system

Abstract

The system according to this embodiment aims to provide busy consumers with an optimal shopping experience. [Solution] The system according to the embodiment comprises a reception unit, a research unit, an addition unit, a notification unit, a feedback collection unit, a suggestion improvement unit, and a fitting image display unit. The reception unit takes the user's photo and personal information. The research unit researches clothes and accessories that suit the user based on the information entered by the reception unit. The addition unit adds the items researched by the research unit to the cart. The notification unit sends notifications on sale days and discount days. The feedback collection unit collects feedback on items that were not purchased. The suggestion improvement unit improves suggestions for the next time based on the feedback collected by the feedback collection unit. The fitting image display unit shows an avatar trying on clothes.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In the conventional technology, there is a problem that it is difficult for busy consumers to shop efficiently and it takes time to find the optimal item.

[0005] The system according to the embodiment aims to provide an optimal shopping experience for busy consumers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a research unit, an addition unit, a notification unit, a feedback collection unit, a suggestion improvement unit, and a fitting image display unit. The reception unit takes the user's photo and personal information. The research unit researches clothes and accessories that suit the user based on the information entered by the reception unit. The addition unit adds the items researched by the research unit to the cart. The notification unit sends notifications on sale days and discount days. The feedback collection unit collects feedback on items that were not purchased. The suggestion improvement unit improves future suggestions based on the feedback collected by the feedback collection unit. The fitting image display unit shows an avatar trying on clothes. [Effects of the Invention]

[0007] The system according to this embodiment can provide busy consumers with an optimal shopping experience. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An embodiment of the present invention provides a shopping support system that offers an optimal shopping experience for busy consumers. Based on the user's photos and personal information, the AI ​​automatically researches clothing and accessories that suit the user and adds them to the cart. Next, on sale or discount days, it notifies the user with "Today is the perfect day to make a purchase!" to support efficient and waste-free shopping. Furthermore, based on feedback on items that were not purchased, the system improves the accuracy of future suggestions. Finally, the user's avatar shows them a try-on image, making it easier to decide on a purchase. For example, the shopping support system inputs the user's photos and personal information into the AI. This includes, for example, the user's facial photo, body type information, and past purchase history. This information is used by the AI ​​to understand the user's preferences and style. Next, the AI ​​automatically researches clothing and accessories that suit the user and accessories that they might like. For example, the AI ​​searches the database of online shopping sites to find the most suitable items for the user. In this process, the AI ​​selects the most suitable items considering the user's preferences and past purchase history. The selected items are automatically added to the cart. For example, clothing and accessories that the AI ​​determines suit the user are added to the cart. This eliminates the need for users to search for items themselves. Furthermore, on sale or discount days, the AI ​​notifies users with messages like, "Today is the perfect day to make a purchase!" For example, the AI ​​collects sale information and notifies users, allowing them to shop at opportune times. For items that are not purchased, feedback is collected from the user. For example, a user might provide feedback such as, "This item didn't suit me." This feedback is used by the AI ​​to improve future suggestions. Finally, the user's avatar is shown a try-on image. For example, the AI ​​generates an avatar of the user and displays an image of them trying on the selected items. This allows users to check whether items suit them without actually trying them on. This system enables busy consumers to shop efficiently and prevents unnecessary purchases.Furthermore, personalized suggestions tailored to the user's preferences lead to increased satisfaction. For example, this AI avatar is an extremely useful tool for people who are busy with work or household chores, or who tend to miss out on sales information. This allows the shopping support system to provide an optimal shopping experience for busy consumers.

[0029] The shopping support system according to this embodiment comprises a reception unit, a research unit, an additional unit, a notification unit, a feedback collection unit, a suggestion improvement unit, and a fitting image display unit. The reception unit inputs the user's photos and personal information. The user's photos and personal information include, but are not limited to, a facial photograph, body shape information, and past purchase history. For example, the reception unit scans the user's facial photograph at high resolution and stores it as digital data. The reception unit can also measure the user's body shape information and store it as digital data. Furthermore, the reception unit can retrieve and store the user's past purchase history from a database. The research unit researches clothing and accessories that suit the user based on the information entered by the reception unit. For example, the research unit searches the database of online shopping sites to find the most suitable items for the user. For example, the research unit uses AI to select the most suitable items, taking into account the user's preferences and past purchase history. For example, the research unit can also use text generation AI (e.g., LLM) to research the most suitable items for the user. The research unit can, for example, use multimodal generation AI to research the most suitable items for the user. The research unit can, for example, use AI to select the most suitable items considering the user's preferences and past purchase history. The addition unit adds the items researched by the research unit to the cart. The addition unit can, for example, automatically add researched items to the cart. The addition unit can, for example, add clothes and accessories that it determines would suit the user to the cart. The addition unit can, for example, use AI to add researched items to the cart. The notification unit sends notifications on sale days and discount days. The notification unit can, for example, collect sale information and notify the user. The notification unit can, for example, use AI to collect sale information and notify the user. The notification unit can, for example, notify the user using push notifications or email. The feedback collection unit collects feedback on items that were not purchased. The feedback collection unit collects feedback from users.The feedback collection unit can collect user feedback, for example, using surveys or reviews. The suggestion improvement unit improves future suggestions based on the feedback collected by the feedback collection unit. The suggestion improvement unit analyzes the collected feedback and improves future suggestions, for example. The suggestion improvement unit can also use AI to analyze the collected feedback and improve future suggestions, for example. The fitting image display unit shows an avatar trying on clothes. The fitting image display unit can, for example, use AI to generate a user avatar and display an image of the selected items being tried on. The fitting image display unit can also use multimodal generation AI to generate a user avatar and display an image of the selected items being tried on, for example. This allows the shopping support system according to the embodiment to provide an optimal shopping experience for busy consumers.

[0030] The reception desk inputs the user's photos and personal information. This information includes, but is not limited to, facial photos, body measurements, and past purchase history. For example, the reception desk scans the user's facial photo at high resolution and stores it as digital data. Specifically, facial photos are taken using a high-resolution camera, and image processing technology is used to remove noise and store them as clear digital data. The reception desk can also measure the user's body measurements and store them as digital data. 3D scanners or body measuring devices can be used to obtain accurate body measurements. Furthermore, the reception desk can retrieve and store the user's past purchase history from a database. This purchase history includes detailed information about items the user has previously purchased (e.g., brand, size, color, price, etc.), allowing for an understanding of the user's preferences and purchasing patterns. This data is stored in a secure database to protect user privacy. The reception desk centrally manages this information and makes it accessible to the research department and other departments. This allows the reception department to efficiently collect detailed user information and improve the overall accuracy and performance of the system.

[0031] The research department researches clothing and accessories that suit the user based on the information entered by the reception department. For example, the research department searches online shopping site databases to find the most suitable items for the user. Specifically, the research department uses AI to select the most suitable items, taking into account the user's preferences and past purchase history. The AI ​​analyzes the user's facial photograph and body type information to identify styles and colors that suit the user. For example, it uses image recognition technology to analyze the user's face shape and skin color and suggests the most suitable clothing and accessories. It can also use text generation AI (e.g., LLM) to research the most suitable items for the user. Based on the user's past purchase history and preferences, LLM uses natural language processing technology to generate text that recommends the most suitable items for the user. Furthermore, it can also use multimodal generation AI to research the most suitable items for the user. Multimodal generation AI integrates and analyzes image data and text data to select the most suitable items for the user. This allows the research department to quickly and accurately research the most suitable items based on detailed user information.

[0032] The Additions unit adds items researched by the Research unit to the cart. Specifically, it automatically adds researched items to the cart. For example, the Additions unit adds clothing and accessories that it determines would suit the user. It can also use AI to add researched items to the cart. The AI ​​considers the user's preferences and past purchase history to select the most suitable items and automatically add them to the cart. For example, it can find new items similar to items the user has previously purchased and add them to the cart. The Additions unit can also adjust the items added to the cart based on user feedback. For example, if the user prefers a particular brand or style, it will prioritize adding items from that brand or style to the cart. This allows the Additions unit to efficiently add the most suitable items to the user's cart, improving the shopping experience.

[0033] The notification unit will send notifications on sale and discount days. Specifically, it will collect sale information and notify users. The notification unit can also use AI to collect sale information and notify users. The AI ​​will automatically collect sale information from online shopping sites and brand official websites and notify users at the optimal time. For example, notifications can be sent to users via push notifications or email. Push notifications will display sale information in real time on smartphones and tablets, allowing users to access it immediately. Email notifications will send users emails containing detailed sale information and discount coupons, increasing their purchase intent. The notification unit can also provide individually customized sale information, taking into account the user's preferences and past purchase history. This allows the notification unit to quickly and accurately provide users with useful sale information, thereby increasing their purchase intent.

[0034] The Feedback Collection Unit collects feedback on items that were not purchased. Specifically, it collects feedback from users. The Feedback Collection Unit can collect user feedback using methods such as surveys and reviews. Surveys include questions asking why a purchase was not made and how the item is evaluated, and are provided in a format that users can easily answer. Reviews are provided in a format that allows users to freely write their opinions, enabling the collection of detailed feedback. The Feedback Collection Unit stores this feedback in a database and makes it accessible to the Suggestion Improvement Unit. Furthermore, the Feedback Collection Unit can use AI to automatically classify and analyze the collected feedback. This allows the Feedback Collection Unit to efficiently collect user opinions and requests and use them to improve the entire system.

[0035] The Proposal Improvement Department improves future proposals based on feedback collected by the Feedback Collection Department. Specifically, it analyzes the collected feedback and improves future proposals. The Proposal Improvement Department can also use AI, for example, to analyze the collected feedback and improve future proposals. The AI ​​uses natural language processing technology to analyze user feedback and identify common problems and areas for improvement. For example, if a user is dissatisfied with a particular item, the proposal for that item will be reviewed and a more appropriate item will be suggested. Furthermore, based on the feedback, the Proposal Improvement Department can re-evaluate user preferences and purchasing patterns to make future proposals more personalized. In this way, the Proposal Improvement Department can leverage user feedback to improve the accuracy and satisfaction of its proposals.

