system

Abstract

The system according to this embodiment aims to propose the optimal coordination that meets the customer's needs. [Solution] The system according to the embodiment comprises a learning unit, a tuning unit, a reception unit, a selection unit, a dialogue unit, and a generation unit. The learning unit learns coordination information. The tuning unit periodically performs tuning based on the information learned by the learning unit. The reception unit receives user searches. The selection unit selects the most suitable staff based on the information received by the reception unit. The dialogue unit interacts with the user based on the data of the staff selected by the selection unit. The generation unit generates and proposes coordination based on the information obtained by the dialogue unit.

Description

Technical Field

[0004]

[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, even when a customer visits a store, there is not always a staff member who matches the customer's sense, and there is a problem that it is difficult to sufficiently meet the customer's needs.

[0005] The system according to the embodiment aims to propose an optimal coordination that matches the needs of customers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a tuning unit, a reception unit, a selection unit, a dialogue unit, and a generation unit. The learning unit learns coordination information. The tuning unit periodically performs tuning based on the information learned by the learning unit. The reception unit receives user searches. The selection unit selects the most suitable staff based on the information received by the reception unit. The dialogue unit interacts with the user based on the data of the staff selected by the selection unit. The generation unit generates and proposes coordination based on the information obtained by the dialogue unit. [Effects of the Invention]

[0007] The system according to this embodiment can propose the optimal coordination that meets the customer's needs. [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 signed storage is one or more non-volatile storage devices that store various programs and various parameters. 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 labeled 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the 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) The AI-powered styling agent "Sense Partner: Style Genius" according to an embodiment of the present invention is a system designed to solve the problem that customers may not always find staff who match their sense of style at the stores they visit. This system uses AI to learn styling information registered by actual popular staff members and periodically enhances the AI's tuning through A / B testing with staff members. Users search by size and desired atmosphere, the AI ​​selects the most suitable staff member, and based on that data, the user and AI engage in dialogue to refine the details and generate and propose a styling plan. This mechanism allows for accurate capture of customer needs and improved staff motivation in professions requiring aesthetic sense, such as interior design, fashion, and flower arranging. For example, the AI ​​learns styling information registered by actual popular staff members. In this process, the AI ​​analyzes diverse styling information to understand each staff member's sense of style. For example, in fashion, it learns about color combinations and how to choose items. This allows the AI ​​to propose styling plans based on each staff member's sense of style. Next, the AI's tuning is periodically enhanced through A / B testing with staff members. Staff members provide their own styling plans to the AI ​​and compare them with the suggestions generated by the AI ​​to improve the AI's accuracy. For example, in interior design, the AI ​​evaluates furniture placement and color balance to improve its suggestions. This allows the AI ​​to always provide suggestions that reflect the latest trends and sensibilities. Users search by size and desired atmosphere. For example, in fashion, a user might search for "casual style, size M outfit." Based on this information, the AI ​​selects the most suitable staff member, and using that data as a basis, the user and AI engage in dialogue to refine the details and generate a suggested outfit. For example, if a user requests "brighter colors," the AI ​​will suggest an outfit that meets that request. This allows customers to receive outfits that match their sense of style, and also improves staff motivation. For example, staff members can feel a sense of accomplishment when their own sense of style is reflected in the AI's suggestions.Furthermore, customers can easily request styling services from the comfort of their homes without having to visit a store. In this way, the AI ​​styling agent "Sense Partner: Style Genius" accurately grasps customer needs and improves staff motivation, thereby increasing customer satisfaction in professions that require aesthetic sense, such as interior design, fashion, and flower arranging.

[0029] The AI ​​coordination agent "Sense Partner: Style Genius" according to this embodiment comprises a learning unit, a tuning unit, a reception unit, a selection unit, a dialogue unit, and a generation unit. The learning unit learns coordination information. For example, the learning unit learns coordination information registered by actual popular staff members. The learning unit uses AI to analyze diverse coordination information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. As a result, the learning unit can propose coordinations based on the sense of each staff member. The tuning unit periodically tunes the AI ​​based on the information learned by the learning unit. For example, the tuning unit strengthens the tuning of the AI ​​through A / B testing with staff members. Staff members provide their own coordinations to the AI ​​and improve the accuracy of the AI ​​by comparing them with the suggestions generated by the AI. For example, in interior design, they evaluate the placement of furniture and the balance of colors to improve the AI's suggestions. As a result, the tuning unit can always make suggestions that reflect the latest trends and sense of style. The reception unit accepts user searches. The reception department receives information such as the user's search criteria, such as size and desired style. For example, in fashion, the user might search for "casual style, size M outfit." The selection department selects the most suitable staff based on the information received by the reception department. The selection department selects the most suitable staff based on the user's search information. The selection department uses AI to select the staff best suited to the user's needs. The dialogue department interacts with the user based on the data of the staff selected by the selection department. The dialogue department, for example, has the user and AI interact to refine the details and generate and propose outfits. For example, if the user requests "brighter colors," the dialogue department will propose outfits that meet that request. The generation department generates and proposes outfits based on the information obtained by the dialogue department. The generation department generates and proposes outfits that meet the user's requests.As a result, the AI-powered coordination agent "Sense Partner: Style Genius" according to this embodiment can accurately grasp customer needs and improve staff motivation.

[0030] The learning unit learns about outfit coordination information. For example, the learning unit learns about outfit coordination information registered by actual popular staff members. Specifically, the learning unit uses AI to analyze diverse outfit coordination information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. This allows the learning unit to propose outfit coordination based on each staff member's sense. The learning unit uses image recognition technology and natural language processing technology to analyze image and text data of outfit coordination. For example, it uses image recognition technology to extract features such as color, shape, and material from outfit images, and uses natural language processing technology to understand style and theme from text data related to outfit coordination. Furthermore, based on past outfit coordination data, the learning unit can grasp the changes in trends and seasonal trends, and make suggestions that reflect the latest fashion trends. This allows the learning unit to provide outfit coordination that meets the diverse needs of users and improve customer satisfaction.

[0031] The tuning unit periodically tunes the AI ​​based on the information learned by the learning unit. The tuning unit enhances the AI's tuning through methods such as A / B testing with staff. Specifically, staff provide the AI ​​with their own coordination ideas and compare them to the suggestions generated by the AI ​​to improve its accuracy. For example, in interior design, staff evaluate furniture placement and color balance to improve the AI's suggestions. The tuning unit adjusts the AI's learning algorithm and parameters to achieve more accurate coordination suggestions. For example, they optimize the number of layers and nodes in the AI's neural network and adjust the batch size and learning rate of the training data to improve the AI's performance. The tuning unit also collects user feedback and uses it as data to improve the AI's suggestions. This allows the tuning unit to always provide suggestions that reflect the latest trends and sensibilities, thereby increasing user satisfaction. Furthermore, the tuning unit regularly evaluates the AI's performance and maintains high accuracy by retraining or updating the model as needed.

[0032] The reception desk receives user searches. For example, it receives information such as the size and desired style of the user's search. Specifically, in the fashion category, a user might search for "casual style, size M outfit." The reception desk uses natural language processing technology to analyze the user's input information and provide appropriate search results. For example, it analyzes the text entered by the user and extracts keywords and intent. In addition, the reception desk can provide personalized suggestions to each user based on their past search and purchase history. This allows the reception desk to provide search results that meet the user's needs quickly and accurately, improving user convenience. Furthermore, the reception desk is designed to allow users to easily input search criteria through its user interface, enabling intuitive operation. This improves the user's search experience and makes the system more widely used by more users.

[0033] The selection department chooses the most suitable staff based on the information received by the reception department. For example, the selection department selects the most suitable staff based on the user's search information. Specifically, the selection department uses AI to select the staff best suited to the user's needs. The selection department considers the staff's past coordination experience, evaluations, and areas of expertise to select the staff best suited to the user's request. For example, it selects staff who excel in casual styles or staff who are knowledgeable about specific brands, etc., according to the user's needs. By using an AI recommendation system to match the user's search criteria with staff profiles, the selection department can quickly select the most suitable staff. This allows the selection department to provide users with high-quality coordination suggestions and improve user satisfaction. Furthermore, the selection department can enhance trust by ensuring transparency in the selection process and explaining the reasons for the selection to the user.

[0034] The dialogue unit interacts with users based on data from staff selected by the selection unit. For example, the dialogue unit interacts with the user and AI to refine the details and generate and propose coordinated outfits. Specifically, if a user requests "I want to use brighter colors," the dialogue unit will propose a coordinated outfit that meets that request. The dialogue unit uses natural language processing technology to understand user requests and generate appropriate responses. For example, it collects detailed requests such as the user's desired colors, style, and budget through dialogue and proposes the optimal coordinated outfit based on that. Through dialogue with users, the dialogue unit can deeply understand the user's preferences and needs and make more personalized suggestions. This allows the dialogue unit to facilitate communication with users and improve user satisfaction. Furthermore, the dialogue unit saves the dialogue history and uses it for future suggestions, enabling it to continuously make suggestions that reflect the user's preferences.

