system

Abstract

We provide the system. [Solution] Means of acquiring image data and personal information, A means for identifying the user's fashion trends by analyzing the aforementioned image data and personal information, Based on the aforementioned fashion trends, a means of selecting suggested items that differ from the usual style, A means for generating outfit ideas by combining the aforementioned proposed items with an existing wardrobe, A means of presenting the aforementioned outfit suggestions to the user and enabling them to try them on, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many individuals have the problem that their fashion choices become fixed with age and they feel resistance to adopting new styles. As a result, the range of fashion becomes narrow and self-expression in daily life is restricted. In response to such a situation, there is a need for support to lower the psychological hurdle to adopting new fashion items and to realize a more diverse and enjoyable fashion life.

Means for Solving the Problems

[0005] This invention provides a system that acquires user image data and personal information, analyzes this data to identify the user's fashion tendencies. Furthermore, based on the identified fashion tendencies, this system selects suggested items that differ from the user's usual style, combines them with the user's existing wardrobe to generate and present coordinated outfit ideas. In addition, the user can virtually try on the suggested items using AR technology, providing a sense of security in trying out new styles. In this way, the user can discover new fashion possibilities and expand the diversity of self-expression.

[0006] "Image data" refers to digital data that represents visual information captured by a user photographing items in their wardrobe.

[0007] "Personal information" refers to information about a user's personal attributes, such as their fashion trends, preferences, and body type.

[0008] "Fashion trends" refer to information that describes style tendencies identified based on a user's past clothing choices and preferences.

[0009] "Suggested items" refer to fashion items that deviate slightly from the user's usual style but can serve as a new accent.

[0010] "Wardrobe" is a term that refers to a collection of clothing and accessories owned by a user.

[0011] "Outfit suggestions" refer to proposed clothing styles created by combining suggested items with an existing wardrobe.

[0012] "Trying on" refers to the act of visually checking a suggested item before actually wearing it, and in particular, when using AR technology, it is displayed digitally.

[0013] "AR technology" refers to technology that enhances visual experiences by overlaying virtual information onto the real world.

[0014] A "machine learning algorithm" is a type of computational method used to analyze data and learn specific patterns or trends. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiment for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is configured as a system that comprehensively supports a user's fashion style. This system begins by transmitting image data captured by the user's device and personal information entered by the user to a server.

[0037] The server analyzes the received image data to identify the color, shape, and style of the clothing owned by the user. This provides detailed data about the user's wardrobe. Next, the server identifies the user's fashion tendencies, taking into account information about their personal preferences and body type. At this stage, machine learning algorithms are used to predict the optimal fashion style based on the user's past selection patterns.

[0038] The next suggested item is selected that is slightly different from the user's usual style. This suggested item is designed to bring a new accent to the user's look. Based on the selected suggested item, the server generates several outfit ideas that combine it with the user's existing wardrobe.

[0039] The generated outfit suggestions are sent to the device and presented to the user. The user can virtually try on the suggested items using AR technology. This allows for visual confirmation before actually wearing the items, providing a sense of security when trying out new styles.

[0040] As a concrete example, consider a user who mostly wears monochrome clothing and generally avoids colorful items. This user takes photos of their wardrobe with the app and enters body type information and preferred colors into a questionnaire. The server analyzes this data and suggests a red bag as an accent color the user should try. It then generates several outfit ideas using the bag and combines them with the user's monochrome clothing. Through the app, the user can try on different looks with the red bag and experiment with new styles.

[0041] Thus, this system aims to help users confidently incorporate new fashion items into their lives and bring variety and enjoyment to their everyday style.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users take photos of items in their wardrobe with their own devices and input personal preferences and body type information through a fashion questionnaire. The device packages this information and sends it to the server using a secure communication protocol.

[0045] Step 2:

[0046] The server receives image data sent from the terminal and uses image recognition algorithms to analyze the color, shape, and style of the clothing. This allows the characteristics of the user's wardrobe to be compiled into data.

[0047] Step 3:

[0048] The server identifies the user's fashion tendencies based on survey data and image analysis results. This process utilizes machine learning algorithms to learn style patterns based on the user's past choices.

[0049] Step 4:

[0050] The server selects suggested items that deviate slightly from the usual style, based on identified fashion trends. The emphasis is on these suggestions adding a new accent to the user's style.

[0051] Step 5:

[0052] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. Multiple combinations are considered, and the best match is chosen.

[0053] Step 6:

[0054] The server sends the generated coordination proposal to the terminal. The terminal receives it and displays it visually to the user.

[0055] Step 7:

[0056] Users can virtually try on suggested fashion items on their devices using augmented reality (AR) technology. This feature allows them to see how an item will look before actually purchasing or using it.

[0057] Step 8:

[0058] If the user is satisfied with the suggested outfit, they can decide to purchase it based on the try-on results or to incorporate it into their actual wardrobe. This step facilitates the adoption of new styles.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Existing fashion systems often only display a user's style in a monotonous way, failing to effectively encourage individual preferences or the exploration of new styles. Furthermore, there is a lack of visual means for users to confirm the suitability of new fashion items before actually trying them on. As a result, many users feel anxious when adopting new styles.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for acquiring image information and user information, means for analyzing the image information and user information to identify an individual's clothing preferences, and means for selecting alternatives that differ from the individual's usual attire based on the individual's clothing preferences. This allows users to confidently try out new fashion items and experiment with new styles.

[0064] 1. "Image information" refers to data that shows the color and shape of clothing, obtained from the user's device.

[0065] 2. "User information" refers to data entered by the user, such as their personal body type and preferred colors.

[0066] 3. "Clothing preferences" refer to the user's fashion style and preferences identified based on the analyzed image information and user information.

[0067] 4. A "substitute" is a different fashion item chosen to add a new element to a user's usual style.

[0068] 5. "Collection of clothing owned" refers to the entirety of the clothing that the user already owns.

[0069] 6. "Decoration suggestions" refer to new coordination ideas, including alternative items, and represent fashion styles combined with the user's existing clothing.

[0070] 7. "Visual confirmation" is a feature that allows users to visually try out new alternatives without having to physically try them on.

[0071] 8. Augmented reality technology is a technology that uses cameras and displays to overlay virtual elements onto real-world images.

[0072] 9. A "machine learning algorithm" is a computational method that learns from data and predicts user preferences.

[0073] This invention is a system that provides multifaceted support for a user's fashion style. The system consists of a terminal, a server, and software that connects them. The user uses a dedicated application on the terminal to take pictures of clothing in their wardrobe and inputs personal information such as body type and preferred colors. The terminal then transmits this data to the server.

[0074] The server analyzes the received image data using a commonly used image analysis software platform (e.g., OpenCV). This identifies the color, shape, and style of clothing, and determines the individual's clothing preferences. The server also learns the user's fashion tendencies using a machine learning algorithm (e.g., TENSORFLOW®). This algorithm suggests new fashion items based on the user's past selection patterns.

[0075] The server selects alternative items that differ slightly from the user's usual style, and generates outfit suggestions based on these. The suggested outfits are presented to the user via their device, and the user can visually confirm the suggested items using augmented reality technology. A common AR platform (e.g., ARKit) is used for the augmented reality technology.

[0076] As a concrete example, a user who prefers monochrome clothing might be suggested a red bag as a new accent piece. This bag is then combined with their existing wardrobe and presented as a new outfit idea. The user can visually see the red bag through the application and try out the new style.

[0077] An example of a prompt to input into the generating AI model is, "Based on the user's fashion preferences, suggest new accent items and generate outfit ideas combining those items with the user's existing wardrobe." This system allows users to confidently incorporate new fashion items into their daily lives.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user launches the application and takes pictures of the clothes in their wardrobe using the device's camera. The image information serves as input. Specifically, the user uses the app's camera function to take pictures of the clothes from multiple angles and saves the image data to the device.

[0081] Step 2:

[0082] Users enter personal information such as body type and preferred colors into the app. This converts personal information into data. Specifically, users tap options on a dedicated form within the app and enter text.

[0083] Step 3:

[0084] The device transmits captured image information and entered personal information to the server. The input consists of image information and personal information, while the output is data transfer to the server. Specifically, the device combines this data and uploads it to the server via the internet.

[0085] Step 4:

[0086] The server uses image analysis software to analyze the received image information. The input is image information, and the output is the result of identifying color and shape. Specifically, the server performs color identification and shape extraction through pixel analysis and stores the characteristics of the clothing in a database.

[0087] Step 5:

[0088] The server analyzes the user's fashion preferences using machine learning algorithms. The input is the user's past preference data, and the output is a prediction of their fashion style. Specifically, the server inputs past data patterns into a neural network to obtain the results of the trend analysis.

[0089] Step 6:

[0090] The server selects alternatives that differ from the user's usual style based on the analysis results. The input is the predicted fashion style, and the output is the selection of suggested items. Specifically, the server uses a generative AI model to design prompt sentences and determine the suggested items.

[0091] Step 7:

[0092] The server combines suggested items with the user's existing wardrobe to generate styling suggestions. The input consists of data on suggested items and the user's wardrobe, while the output is the styling suggestions. Specifically, the server creates outfit patterns by combining suggested items with the user's own clothing and saves them in the database.

[0093] Step 8:

[0094] The device presents the generated decoration suggestions to the user. The input is the decoration suggestions, and the output is the presentation of visual information to the user. Specifically, the device displays the decoration suggestions on the app's UI, allowing the user to freely review them.

[0095] Step 9:

[0096] The user visually checks suggested items using augmented reality technology. The input is AR content, and the output is a visual try-on experience. Specifically, the user checks the suggested items virtually overlaid on the device's camera screen and compares them to their real-life self.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] In modern society, individual fashion styles are diverse, and the choices available are wide-ranging. However, when purchasing new fashion items in physical stores, users face the challenge of having to experiment to determine if they fit their existing wardrobe. There is also a need to provide a better purchasing experience while saving time and effort on trying on clothes. This invention aims to support users in confidently choosing new fashion items and solve the difficulties they face in selecting fashion styles within stores.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for acquiring image data and personal information; means for analyzing the image data and personal information to identify the user's fashion tendencies; means for selecting suggested items that differ from the usual style based on the fashion tendencies; means for generating styling ideas by combining the suggested items with existing clothing; means for presenting the styling ideas to the user and enabling trial fitting; and means for displaying the styling ideas through a visual device and performing fitting simulations when the user views products in the store. This allows the user to easily check whether new fashion items suit them in the store and to try out new styles.

[0102] "Image data" refers to still images or videos captured by a user's device, and is digital information used to analyze the color and shape of fashion items.

[0103] "Personal information" refers to data entered by users, such as body type, preferences, and past fashion choices, and is used to identify the user's fashion tendencies.

[0104] "Fashion trends" refer to the patterns and styles of fashion items that a user has selected in the past, and are taken into consideration when determining suggested items based on their individual style.

[0105] "Suggested items" are new fashion items selected by the system to add a different accent to the user's usual fashion style.

[0106] A "decoration suggestion" is a fashion coordination idea generated by combining suggested items with clothing that the user already owns.

[0107] "Trial fitting" refers to a process where a user virtually wears a newly proposed item using augmented reality technology and visually confirms its appearance.

[0108] "Visual devices" refer to devices such as smart glasses and head-mounted displays, which are hardware used by users to visually confirm design options.

[0109] "Wearing simulation" is a technology that uses augmented reality to simulate what a proposed item would look like when worn by a user, even though the user is not actually wearing it.

[0110] This invention aims to support a user's fashion style using a complexly configured system. First, the user's terminal uses visual devices such as a camera or smart glasses to acquire image data of the user's clothing and newly encountered items. In addition, the user inputs personal information such as their body type, fashion preferences, and past purchase history.

[0111] The server uses an image analysis algorithm (e.g., OpenCV) to analyze the acquired image data. During this process, the server identifies the color, shape, and style of clothing, forming the user's wardrobe data. Based on this information, a machine learning algorithm (e.g., TensorFlow) is used to identify the user's fashion tendencies. The machine learning algorithm learns the user's past selection patterns and determines suggested items to try next.

[0112] After the proposed items are selected, the server combines them with the user's existing clothing to generate styling options. The generated styling options are presented to the user through a visual device, and trial fitting is possible using augmented reality technology (e.g., ARCore). Through this simulation function, the user can try out new styles before actually wearing them.

[0113] As a concrete example, consider a scenario where a user finds a new jacket in a store. They can scan the jacket using a visual device to see how it would look with their usual outfits. This allows the user to purchase new fashion items with confidence.

[0114] By inputting prompts such as, "Combine the user's wardrobe data with images of jackets in the store to generate the best possible outfit suggestions," the AI ​​model can obtain optimal suggestions.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The device acquires the user's image data and personal information. The user uses smart glasses to take photos of their clothing and new items and inputs them into the device. They also input their body type, preferred colors, and past fashion selection history into the application. The input data is sent to the server as image data.

[0118] Step 2:

[0119] The server analyzes the acquired image data. Using image analysis algorithms such as OpenCV, it identifies the color, shape, and style of clothing from the transmitted image data. As a result of the analysis, the user's wardrobe data is output.