[0036] The fitting image display unit shows an avatar trying on clothes. Specifically, AI generates an avatar of the user and displays an image of the selected items being tried on. The AI ​​generates a realistic avatar based on the user's facial photograph and body shape information. For example, 3D modeling technology is used to create an avatar that accurately reproduces the user's body shape and facial features. Furthermore, a multimodal generation AI can also be used to generate the user's avatar and display an image of the selected items being tried on. The multimodal generation AI integrates and analyzes image data and text data to try on the most suitable items for the user's avatar. As a result, the fitting image display unit provides a realistic image as if the user were actually trying on the items. The user can check the fitting image and evaluate the fit and style of the items. In this way, the fitting image display unit can increase the user's purchasing intent and improve the shopping experience.

[0037] The reception desk can input the user's facial photograph, body shape information, and past purchase history. For example, the reception desk can scan the user's facial photograph at high resolution and save it as digital data. The reception desk can also measure the user's body shape information and save it as digital data. Furthermore, the reception desk can retrieve and save the user's past purchase history from a database. This enables more personalized suggestions based on detailed user information. Facial photographs, body shape information, and past purchase history include, but are not limited to, the resolution of the facial photograph, the method of measuring body shape information, and the period of purchase history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input data obtained by scanning the user's facial photograph into a generating AI and have the generating AI perform facial photograph analysis.

[0038] The research department can search online shopping site databases to research the most suitable items for users. For example, the research department can search online shopping site databases to find the most suitable items for users. The research department can, for example, use AI to select the most suitable items considering user preferences and past purchase history. The research department can also, for example, use text generation AI (e.g., LLM) to research the most suitable items for users. The research department can also, for example, use multimodal generation AI to research the most suitable items for users. The research department can, for example, use AI to select the most suitable items considering user preferences and past purchase history. This improves shopping efficiency by automatically researching the most suitable items for users. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can input data obtained by searching online shopping site databases into a generation AI and have the generation AI perform item selection.

[0039] The addition unit can add researched items to the cart. The addition unit can, for example, automatically add researched items to the cart. The addition unit can, for example, add clothes and accessories that it determines would suit the user to the cart. The addition unit can also, for example, use AI to add researched items to the cart. This saves the user the trouble of searching for items themselves. Specific methods and criteria for adding items to the cart include, but are not limited to, the user's preferences and past purchase history. Some or all of the above-described processes in the addition unit may be performed, for example, using AI or not using AI. For example, the addition unit can input researched items into a generating AI and have the generating AI perform the task of adding them to the cart.

[0040] The notification unit can collect sales information and notify users. For example, the notification unit collects sales information and notifies users. The notification unit can also collect sales information and notify users using AI, for example. The notification unit can also notify users using push notifications or email, for example. This allows users to shop at opportune times without missing sales information. Specific methods and criteria for collecting sales information include, but are not limited to, sales type and discount rate. Some or all of the above-described processes in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input sales information into a generating AI and have the generating AI execute the timing and content of the notification.

[0041] The feedback collection unit can collect feedback from users. The feedback collection unit can, for example, collect feedback from users. The feedback collection unit can also collect feedback from users using, for example, surveys or reviews. This allows for improvement of future proposals based on user feedback. Specific methods and criteria for collecting feedback include, but are not limited to, surveys and reviews. Some or all of the above-described processes in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input user feedback into a generating AI and have the generating AI perform analysis of the feedback.

[0042] The proposal improvement unit can improve future proposals based on the collected feedback. For example, the proposal improvement unit can analyze the collected feedback and improve future proposals. The proposal improvement unit can also use AI to analyze the collected feedback and improve future proposals. This allows for improved accuracy of proposals based on user feedback. Specific methods and criteria for proposal improvement include, but are not limited to, feedback analysis methods and improvement algorithms. Some or all of the above-described processes in the proposal improvement unit may be performed using AI or not. For example, the proposal improvement unit can input the collected feedback into a generating AI and have the generating AI perform proposal improvements.

[0043] The fitting image display unit allows an avatar to display images of itself trying on clothes. For example, the fitting image display unit can use AI to generate a user avatar and display an image of the selected items being tried on. The fitting image display unit can also use multimodal generation AI to generate a user avatar and display an image of the selected items being tried on. This allows the user to check whether an item suits them without actually trying it on. Specific display methods and criteria for the fitting image include, but are not limited to, the type of avatar and details of the items to be displayed. Some or all of the above-described processes in the fitting image display unit may be performed using AI or not. For example, the fitting image display unit can input the user's avatar into a generation AI and have the generation AI generate the fitting image.

[0044] The reception desk can analyze the user's past purchase history and select the optimal information input method. For example, the reception desk can automatically display as suggestions information that the user has frequently entered in the past. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest information input methods to be used at specific times based on the user's past purchase history. This improves input efficiency by providing the optimal information input method based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not. For example, the reception desk can input the user's past purchase history data into a generating AI and have the generating AI select the information input method.

[0045] The reception unit can filter information input based on the user's current lifestyle and areas of interest. For example, the reception unit prioritizes inputting information that is highly relevant to the user's current lifestyle. The reception unit can also customize the information to be input based on the user's areas of interest. Furthermore, the reception unit can filter out unnecessary information based on the user's current lifestyle and areas of interest. This allows for the provision of more relevant information by filtering information based on the user's current lifestyle and areas of interest. Specific methods for identifying the current lifestyle and areas of interest include, but are not limited to, survey results and social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input data on the user's lifestyle and areas of interest into a generating AI and have the generating AI perform the information filtering.

[0046] The reception unit can prioritize inputting highly relevant information by considering the user's geographical location when information is entered. For example, the reception unit can prioritize inputting highly relevant information based on the user's current location. The reception unit can also input optimal information by considering the user's geographical location. Furthermore, the reception unit can filter out unnecessary information based on the user's current location. This allows for the provision of more relevant information by considering the user's geographical location. Specific methods and criteria for obtaining geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location information into a generating AI and have the generating AI determine the priority of the information.

[0047] The reception desk can analyze the user's social media activity and input relevant information when information is entered. For example, the reception desk can analyze the user's social media activity and prioritize inputting relevant information. The reception desk can also input the most relevant information based on the user's social media activity. Furthermore, the reception desk can filter out unnecessary information, taking into account the user's social media activity. This allows for the provision of more relevant information by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform information filtering.

[0048] The research department can adjust the level of detail in its research based on the importance of the items. For example, the research department can conduct detailed research on important items, and concise research on less important items. Furthermore, the research department can prioritize research based on the importance of the items. This allows for efficient research by adjusting the level of detail based on the importance of the items. Specific methods for evaluating item importance include, but are not limited to, user ratings and sales figures. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can input item importance data into a generating AI and have the generating AI adjust the level of detail in the research.

[0049] The research department can apply different research algorithms depending on the item category during research. For example, for fashion items, the research department can apply a research algorithm that takes trend information into account. For home appliances, the research department can also apply a research algorithm that emphasizes performance evaluation. Furthermore, for books, the research department can apply a research algorithm that emphasizes review evaluation. This allows for more accurate research by applying research algorithms according to the item category. Specific classification methods for item categories include, but are not limited to, clothing and accessories. Some or all of the above-described processes in the research department may be performed using AI, for example, or without AI. For example, the research department can input item category data into a generating AI and have the generating AI execute the application of research algorithms.

[0050] The research department can prioritize research based on the item submission dates. For example, the research department can prioritize researching items with upcoming submission dates, and postpone researching items with later submission dates. Furthermore, the research department can adjust the research schedule based on the submission dates. This allows for efficient research by prioritizing research based on item submission dates. Specific methods for evaluating item submission dates include, but are not limited to, the latest items and seasonal items. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can input item submission date data into a generating AI and have the generating AI determine the research priorities.

[0051] The research department can adjust the order of research based on the relevance of items during the research process. For example, the research department can prioritize researching highly relevant items. It can also postpone researching less relevant items. Furthermore, the research department can adjust the order of research based on the relevance of items. This allows for more efficient research by adjusting the order of research based on the relevance of items. Specific methods for evaluating item relevance include, but are not limited to, user preferences and past purchase history. Some or all of the above processes in the research department may be performed using AI, for example, or not. For example, the research department can input item relevance data into a generating AI and have the generating AI adjust the order of research.

[0052] The addition function can analyze the user's past purchase history to select the most suitable items when adding items. For example, the addition function can suggest highly relevant items based on items the user has purchased in the past. It can also prioritize suggesting items from specific brands or categories based on the user's past purchase history. Furthermore, the addition function can analyze the user's past purchase history to select the most suitable items. This allows for more personalized suggestions by selecting the most suitable items based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above-described processes in the addition function may be performed using, for example, AI, or not. For example, the addition function can input the user's past purchase history data into a generating AI and have the generating AI perform the item selection.

[0053] The addition function can customize items based on the user's current lifestyle when adding items. For example, the addition function can suggest highly relevant items based on the user's current lifestyle. The addition function can also provide item customization options according to the user's lifestyle. Furthermore, the addition function can filter out unnecessary items based on the user's current lifestyle. This allows for more relevant suggestions by customizing items based on the user's current lifestyle. Specific methods for identifying the current lifestyle include, but are not limited to, survey results and social media activity. Some or all of the processing described above in the addition function may be performed using AI, for example, or without AI. For example, the addition function can input the user's lifestyle data into a generating AI and have the generating AI perform item customization.

