Method and device for providing clothing statistical information

By analyzing clothing information, extracting and assigning main features, and generating statistical information representing characteristics, the problem of difficult to analyze clothing trends is solved, and an effective understanding and prediction of clothing trends is achieved.

CN118939826APending Publication Date: 2024-11-12CLO VIRTUAL FASHION INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410583573.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-08-25
Filing Date
2024-05-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art is difficult to effectively analyze and summarize the characteristics and trends in clothing trends, making it difficult to evaluate or predict clothing trends.

Method used

By analyzing information about multiple clothing, extracting major features and assigning them to relevant groups, generating statistics representing features and displaying these statistics to help understand clothing trends.

Benefits of technology

It realizes effective analysis and summary of clothing trend characteristics and trends, and provides visual statistical information to help users understand and predict clothing trends.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939826A_ABST
    Figure CN118939826A_ABST
Patent Text Reader

Abstract

The present disclosure relates to processing information about garments to generate statistical information. Methods and apparatus for providing statistical information of garments are disclosed. A method of giving statistical information about garments by interaction includes the steps of: analyzing information stored for each of a plurality of garments to extract primary features about a category of garments, where each primary feature represents a predominant feature corresponding to the category of garments; assigning the main features of the garments to groups, each group being associated with a representative feature of a category shared between the garments in each group; processing the information about the group-based garment to generate statistical information about the representative feature; and displaying the generated statistical information including the representative feature identifier.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The following is an embodiment involving processing information about clothing to generate statistical information, and giving the statistical information about clothing through interaction. Background Art

[0002] Different fabric properties can present different characteristics. Fabric properties can include the color, physical properties, and texture of the fabric. Different forms of clothing can be presented based on fabric properties and style. Clothing trends change over time and across regions. These trends are very important for the design, development, and marketing of new clothing, but because the clothing characteristics associated with trends are usually parameterized, they are difficult to analyze, understand, and summarize. In addition, it is difficult to evaluate or predict clothing trends because it is difficult to obtain statistical information about these trends and characteristics. Summary of the invention

[0003] Technical methods to solve problems

[0004] According to one embodiment, a method for providing statistical information includes the following steps: analyzing information stored for each of a plurality of garments to extract main features about the clothing category, wherein each of the main features represents a dominant feature corresponding to the clothing category; assigning the main features of the clothing to groups, wherein the groups are respectively associated with representative features of a category shared between garments in each group; processing information about the clothing based on the groups to generate statistical information about the representative features; and displaying the generated statistical information including the representative feature identifier.

[0005] The statistical information providing method according to an embodiment further includes the step of selecting the clothing for extracting the main features from the stored clothing according to at least one criterion.

[0006] The at least one criterion includes at least one of a design period of the garment, an identifier of a designer of the garment, and a keyword.

[0007] The step of assigning the main features to groups comprises the following steps: determining a reference value representing a standard or common feature for each of the groups; determining a similarity between the reference value of the group and the main feature; and assigning the main features to the groups based on the determined similarity.

[0008] The generated statistical information includes the ratio of the representative features in the clothing.

[0009] The category is one of color, fabric texture, clothing style, or clothing glyphs.

[0010] Also included is the step of, in response to receiving a selection of one of the representative features, displaying statistical information about the main features assigned to the group corresponding to the selected representative feature.

[0011] The statistical information about the primary features includes ratios of subsets of the primary features assigned to the groups.

[0012] The method also includes the step of providing emotion keywords corresponding to the representative features.

[0013] The method further includes the following steps: storing mapping information between the categories and the emotion keywords; and determining the emotion keywords to be displayed according to the stored mapping information.

[0014] According to one embodiment, the device includes a non-temporary computer-readable storage medium storing instructions; and at least one processor, which, when the processor executes the instructions, causes the at least one processor to perform the following steps: analyzing information stored for each of a plurality of garments to extract main features about the clothing category, wherein each of the main features represents a predominant feature corresponding to the clothing category; assigning the main features of the garments to groups, wherein the groups are respectively associated with representative features of a category shared between garments in each group; processing information about the garments based on the groups to generate statistical information about the representative features; and displaying the generated statistical information including the representative feature identifier.

[0015] The non-transitory computer-readable storage medium also stores instructions that cause the at least one processor to select the garment for extracting the primary feature based on at least one criterion.

[0016] The non-transitory computer-readable storage medium stores instructions that cause the at least one processor to perform the following steps when assigning the main features of the garments to the groups: determining a reference value representing a standard or common feature for each of the groups; determining a similarity between the reference value of the group and the main feature; and assigning the main feature to the group based on the determined similarity.

[0017] The non-transitory computer-readable storage medium stores instructions that cause the at least one processor to perform the step of, in response to receiving a selection of one of the representative features, displaying statistical information about primary features assigned to a group corresponding to the selected representative feature.

[0018] The non-transitory computer-readable storage medium further stores instructions for causing the at least one processor to generate an emotion keyword corresponding to the representative feature.

[0019] The non-transitory computer-readable storage medium stores instructions that cause the at least one processor to perform the following steps: storing mapping information between the categories and the emotion keywords; and determining the emotion keywords to be displayed according to the stored mapping information.

[0020] According to one embodiment, an electronic device includes: at least one processor; and a memory storing instructions, and when the at least one processor executes the instructions, the electronic device performs the following steps: analyzing information stored for each of a plurality of garments to extract main features about the clothing category, wherein each of the main features represents a predominant feature corresponding to the clothing category; assigning the main features of the garments to groups, wherein the groups are respectively associated with representative features of a category shared between garments in each group; processing information about the garments based on the groups to generate statistical information about the representative features; and displaying the generated statistical information including the representative feature identifier.

[0021] The at least one processor selects the garment for extracting the primary features based on at least one criterion.

[0022] The at least one processor performs the steps of determining a reference value representing a standard or common feature for each of the groups; determining a similarity between the reference value of the group and the primary feature; and assigning the primary feature to the group based on the determined similarity.