[0120] Step 3:

[0121] The server identifies the user's fashion tendencies. Using the acquired personal information and wardrobe data, a machine learning algorithm (TensorFlow) learns the user's past selection patterns and estimates their fashion tendencies. The output of this process is data about the user's fashion tendencies.

[0122] Step 4:

[0123] The server selects suggested items based on fashion trends. It chooses new items that differ from the user's usual style. Using a generative AI model, it issues a prompt message such as "Generate the best outfit suggestions." The selected suggested items are output.

[0124] Step 5:

[0125] The server generates outfit ideas by combining suggested items with existing clothing. Based on the user's wardrobe data and suggested items, multiple outfit ideas are created. The output of this step is the outfit idea data.

[0126] Step 6:

[0127] The decoration options are sent to the terminal and presented to the user. Using augmented reality technology (ARCore), the user can virtually try on the decoration options through their visual device. The user visually confirms the displayed fitting simulation. This step outputs the virtual fitting results, allowing the user to try on new fashion items.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] This invention is an advanced system that supports users' fashion styles and, by combining it with an emotion engine, provides fashion suggestions based on the user's emotional state. This system begins by collecting not only image data and personal information, but also emotional information through the user's terminal.

[0130] The user's device takes a picture of their wardrobe and sends personal data to the server. During this process, an emotion engine analyzes the user's voice tone and facial expressions to generate data about their current psychological state. This information is transmitted to the server via a secure protocol.

[0131] After receiving this data, the server analyzes the image data to understand the characteristics of the wardrobe, while also learning fashion trends from personal information. A machine learning algorithm derives the optimal style pattern based on the user's past choices. It also identifies the user's current emotions based on the results of the emotion engine. For example, if the user is feeling down, it can suggest colorful items to brighten their mood.

[0132] The server selects suggested items that differ from the user's usual style, based on both fashion trends and emotional information. Based on these selected items, it generates outfit ideas by combining them with the user's existing wardrobe and sends the results to the terminal.

[0133] Users can view outfit suggestions generated on their devices and virtually try them on using AR technology. This virtual try-on allows users to visually experience how fashion items will look before purchasing or going out, and in particular, to confirm that the selected outfits match their emotions and current mood.

[0134] As a concrete example, consider a situation where a user is feeling a bit tired because they haven't achieved the desired results at work. This system recognizes this emotion using an emotion engine, and the server suggests bright-colored accessories to encourage and energize the user. It then generates outfit suggestions based on these suggestions and encourages the user to try them on using augmented reality, thus offering a new style while also having a positive psychological impact.

[0135] In this way, this system aims not only to broaden the scope of self-expression through fashion, but also to provide suggestions tailored to the user's emotions and psychological state, thereby supporting a richer daily life.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] Users take photos of their wardrobe using their device's camera and input personal preferences and body type information through an in-app questionnaire. The device then activates an emotion engine to analyze the user's voice tone and facial expressions to obtain emotional data.

[0139] Step 2:

[0140] The device transmits acquired image data, personal information, and emotional data to the server. All of this data is encrypted and transferred to the server using a secure communication protocol.

[0141] Step 3:

[0142] The server analyzes the received image data to determine the color, style, and shape of the clothing. It also uses machine learning algorithms to evaluate personal information in order to determine the user's fashion preferences. Sentimental data is used to identify the user's current psychological state.

[0143] Step 4:

[0144] Based on identified fashion trends and current emotional information, the server selects suggested items that deviate slightly from the user's usual style. For example, if the user is feeling stressed, it will recommend items in a relaxing style.

[0145] Step 5:

[0146] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. These generated outfits also take emotional information into account, ensuring they are tailored to the user's psychological state.

[0147] Step 6:

[0148] The server sends the generated outfit suggestion data to the device. The device then displays the received outfit suggestion to the user within the app.

[0149] Step 7:

[0150] Users can use their devices to visualize suggested outfits using AR technology and virtually try them on. This allows users to confidently try out new styles.

[0151] Step 8:

[0152] If a user likes the suggested items or outfits, they can review the results of the virtual try-on and then use that information to influence their actual purchase or actions. This allows users to enjoy choosing fashion that aligns with their mood and feelings.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] Fashion choices depend on numerous factors, with the user's emotional state being particularly influential. However, conventional fashion suggestion systems often fail to consider the user's emotional state, resulting in suggestions that don't match the user's actual needs. Furthermore, it's difficult to see how suggested items actually look, which can cause users to feel uneasy about the suggestions. To address these challenges, personalized fashion suggestions that take into account each user's individual emotions and fashion preferences are necessary.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes means for acquiring image data, personal information, and emotional data; means for analyzing the image data, personal information, and emotional data to identify the user's fashion tendencies and emotional state; and means for selecting suggested items that differ from the usual style based on the fashion tendencies and emotional state. This enables the server to make optimal fashion suggestions according to the user's emotions and allows the user to confirm how the suggested items actually look through virtual try-on.

[0158] "Image data" refers to information that visually represents the characteristics of a user's wardrobe and clothing.

[0159] "Personal information" refers to data relating to a specific individual, such as a user's fashion preferences or usage history.

[0160] "Emotional data" refers to information that indicates a user's psychological state, derived from their tone of voice and facial expressions.

[0161] "Fashion trends" refer to style tendencies derived from a user's past fashion choices and preferences.

[0162] A "suggested item" is a piece of clothing or accessory selected to offer a new combination that differs from the user's usual style.

[0163] A "coordinate suggestion" is a fashion proposal for the user, formed by combining suggested items with existing clothing.

[0164] "Virtual try-on" is a method that uses augmented reality technology to allow users to have a visual experience of actually wearing suggested fashion items.

[0165] Augmented reality technology is a technique that uses computer graphics and image analysis to overlay digital information onto the real world's field of view.

[0166] "Machine learning techniques" are computational techniques and algorithms used to learn patterns and knowledge from data and perform predictions and classifications.

[0167] This invention provides an advanced information processing system that assists users in selecting fashion styles and offers fashion suggestions that take their emotional state into consideration. This system is implemented using the user's terminal, a server, an emotion engine, and machine learning techniques.

[0168] First, the user takes pictures of their wardrobe using the device and inputs personal data. Furthermore, the emotion engine analyzes the user's voice tone and facial expressions to generate current emotion data. This emotion analysis can utilize software such as a Python library. The device then transmits this image data, personal information, and emotion data to the server via a secure protocol.

[0169] Next, the server analyzes the received data. OpenCV and TensorFlow are used to analyze image data and understand the characteristics of the clothing. Machine learning techniques (such as Scikit-learn and PyTorch) are utilized to learn fashion trends based on personal information. Furthermore, the server identifies the user's current psychological state based on emotional data. For example, if the server identifies the user as "depressed," it selects items to cheer them up.

[0170] The selected items are combined with the user's existing wardrobe to generate new outfit ideas. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits."

[0171] Users then review the suggested outfits on their devices and virtually try them on using augmented reality technology (such as ARKit or ARCore). This virtual try-on allows users to check the visual impression of fashion items before purchasing or going out, enabling them to make the best choices.

[0172] As described above, the system aims to enrich users' daily lives and broaden the scope of self-expression through fashion by taking into account the user's emotional state and providing personalized fashion suggestions.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The user takes a picture of their wardrobe and inputs relevant personal data (such as preferences and sizes) into the device. This data is temporarily stored by the device. Next, the emotion engine collects voice tone and facial expressions to generate the user's emotion data. The inputs for this step are the wardrobe image, personal data, voice tone, and facial expressions, and the output is the generation of emotion data based on this.

[0176] Step 2:

[0177] The terminal sends the collected image data, personal data, and generated sentiment data to the server in a single batch via a secure protocol. The input to this step is all the data generated in the previous step, and the output is the transmission to the server.

[0178] Step 3:

[0179] The server analyzes the received image data using OpenCV to extract the characteristics of the clothing in the image. This process yields feature data such as the color, shape, and pattern of the clothing. Next, machine learning methods (Scikit-learn or PyTorch) are applied using personal data to identify the user's fashion tendencies. The input for this step is image data and personal data, and based on this, feature data and fashion tendencies are output.

[0180] Step 4:

[0181] The server analyzes emotional data to identify the user's psychological state (for example, recommending cheerful items if the user is feeling down). Based on this emotional information, it links it to fashion trends to select the most suitable suggested items. The inputs for this step are emotional data and fashion trends, and the selected suggested items are output.

[0182] Step 5:

[0183] The server generates new outfit ideas by combining selected suggested items with the existing wardrobe. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits." The input for this step is the suggested items and the existing wardrobe, and the output is outfit ideas.

[0184] Step 6:

[0185] The server sends the generated coordination proposal to the user's terminal, allowing the user to visually confirm the result. The input for this step is the coordination proposal, and the output is its presentation to the terminal.

[0186] Step 7:

[0187] The user reviews the outfit suggestions received on their device and then virtually tries them on using augmented reality technology. This virtual try-on allows them to experience how the fashion items actually look. The input for this step is the outfit suggestion, and the output is the virtual try-on result.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] In today's busy lifestyle, users often find it difficult to choose appropriate clothing that reflects their emotional state. Fashion choices, in particular, are directly linked to mood and psychological state, and without dedicated guidance, appropriate choices can be difficult. Furthermore, traditional systems struggle to provide personalized outfit suggestions that reflect a user's actual emotions in real time. There is a need to solve these problems and help users easily find fashion that suits them.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes means for acquiring image information, personal attributes, and emotional states obtained from voice tone and facial expressions; means for analyzing the image information, personal attributes, and emotional states to identify the user's clothing preferences; and means for selecting suggested items that differ from the usual style based on the clothing preferences and emotional states. This allows the user to receive personalized fashion suggestions that match their emotional state at the time, try them on using augmented reality technology, and make selections while visually confirming them.

[0193] "Image information" refers to information that includes visual data, and is used to obtain information such as a user's appearance and the condition of their clothing.

[0194] "Personal attributes" refer to information unique to a user, including personal preferences, past selection history, and basic profile information.

[0195] "Emotional state" refers to the user's psychological and emotional state, and is obtained from biometric information such as voice tone and facial expressions.

[0196] "Clothing trends" refer to the characteristics of fashion patterns and styles that a user has chosen in the past.

[0197] "Suggested items" refer to new fashion items or styles selected by the system based on the user's emotional state and clothing preferences.

[0198] Augmented reality technology is a technology that overlays virtual information onto the real world, enabling users to virtually try on clothes.

[0199] The system implementing this invention utilizes a user's terminal, a server, and a smart device. The user's terminal acquires image information, personal attributes, and emotional state. This includes the user wearing a smart device, which allows the built-in camera and microphone to sense the user's facial expressions and voice tone. The server receives and processes this information to generate optimized fashion suggestions based on the user's clothing preferences and emotional state. The server analyzes the image information and emotional state and uses machine learning algorithms to identify the user's preferences. The generated suggested items are sent to the user's terminal to provide new options that deviate from the user's usual style and can be virtually tried on using augmented reality technology. Specifically, virtual try-on videos of the selected fashion items are displayed on the screen of smart glasses or a mobile device. This allows the user to visually experience new styles while making appropriate choices according to their emotional state.

[0200] As a concrete example, when a user chooses an outfit for a specific event, they receive personalized suggestions that reflect their emotional state at the time. For instance, if a user wears smart glasses before attending a party on the weekend to analyze their emotional state, the server will suggest items that are both relaxing and stylish. The user can visually review the suggested outfits and select them on the spot.

[0201] Example prompts for generative AI models:

[0202] "Using a fashion suggestion system based on the user's emotional state, please create a story about how a user wearing smart glasses would choose an outfit that matches their emotions. How can users use this system in their daily lives to create a unique style?"

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The user's device uses a smart device to collect image information, personal attributes, and voice tone and facial expressions. Input consists of image data from the device's camera and audio data from the microphone; output is a digital file integrating these. This data is used as foundational information for analyzing the user's current emotional state and preferences. Specific actions include capturing facial expressions with the camera and recording conversational audio with the microphone.

[0206] Step 2:

[0207] The server receives image and audio data transmitted from the user's terminal and analyzes the user's emotional state using an emotion engine. The input is a digital file from the terminal, and the output is an evaluation value of the analyzed emotional state and a specific emotion label. In this process, emotions such as joy, anger, and sadness are identified using facial recognition and voice analysis algorithms.

[0208] Step 3:

[0209] The server uses machine learning algorithms to learn the user's past clothing preferences and generate fashion suggestions based on their emotional state. The input is analyzed emotional state data and past fashion preference history, and the output is a list of suggested fashion items. The server predicts the user's preferred colors, styles, and seasonal choices, and provides individually customized suggestions.

[0210] Step 4:

[0211] The server sends generated fashion suggestions to the user's device, providing an environment where the user can virtually try on the clothes via augmented reality technology. The input is a list of suggested items, and the output is a virtual outfit screen displayed on the device. The user can use augmented reality technology to virtually try on the items on their own avatar and check how they look.

[0212] Step 5:

[0213] Based on the results of the virtual try-on, users can select their favorite fashion items and, if they wish to purchase additional items, proceed with the purchase within the system. The input is the user's selection data, and the output is a confirmation message sent to the user after the purchase is completed. Specific actions include the transaction via electronic payment and the preparation for shipping the purchased items.