[0035] The generation unit generates and proposes outfits based on information obtained from the dialogue unit. For example, the generation unit generates and proposes outfits that meet the user's requests. Specifically, the generation unit uses AI to generate outfits that reflect the user's requests and the taste of selected staff. The generation unit utilizes image generation technology and style transfer technology to generate images of outfits that meet the user's requests. For example, it generates images of outfits that reflect the colors and styles desired by the user and proposes them to the user visually. Based on the generated outfit images, the generation unit can also provide a list of items that the user can actually purchase. This allows the generation unit to make concrete outfit suggestions to the user and increase the user's desire to purchase. Furthermore, the generation unit can improve the accuracy of its suggestions by collecting evaluations of the generated outfits and using them as training data for the AI. This allows the generation unit to always provide high-quality outfit suggestions that reflect the latest trends and user preferences.

[0036] The learning unit can learn from the outfit information registered by actual popular staff members. For example, the learning unit learns from the outfit information registered by actual popular staff members. The learning unit uses AI to analyze diverse outfit information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. As a result, the learning unit can propose outfits based on the sense of each staff member. This allows it to propose outfits that reflect the sense of actual popular staff members. Popular staff members are defined by criteria such as customer ratings, sales performance, and number of followers. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input outfit information registered by actual popular staff members into a generating AI and have the generating AI learn from it.

[0037] The tuning department can periodically enhance the AI's tuning through A / B testing with staff. For example, the tuning department enhances the AI's tuning through A / B testing with staff. Staff provide their own coordinations to the AI ​​and compare them with the suggestions generated by the AI ​​to improve its accuracy. For example, in interior design, staff evaluate furniture placement and color balance to improve the AI's suggestions. This allows the tuning department to always provide suggestions that reflect the latest trends and sensibilities. This improves the AI's accuracy and allows it to provide suggestions that reflect the latest trends and sensibilities. A / B testing is conducted based on criteria such as test setup, evaluation criteria, and result analysis methods. Some or all of the above processes in the tuning department may be performed using AI or not. For example, the tuning department can input coordination information provided by staff into the generating AI and have the generating AI perform tuning.

[0038] The reception desk can receive information from users searching by size and desired style. For example, in fashion, a user might search for "casual style, size M outfit." This allows for searches tailored to the user's specific needs. Size is defined by size notation such as S, M, L, XL, etc. Style is defined by criteria such as casual, formal, elegant, etc. 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 the search information entered by the user into a generating AI, and have the generating AI generate search results.

[0039] The selection unit can select the most suitable staff based on the information received by the reception unit. For example, the selection unit can select the most suitable staff based on the user's search information. The selection unit can use AI to select the most suitable staff for the user's needs. This allows for the selection of staff best suited to the user's needs. The most suitable staff are selected based on criteria such as skill set, past performance, and customer ratings. Some or all of the above processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's search information into a generating AI and have the generating AI select the most suitable staff.

[0040] The dialogue unit can interact with users based on data of staff selected by the selection unit. For example, the dialogue unit can have a conversation with the user and an AI to refine the details and generate a coordinated outfit proposal. If, for example, the user requests "I want to use brighter colors," the dialogue unit will propose an outfit that meets that request. In this way, the user and the AI ​​can interact, refine the details, and generate a coordinated outfit proposal. The staff data consists of, for example, information such as career history, skills, and past achievements. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the data of staff selected by the selection unit into a generating AI and have the generating AI generate the dialogue content.

[0041] The generation unit can generate and propose outfits based on the information obtained by the dialogue unit. For example, the generation unit can generate and propose outfits that meet the user's requests. This allows the generation unit to generate and propose outfits that meet the user's requests. The outfits consist of, for example, clothing combinations, color balance, and accessory selection. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input the information obtained by the dialogue unit into a generation AI, causing the generation AI to generate outfits.

[0042] The learning unit can improve the accuracy of its learning by analyzing each staff member's past success and failure cases during the learning process. For example, the learning unit can analyze each staff member's success cases, extract common elements, and learn from them. For example, the learning unit can analyze each staff member's failure cases, identify areas for improvement, and learn from them. For example, the learning unit can compare success and failure cases, identify factors for success, and learn from them. In this way, the accuracy of learning can be improved by analyzing each staff member's past cases. Success and failure cases are defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input each staff member's past success and failure cases into a generating AI and have the generating AI analyze them.

[0043] The learning unit can dynamically update its learning content in response to changes in seasons and trends during the learning process. For example, the learning unit can collect seasonal trend information and reflect it in its learning content. For example, the learning unit can periodically update its learning content in response to changes in trends. For example, the learning unit can prioritize learning coordination information that is appropriate for the season and trends. This makes it possible to update the learning content in response to changes in seasons and trends. Seasons and trends are defined by criteria such as the four seasons (spring, summer, autumn, and winter) and fashion trends. Some or all of the above-described processes in the learning unit may be performed using AI or not. For example, the learning unit can input seasonal and trend information into a generating AI and have the generating AI dynamically update its learning content.

[0044] The learning unit can incorporate coordination information from different cultural spheres and regions to add diversity to the learning process. For example, the learning unit can collect coordination information from different cultural spheres and reflect it in the learning content. For example, the learning unit can collect trend information from different regions and reflect it in the learning content. For example, the learning unit can analyze successful case studies from different cultural spheres and regions and reflect them in the learning content. This allows for diversity by incorporating coordination information from different cultural spheres and regions. Different cultural spheres and regions can be defined by criteria such as country, region, or cultural background. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input coordination information from different cultural spheres and regions into a generating AI and train the generating AI.

[0045] The learning unit can learn customized coordination information based on the user's lifestyle and occupation during the learning process. For example, the learning unit can collect coordination information according to the user's lifestyle and reflect it in the learning content. For example, the learning unit can collect coordination information according to the user's occupation and reflect it in the learning content. For example, the learning unit can analyze successful cases based on the user's lifestyle and occupation and reflect them in the learning content. This allows the learning unit to learn coordination information according to the user's lifestyle and occupation. Lifestyle and occupation are defined by criteria such as daily activities, work content, and hobbies. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input coordination information based on the user's lifestyle and occupation into a generating AI and have the generating AI learn from it.

[0046] The tuning unit can reflect staff feedback in real time during tuning, instantly improving the accuracy of the AI. For example, the tuning unit can reflect feedback provided by staff in real time and improve the AI's suggestions. For example, the tuning unit can analyze staff feedback and instantly update the AI's learning content. For example, the tuning unit can adjust the AI's tuning parameters based on staff feedback. This allows for instant improvement of the AI's accuracy by reflecting staff feedback in real time. Real time is defined by criteria such as seconds, minutes, or instant reflection. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input staff feedback into the generating AI and reflect it in the generating AI in real time.

[0047] The tuning unit can compare the AI's suggestions with the actual results during tuning, analyze the differences, and identify areas for improvement. For example, the tuning unit can compare the AI's suggestions with the actual results, analyze the differences, and identify areas for improvement. For example, the tuning unit can identify the cause of the differences and update the AI's learning content. For example, the tuning unit can analyze the differences and adjust the AI's tuning parameters. This allows the AI ​​to analyze the differences and identify areas for improvement by comparing the AI's suggestions with the actual results. The differences are defined by criteria such as the difference between the suggested content and the actual results, and the method of identifying areas for improvement. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input the AI's suggestions and actual results into a generating AI and have the generating AI analyze the differences.

[0048] The tuning unit can enhance the versatility of the AI ​​by referencing coordination information from different industries during the tuning process. For example, the tuning unit can collect coordination information from different industries and reflect it in the tuning process. For example, the tuning unit can analyze successful case studies from different industries and reflect them in the tuning process. For example, the tuning unit can collect trend information from different industries and reflect it in the tuning process. This allows the versatility of the AI ​​to be enhanced by referencing coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-described processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input coordination information from different industries into the generating AI and have the generating AI refer to it.

[0049] The tuning unit can evaluate user satisfaction with AI suggestions during tuning and perform tuning based on that satisfaction level. For example, the tuning unit can evaluate user satisfaction and adjust the tuning based on that satisfaction level. For example, the tuning unit can collect user feedback and update the tuning based on that satisfaction level. For example, the tuning unit can analyze user satisfaction and adjust the tuning parameters. By tuning based on user satisfaction, the accuracy of AI suggestions can be improved. Satisfaction is defined by criteria such as surveys, feedback evaluations, and NPS scores. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input user satisfaction data into a generating AI and have the generating AI evaluate it.

[0050] The reception desk can suggest optimal search conditions by referring to the user's past search history at the time of reception. For example, the reception desk can analyze the user's past search history and suggest optimal search conditions. For example, the reception desk can suggest optimal search conditions based on the conditions the user has searched for in the past. For example, the reception desk can customize search conditions by referring to the user's past search history. In this way, it is possible to suggest optimal search conditions by referring to the user's past search history. Search history is defined by criteria such as past search keywords, search date and time, and search results. 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 the user's past search history into a generating AI and have the generating AI suggest optimal search conditions.