[0023] The at least one processor provides an emotion keyword corresponding to the representative feature. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart illustrating a method for providing clothing statistical information according to an embodiment.

[0025] Figure 2 is a schematic conceptual diagram of a grouping of major features of garments 210A to 210N according to one embodiment.

[0026] Figure 3 is a diagram of a user interface screen for displaying a three-dimensional garment pattern according to an embodiment.

[0027] FIG. 4A to FIG. 6 is a diagram showing an example of a user interface screen for providing statistical information about three-dimensional clothing according to an embodiment.

[0028] Fig. 7A and Figure 7B is a diagram illustrating PCCS tone mapping according to an embodiment.

[0029] Figure 8FIG. 4 is a diagram illustrating an HSV coordinate system according to an embodiment.

[0030] 9A to 9E FIG. 2 is a diagram illustrating emotion keywords according to an embodiment.

[0031] Fig.10 is a block diagram of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0032] The description of the specific structure or function of the embodiment is only for example, and the embodiment can be implemented in different forms. The actual implementation is not limited to the specific embodiment disclosed, and the scope of this specification includes all changes within the technical ideas described by the embodiment, their equivalents and even their substitutes.

[0033] The terms "first" or "second" etc. may be used to describe different components, but are only used to distinguish one component from other components. For example, the first component may be named as the second component, and similarly, the second component may also be named as the first component.

[0034] When it is stated that one component is “connected” or “contacting” another component, it can be directly connected or contacting the other component; however, it can also be understood that there is another component between them.

[0035] In the absence of special instructions in the content, a single expression includes multiple meanings. In this specification, the terms "including" or "having" are used to express the existence of features, numbers, steps, operations, components, accessories or combinations thereof recorded in the specification, and do not exclude the possibility of the existence or additional addition of at least one other feature, number, step, operation, component, accessory or combination thereof.

[0036] In the content, each of the sentences such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", "at least one of A, B or C" may include any or all possible combinations of the items listed in the sentence.

[0037] In the absence of other definitions, all terms used herein, including technical or scientific terms, have the common meanings understood by those of ordinary skill in the art. Commonly used terms as defined in dictionaries should be understood as having the meanings in the relevant technical content and should not be interpreted as idealized or overly formalized meanings if they are not clearly defined in this specification.

[0038] In the process of describing the examples with reference to the drawings, the same components are marked with the same reference numerals and repeated descriptions are omitted. In the process of describing the example embodiments, when it is determined that the detailed description of the relevant well-known structure or function will cause unnecessary confusion to the present disclosure, its detailed description is omitted.

[0039] In the following description, "feature" may refer to a characteristic or property of a garment. "Features" may include the color of a garment, the fabric type of a garment, and the style of a garment, etc. Garment features may be divided into multiple categories. For example, these categories may include a color category, a fabric type category, and a style category. A garment may be associated with multiple features of the same category. For example, a garment may include a blue front / back pattern and red sleeves. In this case, the garment features in the color category may include blue and red.

[0040] A main feature may refer to the predominant feature of a category in a single garment. For example, when the garment is predominantly blue, the main feature of the garment associated with the color category may be blue. For example, in the feature category of glyphs, the glyphs that appear the most times on the garment or occupy the largest surface area may be considered the main feature of the garment.

[0041] A primary feature may refer to a feature extracted from a clothing group that shares a class feature. For example, when clothing groups with pastel colors are grouped together, the most frequently occurring color or the color that occupies the largest surface area in the entire clothing group (e.g., pink) may be considered the representative feature of the clothing group.

[0042] Mood keywords can refer to terms or phrases that describe the mood or atmosphere associated with a particular color. Colors can often create a particular or specific atmosphere. Mood keywords are associated with different colors and can be used to describe the emotional or psychological impact of these colors. For example, mood keywords associated with the color red could be "passionate" or "energetic," while mood keywords associated with the color blue could be "calm" or "quiet."

[0043] Figure 1 is a flow chart illustrating a method for providing clothing statistical information according to an embodiment.

[0044] Figure 1 The steps of the embodiment may be performed in the order and manner shown, but the order of some steps may be changed or omitted without departing from the spirit and scope of the embodiment shown. Figure 1 The multiple steps shown may be performed in parallel or concurrently.

[0045] Reference Figure 1The processor 1030 can group the features of the various three-dimensional garments and provide statistical information related to the three-dimensional garments according to the grouped features.

[0046] In step 110, processor 1030 can receive the feature of each three-dimensional garment. These features can be stored in the memory of computing device in the form of garment data. Garment data can represent the pattern, identification information and pattern characteristics (e.g., color, style, texture type and font on the pattern) that constitute the garment. Processor 1030 can receive data related to the subset of three-dimensional garments analyzed for statistical information. The subset of three-dimensional garments can be a garment object for analysis, for example, can include garments designed or developed recently (e.g., designed within one year), garments designed in a specific period, or garments of a specific season (e.g., summer), or garments designed by at least one specific designer.

[0047] Processor 1030 may analyze the information stored for each of the plurality of garments to extract the main features of the garment category. Each main feature may represent a dominant (or predominant) feature of a corresponding category in the garment. The category may be one of the following: color, fabric texture (or multiple textures), garment style, or garment glyphs.

[0048] Most importantly, three-dimensional clothing may include virtual clothing that matches the user's body size, virtual clothing for a three-dimensional virtual character, or virtual clothing for an avatar. Three-dimensional clothing is digital data including information for production and use in the market.

[0049] In step 120, the processor 1030 may determine the main features of each three-dimensional garment based on the features of the received three-dimensional garments. The processor 1030 may select garments for extracting the main features from the stored garments according to at least one criterion. The at least one criterion may include at least one of the design period of the garment, the identifier of the garment designer, and keywords. According to an embodiment, the processor 1030 may determine the main features based on the type of fabric, color, font, or other characteristics occupying at least one pattern on the garment relative to the total surface area of ​​at least one pattern of the same garment. As will be described in Figure 3As detailed in , a three-dimensional garment can be composed of paper pattern pieces 311, 313, 315, 317, and 319 displayed in a two-dimensional pattern area 310. The processor 1030 can determine the overall ratio of specific features in the paper pattern pieces 311, 313, 315, 317, and 319. Features can be associated with a variety of categories such as fabric type, color, and font. For a specific category, the feature that occupies the largest area or is repeated the most times on the garment among all the paper pattern pieces 311, 313, 315, 319 of the garment (e.g., blue or polyester fabric) can be determined as the main feature of the garment.