[0054] The addition unit can select the most relevant items when adding items, taking into account the user's geographical location information. For example, the addition unit can suggest highly relevant items based on the user's current location. It can also select the most relevant items by considering the user's geographical location information. Furthermore, the addition unit can filter out unnecessary items based on the user's current location. This allows for the provision of more relevant items by considering the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the processing described above in the addition unit may be performed using, for example, AI, or without AI. For example, the addition unit can input the user's geographical location information into a generating AI and have the generating AI perform item selection.

[0055] The addition unit can analyze the user's social media activity and suggest items when adding items. For example, the addition unit can analyze the user's social media activity and suggest relevant items. The addition unit can also select the most suitable items based on the user's social media activity. Furthermore, the addition unit can filter out unnecessary items by considering the user's social media activity. This allows for the provision of more relevant items by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the addition unit may be performed using AI, for example, or without AI. For example, the addition unit can input the user's social media activity data into a generating AI and have the generating AI suggest items.

[0056] The notification unit can analyze the user's past purchase history to select the most appropriate notification method when sending a notification. For example, the notification unit can prioritize notifications related to items the user has frequently purchased in the past. It can also prioritize notifications for specific brands or categories based on the user's past purchase history. Furthermore, the notification unit can analyze the user's past purchase history to select the most suitable notification method. This improves notification efficiency by providing the most appropriate notification method based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input the user's past purchase history data into a generating AI and have the generating AI select the notification method.

[0057] The notification unit can customize notification content based on the user's current living situation. For example, the notification unit can provide highly relevant notifications based on the user's current living situation. The notification unit can also customize notification content according to the user's living situation. Furthermore, the notification unit can filter out unnecessary notifications based on the user's current living situation. This allows for more relevant notifications by customizing notification content based on the user's current living situation. Specific methods for identifying the current living situation include, but are not limited to, survey results and social media activity. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user living situation data into a generating AI and have the generating AI customize the notification content.

[0058] The notification unit can select the optimal notification method when sending a notification, taking into account the user's geographical location information. For example, the notification unit can provide highly relevant notifications based on the user's current location. The notification unit can also select the optimal notification method, taking into account the user's geographical location information. Furthermore, the notification unit can filter out unnecessary notifications based on the user's current location. This makes it possible to send more relevant notifications by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input the user's geographical location information into a generating AI and have the generating AI select the notification method.

[0059] The notification unit can analyze the user's social media activity and suggest notification content when sending a notification. For example, the notification unit can analyze the user's social media activity and provide relevant notifications. It can also suggest optimal notification content based on the user's social media activity. Furthermore, the notification unit can filter out unnecessary notifications by considering the user's social media activity. This allows for more relevant notifications by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's social media activity data into a generating AI and have the generating AI suggest notification content.

[0060] The feedback collection unit can analyze the user's past feedback history to select the optimal collection method when collecting feedback. For example, the feedback collection unit can suggest a highly relevant feedback collection method based on the feedback the user has provided in the past. The feedback collection unit can also prioritize the collection of feedback from specific categories based on the user's past feedback history. Furthermore, the feedback collection unit can analyze the user's past feedback history and select the most suitable feedback collection method. This improves the efficiency of feedback by providing the optimal collection method based on the user's past feedback history. Specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of feedback. Some or all of the above-described processes in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input the user's past feedback history data into a generating AI and have the generating AI select the collection method.

[0061] The feedback collection unit can select the optimal collection method when collecting feedback, taking into account the user's geographical location information. For example, the feedback collection unit can collect highly relevant feedback based on the user's current location. The feedback collection unit can also select the optimal feedback collection method, taking into account the user's geographical location information. Furthermore, the feedback collection unit can filter out unnecessary feedback based on the user's current location. This makes it possible to collect more relevant feedback by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input the user's geographical location information into a generating AI and have the generating AI select the collection method.

[0062] The suggestion improvement unit can analyze the user's past feedback history to select the optimal improvement method when improving a suggestion. For example, the suggestion improvement unit can propose highly relevant improvement methods based on the user's past feedback. The suggestion improvement unit can also prioritize suggesting improvement methods in specific categories based on the user's past feedback history. Furthermore, the suggestion improvement unit can analyze the user's past feedback history and select the most suitable improvement method. This improves the efficiency of suggestions by providing the optimal improvement method based on the user's past feedback history. Specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of feedback. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input the user's past feedback history data into a generating AI and have the generating AI select improvement methods.

[0063] The suggestion improvement unit can customize the suggested content based on the user's current living situation when improving suggestions. For example, the suggestion improvement unit can provide highly relevant suggestions based on the user's current living situation. The suggestion improvement unit can also customize the suggested content according to the user's living situation. Furthermore, the suggestion improvement unit can filter out unnecessary suggestions based on the user's current living situation. This makes it possible to provide more relevant suggestions by customizing the suggested content based on the user's current living situation. Specific methods for identifying the current living situation include, but are not limited to, survey results and social media activity. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input user living situation data into a generating AI and have the generating AI perform the customization of the suggested content.

[0064] The suggestion improvement unit can select the optimal improvement method when improving suggestions, taking into account the user's geographical location information. For example, the suggestion improvement unit can provide highly relevant suggestions based on the user's current location. The suggestion improvement unit can also select the optimal improvement method by taking into account the user's geographical location information. Furthermore, the suggestion improvement unit can filter out unnecessary suggestions based on the user's current location. This makes it possible to provide more relevant suggestions by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input the user's geographical location information into a generating AI and have the generating AI select an improvement method.

[0065] The Proposal Improvement Department can improve proposals by analyzing users' social media activity during the proposal improvement process. For example, the Proposal Improvement Department can analyze users' social media activity and provide relevant proposals. It can also select the most appropriate proposals based on users' social media activity. Furthermore, the Proposal Improvement Department can filter out unnecessary proposals by considering users' social media activity. This allows for more relevant proposals by analyzing users' social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above-described processes in the Proposal Improvement Department may be performed using AI, for example, or without AI. For example, the Proposal Improvement Department can input user social media activity data into a generating AI and have the generating AI perform the proposal improvement.

[0066] The fitting image display unit can analyze the user's past fitting history and select the optimal display method when displaying fitting images. For example, the fitting image display unit can provide highly relevant fitting images based on items the user has tried on in the past. The fitting image display unit can also prioritize providing fitting images of specific brands or categories based on the user's past fitting history. Furthermore, the fitting image display unit can analyze the user's past fitting history and select the most suitable fitting image. This improves the efficiency of fitting images by providing the optimal display method based on the user's past fitting history. Specific methods and criteria for analyzing past fitting history include, but are not limited to, the types of items tried on and the number of times they were tried on. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's past fitting history data into a generating AI and have the generating AI select the display method.

[0067] The fitting image display unit can select the optimal display method when displaying fitting images, taking into account the user's geographical location information. For example, the fitting image display unit can provide highly relevant fitting images based on the user's current location. The fitting image display unit can also select the optimal display method, taking into account the user's geographical location information. Furthermore, the fitting image display unit can filter out unnecessary fitting images based on the user's current location. This makes it possible to display more relevant fitting images by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's geographical location information into a generating AI and have the generating AI select the display method.

[0068] The fitting image display unit can analyze the user's social media activity and select the optimal display method when displaying fitting images. For example, the fitting image display unit can analyze the user's social media activity and provide relevant fitting images. The fitting image display unit can also select the optimal display method based on the user's social media activity. Furthermore, the fitting image display unit can filter out unnecessary fitting images by considering the user's social media activity. This makes it possible to provide more relevant fitting images by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, the content of posts and the number of likes. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's social media activity data into a generating AI and have the generating AI select the display method.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The shopping support system can analyze a user's past purchase history and select the optimal research algorithm. For example, it can analyze trends in items a user has purchased in the past and prioritize researching highly relevant items. It can also prioritize researching items from specific brands or categories based on the user's past purchase history. Furthermore, it can analyze the user's past purchase history and select the most suitable research algorithm. This improves research efficiency by providing the optimal research algorithm based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input the user's past purchase history data into a generating AI and have the generating AI select a research algorithm.

[0071] The shopping support system can customize research results based on the user's current lifestyle. For example, it can prioritize researching items that are highly relevant to the user's current lifestyle. It can also customize research results according to the user's lifestyle. Furthermore, it can filter out unnecessary items based on the user's current lifestyle. This allows for the provision of more relevant research results by customizing them based on the user's current lifestyle. Specific methods for identifying the current lifestyle include, but are not limited to, survey results and social media activity. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input user lifestyle data into a generating AI and have the generating AI perform the customization of research results.

[0072] The shopping support system can provide research results while taking the user's geographical location into consideration. For example, it can prioritize researching highly relevant items based on the user's current location. It can also provide optimal research results while considering the user's geographical location. Furthermore, it can filter out unnecessary items based on the user's current location. This allows for the provision of more relevant research results by considering the user's geographical location. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the research unit may be performed using AI or not. For example, the research unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing research results.

[0073] The shopping support system can analyze a user's social media activity and provide relevant research results. For example, it can analyze a user's social media activity and prioritize researching highly relevant items. It can also provide optimal research results based on the user's social media activity. Furthermore, it can filter out unnecessary items by considering the user's social media activity. This allows for the provision of more relevant research results by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input user social media activity data into a generating AI and have the generating AI provide research results.

