive clothing materials, splice the clothing materials, edit and generate clothing images, and send them to the image preview unit;

[0020] The image preview unit is used to receive clothing images and display them to consumers for preview from various angles.

[0021] Wherein, the material storage module includes a clothing pattern storage unit, a fabric storage unit, a color storage unit, a pattern storage unit and an input unit; the input unit is connected to the clothing pattern storage unit, the fabric storage unit, the color storage unit and the pattern storage unit respectively;

[0022] The clothing pattern storage unit is used to store clothing patterns of various sizes and types designed by merchants;

[0023] The fabric storage unit is used to store various fabrics that can be processed and produced by the merchant;

[0024] The color storage unit is used to store various clothing colors that the merchant can process and produce;

[0025] The pattern storage unit is used to store various types of patterns designed by merchants;

[0026] The input unit is used by merchants to input various clothing styles, fabrics, colors and patterns.

[0027] Wherein, the clothing editing generation system based on semantic guidance further includes a custom module; the custom module is connected with the clothing editing module;

[0028] The customization module is used to allow consumers to customize patterns for extraction and use by the clothing editing module.

[0029] Wherein, the custom module includes a material uploading unit and a pattern editing unit; the pattern editing unit is connected to the material uploading unit;

[0030] The material uploading unit is used for allowing consumers to upload materials by themselves and send them to the pattern editing unit;

[0031] The pattern editing unit is used for consumers to edit uploaded materials and generate clothing patterns.

[0032] In a second aspect, the present invention further provides a clothing editing generation method based on semantic guidance, comprising:

[0033] The material preview module displays various optional clothing materials to consumers for them to choose from;

[0034] The semantic guidance module captures consumers’ voice commands, converts them into text output, extracts key words, understands consumers’ intentions, and generates clothing editing commands;

[0035] The clothing editing module extracts the corresponding clothing materials from the material storage module according to the clothing editing command, and edits and generates the clothing styles required by the consumer.

[0036] The invention discloses a clothing editing generation method and system based on semantic guidance, wherein the material storage module stores various types of clothing materials and displays them to consumers through the material preview module for selection by consumers, wherein the clothing materials include clothing pattern, fabric, color and pattern, and the semantic guidance module is used to capture the voice command of consumers, convert the voice command of consumers into text output, extract keywords therein, understand the intention of consumers, generate clothing editing commands and send them to the clothing editing module; the clothing editing module is used to receive the clothing editing commands sent by the semantic guidance module, extract corresponding clothing materials from the material storage module according to the clothing editing commands, and edit and generate clothing styles required by consumers; when in use, consumers issue voice commands to enable the clothing editing module to select corresponding clothing patterns from the material storage module, and edit the fabric, color and pattern selected by consumers into the clothing patterns according to the voice commands of consumers, and consumers can also issue voice commands to change clothing patterns, fabrics, colors and patterns until the clothing that consumers are satisfied with is matched, so that consumers can use the clothing by themselves, and provide the clothing patterns, fabrics, patterns and colors after editing and matching them to merchants. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0038] Figure 1 It is a schematic structural diagram of the first embodiment of the present invention.

[0039] Figure 2 It is a structural diagram of the semantic guidance module of the first embodiment of the present invention.

[0040] Figure 3 4 is a schematic diagram of the structure of the clothing editing module of the first embodiment of the present invention.

[0041] Figure 4 It is a structural diagram of a material storage module according to the first embodiment of the present invention.

[0042] Figure 5 It is a schematic structural diagram of an image generating unit according to the first embodiment of the present invention.

[0043] Figure 6 It is a schematic structural diagram of the second embodiment of the present invention.

[0044] Figure 7 It is a schematic diagram of the structure of a custom module according to the second embodiment of the present invention.

[0045] Figure 8 It is a schematic structural diagram of the third embodiment of the present invention.

[0046] Fig. 9 4 is a schematic structural diagram of a try-on module according to a third embodiment of the present invention.

[0047] Fig.10 is a flow chart of the fourth embodiment of the present invention.