[0050] In step 130, the processor 1030 may classify the main features of the plurality of three-dimensional garments into a plurality of groups based on a predetermined feature grouping method. The processor 1030 may assign the main features to the groups. Each group may be associated with a representative feature of a category shared between garments in each group. The processor 1030 may set a standard or reference value representing a common feature for each group. The processor 1030 may determine a similarity between the reference value of the group and the main feature. The processor 1030 may assign the main feature to the group based on the determined similarity. The reference value may be associated with the representative feature of the category shared between garments in each group. The processor 1030 may set a standard or reference value representing a common feature for each group. The processor 1030 may determine a similarity between the reference value of the group and the main feature. The processor 1030 may assign the main feature to the group based on the determined similarity. Figure 2 Elaborate on the method of grouping the main features into groups.

[0051] In step 140, the processor 1030 may determine one of the main features included in each of the plurality of groups as a primary feature of the corresponding group. The processor 1030 may process the group-based clothing information to generate statistical information about the representative feature.

[0052] The reference values ​​of the plurality of groups according to the predetermined feature grouping method may be different values ​​from the representative features. The reference value may refer to a standard feature generally recognized in an industry or model. For example, the reference value of the pure blue feature is (0, 0, 255) in the RGB model, (240, 100, 100) in the HSV model, and (0, 150, 0.060) in the PCCS (Practical Color Coordinate System).

[0053] On the other hand, the main feature of a color (e.g., red) in a clothing group can be determined by the frequency or dominance of various colors appearing in the clothing group. The frequency of the main features of multiple three-dimensional clothing can refer to the frequency of actually using the corresponding main features in multiple three-dimensional clothing. For example, in a color category, the reference value of the group can be the color coordinates of a common color or a standard color (e.g., pure red). On the other hand, a color that is frequently or mainly used in clothing of a group can be determined as the representative color of the group.

[0054] The processor 1030 according to an embodiment may determine a main feature that is not a representative feature in each of the plurality of groups as a sub feature (eg, a main feature).

[0055] In step 150, the processor 1030 may determine and provide statistical information related to a plurality of three-dimensional garments based on the representative features of the plurality of groups. The processor 1030 may display the generated statistical information including the identifiers of the representative features. The generated statistical information may include the ratio of the representative features in the garments.

[0056] Processor 1030 may, in response to receiving a selection of one of the representative features, display statistical information about the main features assigned to the group corresponding to the selected representative feature. The statistical information about the main features may include a ratio of a subset of the main features assigned to the group.

[0057] The processor 1030 according to an embodiment may match the sub-feature to the sub-feature of the representative feature of the corresponding group, and may display the sub-feature and the representative feature together in response to the user's selection input. Figures 4C to 6 ,as well as Fig.9E to detail the methods for providing statistical information about sub-features.

[0058] According to an embodiment, the processor 1030 may match the representative feature with the predetermined emotion keyword and display the matching result. The predetermined emotion keyword may be generated by matching the multiple axes included in the space representing the feature with the keyword. 9A to 9E Let’s explain the emotion keywords in detail.

[0059] Figure 2 is a schematic conceptual diagram of a grouping of major features of garments 210A to 210N according to one embodiment.

[0060] Reference Figure 2, the processor 1030 may extract each feature (210A to 210N) from a plurality of three-dimensional garments (201A to 210N). The memory 1050 may store three-dimensional garments (201A to 201N) including paper patterns forming the three-dimensional garments and features of each paper pattern (e.g., color, fabric type, and font). The three-dimensional garments (201A to 201N) may be a subset of the garments stored in the memory 1050, and may be filtered using a variety of criteria such as design period, designer's name or identification information, and keywords related to season or style (e.g., summer, winter, classic, young). For example, the processor 1030 may extract the main features (210A to 210N) of the three-dimensional garments (201A to 201N) by counting the frequency or dominance of the features of the three-dimensional garments (201A to 201N) of interest. The processor 1030 may generate groups ( 240A to 240M) from the extracted main features ( 210A to 210N) and determine representative features ( R1 to Rm) based on actual frequencies or dominances of features extracted from the garments ( 210A to 210N).

[0061] Since clothing can have many different features, the main features shown in the accompanying drawings are The number of may vary depending on the data that the processor 1030 is programmed to extract. In this example, it is assumed that each garment (201A to 201N) has z main features, each of which may correspond to one of the categories 1 to z. However, in reality some garments may have fewer main features than other garments. Figure 2 middle, Indicates the main feature, the subscript indicates the three-dimensional clothing number, and the superscript indicates the feature category (such as color, fabric type, font, etc.). For example, Refers to the color that is the main feature of the three-dimensional clothing 201A. Refers to other colors that are the main features of three-dimensional clothing 201B, refers to the type of fabric (e.g. wool) that is the main feature of the three-dimensional garment 201A. Refers to other fabric types (e.g., polyester) that are the primary features of three-dimensional garment 201B.

[0062] After extracting the main features (210A to 210N), the processor 1030 may determine the feature categories used to provide statistical information. For example, if the processor 1030 has received features related to color, texture, fabric type, fabric physical properties, and clothing style, the processor 1030 may only determine color as a feature of interest for providing statistical information.

[0063] In this example, processor 1030 may determine color as a primary feature of the three-dimensional garment based on the frequency or dominance (eg, ratio) of the surface area occupied by the color within the three-dimensional garment.