[0074] The shopping support system can analyze a user's past feedback history and select the most suitable improvement method. For example, it can suggest highly relevant improvement methods based on feedback the user has provided in the past. It can also prioritize suggesting improvement methods for specific categories based on the user's past feedback history. Furthermore, it can analyze the user's past feedback history and select the most appropriate improvement method. This improves the efficiency of suggestions by providing the most suitable improvement method based on the user's past feedback history. The specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of the feedback. Some or all of the above processing in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input the user's past feedback history data into a generating AI and have the generating AI select improvement methods.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The reception desk enters the user's photo and personal information. This includes a facial photograph, body measurements, and past purchase history. For example, the reception desk scans the user's facial photograph at high resolution and saves it as digital data. It can also measure the user's body measurements and save them as digital data. Furthermore, it can retrieve and save the user's past purchase history from a database. Step 2: The research department researches clothing and accessories that suit the user based on the information entered by the reception department. For example, the research department searches the database of online shopping sites to find the most suitable items for the user. The research department can also use AI to select the most suitable items by considering the user's preferences and past purchase history. Furthermore, it is possible to conduct research using text generation AI and multimodal generation AI. Step 3: The Additions section adds items researched by the Research section to the cart. For example, it can automatically add researched items to the cart. The Additions section can also use AI to add clothes and accessories that it determines would suit the user to the cart. Step 4: The notification unit will send notifications on sale days and discount days. For example, it will collect sale information and notify users. The notification unit can also use AI to collect sale information and notify users via push notifications or email. Step 5: The feedback collection team collects feedback on items that were not purchased. For example, user feedback can be collected through surveys or reviews. Step 6: The proposal improvement unit improves future proposals based on the feedback collected by the feedback collection unit. For example, it analyzes the collected feedback and improves future proposals. The proposal improvement unit can also use AI to analyze the collected feedback and improve future proposals. Step 7: The fitting image display unit shows the avatar trying on the clothes. For example, the AI ​​generates the user's avatar and displays an image of the selected items being tried on. The fitting image display unit can also use a multimodal generation AI to generate the user's avatar and display an image of the selected items being tried on.

[0077] (Example of form 2) An embodiment of the present invention provides a shopping support system that offers an optimal shopping experience for busy consumers. Based on the user's photos and personal information, the AI ​​automatically researches clothing and accessories that suit the user and adds them to the cart. Next, on sale or discount days, it notifies the user with "Today is the perfect day to make a purchase!" to support efficient and waste-free shopping. Furthermore, based on feedback on items that were not purchased, the system improves the accuracy of future suggestions. Finally, the user's avatar shows them a try-on image, making it easier to decide on a purchase. For example, the shopping support system inputs the user's photos and personal information into the AI. This includes, for example, the user's facial photo, body type information, and past purchase history. This information is used by the AI ​​to understand the user's preferences and style. Next, the AI ​​automatically researches clothing and accessories that suit the user and accessories that they might like. For example, the AI ​​searches the database of online shopping sites to find the most suitable items for the user. In this process, the AI ​​selects the most suitable items considering the user's preferences and past purchase history. The selected items are automatically added to the cart. For example, clothing and accessories that the AI ​​determines suit the user are added to the cart. This eliminates the need for users to search for items themselves. Furthermore, on sale or discount days, the AI ​​notifies users with messages like, "Today is the perfect day to make a purchase!" For example, the AI ​​collects sale information and notifies users, allowing them to shop at opportune times. For items that are not purchased, feedback is collected from the user. For example, a user might provide feedback such as, "This item didn't suit me." This feedback is used by the AI ​​to improve future suggestions. Finally, the user's avatar is shown a try-on image. For example, the AI ​​generates an avatar of the user and displays an image of them trying on the selected items. This allows users to check whether items suit them without actually trying them on. This system enables busy consumers to shop efficiently and prevents unnecessary purchases.Furthermore, personalized suggestions tailored to the user's preferences lead to increased satisfaction. For example, this AI avatar is an extremely useful tool for people who are busy with work or household chores, or who tend to miss out on sales information. This allows the shopping support system to provide an optimal shopping experience for busy consumers.

[0078] The shopping support system according to this embodiment comprises a reception unit, a research unit, an additional unit, a notification unit, a feedback collection unit, a suggestion improvement unit, and a fitting image display unit. The reception unit inputs the user's photos and personal information. The user's photos and personal information include, but are not limited to, a facial photograph, body shape information, and past purchase history. For example, the reception unit scans the user's facial photograph at high resolution and stores it as digital data. The reception unit can also measure the user's body shape information and store it as digital data. Furthermore, the reception unit can retrieve and store the user's past purchase history from a database. The research unit researches clothing and accessories that suit the user based on the information entered by the reception unit. For example, the research unit searches the database of online shopping sites to find the most suitable items for the user. For example, the research unit uses AI to select the most suitable items, taking into account the user's preferences and past purchase history. For example, the research unit can also use text generation AI (e.g., LLM) to research the most suitable items for the user. The research unit can, for example, use multimodal generation AI to research the most suitable items for the user. The research unit can, for example, use AI to select the most suitable items considering the user's preferences and past purchase history. The addition unit adds the items researched by the research unit to the cart. The addition unit can, for example, automatically add researched items to the cart. The addition unit can, for example, add clothes and accessories that it determines would suit the user to the cart. The addition unit can, for example, use AI to add researched items to the cart. The notification unit sends notifications on sale days and discount days. The notification unit can, for example, collect sale information and notify the user. The notification unit can, for example, use AI to collect sale information and notify the user. The notification unit can, for example, notify the user using push notifications or email. The feedback collection unit collects feedback on items that were not purchased. The feedback collection unit collects feedback from users.The feedback collection unit can collect user feedback, for example, using surveys or reviews. The suggestion improvement unit improves future suggestions based on the feedback collected by the feedback collection unit. The suggestion improvement unit analyzes the collected feedback and improves future suggestions, for example. The suggestion improvement unit can also use AI to analyze the collected feedback and improve future suggestions, for example. The fitting image display unit shows an avatar trying on clothes. The fitting image display unit can, for example, use AI to generate a user avatar and display an image of the selected items being tried on. The fitting image display unit can also use multimodal generation AI to generate a user avatar and display an image of the selected items being tried on, for example. This allows the shopping support system according to the embodiment to provide an optimal shopping experience for busy consumers.

[0079] The reception desk inputs the user's photos and personal information. This information includes, but is not limited to, facial photos, body measurements, and past purchase history. For example, the reception desk scans the user's facial photo at high resolution and stores it as digital data. Specifically, facial photos are taken using a high-resolution camera, and image processing technology is used to remove noise and store them as clear digital data. The reception desk can also measure the user's body measurements and store them as digital data. 3D scanners or body measuring devices can be used to obtain accurate body measurements. Furthermore, the reception desk can retrieve and store the user's past purchase history from a database. This purchase history includes detailed information about items the user has previously purchased (e.g., brand, size, color, price, etc.), allowing for an understanding of the user's preferences and purchasing patterns. This data is stored in a secure database to protect user privacy. The reception desk centrally manages this information and makes it accessible to the research department and other departments. This allows the reception department to efficiently collect detailed user information and improve the overall accuracy and performance of the system.

[0080] The research department researches clothing and accessories that suit the user based on the information entered by the reception department. For example, the research department searches online shopping site databases to find the most suitable items for the user. Specifically, the research department uses AI to select the most suitable items, taking into account the user's preferences and past purchase history. The AI ​​analyzes the user's facial photograph and body type information to identify styles and colors that suit the user. For example, it uses image recognition technology to analyze the user's face shape and skin color and suggests the most suitable clothing and accessories. It can also use text generation AI (e.g., LLM) to research the most suitable items for the user. Based on the user's past purchase history and preferences, LLM uses natural language processing technology to generate text that recommends the most suitable items for the user. Furthermore, it can also use multimodal generation AI to research the most suitable items for the user. Multimodal generation AI integrates and analyzes image data and text data to select the most suitable items for the user. This allows the research department to quickly and accurately research the most suitable items based on detailed user information.

[0081] The Additions unit adds items researched by the Research unit to the cart. Specifically, it automatically adds researched items to the cart. For example, the Additions unit adds clothing and accessories that it determines would suit the user. It can also use AI to add researched items to the cart. The AI ​​considers the user's preferences and past purchase history to select the most suitable items and automatically add them to the cart. For example, it can find new items similar to items the user has previously purchased and add them to the cart. The Additions unit can also adjust the items added to the cart based on user feedback. For example, if the user prefers a particular brand or style, it will prioritize adding items from that brand or style to the cart. This allows the Additions unit to efficiently add the most suitable items to the user's cart, improving the shopping experience.

[0082] The notification unit will send notifications on sale and discount days. Specifically, it will collect sale information and notify users. The notification unit can also use AI to collect sale information and notify users. The AI ​​will automatically collect sale information from online shopping sites and brand official websites and notify users at the optimal time. For example, notifications can be sent to users via push notifications or email. Push notifications will display sale information in real time on smartphones and tablets, allowing users to access it immediately. Email notifications will send users emails containing detailed sale information and discount coupons, increasing their purchase intent. The notification unit can also provide individually customized sale information, taking into account the user's preferences and past purchase history. This allows the notification unit to quickly and accurately provide users with useful sale information, thereby increasing their purchase intent.

[0083] The Feedback Collection Unit collects feedback on items that were not purchased. Specifically, it collects feedback from users. The Feedback Collection Unit can collect user feedback using methods such as surveys and reviews. Surveys include questions asking why a purchase was not made and how the item is evaluated, and are provided in a format that users can easily answer. Reviews are provided in a format that allows users to freely write their opinions, enabling the collection of detailed feedback. The Feedback Collection Unit stores this feedback in a database and makes it accessible to the Suggestion Improvement Unit. Furthermore, the Feedback Collection Unit can use AI to automatically classify and analyze the collected feedback. This allows the Feedback Collection Unit to efficiently collect user opinions and requests and use them to improve the entire system.

[0084] The Proposal Improvement Department improves future proposals based on feedback collected by the Feedback Collection Department. Specifically, it analyzes the collected feedback and improves future proposals. The Proposal Improvement Department can also use AI, for example, to analyze the collected feedback and improve future proposals. The AI ​​uses natural language processing technology to analyze user feedback and identify common problems and areas for improvement. For example, if a user is dissatisfied with a particular item, the proposal for that item will be reviewed and a more appropriate item will be suggested. Furthermore, based on the feedback, the Proposal Improvement Department can re-evaluate user preferences and purchasing patterns to make future proposals more personalized. In this way, the Proposal Improvement Department can leverage user feedback to improve the accuracy and satisfaction of its proposals.