[0048] 101-semantic guidance module, 102-clothing editing module, 103-material storage module, 104-material preview module, 105-voice capture unit, 106-preprocessing unit, 107-conversion unit, 108-keyword extraction unit, 109-intention recognition unit, 110-command generation unit, 111-command execution unit, 112-image generation unit, 113-image preview unit, 114-clothing pattern storage unit, 115-fabric storage unit, 116-color storage unit, 117-pattern storage unit, 118-entry unit, 119-image splicing subunit, 120-image fusion subunit, 121-image simulation subunit; 201-custom module, 202-material upload unit, 203-pattern editing unit, 301-try-on module, 302-human model storage unit, 303-try-on unit. DETAILED DESCRIPTION

[0049] The first embodiment of the present application is:

[0050] See also Figure 1-Figure 5 ,in, Figure 1 It is a schematic structural diagram of the first embodiment of the present invention. Figure 2 It is a structural diagram of the semantic guidance module of the first embodiment of the present invention. Figure 3 4 is a schematic diagram of the structure of the clothing editing module of the first embodiment of the present invention. Figure 4 It is a structural diagram of a material storage module according to the first embodiment of the present invention. Figure 5 It is a schematic structural diagram of an image generating unit according to the first embodiment of the present invention.

[0051] The invention provides a clothing editing and generating system based on semantic guidance, comprising a semantic guidance module 101, a clothing editing module 102, a material storage module 103 and a material preview module 104; the semantic guidance module 101 comprises a voice capturing unit 105, a preprocessing unit 106, a conversion unit 107, a keyword extraction unit 108, an intention recognition unit 109 and a command generating unit 110; the clothing editing module 102 comprises a command executing unit 111, an image generating unit 112 and an image preview unit 113; the material storage module 103 comprises a clothing pattern storing unit 114, a fabric storing unit 115, a color storing unit 116, a pattern storing unit 117 and an input unit 118; the image generating unit 112 comprises an image splicing subunit 119, an image fusion subunit 120 and an image simulation subunit 121; through the above scheme, consumers can use it by themselves, and provide the clothing pattern, fabric, pattern and color after editing and matching them to merchants.

[0052] According to this specific implementation, the clothing editing module 102 is connected to the semantic guidance module 101; the material storage module 103 is connected to the clothing editing module 102; the material preview module 104 is connected to the material storage module 103;

[0053] The semantic guidance module 101 is used to capture the consumer's voice instructions, convert the consumer's voice instructions into text output, extract keywords therein, understand the consumer's intention, generate clothing editing commands and send them to the clothing editing module 102;

[0054] The clothing editing module 102 is used to receive the clothing editing command sent by the semantic guidance module 101, extract the corresponding clothing material from the material storage module 103 according to the clothing editing command, and edit and generate the clothing style required by the consumer;

[0055] The material storage module 103 is used to store various types of clothing materials.

[0056] The material preview module 104 is used to display various clothing materials stored in the material storage module 103 to consumers.

[0057] The material storage module 103 stores various types of clothing materials and displays them to consumers through the material preview module 104 for selection. The clothing materials include clothing patterns, fabrics, colors and patterns. The semantic guidance module 101 is used to capture the voice instructions of consumers, convert the voice instructions of consumers into text output, extract keywords therein, understand the intentions of consumers, generate clothing editing commands and send them to the clothing editing module 102; the clothing editing module 102 is used to receive the clothing editing commands sent by the semantic guidance module 101, extract corresponding clothing materials from the material storage module 103 according to the clothing editing commands, and edit and generate clothing styles required by consumers; when in use, consumers issue voice instructions to make the clothing editing module 102 select the corresponding clothing pattern from the material storage module 103, and edit the fabrics, colors and patterns selected by consumers into the clothing pattern according to the voice instructions of consumers. Consumers can also issue voice instructions to change clothing patterns, fabrics, colors and patterns until the clothing that consumers are satisfied with is matched, so that consumers can use them by themselves, and provide them to merchants after editing and matching the pattern, fabrics, patterns and colors of the clothing.