[0051] The reception unit can analyze the user's input in real time and present appropriate search suggestions. For example, the reception unit can analyze the user's input in real time and present appropriate search suggestions. For example, the reception unit can present the optimal search suggestions based on the user's input. For example, the reception unit can analyze the user's input and customize the search suggestions. This allows the reception unit to present appropriate search suggestions by analyzing the user's input in real time. Search suggestions are defined by criteria such as related keywords, suggestion functions, and autocomplete. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's input into a generating AI and have the generating AI analyze it in real time.

[0052] The reception unit can provide the optimal interface at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception unit will provide an interface optimized for smartphones. For example, if the user is using a tablet, the reception unit will provide an interface optimized for tablets. For example, if the user is using a desktop, the reception unit will provide an interface optimized for desktops. This allows the reception unit to provide an interface tailored to the user's device information. Device information is defined by criteria such as device type, OS, browser, and screen size. Some or all of the processing described above in the reception unit may be performed using AI or not. For example, the reception unit can input the user's device information into a generating AI and have the generating AI provide the optimal interface.

[0053] The reception desk can analyze the user's social media activity and suggest relevant search criteria upon receiving the request. For example, the reception desk can analyze the user's social media activity and suggest relevant search criteria. For example, the reception desk can suggest search criteria based on the content the user has shown interest in on social media. For example, the reception desk can customize search criteria based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to suggest relevant search criteria. Social media activity is defined by criteria such as post content, number of likes, and number of followers. 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 the user's social media activity into a generating AI and have the generating AI analyze it.

[0054] The selection unit can select the most suitable staff member by referring to their past performance data during the selection process. For example, the selection unit can analyze the staff member's past performance data to select the most suitable staff member. For example, the selection unit can select the most suitable staff member based on their success stories. For example, the selection unit can analyze their failure stories, identify areas for improvement, and select the most suitable staff member. In this way, the most suitable staff member can be selected by referring to their past performance data. Performance data is defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the staff member's past performance data into a generating AI and have the generating AI analyze it.

[0055] The selection unit can select the most suitable staff by comparing the user's current needs with their past preferences during the selection process. For example, the selection unit can analyze the user's current needs and select the most suitable staff by comparing them with their past preferences. For example, the selection unit can select staff that meet the user's current needs based on their past preferences. For example, the selection unit can make a comprehensive judgment on the user's current needs and past preferences to select the most suitable staff. In this way, the most suitable staff can be selected by comparing the user's current needs with their past preferences. Current needs and past preferences are defined by criteria such as current trends, past purchase history, and customer preferences. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's current needs and past preferences into a generating AI and have the generating AI compare them.

[0056] The selection unit can conduct a multifaceted selection process by referencing experts from different industries. For example, the selection unit can collect opinions from experts in different industries and reflect them in the selection process. For example, the selection unit can analyze success stories from different industries and reflect them in the selection process. For example, the selection unit can collect trend information from different industries and reflect it in the selection process. This allows for a multifaceted selection process by referencing experts from different industries. Experts from different industries are defined by criteria such as, for example, fashion designers, marketing experts, and technology consultants. Some or all of the processes described above in the selection unit may be performed using AI or not. For example, the selection unit can input opinions from experts in different industries into a generating AI and have the generating AI refer to them.

[0057] The selection unit can select the most suitable staff member by considering the user's geographical location information during the selection process. For example, the selection unit can select the most suitable staff member based on the user's geographical location information. For example, the selection unit can prioritize selecting nearby staff members by considering the user's geographical location information. For example, the selection unit can select staff members that reflect region-specific trends by referring to the user's geographical location information. In this way, the most suitable staff member can be selected by considering the user's geographical location information. Geographical location information is defined by criteria such as the user's address, current location, and regional characteristics. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's geographical location information into a generating AI and have the generating AI consider it.

[0058] The dialogue unit can provide optimal dialogue content by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can analyze the user's past dialogue history and provide optimal dialogue content. For example, the dialogue unit can provide optimal dialogue content based on the content of past conversations the user has had. For example, the dialogue unit can customize the dialogue content by referring to the user's past dialogue history. In this way, by referring to the user's past dialogue history, it is possible to provide optimal dialogue content. Dialogue history is defined by criteria such as past dialogue content, the date and time of the dialogue, and the result of the dialogue. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's past dialogue history into a generating AI and have the generating AI provide optimal dialogue content.

[0059] The dialogue unit can analyze the user's real-time responses during a conversation and dynamically change the content of the conversation. For example, the dialogue unit can analyze the user's real-time responses and dynamically change the content of the conversation. For example, the dialogue unit can customize the content of the conversation based on the user's responses. For example, the dialogue unit can adjust the content of the conversation based on the user's real-time responses. In this way, the content of the conversation can be dynamically changed by analyzing the user's real-time responses. Real-time responses are defined by criteria such as facial recognition, voice analysis, and behavioral analysis. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's real-time responses into a generating AI and have the generating AI analyze them.

[0060] The dialogue unit can provide dialogue content that corresponds to different languages ​​and cultures during a conversation. For example, the dialogue unit provides dialogue content based on the user's language settings. For example, the dialogue unit provides dialogue content that corresponds to different cultures. For example, the dialogue unit customizes the dialogue content according to the user's language and culture. This makes it possible to provide dialogue content that corresponds to different languages ​​and cultures. Different languages ​​and cultures are defined by criteria such as multilingual support, consideration of cultural background, and localization. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's language settings and cultural information into a generating AI and have the generating AI respond accordingly.

[0061] The dialogue unit can analyze the user's social media activity during a conversation and provide relevant dialogue content. For example, the dialogue unit can analyze the user's social media activity and provide relevant dialogue content. For example, the dialogue unit can provide dialogue content based on what the user has shown interest in on social media. For example, the dialogue unit can customize dialogue content based on the user's social media activity. In this way, by analyzing the user's social media activity, it can provide relevant dialogue content. Social media activity is defined by criteria such as post content, number of likes, and number of followers. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's social media activity into a generating AI and have the generating AI analyze it.

[0062] The generation unit can make optimal suggestions by referring to the user's past coordination history during generation. For example, the generation unit analyzes the user's past coordination history and makes optimal suggestions. For example, the generation unit makes optimal suggestions based on the coordinations the user has previously selected. For example, the generation unit customizes the suggested content by referring to the user's past coordination history. In this way, optimal suggestions can be made by referring to the user's past coordination history. Coordination history is defined by criteria such as the content of past coordinations, the date and time of coordination, and evaluation. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input the user's past coordination history into a generation AI and have the generation AI make optimal suggestions.

[0063] The generation unit can dynamically update the generated content in accordance with seasonal and trend changes during generation. For example, the generation unit collects seasonal trend information and reflects it in the generated content. For example, the generation unit periodically updates the generated content in accordance with trend changes. For example, the generation unit prioritizes generating coordination information according to the season and trend. This makes it possible to update the generated content in accordance with seasonal and trend changes. Seasons and trends are defined by criteria such as the four seasons (spring, summer, autumn, winter) and fashion trends. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input seasonal and trend information into a generation AI and cause the generation AI to dynamically update the generated content.

[0064] The generation unit can incorporate coordination information from different industries during the generation process to ensure diversity. For example, the generation unit can collect coordination information from different industries and reflect it in the generated content. For example, the generation unit can analyze successful case studies from different industries and reflect them in the generated content. For example, the generation unit can collect trend information from different industries and reflect it in the generated content. This allows for diversity by incorporating coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input coordination information from different industries into a generation AI and have the generation AI incorporate it.

[0065] The generation unit can generate customized outfits based on the user's lifestyle and occupation during the generation process. For example, the generation unit can generate outfits that match the user's lifestyle. For example, the generation unit can generate outfits that match the user's occupation. For example, the generation unit can analyze successful examples based on the user's lifestyle and occupation and reflect them in the generated content. This allows the generation unit to generate outfits that match the user's lifestyle and occupation. Lifestyle and occupation are defined by criteria such as daily activities, work content, and hobbies. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input outfit information based on the user's lifestyle and occupation into a generation AI and have the generation AI generate the outfits.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The learning unit can improve the accuracy of its learning by analyzing each staff member's past success and failure cases during the learning process. For example, it can analyze each staff member's success cases, extract common elements, and learn from them. It can also analyze each staff member's failure cases, identify areas for improvement, and learn from them. By comparing success and failure cases, it can identify factors for success and learn from them. In this way, the accuracy of learning can be improved by analyzing each staff member's past cases. Success and failure cases are defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input each staff member's past success and failure cases into a generating AI and have the generating AI analyze them.

[0068] The reception desk can suggest optimal search conditions by referring to the user's past search history at the time of reception. For example, it can analyze the user's past search history and suggest optimal search conditions. It can suggest optimal search conditions based on the conditions the user has searched for in the past. It can customize search conditions by referring to the user's past search history. In this way, it can suggest optimal search conditions by referring to the user's past search history. Search history is defined by criteria such as past search keywords, search date and time, and search results. 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 the user's past search history into a generating AI and have the generating AI suggest optimal search conditions.