[0085] The fitting image display unit shows an avatar trying on clothes. Specifically, AI generates an avatar of the user and displays an image of the selected items being tried on. The AI ​​generates a realistic avatar based on the user's facial photograph and body shape information. For example, 3D modeling technology is used to create an avatar that accurately reproduces the user's body shape and facial features. Furthermore, a multimodal generation AI can also be used to generate the user's avatar and display an image of the selected items being tried on. The multimodal generation AI integrates and analyzes image data and text data to try on the most suitable items for the user's avatar. As a result, the fitting image display unit provides a realistic image as if the user were actually trying on the items. The user can check the fitting image and evaluate the fit and style of the items. In this way, the fitting image display unit can increase the user's purchasing intent and improve the shopping experience.

[0086] The reception desk can input the user's facial photograph, body shape information, and past purchase history. For example, the reception desk can scan the user's facial photograph at high resolution and save it as digital data. The reception desk can also measure the user's body shape information and save it as digital data. Furthermore, the reception desk can retrieve and save the user's past purchase history from a database. This enables more personalized suggestions based on detailed user information. Facial photographs, body shape information, and past purchase history include, but are not limited to, the resolution of the facial photograph, the method of measuring body shape information, and the period of purchase history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input data obtained by scanning the user's facial photograph into a generating AI and have the generating AI perform facial photograph analysis.

[0087] The research department can search online shopping site databases to research the most suitable items for users. For example, the research department can search online shopping site databases to find the most suitable items for users. The research department can, for example, use AI to select the most suitable items considering user preferences and past purchase history. The research department can also, for example, use text generation AI (e.g., LLM) to research the most suitable items for users. The research department can also, for example, use multimodal generation AI to research the most suitable items for users. The research department can, for example, use AI to select the most suitable items considering user preferences and past purchase history. This improves shopping efficiency by automatically researching the most suitable items for users. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can input data obtained by searching online shopping site databases into a generation AI and have the generation AI perform item selection.

[0088] The addition unit can add researched items to the cart. The addition unit can, for example, automatically add researched items to the cart. The addition unit can, for example, add clothes and accessories that it determines would suit the user to the cart. The addition unit can also, for example, use AI to add researched items to the cart. This saves the user the trouble of searching for items themselves. Specific methods and criteria for adding items to the cart include, but are not limited to, the user's preferences and past purchase history. Some or all of the above-described processes in the addition unit may be performed, for example, using AI or not using AI. For example, the addition unit can input researched items into a generating AI and have the generating AI perform the task of adding them to the cart.

[0089] The notification unit can collect sales information and notify users. For example, the notification unit collects sales information and notifies users. The notification unit can also collect sales information and notify users using AI, for example. The notification unit can also notify users using push notifications or email, for example. This allows users to shop at opportune times without missing sales information. Specific methods and criteria for collecting sales information include, but are not limited to, sales type and discount rate. Some or all of the above-described processes in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input sales information into a generating AI and have the generating AI execute the timing and content of the notification.

[0090] The feedback collection unit can collect feedback from users. The feedback collection unit can, for example, collect feedback from users. The feedback collection unit can also collect feedback from users using, for example, surveys or reviews. This allows for improvement of future proposals based on user feedback. Specific methods and criteria for collecting feedback include, but are not limited to, surveys and reviews. Some or all of the above-described processes in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input user feedback into a generating AI and have the generating AI perform analysis of the feedback.

[0091] The suggestion improvement unit can improve future suggestions based on the collected feedback. For example, the suggestion improvement unit can analyze the collected feedback and improve future suggestions. The suggestion improvement unit can also use AI to analyze the collected feedback and improve future suggestions. This allows for improved accuracy of suggestions based on user feedback. Specific methods and criteria for suggestion improvement include, but are not limited to, feedback analysis methods and improvement algorithms. Some or all of the above-described processes in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input the collected feedback into a generating AI and have the generating AI perform the suggestion improvement.

[0092] The fitting image display unit allows an avatar to display images of itself trying on clothes. For example, the fitting image display unit can use AI to generate a user avatar and display an image of the selected items being tried on. The fitting image display unit can also use multimodal generation AI to generate a user avatar and display an image of the selected items being tried on. This allows the user to check whether an item suits them without actually trying it on. Specific display methods and criteria for the fitting image include, but are not limited to, the type of avatar and details of the items to be displayed. Some or all of the above-described processes in the fitting image display unit may be performed using AI or not. For example, the fitting image display unit can input the user's avatar into a generation AI and have the generation AI generate the fitting image.

[0093] The reception desk can estimate the user's emotions and adjust the timing of photo and personal information input based on the estimated emotions. For example, if the user is stressed, the reception desk can provide a simple interface and minimize the input steps. If the user is relaxed, the reception desk can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception desk can prioritize voice input to allow for quick input of photos and personal information. This allows for a more comfortable input experience by adjusting the input timing according to the user's emotions. User emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The reception desk can analyze the user's past purchase history and select the optimal information input method. For example, the reception desk can automatically display as suggestions information that the user has frequently entered in the past. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest information input methods to be used at specific times based on the user's past purchase history. This improves input efficiency by providing the optimal information input method based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not. For example, the reception desk can input the user's past purchase history data into a generating AI and have the generating AI select the information input method.

[0095] The reception unit can filter information input based on the user's current lifestyle and areas of interest. For example, the reception unit prioritizes inputting information that is highly relevant to the user's current lifestyle. The reception unit can also customize the information to be input based on the user's areas of interest. Furthermore, the reception unit can filter out unnecessary information based on the user's current lifestyle and areas of interest. This allows for the provision of more relevant information by filtering information based on the user's current lifestyle and areas of interest. Specific methods for identifying the current lifestyle and areas of interest include, but are not limited to, survey results and social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input data on the user's lifestyle and areas of interest into a generating AI and have the generating AI perform the information filtering.

[0096] The reception unit can estimate the user's emotions and determine the priority of the information to be entered based on the estimated emotions. For example, if the user is stressed, the reception unit will prioritize inputting important information. If the user is relaxed, the reception unit can also prioritize inputting detailed information. Furthermore, if the user is in a hurry, the reception unit can also prioritize inputting minimal information. This allows for more efficient information entry by prioritizing information according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, or not using AI. For example, the reception unit can input user emotion data into a generative AI and have the generative AI determine the priority of information.

[0097] The reception unit can prioritize inputting highly relevant information by considering the user's geographical location when information is entered. For example, the reception unit can prioritize inputting highly relevant information based on the user's current location. The reception unit can also input optimal information by considering the user's geographical location. Furthermore, the reception unit can filter out unnecessary information based on the user's current location. This allows for the provision of more relevant information by considering the user's geographical location. Specific methods and criteria for obtaining geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location information into a generating AI and have the generating AI determine the priority of the information.

[0098] The reception desk can analyze the user's social media activity and input relevant information when information is entered. For example, the reception desk can analyze the user's social media activity and prioritize inputting relevant information. The reception desk can also input the most relevant information based on the user's social media activity. Furthermore, the reception desk can filter out unnecessary information, taking into account the user's social media activity. This allows for the provision of more relevant information by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform information filtering.

[0099] The research department can estimate the user's emotions and adjust the presentation of the research based on the estimated emotions. For example, if the user is relaxed, the research department can provide detailed research results. If the user is in a hurry, the research department can also provide concise research results. Furthermore, if the user is excited, the research department can provide visually stimulating research results. In this way, by adjusting the presentation of the research according to the user's emotions, more appropriate research results can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can input user emotion data into the generative AI and have the generative AI adjust the presentation of the research.

[0100] The research department can adjust the level of detail in its research based on the importance of the items. For example, the research department can conduct detailed research on important items, and concise research on less important items. Furthermore, the research department can prioritize research based on the importance of the items. This allows for efficient research by adjusting the level of detail based on the importance of the items. Specific methods for evaluating item importance include, but are not limited to, user ratings and sales figures. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can input item importance data into a generating AI and have the generating AI adjust the level of detail in the research.

[0101] The research department can apply different research algorithms depending on the item category during research. For example, for fashion items, the research department can apply a research algorithm that takes trend information into account. For home appliances, the research department can also apply a research algorithm that emphasizes performance evaluation. Furthermore, for books, the research department can apply a research algorithm that emphasizes review evaluation. This allows for more accurate research by applying research algorithms according to the item category. Specific classification methods for item categories include, but are not limited to, clothing and accessories. Some or all of the above-described processes in the research department may be performed using AI, for example, or without AI. For example, the research department can input item category data into a generating AI and have the generating AI execute the application of research algorithms.

[0102] The research unit can estimate the user's emotions and adjust the length of the research based on the estimated emotions. For example, if the user is in a hurry, the research unit can provide short, concise research results. If the user is relaxed, the research unit can also provide detailed research results. Furthermore, if the user is excited, the research unit can provide visually stimulating research results. By adjusting the length of the research according to the user's emotions, more appropriate research results can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI or not using AI. For example, the research unit can input user emotion data into the generative AI and have the generative AI adjust the length of the research.

[0103] The research department can prioritize research based on the item submission dates. For example, the research department can prioritize researching items with upcoming submission dates, and postpone researching items with later submission dates. Furthermore, the research department can adjust the research schedule based on the submission dates. This allows for efficient research by prioritizing research based on item submission dates. Specific methods for evaluating item submission dates include, but are not limited to, the latest items and seasonal items. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can input item submission date data into a generating AI and have the generating AI determine the research priorities.