[0058] Wherein, the voice capturing unit 105, the preprocessing unit 106, the converting unit 107, the keyword extracting unit 108, the intention identifying unit 109 and the command generating unit 110 are connected in sequence;

[0059] The voice capturing unit 105 is used to capture the voice of the consumer;

[0060] The pre-processing unit 106 is used to clean and standardize speech;

[0061] The conversion unit 107 is used to convert speech into text;

[0062] The keyword extraction unit 108 is used to extract keywords from the text;

[0063] The intention identification unit 109 is used to combine the extracted keywords to determine the consumer intention;

[0064] The command generation unit 110 is used to generate a clothing editing command according to the consumer's intention and send it to the clothing editing module 102.

[0065] The voice capture unit 105 uses a microphone to capture the consumer's voice instructions; the preprocessing unit 106 is used to clean and standardize the voice; the conversion unit 107 is used to convert the sound signal into a digital signal, and then convert it into a text output; the keyword extraction unit 108 extracts keywords from the text based on the existing word library and phrase library; the intention recognition unit 109 combines the extracted keywords to determine the consumer's intention, and finally uses the command generation unit 110 to generate a clothing editing command based on the consumer's intention and send it to the clothing editing module 102.

[0066] Secondly, the image generation unit 112 is connected to the command execution unit 111; the image preview unit 113 is connected to the image generation unit 112;

[0067] The command execution unit 111 is used to receive the clothing editing command sent by the semantic guidance module 101, extract the corresponding clothing material from the material storage module 103 and send it to the image generation unit 112, and guide the image generation unit 112 to perform editing;

[0068] The image generation unit 112 is used to receive clothing materials, splice the clothing materials, edit and generate clothing images, and send them to the image preview unit 113;

[0069] The image preview unit 113 is used to receive clothing images and display them to consumers for preview from various angles.

[0070] The command execution unit 111 is used to receive the clothing editing command sent by the semantic guidance module 101, extract the corresponding clothing material from the material storage module 103 and send it to the image generation unit 112, and guide the image generation unit 112 to edit. The image generation unit 112 is used to splice and edit the clothing version, fabric, color and pattern selected by the consumer, generate a finished clothing image, and send it to the image preview unit 113 to show it to the consumer for preview. The consumer can choose to modify the clothing version, fabric, color and pattern according to the clothing image displayed by the image preview unit 113.

[0071] At the same time, the input unit 118 is connected to the clothing pattern storage unit 114, the fabric storage unit 115, the color storage unit 116 and the pattern storage unit 117 respectively;

[0072] The clothing pattern storage unit 114 is used to store clothing patterns of various sizes and types designed by merchants;

[0073] The fabric storage unit 115 is used to store various fabrics that can be processed and produced by the merchant;

[0074] The color storage unit 116 is used to store various clothing colors that the merchant can process and produce;

[0075] The pattern storage unit 117 is used to store various types of patterns designed by merchants;

[0076] The input unit 118 is used by merchants to input various clothing styles, fabrics, colors and patterns.

[0077] The input unit 118 is used for merchants to input various types of clothing patterns, fabrics, colors and patterns respectively into the clothing pattern storage unit 114, the fabric storage unit 115, the color storage unit 116 and the pattern storage unit 117 in advance.

[0078] In addition, the image stitching subunit 119, the image fusion subunit 120 and the image simulation subunit 121 are connected in sequence;

[0079] The image stitching subunit 119 is used to assemble clothing patterns and patterns;

[0080] The image fusion subunit 120 is used to fuse fabrics and colors into the clothing pattern;

[0081] The image simulation subunit 121 is used to perform simulation optimization on clothing.

[0082] The image stitching subunit 119 cooperates with the image fusion subunit 120 to edit and synthesize the clothing pattern, fabric, pattern and color, and simulates them using the image simulation subunit 121 to make it look more realistic, making it easier for consumers to see the real image of the clothing.

[0083] In the clothing editing generation system based on semantic guidance described in this embodiment, the material storage module 103 stores various types of clothing materials, and displays them to consumers through the material preview module 104 for consumers to choose. The clothing materials include clothing patterns, fabrics, colors and patterns. The semantic guidance module 101 is used to capture the voice instructions of consumers, convert the voice instructions of consumers into text output, extract keywords therein, understand the intentions of consumers, generate clothing editing commands and send them to the clothing editing module 102; the clothing editing module 102 is used to receive the clothing editing commands sent by the semantic guidance module 101, and select the clothing materials according to the clothing materials. The clothing editing command extracts the corresponding clothing materials from the material storage module 103, and edits and generates the clothing style required by the consumer; when in use, the consumer issues a voice command to enable the clothing editing module 102 to select the corresponding clothing pattern from the material storage module 103, and edit the fabric, color and pattern selected by the consumer into the clothing pattern according to the voice command of the consumer. The consumer can also issue a voice command to change the clothing pattern, fabric, color and pattern until the clothing that the consumer is satisfied with is matched, so that the consumer can use it by himself, and provide the clothing pattern, fabric, pattern and color after editing and matching it to the merchant.