[0064] For example, when red occupies 70% of the surface area of ​​the three-dimensional garment 201A and yellow occupies 30% of the surface area, the processor 1030 determines that red is the main feature of the three-dimensional garment 201A. Likewise, when red occupies 70% of the surface area of ​​the three-dimensional garment 201B and yellow occupies 30% of the surface area, the processor 1030 determines that red is the main feature of the three-dimensional garment 201B. As another example, when yellow occupies 70% of the surface area of ​​three-dimensional garment 201N and red occupies 30% of the surface area, processor 1030 determines yellow as the primary feature of three-dimensional garment 201N.

[0065] When color is used as a feature of clothing, the color may be parameterized according to a color model or system (e.g., red, green, blue (RGB) values, HSV coordinate system, and PCCS hue diagram). The processor 1030 may use color parameters or values ​​under the color model or system to parameterize the primary features. K-means clustering and other algorithms can be used to generate and classify the main features. For example, the main features and main features If the main feature is pure red and light red, then these two features can be assigned to the same group 240A according to a series of grouping methods. On the other hand, if the main feature If it is yellow, it can be assigned to group 240M according to a series of grouping methods (such as K-means clustering).

[0066] The processor 1030 may determine each group (G 1 , G 2 , …, G m ). In the context of color, the reference value may represent the color coordinates of a standard or common color under a color model or system. For example, pure red, pure green, and pure blue are part of the standard or common colors, and the corresponding color coordinates may be the reference values ​​of these colors. The processor 1030 according to an embodiment may select the main feature according to the similarity with the reference value. The similarity between the main feature and the reference value can be determined based on the distance between the color coordinates of the main feature and the reference value. For example, when the reference value G 1 is the reference value of the red color coordinate, then the color coordinate can be located at the reference value G 1 The color coordinates of Assigned to group 240A. Similarly, when the reference value G m is the yellow color coordinate, then the color coordinate can be located at the reference value G m The color coordinates of Assigned to group 240M. Thus, each main feature can be assigned to a color group.

[0067] After assigning the main features of different three-dimensional garments to each group, the processor 1030 may determine a representative feature (RR) of each of the plurality of groups. 1 , R 2 , …, R m ). Representative features (R 1 , R 2 , …, R m ) can be determined by weighted averaging the main features assigned to the respective groups 240A to 240M. The weight may refer to the frequency or surface area ratio of the main features appearing in each group. The representative characteristic (R) of the group (240A to 240M) 1 , R 2 , …, R m ) may be different from the reference value (G 1 , G 2 , …, G m )different.

[0068] In the example of 100 garments and 100 main features, the main features can be classified into 10 groups, and the reference value G of group 240A is 1 It can be a pure red color coordinate. Here, 10 is the reference value G in group 240A. 1 The main features are similar, among which 5 main features are light red, 3 main features are dark red, and 2 main features are yellow-red. In this case, the frequencies of light red, dark red, and yellow-red are 5, 3, and 2, respectively. Therefore, the processor 1030 can assign these frequencies as weights to the color coordinates of light red, dark red, and yellow-red, and assign the weighted average of the coordinates to the representative feature R 1 In contrast, the reference value G of group 240A 1 The same process applies to other groups.

[0069] Will refer to later FIG. 4A to FIG. 6 Detailed description of representative features (R) for display or further processing by processor 1030 1 , R 2 , …, R m )260 statistics.

[0070] Figure 3 is a diagram of a user interface screen for displaying a three-dimensional garment pattern according to an embodiment.

[0071] Reference Figure 1 and Figure 2 The same description applies to Figure 3 , and the repeated content is omitted here.

[0072] Reference Figure 3 , the three-dimensional clothing can be displayed in the two-dimensional space 310 and the three-dimensional virtual space 330. The three-dimensional clothing can be composed of the paper patterns 311, 313, 315, 317 and 319 shown in the two-dimensional space 310. In addition, the three-dimensional clothing can be configured around the avatar 331 in the three-dimensional space 330 or worn on the avatar 311.

[0073] According to one embodiment, fabric property data of patterns 311, 313, 315, 317 and 319 and surface areas of patterns 311, 313, 315, 317 and 319 are used to determine the main features of the three-dimensional garment. The fabric property data and the surface areas of the patterns may be stored in the memory 1050 for use.

[0074] For example, suppose Figure 3 The garment shown is three-dimensional garment 201A. Pattern 311 is yellow with an area ratio of 12%, pattern 313 is red with an area ratio of 33%, pattern 315 is yellow with an area ratio of 12%, pattern 317 is red with an area ratio of 38%, and pattern 319 is white with an area ratio of 5%. At this time, red accounts for the largest proportion of the surface area (33%+38%=71%), so processor 1030 can determine the main features of three-dimensional garment 201A. Is red.

[0075] Although color is described as a primary feature, this is only an example. For example, fabric physical properties, fabric feel (or texture), clothing style, and font shape can all be used as features, and the primary feature can be determined based on the predominance or ratio of the surface area occupied in the three-dimensional garment.

[0076] FIG. 4A to FIG. 6 is a diagram showing an example of a user interface screen for providing statistical information about three-dimensional clothing according to an embodiment.

[0077] Reference Figures 1 to 3 The same description applies to FIG. 4A to FIG. 6 , and the repeated content is omitted here.

[0078] Reference FIG. 4A to FIG. 4C , the processor 1030 may provide the three-dimensional garment content statistics in the form of a ring 410 and / or a list 420 .

[0079] According to an embodiment, the three-dimensional clothing statistical information may include information about representative features (R 1 , R 2 , …, R m )260 and / or statistical information about the ratios of main features within the group to which the representative features correspond.

[0080] According to one embodiment, the statistical information of the ring 410 includes information about the representative features (R 1 , R 2 , …, R m )260 ratios and / or key features included in a group For example, each representative feature (R 1 , R 2 , …, R m ) is 50% red, 30% yellow and 20% blue, the area occupied by each of the rings 410 can be determined according to the ratio of red, yellow and blue. 1 The main features included The ratio is 50% light red, 30% red, and 30% dark red.

[0081] When the area is 20%, the area occupied by each color in the statistics of the ring 410 is determined according to the ratio of light red, red, and dark red.