[0069] The generation unit can make optimal suggestions by referring to the user's past coordination history during generation. For example, it can analyze the user's past coordination history and make optimal suggestions. It can make optimal suggestions based on the coordinations the user has selected in the past. It can customize the suggested content by referring to the user's past coordination history. This allows for optimal suggestions to be made by referring to the user's past coordination history. Coordination history is defined by criteria such as past coordination content, the date and time of coordination, and evaluation. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input the user's past coordination history into a generation AI and have the generation AI make optimal suggestions.

[0070] The tuning unit can enhance the versatility of the AI ​​by referencing coordination information from different industries during the tuning process. For example, it can collect coordination information from different industries and reflect it in the tuning process. It can analyze successful case studies from different industries and reflect them in the tuning process. It can collect trend information from different industries and reflect it in the tuning process. In this way, the versatility of the AI ​​can be enhanced by referencing coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-mentioned processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input coordination information from different industries into the generating AI and have the generating AI refer to it.

[0071] The reception desk can analyze the user's social media activity and suggest relevant search criteria upon receiving a request. For example, it can analyze the user's social media activity and suggest relevant search criteria. It can suggest search criteria based on the content the user has shown interest in on social media. It can customize search criteria based on the user's social media activity. This allows for the suggestion of relevant search criteria by analyzing the user's social media activity. Social media activity is defined by criteria such as post content, number of likes, and number of followers. 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 the user's social media activity into a generating AI and have the generating AI analyze it.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The learning unit learns about outfit coordination information. For example, it learns about outfit coordination information registered by actual popular staff members and uses AI to analyze diverse outfit coordination information in order to understand each staff member's sense of style. As a result, the learning unit can propose outfit coordination based on each staff member's sense of style. Step 2: The tuning unit periodically performs tuning based on the information learned by the learning unit. For example, the AI ​​tuning can be enhanced through A / B testing by staff, ensuring that suggestions always reflect the latest trends and sensibilities. Step 3: The reception desk accepts user searches. For example, it accepts information such as the user's desired size or style. Step 4: The selection department selects the most suitable staff based on the information received by the reception department. For example, they might use AI to select the most suitable staff based on the user's search information. Step 5: The dialogue department interacts with the user based on data from staff selected by the selection department. For example, the user and AI interact to finalize the details and generate a coordinated plan. Step 6: The generation unit generates and proposes a coordinate based on the information obtained by the dialogue unit. For example, it generates and proposes a coordinate that meets the user's requests.

[0074] (Example of form 2) The AI-powered styling agent "Sense Partner: Style Genius" according to an embodiment of the present invention is a system designed to solve the problem that customers may not always find staff who match their sense of style at the stores they visit. This system uses AI to learn styling information registered by actual popular staff members and periodically enhances the AI's tuning through A / B testing with staff members. Users search by size and desired atmosphere, the AI ​​selects the most suitable staff member, and based on that data, the user and AI engage in dialogue to refine the details and generate and propose a styling plan. This mechanism allows for accurate capture of customer needs and improved staff motivation in professions requiring aesthetic sense, such as interior design, fashion, and flower arranging. For example, the AI ​​learns styling information registered by actual popular staff members. In this process, the AI ​​analyzes diverse styling information to understand each staff member's sense of style. For example, in fashion, it learns about color combinations and how to choose items. This allows the AI ​​to propose styling plans based on each staff member's sense of style. Next, the AI's tuning is periodically enhanced through A / B testing with staff members. Staff members provide their own styling plans to the AI ​​and compare them with the suggestions generated by the AI ​​to improve the AI's accuracy. For example, in interior design, the AI ​​evaluates furniture placement and color balance to improve its suggestions. This allows the AI ​​to always provide suggestions that reflect the latest trends and sensibilities. Users search by size and desired atmosphere. For example, in fashion, a user might search for "casual style, size M outfit." Based on this information, the AI ​​selects the most suitable staff member, and using that data as a basis, the user and AI engage in dialogue to refine the details and generate a suggested outfit. For example, if a user requests "brighter colors," the AI ​​will suggest an outfit that meets that request. This allows customers to receive outfits that match their sense of style, and also improves staff motivation. For example, staff members can feel a sense of accomplishment when their own sense of style is reflected in the AI's suggestions.Furthermore, customers can easily request styling services from the comfort of their homes without having to visit a store. In this way, the AI ​​styling agent "Sense Partner: Style Genius" accurately grasps customer needs and improves staff motivation, thereby increasing customer satisfaction in professions that require aesthetic sense, such as interior design, fashion, and flower arranging.

[0075] The AI ​​coordination agent "Sense Partner: Style Genius" according to this embodiment comprises a learning unit, a tuning unit, a reception unit, a selection unit, a dialogue unit, and a generation unit. The learning unit learns coordination information. For example, the learning unit learns coordination information registered by actual popular staff members. The learning unit uses AI to analyze diverse coordination information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. As a result, the learning unit can propose coordinations based on the sense of each staff member. The tuning unit periodically tunes the AI ​​based on the information learned by the learning unit. For example, the tuning unit strengthens the tuning of the AI ​​through A / B testing with staff members. Staff members provide their own coordinations to the AI ​​and improve the accuracy of the AI ​​by comparing them with the suggestions generated by the AI. For example, in interior design, they evaluate the placement of furniture and the balance of colors to improve the AI's suggestions. As a result, the tuning unit can always make suggestions that reflect the latest trends and sense of style. The reception unit accepts user searches. The reception department receives information such as the user's search criteria, such as size and desired style. For example, in fashion, the user might search for "casual style, size M outfit." The selection department selects the most suitable staff based on the information received by the reception department. The selection department selects the most suitable staff based on the user's search information. The selection department uses AI to select the staff best suited to the user's needs. The dialogue department interacts with the user based on the data of the staff selected by the selection department. The dialogue department, for example, has the user and AI interact to refine the details and generate and propose outfits. For example, if the user requests "brighter colors," the dialogue department will propose outfits that meet that request. The generation department generates and proposes outfits based on the information obtained by the dialogue department. The generation department generates and proposes outfits that meet the user's requests.As a result, the AI-powered coordination agent "Sense Partner: Style Genius" according to this embodiment can accurately grasp customer needs and improve staff motivation.

[0076] The learning unit learns about outfit coordination information. For example, the learning unit learns about outfit coordination information registered by actual popular staff members. Specifically, the learning unit uses AI to analyze diverse outfit coordination information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. This allows the learning unit to propose outfit coordination based on each staff member's sense. The learning unit uses image recognition technology and natural language processing technology to analyze image and text data of outfit coordination. For example, it uses image recognition technology to extract features such as color, shape, and material from outfit images, and uses natural language processing technology to understand style and theme from text data related to outfit coordination. Furthermore, based on past outfit coordination data, the learning unit can grasp the changes in trends and seasonal trends, and make suggestions that reflect the latest fashion trends. This allows the learning unit to provide outfit coordination that meets the diverse needs of users and improve customer satisfaction.

[0077] The tuning unit periodically tunes the AI ​​based on the information learned by the learning unit. The tuning unit enhances the AI's tuning through methods such as A / B testing with staff. Specifically, staff provide the AI ​​with their own coordination ideas and compare them to the suggestions generated by the AI ​​to improve its accuracy. For example, in interior design, staff evaluate furniture placement and color balance to improve the AI's suggestions. The tuning unit adjusts the AI's learning algorithm and parameters to achieve more accurate coordination suggestions. For example, they optimize the number of layers and nodes in the AI's neural network and adjust the batch size and learning rate of the training data to improve the AI's performance. The tuning unit also collects user feedback and uses it as data to improve the AI's suggestions. This allows the tuning unit to always provide suggestions that reflect the latest trends and sensibilities, thereby increasing user satisfaction. Furthermore, the tuning unit regularly evaluates the AI's performance and maintains high accuracy by retraining or updating the model as needed.

[0078] The reception desk receives user searches. For example, it receives information such as the size and desired style of the user's search. Specifically, in the fashion category, a user might search for "casual style, size M outfit." The reception desk uses natural language processing technology to analyze the user's input information and provide appropriate search results. For example, it analyzes the text entered by the user and extracts keywords and intent. In addition, the reception desk can provide personalized suggestions to each user based on their past search and purchase history. This allows the reception desk to provide search results that meet the user's needs quickly and accurately, improving user convenience. Furthermore, the reception desk is designed to allow users to easily input search criteria through its user interface, enabling intuitive operation. This improves the user's search experience and makes the system more widely used by more users.

[0079] The selection department chooses the most suitable staff based on the information received by the reception department. For example, the selection department selects the most suitable staff based on the user's search information. Specifically, the selection department uses AI to select the staff best suited to the user's needs. The selection department considers the staff's past coordination experience, evaluations, and areas of expertise to select the staff best suited to the user's request. For example, it selects staff who excel in casual styles or staff who are knowledgeable about specific brands, etc., according to the user's needs. By using an AI recommendation system to match the user's search criteria with staff profiles, the selection department can quickly select the most suitable staff. This allows the selection department to provide users with high-quality coordination suggestions and improve user satisfaction. Furthermore, the selection department can enhance trust by ensuring transparency in the selection process and explaining the reasons for the selection to the user.