[0084] The second embodiment of the present application is:

[0085] Based on the first embodiment, please refer to Figure 6-Figure 7 ,in, Figure 6 It is a schematic structural diagram of the second embodiment of the present invention. Figure 7 It is a schematic diagram of the structure of a custom module according to the second embodiment of the present invention.

[0086] The semantically guided clothing editing and generating system provided by the present invention further comprises a custom module 201 ; the custom module 201 comprises a material uploading unit 202 and a pattern editing unit 203 .

[0087] For this specific implementation, the customization module 201 is connected to the clothing editing module 102;

[0088] The custom module 201 is used for allowing consumers to customize patterns for extraction and use by the clothing editing module 102. The addition of the custom module 201 increases personalized design, making it convenient for consumers to add their favorite patterns to clothing.

[0089] Wherein, the pattern editing unit 203 is connected to the material uploading unit 202;

[0090] The material uploading unit 202 is used for allowing consumers to upload materials by themselves and send them to the pattern editing unit 203;

[0091] The pattern editing unit 203 is used for allowing consumers to edit uploaded materials and generate clothing patterns.

[0092] The material uploading unit 202 can be connected to the Internet, allowing consumers to upload some favorite materials by themselves, and then arrange and combine the uploaded materials into their favorite patterns in the pattern editing unit 203, and finally edit the patterns into the clothing pattern in the clothing editing module 102.

[0093] In the semantically guided clothing editing and generating system described in this embodiment, the material uploading unit 202 can be connected to the Internet, allowing consumers to upload some favorite materials by themselves, and then modify the uploaded materials into their favorite patterns in the pattern editing unit 203, and finally edit the pattern into the clothing version in the clothing editing module 102, further increasing the personalized design.

[0094] The third embodiment of the present application is:

[0095] Based on the second embodiment, please refer to Figure 8-Figure 9 ,in, Figure 8 It is a schematic structural diagram of the third embodiment of the present invention. Fig. 9 4 is a schematic structural diagram of a try-on module according to a third embodiment of the present invention.

[0096] The semantically guided clothing editing and generating system provided by the present invention further comprises a fitting module 301 ; the fitting module 301 comprises a human body model storage unit 302 and a fitting unit 303 .

[0097] For this specific implementation, the try-on module 301 is connected to the clothing editing module 102;

[0098] The try-on module 301 is used to try on the clothes edited by the consumer on a human body model to see the overall effect on the body.

[0099] Wherein, the fitting unit 303 is connected to the human body model storage unit 302;

[0100] The human body model storage unit 302 is used to store human body models of various body types;

[0101] The fitting unit 303 is used to fit the edited garment onto a human body model.

[0102] After editing the clothing, the consumer can import the clothing model into the fitting unit 303, then select a suitable human body model from the human body model storage unit 302, and fit the clothing model on the human body model for the consumer to see the effect on the body.

[0103] In the clothing editing and generating system based on semantic guidance described in this embodiment, after the consumer has edited the clothing, the consumer can import the clothing model into the try-on unit 303, and then select a suitable human body model from the human body model storage unit 302, and try the clothing model on the human body model for the consumer to view a simple upper body effect.

[0104] The fourth embodiment of the present application is:

[0105] See also Fig.10 ,in, Fig.10 is a flow chart of the fourth embodiment of the present invention.

[0106] The present invention provides a semantically guided clothing editing generation method, comprising:

[0107] S1 material preview module 104 displays various optional clothing materials to consumers for their own selection;

[0108] S2 semantic guidance module 101 captures the consumer's voice instructions, converts the consumer's voice instructions into text output, extracts keywords, understands the consumer's intention, and generates clothing editing commands;

[0109] S3 The clothing editing module 102 extracts the corresponding clothing material from the material storage module 103 according to the clothing editing command, and edits and generates the clothing style required by the consumer.