[0214] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] This invention is configured as a system that comprehensively supports a user's fashion style. This system begins by transmitting image data captured by the user's device and personal information entered by the user to a server.

[0231] The server analyzes the received image data to identify the color, shape, and style of the clothing owned by the user. This provides detailed data about the user's wardrobe. Next, the server identifies the user's fashion tendencies, taking into account information about their personal preferences and body type. At this stage, machine learning algorithms are used to predict the optimal fashion style based on the user's past selection patterns.

[0232] The next suggested item is selected that is slightly different from the user's usual style. This suggested item is designed to bring a new accent to the user's look. Based on the selected suggested item, the server generates several outfit ideas that combine it with the user's existing wardrobe.

[0233] The generated outfit suggestions are sent to the device and presented to the user. The user can virtually try on the suggested items using AR technology. This allows for visual confirmation before actually wearing the items, providing a sense of security when trying out new styles.

[0234] As a concrete example, consider a user who mostly wears monochrome clothing and generally avoids colorful items. This user takes photos of their wardrobe with the app and enters body type information and preferred colors into a questionnaire. The server analyzes this data and suggests a red bag as an accent color the user should try. It then generates several outfit ideas using the bag and combines them with the user's monochrome clothing. Through the app, the user can try on different looks with the red bag and experiment with new styles.

[0235] Thus, this system aims to help users confidently incorporate new fashion items into their lives and bring variety and enjoyment to their everyday style.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] Users take photos of items in their wardrobe with their own devices and input personal preferences and body type information through a fashion questionnaire. The device packages this information and sends it to the server using a secure communication protocol.

[0239] Step 2:

[0240] The server receives image data sent from the terminal and uses image recognition algorithms to analyze the color, shape, and style of the clothing. This allows the characteristics of the user's wardrobe to be compiled into data.

[0241] Step 3:

[0242] The server identifies the user's fashion tendencies based on survey data and image analysis results. This process utilizes machine learning algorithms to learn style patterns based on the user's past choices.

[0243] Step 4:

[0244] The server selects suggested items that deviate slightly from the usual style, based on identified fashion trends. The emphasis is on these suggestions adding a new accent to the user's style.

[0245] Step 5:

[0246] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. Multiple combinations are considered, and the best match is chosen.

[0247] Step 6:

[0248] The server sends the generated coordination proposal to the terminal. The terminal receives it and displays it visually to the user.

[0249] Step 7:

[0250] Users can virtually try on suggested fashion items on their devices using augmented reality (AR) technology. This feature allows them to see how an item will look before actually purchasing or using it.

[0251] Step 8:

[0252] If the user is satisfied with the suggested outfit, they can decide to purchase it based on the try-on results or to incorporate it into their actual wardrobe. This step facilitates the adoption of new styles.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] Existing fashion systems often only display a user's style in a monotonous way, failing to effectively encourage individual preferences or the exploration of new styles. Furthermore, there is a lack of visual means for users to confirm the suitability of new fashion items before actually trying them on. As a result, many users feel anxious when adopting new styles.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for acquiring image information and user information, means for analyzing the image information and user information to identify an individual's clothing preferences, and means for selecting alternatives that differ from the individual's usual attire based on the individual's clothing preferences. This allows users to confidently try out new fashion items and experiment with new styles.

[0258] 1. "Image information" refers to data that shows the color and shape of clothing, obtained from the user's device.

[0259] 2. "User information" refers to data entered by the user, such as their personal body type and preferred colors.

[0260] 3. "Clothing preferences" refer to the user's fashion style and preferences identified based on the analyzed image information and user information.

[0261] 4. A "substitute" is a different fashion item chosen to add a new element to a user's usual style.

[0262] 5. "Collection of clothing owned" refers to the entirety of the clothing that the user already owns.

[0263] 6. "Decoration suggestions" refer to new coordination ideas, including alternative items, and represent fashion styles combined with the user's existing clothing.

[0264] 7. "Visual confirmation" is a feature that allows users to visually try out new alternatives without having to physically try them on.

[0265] 8. Augmented reality technology is a technology that uses cameras and displays to overlay virtual elements onto real-world images.

[0266] 9. A "machine learning algorithm" is a computational method that learns from data and predicts user preferences.

[0267] This invention is a system that provides multifaceted support for a user's fashion style. The system consists of a terminal, a server, and software that connects them. The user uses a dedicated application on the terminal to take pictures of clothing in their wardrobe and inputs personal information such as body type and preferred colors. The terminal then transmits this data to the server.

[0268] The server analyzes received image data using a commonly used image analysis software platform (e.g., OpenCV). This identifies the color, shape, and style of clothing, and determines the individual's clothing preferences. The server also learns the user's fashion tendencies using a machine learning algorithm (e.g., TensorFlow). This algorithm suggests new fashion items based on the user's past selection patterns.

[0269] The server selects alternative items that differ slightly from the user's usual style, and generates outfit suggestions based on these. The suggested outfits are presented to the user via their device, and the user can visually confirm the suggested items using augmented reality technology. A common AR platform (e.g., ARKit) is used for the augmented reality technology.

[0270] As a concrete example, a user who prefers monochrome clothing might be suggested a red bag as a new accent piece. This bag is then combined with their existing wardrobe and presented as a new outfit idea. The user can visually see the red bag through the application and try out the new style.

[0271] An example of a prompt to input into the generating AI model is, "Based on the user's fashion preferences, suggest new accent items and generate outfit ideas combining those items with the user's existing wardrobe." This system allows users to confidently incorporate new fashion items into their daily lives.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The user launches the application and takes pictures of the clothes in their wardrobe using the device's camera. The image information serves as input. Specifically, the user uses the app's camera function to take pictures of the clothes from multiple angles and saves the image data to the device.

[0275] Step 2:

[0276] Users enter personal information such as body type and preferred colors into the app. This converts personal information into data. Specifically, users tap options on a dedicated form within the app and enter text.

[0277] Step 3:

[0278] The device transmits captured image information and entered personal information to the server. The input consists of image information and personal information, while the output is data transfer to the server. Specifically, the device combines this data and uploads it to the server via the internet.

[0279] Step 4:

[0280] The server uses image analysis software to analyze the received image information. The input is image information, and the output is the result of identifying color and shape. Specifically, the server performs color identification and shape extraction through pixel analysis and stores the characteristics of the clothing in a database.

[0281] Step 5:

[0282] The server analyzes the user's fashion preferences using machine learning algorithms. The input is the user's past preference data, and the output is a prediction of their fashion style. Specifically, the server inputs past data patterns into a neural network to obtain the results of the trend analysis.

[0283] Step 6:

[0284] The server selects alternatives that are different from the user's normal style based on the analysis results. The input is the prediction result of the fashion style, and the output is the selection of the proposed items. As a specific operation, the server designs a prompt sentence using a generative AI model and determines the proposed items.

[0285] Step 7:

[0286] The server combines the proposed items with the existing wardrobe and generates a decoration proposal. The input is the data of the proposed items and the wardrobe, and the output is the decoration proposal. As a specific operation, the server creates a coordination pattern by combining the proposed items with the user's owned clothes and saves it in the database.

[0287] Step 8:

[0288] The terminal presents the generated decoration proposal to the user. The input is the decoration proposal, and the output is the visual information presentation to the user. As a specific operation, the terminal displays the decoration plan on the UI of the app so that the user can freely check it.

[0289] Step 9:

[0290] The user visually checks the proposed items using augmented reality technology. The input is the AR content, and the output is the visual try-on experience. As a specific operation, the user checks the proposed items virtually superimposed on the camera screen of the terminal and compares them with the real self.

[0291] (Application Example 1)

[0292] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0293] In modern society, individual fashion styles are diverse, and the choices available are wide-ranging. However, when purchasing new fashion items in physical stores, users face the challenge of having to experiment to determine if they fit their existing wardrobe. There is also a need to provide a better purchasing experience while saving time and effort on trying on clothes. This invention aims to support users in confidently choosing new fashion items and solve the difficulties they face in selecting fashion styles within stores.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for acquiring image data and personal information; means for analyzing the image data and personal information to identify the user's fashion tendencies; means for selecting suggested items that differ from the usual style based on the fashion tendencies; means for generating styling ideas by combining the suggested items with existing clothing; means for presenting the styling ideas to the user and enabling trial fitting; and means for displaying the styling ideas through a visual device and performing fitting simulations when the user views products in the store. This allows the user to easily check whether new fashion items suit them in the store and to try out new styles.

[0296] "Image data" refers to still images or videos captured by a user's device, and is digital information used to analyze the color and shape of fashion items.

[0297] "Personal information" refers to data entered by users, such as body type, preferences, and past fashion choices, and is used to identify the user's fashion tendencies.

[0298] "Fashion trends" refer to the patterns and styles of fashion items that a user has selected in the past, and are taken into consideration when determining suggested items based on their individual style.

[0299] "Suggested items" are new fashion items selected by the system to add a different accent to the user's usual fashion style.

[0300] A "decoration suggestion" is a fashion coordination idea generated by combining suggested items with clothing that the user already owns.

[0301] "Trial fitting" refers to a process where a user virtually wears a newly proposed item using augmented reality technology and visually confirms its appearance.

[0302] "Visual devices" refer to devices such as smart glasses and head-mounted displays, which are hardware used by users to visually confirm design options.

[0303] "Wearing simulation" is a technology that uses augmented reality to simulate what a proposed item would look like when worn by a user, even though the user is not actually wearing it.

[0304] This invention aims to support a user's fashion style using a complexly configured system. First, the user's terminal uses visual devices such as a camera or smart glasses to acquire image data of the user's clothing and newly encountered items. In addition, the user inputs personal information such as their body type, fashion preferences, and past purchase history.

[0305] The server uses an image analysis algorithm (e.g., OpenCV) to analyze the acquired image data. At that time, the color, shape, style, etc. of the clothes are identified by image analysis, and the user's wardrobe data is formed. Based on this information, a machine learning algorithm (e.g., TensorFlow) is used to identify the user's fashion trends. The machine learning algorithm learns the user's past selection patterns and then determines the proposed items to try next.

[0306] After the proposed item is selected, the server combines it with the user's existing clothing to generate a styling plan. The generated styling plan is presented to the user through a visual device, enabling a trial fitting using augmented reality technology (e.g., ARCore). Through this simulation function, the user can try out new styles before actually wearing them.

[0307] As a specific example, consider the case where a user finds a new jacket in a store. It is possible to scan the jacket through a visual device and check how it looks when combined with regular clothing. This enables the user to purchase new fashion items with confidence.

[0308] By inputting a prompt sentence such as "Please combine the wardrobe data owned by the user and the image of the jacket in the store to generate an optimal coordination proposal" into the generative AI model, an optimal proposal can be obtained.

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The terminal acquires the user's image data and personal information. The user takes photos of clothing and new items using smart glasses and inputs them into the terminal. Also, the user inputs their body type, favorite color, and past fashion selection history into the application. The input data is transmitted to the server as image data.

[0312] Step 2:

[0313] The server analyzes the acquired image data. Using image analysis algorithms such as OpenCV, it identifies the color, shape, and style of clothing from the transmitted image data. As a result of the analysis, the user's wardrobe data is output.

[0314] Step 3:

[0315] The server identifies the user's fashion tendencies. Using the acquired personal information and wardrobe data, a machine learning algorithm (TensorFlow) learns the user's past selection patterns and estimates their fashion tendencies. The output of this process is data about the user's fashion tendencies.

[0316] Step 4:

[0317] The server selects suggested items based on fashion trends. It chooses new items that differ from the user's usual style. Using a generative AI model, it issues a prompt message such as "Generate the best outfit suggestions." The selected suggested items are output.

[0318] Step 5:

[0319] The server generates outfit ideas by combining suggested items with existing clothing. Based on the user's wardrobe data and suggested items, multiple outfit ideas are created. The output of this step is the outfit idea data.

[0320] Step 6:

[0321] The decoration options are sent to the terminal and presented to the user. Using augmented reality technology (ARCore), the user can virtually try on the decoration options through their visual device. The user visually confirms the displayed fitting simulation. This step outputs the virtual fitting results, allowing the user to try on new fashion items.

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] This invention is an advanced system that supports users' fashion styles and, by combining it with an emotion engine, provides fashion suggestions based on the user's emotional state. This system begins by collecting not only image data and personal information, but also emotional information through the user's terminal.

[0324] The user's device takes a picture of their wardrobe and sends personal data to the server. During this process, an emotion engine analyzes the user's voice tone and facial expressions to generate data about their current psychological state. This information is transmitted to the server via a secure protocol.

[0325] After receiving this data, the server analyzes the image data to understand the characteristics of the wardrobe, while also learning fashion trends from personal information. A machine learning algorithm derives the optimal style pattern based on the user's past choices. It also identifies the user's current emotions based on the results of the emotion engine. For example, if the user is feeling down, it can suggest colorful items to brighten their mood.

[0326] The server selects suggested items that differ from the user's usual style, based on both fashion trends and emotional information. Based on these selected items, it generates outfit ideas by combining them with the user's existing wardrobe and sends the results to the terminal.