[0080] The dialogue unit interacts with users based on data from staff selected by the selection unit. For example, the dialogue unit interacts with the user and AI to refine the details and generate and propose coordinated outfits. Specifically, if a user requests "I want to use brighter colors," the dialogue unit will propose a coordinated outfit that meets that request. The dialogue unit uses natural language processing technology to understand user requests and generate appropriate responses. For example, it collects detailed requests such as the user's desired colors, style, and budget through dialogue and proposes the optimal coordinated outfit based on that. Through dialogue with users, the dialogue unit can deeply understand the user's preferences and needs and make more personalized suggestions. This allows the dialogue unit to facilitate communication with users and improve user satisfaction. Furthermore, the dialogue unit saves the dialogue history and uses it for future suggestions, enabling it to continuously make suggestions that reflect the user's preferences.

[0081] The generation unit generates and proposes outfits based on information obtained from the dialogue unit. For example, the generation unit generates and proposes outfits that meet the user's requests. Specifically, the generation unit uses AI to generate outfits that reflect the user's requests and the taste of selected staff. The generation unit utilizes image generation technology and style transfer technology to generate images of outfits that meet the user's requests. For example, it generates images of outfits that reflect the colors and styles desired by the user and proposes them to the user visually. Based on the generated outfit images, the generation unit can also provide a list of items that the user can actually purchase. This allows the generation unit to make concrete outfit suggestions to the user and increase the user's desire to purchase. Furthermore, the generation unit can improve the accuracy of its suggestions by collecting evaluations of the generated outfits and using them as training data for the AI. This allows the generation unit to always provide high-quality outfit suggestions that reflect the latest trends and user preferences.

[0082] The learning unit can learn from the outfit information registered by actual popular staff members. For example, the learning unit learns from the outfit information registered by actual popular staff members. The learning unit uses AI to analyze diverse outfit information in order to understand the sense and style of each staff member. For example, in fashion, it learns about color combinations and how to choose items. As a result, the learning unit can propose outfits based on the sense of each staff member. This allows it to propose outfits that reflect the sense of actual popular staff members. Popular staff members are defined by criteria such as customer ratings, sales performance, and number of followers. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input outfit information registered by actual popular staff members into a generating AI and have the generating AI learn from it.

[0083] The tuning department can periodically enhance the AI's tuning through A / B testing with staff. For example, the tuning department enhances the AI's tuning through A / B testing with staff. Staff provide their own coordinations to the AI ​​and compare them with the suggestions generated by the AI ​​to improve its accuracy. For example, in interior design, staff evaluate furniture placement and color balance to improve the AI's suggestions. This allows the tuning department to always provide suggestions that reflect the latest trends and sensibilities. This improves the AI's accuracy and allows it to provide suggestions that reflect the latest trends and sensibilities. A / B testing is conducted based on criteria such as test setup, evaluation criteria, and result analysis methods. Some or all of the above processes in the tuning department may be performed using AI or not. For example, the tuning department can input coordination information provided by staff into the generating AI and have the generating AI perform tuning.

[0084] The reception desk can receive information from users searching by size and desired style. For example, in fashion, a user might search for "casual style, size M outfit." This allows for searches tailored to the user's specific needs. Size is defined by size notation such as S, M, L, XL, etc. Style is defined by criteria such as casual, formal, elegant, etc. 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 the search information entered by the user into a generating AI, and have the generating AI generate search results.

[0085] The selection unit can select the most suitable staff based on the information received by the reception unit. For example, the selection unit can select the most suitable staff based on the user's search information. The selection unit can use AI to select the most suitable staff for the user's needs. This allows for the selection of staff best suited to the user's needs. The most suitable staff are selected based on criteria such as skill set, past performance, and customer ratings. Some or all of the above processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's search information into a generating AI and have the generating AI select the most suitable staff.

[0086] The dialogue unit can interact with users based on data of staff selected by the selection unit. For example, the dialogue unit can have a conversation with the user and an AI to refine the details and generate a coordinated outfit proposal. If, for example, the user requests "I want to use brighter colors," the dialogue unit will propose an outfit that meets that request. In this way, the user and the AI ​​can interact, refine the details, and generate a coordinated outfit proposal. The staff data consists of, for example, information such as career history, skills, and past achievements. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the data of staff selected by the selection unit into a generating AI and have the generating AI generate the dialogue content.

[0087] The generation unit can generate and propose outfits based on the information obtained by the dialogue unit. For example, the generation unit can generate and propose outfits that meet the user's requests. This allows the generation unit to generate and propose outfits that meet the user's requests. The outfits consist of, for example, clothing combinations, color balance, and accessory selection. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input the information obtained by the dialogue unit into a generation AI, causing the generation AI to generate outfits.

[0088] The learning unit can estimate the user's emotions and determine the priority of coordination information to learn based on the estimated user emotions. For example, if the user is relaxed, the learning unit will prioritize learning casual coordination information. For example, if the user is nervous, the learning unit will prioritize learning formal coordination information. For example, if the user is excited, the learning unit will prioritize learning trend-sensitive coordination information. This allows the learning unit to learn coordination information with priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 learning unit may be performed using AI or not. For example, the learning unit can input user emotion data into a generative AI and have the generative AI determine the priority of coordination information.

[0089] The learning unit can improve the accuracy of its learning by analyzing each staff member's past success and failure cases during the learning process. For example, the learning unit can analyze each staff member's success cases, extract common elements, and learn from them. For example, the learning unit can analyze each staff member's failure cases, identify areas for improvement, and learn from them. For example, the learning unit can compare success and failure cases, identify factors for success, and learn from them. In this way, the accuracy of learning can be improved by analyzing each staff member's past cases. Success and failure cases are defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input each staff member's past success and failure cases into a generating AI and have the generating AI analyze them.

[0090] The learning unit can dynamically update its learning content in response to changes in seasons and trends during the learning process. For example, the learning unit can collect seasonal trend information and reflect it in its learning content. For example, the learning unit can periodically update its learning content in response to changes in trends. For example, the learning unit can prioritize learning coordination information that is appropriate for the season and trends. This makes it possible to update the learning content in response to changes in seasons and trends. Seasons and trends are defined by criteria such as the four seasons (spring, summer, autumn, and winter) and fashion trends. Some or all of the above-described processes in the learning unit may be performed using AI or not. For example, the learning unit can input seasonal and trend information into a generating AI and have the generating AI dynamically update its learning content.

[0091] The learning unit can estimate the user's emotions and adjust the range of coordination information it learns based on the estimated user emotions. For example, if the user is relaxed, the learning unit will learn a wide range of casual coordination information. For example, if the user is nervous, the learning unit will learn a limited range of formal coordination information. For example, if the user is excited, the learning unit will learn a wide range of trend-sensitive coordination information. This allows the learning unit to learn coordination information within a range that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 learning unit may be performed using AI or not. For example, the learning unit can input user emotion data into a generative AI and cause the generative AI to adjust the range of coordination information.

[0092] The learning unit can incorporate coordination information from different cultural spheres and regions to add diversity to the learning process. For example, the learning unit can collect coordination information from different cultural spheres and reflect it in the learning content. For example, the learning unit can collect trend information from different regions and reflect it in the learning content. For example, the learning unit can analyze successful case studies from different cultural spheres and regions and reflect them in the learning content. This allows for diversity by incorporating coordination information from different cultural spheres and regions. Different cultural spheres and regions can be defined by criteria such as country, region, or cultural background. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input coordination information from different cultural spheres and regions into a generating AI and train the generating AI.

[0093] The learning unit can learn customized coordination information based on the user's lifestyle and occupation during the learning process. For example, the learning unit can collect coordination information according to the user's lifestyle and reflect it in the learning content. For example, the learning unit can collect coordination information according to the user's occupation and reflect it in the learning content. For example, the learning unit can analyze successful cases based on the user's lifestyle and occupation and reflect them in the learning content. This allows the learning unit to learn coordination information according to the user's lifestyle and occupation. Lifestyle and occupation are defined by criteria such as daily activities, work content, and hobbies. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input coordination information based on the user's lifestyle and occupation into a generating AI and have the generating AI learn from it.

[0094] The tuning unit can estimate the user's emotions and adjust the tuning frequency based on the estimated emotions. For example, if the user is relaxed, the tuning unit will set the tuning frequency low. For example, if the user is tense, the tuning unit will set the tuning frequency high. For example, if the user is excited, the tuning unit will set the tuning frequency to a medium level. This allows tuning to be performed at a frequency appropriate to the user's emotions. Emotion estimation 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, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the tuning unit may be performed using AI or not. For example, the tuning unit can input user emotion data into a generative AI and have the generative AI adjust the tuning frequency.