[0104] The research department can adjust the order of research based on the relevance of items during the research process. For example, the research department can prioritize researching highly relevant items. It can also postpone researching less relevant items. Furthermore, the research department can adjust the order of research based on the relevance of items. This allows for more efficient research by adjusting the order of research based on the relevance of items. Specific methods for evaluating item relevance include, but are not limited to, user preferences and past purchase history. Some or all of the above processes in the research department may be performed using AI, for example, or not. For example, the research department can input item relevance data into a generating AI and have the generating AI adjust the order of research.

[0105] The add-on function can estimate the user's emotions and determine the priority of items to add to the cart based on the estimated emotions. For example, if the user is stressed, the add-on function will prioritize adding important items to the cart. If the user is relaxed, the add-on function can also provide detailed information and suggest customizable items. Furthermore, if the user is in a hurry, the add-on function can quickly add items to the cart with minimal information. This allows for the addition of more appropriate items to the cart by prioritizing items according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the add-on function may be performed using AI or not. For example, the add-on function can input user emotion data into a generative AI and have the generative AI perform the determination of item priorities.

[0106] The addition function can analyze the user's past purchase history to select the most suitable items when adding items. For example, the addition function can suggest highly relevant items based on items the user has purchased in the past. It can also prioritize suggesting items from specific brands or categories based on the user's past purchase history. Furthermore, the addition function can analyze the user's past purchase history to select the most suitable items. This allows for more personalized suggestions by selecting the most suitable items based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above-described processes in the addition function may be performed using, for example, AI, or not. For example, the addition function can input the user's past purchase history data into a generating AI and have the generating AI perform the item selection.

[0107] The addition function can customize items based on the user's current lifestyle when adding items. For example, the addition function can suggest highly relevant items based on the user's current lifestyle. The addition function can also provide item customization options according to the user's lifestyle. Furthermore, the addition function can filter out unnecessary items based on the user's current lifestyle. This allows for more relevant suggestions by customizing items based on the user's current lifestyle. Specific methods for identifying the current lifestyle include, but are not limited to, survey results and social media activity. Some or all of the processing described above in the addition function may be performed using AI, for example, or without AI. For example, the addition function can input the user's lifestyle data into a generating AI and have the generating AI perform item customization.

[0108] The additional section can estimate the user's emotions and adjust how items added to the cart are displayed based on the estimated emotions. For example, if the user is stressed, the additional section can provide a simple display. If the user is relaxed, it can also provide a display with more detailed information. Furthermore, if the user is in a hurry, it can provide a display that gets straight to the point. This allows for a more appropriate display by adjusting how items are displayed according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the additional section may be performed using AI or not using AI. For example, the additional section can input user emotion data into a generative AI and have the generative AI adjust how items are displayed.

[0109] The addition unit can select the most relevant items when adding items, taking into account the user's geographical location information. For example, the addition unit can suggest highly relevant items based on the user's current location. It can also select the most relevant items by considering the user's geographical location information. Furthermore, the addition unit can filter out unnecessary items based on the user's current location. This allows for the provision of more relevant items by considering the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the processing described above in the addition unit may be performed using, for example, AI, or without AI. For example, the addition unit can input the user's geographical location information into a generating AI and have the generating AI perform item selection.

[0110] The addition unit can analyze the user's social media activity and suggest items when adding items. For example, the addition unit can analyze the user's social media activity and suggest relevant items. The addition unit can also select the most suitable items based on the user's social media activity. Furthermore, the addition unit can filter out unnecessary items by considering the user's social media activity. This allows for the provision of more relevant items by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the addition unit may be performed using AI, for example, or without AI. For example, the addition unit can input the user's social media activity data into a generating AI and have the generating AI suggest items.

[0111] The notification unit can estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is stressed, the notification unit can reduce the frequency of notifications. It can also provide more detailed notifications if the user is relaxed. Furthermore, if the user is in a hurry, the notification unit can prioritize important notifications. This allows for more appropriate notifications by adjusting the timing according to the user's emotions. The estimation of user emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, or not. For example, the notification unit can input user emotion data into a generative AI and have the generative AI adjust the timing of notifications.

[0112] The notification unit can analyze the user's past purchase history to select the most appropriate notification method when sending a notification. For example, the notification unit can prioritize notifications related to items the user has frequently purchased in the past. It can also prioritize notifications for specific brands or categories based on the user's past purchase history. Furthermore, the notification unit can analyze the user's past purchase history to select the most suitable notification method. This improves notification efficiency by providing the most appropriate notification method based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input the user's past purchase history data into a generating AI and have the generating AI select the notification method.

[0113] The notification unit can customize notification content based on the user's current living situation. For example, the notification unit can provide highly relevant notifications based on the user's current living situation. The notification unit can also customize notification content according to the user's living situation. Furthermore, the notification unit can filter out unnecessary notifications based on the user's current living situation. This allows for more relevant notifications by customizing notification content based on the user's current living situation. Specific methods for identifying the current living situation include, but are not limited to, survey results and social media activity. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user living situation data into a generating AI and have the generating AI customize the notification content.

[0114] The notification unit can estimate the user's emotions and determine notification priorities based on those emotions. For example, if the user is stressed, the notification unit will prioritize important notifications. It can also provide detailed notifications if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize minimal notifications. This allows for more appropriate notifications by prioritizing them according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into a generative AI and have the generative AI determine notification priorities.

[0115] The notification unit can select the optimal notification method when sending a notification, taking into account the user's geographical location information. For example, the notification unit can provide highly relevant notifications based on the user's current location. The notification unit can also select the optimal notification method, taking into account the user's geographical location information. Furthermore, the notification unit can filter out unnecessary notifications based on the user's current location. This makes it possible to send more relevant notifications by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input the user's geographical location information into a generating AI and have the generating AI select the notification method.

[0116] The notification unit can analyze the user's social media activity and suggest notification content when sending a notification. For example, the notification unit can analyze the user's social media activity and provide relevant notifications. It can also suggest optimal notification content based on the user's social media activity. Furthermore, the notification unit can filter out unnecessary notifications by considering the user's social media activity. This allows for more relevant notifications by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's social media activity data into a generating AI and have the generating AI suggest notification content.

[0117] The feedback collection unit can estimate the user's emotions and adjust the feedback collection method based on the estimated emotions. For example, if the user is stressed, the feedback collection unit can provide a concise feedback form. If the user is relaxed, the feedback collection unit can also provide a detailed feedback form. Furthermore, if the user is in a hurry, the feedback collection unit can prioritize voice input and collect feedback quickly. This allows for more appropriate feedback by adjusting the feedback collection method according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback collection unit may be performed using AI or not using AI. For example, the feedback collection unit can input user emotion data into the generative AI and have the generative AI adjust the feedback collection method.

[0118] The feedback collection unit can analyze the user's past feedback history to select the optimal collection method when collecting feedback. For example, the feedback collection unit can suggest a highly relevant feedback collection method based on the feedback the user has provided in the past. The feedback collection unit can also prioritize the collection of feedback from specific categories based on the user's past feedback history. Furthermore, the feedback collection unit can analyze the user's past feedback history and select the most suitable feedback collection method. This improves the efficiency of feedback by providing the optimal collection method based on the user's past feedback history. Specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of feedback. Some or all of the above-described processes in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input the user's past feedback history data into a generating AI and have the generating AI select the collection method.

[0119] The feedback collection unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. For example, if the user is stressed, the feedback collection unit will prioritize collecting important feedback. It can also prioritize collecting detailed feedback if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize collecting minimal feedback. This allows for more appropriate feedback by prioritizing feedback according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the feedback collection unit may be performed using AI, or not. For example, the feedback collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of feedback.

[0120] The feedback collection unit can select the optimal collection method when collecting feedback, taking into account the user's geographical location information. For example, the feedback collection unit can collect highly relevant feedback based on the user's current location. The feedback collection unit can also select the optimal feedback collection method, taking into account the user's geographical location information. Furthermore, the feedback collection unit can filter out unnecessary feedback based on the user's current location. This makes it possible to collect more relevant feedback by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the feedback collection unit may be performed using, for example, AI, or not using AI. For example, the feedback collection unit can input the user's geographical location information into a generating AI and have the generating AI select the collection method.

[0121] The suggestion improvement unit can estimate the user's emotions and adjust the suggestion improvement method based on the estimated user emotions. For example, if the user is feeling stressed, the suggestion improvement unit can provide a simple suggestion. If the user is relaxed, the suggestion improvement unit can also provide a detailed suggestion. Furthermore, if the user is in a hurry, the suggestion improvement unit can provide a suggestion quickly with minimal information. This allows for more appropriate suggestions by adjusting the suggestion improvement method according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input user emotion data into a generative AI and have the generative AI adjust the suggestion improvement method.

[0122] The suggestion improvement unit can analyze the user's past feedback history to select the optimal improvement method when improving a suggestion. For example, the suggestion improvement unit can propose highly relevant improvement methods based on the user's past feedback. The suggestion improvement unit can also prioritize suggesting improvement methods in specific categories based on the user's past feedback history. Furthermore, the suggestion improvement unit can analyze the user's past feedback history and select the most suitable improvement method. This improves the efficiency of suggestions by providing the optimal improvement method based on the user's past feedback history. Specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of feedback. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input the user's past feedback history data into a generating AI and have the generating AI select improvement methods.

[0123] The suggestion improvement unit can customize the suggested content based on the user's current living situation when improving suggestions. For example, the suggestion improvement unit can provide highly relevant suggestions based on the user's current living situation. The suggestion improvement unit can also customize the suggested content according to the user's living situation. Furthermore, the suggestion improvement unit can filter out unnecessary suggestions based on the user's current living situation. This makes it possible to provide more relevant suggestions by customizing the suggested content based on the user's current living situation. Specific methods for identifying the current living situation include, but are not limited to, survey results and social media activity. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input user living situation data into a generating AI and have the generating AI perform the customization of the suggested content.