[0327] Users can view outfit suggestions generated on their devices and virtually try them on using AR technology. This virtual try-on allows users to visually experience how fashion items will look before purchasing or going out, and in particular, to confirm that the selected outfits match their emotions and current mood.

[0328] As a concrete example, consider a situation where a user is feeling a bit tired because they haven't achieved the desired results at work. This system recognizes this emotion using an emotion engine, and the server suggests bright-colored accessories to encourage and energize the user. It then generates outfit suggestions based on these suggestions and encourages the user to try them on using augmented reality, thus offering a new style while also having a positive psychological impact.

[0329] In this way, this system aims not only to broaden the scope of self-expression through fashion, but also to provide suggestions tailored to the user's emotions and psychological state, thereby supporting a richer daily life.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] Users take photos of their wardrobe using their device's camera and input personal preferences and body type information through an in-app questionnaire. The device then activates an emotion engine to analyze the user's voice tone and facial expressions to obtain emotional data.

[0333] Step 2:

[0334] The device transmits acquired image data, personal information, and emotional data to the server. All of this data is encrypted and transferred to the server using a secure communication protocol.

[0335] Step 3:

[0336] The server analyzes the received image data to determine the color, style, and shape of the clothing. It also uses machine learning algorithms to evaluate personal information in order to determine the user's fashion preferences. Sentimental data is used to identify the user's current psychological state.

[0337] Step 4:

[0338] Based on identified fashion trends and current emotional information, the server selects suggested items that deviate slightly from the user's usual style. For example, if the user is feeling stressed, it will recommend items in a relaxing style.

[0339] Step 5:

[0340] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. These generated outfits also take emotional information into account, ensuring they are tailored to the user's psychological state.

[0341] Step 6:

[0342] The server sends the generated outfit suggestion data to the device. The device then displays the received outfit suggestion to the user within the app.

[0343] Step 7:

[0344] Users can use their devices to visualize suggested outfits using AR technology and virtually try them on. This allows users to confidently try out new styles.

[0345] Step 8:

[0346] If a user likes the suggested items or outfits, they can review the results of the virtual try-on and then use that information to influence their actual purchase or actions. This allows users to enjoy choosing fashion that aligns with their mood and feelings.

[0347] (Example 2)

[0348] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0349] Fashion choices depend on numerous factors, with the user's emotional state being particularly influential. However, conventional fashion suggestion systems often fail to consider the user's emotional state, resulting in suggestions that don't match the user's actual needs. Furthermore, it's difficult to see how suggested items actually look, which can cause users to feel uneasy about the suggestions. To address these challenges, personalized fashion suggestions that take into account each user's individual emotions and fashion preferences are necessary.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for acquiring image data, personal information, and emotional data; means for analyzing the image data, personal information, and emotional data to identify the user's fashion tendencies and emotional state; and means for selecting suggested items that differ from the usual style based on the fashion tendencies and emotional state. This enables the server to make optimal fashion suggestions according to the user's emotions and allows the user to confirm how the suggested items actually look through virtual try-on.

[0352] "Image data" refers to information that visually represents the characteristics of a user's wardrobe and clothing.

[0353] "Personal information" refers to data relating to a specific individual, such as a user's fashion preferences or usage history.

[0354] "Emotional data" refers to information that indicates a user's psychological state, derived from their tone of voice and facial expressions.

[0355] "Fashion trends" refer to style tendencies derived from a user's past fashion choices and preferences.

[0356] A "suggested item" is a piece of clothing or accessory selected to offer a new combination that differs from the user's usual style.

[0357] A "coordinate suggestion" is a fashion proposal for the user, formed by combining suggested items with existing clothing.

[0358] "Virtual try-on" is a method that uses augmented reality technology to allow users to have a visual experience of actually wearing suggested fashion items.

[0359] Augmented reality technology is a technique that uses computer graphics and image analysis to overlay digital information onto the real world's field of view.

[0360] "Machine learning techniques" are computational techniques and algorithms used to learn patterns and knowledge from data and perform predictions and classifications.

[0361] This invention provides an advanced information processing system that assists users in selecting fashion styles and offers fashion suggestions that take their emotional state into consideration. This system is implemented using the user's terminal, a server, an emotion engine, and machine learning techniques.

[0362] First, the user takes pictures of their wardrobe using the device and inputs personal data. Furthermore, the emotion engine analyzes the user's voice tone and facial expressions to generate current emotion data. This emotion analysis can utilize software such as a Python library. The device then transmits this image data, personal information, and emotion data to the server via a secure protocol.

[0363] Next, the server analyzes the received data. OpenCV and TensorFlow are used to analyze image data and understand the characteristics of the clothing. Machine learning techniques (such as Scikit-learn and PyTorch) are utilized to learn fashion trends based on personal information. Furthermore, the server identifies the user's current psychological state based on emotional data. For example, if the server identifies the user as "depressed," it selects items to cheer them up.

[0364] The selected items are combined with the user's existing wardrobe to generate new outfit ideas. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits."

[0365] Users then review the suggested outfits on their devices and virtually try them on using augmented reality technology (such as ARKit or ARCore). This virtual try-on allows users to check the visual impression of fashion items before purchasing or going out, enabling them to make the best choices.

[0366] As described above, the system aims to enrich users' daily lives and broaden the scope of self-expression through fashion by taking into account the user's emotional state and providing personalized fashion suggestions.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The user takes a picture of their wardrobe and inputs relevant personal data (such as preferences and sizes) into the device. This data is temporarily stored by the device. Next, the emotion engine collects voice tone and facial expressions to generate the user's emotion data. The inputs for this step are the wardrobe image, personal data, voice tone, and facial expressions, and the output is the generation of emotion data based on this.

[0370] Step 2:

[0371] The terminal sends the collected image data, personal data, and generated sentiment data to the server in a single batch via a secure protocol. The input to this step is all the data generated in the previous step, and the output is the transmission to the server.

[0372] Step 3:

[0373] The server analyzes the received image data using OpenCV to extract the characteristics of the clothing in the image. This process yields feature data such as the color, shape, and pattern of the clothing. Next, machine learning methods (Scikit-learn or PyTorch) are applied using personal data to identify the user's fashion tendencies. The input for this step is image data and personal data, and based on this, feature data and fashion tendencies are output.

[0374] Step 4:

[0375] The server analyzes emotional data to identify the user's psychological state (for example, recommending cheerful items if the user is feeling down). Based on this emotional information, it links it to fashion trends to select the most suitable suggested items. The inputs for this step are emotional data and fashion trends, and the selected suggested items are output.

[0376] Step 5:

[0377] The server generates new outfit ideas by combining selected suggested items with the existing wardrobe. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits." The input for this step is the suggested items and the existing wardrobe, and the output is outfit ideas.

[0378] Step 6:

[0379] The server sends the generated coordination proposal to the user's terminal, allowing the user to visually confirm the result. The input for this step is the coordination proposal, and the output is its presentation to the terminal.

[0380] Step 7:

[0381] The user reviews the outfit suggestions received on their device and then virtually tries them on using augmented reality technology. This virtual try-on allows them to experience how the fashion items actually look. The input for this step is the outfit suggestion, and the output is the virtual try-on result.

[0382] (Application Example 2)

[0383] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0384] In today's busy lifestyle, users often find it difficult to choose appropriate clothing that reflects their emotional state. Fashion choices, in particular, are directly linked to mood and psychological state, and without dedicated guidance, appropriate choices can be difficult. Furthermore, traditional systems struggle to provide personalized outfit suggestions that reflect a user's actual emotions in real time. There is a need to solve these problems and help users easily find fashion that suits them.

[0385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0386] In this invention, the server includes means for acquiring image information, personal attributes, and emotional states obtained from voice tone and facial expressions; means for analyzing the image information, personal attributes, and emotional states to identify the user's clothing preferences; and means for selecting suggested items that differ from the usual style based on the clothing preferences and emotional states. This allows the user to receive personalized fashion suggestions that match their emotional state at the time, try them on using augmented reality technology, and make selections while visually confirming them.

[0387] "Image information" refers to information that includes visual data, and is used to obtain information such as a user's appearance and the condition of their clothing.

[0388] "Personal attributes" refer to information unique to a user, including personal preferences, past selection history, and basic profile information.

[0389] "Emotional state" refers to the user's psychological and emotional state, and is obtained from biometric information such as voice tone and facial expressions.

[0390] "Clothing trends" refer to the characteristics of fashion patterns and styles that a user has chosen in the past.

[0391] "Suggested items" refer to new fashion items or styles selected by the system based on the user's emotional state and clothing preferences.

[0392] Augmented reality technology is a technology that overlays virtual information onto the real world, enabling users to virtually try on clothes.

[0393] The system implementing this invention utilizes a user's terminal, a server, and a smart device. The user's terminal acquires image information, personal attributes, and emotional state. This includes the user wearing a smart device, which allows the built-in camera and microphone to sense the user's facial expressions and voice tone. The server receives and processes this information to generate optimized fashion suggestions based on the user's clothing preferences and emotional state. The server analyzes the image information and emotional state and uses machine learning algorithms to identify the user's preferences. The generated suggested items are sent to the user's terminal to provide new options that deviate from the user's usual style and can be virtually tried on using augmented reality technology. Specifically, virtual try-on videos of the selected fashion items are displayed on the screen of smart glasses or a mobile device. This allows the user to visually experience new styles while making appropriate choices according to their emotional state.

[0394] As a concrete example, when a user chooses an outfit for a specific event, they receive personalized suggestions that reflect their emotional state at the time. For instance, if a user wears smart glasses before attending a party on the weekend to analyze their emotional state, the server will suggest items that are both relaxing and stylish. The user can visually review the suggested outfits and select them on the spot.

[0395] Example prompts for generative AI models:

[0396] "Using a fashion suggestion system based on the user's emotional state, please create a story about how a user wearing smart glasses would choose an outfit that matches their emotions. How can users use this system in their daily lives to create a unique style?"

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The user's device uses a smart device to collect image information, personal attributes, and voice tone and facial expressions. Input consists of image data from the device's camera and audio data from the microphone; output is a digital file integrating these. This data is used as foundational information for analyzing the user's current emotional state and preferences. Specific actions include capturing facial expressions with the camera and recording conversational audio with the microphone.

[0400] Step 2:

[0401] The server receives image and audio data transmitted from the user's terminal and analyzes the user's emotional state using an emotion engine. The input is a digital file from the terminal, and the output is an evaluation value of the analyzed emotional state and a specific emotion label. In this process, emotions such as joy, anger, and sadness are identified using facial recognition and voice analysis algorithms.

[0402] Step 3:

[0403] The server uses machine learning algorithms to learn the user's past clothing preferences and generate fashion suggestions based on their emotional state. The input is analyzed emotional state data and past fashion preference history, and the output is a list of suggested fashion items. The server predicts the user's preferred colors, styles, and seasonal choices, and provides individually customized suggestions.

[0404] Step 4:

[0405] The server sends generated fashion suggestions to the user's device, providing an environment where the user can virtually try on the clothes via augmented reality technology. The input is a list of suggested items, and the output is a virtual outfit screen displayed on the device. The user can use augmented reality technology to virtually try on the items on their own avatar and check how they look.

[0406] Step 5:

[0407] Based on the results of the virtual try-on, users can select their favorite fashion items and, if they wish to purchase additional items, proceed with the purchase within the system. The input is the user's selection data, and the output is a confirmation message sent to the user after the purchase is completed. Specific actions include the transaction via electronic payment and the preparation for shipping the purchased items.

[0408] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0409] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0410] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0411] [Third Embodiment]

[0412] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0413] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0414] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0415] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0416] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0417] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0418] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0419] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0420] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0421] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0422] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0423] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0424] This invention is configured as a system that comprehensively supports a user's fashion style. This system begins by transmitting image data captured by the user's device and personal information entered by the user to a server.

[0425] The server analyzes the received image data to identify the color, shape, and style of the clothing owned by the user. This provides detailed data about the user's wardrobe. Next, the server identifies the user's fashion tendencies, taking into account information about their personal preferences and body type. At this stage, machine learning algorithms are used to predict the optimal fashion style based on the user's past selection patterns.

[0426] The next suggested item is selected that is slightly different from the user's usual style. This suggested item is designed to bring a new accent to the user's look. Based on the selected suggested item, the server generates several outfit ideas that combine it with the user's existing wardrobe.

[0427] The generated outfit suggestions are sent to the device and presented to the user. The user can virtually try on the suggested items using AR technology. This allows for visual confirmation before actually wearing the items, providing a sense of security when trying out new styles.

[0428] As a concrete example, consider a user who mostly wears monochrome clothing and generally avoids colorful items. This user takes photos of their wardrobe with the app and enters body type information and preferred colors into a questionnaire. The server analyzes this data and suggests a red bag as an accent color the user should try. It then generates several outfit ideas using the bag and combines them with the user's monochrome clothing. Through the app, the user can try on different looks with the red bag and experiment with new styles.