[0095] The tuning unit can reflect staff feedback in real time during tuning, instantly improving the accuracy of the AI. For example, the tuning unit can reflect feedback provided by staff in real time and improve the AI's suggestions. For example, the tuning unit can analyze staff feedback and instantly update the AI's learning content. For example, the tuning unit can adjust the AI's tuning parameters based on staff feedback. This allows for instant improvement of the AI's accuracy by reflecting staff feedback in real time. Real time is defined by criteria such as seconds, minutes, or instant reflection. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input staff feedback into the generating AI and reflect it in the generating AI in real time.

[0096] The tuning unit can compare the AI's suggestions with the actual results during tuning, analyze the differences, and identify areas for improvement. For example, the tuning unit can compare the AI's suggestions with the actual results, analyze the differences, and identify areas for improvement. For example, the tuning unit can identify the cause of the differences and update the AI's learning content. For example, the tuning unit can analyze the differences and adjust the AI's tuning parameters. This allows the AI ​​to analyze the differences and identify areas for improvement by comparing the AI's suggestions with the actual results. The differences are defined by criteria such as the difference between the suggested content and the actual results, and the method of identifying areas for improvement. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input the AI's suggestions and actual results into a generating AI and have the generating AI analyze the differences.

[0097] The tuning unit can estimate the user's emotions and adjust the tuning parameters based on the estimated emotions. For example, if the user is relaxed, the tuning unit will set the tuning parameters loosely. If the user is tense, the tuning unit will set the tuning parameters tightly. If the user is excited, the tuning unit will set the tuning parameters moderately. This allows tuning to be performed with parameters appropriate to the user's emotions. Emotion estimation 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, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the tuning unit may be performed using AI or not. For example, the tuning unit can input user emotion data into a generative AI and have the generative AI adjust the tuning parameters.

[0098] The tuning unit can enhance the versatility of the AI ​​by referencing coordination information from different industries during the tuning process. For example, the tuning unit can collect coordination information from different industries and reflect it in the tuning process. For example, the tuning unit can analyze successful case studies from different industries and reflect them in the tuning process. For example, the tuning unit can collect trend information from different industries and reflect it in the tuning process. This allows the versatility of the AI ​​to be enhanced by referencing coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-described processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input coordination information from different industries into the generating AI and have the generating AI refer to it.

[0099] The tuning unit can evaluate user satisfaction with AI suggestions during tuning and perform tuning based on that satisfaction level. For example, the tuning unit can evaluate user satisfaction and adjust the tuning based on that satisfaction level. For example, the tuning unit can collect user feedback and update the tuning based on that satisfaction level. For example, the tuning unit can analyze user satisfaction and adjust the tuning parameters. By tuning based on user satisfaction, the accuracy of AI suggestions can be improved. Satisfaction is defined by criteria such as surveys, feedback evaluations, and NPS scores. Some or all of the above processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input user satisfaction data into a generating AI and have the generating AI evaluate it.

[0100] The reception desk can estimate the user's emotions and adjust the reception interface based on the estimated emotions. For example, if the user is relaxed, the reception desk can provide a casual interface. If the user is nervous, the reception desk can provide a formal interface. If the user is excited, the reception desk can provide a trend-sensitive interface. This allows the reception desk to provide an interface that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 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 adjust the interface.

[0101] The reception desk can suggest optimal search conditions by referring to the user's past search history at the time of reception. For example, the reception desk can analyze the user's past search history and suggest optimal search conditions. For example, the reception desk can suggest optimal search conditions based on the conditions the user has searched for in the past. For example, the reception desk can customize search conditions by referring to the user's past search history. In this way, it is possible to suggest optimal search conditions by referring to the user's past search history. Search history is defined by criteria such as past search keywords, search date and time, and search results. 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 the user's past search history into a generating AI and have the generating AI suggest optimal search conditions.

[0102] The reception unit can analyze the user's input in real time and present appropriate search suggestions. For example, the reception unit can analyze the user's input in real time and present appropriate search suggestions. For example, the reception unit can present the optimal search suggestions based on the user's input. For example, the reception unit can analyze the user's input and customize the search suggestions. This allows the reception unit to present appropriate search suggestions by analyzing the user's input in real time. Search suggestions are defined by criteria such as related keywords, suggestion functions, and autocomplete. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's input into a generating AI and have the generating AI analyze it in real time.

[0103] The reception desk can estimate the user's emotions and adjust the guide message at the time of reception based on the estimated emotions. For example, if the user is relaxed, the reception desk will provide a casual guide message. For example, if the user is nervous, the reception desk will provide a formal guide message. For example, if the user is excited, the reception desk will provide a trend-sensitive guide message. This allows the reception desk to provide guide messages that are appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 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 adjust the guide message.

[0104] The reception unit can provide the optimal interface at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception unit will provide an interface optimized for smartphones. For example, if the user is using a tablet, the reception unit will provide an interface optimized for tablets. For example, if the user is using a desktop, the reception unit will provide an interface optimized for desktops. This allows the reception unit to provide an interface tailored to the user's device information. Device information is defined by criteria such as device type, OS, browser, and screen size. Some or all of the processing described above in the reception unit may be performed using AI or not. For example, the reception unit can input the user's device information into a generating AI and have the generating AI provide the optimal interface.

[0105] The reception desk can analyze the user's social media activity and suggest relevant search criteria upon receiving the request. For example, the reception desk can analyze the user's social media activity and suggest relevant search criteria. For example, the reception desk can suggest search criteria based on the content the user has shown interest in on social media. For example, the reception desk can customize search criteria based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to suggest relevant search criteria. Social media activity is defined by criteria such as post content, number of likes, and number of followers. 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 the user's social media activity into a generating AI and have the generating AI analyze it.

[0106] The selection unit can estimate the user's emotions and adjust the selection criteria based on the estimated emotions. For example, if the user is relaxed, the selection unit can apply casual selection criteria. For example, if the user is tense, the selection unit can apply formal selection criteria. For example, if the user is excited, the selection unit can apply trend-sensitive selection criteria. This allows the selection unit to apply selection criteria that are appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 selection unit may be performed using AI or not. For example, the selection unit can input user emotion data into a generative AI and have the generative AI adjust the selection criteria.

[0107] The selection unit can select the most suitable staff member by referring to their past performance data during the selection process. For example, the selection unit can analyze the staff member's past performance data to select the most suitable staff member. For example, the selection unit can select the most suitable staff member based on their success stories. For example, the selection unit can analyze their failure stories, identify areas for improvement, and select the most suitable staff member. In this way, the most suitable staff member can be selected by referring to their past performance data. Performance data is defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the staff member's past performance data into a generating AI and have the generating AI analyze it.

[0108] The selection unit can select the most suitable staff by comparing the user's current needs with their past preferences during the selection process. For example, the selection unit can analyze the user's current needs and select the most suitable staff by comparing them with their past preferences. For example, the selection unit can select staff that meet the user's current needs based on their past preferences. For example, the selection unit can make a comprehensive judgment on the user's current needs and past preferences to select the most suitable staff. In this way, the most suitable staff can be selected by comparing the user's current needs with their past preferences. Current needs and past preferences are defined by criteria such as current trends, past purchase history, and customer preferences. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's current needs and past preferences into a generating AI and have the generating AI compare them.

[0109] The selection unit can estimate the user's emotions and adjust the display method of the selection results based on the estimated user emotions. For example, if the user is relaxed, the selection unit provides a casual display method. For example, if the user is tense, the selection unit provides a formal display method. For example, if the user is excited, the selection unit provides a trend-sensitive display method. This allows for the provision of a display method that corresponds to the user's emotions. Emotion estimation 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, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input user emotion data into a generative AI and have the generative AI adjust the display method.

[0110] The selection unit can conduct a multifaceted selection process by referencing experts from different industries. For example, the selection unit can collect opinions from experts in different industries and reflect them in the selection process. For example, the selection unit can analyze success stories from different industries and reflect them in the selection process. For example, the selection unit can collect trend information from different industries and reflect it in the selection process. This allows for a multifaceted selection process by referencing experts from different industries. Experts from different industries are defined by criteria such as, for example, fashion designers, marketing experts, and technology consultants. Some or all of the processes described above in the selection unit may be performed using AI or not. For example, the selection unit can input opinions from experts in different industries into a generating AI and have the generating AI refer to them.

[0111] The selection unit can select the most suitable staff member by considering the user's geographical location information during the selection process. For example, the selection unit can select the most suitable staff member based on the user's geographical location information. For example, the selection unit can prioritize selecting nearby staff members by considering the user's geographical location information. For example, the selection unit can select staff members that reflect region-specific trends by referring to the user's geographical location information. In this way, the most suitable staff member can be selected by considering the user's geographical location information. Geographical location information is defined by criteria such as the user's address, current location, and regional characteristics. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input the user's geographical location information into a generating AI and have the generating AI consider it.

[0112] The dialogue unit can estimate the user's emotions and adjust the way the dialogue progresses based on the estimated emotions. For example, if the user is relaxed, the dialogue unit will provide a casual dialogue approach. For example, if the user is nervous, the dialogue unit will provide a formal dialogue approach. For example, if the user is excited, the dialogue unit will provide a trend-sensitive dialogue approach. This allows the dialogue to progress in a way that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 dialogue unit may be performed using AI or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the way the dialogue progresses.