[0082] like Figures 4A to 4C As shown, a hexadecimal color code can be used to display a color as a feature. In a hexadecimal color code, a six-digit code can be used to represent a color, wherein the first two digits provide information about the intensity of red in the color, the middle two digits provide information about the intensity of green in the color, and the last two digits provide information about the intensity of blue in the color. The value of each pair of two digits can have a value between 0 and 255.

[0083] Figure 4A A user interface screen 401 including a statistics of a circle 410 is shown, wherein there are 9 representative features in the statistics of the circle 410, wherein red having a color hexadecimal code of CA2744 accounts for the largest proportion, which is 23.12%. For example, when a user selects a color by hovering a cursor over a portion 410-1 of the statistics of the circle 410 or clicking on the portion 410-1, the color hexadecimal code of CA2744 and its ratio (23.12%) may be displayed and may be displayed overlaid on the interface screen 401.

[0084] The user may request a list 421 of statistical information that lists a subset of representative features in the statistics of the ring 410 and their ratios. The processor 1030 may detect receipt of such a request from the user and, if Figure 4B 4, a representative feature shown in user interface 402 is shown. A user can invoke a menu by double-clicking on circle 410 and then selecting an item from the menu to make a request. Figure 4B In the example of FIG. 4 , nine representative features are displayed in the statistics of the ring 410 , but six representative features are listed in the list 421 . The number of representative features displayed may be preset or set by the user.

[0085] The characteristic color hexadecimal codes, Pantone colors, and ratios shown in table 421 may be as follows: Figure 4B The Pantone color matching system is a standardized color reproduction system frequently used in the printing and design industries. Figure 4B As shown, the representative features of all the garments of interest (R 1 (Red: Color Hex #CA2744, Pantone Color Card 0000-ekf44); R 2 (Pantone color card cashew nut 0000-ekf44, color hexadecimal #FH546D); R 3 (Pantone color mustard girl color, color hexadecimal #SONG32); R 4 (Pantone color chocolate bay, color hex #DHJK51); R 5 (Pantone color card cyscys150504-02, color hexadecimal #DJHDHD), and R 6 The ratios of (Pantone color ivory 0000-ekf44, color hexadecimal #WU155D) are 23.12%, 18.95%, 14.12%, 13.01%, 9.76% and 7.01%, respectively, and these ratios can be displayed in the list 421.

[0086] Figure 4C 4 is a user interface screen 403 that displays a main feature list 422 based on a representative feature list 421 and a ring 410 according to an embodiment. The user interface screen 403 may be displayed in response to receiving a user input selecting one of the representative features 421-1 (red, hexadecimal #CA2744) in the representative feature list 421. For example, the user input selecting the representative feature of interest may be clicking on a screen area that displays one of the representative features. After receiving the user input, the processor 130 may Figure 4CAs shown, statistical information about the ratio of the main features in the selected representative feature group is displayed in the main feature list 422. Figure 4B As shown, it can be Figure 4C The representative feature list 421 shows 6 representative features. Figure 4C Six main features are displayed in the main feature list 422.

[0087] exist Figure 4C In one embodiment, the table 420 shows the statistical information about the representative features (R 1 , R 2 , …, R m )260 ratios and / or main features assigned to a group In addition, when the user selects the representative feature R 1 (red, color hex #CA2744), the main feature list 422 includes the same as R 1 Related main features (e.g., colors with color hexadecimals CA2755, D6F4DF, CFDAFF, 12DF44, CA2744, and DFSDD). In addition, statistical information about main feature ratios (e.g., 47.02%, 19.73%, 12.48%, 10.26%, 6.51%, and 3.99%) can be shown in list 420.

[0088] According to one embodiment, the processor 1030 can link the ring 410 statistics and the list 420 statistics, and provide the list 420 statistics through the user's selection input in the ring 410 (for example, selecting a color in the ring 410 statistics), and can also provide the ring 410 statistics based on the user's selection input in the list 420 statistics (for example, selecting a color in the list 420 statistics).

[0089] like FIG. 4A to FIG. 6 As shown, the processor 1030 according to an embodiment can display three-dimensional clothing statistics. FIG. 4A to FIG. 4CThe examples provided relate to a part of a workspace on an application and / or a network that can be implemented as a project, an assortment, a workroom, etc. Specifically, the processor 1030 can provide a variety of statistical data based on the three-dimensional clothing content. The processor 1030 can receive the selected representative features and the main features of the selected representative features from a server connected to a database. More specifically, the processor 1030 can provide various statistical information based on the three-dimensional clothing, and can provide comparative statistical information between each project, assortment, and workroom using the features extracted from the project, assortment, and workroom of the above examples. The project, assortment, and workroom in the above examples are the names of a part of the workspace on the application and / or the network, which are equivalent to concepts such as groups, categories, and folders. In the following content, the project, assortment, and workroom that may include three-dimensional clothing are referred to as groups.

[0090] Reference Figure 5 , the processor 1030 may provide statistical information related to the three-dimensional garment data in the form of a column 500 .

[0091] The processor 1030 according to an embodiment may extract representative features (R) from the three-dimensional clothing released in the previous year. 1 , R 2 , …, R m ) with the current trend features to provide statistical information. For example, the processor 1030 may match the representative features (R 1 , R 2 , …, R m ) in descending order of frequency, and then provide the color usage ratios (Rate) of the past years in a column 500. When receiving user input, the processor 1030 may Figure 5 The bar graph shown is shown as Figure 4B or Figure 4C The statistical information of the representative feature list 421 and / or the representative main feature list 422 is shown. The use of a bar chart can help users easily understand the trend or change of the main functions over the years.

[0092] Reference Figure 6, the processor 1030 can provide statistical information related to the three-dimensional clothing data through a scatter chart (Scatter Chart) 600. The processor 1030 can distribute the representative features and main features in the form of dots on the chart based on the X-axis 602 (for example, Hue (0-360 degree color spectrum unit)) and the Y-axis 601 (for example: saturation / brightness (100% unit as a reference)) for display. In addition, the size of the dot can indicate the usage frequency and area ratio of the distributed representative features or main features. The feature points represent multiple groups as representative features (R 1 , R 2 , …, R m ) color or circular form.