[0429] Thus, this system aims to help users confidently incorporate new fashion items into their lives and bring variety and enjoyment to their everyday style.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] Users take photos of items in their wardrobe with their own devices and input personal preferences and body type information through a fashion questionnaire. The device packages this information and sends it to the server using a secure communication protocol.

[0433] Step 2:

[0434] The server receives image data sent from the terminal and uses image recognition algorithms to analyze the color, shape, and style of the clothing. This allows the characteristics of the user's wardrobe to be compiled into data.

[0435] Step 3:

[0436] The server identifies the user's fashion tendencies based on survey data and image analysis results. This process utilizes machine learning algorithms to learn style patterns based on the user's past choices.

[0437] Step 4:

[0438] The server selects suggested items that deviate slightly from the usual style, based on identified fashion trends. The emphasis is on these suggestions being able to add a new accent to the user's style.

[0439] Step 5:

[0440] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. Multiple combinations are considered, and the best match is chosen.

[0441] Step 6:

[0442] The server sends the generated coordination proposal to the terminal. The terminal receives it and displays it visually to the user.

[0443] Step 7:

[0444] Users can virtually try on suggested fashion items on their devices using augmented reality (AR) technology. This feature allows them to see how an item will look before actually purchasing or using it.

[0445] Step 8:

[0446] If the user is satisfied with the suggested outfit, they can decide to purchase it based on the try-on results or to incorporate it into their actual wardrobe. This step facilitates the adoption of new styles.

[0447] (Example 1)

[0448] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] Existing fashion systems often only display a user's style in a monotonous way, failing to effectively encourage individual preferences or the exploration of new styles. Furthermore, there is a lack of visual means for users to confirm the suitability of new fashion items before actually trying them on. As a result, many users feel anxious when adopting new styles.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes means for acquiring image information and user information, means for analyzing the image information and user information to identify an individual's clothing preferences, and means for selecting alternatives that differ from the individual's usual attire based on the individual's clothing preferences. This allows users to confidently try out new fashion items and experiment with new styles.

[0452] 1. "Image information" refers to data that shows the color and shape of clothing, obtained from the user's device.

[0453] 2. "User information" refers to data entered by the user, such as their personal body type and preferred colors.

[0454] 3. "Clothing preferences" refer to the user's fashion style and preferences identified based on the analyzed image information and user information.

[0455] 4. A "substitute" is a different fashion item chosen to add a new element to a user's usual style.

[0456] 5. "Collection of clothing owned" refers to the entirety of the clothing that the user already owns.

[0457] 6. "Decoration suggestions" refer to new coordination ideas, including alternative items, and represent fashion styles combined with the user's existing clothing.

[0458] 7. "Visual confirmation" is a feature that allows users to visually try out new alternatives without having to physically try them on.

[0459] 8. Augmented reality technology is a technology that uses cameras and displays to overlay virtual elements onto real-world images.

[0460] 9. A "machine learning algorithm" is a computational method that learns from data and predicts user preferences.

[0461] This invention is a system that provides multifaceted support for a user's fashion style. The system consists of a terminal, a server, and software that connects them. The user uses a dedicated application on the terminal to take pictures of clothing in their wardrobe and inputs personal information such as body type and preferred colors. The terminal then transmits this data to the server.

[0462] The server analyzes received image data using a commonly used image analysis software platform (e.g., OpenCV). This identifies the color, shape, and style of clothing, and determines the individual's clothing preferences. The server also learns the user's fashion tendencies using a machine learning algorithm (e.g., TensorFlow). This algorithm suggests new fashion items based on the user's past selection patterns.

[0463] The server selects alternative items that differ slightly from the user's usual style, and generates outfit suggestions based on these. The suggested outfits are presented to the user via their device, and the user can visually confirm the suggested items using augmented reality technology. A common AR platform (e.g., ARKit) is used for the augmented reality technology.

[0464] As a concrete example, a user who prefers monochrome clothing might be suggested a red bag as a new accent piece. This bag is then combined with their existing wardrobe and presented as a new outfit idea. The user can visually see the red bag through the application and try out the new style.

[0465] An example of a prompt to input into the generating AI model is, "Based on the user's fashion preferences, suggest new accent items and generate outfit ideas combining those items with the user's existing wardrobe." This system allows users to confidently incorporate new fashion items into their daily lives.

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The user launches the application and takes pictures of the clothes in their wardrobe using the device's camera. The image information serves as input. Specifically, the user uses the app's camera function to take pictures of the clothes from multiple angles and saves the image data to the device.

[0469] Step 2:

[0470] Users enter personal information such as body type and preferred colors into the app. This converts personal information into data. Specifically, users tap options on a dedicated form within the app and enter text.

[0471] Step 3:

[0472] The device transmits captured image information and entered personal information to the server. The input consists of image information and personal information, while the output is data transfer to the server. Specifically, the device combines this data and uploads it to the server via the internet.

[0473] Step 4:

[0474] The server uses image analysis software to analyze the received image information. The input is image information, and the output is the result of identifying color and shape. Specifically, the server performs color identification and shape extraction through pixel analysis and stores the characteristics of the clothing in a database.

[0475] Step 5:

[0476] The server analyzes the user's fashion preferences using machine learning algorithms. The input is the user's past preference data, and the output is a prediction of their fashion style. Specifically, the server inputs past data patterns into a neural network to obtain the results of the trend analysis.

[0477] Step 6:

[0478] The server selects alternatives that differ from the user's usual style based on the analysis results. The input is the predicted fashion style, and the output is the selection of suggested items. Specifically, the server uses a generative AI model to design prompt sentences and determine the suggested items.

[0479] Step 7:

[0480] The server combines suggested items with the user's existing wardrobe to generate styling suggestions. The input consists of data on suggested items and the user's wardrobe, while the output is the styling suggestions. Specifically, the server creates outfit patterns by combining suggested items with the user's own clothing and saves them in the database.

[0481] Step 8:

[0482] The device presents the generated decoration suggestions to the user. The input is the decoration suggestions, and the output is the presentation of visual information to the user. Specifically, the device displays the decoration suggestions on the app's UI, allowing the user to freely review them.

[0483] Step 9:

[0484] The user visually checks suggested items using augmented reality technology. The input is AR content, and the output is a visual try-on experience. Specifically, the user checks the suggested items virtually overlaid on the device's camera screen and compares them to their real-life self.

[0485] (Application Example 1)

[0486] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0487] In modern society, individual fashion styles are diverse, and the choices available are wide-ranging. However, when purchasing new fashion items in physical stores, users face the challenge of having to experiment to determine if they fit their existing wardrobe. There is also a need to provide a better purchasing experience while saving time and effort on trying on clothes. This invention aims to support users in confidently choosing new fashion items and solve the difficulties they face in selecting fashion styles within stores.

[0488] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0489] In this invention, the server includes means for acquiring image data and personal information; means for analyzing the image data and personal information to identify the user's fashion tendencies; means for selecting suggested items that differ from the usual style based on the fashion tendencies; means for generating styling ideas by combining the suggested items with existing clothing; means for presenting the styling ideas to the user and enabling trial fitting; and means for displaying the styling ideas through a visual device and performing fitting simulations when the user views products in the store. This allows the user to easily check whether new fashion items suit them in the store and to try out new styles.

[0490] "Image data" refers to still images or videos captured by a user's device, and is digital information used to analyze the color and shape of fashion items.

[0491] "Personal information" refers to data entered by users, such as body type, preferences, and past fashion choices, and is used to identify the user's fashion tendencies.

[0492] "Fashion trends" refer to the patterns and styles of fashion items that a user has selected in the past, and are taken into consideration when determining suggested items based on their individual style.

[0493] "Suggested items" are new fashion items selected by the system to add a different accent to the user's usual fashion style.

[0494] A "decoration suggestion" is a fashion coordination idea generated by combining suggested items with clothing that the user already owns.

[0495] "Trial fitting" refers to a process where a user virtually wears a newly proposed item using augmented reality technology and visually confirms its appearance.

[0496] "Visual devices" refer to devices such as smart glasses and head-mounted displays, which are hardware used by users to visually confirm design options.

[0497] "Wearing simulation" is a technology that uses augmented reality to simulate what a proposed item would look like when worn by a user, even though the user is not actually wearing it.

[0498] This invention aims to support a user's fashion style using a complexly configured system. First, the user's terminal uses visual devices such as a camera or smart glasses to acquire image data of the user's clothing and newly encountered items. In addition, the user inputs personal information such as their body type, fashion preferences, and past purchase history.

[0499] The server uses an image analysis algorithm (e.g., OpenCV) to analyze the acquired image data. During this process, the server identifies the color, shape, and style of clothing, forming the user's wardrobe data. Based on this information, a machine learning algorithm (e.g., TensorFlow) is used to identify the user's fashion tendencies. The machine learning algorithm learns the user's past selection patterns and determines suggested items to try next.

[0500] After the proposed items are selected, the server combines them with the user's existing clothing to generate styling options. The generated styling options are presented to the user through a visual device, and trial fitting is possible using augmented reality technology (e.g., ARCore). Through this simulation function, the user can try out new styles before actually wearing them.

[0501] As a concrete example, consider a scenario where a user finds a new jacket in a store. They can scan the jacket using a visual device to see how it would look with their usual outfits. This allows the user to purchase new fashion items with confidence.

[0502] By inputting prompts such as, "Combine the user's wardrobe data with images of jackets in the store to generate the best possible outfit suggestions," the AI ​​model can obtain optimal suggestions.

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The device acquires the user's image data and personal information. The user uses smart glasses to take photos of their clothing and new items and inputs them into the device. They also input their body type, preferred colors, and past fashion selection history into the application. The input data is sent to the server as image data.

[0506] Step 2:

[0507] The server analyzes the acquired image data. Using image analysis algorithms such as OpenCV, it identifies the color, shape, and style of clothing from the transmitted image data. As a result of the analysis, the user's wardrobe data is output.

[0508] Step 3:

[0509] The server identifies the user's fashion tendencies. Using the acquired personal information and wardrobe data, a machine learning algorithm (TensorFlow) learns the user's past selection patterns and estimates their fashion tendencies. The output of this process is data about the user's fashion tendencies.

[0510] Step 4:

[0511] The server selects suggested items based on fashion trends. It chooses new items that differ from the user's usual style. Using a generative AI model, it issues a prompt message such as "Generate the best outfit suggestions." The selected suggested items are output.

[0512] Step 5:

[0513] The server generates outfit ideas by combining suggested items with existing clothing. Based on the user's wardrobe data and suggested items, multiple outfit ideas are created. The output of this step is the outfit idea data.

[0514] Step 6:

[0515] The decoration options are sent to the terminal and presented to the user. Using augmented reality technology (ARCore), the user can virtually try on the decoration options through their visual device. The user visually confirms the displayed fitting simulation. This step outputs the virtual fitting results, allowing the user to try on new fashion items.

[0516] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0517] This invention is an advanced system that supports users' fashion styles and, by combining it with an emotion engine, provides fashion suggestions based on the user's emotional state. This system begins by collecting not only image data and personal information, but also emotional information through the user's terminal.

[0518] The user's device takes a picture of their wardrobe and sends personal data to the server. During this process, an emotion engine analyzes the user's voice tone and facial expressions to generate data about their current psychological state. This information is transmitted to the server via a secure protocol.

[0519] After receiving this data, the server analyzes the image data to understand the characteristics of the wardrobe, while also learning fashion trends from personal information. A machine learning algorithm derives the optimal style pattern based on the user's past choices. It also identifies the user's current emotions based on the results of the emotion engine. For example, if the user is feeling down, it can suggest colorful items to brighten their mood.

[0520] The server selects suggested items that differ from the user's usual style, based on both fashion trends and emotional information. Based on these selected items, it generates outfit ideas by combining them with the user's existing wardrobe and sends the results to the terminal.

[0521] Users can view outfit suggestions generated on their devices and virtually try them on using AR technology. This virtual try-on allows users to visually experience how fashion items will look before purchasing or going out, and in particular, to confirm that the selected outfits match their emotions and current mood.

[0522] As a concrete example, consider a situation where a user is feeling a bit tired because they haven't achieved the desired results at work. This system recognizes this emotion using an emotion engine, and the server suggests bright-colored accessories to encourage and energize the user. It then generates outfit suggestions based on these suggestions and encourages the user to try them on using augmented reality, thus offering a new style while also having a positive psychological impact.

[0523] In this way, this system aims not only to broaden the scope of self-expression through fashion, but also to provide suggestions tailored to the user's emotions and psychological state, thereby supporting a richer daily life.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] Users take photos of their wardrobe using their device's camera and input personal preferences and body type information through an in-app questionnaire. The device then activates an emotion engine to analyze the user's voice tone and facial expressions to obtain emotional data.

[0527] Step 2:

[0528] The device transmits acquired image data, personal information, and emotional data to the server. All of this data is encrypted and transferred to the server using a secure communication protocol.

[0529] Step 3:

[0530] The server analyzes the received image data to determine the color, style, and shape of the clothing. It also uses machine learning algorithms to evaluate personal information in order to determine the user's fashion preferences. Sentimental data is used to identify the user's current psychological state.