[0113] The dialogue unit can provide optimal dialogue content by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can analyze the user's past dialogue history and provide optimal dialogue content. For example, the dialogue unit can provide optimal dialogue content based on the content of past conversations the user has had. For example, the dialogue unit can customize the dialogue content by referring to the user's past dialogue history. In this way, by referring to the user's past dialogue history, it is possible to provide optimal dialogue content. Dialogue history is defined by criteria such as past dialogue content, the date and time of the dialogue, and the result of the dialogue. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's past dialogue history into a generating AI and have the generating AI provide optimal dialogue content.

[0114] The dialogue unit can analyze the user's real-time responses during a conversation and dynamically change the content of the conversation. For example, the dialogue unit can analyze the user's real-time responses and dynamically change the content of the conversation. For example, the dialogue unit can customize the content of the conversation based on the user's responses. For example, the dialogue unit can adjust the content of the conversation based on the user's real-time responses. In this way, the content of the conversation can be dynamically changed by analyzing the user's real-time responses. Real-time responses are defined by criteria such as facial recognition, voice analysis, and behavioral analysis. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's real-time responses into a generating AI and have the generating AI analyze them.

[0115] The dialogue unit can estimate the user's emotions and adjust the tone of the dialogue based on the estimated emotions. For example, if the user is relaxed, the dialogue unit will use a casual tone. If the user is tense, the dialogue unit will use a formal tone. If the user is excited, the dialogue unit will use a trend-sensitive tone. This allows the dialogue unit to provide a tone of dialogue that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 dialogue unit may be performed using AI or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the tone of the dialogue.

[0116] The dialogue unit can provide dialogue content that corresponds to different languages ​​and cultures during a conversation. For example, the dialogue unit provides dialogue content based on the user's language settings. For example, the dialogue unit provides dialogue content that corresponds to different cultures. For example, the dialogue unit customizes the dialogue content according to the user's language and culture. This makes it possible to provide dialogue content that corresponds to different languages ​​and cultures. Different languages ​​and cultures are defined by criteria such as multilingual support, consideration of cultural background, and localization. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's language settings and cultural information into a generating AI and have the generating AI respond accordingly.

[0117] The dialogue unit can analyze the user's social media activity during a conversation and provide relevant dialogue content. For example, the dialogue unit can analyze the user's social media activity and provide relevant dialogue content. For example, the dialogue unit can provide dialogue content based on what the user has shown interest in on social media. For example, the dialogue unit can customize dialogue content based on the user's social media activity. In this way, by analyzing the user's social media activity, it can provide relevant dialogue content. Social media activity is defined by criteria such as post content, number of likes, and number of followers. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input the user's social media activity into a generating AI and have the generating AI analyze it.

[0118] The generation unit can estimate the user's emotions and adjust the style of the outfit it generates based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate a casual style outfit. For example, if the user is nervous, the generation unit will generate a formal style outfit. For example, if the user is excited, the generation unit will generate a trendy style outfit. This allows the generation of outfits to match the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the style of the outfit.

[0119] The generation unit can make optimal suggestions by referring to the user's past coordination history during generation. For example, the generation unit analyzes the user's past coordination history and makes optimal suggestions. For example, the generation unit makes optimal suggestions based on the coordinations the user has previously selected. For example, the generation unit customizes the suggested content by referring to the user's past coordination history. In this way, optimal suggestions can be made by referring to the user's past coordination history. Coordination history is defined by criteria such as the content of past coordinations, the date and time of coordination, and evaluation. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input the user's past coordination history into a generation AI and have the generation AI make optimal suggestions.

[0120] The generation unit can dynamically update the generated content in accordance with seasonal and trend changes during generation. For example, the generation unit collects seasonal trend information and reflects it in the generated content. For example, the generation unit periodically updates the generated content in accordance with trend changes. For example, the generation unit prioritizes generating coordination information according to the season and trend. This makes it possible to update the generated content in accordance with seasonal and trend changes. Seasons and trends are defined by criteria such as the four seasons (spring, summer, autumn, winter) and fashion trends. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input seasonal and trend information into a generation AI and cause the generation AI to dynamically update the generated content.

[0121] The generation unit can estimate the user's emotions and adjust the level of detail in the generated outfits based on the estimated emotions. For example, if the user is relaxed, the generation unit generates a detailed outfit. If the user is tense, the generation unit generates a concise outfit. If the user is excited, the generation unit generates a trend-sensitive, detailed outfit. This allows for the generation of outfits with a level of detail that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the level of detail in the outfits.

[0122] The generation unit can incorporate coordination information from different industries during the generation process to ensure diversity. For example, the generation unit can collect coordination information from different industries and reflect it in the generated content. For example, the generation unit can analyze successful case studies from different industries and reflect them in the generated content. For example, the generation unit can collect trend information from different industries and reflect it in the generated content. This allows for diversity by incorporating coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input coordination information from different industries into a generation AI and have the generation AI incorporate it.

[0123] The generation unit can generate customized outfits based on the user's lifestyle and occupation during the generation process. For example, the generation unit can generate outfits that match the user's lifestyle. For example, the generation unit can generate outfits that match the user's occupation. For example, the generation unit can analyze successful examples based on the user's lifestyle and occupation and reflect them in the generated content. This allows the generation unit to generate outfits that match the user's lifestyle and occupation. Lifestyle and occupation are defined by criteria such as daily activities, work content, and hobbies. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input outfit information based on the user's lifestyle and occupation into a generation AI and have the generation AI generate the outfits.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The selection unit can estimate the user's emotions and adjust the selection criteria based on the estimated emotions. For example, if the user is relaxed, casual selection criteria can be applied. If the user is tense, formal selection criteria can be applied. If the user is excited, trend-sensitive selection criteria can be applied. This allows for the application of selection criteria that are appropriate to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can input user emotion data into a generative AI and have the generative AI adjust the selection criteria.

[0126] The learning unit can improve the accuracy of its learning by analyzing each staff member's past success and failure cases during the learning process. For example, it can analyze each staff member's success cases, extract common elements, and learn from them. It can also analyze each staff member's failure cases, identify areas for improvement, and learn from them. By comparing success and failure cases, it can identify factors for success and learn from them. In this way, the accuracy of learning can be improved by analyzing each staff member's past cases. Success and failure cases are defined by criteria such as sales performance, customer satisfaction, and feedback. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input each staff member's past success and failure cases into a generating AI and have the generating AI analyze them.

[0127] The tuning unit can estimate the user's emotions and adjust the tuning frequency based on the estimated emotions. For example, if the user is relaxed, the tuning frequency can be set low. If the user is tense, the tuning frequency can be set high. If the user is excited, the tuning frequency can be set to a moderate level. This allows tuning to be performed at a frequency appropriate to the user's emotions. Emotion estimation is achieved using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above-described processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input user emotion data into a generative AI and have the generative AI adjust the tuning frequency.

[0128] The reception desk can suggest optimal search conditions by referring to the user's past search history at the time of reception. For example, it can analyze the user's past search history and suggest optimal search conditions. It can suggest optimal search conditions based on the conditions the user has searched for in the past. It can customize search conditions by referring to the user's past search history. In this way, it can suggest optimal search conditions by referring to the user's past search history. Search history is defined by criteria such as past search keywords, search date and time, and search results. 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 the user's past search history into a generating AI and have the generating AI suggest optimal search conditions.

[0129] The dialogue unit can estimate the user's emotions and adjust the dialogue flow based on the estimated emotions. For example, if the user is relaxed, a casual dialogue flow can be provided. If the user is tense, a formal dialogue flow can be provided. If the user is excited, a trend-sensitive dialogue flow can be provided. This allows for a dialogue flow that is tailored to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the dialogue flow.

[0130] The generation unit can make optimal suggestions by referring to the user's past coordination history during generation. For example, it can analyze the user's past coordination history and make optimal suggestions. It can make optimal suggestions based on the coordinations the user has selected in the past. It can customize the suggested content by referring to the user's past coordination history. This allows for optimal suggestions to be made by referring to the user's past coordination history. Coordination history is defined by criteria such as past coordination content, the date and time of coordination, and evaluation. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input the user's past coordination history into a generation AI and have the generation AI make optimal suggestions.

[0131] The learning unit can estimate the user's emotions and determine the priority of coordination information to learn based on the estimated user emotions. For example, if the user is relaxed, casual coordination information can be prioritized for learning. If the user is nervous, formal coordination information can be prioritized for learning. If the user is excited, trend-sensitive coordination information can be prioritized for learning. This allows coordination information to be learned with priorities that correspond to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user emotion data into a generative AI and have the generative AI determine the priority of coordination information.

[0132] The tuning unit can enhance the versatility of the AI ​​by referencing coordination information from different industries during the tuning process. For example, it can collect coordination information from different industries and reflect it in the tuning process. It can analyze successful case studies from different industries and reflect them in the tuning process. It can collect trend information from different industries and reflect it in the tuning process. In this way, the versatility of the AI ​​can be enhanced by referencing coordination information from different industries. Different industries are defined by criteria such as the fashion industry, the IT industry, and the medical industry. Some or all of the above-mentioned processes in the tuning unit may be performed using AI or not. For example, the tuning unit can input coordination information from different industries into the generating AI and have the generating AI refer to it.