[0093] For example, when the representative feature (R 1 , R 2 , …, R m ) is displayed as a distribution of points, the points may be distributed in the yellow region 610, the blue region 620, and the red region 630 representing the color spectrum. When the user clicks (or hovers the cursor over) a point in the blue region 620 (representing a main feature associated with blue), the processor 1030 displays the aggregated sub-color values ​​(e.g., main feature) associated with the selected point in a frame 621 superimposed on the scatter plot 600. ).

[0094] Fig. 7A and Figure 7B is a diagram illustrating PCCS tone mapping according to an embodiment.

[0095] Reference Figures 1 to 6 The same description applies to FIG. 7A to FIG. 7B , and the repeated content is omitted here.

[0096] Each feature according to an embodiment may include color or color and texture. The color may be determined based on at least one of a base color of the fabric and a base color of the fabric and a base texture of the fabric. The color of the fabric may be defined by calculating the average value of the resultant color obtained by multiplying the base texture with the base color of the fabric. However, when calculating the color of the fabric, if only a gray texture is used, the representative color may be extracted using only the base color of the fabric.

[0097] Reference Fig. 7A , the processor 1030 may convert the main features into Mapped to a tone map. Here, the preset color system can be expanded to multiple types, and in one embodiment of the present disclosure, it is a PCCS color system 700. In the PCCS color system 700, colors are based on the four psychological primary colors: R (red), Y (yellow), G (green) and B (blue), and these four colors are placed relative to each other. These four colors are divided into 8 colors in two, and 4 colors that make the colors equidistant are added to form a total of 12 colors, and these 12 colors are then divided into 24 colors. In the color symbol, ':' is used to connect numbers and symbols. The color symbol is marked with the first letter of the English name of the color, plus the lowercase letter of the adjective of the color as a prefix, starting from red and marked as 1: pR, 2: R, 3: yR, 4: rO, 5: O·······, 22: P, 23: rP, 24: RP.

[0098] In the PCCS color system 700, the lightness standard visually divides white to black at equal intervals. White to black is divided into two halves, then divided in the middle to form 5 levels, and then divided again into 9 levels, and finally divided into 17 levels. The lightness symbol refers to the Munsell system, white is 9.5, black is 1.5, and every 0.5 in between is one level, for a total of 17 levels.

[0099] The standard of saturation is to use the high-saturation color area that is obviously felt by the senses in the actual color material as the reference color of each color. In the lightness level of the reference color of each color, the reference color and the lowest saturation color are evenly divided into 9 levels, and the saturation symbol s is added to distinguish it from other systems to mark it as 1s, 2s, 3s,..., 9s. Unlike Munsell, saturation uses absolute saturation values. In other words, all colors are composed of 9 levels of absolute values, regardless of being perceived at equal intervals.

[0100] refer to Figure 7BHue can be said to be a composite concept of brightness and saturation, which refers to the difference in color state. The difference in color state means that even colors in the same series have different degrees of brightness, darkness, strength, weakness, thickness, lightness, shallowness, and depth. The PCCS hue diagram 710 has 12 hues, namely pale, light, bright, vivid, strong, soft, dull, deep, dark, light grayish, grayish, and dark grayish. Each color can be divided into 12 hues. When colors with the same hue are grouped together, they can be clearly felt to belong to the same group despite the difference in brightness. In low-saturation hues such as light grayish hues and dark grayish hues, there is no obvious color-based brightness difference, but in high-saturation vivid hues, the brightness difference is obvious. In addition, even if the colors are in the same color system, if the hues are different, the emotional effects will be different, and even if the colors are in different color systems, the emotional effects will be the same if the hues are the same. Therefore, hue can more accurately represent the image, color scheme, or color name of a color.

[0101] Processor 1030 may use PCCS color system 700 and PCCS tone map 710 to identify the main features. For example, the main features (e.g., red) can be mapped to Strong R in the PCCS tone map 710. Main feature 2 (e.g., light red) can be mapped to Soft R in the PCCS tone map 710. By repeating the above process, the main features can be Clustering and grouping.

[0102] Figure 8 FIG. 4 is a diagram illustrating an HSV coordinate system according to an embodiment.

[0103] Reference Figures 1 to 7B The same description applies to Figure 8 , and the repeated content is omitted here.

[0104] HSV (Hue, Saturation, Value) color space or HSV model is a method of expressing colors and also a method of arranging colors. HSV space, HSV color space or HSV model can use hue (Hue), saturation (Saturation) and value (Value) as three axes, and use the coordinates of the three axes to map a specific color to the coordinates to specify the color. For example, the three axes can be the x-axis, y-axis and z-axis, or can be composed of the x-axis, y-axis and angle. In the present invention, HSV space, HSV color space, HSV model, etc. are only examples of color spaces for expressing specific colors, and the implementation method is not limited to this.

[0105] Reference Figure 8 , the processor 1030 can identify the main features in the color space (e.g., HSV space 800) For example, the HSV space 800 may be represented as an H axis, an S axis, and a V axis. At this time, the processor 1030 separates the main features into the H axis based on the S axis threshold 810 set in the HSV space 800. It is divided into colored and achromatic colors. Colored and achromatic colors are determined based on saturation. The closer to the center line of the cylinder, the closer to the achromatic color. For example, the S-axis threshold 810 can be set to any point on the saturation axis (hereinafter referred to as the S-axis) in the HSV space 800, which is represented as the circumference of the cylinder from the center line of the cylinder to the circumference of the cylinder. Therefore, when the S-axis threshold 810 is applied to the H-axis and V-axis representation, it can be represented as the circumference of the small cylinder represented by the dotted line in the HSV space 800 represented by the cylinder. For example, when the main feature 1 If the color is red, it can be located at red 820. Since red 820 is located at a position on the S axis that exceeds the S axis threshold 810, the processor 1030 can determine that red 820 is colored. Therefore, the processor 1030 can distinguish the main features based on the S axis threshold 810 set in the color space. Thresholds can be set for H, S, and V of the color space respectively. Therefore, by setting the H axis threshold, the main features can be distinguished according to color. By setting the V-axis threshold, you can distinguish the main features according to brightness

[0106]

[0107] The HSV spatial expression method of the present invention is not limited to the cylinder in the described embodiment, and can be expressed in various possible ways such as a cone.