[0531] Step 4:

[0532] Based on identified fashion trends and current emotional information, the server selects suggested items that deviate slightly from the user's usual style. For example, if the user is feeling stressed, it will recommend items in a relaxing style.

[0533] Step 5:

[0534] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. These generated outfits also take emotional information into account, ensuring they are tailored to the user's psychological state.

[0535] Step 6:

[0536] The server sends the generated outfit suggestion data to the device. The device then displays the received outfit suggestion to the user within the app.

[0537] Step 7:

[0538] Users can use their devices to visualize suggested outfits using AR technology and virtually try them on. This allows users to confidently try out new styles.

[0539] Step 8:

[0540] If a user likes the suggested items or outfits, they can review the results of the virtual try-on and then use that information to influence their actual purchase or actions. This allows users to enjoy choosing fashion that aligns with their mood and feelings.

[0541] (Example 2)

[0542] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0543] Fashion choices depend on numerous factors, with the user's emotional state being particularly influential. However, conventional fashion suggestion systems often fail to consider the user's emotional state, resulting in suggestions that don't match the user's actual needs. Furthermore, it's difficult to see how suggested items actually look, which can cause users to feel uneasy about the suggestions. To address these challenges, personalized fashion suggestions that take into account each user's individual emotions and fashion preferences are necessary.

[0544] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0545] In this invention, the server includes means for acquiring image data, personal information, and emotional data; means for analyzing the image data, personal information, and emotional data to identify the user's fashion tendencies and emotional state; and means for selecting suggested items that differ from the usual style based on the fashion tendencies and emotional state. This enables the server to make optimal fashion suggestions according to the user's emotions and allows the user to confirm how the suggested items actually look through virtual try-on.

[0546] "Image data" refers to information that visually represents the characteristics of a user's wardrobe and clothing.

[0547] "Personal information" refers to data relating to a specific individual, such as a user's fashion preferences or usage history.

[0548] "Emotional data" refers to information that indicates a user's psychological state, derived from their tone of voice and facial expressions.

[0549] "Fashion trends" refer to style tendencies derived from a user's past fashion choices and preferences.

[0550] A "suggested item" is a piece of clothing or accessory selected to offer a new combination that differs from the user's usual style.

[0551] A "coordinate suggestion" is a fashion proposal for the user, formed by combining suggested items with existing clothing.

[0552] "Virtual try-on" is a method that uses augmented reality technology to allow users to have a visual experience of actually wearing suggested fashion items.

[0553] Augmented reality technology is a technique that uses computer graphics and image analysis to overlay digital information onto the real world's field of view.

[0554] "Machine learning techniques" are computational techniques and algorithms used to learn patterns and knowledge from data and perform predictions and classifications.

[0555] This invention provides an advanced information processing system that assists users in selecting fashion styles and offers fashion suggestions that take their emotional state into consideration. This system is implemented using the user's terminal, a server, an emotion engine, and machine learning techniques.

[0556] First, the user takes pictures of their wardrobe using the device and inputs personal data. Furthermore, the emotion engine analyzes the user's voice tone and facial expressions to generate current emotion data. This emotion analysis can utilize software such as a Python library. The device then transmits this image data, personal information, and emotion data to the server via a secure protocol.

[0557] Next, the server analyzes the received data. OpenCV and TensorFlow are used to analyze image data and understand the characteristics of the clothing. Machine learning techniques (such as Scikit-learn and PyTorch) are utilized to learn fashion trends based on personal information. Furthermore, the server identifies the user's current psychological state based on emotional data. For example, if the server identifies the user as "depressed," it selects items to cheer them up.

[0558] The selected items are combined with the user's existing wardrobe to generate new outfit ideas. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits."

[0559] Users then review the suggested outfits on their devices and virtually try them on using augmented reality technology (such as ARKit or ARCore). This virtual try-on allows users to check the visual impression of fashion items before purchasing or going out, enabling them to make the best choices.

[0560] As described above, the system aims to enrich users' daily lives and broaden the scope of self-expression through fashion by taking into account the user's emotional state and providing personalized fashion suggestions.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] The user takes a picture of their wardrobe and inputs relevant personal data (such as preferences and sizes) into the device. This data is temporarily stored by the device. Next, the emotion engine collects voice tone and facial expressions to generate the user's emotion data. The inputs for this step are the wardrobe image, personal data, voice tone, and facial expressions, and the output is the generation of emotion data based on this.

[0564] Step 2:

[0565] The terminal sends the collected image data, personal data, and generated sentiment data to the server in a single batch via a secure protocol. The input to this step is all the data generated in the previous step, and the output is the transmission to the server.

[0566] Step 3:

[0567] The server analyzes the received image data using OpenCV to extract the characteristics of the clothing in the image. This process yields feature data such as the color, shape, and pattern of the clothing. Next, machine learning methods (Scikit-learn or PyTorch) are applied using personal data to identify the user's fashion tendencies. The input for this step is image data and personal data, and based on this, feature data and fashion tendencies are output.

[0568] Step 4:

[0569] The server analyzes emotional data to identify the user's psychological state (for example, recommending cheerful items if the user is feeling down). Based on this emotional information, it links it to fashion trends to select the most suitable suggested items. The inputs for this step are emotional data and fashion trends, and the selected suggested items are output.

[0570] Step 5:

[0571] The server generates new outfit ideas by combining selected suggested items with the existing wardrobe. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits." The input for this step is the suggested items and the existing wardrobe, and the output is outfit ideas.

[0572] Step 6:

[0573] The server sends the generated coordination proposal to the user's terminal, allowing the user to visually confirm the result. The input for this step is the coordination proposal, and the output is its presentation to the terminal.

[0574] Step 7:

[0575] The user reviews the outfit suggestions received on their device and then virtually tries them on using augmented reality technology. This virtual try-on allows them to experience how the fashion items actually look. The input for this step is the outfit suggestion, and the output is the virtual try-on result.

[0576] (Application Example 2)

[0577] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0578] In today's busy lifestyle, users often find it difficult to choose appropriate clothing that reflects their emotional state. Fashion choices, in particular, are directly linked to mood and psychological state, and without dedicated guidance, appropriate choices can be difficult. Furthermore, traditional systems struggle to provide personalized outfit suggestions that reflect a user's actual emotions in real time. There is a need to solve these problems and help users easily find fashion that suits them.

[0579] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0580] In this invention, the server includes means for acquiring image information, personal attributes, and emotional states obtained from voice tone and facial expressions; means for analyzing the image information, personal attributes, and emotional states to identify the user's clothing preferences; and means for selecting suggested items that differ from the usual style based on the clothing preferences and emotional states. This allows the user to receive personalized fashion suggestions that match their emotional state at the time, try them on using augmented reality technology, and make selections while visually confirming them.

[0581] "Image information" refers to information that includes visual data, and is used to obtain information such as a user's appearance and the condition of their clothing.

[0582] "Personal attributes" refer to information unique to a user, including personal preferences, past selection history, and basic profile information.

[0583] "Emotional state" refers to the user's psychological and emotional state, and is obtained from biometric information such as voice tone and facial expressions.

[0584] "Clothing trends" refer to the characteristics of fashion patterns and styles that a user has chosen in the past.

[0585] "Suggested items" refer to new fashion items or styles selected by the system based on the user's emotional state and clothing preferences.

[0586] Augmented reality technology is a technology that overlays virtual information onto the real world, enabling users to virtually try on clothes.

[0587] The system implementing this invention utilizes a user's terminal, a server, and a smart device. The user's terminal acquires image information, personal attributes, and emotional state. This includes the user wearing a smart device, which allows the built-in camera and microphone to sense the user's facial expressions and voice tone. The server receives and processes this information to generate optimized fashion suggestions based on the user's clothing preferences and emotional state. The server analyzes the image information and emotional state and uses machine learning algorithms to identify the user's preferences. The generated suggested items are sent to the user's terminal to provide new options that deviate from the user's usual style and can be virtually tried on using augmented reality technology. Specifically, virtual try-on videos of the selected fashion items are displayed on the screen of smart glasses or a mobile device. This allows the user to visually experience new styles while making appropriate choices according to their emotional state.

[0588] As a concrete example, when a user chooses an outfit for a specific event, they receive personalized suggestions that reflect their emotional state at the time. For instance, if a user wears smart glasses before attending a party on the weekend to analyze their emotional state, the server will suggest items that are both relaxing and stylish. The user can visually review the suggested outfits and select them on the spot.

[0589] Example prompts for generative AI models:

[0590] "Using a fashion suggestion system based on the user's emotional state, please create a story about how a user wearing smart glasses would choose an outfit that matches their emotions. How can users use this system in their daily lives to create a unique style?"

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The user's device uses a smart device to collect image information, personal attributes, and voice tone and facial expressions. Input consists of image data from the device's camera and audio data from the microphone; output is a digital file integrating these. This data is used as foundational information for analyzing the user's current emotional state and preferences. Specific actions include capturing facial expressions with the camera and recording conversational audio with the microphone.

[0594] Step 2:

[0595] The server receives image and audio data transmitted from the user's terminal and analyzes the user's emotional state using an emotion engine. The input is a digital file from the terminal, and the output is an evaluation value of the analyzed emotional state and a specific emotion label. In this process, emotions such as joy, anger, and sadness are identified using facial recognition and voice analysis algorithms.

[0596] Step 3:

[0597] The server uses machine learning algorithms to learn the user's past clothing preferences and generate fashion suggestions based on their emotional state. The input is analyzed emotional state data and past fashion preference history, and the output is a list of suggested fashion items. The server predicts the user's preferred colors, styles, and seasonal choices, and provides individually customized suggestions.

[0598] Step 4:

[0599] The server sends generated fashion suggestions to the user's device, providing an environment where the user can virtually try on the clothes via augmented reality technology. The input is a list of suggested items, and the output is a virtual outfit screen displayed on the device. The user can use augmented reality technology to virtually try on the items on their own avatar and check how they look.

[0600] Step 5:

[0601] Based on the results of the virtual try-on, users can select their favorite fashion items and, if they wish to purchase additional items, proceed with the purchase within the system. The input is the user's selection data, and the output is a confirmation message sent to the user after the purchase is completed. Specific actions include the transaction via electronic payment and the preparation for shipping the purchased items.

[0602] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0603] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0604] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0608] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0609] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0610] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0611] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0612] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0613] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0614] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0615] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0616] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0617] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0618] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] This invention is configured as a system that comprehensively supports a user's fashion style. This system begins by transmitting image data captured by the user's device and personal information entered by the user to a server.

[0620] The server analyzes the received image data to identify the color, shape, and style of the clothing owned by the user. This provides detailed data about the user's wardrobe. Next, the server identifies the user's fashion tendencies, taking into account information about their personal preferences and body type. At this stage, machine learning algorithms are used to predict the optimal fashion style based on the user's past selection patterns.

[0621] The next suggested item is selected that is slightly different from the user's usual style. This suggested item is designed to bring a new accent to the user's look. Based on the selected suggested item, the server generates several outfit ideas that combine it with the user's existing wardrobe.

[0622] The generated outfit suggestions are sent to the device and presented to the user. The user can virtually try on the suggested items using AR technology. This allows for visual confirmation before actually wearing the items, providing a sense of security when trying out new styles.

[0623] As a concrete example, consider a user who mostly wears monochrome clothing and generally avoids colorful items. This user takes photos of their wardrobe with the app and enters body type information and preferred colors into a questionnaire. The server analyzes this data and suggests a red bag as an accent color the user should try. It then generates several outfit ideas using the bag and combines them with the user's monochrome clothing. Through the app, the user can try on different looks with the red bag and experiment with new styles.

[0624] Thus, this system aims to help users confidently incorporate new fashion items into their lives and bring variety and enjoyment to their everyday style.

[0625] The following describes the processing flow.

[0626] Step 1:

[0627] Users take photos of items in their wardrobe with their own devices and input personal preferences and body type information through a fashion questionnaire. The device packages this information and sends it to the server using a secure communication protocol.

[0628] Step 2:

[0629] The server receives image data sent from the terminal and uses image recognition algorithms to analyze the color, shape, and style of the clothing. This allows the characteristics of the user's wardrobe to be compiled into data.

[0630] Step 3:

[0631] The server identifies the user's fashion tendencies based on survey data and image analysis results. This process utilizes machine learning algorithms to learn style patterns based on the user's past choices.

[0632] Step 4:

[0633] The server selects suggested items that deviate slightly from the usual style, based on identified fashion trends. The emphasis is on these suggestions adding a new accent to the user's style.

[0634] Step 5:

[0635] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. Multiple combinations are considered, and the best match is chosen.

[0636] Step 6:

[0637] The server sends the generated coordination proposal to the terminal. The terminal receives it and displays it visually to the user.

[0638] Step 7:

[0639] Users can virtually try on suggested fashion items on their devices using augmented reality (AR) technology. This feature allows them to see how an item will look before actually purchasing or using it.

[0640] Step 8:

[0641] If the user is satisfied with the suggested outfit, they can decide to purchase it based on the try-on results or to incorporate it into their actual wardrobe. This step facilitates the adoption of new styles.