[0124] The suggestion improvement unit can estimate the user's emotions and determine the priority of suggestions based on those emotions. For example, if the user is stressed, the suggestion improvement unit will prioritize important suggestions. It can also prioritize detailed suggestions if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize minimal suggestions. This allows for more appropriate suggestions by prioritizing suggestions according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input user emotion data into a generative AI and have the generative AI determine the priority of suggestions.

[0125] The suggestion improvement unit can select the optimal improvement method when improving suggestions, taking into account the user's geographical location information. For example, the suggestion improvement unit can provide highly relevant suggestions based on the user's current location. The suggestion improvement unit can also select the optimal improvement method by taking into account the user's geographical location information. Furthermore, the suggestion improvement unit can filter out unnecessary suggestions based on the user's current location. This makes it possible to provide more relevant suggestions by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the suggestion improvement unit may be performed using AI, for example, or without AI. For example, the suggestion improvement unit can input the user's geographical location information into a generating AI and have the generating AI select an improvement method.

[0126] The Proposal Improvement Department can improve proposals by analyzing users' social media activity during the proposal improvement process. For example, the Proposal Improvement Department can analyze users' social media activity and provide relevant proposals. It can also select the most appropriate proposals based on users' social media activity. Furthermore, the Proposal Improvement Department can filter out unnecessary proposals by considering users' social media activity. This allows for more relevant proposals by analyzing users' social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above-described processes in the Proposal Improvement Department may be performed using AI, for example, or without AI. For example, the Proposal Improvement Department can input user social media activity data into a generating AI and have the generating AI perform the proposal improvement.

[0127] The fitting image display unit can estimate the user's emotions and adjust the display method of the fitting images based on the estimated user emotions. For example, if the user is relaxed, the fitting image display unit can provide detailed fitting images. If the user is in a hurry, the fitting image display unit can also provide concise fitting images. Furthermore, if the user is excited, the fitting image display unit can provide visually stimulating fitting images. By adjusting the display method of the fitting images according to the user's emotions, a more appropriate display becomes possible. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the fitting image display unit may be performed using AI, or not using AI. For example, the fitting image display unit can input user emotion data into the generative AI and have the generative AI adjust the display method of the fitting images.

[0128] The fitting image display unit can analyze the user's past fitting history and select the optimal display method when displaying fitting images. For example, the fitting image display unit can provide highly relevant fitting images based on items the user has tried on in the past. The fitting image display unit can also prioritize providing fitting images of specific brands or categories based on the user's past fitting history. Furthermore, the fitting image display unit can analyze the user's past fitting history and select the most suitable fitting image. This improves the efficiency of fitting images by providing the optimal display method based on the user's past fitting history. Specific methods and criteria for analyzing past fitting history include, but are not limited to, the types of items tried on and the number of times they were tried on. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's past fitting history data into a generating AI and have the generating AI select the display method.

[0129] The fitting image display unit can estimate the user's emotions and determine the priority of fitting images based on the estimated emotions. For example, if the user is feeling stressed, the fitting image display unit will prioritize providing important fitting images. It can also prioritize providing detailed fitting images if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize providing minimal fitting images. This allows for more appropriate fitting images by prioritizing them according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the fitting image display unit may be performed using AI, or not. For example, the fitting image display unit can input user emotion data into a generative AI and have the generative AI determine the priority of fitting images.

[0130] The fitting image display unit can select the optimal display method when displaying fitting images, taking into account the user's geographical location information. For example, the fitting image display unit can provide highly relevant fitting images based on the user's current location. The fitting image display unit can also select the optimal display method, taking into account the user's geographical location information. Furthermore, the fitting image display unit can filter out unnecessary fitting images based on the user's current location. This makes it possible to display more relevant fitting images by taking into account the user's geographical location information. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's geographical location information into a generating AI and have the generating AI select the display method.

[0131] The fitting image display unit can analyze the user's social media activity and select the optimal display method when displaying fitting images. For example, the fitting image display unit can analyze the user's social media activity and provide relevant fitting images. The fitting image display unit can also select the optimal display method based on the user's social media activity. Furthermore, the fitting image display unit can filter out unnecessary fitting images by considering the user's social media activity. This makes it possible to provide more relevant fitting images by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, the content of posts and the number of likes. Some or all of the above processing in the fitting image display unit may be performed using, for example, AI, or without AI. For example, the fitting image display unit can input the user's social media activity data into a generating AI and have the generating AI select the display method.

[0132] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0133] The shopping support system can estimate the user's emotions and adjust how research results are displayed based on those emotions. For example, if the user is stressed, the research results can be displayed in a concise summary. If the user is relaxed, detailed research results can be provided. Furthermore, if the user is excited, visually appealing research results can be displayed. This allows for a more appropriate shopping experience by providing research results that are tailored to the user's emotions. Emotion estimation is performed using, for example, an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI or not. For example, the research unit can input user emotion data into the generative AI and have the generative AI adjust how the research results are displayed.

[0134] The shopping support system can analyze a user's past purchase history and select the optimal research algorithm. For example, it can analyze trends in items a user has purchased in the past and prioritize researching highly relevant items. It can also prioritize researching items from specific brands or categories based on the user's past purchase history. Furthermore, it can analyze the user's past purchase history and select the most suitable research algorithm. This improves research efficiency by providing the optimal research algorithm based on the user's past purchase history. Specific methods and criteria for analyzing past purchase history include, but are not limited to, purchase frequency and purchase amount. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input the user's past purchase history data into a generating AI and have the generating AI select a research algorithm.

[0135] The shopping support system can customize research results based on the user's current lifestyle. For example, it can prioritize researching items that are highly relevant to the user's current lifestyle. It can also customize research results according to the user's lifestyle. Furthermore, it can filter out unnecessary items based on the user's current lifestyle. This allows for the provision of more relevant research results by customizing them based on the user's current lifestyle. Specific methods for identifying the current lifestyle include, but are not limited to, survey results and social media activity. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input user lifestyle data into a generating AI and have the generating AI perform the customization of research results.

[0136] The shopping support system can estimate the user's emotions and adjust the content of notifications based on those emotions. For example, if the user is stressed, it can provide a concise notification. If the user is relaxed, it can provide a more detailed notification. Furthermore, if the user is in a hurry, it can prioritize important notifications. This allows for more appropriate notifications by providing content tailored to the user's emotions. Emotion estimation is performed using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI or multimodal generation AI. Some or all of the processing described above in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into the generative AI and have the generative AI adjust the notification content.

[0137] The shopping support system can provide research results while taking the user's geographical location into consideration. For example, it can prioritize researching highly relevant items based on the user's current location. It can also provide optimal research results while considering the user's geographical location. Furthermore, it can filter out unnecessary items based on the user's current location. This allows for the provision of more relevant research results by considering the user's geographical location. Specific methods and criteria for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. Some or all of the above processing in the research unit may be performed using AI or not. For example, the research unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing research results.

[0138] The shopping support system can estimate the user's emotions and adjust the feedback collection method based on the estimated emotions. For example, if the user is stressed, it can provide a concise feedback form. If the user is relaxed, it can provide a more detailed feedback form. Furthermore, if the user is in a hurry, it can prioritize voice input and collect feedback quickly. This allows for more appropriate feedback by providing feedback collection methods tailored to the user's emotions. Emotion estimation is performed using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can input user emotion data into the generative AI and have the generative AI adjust the feedback collection method.

[0139] The shopping support system can analyze a user's social media activity and provide relevant research results. For example, it can analyze a user's social media activity and prioritize researching highly relevant items. It can also provide optimal research results based on the user's social media activity. Furthermore, it can filter out unnecessary items by considering the user's social media activity. This allows for the provision of more relevant research results by analyzing the user's social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, posts and the number of likes. Some or all of the above processing in the research department may be performed using AI or not. For example, the research department can input user social media activity data into a generating AI and have the generating AI provide research results.

[0140] The shopping support system can estimate the user's emotions and adjust the display method of try-on images based on the estimated emotions. For example, if the user is relaxed, it can provide detailed try-on images. If the user is in a hurry, it can provide concise try-on images. Furthermore, if the user is excited, it can provide visually stimulating try-on images. By providing a try-on image display method that corresponds to the user's emotions, more appropriate try-on images can be found. Emotion estimation is performed using an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the try-on image display unit may be performed using AI or not. For example, the try-on image display unit can input user emotion data into the generative AI and have the generative AI adjust the try-on image display method.

[0141] The shopping support system can analyze a user's past feedback history and select the most suitable improvement method. For example, it can suggest highly relevant improvement methods based on feedback the user has provided in the past. It can also prioritize suggesting improvement methods for specific categories based on the user's past feedback history. Furthermore, it can analyze the user's past feedback history and select the most appropriate improvement method. This improves the efficiency of suggestions by providing the most suitable improvement method based on the user's past feedback history. The specific methods and criteria for analyzing past feedback history include, but are not limited to, the content and frequency of the feedback. Some or all of the above processing in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input the user's past feedback history data into a generating AI and have the generating AI select improvement methods.

[0142] The shopping support system can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is stressed, important suggestions can be prioritized. If the user is relaxed, detailed suggestions can be prioritized. Furthermore, if the user is in a hurry, minimal suggestions can be prioritized. By prioritizing suggestions according to the user's emotions, more appropriate suggestions can be made. Emotion estimation is performed using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the suggestion improvement unit may be performed using AI or not. For example, the suggestion improvement unit can input user emotion data into the generative AI and have the generative AI determine the priority of suggestions.

[0143] The following briefly describes the processing flow for example form 2.