[0108] Fig. 9A and Fig. 9B FIG. 2 is a diagram illustrating emotion keywords according to an embodiment.

[0109] Reference Figures 1 to 8 The same description applies to Fig. 9A and Fig. 9B , and the repeated content is omitted here.

[0110] Reference Fig. 9A and Fig. 9B , the processor 1030 may provide the emotion keyword corresponding to the representative feature. The processor 1030 may store the mapping information between the category and the emotion keyword, and may determine the emotion keyword to be displayed according to the stored mapping degree. The processor 1030 maps the main features of the PCCS tone map 710 to and representative features (R 1 , R 2 , …, R m ) to match the emotion keywords. The processor 1030 may use the three-dimensional emotion keyword map 900 and / or the two-dimensional emotion keyword map 910 to match the main features And representative features (R 1 , R 2 , …, R m ). For example, although the main feature indicates red, but it may match Warm Red in the 3D emotional keyword map.

[0111] Reference Fig. 9A , emotional keywords can be represented by a three-dimensional keyword graph 900. Or, Fig. 9B As shown, the emotion keywords can be represented by a two-dimensional emotion keyword map 910. The processor 1030 can select one of these methods to map colors to emotion keywords. For example, the processor 1030 can use a large language model (LLM) and map colors to emotion keywords. For example, the two-dimensional emotion keyword map 910 can be used and the color can be mapped to the emotion keyword by using the following method: FIG. 9C to FIG. 9E The user interface screen shown provides statistical information.

[0112] Fig. 9C 9 is an example of a user interface screen 903 providing statistical information based on a donut chart 930. Specifically, the processor 1030 may display the colors extracted from the clothing and the emotional keywords mapped thereto in the form of a donut chart 930. The mapping between the colors and the emotional keywords may be stored in a database of the server. The mapping between the colors and the emotional keywords is not always a one-to-one correlation, and multiple colors may be mapped to the same emotional keyword.

[0113] When the user hovers the cursor over a portion 930 - 1 of the doughnut chart 930 or clicks the portion 930 - 1 , an emotion keyword (eg, gentlemanly) mapped to a color ratio (eg, 25.87%) as a representative feature may be displayed on the user interface screen 903 .

[0114] The user can command the display of a representative feature list 941 listing all representative features or a subset. Fig.9D For example, when a user requests statistical information, six representative colors (features) and the emotional keywords mapped to them (for example: Dandy; Clear; Casual; Gorgeous; Formal; Pretty) can be displayed in the form of a feature list 941.

[0115] Fig.9E 9 is a diagram of a user interface screen 905 according to an embodiment, which displays a main feature list 941 of emotion keywords mapped to main features (colors) in response to a user selecting a representative feature. Fig.9E , the user can select the first color mapped to the emotional keyword "gentleman" by clicking on portion 941-1. By selecting a color (e.g., a representative feature), all or a subset of the main features associated with the selected color can be displayed in the main feature list 942. For example, the first 6 main features associated with the representative feature color (mapped to the emotional keyword "gentleman") can be listed in the main feature list 942. The remaining main features associated with the same representative feature color may not be listed in the main feature list 942.

[0116] According to an embodiment, according to different countries, cultural circles, life circles, etc., people have different cognitions for the same color area of ​​the same color, therefore, different emotion keywords can be set based on this. For example, when generating statistical information of a country, the emotion keywords provided by the processor 1030 can match the emotion keywords perceived by the country to the color. In this way, the processor 1030 can adopt an emotion keyword graph capable of deriving localized results. For another example, the processor 1030 can adopt an emotion keyword graph based on different personal information such as age, gender and race. Thus, the processor 1030 can provide different emotion keywords for each user. As another example, the processor 1030 can adopt an emotion keyword graph capable of deriving personalized and localized results. The user can manually set these different mapping structures, or they can be pre-stored in the memory 1050 for loading. Thus, after obtaining statistical information, the user can conveniently and accurately determine whether a specific type or style of clothing is needed.

[0117] According to one embodiment, the processor 1030 can provide statistical data related to multiple three-dimensional clothing in a manner suitable for the user. For example, the processor 1030 can provide statistical information related to different types of clothing. At this time, the first category of clothing can be clothing for the S / S (spring / summer) season, which belongs to the first group; the second category of clothing can be clothing for the F / W (autumn / winter) season, which belongs to the second group. In other words, the processor 1030 can provide statistical information related to three-dimensional clothing in response to the selection of clothing by users in each group. That is, the processor 1030 can provide statistical information related to the clothing data of the first group and statistical information related to other clothing in the second group. As another example, the processor 1030 can compare the clothing-related statistical information of the two groups, thereby allowing the user to easily identify the similarities and differences between the statistical information associated with the two groups.

[0118] Fig.10 is a block diagram of an electronic device according to an embodiment. Fig.10 According to an embodiment, the electronic device 1000 may include a processor 1030 , a memory 1050 , and an output device 1070 (eg, a display). The processor 1030 , the memory 1050 , and the output device 1070 may be connected to each other via a communication bus 1005 .

[0119] The output device 1070 may display the three-dimensional garment statistical information processed by the processor 1030 .

[0120] The memory 1050 can store the three-dimensional clothing converted by the processor 1030. In addition, the memory 1050 can store various information generated during the processing of the processor 1030. In addition, the memory 1050 can store various data and programs. The memory 1050 can include a volatile memory or a non-volatile memory. The memory 1050 has a large-capacity storage medium such as a hard disk, thereby storing various data.