[0642] (Example 1)

[0643] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0644] Existing fashion systems often only display a user's style in a monotonous way, failing to effectively encourage individual preferences or the exploration of new styles. Furthermore, there is a lack of visual means for users to confirm the suitability of new fashion items before actually trying them on. As a result, many users feel anxious when adopting new styles.

[0645] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0646] In this invention, the server includes means for acquiring image information and user information, means for analyzing the image information and user information to identify an individual's clothing preferences, and means for selecting alternatives that differ from the individual's usual attire based on the individual's clothing preferences. This allows users to confidently try out new fashion items and experiment with new styles.

[0647] 1. "Image information" refers to data that shows the color and shape of clothing, obtained from the user's device.

[0648] 2. "User information" refers to data entered by the user, such as their personal body type and preferred colors.

[0649] 3. "Clothing preferences" refer to the user's fashion style and preferences identified based on the analyzed image information and user information.

[0650] 4. A "substitute" is a different fashion item chosen to add a new element to a user's usual style.

[0651] 5. "Collection of clothing owned" refers to the entirety of the clothing that the user already owns.

[0652] 6. "Decoration suggestions" refer to new coordination ideas, including alternative items, and represent fashion styles combined with the user's existing clothing.

[0653] 7. "Visual confirmation" is a feature that allows users to visually try out new alternatives without having to physically try them on.

[0654] 8. Augmented reality technology is a technology that uses cameras and displays to overlay virtual elements onto real-world images.

[0655] 9. A "machine learning algorithm" is a computational method that learns from data and predicts user preferences.

[0656] This invention is a system that provides multifaceted support for a user's fashion style. The system consists of a terminal, a server, and software that connects them. The user uses a dedicated application on the terminal to take pictures of clothing in their wardrobe and inputs personal information such as body type and preferred colors. The terminal then transmits this data to the server.

[0657] The server analyzes received image data using a commonly used image analysis software platform (e.g., OpenCV). This identifies the color, shape, and style of clothing, and determines the individual's clothing preferences. The server also learns the user's fashion tendencies using a machine learning algorithm (e.g., TensorFlow). This algorithm suggests new fashion items based on the user's past selection patterns.

[0658] The server selects alternative items that differ slightly from the user's usual style, and generates outfit suggestions based on these. The suggested outfits are presented to the user via their device, and the user can visually confirm the suggested items using augmented reality technology. A common AR platform (e.g., ARKit) is used for the augmented reality technology.

[0659] As a concrete example, a user who prefers monochrome clothing might be suggested a red bag as a new accent piece. This bag is then combined with their existing wardrobe and presented as a new outfit idea. The user can visually see the red bag through the application and try out the new style.

[0660] An example of a prompt to input into the generating AI model is, "Based on the user's fashion preferences, suggest new accent items and generate outfit ideas combining those items with the user's existing wardrobe." This system allows users to confidently incorporate new fashion items into their daily lives.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] The user launches the application and takes pictures of the clothes in their wardrobe using the device's camera. The image information serves as input. Specifically, the user uses the app's camera function to take pictures of the clothes from multiple angles and saves the image data to the device.

[0664] Step 2:

[0665] Users enter personal information such as body type and preferred colors into the app. This converts personal information into data. Specifically, users tap options on a dedicated form within the app and enter text.

[0666] Step 3:

[0667] The device transmits captured image information and entered personal information to the server. The input consists of image information and personal information, while the output is data transfer to the server. Specifically, the device combines this data and uploads it to the server via the internet.

[0668] Step 4:

[0669] The server uses image analysis software to analyze the received image information. The input is image information, and the output is the result of identifying color and shape. Specifically, the server performs color identification and shape extraction through pixel analysis and stores the characteristics of the clothing in a database.

[0670] Step 5:

[0671] The server analyzes the user's fashion preferences using machine learning algorithms. The input is the user's past preference data, and the output is a prediction of their fashion style. Specifically, the server inputs past data patterns into a neural network to obtain the results of the trend analysis.

[0672] Step 6:

[0673] The server selects alternatives that differ from the user's usual style based on the analysis results. The input is the predicted fashion style, and the output is the selection of suggested items. Specifically, the server uses a generative AI model to design prompt sentences and determine the suggested items.

[0674] Step 7:

[0675] The server combines suggested items with the user's existing wardrobe to generate styling suggestions. The input consists of data on suggested items and the user's wardrobe, while the output is the styling suggestions. Specifically, the server creates outfit patterns by combining suggested items with the user's own clothing and saves them in the database.

[0676] Step 8:

[0677] The device presents the generated decoration suggestions to the user. The input is the decoration suggestions, and the output is the presentation of visual information to the user. Specifically, the device displays the decoration suggestions on the app's UI, allowing the user to freely review them.

[0678] Step 9:

[0679] The user visually checks suggested items using augmented reality technology. The input is AR content, and the output is a visual try-on experience. Specifically, the user checks the suggested items virtually overlaid on the device's camera screen and compares them to their real-life self.

[0680] (Application Example 1)

[0681] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] In modern society, individual fashion styles are diverse, and the choices available are wide-ranging. However, when purchasing new fashion items in physical stores, users face the challenge of having to experiment to determine if they fit their existing wardrobe. There is also a need to provide a better purchasing experience while saving time and effort on trying on clothes. This invention aims to support users in confidently choosing new fashion items and solve the difficulties they face in selecting fashion styles within stores.

[0683] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0684] In this invention, the server includes means for acquiring image data and personal information; means for analyzing the image data and personal information to identify the user's fashion tendencies; means for selecting suggested items that differ from the usual style based on the fashion tendencies; means for generating styling ideas by combining the suggested items with existing clothing; means for presenting the styling ideas to the user and enabling trial fitting; and means for displaying the styling ideas through a visual device and performing fitting simulations when the user views products in the store. This allows the user to easily check whether new fashion items suit them in the store and to try out new styles.

[0685] "Image data" refers to still images or videos captured by a user's device, and is digital information used to analyze the color and shape of fashion items.

[0686] "Personal information" refers to data entered by users, such as body type, preferences, and past fashion choices, and is used to identify the user's fashion tendencies.

[0687] "Fashion trends" refer to the patterns and styles of fashion items that a user has selected in the past, and are taken into consideration when determining suggested items based on their individual style.

[0688] "Suggested items" are new fashion items selected by the system to add a different accent to the user's usual fashion style.

[0689] A "decoration suggestion" is a fashion coordination idea generated by combining suggested items with clothing that the user already owns.

[0690] "Trial fitting" refers to a process where a user virtually wears a newly proposed item using augmented reality technology and visually confirms its appearance.

[0691] "Visual devices" refer to devices such as smart glasses and head-mounted displays, which are hardware used by users to visually confirm design options.

[0692] "Wearing simulation" is a technology that uses augmented reality to simulate what a proposed item would look like when worn by a user, even though the user is not actually wearing it.

[0693] This invention aims to support a user's fashion style using a complexly configured system. First, the user's terminal uses visual devices such as a camera or smart glasses to acquire image data of the user's clothing and newly encountered items. In addition, the user inputs personal information such as their body type, fashion preferences, and past purchase history.

[0694] The server uses an image analysis algorithm (e.g., OpenCV) to analyze the acquired image data. During this process, the server identifies the color, shape, and style of clothing, forming the user's wardrobe data. Based on this information, a machine learning algorithm (e.g., TensorFlow) is used to identify the user's fashion tendencies. The machine learning algorithm learns the user's past selection patterns and determines suggested items to try next.

[0695] After the proposed items are selected, the server combines them with the user's existing clothing to generate styling options. The generated styling options are presented to the user through a visual device, and trial fitting is possible using augmented reality technology (e.g., ARCore). Through this simulation function, the user can try out new styles before actually wearing them.

[0696] As a concrete example, consider a scenario where a user finds a new jacket in a store. They can scan the jacket using a visual device to see how it would look with their usual outfits. This allows the user to purchase new fashion items with confidence.

[0697] By inputting prompts such as, "Combine the user's wardrobe data with images of jackets in the store to generate the best possible outfit suggestions," the AI ​​model can obtain optimal suggestions.

[0698] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0699] Step 1:

[0700] The device acquires the user's image data and personal information. The user uses smart glasses to take photos of their clothing and new items and inputs them into the device. They also input their body type, preferred colors, and past fashion selection history into the application. The input data is sent to the server as image data.

[0701] Step 2:

[0702] The server analyzes the acquired image data. Using image analysis algorithms such as OpenCV, it identifies the color, shape, and style of clothing from the transmitted image data. As a result of the analysis, the user's wardrobe data is output.

[0703] Step 3:

[0704] The server identifies the user's fashion tendencies. Using the acquired personal information and wardrobe data, a machine learning algorithm (TensorFlow) learns the user's past selection patterns and estimates their fashion tendencies. The output of this process is data about the user's fashion tendencies.

[0705] Step 4:

[0706] The server selects suggested items based on fashion trends. It chooses new items that differ from the user's usual style. Using a generative AI model, it issues a prompt message such as "Generate the best outfit suggestions." The selected suggested items are output.

[0707] Step 5:

[0708] The server generates outfit ideas by combining suggested items with existing clothing. Based on the user's wardrobe data and suggested items, multiple outfit ideas are created. The output of this step is the outfit idea data.

[0709] Step 6:

[0710] The decoration options are sent to the terminal and presented to the user. Using augmented reality technology (ARCore), the user can virtually try on the decoration options through their visual device. The user visually confirms the displayed fitting simulation. This step outputs the virtual fitting results, allowing the user to try on new fashion items.

[0711] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0712] This invention is an advanced system that supports users' fashion styles and, by combining it with an emotion engine, provides fashion suggestions based on the user's emotional state. This system begins by collecting not only image data and personal information, but also emotional information through the user's terminal.

[0713] The user's device takes a picture of their wardrobe and sends personal data to the server. During this process, an emotion engine analyzes the user's voice tone and facial expressions to generate data about their current psychological state. This information is transmitted to the server via a secure protocol.

[0714] After receiving this data, the server analyzes the image data to understand the characteristics of the wardrobe, while also learning fashion trends from personal information. A machine learning algorithm derives the optimal style pattern based on the user's past choices. It also identifies the user's current emotions based on the results of the emotion engine. For example, if the user is feeling down, it can suggest colorful items to brighten their mood.

[0715] The server selects suggested items that differ from the user's usual style, based on both fashion trends and emotional information. Based on these selected items, it generates outfit ideas by combining them with the user's existing wardrobe and sends the results to the terminal.

[0716] Users can view outfit suggestions generated on their devices and virtually try them on using AR technology. This virtual try-on allows users to visually experience how fashion items will look before purchasing or going out, and in particular, to confirm that the selected outfits match their emotions and current mood.

[0717] As a concrete example, consider a situation where a user is feeling a bit tired because they haven't achieved the desired results at work. This system recognizes this emotion using an emotion engine, and the server suggests bright-colored accessories to encourage and energize the user. It then generates outfit suggestions based on these suggestions and encourages the user to try them on using augmented reality, thus offering a new style while also having a positive psychological impact.

[0718] In this way, this system aims not only to broaden the scope of self-expression through fashion, but also to provide suggestions tailored to the user's emotions and psychological state, thereby supporting a richer daily life.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] Users take photos of their wardrobe using their device's camera and input personal preferences and body type information through an in-app questionnaire. The device then activates an emotion engine to analyze the user's voice tone and facial expressions to obtain emotional data.

[0722] Step 2:

[0723] The device transmits acquired image data, personal information, and emotional data to the server. All of this data is encrypted and transferred to the server using a secure communication protocol.

[0724] Step 3:

[0725] The server analyzes the received image data to determine the color, style, and shape of the clothing. It also uses machine learning algorithms to evaluate personal information in order to determine the user's fashion preferences. Sentimental data is used to identify the user's current psychological state.

[0726] Step 4:

[0727] Based on identified fashion trends and current emotional information, the server selects suggested items that deviate slightly from the user's usual style. For example, if the user is feeling stressed, it will recommend items in a relaxing style.

[0728] Step 5:

[0729] The server generates outfit suggestions based on the selected items, combining them with the user's existing wardrobe. These generated outfits also take emotional information into account, ensuring they are tailored to the user's psychological state.

[0730] Step 6:

[0731] The server sends the generated outfit suggestion data to the device. The device then displays the received outfit suggestion to the user within the app.

[0732] Step 7:

[0733] Users can use their devices to visualize suggested outfits using AR technology and virtually try them on. This allows users to confidently try out new styles.

[0734] Step 8:

[0735] If a user likes the suggested items or outfits, they can review the results of the virtual try-on and then use that information to influence their actual purchase or actions. This allows users to enjoy choosing fashion that aligns with their mood and feelings.

[0736] (Example 2)

[0737] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] Fashion choices depend on numerous factors, with the user's emotional state being particularly influential. However, conventional fashion suggestion systems often fail to consider the user's emotional state, resulting in suggestions that don't match the user's actual needs. Furthermore, it's difficult to see how suggested items actually look, which can cause users to feel uneasy about the suggestions. To address these challenges, personalized fashion suggestions that take into account each user's individual emotions and fashion preferences are necessary.