[0110] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A clothing editing generation system based on semantic guidance, characterized in that: It includes a semantic guidance module, a clothing editing module, a material storage module and a material preview module; the clothing editing module is connected to the semantic guidance module; the material storage module is connected to the clothing editing module; the material preview module is connected to the material storage module; The semantic guidance module is used to capture the consumer's voice instructions, convert the consumer's voice instructions into text output, extract keywords therein, understand the consumer's intention, generate clothing editing commands and send them to the clothing editing module; The clothing editing module is used to receive the clothing editing command sent by the semantic guidance module, extract the corresponding clothing material from the material storage module according to the clothing editing command, and edit and generate the clothing style required by the consumer; The material storage module is used to store various types of clothing materials. The material preview module is used to display various clothing materials stored in the material storage module to consumers.

2. A clothing editing generation system based on semantic guidance as claimed in claim 1, characterized in that: The semantic guidance module includes a speech capture unit, a preprocessing unit, a conversion unit, a keyword extraction unit, an intention recognition unit and a command generation unit; the speech capture unit, the preprocessing unit, the conversion unit, the keyword extraction unit, the intention recognition unit and the command generation unit are connected in sequence; The voice capturing unit is used to capture the voice of the consumer; The pre-processing unit is used to clean and standardize speech; The conversion unit is used to convert speech into text; The keyword extraction unit is used to extract keywords from the text; The intention identification unit is used to combine the extracted keywords to determine the consumer intention; The command generation unit is used to generate a clothing editing command according to the consumer's intention and send it to the clothing editing module.

3. A clothing editing generation system based on semantic guidance as claimed in claim 2, characterized in that: The clothing editing module includes a command execution unit, an image generation unit and an image preview unit; the image generation unit is connected to the command execution unit; the image preview unit is connected to the image generation unit; The command execution unit is used to receive the clothing editing command sent by the semantic guidance module, extract the corresponding clothing material from the material storage module and send it to the image generation unit, and guide the image generation unit to perform editing; The image generation unit is used to receive clothing materials, splice the clothing materials, edit and generate clothing images, and send them to the image preview unit; The image preview unit is used to receive clothing images and display them to consumers for preview from various angles.

4. A clothing editing generation system based on semantic guidance as claimed in claim 3, characterized in that: The material storage module includes a clothing pattern storage unit, a fabric storage unit, a color storage unit, a pattern storage unit and an input unit; the input unit is connected to the clothing pattern storage unit, the fabric storage unit, the color storage unit and the pattern storage unit respectively; The clothing pattern storage unit is used to store clothing patterns of various sizes and types designed by merchants; The fabric storage unit is used to store various fabrics that can be processed and produced by the merchant; The color storage unit is used to store various clothing colors that the merchant can process and produce; The pattern storage unit is used to store various types of patterns designed by merchants; The input unit is used by merchants to input various clothing styles, fabrics, colors and patterns.

5. A semantically guided clothing editing generation system as claimed in claim 4, characterized in that: The clothing editing generation system based on semantic guidance also includes a custom module; the custom module is connected to the clothing editing module; The customization module is used to allow consumers to customize patterns for extraction and use by the clothing editing module.

6. A clothing editing generation system based on semantic guidance as claimed in claim 5, characterized in that: The custom module includes a material uploading unit and a pattern editing unit; the pattern editing unit is connected to the material uploading unit; The material uploading unit is used for allowing consumers to upload materials by themselves and send them to the pattern editing unit; The pattern editing unit is used for consumers to edit uploaded materials and generate clothing patterns.

7. A method for generating clothing edits based on semantic guidance, applied to a clothing edit generation system based on semantic guidance as claimed in any one of claims 1 to 6, characterized in that: include: The material preview module displays various optional clothing materials to consumers for them to choose from; The semantic guidance module captures consumers’ voice commands, converts them into text output, extracts key words, understands consumers’ intentions, and generates clothing editing commands; The clothing editing module extracts the corresponding clothing materials from the material storage module according to the clothing editing command, and edits and generates the clothing styles required by the consumer.

Images