[0133] The generation unit can estimate the user's emotions and adjust the style of the outfit it generates based on the estimated emotions. For example, if the user is relaxed, it can generate a casual style outfit. If the user is nervous, it can generate a formal style outfit. If the user is excited, it can generate a trendy style outfit. This allows for the generation of outfits that match the user's emotions. Emotion estimation is achieved using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into a generation AI and have the generation AI adjust the style of the outfit.

[0134] The reception desk can analyze the user's social media activity and suggest relevant search criteria upon receiving a request. For example, it can analyze the user's social media activity and suggest relevant search criteria. It can suggest search criteria based on the content the user has shown interest in on social media. It can customize search criteria based on the user's social media activity. This allows for the suggestion of relevant search criteria by analyzing the user's social media activity. Social media activity is defined by criteria such as post content, number of likes, and number of followers. 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 the user's social media activity into a generating AI and have the generating AI analyze it.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The learning unit learns about outfit coordination information. For example, it learns about outfit coordination information registered by actual popular staff members and uses AI to analyze diverse outfit coordination information in order to understand each staff member's sense of style. As a result, the learning unit can propose outfit coordination based on each staff member's sense of style. Step 2: The tuning unit periodically performs tuning based on the information learned by the learning unit. For example, the AI ​​tuning can be enhanced through A / B testing by staff, ensuring that suggestions always reflect the latest trends and sensibilities. Step 3: The reception desk accepts user searches. For example, it accepts information such as the user's desired size or style. Step 4: The selection department selects the most suitable staff based on the information received by the reception department. For example, they might use AI to select the most suitable staff based on the user's search information. Step 5: The dialogue department interacts with the user based on data from staff selected by the selection department. For example, the user and the AI ​​engage in a dialogue to finalize the details and generate a coordinated plan. Step 6: The generation unit generates and proposes a coordinate based on the information obtained by the dialogue unit. For example, it generates and proposes a coordinate that meets the user's requests.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the learning unit, tuning unit, reception unit, selection unit, dialogue unit, and generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and learns coordination information. The tuning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs periodic tuning based on the learned information. The reception unit is implemented by the control unit 46A of the smart device 14 and accepts user searches. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the optimal staff. The dialogue unit is implemented by the control unit 46A of the smart device 14 and interacts with the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates and proposes coordination. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the learning unit, tuning unit, reception unit, selection unit, dialogue unit, and generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and learns coordination information. The tuning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs periodic tuning based on the learned information. The reception unit is implemented by the control unit 46A of the smart glasses 214 and accepts user searches. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the optimal staff. The dialogue unit is implemented by the control unit 46A of the smart glasses 214 and interacts with the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates and proposes coordination. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] Each of the multiple elements described above, including the learning unit, tuning unit, reception unit, selection unit, dialogue unit, and generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and learns coordination information. The tuning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs periodic tuning based on the learned information. The reception unit is implemented by the control unit 46A of the headset terminal 314 and accepts user searches. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the optimal staff. The dialogue unit is implemented by the control unit 46A of the headset terminal 314 and interacts with the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates and proposes coordination. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] Each of the multiple elements described above, including the learning unit, tuning unit, reception unit, selection unit, dialogue unit, and generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and learns coordination information. The tuning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs periodic tuning based on the learned information. The reception unit is implemented by the control unit 46A of the robot 414 and accepts user searches. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the optimal staff. The dialogue unit is implemented by the control unit 46A of the robot 414 and interacts with the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates and proposes coordination. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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."

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] (Note 1) A learning section for learning coordination information, A tuning unit that periodically performs tuning based on the information learned by the learning unit, A reception desk that accepts user searches, A selection department selects the most suitable staff based on the information received by the aforementioned reception department, A dialogue unit that interacts with users based on data of staff selected by the aforementioned selection unit, The system includes a generation unit that generates and proposes a coordination based on the information obtained by the aforementioned dialogue unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Learn from the outfit information registered by actual popular staff members. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned tuning unit is We regularly refine the AI ​​tuning through A / B testing and other methods conducted by our staff. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reception unit is The system accepts information from users who search based on size and desired style. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned selection unit is Based on the information received by the aforementioned reception desk, the most suitable staff member will be selected. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned dialogue unit, The staff selected by the aforementioned selection department will interact with the user based on their data. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is Based on the information obtained through the aforementioned dialogue unit, a coordinate is generated and proposed. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, It estimates the user's emotions and determines the priority of learning coordination information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During the learning process, we analyze each staff member's past successes and failures to improve the accuracy of the learning. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, During learning, the learning content is dynamically updated in accordance with seasonal and trend changes. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, It estimates the user's emotions and adjusts the range of coordination information learned based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During learning, incorporate information on coordination from different cultural spheres and regions to create diversity. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, During learning, the system learns customized outfit information based on the user's lifestyle and occupation. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned tuning unit is It estimates the user's emotions and adjusts the tuning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned tuning unit is During tuning, staff feedback is incorporated in real time to instantly improve the accuracy of the AI. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned tuning unit is During tuning, the AI's suggestions are compared with the actual results, the differences are analyzed, and areas for improvement are identified. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned tuning unit is It estimates the user's emotions and adjusts the tuning parameters based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned tuning unit is During tuning, referencing coordination information from different industries enhances the versatility of the AI. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned tuning unit is During tuning, user satisfaction with the AI's suggestions is evaluated, and tuning is performed based on that satisfaction level. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reception unit is It estimates the user's emotions and adjusts the reception interface based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned reception unit is During registration, the system will refer to the user's past search history to suggest the most suitable search criteria. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reception unit is At the time of registration, the system analyzes the user's input in real time and presents appropriate search suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reception unit is The system estimates the user's emotions and adjusts the guide message at the time of check-in based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reception unit is At the time of registration, the system provides the optimal interface considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reception unit is During registration, the system analyzes the user's social media activity and suggests relevant search criteria. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned selection unit is It estimates user sentiment and adjusts selection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned selection unit is During the selection process, the most suitable staff members are chosen by referring to their past performance data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned selection unit is During the selection process, the most suitable staff members are chosen by comparing the user's current needs with their past preferences. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned selection unit is The system estimates the user's emotions and adjusts how the selection results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned selection unit is During the selection process, we will conduct a multifaceted selection by consulting with experts from different industries. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned selection unit is During the selection process, the most suitable staff members will be chosen, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the conversation progresses based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned dialogue unit, During conversations, the system provides optimal dialogue content by referring to the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned dialogue unit, During the interaction, the system analyzes the user's real-time responses and dynamically changes the content of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the tone of the conversation based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned dialogue unit, During conversations, provide dialogue content that is compatible with different languages ​​and cultures. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned dialogue unit, During conversations, the system analyzes the user's social media activity and provides relevant conversation content. The system described in Appendix 1, characterized by the features described herein. (Note 38) The generating unit is It estimates the user's emotions and adjusts the style of the generated outfits based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The generating unit is During generation, the system references the user's past styling history to provide optimal suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The generating unit is During generation, the generated content is dynamically updated according to seasonal and trend changes. The system described in Appendix 1, characterized by the features described herein. (Note 41) The generating unit is It estimates the user's emotions and adjusts the level of detail in the generated outfits based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The generating unit is During generation, incorporate coordination information from different industries to create diversity. The system described in Appendix 1, characterized by the features described herein. (Note 43) The generating unit is During the generation process, a customized outfit is created based on the user's lifestyle and occupation. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning section for learning coordination information, A tuning unit that periodically performs tuning based on the information learned by the learning unit, A reception desk that accepts user searches, A selection department selects the most suitable staff based on the information received by the aforementioned reception department, A dialogue unit that interacts with users based on data of staff selected by the aforementioned selection unit, The system includes a generation unit that generates and proposes a coordination based on the information obtained by the aforementioned dialogue unit. A system characterized by the following features.

2. The aforementioned learning unit, Learn from the outfit information registered by actual popular staff members. The system according to feature 1.

3. The aforementioned tuning unit is We regularly enhance the AI's tuning through A / B testing and other methods conducted by our staff. The system according to feature 1.

4. The aforementioned reception unit is The system accepts information from users who search based on size and desired style. The system according to feature 1.

5. The aforementioned selection unit is Based on the information received by the aforementioned reception desk, the most suitable staff member will be selected. The system according to feature 1.

6. The aforementioned dialogue unit, The staff selected by the aforementioned selection department will interact with the user based on their data. The system according to feature 1.

7. The generating unit is Based on the information obtained through the aforementioned dialogue unit, a coordinate is generated and proposed. The system according to feature 1.

8. The aforementioned learning unit, It estimates the user's emotions and determines the priority of learning coordination information based on the estimated user emotions. The system according to feature 1.

Images