[0739] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0740] In this invention, the server includes means for acquiring image data, personal information, and emotional data; means for analyzing the image data, personal information, and emotional data to identify the user's fashion tendencies and emotional state; and means for selecting suggested items that differ from the usual style based on the fashion tendencies and emotional state. This enables the server to make optimal fashion suggestions according to the user's emotions and allows the user to confirm how the suggested items actually look through virtual try-on.

[0741] "Image data" refers to information that visually represents the characteristics of a user's wardrobe and clothing.

[0742] "Personal information" refers to data relating to a specific individual, such as a user's fashion preferences or usage history.

[0743] "Emotional data" refers to information that indicates a user's psychological state, derived from their tone of voice and facial expressions.

[0744] "Fashion trends" refer to style tendencies derived from a user's past fashion choices and preferences.

[0745] A "suggested item" is a piece of clothing or accessory selected to offer a new combination that differs from the user's usual style.

[0746] A "coordinate suggestion" is a fashion proposal for the user, formed by combining suggested items with existing clothing.

[0747] "Virtual try-on" is a method that uses augmented reality technology to allow users to have a visual experience of actually wearing suggested fashion items.

[0748] Augmented reality technology is a technique that uses computer graphics and image analysis to overlay digital information onto the real world's field of view.

[0749] "Machine learning techniques" are computational techniques and algorithms used to learn patterns and knowledge from data and perform predictions and classifications.

[0750] This invention provides an advanced information processing system that assists users in selecting fashion styles and offers fashion suggestions that take their emotional state into consideration. This system is implemented using the user's terminal, a server, an emotion engine, and machine learning techniques.

[0751] First, the user takes pictures of their wardrobe using the device and inputs personal data. Furthermore, the emotion engine analyzes the user's voice tone and facial expressions to generate current emotion data. This emotion analysis can utilize software such as a Python library. The device then transmits this image data, personal information, and emotion data to the server via a secure protocol.

[0752] Next, the server analyzes the received data. OpenCV and TensorFlow are used to analyze image data and understand the characteristics of the clothing. Machine learning techniques (such as Scikit-learn and PyTorch) are utilized to learn fashion trends based on personal information. Furthermore, the server identifies the user's current psychological state based on emotional data. For example, if the server identifies the user as "depressed," it selects items to cheer them up.

[0753] The selected items are combined with the user's existing wardrobe to generate new outfit ideas. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits."

[0754] Users then review the suggested outfits on their devices and virtually try them on using augmented reality technology (such as ARKit or ARCore). This virtual try-on allows users to check the visual impression of fashion items before purchasing or going out, enabling them to make the best choices.

[0755] As described above, the system aims to enrich users' daily lives and broaden the scope of self-expression through fashion by taking into account the user's emotional state and providing personalized fashion suggestions.

[0756] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0757] Step 1:

[0758] The user takes a picture of their wardrobe and inputs relevant personal data (such as preferences and sizes) into the device. This data is temporarily stored by the device. Next, the emotion engine collects voice tone and facial expressions to generate the user's emotion data. The inputs for this step are the wardrobe image, personal data, voice tone, and facial expressions, and the output is the generation of emotion data based on this.

[0759] Step 2:

[0760] The terminal sends the collected image data, personal data, and generated sentiment data to the server in a single batch via a secure protocol. The input to this step is all the data generated in the previous step, and the output is the transmission to the server.

[0761] Step 3:

[0762] The server analyzes the received image data using OpenCV to extract the characteristics of the clothing in the image. This process yields feature data such as the color, shape, and pattern of the clothing. Next, machine learning methods (Scikit-learn or PyTorch) are applied using personal data to identify the user's fashion tendencies. The input for this step is image data and personal data, and based on this, feature data and fashion tendencies are output.

[0763] Step 4:

[0764] The server analyzes emotional data to identify the user's psychological state (for example, recommending cheerful items if the user is feeling down). Based on this emotional information, it links it to fashion trends to select the most suitable suggested items. The inputs for this step are emotional data and fashion trends, and the selected suggested items are output.

[0765] Step 5:

[0766] The server generates new outfit ideas by combining selected suggested items with the existing wardrobe. This generation process utilizes a generative AI model and can leverage prompts such as "Think of fashion to lift my spirits." The input for this step is the suggested items and the existing wardrobe, and the output is outfit ideas.

[0767] Step 6:

[0768] The server sends the generated coordination proposal to the user's terminal, allowing the user to visually confirm the result. The input for this step is the coordination proposal, and the output is its presentation to the terminal.

[0769] Step 7:

[0770] The user reviews the outfit suggestions received on their device and then virtually tries them on using augmented reality technology. This virtual try-on allows them to experience how the fashion items actually look. The input for this step is the outfit suggestion, and the output is the virtual try-on result.

[0771] (Application Example 2)

[0772] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] In today's busy lifestyle, users often find it difficult to choose appropriate clothing that reflects their emotional state. Fashion choices, in particular, are directly linked to mood and psychological state, and without dedicated guidance, appropriate choices can be difficult. Furthermore, traditional systems struggle to provide personalized outfit suggestions that reflect a user's actual emotions in real time. There is a need to solve these problems and help users easily find fashion that suits them.

[0774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0775] In this invention, the server includes means for acquiring image information, personal attributes, and emotional states obtained from voice tone and facial expressions; means for analyzing the image information, personal attributes, and emotional states to identify the user's clothing preferences; and means for selecting suggested items that differ from the usual style based on the clothing preferences and emotional states. This allows the user to receive personalized fashion suggestions that match their emotional state at the time, try them on using augmented reality technology, and make selections while visually confirming them.

[0776] "Image information" refers to information that includes visual data, and is used to obtain information such as a user's appearance and the condition of their clothing.

[0777] "Personal attributes" refer to information unique to a user, including personal preferences, past selection history, and basic profile information.

[0778] "Emotional state" refers to the user's psychological and emotional state, and is obtained from biometric information such as voice tone and facial expressions.

[0779] "Clothing trends" refer to the characteristics of fashion patterns and styles that a user has chosen in the past.

[0780] "Suggested items" refer to new fashion items or styles selected by the system based on the user's emotional state and clothing preferences.

[0781] Augmented reality technology is a technology that overlays virtual information onto the real world, enabling users to virtually try on clothes.

[0782] The system implementing this invention utilizes a user's terminal, a server, and a smart device. The user's terminal acquires image information, personal attributes, and emotional state. This includes the user wearing a smart device, which allows the built-in camera and microphone to sense the user's facial expressions and voice tone. The server receives and processes this information to generate optimized fashion suggestions based on the user's clothing preferences and emotional state. The server analyzes the image information and emotional state and uses machine learning algorithms to identify the user's preferences. The generated suggested items are sent to the user's terminal to provide new options that deviate from the user's usual style and can be virtually tried on using augmented reality technology. Specifically, virtual try-on videos of the selected fashion items are displayed on the screen of smart glasses or a mobile device. This allows the user to visually experience new styles while making appropriate choices according to their emotional state.

[0783] As a concrete example, when a user chooses an outfit for a specific event, they receive personalized suggestions that reflect their emotional state at the time. For instance, if a user wears smart glasses before attending a party on the weekend to analyze their emotional state, the server will suggest items that are both relaxing and stylish. The user can visually review the suggested outfits and select them on the spot.

[0784] Example prompts for generative AI models:

[0785] "Using a fashion suggestion system based on the user's emotional state, please create a story about how a user wearing smart glasses would choose an outfit that matches their emotions. How can users use this system in their daily lives to create a unique style?"

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The user's device uses a smart device to collect image information, personal attributes, and voice tone and facial expressions. Input consists of image data from the device's camera and audio data from the microphone; output is a digital file integrating these. This data is used as foundational information for analyzing the user's current emotional state and preferences. Specific actions include capturing facial expressions with the camera and recording conversational audio with the microphone.

[0789] Step 2:

[0790] The server receives image and audio data transmitted from the user's terminal and analyzes the user's emotional state using an emotion engine. The input is a digital file from the terminal, and the output is an evaluation value of the analyzed emotional state and a specific emotion label. In this process, emotions such as joy, anger, and sadness are identified using facial recognition and voice analysis algorithms.

[0791] Step 3:

[0792] The server uses machine learning algorithms to learn the user's past clothing preferences and generate fashion suggestions based on their emotional state. The input is analyzed emotional state data and past fashion preference history, and the output is a list of suggested fashion items. The server predicts the user's preferred colors, styles, and seasonal choices, and provides individually customized suggestions.

[0793] Step 4:

[0794] The server sends generated fashion suggestions to the user's device, providing an environment where the user can virtually try on the clothes via augmented reality technology. The input is a list of suggested items, and the output is a virtual outfit screen displayed on the device. The user can use augmented reality technology to virtually try on the items on their own avatar and check how they look.

[0795] Step 5:

[0796] Based on the results of the virtual try-on, users can select their favorite fashion items and, if they wish to purchase additional items, proceed with the purchase within the system. The input is the user's selection data, and the output is a confirmation message sent to the user after the purchase is completed. Specific actions include the transaction via electronic payment and the preparation for shipping the purchased items.

[0797] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0798] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0799] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0800] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0801] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0802] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0803] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0804] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0805] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0806] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0807] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0808] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0809] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0810] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0811] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0812] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0813] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0814] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0815] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0816] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0817] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0818] The following is further disclosed regarding the embodiments described above.

[0819] (Claim 1)

[0820] Means of acquiring image data and personal information,

[0821] A means for identifying the user's fashion trends by analyzing the aforementioned image data and personal information,

[0822] Based on the aforementioned fashion trends, a means of selecting suggested items that differ from the usual style,

[0823] A means for generating outfit ideas by combining the aforementioned proposed items with an existing wardrobe,

[0824] A means of presenting the aforementioned outfit suggestions to the user and enabling them to try them on,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, further comprising means for a user to virtually try on the proposed items using AR technology.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising means for learning the user's fashion preferences using a machine learning algorithm.

[0830] "Example 1"

[0831] (Claim 1)

[0832] Means for acquiring image information and user information,

[0833] A means for analyzing the aforementioned image information and user information to identify an individual's clothing preferences,

[0834] A means of selecting alternatives from the usual attire based on the aforementioned individual's clothing preferences,

[0835] Means for generating decorative suggestions in combination with the aforementioned set of clothing possessing substitutes,

[0836] A means for presenting the aforementioned decorative proposal to the user and enabling visual confirmation,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, further comprising means for the user to visually confirm the substitute using augmented reality technology.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising means for learning the aforementioned individual's clothing preferences using a machine learning algorithm.

[0842] "Application Example 1"

[0843] (Claim 1)

[0844] Means of acquiring image data and personal information,

[0845] A means for identifying the user's fashion trends by analyzing the aforementioned image data and personal information,

[0846] Based on the aforementioned fashion trends, a means of selecting suggested items that differ from the usual style,

[0847] Means for generating decorative designs by combining the proposed items with existing clothing,

[0848] A means for presenting the aforementioned decorative design to the user and enabling trial fitting,

[0849] A means for displaying the aforementioned decoration plan through a visual device and performing an installation simulation when a user views products in a store,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for a user to try on the proposed article using augmented reality technology.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising means for learning the user's fashion preferences using a learning algorithm.

[0855] "Example 2 of combining an emotion engine"

[0856] (Claim 1)

[0857] Means for acquiring image data, personal information, and emotional data,

[0858] A means for analyzing the aforementioned image data, personal information, and emotional data to identify the user's fashion tendencies and emotional state,

[0859] A means of selecting suggested items that differ from the usual style based on the aforementioned fashion trends and emotional state,

[0860] A means for generating coordination ideas by combining the aforementioned proposed items with existing clothing,

[0861] A means for presenting the aforementioned outfit suggestions to the user and enabling virtual try-on,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising means for a user to virtually try on the proposed item using augmented reality technology.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means for learning the user's fashion preferences using a machine learning method.

[0867] "Application example 2 when combining with an emotional engine"

[0868] (Claim 1)

[0869] A means for acquiring emotional states obtained from image information, personal attributes, and voice tone and facial expressions,

[0870] A means for identifying the user's clothing tendencies by analyzing the aforementioned image information, personal attributes, and emotional state,

[0871] A means for selecting suggested items that differ from the usual style based on the aforementioned clothing trends and emotional state,

[0872] A means for generating combination ideas by combining the aforementioned proposed items with existing clothing sets,

[0873] A means of presenting the aforementioned combination options to the user and enabling them to try them on using augmented reality technology,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, comprising means for selecting the proposed article in real time based on emotional state and visually presenting it through a display device.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for learning the user's clothing tendencies and emotional state using a machine learning algorithm. [Explanation of Symbols]

[0879] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of acquiring image data and personal information, A means for identifying the user's fashion trends by analyzing the aforementioned image data and personal information, Based on the aforementioned fashion trends, a means of selecting suggested items that differ from the usual style, A means for generating outfit ideas by combining the aforementioned proposed items with an existing wardrobe, A means of presenting the aforementioned outfit suggestions to the user and enabling them to try them on, A system that includes this.

2. The system according to claim 1, further comprising means for a user to virtually try on the proposed items using AR technology.

3. The system according to claim 1, further comprising means for learning the user's fashion preferences using a machine learning algorithm.

Images