[0144] Step 1: The reception desk enters the user's photo and personal information. This includes a facial photograph, body measurements, and past purchase history. For example, the reception desk scans the user's facial photograph at high resolution and saves it as digital data. It can also measure the user's body measurements and save them as digital data. Furthermore, it can retrieve and save the user's past purchase history from a database. Step 2: The research department researches clothing and accessories that suit the user based on the information entered by the reception department. For example, the research department searches the database of online shopping sites to find the most suitable items for the user. The research department can also use AI to select the most suitable items by considering the user's preferences and past purchase history. Furthermore, it is possible to conduct research using text generation AI and multimodal generation AI. Step 3: The Additions section adds items researched by the Research section to the cart. For example, it can automatically add researched items to the cart. The Additions section can also use AI to add clothes and accessories that it determines would suit the user to the cart. Step 4: The notification unit will send notifications on sale days and discount days. For example, it will collect sale information and notify users. The notification unit can also use AI to collect sale information and notify users via push notifications or email. Step 5: The feedback collection team collects feedback on items that were not purchased. For example, user feedback can be collected through surveys or reviews. Step 6: The proposal improvement unit improves future proposals based on the feedback collected by the feedback collection unit. For example, it analyzes the collected feedback and improves future proposals. The proposal improvement unit can also use AI to analyze the collected feedback and improve future proposals. Step 7: The fitting image display unit shows the avatar trying on the clothes. For example, the AI ​​generates the user's avatar and displays an image of the selected items being tried on. The fitting image display unit can also use a multimodal generation AI to generate the user's avatar and display an image of the selected items being tried on.

[0145] 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.

[0146] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0147] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the reception unit, research unit, addition unit, notification unit, feedback collection unit, suggestion improvement unit, and try-on image display unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14, which inputs the user's photo and personal information. The research unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which researches clothes and accessories that suit the user. The addition unit is implemented, for example, by the control unit 46A of the smart device 14, which adds the researched items to the cart. The notification unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which sends notifications on sale days and discount days. The feedback collection unit is implemented, for example, by the reception device 38 of the smart device 14, which collects feedback on items that were not purchased. The suggestion improvement unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which improves suggestions for the next time based on the collected feedback. The fitting image display unit is implemented, for example, by the output device 40 of the smart device 14, and the avatar displays the fitting image. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0150] 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.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0152] 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.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0154] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] 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.

[0156] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] 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.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the reception unit, research unit, addition unit, notification unit, feedback collection unit, suggestion improvement unit, and try-on image display unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the smart glasses 214, which inputs the user's photo and personal information. The research unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which researches clothes and accessories that suit the user. The addition unit is implemented, for example, by the control unit 46A of the smart glasses 214, which adds the researched items to the cart. The notification unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which provides notifications on sale days and discount days. The feedback collection unit is implemented, for example, by the microphone 238 of the smart glasses 214, which collects feedback on items that were not purchased. The suggestion improvement unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which improves suggestions for future purchases based on the collected feedback. The fitting image display unit is implemented, for example, by the speaker 240 of the smart glasses 214, and the avatar displays the fitting image. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0165] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0166] 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.

[0167] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0168] 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.

[0169] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0170] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0171] 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.

[0172] 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.

[0173] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0174] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0175] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0176] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0177] 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.

[0178] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0179] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0180] Each of the multiple elements described above, including the reception unit, research unit, addition unit, notification unit, feedback collection unit, suggestion improvement unit, and try-on image display unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and takes the user's photo and personal information. The research unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and researches clothes and accessories that suit the user. The addition unit is implemented by, for example, the control unit 46A of the headset terminal 314 and adds the researched items to the cart. The notification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and sends notifications on sale days and discount days. The feedback collection unit is implemented by, for example, the microphone 238 of the headset terminal 314 and collects feedback on items that were not purchased. The suggestion improvement unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and improves suggestions for the next time based on the collected feedback. The fitting image display unit is implemented, for example, by the display 343 of the headset terminal 314, where the avatar displays the fitting image. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0181] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0182] 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.

[0183] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0184] 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.

[0185] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0186] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0187] 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.

[0188] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0189] 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.

[0190] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0191] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0192] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0193] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0194] 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.

[0195] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0196] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0197] Each of the multiple elements described above, including the reception unit, research unit, addition unit, notification unit, feedback collection unit, suggestion improvement unit, and try-on image display unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the robot 414, which inputs the user's photo and personal information. The research unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which researches clothes and accessories that suit the user. The addition unit is implemented by, for example, the control unit 46A of the robot 414, which adds the researched items to the cart. The notification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which provides notifications on sale days and discount days. The feedback collection unit is implemented by, for example, the microphone 238 of the robot 414, which collects feedback on items that were not purchased. The suggestion improvement unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which improves suggestions for future purchases based on the collected feedback. The fitting image display unit is implemented, for example, by the speaker 240 of robot 414, and the avatar displays the fitting image. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0198] 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.

[0199] Figure 9 shows the 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.

[0200] 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.

[0201] 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.

[0202] 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, and motorcycles, 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 based, for example, 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.

[0203] 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."

[0204] 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.

[0205] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0214] 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 other things 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.

[0215] 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.

[0216] (Note 1) The reception area where users enter their photos and personal information, Based on the information entered by the reception department, the research department researches clothing and accessories that suit the user, An addition unit that adds items researched by the aforementioned research unit to the cart, A notification unit that sends out notifications on sale days and discount days, A feedback collection department that collects feedback on items that were not purchased, Based on the feedback collected by the aforementioned feedback collection unit, the proposal improvement unit improves subsequent proposals, It includes a fitting image display unit that shows an avatar trying on clothes. A system characterized by the following features. (Note 2) The aforementioned reception unit is Enter your profile picture, body type information, past purchase history, etc. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned research department, Search the database of online shopping sites to research the best items for the user. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned additional part is, Add researched items to cart The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, Collect sales information and notify users. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned feedback collection unit is Collect user feedback. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proposed improvement unit is We will use the collected feedback to improve future proposals. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned fitting image display unit is The avatar shows how it looks when you try it on. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of photo and personal information input based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is Analyze the user's past purchase history and select the optimal method for inputting information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When users input information, filtering is performed based on their current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is It estimates the user's emotions and prioritizes the information to be entered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When entering information, the system prioritizes inputting highly relevant information, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When entering information, the system analyzes the user's social media activity and inputs relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned research department, We estimate user sentiment and adjust the research presentation based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned research department, During research, adjust the level of detail based on the importance of the items. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned research department, During research, different research algorithms are applied depending on the item category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned research department, We estimate user sentiment and adjust the length of the research based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned research department, During research, prioritize research based on when items are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned research department, When conducting research, adjust the order of research based on the relevance of the items. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned additional part is, It estimates the user's emotions and determines the priority of items to add to the cart based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned additional part is, When adding items, the system analyzes the user's past purchase history to select the most suitable items. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned additional part is, When adding an item, customize the item based on the user's current lifestyle. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned additional part is, It estimates the user's emotions and adjusts how items are displayed in the cart based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned additional part is, When adding items, the system selects the most suitable items by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned additional part is, When adding items, the system analyzes the user's social media activity to suggest items. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, It estimates the user's emotions and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, When sending a notification, the system analyzes the user's past purchase history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, When a notification is sent, the content of the notification will be customized based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, It estimates the user's emotions and prioritizes notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When sending notifications, the system will select the most suitable notification method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, When sending notifications, the system analyzes the user's social media activity to suggest appropriate notification content. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned feedback collection unit is We estimate the user's emotions and adjust the feedback collection method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned feedback collection unit is When collecting feedback, the system analyzes the user's past feedback history to select the optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned feedback collection unit is It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned feedback collection unit is When collecting feedback, the optimal collection method is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned proposed improvement unit is It estimates the user's emotions and adjusts how to improve the suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned proposed improvement unit is When improving a proposal, we analyze the user's past feedback history to select the most suitable improvement method. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned proposed improvement unit is When improving suggestions, customize the suggestions based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned proposed improvement unit is It estimates the user's emotions and determines the priority of suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned proposed improvement unit is When improving a proposal, the optimal improvement method will be selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned proposed improvement unit is When improving a proposal, we analyze users' social media activity to improve the proposal content. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned fitting image display unit is The system estimates the user's emotions and adjusts how the try-on images are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned fitting image display unit is When displaying try-on images, the system analyzes the user's past try-on history to select the optimal display method. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned fitting image display unit is The system estimates the user's emotions and prioritizes the try-on images based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned fitting image display unit is When displaying try-on images, the system selects the optimal display method considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 47) The aforementioned fitting image display unit is When displaying try-on images, the system analyzes the user's social media activity to select the optimal display method. The system according to appended note 1, characterized by the above.

Explanation of symbols

[0217] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims

1. The reception area where users enter their photos and personal information, Based on the information entered by the reception department, the research department researches clothing and accessories that suit the user, An addition unit that adds items researched by the aforementioned research unit to the cart, A notification unit that sends out notifications on sale days and discount days, A feedback collection department that collects feedback on items that were not purchased, Based on the feedback collected by the aforementioned feedback collection unit, the proposal improvement unit improves subsequent proposals, It includes a fitting image display unit that shows an avatar trying on clothes. A system characterized by the following features.

2. The aforementioned reception unit is Enter your profile picture, body type information, past purchase history, etc. The system according to feature 1.

3. The aforementioned research department, Search the database of online shopping sites to research the best items for the user. The system according to feature 1.

4. The aforementioned additional part is, Add researched items to cart The system according to feature 1.

5. The aforementioned notification unit, Collect sales information and notify users. The system according to feature 1.

6. The aforementioned feedback collection unit is Collect user feedback. The system according to feature 1.

7. The aforementioned proposed improvement unit is We will use the collected feedback to improve future proposals. The system according to feature 1.

8. The aforementioned fitting image display unit is The avatar shows how it looks when you try it on. The system according to feature 1.

9. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of photo and personal information input based on those estimated emotions. The system according to feature 1.

10. The aforementioned reception unit is Analyze the user's past purchase history and select the optimal method for inputting information. The system according to feature 1.

Images