[0121] In addition, the processor 1030 may execute the above-referenced Figure 1At least one method or algorithm corresponding to at least one method described in Figure 9. Processor 1030 can be a data processing device embodied by hardware, wherein the hardware includes a circuit having a physical structure for performing a desired operation. For example, the target operation may include a code or instructions included in a program. For example, a device implemented by hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an application-specific integrated circuit (ASIC), and a field programmable gate array (FPGA).

[0122] The processor 1030 may execute a program and control the electronic device 1000. The program code executed by the processor 1030 may be stored in the memory 1050.

[0123] The above-described device can be implemented by hardware components, software components, and / or a combination of hardware components and software components. For example, the device and components described in the embodiment can be embodied using one or more general-purpose computers or special-purpose computers such as processors, controllers, arithmetic logic units (arithmetic logic units, ALU), digital signal processors (digital signal processors), microcomputers, field programmable arrays (field programmable arrays, FPA), programmable logic units (programmable logic units, PLU), microprocessors, or any other device capable of executing and responding to instructions (instructions). The processing device can execute an operating system (OS) and one or more application software executed in the operating system. In addition, the processing device responds to the execution of the software to access, store, operate, process and generate data. For ease of understanding, a method with only one processing device is described, but a person of ordinary skill in the art should understand that the processing device can include multiple processing elements (processing element) and / or multiple types of processing elements. For example, the processing device can include multiple processors or a processor and a controller. Furthermore, other processing configurations such as parallel processors can also be included.

[0124] Software can include a computer program, code, instructions, or a combination of more than one of these, that causes a processing device to operate in a desired manner, or that, alone or collectively, commands a processing device. Software and / or data can be permanently or temporarily embody any type of device, component, physical device, virtual device, computer storage medium or device, or transmitted signal wave for interpretation by a processing device or for providing commands or data to a processing device. Software is distributed on computer systems connected by a network and can be stored or executed in a distributed manner. Software and data can be stored in one or more computer-readable storage media.

[0125] The method according to the embodiment is embodied in the form of a program command that can be executed by a variety of computer means and recorded in a computer-readable medium. The computer-readable medium can include program commands, data files, data structures, etc. in a single or combined form. The program instructions recorded in the medium can be instructions specially designed and constructed to implement the embodiment, or instructions that ordinary technicians in the field of computer software can use based on known ones. The computer-readable recording medium can include magnetic media such as hard disks, floppy disks, and tapes; optical media similar to CD-ROMs, DVDs, etc.; magneto-optical media similar to floptical disks, and hardware devices specially constructed for storing and executing program commands similar to read-only memories (ROMs), random access memories (RAMs), flash memories, etc. Examples of program instructions include not only machine language codes generated by compilers, but also high-level language codes that can be executed by computers by using interpreters, etc.

[0126] To perform the operations of the embodiments, the hardware device may be configured in such a manner that the operations are implemented with one or more software modules, and vice versa.

[0127] In summary, the embodiments are described through limited drawings, and a person skilled in the art can make various changes and modifications based on the description. For example, the described techniques are performed in a different order from the described method, and / or the described systems, structures, devices, circuits and other components are combined or combined in a different form from the described method, or replaced or substituted by other components or equivalents, and appropriate results can also be obtained.

[0128] Accordingly, other embodiments, other examples, and their equivalents are within the scope of the appended claims.

Claims

1. A method for providing statistical information, characterized in that: The following steps are involved: analyzing information stored for each of a plurality of garments to extract main features related to the garment category, wherein each of the main features represents a dominant feature corresponding to the garment category; assigning the main features of the garments to groups, wherein the groups are respectively associated with representative features of the categories shared between the garments in each group; processing information about the garments based on the group to generate statistical information about the representative features; and The generated statistical information including the representative feature identifier is displayed.

2. The statistical information providing method according to claim 1, characterized in that: The method further includes selecting the garment for extracting the main features from the stored garments according to at least one criterion.

3. The statistical information providing method according to claim 2, characterized in that: The at least one criterion includes at least one of a design period of the garment, an identifier of a designer of the garment, and a keyword.

4. The statistical information providing method according to claim 1, characterized in that: The step of assigning the main features to groups comprises the following steps: determining for each of said groups a reference value representing a standard or common characteristic; determining a similarity between a reference value of the group and the primary feature; and The primary features are assigned to the groups based on the determined similarities.

5. The statistical information providing method according to claim 1, characterized in that: The generated statistical information includes the ratio of the representative features in the clothing.

6. The statistical information providing method according to claim 1, characterized in that: The category is one of color, fabric texture, clothing style, or clothing font.

7. The statistical information providing method according to claim 1, characterized in that: The following steps are also included: In response to receiving a selection of one of the representative features, statistical information about the main features assigned to the group corresponding to the selected representative feature is displayed.

8. The statistical information providing method according to claim 7, characterized in that: The statistical information about the primary features includes ratios of subsets of the primary features assigned to the groups.

9. A device, characterized in that: include: a non-transitory computer-readable storage medium storing instructions; and at least one processor, When the processor executes the instructions, the at least one processor performs the following steps: analyzing information stored for each of a plurality of garments to extract main features related to the garment category, wherein each of the main features represents a dominant feature corresponding to the garment category; assigning the main features of the garments to groups, wherein the groups are respectively associated with representative features of the categories shared between the garments in each group; processing information about the garments based on the group to generate statistical information about the representative features; and The generated statistical information including the representative feature identifier is displayed.

10. An electronic device, characterized in that: include: at least one processor; and Memory for storing instructions, When the at least one processor executes the instructions, the electronic device performs the following steps: analyzing information stored for each of a plurality of garments to extract main features related to the garment category, wherein each of the main features represents a dominant feature corresponding to the garment category; assigning the main features of the garments to groups, wherein the groups are respectively associated with representative features of the categories shared between the garments in each group; processing information about the garments based on the group to generate statistical information about the representative features; and The generated statistical information including the representative feature identifier is displayed.